Search

The power system using hydrogen fuel cells (FCs) as the primary energy source holds significant potential for applications in emergency fields such as post-disaster relief and outdoor power supply. The operational environment of the FC emergency power supply system (FCEPSS) is challenging, with long continuous operation time, difficulties in hydrogen supply, high maintenance costs, and, accordingly, requirements for hydrogen consumption and useful life of FCs are heightened. Hence, this paper proposes a multi-objective energy management strategy (EMS) for FCEPSS. First, the structure of FCEPSS is designed based on the demand analysis in emergency scenarios. Then, the hydrogen consumption and life degradation models of FCEPSS are established. Aiming at the multi-objective optimization problem of minimizing hydrogen consumption and life degradation value in the FCEPSS, an improved multi-objective optimization algorithm is proposed. This paper converts complex constraints into the penalty term and incorporates it as one of the objectives, constructing a three-objective optimization model. To enhance the solution of multi-objective optimization problems, an improved strategy based on relaxation-tightening and three-objective sorting is proposed. Combining the fast non-dominated sorting genetic algorithm-II and the above improved strategy, an improved multi-objective optimization algorithm (IMOOA) is constructed. In the simulation, the advantages of the proposed IMOOA algorithm are verified. In the experimental part, compared with the logical threshold strategy, the proposed strategy saves 0.60% of hydrogen consumption and reduces 5.65% of life degradation within 24 h, respectively. Finally, the superiority of the multi-objective EMS utilizing the IMOOA is demonstrated. [Display omitted] • The demand analysis and scheme design of fuel cell emergency power supply system are carried out. • A multi-objective energy management strategy for low hydrogen consumption and long useful life is designed. • An algorithm based on the relaxation-tightening and three-sorting principle is constructed. [ABSTRACT FROM AUTHOR]

When constructing an investment portfolio, it is important to maximize returns while minimizing risks. This portfolio optimization can be considered as a multi-objective optimization problem that is solved by means of multi-objective evolutionary algorithms. The use of multi-objective evolutionary algorithms (MOEAs) provides an effective approach for dealing with the complex data involved in multi-objective optimization problems. However, current MOEAs often rely on a single strategy to obtain optimal solutions, leading to premature convergence and an insufficient population diversity. In this paper, a new MOEA called the Synergistic MOEA with Diffusion Population Generation (DPG-SMOEA) is proposed to address these limitations by integrating MOEAs with diffusion models. To train the diffusion model, a mixed memory pool strategy is optimized, which collects improved solutions from the MOEA/D-AEE, an optimized MOEA, as training samples. The trained model is then used to generate offspring. Considering the cold-start mechanism of the diffusion model, particularly during the training phase where it is not suitable for generating initial offspring, this paper adjusts and optimizes the collaborative strategy to enhance the synergy between the diffusion model and MOEA/D-AEE. Experimental validation of the DPG-SMOEA demonstrates the advantages of using diffusion models in low-dimensional and relatively continuous data analysis. The results show that the DPG-SMOEA performs well on the low-dimensional Hang Seng Index test dataset, while achieving average performance on other high-dimensional datasets, consistent with theoretical predictions. Overall, the DPG-SMOEA achieves better results compared to MOEA/D-AEE and other multi-objective optimization algorithms. [ABSTRACT FROM AUTHOR]

This paper explores the application of multi-objective optimization techniques, including MOPSO, NSGA II, and SPEA2, to optimize the hyperparameters of artificial neural networks (ANNs) and support vector machines (SVMs) for predicting the physical properties of textile polymer composite materials (TPCMs). The optimization process utilizes data on the physical characteristics of the constituent fibers and fabrics used to manufacture these composites. By employing optimization algorithms, we aim to enhance the predictive accuracy of the ANN and SVM models, thereby facilitating the design and development of high-performance textile polymer composites. The effectiveness of the proposed approach is demonstrated through comparative analyses and validation experiments, highlighting its potential for optimizing complex material systems. [ABSTRACT FROM AUTHOR]

The paper takes the Jidong Nanbu high temperature oil reservoir as the research object and establishes the comprehensive numerical model of CO2 storage and displacement based on the CO2 displacement mechanism, CO2 heat recovery mechanism, and CO2 geological storage mechanism. On this basis, the injection and production optimization model is established by combining the theory of multi-objective and single-objective optimization algorithm respectively. The objective function of the multi-objective injection and production optimization model is NPV and CO2 heat recovery. The model is solved using the NSGAII and MOPSO algorithm. The results show that the objective function value obtained by the MOPSO algorithm is better than the NSGAII algorithm. The optimal values of NPV and CO2 heat recovery were 4.781 × 108 CNY and 1.078 × 1016 J respectively. The objective function of the single objective injection and production optimization model is the NPV. GA and DE optimization algorithms are used to solve the model. The results show that the DE algorithm gets the better objective function value than the GA algorithm. The optimal value of NPV is 3.69 × 1010 CNY. [ABSTRACT FROM AUTHOR]

Community structure is a very interesting attribute and feature in complex networks, which has attracted scholars' attention and research on community detection. Many single-objective optimization algorithms have been migrated and modified to serve community detection problems. Due to the limitation of resolution, the final algorithm implementation effect is not ideal. In this paper, a multi-objective community detection method based on a pigeon-inspired optimization algorithm, MOPIO-Net, is proposed. Firstly, the PIO algorithm is discretized in terms of the solution space representation, position, and velocity-updating strategies to adapt to discrete community detection scenarios. Secondly, by minimizing the two objective functions of community score and community fitness at the same time, the community structure with a tight interior and sparse exterior is obtained. Finally, for the misclassification caused by boundary nodes, a mutation strategy is added to improve the accuracy of the final community recognition. Experiments on synthetic and real networks verify that the proposed algorithm is more accurate in community recognition compared to 11 benchmark algorithms, confirming the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In recent years, swarm intelligence optimization methods have been increasingly applied in many fields such as mechanical design, microgrid scheduling, drone technology, neural network training, and multi-objective optimization. In this paper, a multi-strategy particle swarm optimization hybrid dandelion optimization algorithm (PSODO) is proposed, which is based on the problems of slow optimization speed and being easily susceptible to falling into local extremum in the optimization ability of the dandelion optimization algorithm. This hybrid algorithm makes the whole algorithm more diverse by introducing the strong global search ability of particle swarm optimization and the unique individual update rules of the dandelion algorithm (i.e., rising, falling and landing). The ascending and descending stages of dandelion also help to introduce more changes and explorations into the search space, thus better balancing the global and local search. The experimental results show that compared with other algorithms, the proposed PSODO algorithm greatly improves the global optimal value search ability, convergence speed and optimization speed. The effectiveness and feasibility of the PSODO algorithm are verified by solving 22 benchmark functions and three engineering design problems with different complexities in CEC 2005 and comparing it with other optimization algorithms. [ABSTRACT FROM AUTHOR]

In order to accurately predict the minimum creep rate under the actual working conditions of compacted graphite cast iron cylinder head, this paper conducted creep experiments in the temperature range of 723.15–823.15 K and the stress range of 100–300 MPa. The creep damage evolution and damage mechanisms under test conditions were also analyzed. Then the data fitting performances were analyzed and compared from three aspects: the optimization‐seeking algorithm, the form of the objective function and the construction of the creep constitutive model. Finally, the chosen optimization algorithm combined with the proposed objective function and creep constitutive model resulted in 100% of the predicted values within the 3 times error band and 26.67% of the predicted values within the 1.5 times error band. This improves the prediction accuracy while reducing the effect of data overfitting. [ABSTRACT FROM AUTHOR]

In this paper, a dual multi-objective optimization design method for compliant mechanism is proposed, and a new compliant guide mechanism is designed by using this method. The method combines the local optimization of multi-objective optimization algorithm and the structural optimization of multi-objective topology analysis, which can carry out the optimization design more systematically and comprehensively. Firstly, we present the specific optimization workflow and construct the mechanism amplification ratio model and pseudo-rigid body model. Secondly, the single design is carried out through using a combination of sensitivity analysis and NSGA-II multi-objective optimization, and meanwhile the EMM + TOPSIS are utilized to ensure the objectivity of the result ordering. On this basis, double design is then conducted and a better comprehensive working performance could be obtained by applying multi-objective topology design. Finally, a prototype is fabricated for experimental testing. The results show that the amplification ratio error between simulation and experiment is just 2.16%, and the operating frequency reaches 1762.9 Hz. The experimental results prove the correctness of the simulation results and show the practical application of the optimization method. [ABSTRACT FROM AUTHOR]

Due to the non-deterministic and probabilistic qualities of renewable energy resources (RER), integrating these resources has posed a challenge for energy companies and government policy planners. Hybrid power systems require frequent voltage regulation to address the changes in renewable generation and facilitate voltage management. This leads to an increment in the operating time of the tap changer in the power transformer, thus resulting in accelerated degradation of the on-load tap changer (OLTC) device. The primary focus of this paper is to optimally manage the penetration level of renewable generation while maintaining the minimum time for proper operation of voltage regulation devices. Accordingly, the major contribution of this paper is to address the switching cycle issues of the on-load tap-changing transformer. Initially, a framework is proposed to optimize the location and size of renewable power generation using a multi-objective cuckoo search optimization algorithm. The main goal here is to reduce power losses and tap changer operations while improving the system voltage profile under different levels of renewable energy penetration. The optimization problem takes into consideration the fluctuating nature of wind speed and solar irradiance for sunny and cloudy days over 24 h. The framework has been applied to the IEEE 57-bus and 118-bus systems with different load levels. The performance of the proposed approach has been benchmarked by comparing it with the genetic optimization algorithm to identify the higher potential buses for renewable generation allocation. The cuckoo search algorithm (CSA) shows outstanding results in reducing the number of switching cycles to about (37 – 43) % whereas the genetic algorithm (GA) only (17 – 18). In this sense, the number of changes in tap position when using the CSA is 1956 for sunny days and 1763 for cloudy days compared to GA 2558 for sunny days and 2547 for cloudy days. The voltage profiles for both algorithms are maintained in the range of (1.06 and 0.94) per unit. The results affirm the effectiveness of the proposed approach in determining the optimal placement and size of RER with voltage profile improvement and reduction in the switching cycles of OLTC. [ABSTRACT FROM AUTHOR]

Energy generation systems based on FC (fuel cell) are viewed as a viable substitute for those that simply rely on thermodynamic cycles in the power production field. In this paper, a 10-stack SOFC systems performance and optimization of that utilizing a newly improved optimizer known as the Fractional-order Kho-Kho optimization method will be presented in this paper. The multi-objective optimization approach is applied in the optimization phase to achieve the desired performance goals for the SOFC system. With the help of this technique, the desired system can be optimized in accordance with two objective functions: first, the electric power of the system can be maximized, while the equalized price of the electricity produced is minimized. Then, the electrical efficiency of the system can be maximized, while the equalized price of the electricity produced is minimized. The results show that, by reducing the coefficient and increasing efficiency, optimal solutions were achieved with higher electricity prices. It is observed that an increase in energy prices led to a 9% increase in productivity, whereas a 15% increase resulted in only a 2% increase. The findings demonstrate that multi-objective optimization may be used as a sophisticated analytical tool as well as a guiding element for decision-makers utilizing such a system. [ABSTRACT FROM AUTHOR]

Multi-objective evolutionary algorithms (MOEA) have attracted much attention because of their good global exploration ability; however, their local search ability near the optimal value is weak, and for large-scale decision-variable optimization problems the number of populations and iterations required by MOEA are very large, so the optimization efficiency is low. Gradient optimization algorithms can overcome these difficulties well, but gradient search methods are difficult to apply to multi-objective optimization problems (MOPs). To this end, this paper introduces a stochastic weighting function based on the weighted average gradient and proposes two multi-objective stochastic gradient operators. Further, two efficient evolutionary algorithms, MOGBA and HMOEA, are developed. Their local search capability has been greatly enhanced while retaining the good global exploration capability by using different offspring update strategies for different subpopulations. Numerical experiments show that HMOEA has excellent capture ability for various Pareto formations, and it can easily solve multi-objective optimization problems with many objectives, which improves the efficiency by a factor of 5–10 compared with typical multi-objective evolutionary algorithms. HMOEA is further applied to the multi-objective aerodynamic optimization design of the RAE2822 airfoil and the ideal Pareto front is obtained, which indicates that HMOEA is an efficient optimization algorithm with potential applications in aerodynamic optimization design. [ABSTRACT FROM AUTHOR]

Cloud computing provides consumers and organizations with shared pools of resources for data storage and processing and its optimization is essential as 98% of the allocated resources have been utilized only 86% of 98%. Hence, we carry out optimization to automatically allocate resources. In a cloud data center, Virtual machine placement is essential, and choosing the optimal physical machine to host the virtual machine is a critical step. The efficacy of the Virtual machine placement strategy has a considerable impact on cloud computing efficiency. Today, cloud computing optimization is needed for business goals and competition in the digital landscape for cost reduction (20–28%) and Energy consumption (16–22%), improving performance (30–42%) and scaling (12–14%) to meet changing business needs. Virtual machine placement optimization problems are a class of problems that arise in cloud computing when allocating resources to virtual machines across a set of physical machines or hosts. The goal is to optimize resource utilization (12–16%) while satisfying various constraints, such as performance requirements, availability, and energy efficiency than non-metaheuristic optimization techniques. Several virtual machine placement optimization problems include placement, consolidation, migration, and scheduling. Virtualization facilitated by virtual machine placement and migration meets the ever-increasing demands of a dynamic workload by transferring virtual machines inside cloud data center. Many resource management goals, including power efficiency, load balancing, fault tolerance, and system maintenance, are aided by virtual machine placement and migration. To propose a multi-objective Mayfly virtual machine placement algorithm with a massive cloud data center with different and multi-dimensional resources to handle these issues. A multi-objective, dynamic virtual machine placement strategy simultaneously reduces resource wastage, overcommitment ratio, migration time, service level agreement violation, and energy consumption. This paper presents a dynamic, multi-objective virtual machine placement strategy in cloud data centers based on overcommitment resource allocation to influence Virtual machine Physical machine mapping and achieved an increase in the range of 12.5–14.89% in allocation than the existing works. We validated our method by conducting a performance evaluation study using the CloudSim tool. The experimental results demonstrate that this article improves resource usage while reducing energy consumption, makespan, over-commitment, and physical machine overload. [ABSTRACT FROM AUTHOR]

Addressing the challenge of efficiently solving multi-objective optimization problems (MOP) and attaining satisfactory optimal solutions has always posed a formidable task. In this paper, based on the chicken swarm optimization algorithm, proposes the non-dominated sorting chicken swarm optimization (NSCSO) algorithm. The proposed approach involves assigning ranks to individuals in the chicken swarm through fast non-dominance sorting and utilizing the crowding distance strategy to sort particles within the same rank. The MOP is tackled based on these two strategies, with the integration of an elite opposition-based learning strategy to facilitate the exploration of optimal solution directions by individual roosters. NSCSO and 6 other excellent algorithms were tested in 15 different benchmark functions for experiments. By comprehensive comparison of the test function results and Friedman test results, the results obtained by using the NSCSO algorithm to solve the MOP problem have better performance. Compares the NSCSO algorithm with other multi-objective optimization algorithms in six different engineering design problems. The results show that NSCSO not only performs well in multi-objective function tests, but also obtains realistic solutions in multi-objective engineering example problems. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach that facilitates the design of active controllers to mitigate seismically induced damage in structural systems. The proposed method is based on stochastic Modified Black Hole optimization algorithm. Two traditional controllers, namely Proportional-Integral-Derivative (PID) and Linear–Quadratic Gaussian (LQG) controllers were designed, and their performance was demonstrated on a benchmark 20-story steel-framed building. Evaluation criteria were defined to satisfy constraints on various response quantities, including drift, base shear, ductility, residual story drift, and control force. The constraint limits were defined in view of performance-based design requirements for the benchmark structure. The performance of the controllers was contrasted with that of traditional LQG, and significant reductions of all response quantities were achieved for design-level earthquakes. [ABSTRACT FROM AUTHOR]

Following the evolution of big data collection, storage, and manipulation techniques, deep learning has drawn the attention of numerous recent studies proposing solutions for smart cities. These solutions were focusing especially on energy consumption, pollution levels, public services, and traffic management issues. Predicting urban evolution and planning is another recent concern for smart cities. In this context, this paper introduces a hybrid model that incorporates evolutionary optimization algorithms, such as Teaching–learning-based optimization (TLBO), into the functioning process of neural deep learning models, such as recurrent neural network (RNN) networks. According to the achieved simulations, deep learning enhanced by evolutionary optimizers can be an effective and promising method for predicting urban evolution of future smart cities. [ABSTRACT FROM AUTHOR]

Software refactoring solutions aim at mitigating the negative effects of code and design smells on the overall software quality. Many efforts have been exerted to improve the software refactoring process. However, most of these efforts, despite their contributions, overlooked the side effects of the identified refactoring opportunities that may lead to new smells that will go unnoticed. This paper addresses the side effects of software refactoring and proposes sound solutions for handling them. Unlike current practices in software maintenance, we recommend three different approaches to handle the refactoring side effects. In the first approach, called the baseline, we opt to ignore the smells, caused by refactoring, while executing the identified refactoring decisions. In the second one, refactoring decisions are continually updated to fix all smells caused by side effects. In the last approach, only a subset of these smells is appended to the original smell sequence during the execution of the refactoring decisions. Thanks to the proposed approaches, optimal refactoring decisions are identified using a multi‐objective (MO) optimization algorithm commonly known as the MO covariance matrix adaptation evolution strategy (MO‐CMA‐ES). Experiment results corroborate our assumptions and show the superiority of the second approach over the other ones. [ABSTRACT FROM AUTHOR]

Combinatorial optimization problems (COPs) play an important role in both industrial production and theoretical research. As a classical class of optimization algorithms, evolutionary algorithms have shown good performance in COPs. However, as the size of the problem increases, it becomes difficult for evolutionary algorithms to produce satisfactory solutions within the specified time. In recent years, neural network algorithms have been applied to solve COPs and have shown superior effects. Inspired by this, this paper proposes a new algorithm based on graph structure for solving COPs. Through relaxation, COPs are transformed into their corresponding continuous optimization problems. The output state of our algorithm is converted to a discrete solution by approximation method. Compared with previous algorithms, our algorithm can not only solve COPs with general form such as binary quadratic programming (BQP), but also solve COPs with special form, which greatly expands the application scope of neural network algorithms. In addition, our algorithm can be embedded into other problem frameworks such as solving multi-objective combinatorial optimization problem (MOCOP) through scalarization method. A new penalty function is added to the objective function, which enables our algorithm to overcome the inconsistency between the optimal solution of the original problem and the corresponding continuous problem, so that our algorithm can perform well on various problems. Several numerical simulations are used to illustrate the effectiveness of our algorithm in solving COPs. Experimental results show that our algorithm can effectively solve COPs with general form and has a shorter solving time compared to traditional evolutionary algorithms. [ABSTRACT FROM AUTHOR]

[Display omitted] • Current intensity, current density and resistance voltage under thermal equilibrium are considered. • Studied the influence of various electrode structural parameters on the performance of the electrolysis cell. • Compared multiple optimization algorithms to verify the reliability of the obtained Pareto frontier distribution. • Utilized NSGA-II for multi-objective optimization of the Multipolar electrolysis cell. • Reduced electrolysis cell resistance voltage, enhanced current density. In the operation of industrial multipolar magnesium electrolysis cell, cell voltage and current density are important indicators of the production performance of the cell, while thermal balance is a key factor for normal operation. This paper utilizes the finite element method to establish a three-dimensional full cell thermal-electric model, studying the thermal field distribution and current density distribution in a 165kA multipolar magnesium electrolysis cell. Based on the heat balance of the multipolar cell, the influence of structural parameters on current intensity, average current density at the anode surface and resistance voltage is assessed. Dimensionless analysis yielded optimization criteria, and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was employed for multi-objective optimization problems. When stringent optimization is executed, significant performance improvements can be achieved in terms of the electrolysis cell's resistance voltage and current density. Moreover, under the optimization criteria, the relative error of the 265kA multipolar magnesium electrolysis cell model is less than 1 %. The results indicate that the workflow combining the finite element method with multi-objective optimization algorithms can be applied to the optimization and scale-up design of high-current multipolar magnesium electrolysis cell. [ABSTRACT FROM AUTHOR]

• A morphing nose cone that can achieve length and bending angle adjustments is introduced into an underwater glider. • The optimal configurations of morphing nose cone are determined by multi-objective optimization and surrogate models. • A novel design scheme for the driving mechanism of the morphing nose cone and its principle prototype. • The morphing nose cone effectively balances the glider energy utilization rate, static stability, and voyage velocity. As an autonomous underwater vehicle with low energy consumption, underwater glider has been widely applied to long-term ocean exploration missions. To better deal with complex working environments and various mission requirements, morphing underwater gliders are receiving increasing attention. This paper attempts to introduce the morphing nose cone that can achieve length and bending angle adjustments into the glider to improve its comprehensive performance. The performance indicators of the glider include energy utilization rate, static stability, and voyage velocity. Based on dynamic analysis and CFD simulation, performance evaluation models of a glider are established, and the effect of morphing nose cone configurations on the glider's hydrodynamic characteristics is discussed. Then, mathematical optimization models for morphing parameters of the nose cone are established, and they are solved by a multi-objective optimization algorithm and surrogate model technology. Especially, the diving and ascending motion processes of the glider are separately considered in the above optimization. Finally, the multi-objective optimization results are used for guiding the driving mechanism design of the morphing nose cone, and the principle prototype of a novel design scheme is manufactured to verify the feasibility. The research methods and results will provide new development direction for the morphing underwater glider technology. [ABSTRACT FROM AUTHOR]

Adaptive operator selection is an online method that automatically adjusts the application rate of different operators based on their actual performance. This paper proposes an adaptive operator selection paradigm based on dueling deep Q-network (DDQN), aiming to improve the training efficiency of the Q-network for solving multi-objective optimization problems. The Q-network is decomposed into state value and action advantage networks, allowing the agent to learn state values more frequently and accurately. A novel state space and reward mechanism are designed to adapt to the characteristics of evolutionary multi-objective optimization. Combining adaptive operator selection with a multi-objective evolutionary algorithm with adaptive weights (AdaW), an AdaW-DDQN algorithm with high adaptability is proposed. Experimental results on three complex benchmark suites demonstrate that the proposed adaptive operator selection paradigm significantly improves the performance of multi-objective optimization algorithms. The AdaW-DDQN algorithm provides an effective and efficient solution for solving multi-objective optimization problems. • An adaptive operator selection paradigm based on dueling deep Q-network is proposed. • Ten effective crossover operators are designed as a pool of candidate operators. • A new state space and reward mechanism are designed for the multi-objective optimization problem. • The proposed adaptive operator selection paradigm is embedded into MOEA/D with adaptive weights. • Experimental results show that AdaW-DDQN has strong generalization ability. [ABSTRACT FROM AUTHOR]

This paper explores the influence of different turbocharging modes and multi-parameter coordinated control on the performance of compression-ignition (CI) aviation piston engine (APE). Firstly, based on a constructed one-dimensional thermodynamic model of a CI APE, the study investigates the effects of different turbocharging modes and combinations of high and low-pressure stage variable geometry turbines (VGT) on the operational performance of the engine. Subsequently, a novel stepwise approximate multi-objective optimization algorithm is proposed, combining backpropagation neural networks and the non-dominated sorting genetic algorithm II. This algorithm evaluates the influence of multiple control parameters on a two-stage turbocharged engine's performance, achieving a balance between fuel economy and reliability. The research shows that equipping CI APEs with twin VGT for supercharging can notably enhance engine performance, enabling the achievement of favorable power recovery objectives at an altitude of 8000 m. The proposed optimization algorithm exhibits strong predictability and reliability, substantially accelerating the computation speed and reducing the data volume by approximately 95%. At an engine speed of 3887 rpm, compared to the unoptimized conditions, the brake specific fuel consumption of the best scenario at altitudes of 2000 m, 4000 m, 6000 m, and 8000 m is reduced by 7.1%, 7.2%, 8.6%, and 6.9%, respectively. • Influences of different turbocharging modes on the performance of a CI APE are investigated. • A novel stepwise approximate multi-objective optimization method based on a hybrid model is proposed. • Explored the altitude-varying control strategy under coordinated multi-parameter optimization. • Increased the altitude ceiling for the CI APE, reaching 82% power recovery target at 8000 m. [ABSTRACT FROM AUTHOR]

Flue gas water-alternating gas (flue gas-WAG) is a promising technique for enhancing oil production and reducing greenhouse gas emissions. The effective utilization of this technique relies on identifying the optimal factors, often determined through numerous numerical simulations. This paper introduces a cost-effective optimization framework that integrates machine learning models and diverse optimization algorithms to identify the best parameters for injecting flue gas-WAG into the "Gullfaks" reservoir. Robust Machine learning models, including Multilayer Perceptron, Cascade Forward Neural Network (CFNN), Radial Basis Function, and Generalized Regression Neural Network, were employed as proxy models. The CFNN model, with satisfactory agreement with actual data (average absolute relative error of 0.4543 % for oil recovery factor (RF) and 1.9366 % for CO 2 storage), is selected for optimization through metaheuristic algorithms, including Non-dominated sorting genetic algorithm version II (NSGA-II), Pareto envelope-based selection Algorithm version-II (PESA_II), Multi-objective particle swarm optimization (MOPSO), and Multi-objective gray wolf optimization (MOGWO(. Among the optimization algorithms, MOGWO outperforms others in terms of speed and accuracy, yielding Pareto-optimal solutions with an RF of 0.8284 and a CO 2 storage of 1.5314 × 107 (kg-mol). The proposed approach uses Pareto dominance for insightful field development planning, enabling decision-makers to choose flue gas-WAG parameters based on future circumstances. [Display omitted] • A robust optimization framework is proposed for flue gas storage and enhanced oil recovery. • NSGA-II, MOPSO, MOGWO and PESA-II algorithms are utilized to optimize the water-alternating flue gas process. • CFNN, MLP, RBFNN, and GRNN are developed as proxy models that imitate the numerical simulator. • CFNN outperforms all developed models with AAPRE of 0.4543 % and 1.9633 % to estimate oil recovery factor and CO 2 storage, respectively. • The created Pareto fronts allow flexible applicability conditions to examine the design factors of the process. [ABSTRACT FROM AUTHOR]

This paper proposes a new Multi-Objective Mantis Search Algorithm (MOMSA) to handle complex optimization problems, including real-world engineering optimization problems. The Mantis Search Algorithm (MSA) is a recently reported nature-inspired metaheuristic algorithm, and it has been inspired by the unique hunting behavior and sexual cannibalism of praying mantises. The proposed MOMSA algorithm employs the same underlying MSA mechanisms for convergence combined with an elitist non-dominated sorting approach to estimate Pareto-optimal solutions. In addition, MOMSA employs the crowding distance mechanism to enhance the coverage of optimal solutions across all objectives. To validate its performance, we conduct 29 case studies, encompassing twenty multi-objective benchmark problems (ZDT, DTLZ, and CEC 2009) and nine engineering design problems. Furthermore, MOMSA is applied to the IEEE-30 bus system, addressing both single- and multi-objective optimal power flow problems across eight distinct cases. Results are compared with some state-of-the-art approaches using various performance metrics such as GD, MS, IGD, and HV. The findings demonstrate MOMSA's ability to effectively balance convergence, diversity, and uniformity, providing valuable insights for decision-makers addressing complex problems. The source code of MOMSA is publicly accessible at https://www.mathworks.com/matlabcentral/fileexchange/159623-momsa-multi-objective-mantis-search-algorithm. • MOMSA: A Novel Multi-Objective Optimization Algorithm. • Enhancing Engineering Design through MOMSA. • Pareto-Optimal Front Maintenance by MOMSA. • MOMSA in Complex Power System Optimization. • Comparative Analysis with Leading Methods. [ABSTRACT FROM AUTHOR]

• Microchannel heat sink with cavities and longitudinal vortex generators is proposed and evaluated based on three-dimensional numerical simulation. • The main effects of cavities and longitudinal vortex generators geometric parameters on thermal resistance and pumping power of the microchannel heat sink are studied. • The optimal results based on the primary geometric parameters are obtained by the multi-objective optimization algorithms. • The optimal solutions from 0.2594 K/W to 0.4176 K/W for thermal resistance and 0.0117 W to 0.047 W for pumping power, respectively. Microchannel heat sink (MCHS) is an innovative cooling device for high-powered integrated circuits. Cavities and longitudinal vortex generators (LVGs) are two kinds of effective heat transfer enhancement techniques for MCHS. It has been demonstrated that cavities can enhance the heat transfer but generate the dead zone of flow, while longitudinal vortex generators (LVGs) have the advantage of low pressure drop. In this paper, an integrated microchannel heat sink combing cavities and LVGs (MC-LVG-C) is proposed. The impacts of geometric parameters of cavities and LVGs on the thermal-hydraulic performance of proposed MCHSs are analyzed and evaluated by CFD when the Reynolds number (Re) ranges from 150 to 325. Further, the multi-objective configuration optimization based on Non-dominated Sorted Genetic Algorithm-II (NSGA-II) is performed at Re= 325 to minimize the thermal resistance and pumping power of MC-LVG-C simultaneously. It is found that the proposed scheme (MC-LVG-C) has clear superiority in the thermal-hydraulic performance over MCHS with cavities only (MC-C) and MCHS with LVGs only (MC-LVG). Geometric parameters analysis reveals that the height (h l) and length (L) of LVGs and the spacing (L 2) between LVGs and cavities have significant impact on the thermal-hydraulic performance. The NSGA-II optimization indicates that optimal thermal-hydraulic performance values for MC-LVG-C are divided into four design zones. For optimal solutions, better heat transfer can be obtained by increasing h l and L , while smaller resistance can be provided by increasing h l and L 2. In practical design, the reasonable geometric parameters can be chosen from the proposed four design zones by the design requirement. [ABSTRACT FROM AUTHOR]

Most previous studies on the scheduling problem in remanufacturing systems have focused on single or two production stages and economic criteria such as makespan or tardiness. However, environmental criteria like energy consumption or carbon emissions, as well as the lot-streaming production mode, have not been adequately addressed. This paper presents a novel approach to the energy-efficient remanufacturing system scheduling problem with lot-streaming production mode (ERSSP-LS) for the first time, which integrates disassembly, reprocessing, and reassembly three pivotal production stages. Firstly, a multi-objective mathematical model aimed at simultaneously minimizing the total energy consumption (TEC) and makespan (C max) is established and presented. To further reduce the TEC, the well-accepted energy-saving measure, known as the turn off and on strategy, is also integrated. Subsequently, a hybrid multi-objective optimization algorithm called HMOFFO, which combines the fruit fly optimization algorithm and simulated annealing mechanism is developed to seek the promising Pareto solution set. Finally, several experiments on a real-life case and a group of ten random test instances are carried out and the computational results affirm the feasibility and effectiveness of the proposed HMOFFO in solving the ERSSP-LS. [ABSTRACT FROM AUTHOR]

An unmanned metamorphic vehicle is a new deformable robot that can transform its configuration according to different road conditions in order to realize wheeled driving or legged walking. This paper proposes a method of multi-objective integrated optimization design based on the motion control of unmanned metamorphic vehicle. The aim of this method is to improve the stability and reduce energy consumption of multi-configuration motion. The vehicle state configuration and the humanoid state walking performance were designed. The kinematic model of reconfiguration and humanoid walking was established from screw theory, while the Lagrangian dynamics model for reconfiguration and humanoid walking using analytical mechanics. Reconfiguration and gait planning were carried out for an unmanned metamorphic vehicle, and a sliding mode controller was designed for position feedback control of the zero moment point in order to improve the stability of reconfiguration and walking. In order to improve the kinematic performance of an unmanned metamorphic vehicle under multiconfiguration, the NSGA-II intelligent optimization algorithm was used to optimize the multi-objective integrated design of the structural parameters, posture parameters, and control parameters of the sliding mode controller of the system. The simulation and test results showed that the integrated design performs higher reconfiguration stability, lower energy consumption, and higher control quality than the sequential design and pre-optimization under the reconfiguration condition; in the vehicle state, the transient steering stability and the steady-state steering stability of the system during driving are significantly improved; in the humanoid state, the energy consumption of the striding process and the movement of the center of mass to the single-legged support region in the walking process is reduced and the walking stability is improved, thus is more conducive to walking. [ABSTRACT FROM AUTHOR]

• The effect of different parameter changes on the objective functions are analyzed. • The energy-saving, economic, environmental, and exergy efficiency is optimized. • When the WHRB efficiency reaches 0.71, the cost of the CCHP system is the lowest. • The PECSR and CDERR of the CCHP system are improved by more than 24 % and 41 %. A distributed energy system integrated with solar and natural gas can achieve cascade energy utilization, high efficiency and energy-saving, and significantly reduce carbon emissions, which is receiving increasing attention. Therefore, this paper establishes an optimization model for primary energy consumption saving rate (PECSR), annual total cost saving rate (ATCSR), carbon dioxide emission reduction rate (CDERR) and exergy efficiency of micro-gas turbine coupled with low-concentrating photovoltaic/thermal (LCPV/T) CCHP system, and analyzes the influence of the parameters, such as solar irradiation, LCPV/T inlet temperature, LCPV/T inlet flow, LCPV/T area, low-temperature water source heat pump capacity, high-temperature water source heat pump capacity, the heat transfer efficiency of waste heat recovery boiler (WHRB) and gas boiler capacity, on the objective functions. The analysis results indicate that when the heat exchange efficiency of WHRB reaches 0.71, the CCHP system is most economical. Based on this, the Strength Pareto Evolutionary Algorithm-II (SPEA-II) optimization algorithm and decision-making method combining Technique for order preference by similarity to an ideal solution (TOPSIS) and weight entropy method are employed to solve the model comprehensively, and acquire the optimum solution. After multi-objective optimization and selection, the system exergy efficiency remains around 25 %. Compared with the separation production system, the PECSR and CDERR of the CCHP system are improved by more than 24 % and 41 %, respectively. [ABSTRACT FROM AUTHOR]