Search

The increased application of Information and Communications Technology in automation and digitization is the driving concept towards the actualization of the Industrial Revolution 4.0. Many aspects of industrial design and operations including offshore engineering have been automated. However, the selection procedure of mooring design parameters including azimuth angle, pretension, diameter, fairlead slope, and mooring radius, which is a critical aspect of mooring system design has remained heavily based on a manual approach despite the availability of sophisticated hydrodynamic analysis software. Up to date, there is no proper review on optimisation techniques that have the potential of automating these procedures. In the past, some of the few available mooring optimisation procedures consider only the mooring lines for the prediction of optimal platform offset without due consideration to the integrity of the risers. Thus, the significance of adopting an integrated riser-mooring design methodology in the optimisation of mooring design variables is discussed in this paper where the integrity of the riser is adequately represented using a Safe Operation (SAFOP) zone polar diagram. We also review the developmental transition from the use of classical to Evolutionary Algorithms (EA) in the optimisation procedure. EA has been acknowledged as a practical alternative for solving mooring optimisation problems. Hence, some of the EA techniques are presented and their computational capabilities explored. In the last part, a concise review of the application of optimisation techniques for mooring optimisation of the different offshore floating platforms is presented based on their capabilities in minimizing platform offset and efficiency in terms of simulation time. So far, EA techniques like the Differential Evolution (DE), variants of Genetic Algorithms (GA) and Particle Swarm Optimisation (PSO) have been used to optimize mooring line design variables. Based on the discussions, the potentials of DE, RegPSO and other variants of PSO can be further explored for better efficiency. • Previous studies addressing differential evolution (DE), genetic algorithm (GE) and particle swarm optimisation (PSO) techniques used for optimisation of mooring parameters have been critically reviewed. • The integrated riser -mooring design methodology is effective in accounting for integrity of riser and mooring systems. • The application of evolutionary algorithms, particularly the variants and hybrids of DE ,PSO and GA, have proven to be efficient optimisation of mooring systems. • Some variants of PSO like the RegPSO have demonstrated improved capability in terms of escaping premature convergence , thereby resulting in better computational efficiency. [ABSTRACT FROM AUTHOR]

The method used and results found by the team "ASTL-NUAA" from NUAA for the problem of GTOC 11 are presented in the paper. The problem is mainly decomposed into three parts: multiple targets flyby sequence optimization for the Mother Ships, station-building database construction problem of asteroid transfer arcs, and station-building mission planning. Therefore, a three-step optimization framework is proposed to solve the problem. After analyzing the data of all the asteroids and selecting according to the orbital elements and mass of the asteroids, an asteroid candidate set RS1 is chosen as candidate targets for the Mother Ships. A two-level optimization algorithm based on a genetic principle is applied to solve the two-impulse asteroid flyby problem and rapidly determine the asteroid sequence of each Mother Ship. Subsequently, a method of filtering input data for the time-optimal rendezvous problem by the optimal flight time and the corresponding optimal relative phase is proposed to construct a station-building database with less computation burden. The optimal relative phase is obtained by solving free final-phase continuous low-thrust time-optimal problem. The station-building database is composed of the results of continuous low-thrust time-optimal rendezvous problems. At last, a branch-and-bound algorithm based on the greedy strategy is adopted to rapidly get the result by maximizing the minimal mass among the stations. The final score of our solution is 4315.6663, which is obtained after the competition. • The method used and results found by NUAA for the GTOC 11 is presented. • The flyby sequence of asteroids is obtained by the two-level optimization algorithm. • For less computation burden, a filter strategy is proposed to filter the input of time-optimal problem. • To assign asteroids, the branch-and-bound algorithm is applied. [ABSTRACT FROM AUTHOR]

Nonuniform irradiance on the Photovoltaic (PV) array would cause mismatch problem and decrease the generated power. To relieve the negative effects of partial shading, reconfiguring the interconnection of the PV array is a favorable solution. However, the current reconfiguration techniques are usually limited by different corresponding factors, e.g., not suit for various instantaneous shade cases, the shortage of experts' knowledge or large amounts of data, easy coverage to local optima, and the strict assumptions for application. Therefore, in this paper a unsupervised adaptive PV array reconfiguration technique is proposed with a Divide and Conquer Q-Learning (DCQL) based array reconfiguration scheme designed to decrease the influence of partial shades. To testify the performance of the proposed PV array reconfiguration scheme, mathematic theoretical evaluation and electric characteristic analyses are made and compared with those obtained by the conventional Total-Cross-Tied (TCT) arrangement, SuDoKu connection, Genetic Algorithm (GA) based scheme, as well as some lately proposed Grasshopper Optimization Algorithm (GOA), Harris Hawks Optimizer (HHO), and Lo Shu (LS) technique based reconfiguration methods. Besides, additional estimation indices, including mismatch loss, fill factor, percentage power loss and percentage power enhancement are calculated with substantial analyses and comparisons. Subsequently, the application of the proposed scheme in real-time conditions is evaluated, with energy saving and income analysis estimated in comparison with other eminent challenger reconfiguration schemes. At last, a comprehensive qualitative comparison assessment, with respect to dispersion ability under partial shading conditions (PSC), sensor requirement, wiring complexity and capital investment is carried out and proves the versatility of proposed methodology. • States, actions and rewards are designed in the Q-Learning based reconfiguration. • The combination of divide and conquer principle fastens the decision making process. • The proposed reconfiguration is estimated better performance through variety contrasts. [ABSTRACT FROM AUTHOR]

A periodic close encounter orbit is an orbit that periodically surveys a target spacecraft. The design of such orbits is important for both military and civil missions. As an example, it can be used for a preliminary mission design to better plan the repair of damaged, expensive, strategic, or extremely critical space assets. Indeed, this paper proposes an optimization approach and algorithm to reach periodic close encounter orbits through n -impulse maneuvers within the framework of Keplerian motion. The optimization is constrained to several bound requirements, such as a) distance bounds at encounter, b) total Δ v tot cost, c) single impulse cost Δ v k , d) encounter illumination angle, e) daily observation time, f) minimum perigee radius, g) maximum repetition time, h) maximum eccentricity, and i) maximum encounter time. The optimization, performed using Genetic Algorithm, has been validated by several numerical examples using the TLEs of existing satellites. The simulations showed good results and the reliability of the proposed approach via the Genetic Algorithm has been validated by a comparison with the Particle Swarm Optimization algorithm. [ABSTRACT FROM AUTHOR]

The traditional circulating cooling water system regulates the flow rate through parallel pumps and valves. Due to fluctuations in operation, there will be lots of energy waste, resulting in inefficient operation of the circulating cooling water system. This research proposed a mixed-integer nonlinear programming (MINLP) method. By installing variable frequency drives (VFDs) on the pumps, changing constant-speed pumps (CSPs) into variable speed pumps (VSPs), we can regulate flow rate with valves and VSPs simultaneously. Optimizing the system using Genetical algorithm (GA) to obtain precise operating parameters, including the configuration of VFDs, the number of CSPs and VSPs and the resistance coefficients of valve in the branch and main pipe. Sensitivity analysis of the model is carried out, and the energy-saving effect of VFD under different temperature differences, pump types and electricity prices, the operating status of the pump and the status of the pipeline are compared. The results indicate that the MINLP genetic algorithm optimization model for industrial circulating water considering variable frequency drive proposed in this paper has a wide range of applicability. It can save an average of 23 % of the total cost under different conditions, and has a promising energy saving effect. • The synergy between pump system and pipeline system are considered. • The precise operation can be obtained in different outer conditions. • The MINLP model can optimize the operation of the existing circulating water system with VSPs. [ABSTRACT FROM AUTHOR]

Based on the yield mechanism control principle of "strong columns and weak beams, strong joints and weak components" in steel frames connected by top-and-seat steel angles, this paper proposes a method to define the relationship between the bending capacity of various components through inequality iteration and deduction. A number of component parameters has been identified that enables control of the yielding sequence in structural components. The study also developed an objective function and used genetic algorithms to create a multi-objective optimization technique for semi-rigid steel frame structures. The method considers the non-dominated cost interval, resulting in a more comprehensive approach. From the optimization case studies against the published experimental results and finite element simulations, it demonstrates that the proposed approach efficiently manages the yielding sequence and minimizes the decision space. The optimization model provides the coordination optimization between structural cost and lateral base shear capacity. • A new method to calculate relationship between semi-rigid joint parameters and structural components' yield sequences. • A new multi-objective optimization method for steel frame structure. • A new method to improve the optimization efficiency [ABSTRACT FROM AUTHOR]

Minimising energy consumption in today's industrial sector is a crucial objective for achieving established climate goals. One effective strategy to enhance efficiency is optimising energy system operations within industries. The initial step in establishing operational optimisation involves developing a comprehensive model of the energy system. This model necessitates a specific structure to meet optimisation requirements. However, creating a model from scratch incurs substantial effort. While numerous companies possess energy models, they often lack the requisite structure for optimisation. Consequently, simplifying existing models can significantly reduce the effort needed to implement operational optimisation. This paper investigates the simplification of intricate industrial energy system models for optimisation purposes. The subsequent sections analyse two distinct approaches. One approach involves linearisation, while the other utilises neural networks. To facilitate a comparative analysis of these approaches, a reference model is developed. The assessment of these methodologies includes an investigation into optimisation robustness, computation time, accuracy concerning the reference model, and the effort required for developing and maintaining the simplified models. It proved that both approaches are suitable for operational optimisation. Linearisation exhibits superior computational efficiency compared to the neural network approach. The linearisation modelling approach together with the optimisation only required a few milliseconds for the calculation. The neural network approach needed 3 h for the calculation of the optimum with the genetic algorithm. The simulation of the neural network itself only required a few milliseconds. Hence, an improvement of the genetic algorithm is needed. However, the accuracy of linearisation falls short of that achieved by neural networks. The linearisation achieves a mean average percentage error from only 13%. In comparison the neural network's mean average error is 2.3%. Therefore, the linearisation must be improved. The impact using a piecewise linearisation on the results will be analysed in further research. [ABSTRACT FROM AUTHOR]

More accurate multivariate load forecasting is conducive to integrated energy system planning optimization and economic operation. In this paper, based on the consideration of exogenous factors such as weather, endogenous factors are added into the prediction, and a short-term prediction model for integrated energy multivariate load based on endo-exogenous uncertainty is established using fine-tuned transfer learning. The LSTM pre-training model is first initially established using genetic algorithm and exogenous factors such as weather. Then the exogenous uncertainty of the pre-training model and the knowledge of endogenous uncertainty in the target model are combined using fine-tuned transfer learning to continuously optimize the basic parameters of the prediction model to obtain the final multivariate load prediction model. The performance of the four models is comprehensively evaluated after the historical load validation of the integrated energy system in Beijing, China. Compared with the traditional LSTM multivariate load forecasting model, the MAPE of the proposed model in this paper is reduced by 21.03 %, 13.00 %, and 24.39 % for electricity, heat, and cooling load forecasting, respectively. • The coupling mechanism between multiple energy sources of the integrated energy system is analyzed. • An endogenous-exogenous uncertainty method is proposed to extract the dynamic coupling relationship between multiple loads. • An endogenous-exogenous uncertainty-based GA-LSTM multivariate load prediction model is developed. • Optimizing model parameters using fine-tuned migration learning to deepen the impact of endo-exogenous uncertainty. [ABSTRACT FROM AUTHOR]

• An optimization approach was provided to construct efficient evacuation network. • The study on using LOS concept in evacuation planning was extended. • The approach was validated by computational experiments on a hypothetical three-story building and a twelve-deck cruise ship. • Sensitivity analysis of the optimized LOS design was concluded. This paper introduces a novel technique to design the level of service (LOS) for facilities or sub spaces of buildings for the purpose of evacuation planning. LOS is a standard qualitative indicator used to describe flow characteristics in a pedestrian environment. Some evacuation planners use LOS to help determine the network parameters when solving evacuation planning problems by the network flow approach. However, there is currently limited research into the optimization of the LOS parameters themselves to construct more efficient evacuation networks. In this paper the authors used a genetic algorithm optimization approach to determine LOS for facilities to improve the evacuation performance of building networks. Each individual chromosome containing a LOS design represents a fully defined evacuation network that can be solved. The fitness of each network is measured by minimum clearance time, which is calculated by the Capacity Constrained Route Planner (CCRP) approach. A comparative computational test in a hypothetical three-story building shows that the evacuation network under the optimized LOS design has a roughly 11% less minimum clearance time compared to the network under the original LOS design. Sensitivity analysis is also included, focusing on how the population size and the building layout influence the LOS design. In addition, an additional computational test for a twelve-deck cruise ship shows that the approach is scalable to solve more complex evacuation networks. The proposed approach has the potential to provide better LOS assignments for facilities for the government officials to develop effective emergency management strategies. [ABSTRACT FROM AUTHOR]

Fuel cell distributed drive electric tractors (FCDET) are one of the necessary means to achieve truly green agriculture. However, low traction efficiency, poor control coordination, and excessive energy consumption are the main reasons hindering the industrialization of FCDET. This paper proposed a parametric collaborative optimization design method and innovative verification system that considers the drive system and energy system. Based on the tractor plowing operating conditions, a 7-DOF coupled dynamics model of the distributed drive system and a tire-soil interaction model were established, and the key component selection and parameter matching were completed. On the drive system optimization level, the front and rear wheelside transmission ratios are optimized based on a multi-island genetic algorithm (MIGA). On the energy system optimization level, the globally optimal power distribution ratio is found based on the dynamic programming algorithm (DP). A complete experimental prototype verification system is constructed based on the MATLAB/Simulink-NI PXI joint simulation platform, physical prototype test bench, and real vehicle multi-index test platform. The results show that the average efficiencies of the optimized drive and energy system are increased by 0.38 % and 3.82 %, the total energy consumption (total hydrogen consumption) is reduced by 25.40 % and 15.39 %, respectively. The maximum fault-free operating time is 5.5h, the average traction power is 21.07 kW, and the average traction force is 10610 N in the all-wheel drive mode. The experimental results fully demonstrate that the electric tractor with the fuel cell distributed drive system as the core can meet the verification of multiple indicators. This study can provide a new theoretical basis and technical verification method for the optimal design and system control of fuel cell distributed drive electric tractors. • Parameter collaborative optimization of drive system and energy system. • Tractor multi-body dynamics model and tire-soil interaction model. • Multi-island genetic algorithm and dynamic programming algorithm. • MATLAB/Simulink-NI PXI joint simulation test, physical prototype test and real vehicle multi-indicator test. • Innovative verification method combining theoretical and experimental. [ABSTRACT FROM AUTHOR]

The gradual transition of wind power from onshore to deep sea poses an urgent challenge in optimizing cost-efficiency while ensuring the safety of floating wind turbines. This paper presents a new approach for parametrically optimizing the mooring system for offshore floating wind turbines. A semi-submersible wind turbine platform was selected as the reference structure, with a calculated water depth of 130 m that meets the requirements of the application of the wind turbine platform. A sample library of mooring system parameters was established and the wind-wave coupling simulations were carried out using OpenFAST. Considering platform safety as a priority, a combination of BP neural network and genetic algorithm was employed to optimize mooring system parameters to minimize the costs. This approach provides an important foundation for future research on the parameter optimization of mooring systems for floating wind turbines. • A novel methodology to optimize the mooring system for a semi-submersible floating wind turbine is presented. • The relationship between the mooring parameters and the floating wind turbine performance is established using neural network techniques. • The mooring system parameters are optimized using genetic algorithms to minimize costs. [ABSTRACT FROM AUTHOR]

Abstract Many decisions in operations management (OM) belong to the class of Non-deterministic Polynomial hard problems and thus heuristic search methods have been applied to improve OM decisions. While genetic algorithms (GAs) are promising tools for searching fast and good solutions in diverse OM areas, future research will benefit from a review of the OM problems solved by GAs. The purpose of this paper is to review the literature on OM with GA-based solutions and to suggest possible gaps from the point of view of researchers and practitioners. A total of 119 peer reviewed journal papers published from 2007 to 2017 are reviewed and analysed methodologically. The applications of GAs in OM are categorized into process and product design, operations planning and control, and operations improvement. Observations from the existing literature are presented and future research directions are suggested. Although GAs have been one of the most popular heuristic approaches for optimization, there are OM problems that are yet to be investigated. The findings of this review pave the path for future research to apply GAs to solve OM problems. Highlights • Review literature on applications of genetic algorithms in operations management. • Categorize applications in operations management into 3 themes and 9 decision areas. • Provide research and application agenda for further work. [ABSTRACT FROM AUTHOR]

Although the advancements in automotive diesel engines in the last two decades have resulted in the possibility of achieving better performance with lower pollutant emissions and fuel consumption, the increased complexity of the system and the high number of control parameters require the solution of optimization problems of high dimensionality. It is of crucial importance to identify suitable methodologies, which allow achieving the full exploitation of the potential of these powertrains. In this paper, an original methodology for optimizing the latest generation of common rail automotive diesel engines has been presented. Random optimization methods along with surrogate models were firstly used to generate a population of engine calibrations, which then served as an initial population to a specifically conceived Genetic Algorithm (GA) based optimizer, which was finally applied on a real data set for a particular engine operating point. The results were compared with a calibration optimized using a traditional local approach method. A simultaneous reduction of about 20% in NO X and 1% in Brake Specific Fuel Consumption was achieved, with no significant increase in other emissions. The methodology described in the paper has the potential to reduce the calibration time and effort by half, while obtaining better calibrations. [ABSTRACT FROM AUTHOR]

• To propose sooty-tern optimization (STO) for designing PSS parameters of multi-machine power system. • The performance of STO is evaluated using eigenvalue analysis, simulation results and performance indices. • The results are matched with other powerful optimization techniques. • Robustness is verified on hidden operating cases also under critical disturbances. This paper reports a comparative study among four bio-inspired meta-heuristic techniques i.e. Sooty-Tern Optimization (STO), Grey Wolf Optimization (GWO), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) to tune the robust Power System Stabilizer (PSS) parameters of the multi-machine power system. These approaches are successfully tested on two bench-mark systems: sixteen-machine, sixty-eight-bus New England Extended Power Grid (NEEPG) and three-machine, nine-bus Western System Coordinating Council (WSCC). The efficacy of planned PSS via STO and GWO is validated by extensive non-linear simulations, eigenvalue analysis, and performance indices for numerous operating conditions under decisive perturbations, and outcomes are matched with those of GA and PSO techniques. In addition, the robustness is also tested for these algorithms. The results indicate that the PSS design using STO and GWO improves the small-signal stability and damping performance for mitigating inter-area and local area modes of low-frequency oscillations compared to GA and PSO. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to optimize selective wireless power transmission to multiple receivers utilizing a single transmitter. The primary focus is on achieving target power levels at specific resonant frequencies on each receiver while ensuring maximum transmission efficiency. To address this, an analytical model based on magnetic coupling between coils is employed to explore different solutions, and a Genetic Algorithm (GA) is applied to identify the optimal configuration. The application of a GA for system design optimization is introduced, which proves highly effective, especially when dealing with multiple receivers where analytical models become difficult to manage. The GA-based approach facilitates the discovery of numerical solutions that might be challenging to deduce analytically. The validity of the proposed approach is confirmed through simulation and experimental measurements. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for characterizing electrochemical parameters in non-isothermal three-dimensional (3 D) simulation models of fuel cell stacks. The proposed methodology involves utilizing only easily measurable construction and non-invasive operational data. In order to achieve a reasonable computational cost, an iterative method developed on various 3 D computational domains is combined with a genetic algorithm optimization technique. The effectiveness of the methodology is demonstrated through its application on a real scale 40-cell high temperature PEM fuel cell (HTPEMFC) stack, with the results indicating good agreement between the model and experimental data. This approach has the potential to significantly reduce the computational cost of optimizing fuel cell designs while still maintaining accuracy. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper introduces application of genetic algorithm (GA) in designing air-termination system of the high-voltage (HV) open-air substation external lightning protection system (LPS). As far as the authors are informed, this is the first proposal for using GA in designing LPS of substations. The complex air-termination system, as a part of the external LPS of HV substation, is known to be cumbersome to design using traditional techniques, where optimisation is often relegated to the trial-and-error approach. In addition, traditional methods are often associated with geometric constraints and implementation difficulties. This paper proposes a novel approach which utilizes a combination of statistical LPS efficiency and GA in designing techno–economically optimal external LPS of open-air substations. The LPS optimisation problem is particularly well suited to the GA solution approach, due to the stochastic nature of lightning, expert knowledge involved in constructing the fitness function, and the fact that the optimal solution is not, strictly speaking, a unique value (it can be obtained using different combinations of the air-termination system elements). Proposed approach offers a LPS designer unique and valuable assistance in optimally arranging elements of air-termination system for obtaining maximum lightning shielding effects with minimum total investments. [ABSTRACT FROM AUTHOR]

With the penetration of Internet of things in manufacturing industry, it is an unavoidable issue to maintain robust wireless connections among machines and human workers in harsh industrial environments. However, the existing wireless planning tools focus on office environments, which are less harsh than industrial environments regarding shadowing effects of diverse obstacles. To fill this gap, this paper proposes an over-dimensioning (OD) model, which automates the decision making on deploying a robust industrial wireless local area network (IWLAN). This model creates two full coverage layers while minimizing the deployment cost, and guaranteeing a minimal separation distance between two access points (APs) to prevent APs that cover the same region from being simultaneously shadowed by an obstacle. Moreover, an empirical one-slope path loss model, which considers three-dimensional obstacle shadowing effects, is proposed for simple yet precise coverage calculation. To solve this OD model even at a large size, an efficient genetic algorithm based over-dimensioning (GAOD) algorithm is designed. Genetic operators, parallelism, and speedup measures are tailored to enable large-scale optimization. A greedy heuristic based over-dimensioning (GHOD) algorithm is further proposed, as a state-of-the-art heuristic benchmark algorithm. In small- and large-size OD problems based on industrial data, the GAOD was demonstrated to be 20%–25% more economical than benchmark algorithms for OD in the same environment. The effectiveness of GAOD was further experimentally validated with a real deployment system. Though this paper focuses on an IWLAN, the proposed GAOD can serve as a decision making tool for deploying other types of robust industrial wireless networks in terms of coverage, such as wireless sensor networks and radio-frequency identification (RFID) networks. [ABSTRACT FROM AUTHOR]

Whether or not alternative fuel vehicles (AFVs) will finally find a place in the global mass-market or even will dominate the vehicle segment will depend on several success factors: reduction of customer anxiety, fast recharging, better charging infrastructure, environmental justice policies and some others. Current technological advances in battery electric vehicles and hydrogen fuelled electric vehicles could represent a hopefully option in the near future. Nevertheless, and until electric/hydrogen technological barriers are not torn down, both power architecture do not have an opportunity to be fully introduced in the vehicle market. In this paper, the authors present a powertrain architecture concept based in current fossil fuel extender range, but changing it to a hydrogen fuel cell stack system that works as range extender. The objective is to probe how optimization techniques, by the inclusion of genetic algorithms, could be a crucial help when planning the fuel consumption/selection. The paper ambition is to highlight the possibilities of this powertrain and its appropriated management to allow hydrogen become an energy carrier feasible today in the automotive world. [ABSTRACT FROM AUTHOR]

This paper presents a practical genetic algorithm (GA)-based solution for solving the economic load dispatch problem (ELDP) and further compares the performance of the improved GA (IGA) with that of dynamic programming (DP). Specifically, their performance is comprehensively evaluated in terms of addressing the ELDP through a case study of 26 turbines in the Three Gorges Hydropower Plant with a focus on calculation accuracy, calculation time, and algorithm stability. Evaluation results show that the improved GA method can significantly reduce the ineffectiveness of the GA in current use and could avoid the running of the turbines in the cavitation/vibration zone, thereby ensuring the safety of the turbines during generating operations. Further, the analysis comparing the performance of the IGA and DP show that the IGA is superior to DP when a small number of turbines are involved. However, as the number of turbines increases, the IGA requires more calculation time than DP; moreover, its calculation accuracy and convergence rate are significantly reduced. It is difficult to guarantee the stability of IGA in high-dimension space even though the population grows, on account of the exponential expansion of the calculation dimension, the algorithm’s premature convergence, and the lack of a local search capability. The improvement of the GA as well as the evaluation method proposed in this paper provide a new approach for choosing and improving optimization algorithms to solve the ELDP of large-scale hydropower plants. [ABSTRACT FROM AUTHOR]

The present paper proposes application of the genetic algorithm (GA) and the innovative weighting factor method to optimize the reloading pattern of Bushehr VVER-1000 reactor in the second cycle. To estimate the composition of fuel assemblies remaining from the first cycle and precisely calculate the objective parameters of each reloading pattern in the second cycle, coupling of WIMSD5-B and CITATION-LDI2 codes in the neutronic section and the WERL code in the thermo-hydraulic section was employed. Optimization of the reloading patterns was carried out in two states. To meet the mentioned objective, with application of the weighting factor method in the first state, the type and quantity of the loadable fresh assemblies were determined to enable the reactor core to maintain the core criticality over the entire cycle length. Afterwards, the genetic algorithm was used to optimize the reloading pattern of the reactor to obtain an arrangement with flat radial power distribution. In the second state, the optimization algorithm was free to select the type and number of fresh fuel assemblies to be able to search for an arrangement with the maximum effective multiplication factor and the safe power peaking factor. In addition, in order to ensure the safety and desirability of the proposed patterns in both states, a time-dependent examination of the thermo-neutronic behavior of the reactor core was carried out during the second cycle. With consideration of the new solutions proposed in this research to increase the precision, speed, and scope of the searches and the structural constraints on reloading pattern optimization calculations, it seems that the present paper is a novel step toward the optimization of the reloading patterns of nuclear reactors. [ABSTRACT FROM AUTHOR]

This paper develops a new model for redundancy allocation problem. In this paper, like many recent papers, the choice of the redundancy strategy is considered as a decision variable. But, in our model each subsystem can exploit both active and cold-standby strategies simultaneously. Moreover, the model allows for component mixing such that components of different types may be used in each subsystem. The problem, therefore, boils down to determining the types of components, redundancy levels, and number of active and cold-standby units of each type for each subsystem to maximize system reliability by considering such constraints as available budget, weight, and space. Since RAP belongs to the NP-hard class of optimization problems, a genetic algorithm (GA) is developed for solving the problem. Finally, the performance of the proposed algorithm is evaluated by applying it to a well-known test problem from the literature with relatively satisfactory results. [ABSTRACT FROM AUTHOR]

• The proposed framework can effectively enhance the surrogate model accuracy. • The proposed framework can extend the comprehensive performance of Pareto solutions. • Pareto solutions obtained by the new algorithm have greater diversity and stability. • Results obtained by three-objective optimization model provides broader information. • New algorithm is more applicable than the nondominated sorting genetic algorithm II. This paper proposes an online surrogate model-assisted multiobjective optimization framework to identify optimal remediation strategies for groundwater contaminated with dense non-aqueous phase liquids. The optimization involves three objectives: minimizing the remediation cost and duration and maximizing the contamination removal rate. The proposed framework adopts a multiobjective feasibility-enhanced particle swarm optimization algorithm to solve the optimization model and uses an online surrogate model as a substitute for the time-consuming multiphase flow model for calculating contamination removal rates during the optimization process. The resulting approach allows decision makers to find a balance among the remediation cost, remediation duration and contamination removal rate for remediating contaminated groundwater. The new algorithm is compared with the nondominated sorting genetic algorithm II, which is an extensively applied and well-known algorithm. The results show that the Pareto solutions obtained by the new algorithm have greater diversity and stability than those obtained by the nondominated sorting genetic algorithm II, indicating that the new algorithm is more applicable than the nondominated sorting genetic algorithm II for optimizing remediation strategies for contaminated groundwater. Additionally, the surrogate model and Pareto optimal set obtained by the proposed framework are compared with those of the offline surrogate model-assisted multiobjective optimization framework. The results indicate that the surrogate model accuracy and Pareto front achieved by the proposed framework outperform those of the offline surrogate model-assisted optimization framework. Thus, we conclude that the proposed framework can effectively enhance the surrogate model accuracy and further extend the comprehensive performance of Pareto solutions. [ABSTRACT FROM AUTHOR]

• A hydrogen liquefaction process is modified, simulated and analyzed. • The HYSYS process diagram with ortho-para hydrogen converters is presented. • Genetic algorithm in MATLAB is selected as the optimization method for the process. • The process SEC is 7.1329 kWh/kg LH2 and the exergy efficiency is 0.4941. • The proposed systems and other systems are compared and analyzed. The preliminary designed hydrogen liquefaction plant process based on liquid nitrogen precooling and helium gas turbine expansion refrigeration is firstly modified, simulated and analyzed by Aspen HYSYS. In addition, the multi-parameter optimization of the system is carried out by genetic algorithm (GA) by considering the specific energy consumption (SEC) of the system as the objective function. After optimization, it can be found that the SEC of the system is 7.1329 kWh kg LH2 −1, which is 19.65% lower than that of base case and the coefficient of performance (COP) and figure of merit (FOM) are 0.1704 and 0.4941, which are higher than that prior to the process optimization. In addition, sensitivity analysis is conducted to present the effects of different operation conditions of the designed process on the features of the hydrogen liquefaction process. Compared with the other two systems of hydrogen liquefaction, the process in this paper shows the best performance. [ABSTRACT FROM AUTHOR]

This paper proposes a method to find the hyperparameter tuning for a deep neural network by using a univariate dynamic encoding algorithm for searches. Optimizing hyperparameters for such a neural network is difficult because the neural network that has several parameters to configure; furthermore, the training speed for such a network is slow. The proposed method was tested for two neural network models; an autoencoder and a convolution neural network with the Modified National Institute of Standards and Technology (MNIST) dataset. To optimize hyperparameters with the proposed method, the cost functions were selected as the average of the difference between the decoded value and the original image for the autoencoder, and the inverse of the evaluation accuracy for the convolution neural network. The hyperparameters were optimized using the proposed method with fast convergence speed and few computational resources, and the results were compared with those of the other considered optimization algorithms (namely, simulated annealing, genetic algorithm, and particle swarm algorithm) to show the effectiveness of the proposed methodology. • An optimization method for hyper-parameters for a deep neural network. • Performing optimization of the network using a univariate dynamic encoding algorithm for searches. • Validation of the proposed method with two neural network model with MNIST data set. • Fast convergence speed and a small computational amount to optimize hyper-parameter of the network. [ABSTRACT FROM AUTHOR]

In conventional mobile crowdsensing (MCS) applications, the crowdsensing server (CS-server) needs mobile users' precise locations for optimal task allocation, which raises privacy concerns. This paper proposes a privacy-preserving task allocation framework (called P2TA) for edge computing enhanced MCS, focusing on optimize task acceptance rate while protecting participants' privacy by introducing edge nodes. The basic idea is that edge nodes act as task assignment agents with privacy protection that prevents an untrusted CS-server from accessing a user's private data. We begin with a thorough analysis of the limitations of typical task allocation and obfuscation schemes. On this basis, the optimization problem about location obfuscation and task allocation is formulated in consideration of privacy constraints, travel distance and impact of location perturbation. Through problem decomposition, the location obfuscation subproblem is modeled as a leader-follower game between the designer of location obfuscation mechanism and the potential attacker. Against inference attack with background knowledge, a genetic algorithm is introduced to initialize an obfuscation matrix. With the matrix, an edge node makes task allocation decisions that maximize task acceptance rate subject to differential and distortion privacy constraints. The effectiveness and superiority of P2TA compared to exiting task allocation schemes are validated via extensive simulations. [ABSTRACT FROM AUTHOR]

• Propose a multi-level maintenance policy considering quality and shocks. • Establish the link between maintenance, shocks, production and defect rate. • Provide a hybrid method to optimize the policy and the cost rate effectively. In this paper, an innovative maintenance strategy is proposed for a system operating exposed to shock environments. The system contains a deteriorating production machine and a buffer inventory. As the number of completed production batches increases, the machine and the associated process state deteriorate. Accordingly, the production defect rate increases, perhaps to an unsatisfactory level. Two types of shocks, both arriving stochastically, also increase the defect rate or cause failures. To restore or improve the machine performance at decision times, one action is determined among four selectable options. Considering the complexity of the problem, a hybrid method is proposed to optimize the maintenance strategy. The hybrid method involves the integration of a modified human decision-making method (MHDM), Monte Carlo simulation and genetic algorithm (GA). MHDM is used to select effective maintenance activities at the decision times by considering relevant system information, e.g., buffer inventory levels, production defects, maintenance effects and previous decisions. Then, based on the established mathematical model, Monte Carlo simulation and GA are combined to adjust the key parameters of MHDM, to optimize the policy and minimize the expected cost rate. Finally, numerical examples are given to illustrate the proposed method, test its accuracy and provide sensitivity analyses. [ABSTRACT FROM AUTHOR]

This paper explores the use of an elitist-Jaya algorithm for economic optimization of shell-and-tube heat exchanger (STHE) design. Three different optimization problems of STHE are considered in this work. The same problems were earlier attempted by other researchers using genetic algorithm (GA), simulated annealing (SA), non-dominated sorting algorithm (NSGA-II) and design approaches motivated by constructional theory. Jaya algorithm is a newly developed algorithm and it does not require any specific parameters to be tuned except the common control parameters. Elitist version of the algorithm is proposed in this paper to optimize the setup cost and operational cost of STHE simultaneously. Discrete variable optimization is also carried out in order to take the advantage of the standard design available for heat exchanger parts. The effect of common controlling parameters e.g. population size, number of iterations and elite size, is tested by considering different combinations of the same. Furthermore, two other case studies of STHE design are considered from the literature and the performance of the elitist-Jaya algorithm is compared with the recently published results. The results of computational experiments proved the superiority of the proposed algorithm over the latest reported methods used for the optimization of the same problems. [ABSTRACT FROM AUTHOR]

A new class of wind turbine termed the external axis wind turbine (EAWT) has been recently developed in response to the anticipated increase in global demand for renewable energy. The EAWT combines the high power output of the HAWT with the low installation and maintenance cost of the VAWT. This paper optimizes this EAWT to simultaneously maximize the power while minimizing power fluctuation and the time required to reach the optimal operating point. The multi-objective optimization on the EAWT using Genetic Algorithm is performed on a response surface that is generated using CFD simulations in OpenFOAM. The turbulence model and mesh-sizing for the CFD simulations are validated against previously published experimental results on a bluff body. The paper first optimizes the EAWT using steady state CFD simulations which are found to be not valid. The paper then optimizes the EAWT using transient CFD simulation with moving mesh, first for a single Reynolds number then for a wide range of Reynolds numbers. From the analysis, a blade count of 10 at an operational tip speed ratio of 0.32 is recommended. This paper is the first study on EAWT. To the best of authors' knowledge, this paper is also the first study on wind-turbines to optimize changing blade count and operating point to simultaneously maximize power, while minimizing power fluctuation and the time needed to reach peak operating point. [ABSTRACT FROM AUTHOR]

A major development of the offshore wind energy market is being witnessed. Since the implicated costs are considerably high, it is extremely important to ensure that the energy production is maximum, so that the costs per energy unit are minimized. Thus, the turbines should be strategically positioned to extract as much energy as possible from the wind, considering wake effect losses, as well as internal grid electrical losses. In order to avoid turbines to be placed in unrealistic positions, they should be distributed according to a grid of rectangular shaped cells; each of these is divided in multiple sub-cells. The problem of finding the turbines optimal position among the pre-defined sub-cells so that maximum annual energy is produced could be addressed using a deterministic approach. However, the problem becomes unfeasible when the number of turbines and/or the number of sub-cells increase. To overcome this difficulty, optimization techniques should be used. Genetic Algorithm and Particle Swarm Optimization are approached in this paper. This paper deals with the wind park layout optimization problem. A methodology to position the turbines inside a wind park so that the annual energy production is maximum is proposed. The results proved that the meta-heuristic method is much more CPU time efficient in providing the maximum annual year production as compared to the traditional deterministic approach. [ABSTRACT FROM AUTHOR]

Hybrid evolutionary algorithms to optimize layouts for multi-robot cellular manufacturing systems, which includes cooperative tasks among the robots is proposed in this paper. Layout area, operation time and manipulability of robot are the three design criteria useful to evaluate the robotic assembly systems are presented. Layout design candidates are represented using a sequence-pair scheme to prevent interferences between assembly system components, and the introduction of dummy components is proposed to represent layout areas where components are sparse. The main objective of this paper is to propose and evaluate hybrid algorithms by hybridizing them with genetic algorithm, which has been in use for decades. Differential evolution (DE), artificial bee colony (ABC), charged system search (CSS) and particle swarm optimization (PSO) are hybridized with genetic algorithm to have four hybrid (GA+DE, GA+ABC, GA+CSS and GA+PSO) algorithms. The performances of these algorithms are tested with genetic algorithm reported in the literature. The concept of non-dominated sorting genetic algorithm (NSGA-II) is borrowed to handle multiple objectives and to obtain Pareto solutions for the problems considered. These hybrid algorithms are evaluated using an example design problem of multi-robotic assembly system, and the effectiveness of these algorithms are presented in this paper. It is found that GA+PSO performs better over other hybrid algorithms considered. The application of the proposed algorithms are tested using Mitsubishi RV-6SQ robot configuration. [ABSTRACT FROM AUTHOR]

For optimization of timetables in metro systems with regular cyclic operation, this paper develops a bi-objective programming approach addressed to minimization of net energy consumption and total travel time with provision for dwell time uncertainty. Firstly, we formulate the bi-objective timetable optimization problem as an expected value model with speed profile control. Secondly, we use the ɛ -constraint method within a genetic algorithm framework to determine the Pareto optimal solutions. Finally, numerical examples based on the real-life operation data from the Beijing Metro Yizhuang Line are presented in order to illustrate the practicability and effectiveness of the approach developed in the paper. [ABSTRACT FROM AUTHOR]

The objective of this paper is to provide the development of a new algorithm that produces a family of minimal weight cold-formed steel lipped channels with the smallest number of individual cross-sections (family size) that are still capable of covering the current engineering design demands as commonly found in light steel framing. Current research in cold-formed steel optimization has largely sought optimal cross-sections for single members under a single applied action. In this paper, the optimization effort is extended to a broad set of axial (P) and bending (M) demands. A two-level optimization framework is proposed: level one focuses on member optimization of the P-M demand space as derived from current commercially available lipped channel sections in the United States; while level two focuses on the selection of a new family of optimal lipped channel sections that have the same efficiency in covering the design space, but utilize a minimal family size. As the focus of the effort is on the two-level optimization the cross-section optimization is simplified in this case to lipped channels against local and distortional buckling only; however the adopted algorithms are readily extensible. The results show that a new family of shapes with only 12 sections can achieve the same or better performance as the 108 sections commercially available in the United States. The developed family of shapes provides a direct demonstration of the potential for optimization to improve cold-formed steel manufacturing. In the future, the first-level member optimization will include new cross-section shapes, e.g., sigma sections, as well as global buckling, and will be performed along with the second family-level optimization to demonstrate additional potential benefits. [ABSTRACT FROM AUTHOR]

This paper addresses the numeric optimization for NaBH 4 powder flow which is commonly used for hydrogen gas production. During the motion process of the powder, a high number of collisions occur between particles constituting the powder. This paper focuses on modeling and finding the parameters that govern these collisions. We use a discrete element method to model the powder and assume that the powder is composed of tiny spheres interacting according to a specific spring damping model. In a series of appropriate physical wedge penetration experiments, force-displacement graphs were measured. In addition, a set of shear tests were conducted from which normal-shear force graphs were extracted. Analytical estimations were formulated for each of the experiments. These graphs were then compared with graphs generated by corresponding simulation tests. Using Genetic Algorithm optimization we obtained a set of governing parameters that best fits the powder behavior. In order to refine our results we have used our analytical formulations to manually search the parameter space for a better fit. Lastly, an angle of repose test validated our model. [ABSTRACT FROM AUTHOR]

In this paper we propose a new approach to learning fuzzy cognitive maps (FCMs) as a predictive model for time series forecasting. The first contribution of this paper is the dynamic optimization of the FCM structure, i.e., we propose to select concepts involved in the FCM model before every prediction is made. In addition, the FCM transformation function together with the corresponding parameters are proposed to be optimized dynamically. Finally, the FCM weights are learned. In this way, the entire FCM model is learned in a completely new manner, i.e., it is continuously adapted to the current local characteristics of the forecasted time series. To optimize all of the aforementioned elements, we apply and compare 5 different population-based algorithms: genetic, particle swarm optimization, simulated annealing, artificial bee colony and differential evolution. For the evaluation of the proposed approach we use 11 publicly available data sets. The results of comparative experiments provide evidence that our approach offers a competitive forecasting method that outperforms many state-of-the-art forecasting models. We recommend to use our FCM-based approach for the forecasting of time series that are linear and tend to be trend stationary. [ABSTRACT FROM AUTHOR]

In this study, the shape of the autonomous underwater helicopter (AUH) was optimized. AUH is a new type of disc autonomous underwater vehicle with good maneuverability and flexibility. In this paper, an optimization mathematical model is established, which takes the resistance coefficient as the optimization objective and the internal volume and the actual engineering demand as the constraints. The optimization mathematical model of AUH is solved by using two combinatorial optimization strategies. Two combinatorial optimization strategies use experimental design algorithm and multi Island genetic algorithm (MIGA) as global search algorithm, and sequential quadratic programming algorithm as local search algorithm. And based on the back propagation (BP) neural network, the sample points are trained and fitted, and the cloud map of the resistance coefficient distribution in the design space is obtained. The optimization results show that compared with the initial resistance coefficient, the first optimal solution reduces by 9.14%, and the second optimal solution reduces by 9.53%. So the resistance performance of AUH is significantly improved, which proves the feasibility of the method proposed in this paper. This provides theoretical support for the shape optimization design of AUH, which will improve the motion performance of AUH in practical engineering applications. • The large range iteration of AUH curve is realized. The optimal solution is obtained and compared with two combined optimization strategies. [ABSTRACT FROM AUTHOR]

Partial shading on photovoltaic (PV) modules significantly affects their productivity. Therefore, different PV reconfiguration approaches were employed as solutions for distributing the shade across the array. This paper proposes an advanced four-square (FS) sudoku technique for configuring the 9 × 9 total-cross-tied (TCT) PV array via moving the modules physically for one time to enhance the harvested maximum power under all possible shading patterns. The proposed FS is validated under different shading classes, including deterministic and random shading patterns. The performance of the proposed strategy is assessed versus six different approaches representing the literature, including basic sudoku (SDU), optimal sudoku (OSDU), chaos map (CMP), skyscraper (Sky-S), odd-even prime (OEP), and ancient chinese magic square (ACMS). The assessment process is conducted using the global maximum power point, execution ratio (ER), fill factor (FF), percentage power losses (% P L), power enhancement (% P H), and array output power-voltage (P-V) characteristic. Moreover, an extensive analysis of the cost and the energy saving during a day is performed to investigate the reliability of the proposed FS strategy. Furthermore, a critical evaluation is performed among the FS and recent dynamic reconfiguration approaches, including particle swarm optimizer (PSO), harris hawk optimization algorithm (HHO), genetic algorithm (GA), butterfly optimization algorithm (BOA), coyote optimization algorithm (COA) and artificial ecosystem-based optimization (AEO). The results of this paper reveal that the rearranged scheme-based FS approach can disperse different categories of shading efficiently with a high generated energy from the entire system and high revenue compared to TCT and other state-of-the-art arrangements with achieving smooth uni-peak P-V characteristics. • A novel static reconfiguration approach using four square sudoku (FS) is proposed. • FS is proposed as a universal scheme for dispersing several shade patterns. • FS is evaluated versus several static and dynamic reconfiguration approaches. • FS reliability is assessed by determining the energy savings over a day. • FS enhanced the power by 38.016% in the existence of random failed modules. [ABSTRACT FROM AUTHOR]

In this paper, the influence of the spatial configuration of a wave energy converter (WEC) array upon total power output is investigated. A power prediction model has been proposed to improve the efficiency of calculating the total power from the array with guaranteed accuracy. The prediction model consists of two main components. One is the automatic generation model for training samples by establishing an interface between MATLAB and AQWA. The other is the artificial neural network (ANN) adaptive training model improved by the adaptive genetic algorithm (AGA), which helps to improve the prediction accuracy by 80% according to experimental validation and simulation comparison. The traditional genetic algorithm (GA) has been widely used in WEC arrays optimization. The method proposed in this paper has improved the GA optimization efficiency by about 50%. Arrays with different numbers of devices are studied in irregular waves measured in the previous sea trials, and similar optimal layouts appear in all cases, which allows extrapolation of the results to even larger arrays. The solution space calculated by the optimization algorithm is further analyzed based on separate considerations of different spacing between devices and wave directions. The resulting behaviour is expected to guide engineering applications. • A new power prediction method for WEC array, including an automatic generation model and an adaptive training model, is proposed. • A new adaptive genetic algorithm is proposed to optimize WEC array. • The influence of the spatial configuration of a WEC array upon total power output is investigated. • The linear arrangement of WEC has important properties and the resulting behaviour is expected to guide engineering applications. [ABSTRACT FROM AUTHOR]

The marine vehicle is one of the most important platforms in oceanic research and development. During the evolution of marine vehicle design, hull optimization is a key topic consisting of various steps such as hull deformation analysis, optimization algorithm selection and hydrodynamic performance evaluation. For hull deformation analysis, radial based function interpolation technique is usually applied with Wendland's ψ 3 , 1 function, which requires a great number of fixed points. To improve the optimization effect, this paper proposes a novel radial basis function for better support radius condition. According to the support radius condition, the effect of different deformation functions acting on hull form is studied. To verify the effectiveness of the improved radial basis function in marine vehicle hull optimization, a Series 60 hull is taken as the initial hull, and the Rankine source method is utilized as the solver to calculate the wave resistance coefficient. The Non-dominated Sorting Genetic Algorithm (NSGA) is applied to determine the optimal hull form at given speeds. By comparing the optimization results, the benefits and drawbacks of the improved radial basis function are analyzed. The results show that the number of fixed control points can be reduced by applying the improved radial basis function. When different deformation functions are acting on the marine vehicle hull, the improved radial basis function makes the gradient transition smoother. In the process of hull optimization, the wave resistance coefficient obtained by utilizing the improved function to deform the hull is smaller than that of using Wendland's ψ 3 , 1 function under different support radii. • An improved Radial Basis Function is proposed for marine vehicle hull optimization. • The effectiveness of the improved function proposed in this paper is demonstrated. • Advantages of the improved function for hull deformation is discussed extensively. [ABSTRACT FROM AUTHOR]

Although various tools and procedures have been developed to help transportation engineers objectively evaluate bridge maintenance needs, selecting and scoping projects still relies on engineering judgment. The present paper intends to help engineers evaluate and maintain bridges by developing a comprehensive bridge maintenance planning framework (BMPF) within financial and performance constraints. The paper's objectives are to maximize the performance condition level of bridges and to minimize the maintenance cost by optimally planning the maintenance treatments. The framework includes bridge performance impact assessment, machine learning models, multi-attribute utility theory ranking model and genetic algorithm optimization model. The study analysed 95 bridges in a network with an 84% accuracy machine learning model prediction. Decision-makers' preferences were considered to rank all bridges using Multi-Attribute Utility Theory. 19 bridges were then chosen for maintenance based on budget and performance using a genetic algorithm model. The BMPF was observed to improve project productivity, reduce down time, and improve bridge inventory condition. Future research can explore the use of other optimization approaches and also include traffic flow and construction cost analysis for a better maintenance cost estimation. The machine learning model for performance prediction can be enhanced by utilizing different techniques. •.The paper developed a Bridge Maintenance Planning Framework for effective bridge maintenance planning. • The proposed framework uses Machine Learning models to predict bridge condition. • Multi-attribute utility theory model ranked bridges by capturing the decision-maker's preference uncertainty and risk attitude. • Genetic algorithms were utilized to optimize bridge maintenance planning. • The Framework improved project productivity, downtime, and bridge inventory condition. [ABSTRACT FROM AUTHOR]

Abstract In this paper, a BIPV/T-PCM installed in an office building façade is investigated to approach the system efficiency optimization using Genetic Algorithm method. Based on an updated mathematical model, theoretical simulation has been conducted for BIPV/T-PCM in this case for the existing system set-up (geometry-air cavity width, ventilation, system layers). Furthermore, field testing for this case has also been performed to validate the model, and then the simulated and experimental results are compared and found in considerably good agreement. The overall energy efficiency of the system was evaluated for winter and summer condition adopting different utilization strategies and optimization variables have been identified. The thermal and electric efficiencies were calculated based on the optimization variables and the results shown that the system can achieve a maximum overall efficiency of 64% with winter configuration and 32% with summer configuration. Highlights • Efficiency optimization of a BIPV/T-PCM using Genetic Algorithm approach is proposed. • A numerical model is presented and validated. • With optimization process the system can achieve a higher efficiency. [ABSTRACT FROM AUTHOR]

• A new hyperparameters optimization method for convolutional neural networks. • A new multiscale and multilevel genetic algorithm. • Bayesian optimization and genetic algorithm are combined to optimize the hyperparameters on multiscale grids. The use of convolutional neural networks involves hyperparameters optimization. Gaussian process based Bayesian optimization (GPEI) has proven to be an effective algorithm to optimize several hyperparameters. Then deep networks for global optimization algorithm (DNGO) that used neural network as an alternative to Gaussian process was proposed to optimize more hyperparameters. This paper presents a new algorithm that combines multiscale and multilevel evolutionary optimization (MSMLEO) with GPEI to optimize dozens of hyperparameters. These hyperparameters are divided into two groups. The first group related with the sizes of layers and kernels are discrete integers. The second group related with learning rates and so on is continuous floating-point numbers. All combinations of the first group are corresponding to the combinations of grid points on multi-scale grids and MSMLEO launches GPEI to optimize the second group of hyperparameters while the first group keeps fixed. The output of convolutional networks configured with above two groups of optimized hyperparameters is used as the fitness of MSMLEO. MSMLEO alternates with GPEI to search the optimal hyperparameters from coarsest scale to finest scale. Experimental results show that our algorithm has better performance and adaptability on optimizing dozens of hyperparameters of neural networks with a variety of numerical types. Image, graphical abstract [ABSTRACT FROM AUTHOR]

Abstract Artificial neuro-fuzzy inference system known as the ANFIS tool was earlier developed by authors [1] for exergoeconomic optimization of an energy system. It was shown that the ANFIS could achieve the optimal solutions of systems with reasonable accuracy, very low computation time, and less dependency on experts' knowledge. This paper aims to test a similar methodology for retrofit and real-time optimization of a large energy system in response to the load variation. A 250 MW unit in a fossil-fueled steam power plant was considered as a case study. The profit of the power plant was estimated using an exergoeconomic analysis, and it was maximized by adjusting flow rates of extracted steams that flow from turbines into feed-water heaters. The ANFIS methodology was developed in detail to optimize the profit of the proposed power plant. The advantage of the ANFIS for this purpose was compared to other alternatives such as genetic algorithm (GA) and fuzzy-inference system (FIS). It was shown that the ANFIS is much faster than the GA and considerably easier than the FIS for real-time optimization energy systems. It was shown that using ANFIS, it is possible to achieve more profit in the proposed power plant up to 320 $.hr−1 by implication control on the flow of extracted steam; however, this figure is different at various loads of the power plant. Highlights • Real-time optimization based on adaptive neuro-fuzzy inference system, ANFIS. • Optimizing extracted steams in response to the load using the ANFIS. • Maximizing the profit of a fossil-fueled steam power plant. • A quite faster optimization methodology in comparison to conventional methods. • Automatic generation of governing fuzzy rules of optimization by the ANFIS. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • Design of slotless PMBLDC motor has been optimized using WSM, MOGA and NPGA. • An objective function consists of output torque, total volume and total power loss. • The sensitivity analysis has been carried out to identify the design variables. • The NPGA has better performance compared with WSM and MOGA. • The magnetic flux distribution and thermal analysis has been carried out. Abstract In this paper, Multi-Objective Optimization (MOO) techniques namely: Weighted Sum Method (WSM), Multi Objective Genetic Algorithm (MOGA) and Niched Pareto Genetic Algorithm (NPGA) are proposed for the design optimization and analysis of magnetic flux distribution for a slotless permanent magnet Brushless DC (BLDC) motor. The sensitivity analysis is carried out to identify the design variables of BLDC motor which influence the objective function. The objective functions are conflicting in nature (maximization of output torque and minimization of total volume and losses), hence, are optimized simultaneously by means of MOO algorithms. The proposed MOOs account for four kinds of design variables namely: rotor radius, stator/ rotor axial length, magnet thickness and winding thickness simultaneously to maximize the output torque and to reduce the total volume and total power loss. The conventional MOO such as WSM gives single pareto optimal solution. However, the proposed MOGA and NPGA algorithms create accurate and well-distributed pareto front set with few function evaluations. The performances of the three MOOs are evaluated and compared using the four performance metrics namely: Hyper Volume (HV), Generational Distance (GD), Inverted Generational Distance (IGD) and Spread. From the comparison, it is observed that NPGA gives better results. Using the design parameter obtained from NPGA, the magnetic flux distribution analysis of the BLDC motor is carried out to analyze variation of flux distribution in the different parts of the motor. The results thus obtained are compared with those obtained through Partial differential equation and single objective GA optimization. The detailed thermal analysis is also carried out to analyze the thermal behavior at different parts of the machine for different working conditions in the continuous operation mode and hence, the results obtained are compared with single objective GA optimization. The advantages of MOOs in the design optimization of slotless permanent magnet BLDC motor are highlighted. [ABSTRACT FROM AUTHOR]

Highlights • A heuristic search strategy was proposed for optimal learning group formation. • NSGA-II, a multi-objective optimization tool, was utilized for optimal grouping. • It was capable of enhancing inter-group homogeneity and Intra-group Heterogeneity. • Efficient and reliable fitness functions were defined to stop iterations. • Various characteristics of any data types and range of variations can be handled. Abstract In modern education systems, plenty of research suggests that clustering the learners into optimal learning groups based on their multiple characteristics is a determining effort in enhancing the effectiveness of collaborative learning. Although there have been several evidences on developing and implementing appropriate computational tools to handle classification processes in expert and intelligent systems, the effectiveness and accuracy of optimal grouping algorithms are still worth improving. For instance, the majority of grouping processes in collaborative learning environments is orchestrated through single-objective optimization algorithms, which need to be revisited due to some intrinsic limitations. In this paper, we propose a novel algorithm capable of properly addressing a variety of optimization problems in optimal learning group formation processes. To this end, a multi-objective version of Genetic Algorithms, i.e. Non-dominated Sorting Genetic Algorithm, NSGA-II, was successfully implemented and applied to improve the performance and accuracy of optimally formed learning groups. In contrast to the previous related works applying single-objective algorithms, the main advantage of our work is simultaneous satisfaction of multiple targets predefined for the formation of optimal learning groups, especially the inter-homogeneity and intra-heterogeneity of each learning group, which significantly enhance both effectiveness and accuracy of optimal grouping processes in the underlying intelligent systems. Challenging the proposed optimization algorithms, both single- and multi-objective optimizers, with a similar grouping problem, clearly proved that the single-objective optimization technique has limited control and sensitivity to the quality of individual groups. Contrary to single-objective optimization techniques, which are mainly governed by adjusting the quality of the groups altogether in average, the proposed multi-objective algorithm not only takes the average desirability of all formed groups into account but also precisely monitors the fitness of each group in a potential solution distinctively. The generality of the proposed algorithm makes it a suitable candidate not only to handle optimal grouping in learning environments but also to be competent enough for grouping problems in other domains as well. [ABSTRACT FROM AUTHOR]