Search

Aiming at the problem of solving nonlinear equilibrium points of automobile steering, the solving effect of the genetic algorithm was studied and an improved method was proposed. A two-degree-of-freedom model of automobile steering was established, and the reason why the nonlinear equilibrium points of automobile steering can only be solved by numerical iteration was explained, a fitness function suitable for the intelligent optimization method was constructed, and a method to determine the feasible solution range was proposed. Under the driving conditions of a vehicle speed of 70km/h, road adhesion coefficient of 0.5 and a front wheel angle of 0~0.2rad, three equilibrium points were solved by using genetic algorithm. By comparing the fitness value surfaces of large and small steering angles, the reason why the genetic algorithm can not meet the solving accuracy of small steering angle equilibrium point was explained, and the solution flow of the fusing genetic algorithm and BFGS quasi-Newton method was presented. The results show that the proposed fusion solution process can solve the small steering angle equilibrium points that meet the solving accuracy requirements and have higher solving efficiency, which makes up for the shortage of the genetic algorithm solving alone. [ABSTRACT FROM AUTHOR]

CAN( controller area network) bus is the most widely used field bus. Due to the lack of authentication and message checking mechanism, CAN bus has great security risks, so it is necessary to design a defense mechanism for CAN bus. In this paper, a priority hopping mechanism is designed, which introduces the dynamic hopping of identifiers by Hash function into a real-time scheduling algorithm. The fixed priority is calculated by a genetic algorithm, and the compromise range of priority is found out. Each frame is grouped, and the ID segment of data frame is segmented and reconstructed. The former part of the ID segment determines the priority and performs priority hopping, while the latter part of the ID segment hops dynamically at one time. Experimental results show that using dynamic priority and one-time ID Hopping to hop has a greater security improvement than the existing ID Hopping mechanism. [ABSTRACT FROM AUTHOR]

In order to improve the travel service quality of conventional bus, an optimization model of buses’ flexible departure intervals considering crowdedness state in the bus is established. By quantifying the crowdedness state in the bus, the travel cost under each crowdedness state is given, and the crowdedness state transfer function of each section of the line is established. Considering passengers’ perception of the crowdedness state in the bus, the measurement model of the number of passengers getting on and off the bus over time is established;the travel cost measurement model is established, and the optimization model of buses’ flexible departure intervals is established with the objective function of minimizing the sum of passenger travel cost and vehicle operating loss;and the genetic algorithm is designed to solve the model. The results show that the optimization model can effectively reduce the travel cost.The model has a"short board filling"effect on the waiting cost, and a"peak cutting"effect on the travel cost. That is, by increasing the waiting cost of the stop with fewer passenger arrivals, reducing the waiting cost of the stop with more passenger arrivals and weakening the peak value of the travel cost, the total cost can be minimized. [ABSTRACT FROM AUTHOR]

Due to the high dynamics and limited resources of space network， its reliability is faced with severely tested， and a reasonable risk assessment and performance recovery plan was urgently needed. For the elastic recovery strategy of spatial information network， the repair order of damaged components was determined by the recovery strategy based on the improved genetic algorithm， so as to speed up the elastic recovery. The network topology control method was adopted to reduce the importance of damaged key nodes and the loss of network elasticity. The experiment simulates the loss of network resilience with different recovery strategies under different amounts of recovery resources. The results show that the two schemes have better recovery performances when recovery resources are limited and scarce. [ABSTRACT FROM AUTHOR]

In view of the problems that genetic algorithm (GA) has slow convergence speed， be easy to fall into local optimum and difficult to realize online application， and that the identification background of power battery equivalent circuit model is with strong nonlinearity and high real-time requirements. An optimized identification framework is proposed that can quickly reduce the search space and effectively avoid falling into the local optimum for online fast search， thus realizing the online fast identification of the parameters of the equivalent circuit model of the electric vehicle power battery， and expanding the application range of the global search optimization algorithm. Further， the proposed algorithm is applied to the state of charge (SOC) estimation， based on the improved GA unscented partical filter (IGA-UPF) is proposed. The SOC estimation method is compared with the SOC estimation method based on least square-unscented partical filter (LS-UPF)， which proves that the online fast parameter identification framework proposed has better model parameter identification accuracy. [ABSTRACT FROM AUTHOR]

Ａ ｂｉｇ ｄａｔａ ｂａｓｅｄ ３Ｄ ｍａｐ ｒｅｃｏｎｓｔｒｕｃｔｉｏｎ ｍｅｔｈｏｄ ｗａｓ ｐｒｅｓｅｎｔｅｄ ｂａｓｅｄ ｏｎ ｍｕｌｔｉｐｌｅ ｖｅｈｉｃｌｅｓ ｄａｔａ. Ｏｎ ｉｎｄｉｖｉｄｕａｌ ｖｅｈｉｃｌｅ ｓｉｔｅꎬ ｉｎ ｔｈｅ ｐｒｏｐｏｓｅｄ ａｌｇｏｒｉｔｈｍꎬ ｔｈｅ ｌｅａｓｔ ｓｑｕａｒｅ ｍｅｔｈｏｄ ａｎｄ Ｋａｌｍａｎ ｆｉｌｔｅｒ ｗｅｒｅ ｕｓｅｄꎬ ａｎｄ ｔｈｅ ｒｅｆｉｎｅｄ ｖｅｈｉｃｌｅ ｉｎｓｔａｎｔ ３Ｄ ｐｏｓｉｔｉｏｎ ｗａｓ ｕｐｌｏａｄｅｄ ｔｏ ｔｈｅ ｓｅｒｖｅｒ. Ｔｈｅ ｏｒｉｇｉｎａｌ ＧＰＳ ｓｉｇｎａｌ ｅｒｒｏｒ ｗａｓ ｒｅｄｕｃｅｄ ｂｙ ｏｖｅｒ ５０％ . Ｎｅｘｔꎬ ｇｅｎｅｔｉｃ ａｌｇｏｒｉｔｈｍ ｗａｓ ｕｓｅｄ ｉｎｓｔｅａｄ ｏｆ Ｋａｌｍａｎ ｆｉｌｔｅｒꎬ ｒｅｓｕｌｔｉｎｇ ｉｎ ｔｈｅ ｅｒｒｏｒ ｂｅｉｎｇ ｆｕｒｔｈｅｒ ｒｅｄｕｃｅｄ ｂｙ ｏｖｅｒ １６％ . Ｏｎ ｔｈｅ ｓｅｒｖｅｒ ｓｉｔｅꎬ ａ ３Ｄ ｒｏａｄ ｓｕｒｆａｃｅ ｐｏｉｎｔ ｃｌｏｕｄ ｄａｔａｂａｓｅ ｗａｓ ｇｅｎｅｒａｔｅｄ ｂａｓｅｄ ｏｎ ｔｈｅ ｄａｔａ ｆｒｏｍ ｍｕｌｔｉｐｌｅ ｖｅｈｉｃｌｅｓ. Ｋ-ｍｅａｎｓ ｍｅｔｈｏｄ ｗａｓ ｕｓｅｄ ａｓ ｔｈｅ ｄａｔａ ｍｉｎｉｎｇ ｓｔｒａｔｅｇｙ ｔｏ ｓｅａｒｃｈ ｆｏｒ ｔｈｅ ｌａｎｅ ｃｅｎｔｅｒｓ ｆｒｏｍ ｒｏａｄｓ ｗｉｔｈ ｍｕｌｔｉｐｌｅ ｌａｎｅｓ. Ｔｈｅ ｒｅｃｏｎｓｔｒｕｃｔｅｄ ｍａｐ ｃａｎ ｂｅ ｕｓｅｄ ｂｙ ｅｖｅｒｙ ｏｎｌｉｎｅ ｖｅｈｉｃｌｅｓ ｔｈａｔ ｓｕｐｐｏｒｔ ｔｈｅ ｒｅｌｅｖａｎｔ ｒｅｓｅａｒｃｈｅｓ ｆｏｒ ｔｈｅ ｏｐｔｉｍｕｍ ｄｒｉｖｉｎｇ ｓｔｒａｔｅｇｙ. [ABSTRACT FROM AUTHOR]

Ａｎ ｅｆｆｅｃｔｉｖｅ ｅｓｔｉｍａｔｉｏｎ ｍｅｔｈｏｄ ｆｏｒ ｏｎｌｉｎｅ ｏｐｅｒａｔｉｏｎ ｏｆ ｅｌｅｃｔｒｉｃ ｖｅｈｉｃｌｅ ｐｏｗｅｒ ｂａｔｔｅｒｙ ＳＯＨ ｗａｓ ｐｒｏｐｏｓｅｄ. Ｔｈｅ ａｄｖａｎｔａｇｅ ｉｓ ｔｈａｔ ｉｔ ｏｎｌｙ ｒｅｌｉｅｓ ｏｎ ｔｈｅ ｖｏｌｔａｇｅ ａｎｄ ｃｕｒｒｅｎｔ ｄａｔａ ｍｅａｓｕｒｅｄ ｂｙ ｔｈｅ ｂａｔｔｅｒｙ ｍａｎａｇｅｍｅｎｔ ｓｙｓｔｅｍ ｉｎ ｒｅａｌ ｔｉｍｅ, ｗｉｔｈｏｕｔ ｔｈｅ ｎｅｅｄ ｏｆ ｏｆｆｌｉｎｅ ｂａｔｔｅｒｙ ｌｉｆｅ ｄｅｃａｙ ｃｕｒｖｅ ａｎｄ ｔｈｅ ｉｎｉｔｉａｌ ｓｔａｔｅ ｏｆ ｔｈｅ ｂａｔｔｅｒｙ. Ｔｈｅｒｅｆｏｒｅ, ｉｔ ｉｓ ｍｏｒｅ ｉｎ ｌｉｎｅ ｗｉｔｈ ｔｈｅ ａｃｔｕａｌ ｎｅｅｄｓ ｏｆ ｅｌｅｃｔｒｉｃ ｖｅｈｉｃｌｅｓ ｆｏｒ ＳＯＨ ｅｓｔｉｍａｔｉｏｎ. Ｂａｓｅｄ ｏｎ ｔｈｅ Ｔｈｅｖｅｎｉｎ ａｎｄ ＯＣＶ-ＳＯＣ ｍｏｄｅｌｓ, ａ ｂａｔｔｅｒｙ ｍｏｄｅｌ ｗｉｔｈ ｔｉｍｅ ａｎｄ ＳＯＨ ａｓ ｈｉｄｄｅｎ ｖａｒｉａｂｌｅｓ ｗａｓ ｃｏｎｓｔｒｕｃｔｅｄ ｉｎ ｔｈｅ ｂａｔｔｅｒｙ ｃｏｎｓｔａｎｔ-ｃｕｒｒｅｎｔ ｃｈａｒｇｉｎｇ ｍｏｄｅ. Ｂａｓｅｄ ｏｎ ｔｈｉｓ ｂａｔｔｅｒｙ ｍｏｄｅｌ, ａ ｆａｓｔ ｓｏｌｖｉｎｇ ａｌｇｏｒｉｔｈｍ ｂａｓｅｄ ｏｎ ＮＬＳ (ｎｏｎｌｉｎｅａｒ ｌｅａｓｔ ｓｑｕａｒｅ) ｉｎｉｔｉａｌｉｚａｔｉｏｎ ＧＡ ｓｅａｒｃｈ ｒａｎｇｅ ｗａｓ ｐｒｏｐｏｓｅｄ ｆｏｒ ｏｎｌｉｎｅ ｐａｒａｍｅｔｅｒ ｉｄｅｎｔｉｆｉｃａｔｉｏｎ, ａｎｄ ｔｈｅ ｒｅａｌ-ｔｉｍｅ ＳＯＨ ｅｓｔｉｍａｔｉｏｎ ｖａｌｕｅ ｏｆ ｅｌｅｃｔｒｉｃ ｖｅｈｉｃｌｅ ｗａｓ ｏｂｔａｉｎｅｄ. Ｔｈｅ ｖｅｒｉｆｉｃａｔｉｏｎ ｒｅｓｕｌｔｓ ｓｈｏｗｅｄ ｔｈａｔ ｔｈｅ ＳＯＨ ｅｓｔｉｍａｔｉｏｎ ａｌｇｏｒｉｔｈｍ ｈａｓ ｇｏｏｄ ｐｒａｃｔｉｃａｂｉｌｉｔｙ ａｎｄ ｈｉｇｈ ｅｓｔｉｍａｔｉｏｎ ａｃｃｕｒａｃｙ [ABSTRACT FROM AUTHOR]

Ｎｕｍｅｒｉｃａｌ ｓｉｍｕｌａｔｉｏｎ ａｎｄ ｎｅｕｒａｌ ｎｅｔｗｏｒｋ ｔｅｃｈｎｏｌｏｇｙ ｗｅｒｅ ｕｓｅｄ ｆｏｒ ｔｈｅ ｂｌａｎｋ ｈｏｌｄｅｒ ｆｏｒｃｅ(ＢＨＦ) ｐｒｅｄｉｃｔｉｏｎ ｏｆ ｔａｉｌｏｒ ｗｅｌｄｅｄ ｂｌａｎｋ(ＴＷＢ) ｂｏｘ ｐａｒｔ ｉｎ ｄｅｅｐ ｄｒａｗｉｎｇ. Ｔｈｅ ｉｎｆｌｕｅｎｃｅ ｏｆ ＢＨＦ ｌｏａｄｉｎｇ ｔｙｐｅ ｏｎ ｔｈｅ ｆｏｒｍａｂｉｌｉｔｙ ｏｆ ＴＷＢ ｂｏｘ ｐａｒｔ ｗａｓ ａｎａｌｙｚｅｄ ｂｙ ｎｕｍｅｒｉｃａｌ ｓｉｍｕｌａｔｉｏｎꎬ ａｎｄ ａ ｐｒｅｆｅｒａｂｌｅ ＢＨＦ ｌｏａｄｉｎｇ ｔｙｐｅ ｗａｓ ｏｂｔａｉｎｅｄ. Ｔｈｅｎ ＢＰ ｎｅｕｒａｌ ｎｅｔｗｏｒｋ ｍｏｄｅｌ ｓｕｉｔａｂｌｅ ｆｏｒ ＢＨＦ ｐｒｅｄｉｃｔｉｏｎ ｗａｓ ｄｅｖｅｌｏｐｅｄ. Ａｔ ｌａｓｔꎬ ｔｈｅ ｎｅｕｒａｌ ｎｅｔｗｏｒｋ ｍｏｄｅｌ ｗａｓ ｏｐｔｉｍｉｚｅｄ ｂｙ ｔｈｅ ｇｅｎｅｔｉｃ ａｌｇｏｒｉｔｈｍ. Ｔｈｅ ｅｌｉｔｉｓｍ ｓｔｒａｔｅｇｙ ｗａｓ ｉｎｔｒｏｄｕｃｅｄ ｉｎｔｏ ｔｈｅ ｃｏｕｒｓｅ ｏｆ ｇｅｎｅ ｓｅｌｅｃｔｉｏｎꎬ ａｎｄ ｆｉｎａｌｌｙ ａｎ ｉｄｅａｌ ＢＨＦ ｃｕｒｖｅ ｗａｓ ｏｂｔａｉｎｅｄ ｂｙ ｔｈｅ ｎｅｕｒａｌ ｎｅｔｗｏｒｋ ｍｏｄｅｌ ｏｐｔｉｍｉｚｅｄ ｂｙ ｔｈｅ ｇｅｎｅｔｉｃ ａｌｇｏｒｉｔｈｍꎬ ｗｈｉｃｈ ｃａｎ ｐｒｅｄｉｃｔ ＢＨＦ ｖａｌｕｅ ｖａｒｙｉｎｇ ｉｎ ｄｅｅｐ ｄｒａｗｉｎｇ ｐｒｏｃｅｓｓ ａｎｄ ｃａｎ ｌａｙ ｔｈｅ ｔｅｃｈｎｉｃａｌ ｆｏｕｎｄａｔｉｏｎ ｆｏｒ ｉｎｔｅｌｌｉｇｅｎｔ ｓｔａｍｐｉｎｇ. [ABSTRACT FROM AUTHOR]

A hybrid cycle algorithm was proposed aiming at solving the problems that single algorithm cannot realize intelligent assembly sequence planning of complex assembly and the lack of deep human-computer interaction causes poor improvement effects. This algorithm， based on genetic algorithm， uses interference matrix and contact matrix to adjust random assembly sequence and constructs fitness function on the basis of the uniformity of assembly direction and tool. In addition， combining with simulated annealing algorithm， adding annealing operation and using Metropolis criterion， individual sequences were obtained and accepted by crossover and mutation. Meanwhile， by introducing particle swarm optimization， optimal sequence of individuals and groups were selected to cross with the offspring directly. Finally， assembly simulation platform combined with virtual reality were built and the sequence was optimized from the two dimensions of assembly stability and tool operation space. In conclusion， taking automobile rear axle assembly as an example， it is shown that the assembly sequence obtained fits actual production and the method is effective and practical. [ABSTRACT FROM AUTHOR]

Based on the nonlinear energy sink (NES) model with piecewise linear stiffness previously proposed by the authors， the optimization problem of the NESs is studied by means of genetic algorithm (GA). Firstly， the NES with piecewise linear stiffness is introduced， and its nonlinear characteristic is analyzed. Then， the spatial dimension of optimum design is reduced by adopting the endpoint connection fitting for cubic polynomial， and the optimization method is presented with mixed binary and real coding. Finally， the optimization of the NESs in multi-degree freedom system is carried out by taking the frame-shear structure-NESs system as an example， and its effectiveness is verified by experiments. The results show that the optimized NESs can effectively suppress vibration at a wider excitation frequency and meanwhile obtain a better multi-modal vibration suppression effect. [ABSTRACT FROM AUTHOR]

Sunshine has played a critical role in trajectory analysis. It is of great significance to design an algorithm that could not only estimate the sunshine information of the trajectory effectively, but also remove the redundant points and keep the necessary sunshine-based information. This paper proposes a sunshine based trajectory simplification algorithm, which considers the urban trajectory character, to solve the challenges of trajectory analyzing in various sunshine related scenarios. On the one hand, an orientation model is established to abstract the relationship between trajectory and sunlight. On the other hand, a sunshine related trajectory simplification model is proposed, and the genetic algorithm is applied to find the points that need to be reserved. Finally, the real-world data of Minneapolis, US, is used for experiment. The results demonstrate that the proposed algorithm can effectively reduce the number of turning points in the trajectories under the control of bound Tmax. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the process of cross and mutation in traditional genetic algorithm is too cumbersome， and the extreme value judgment and the convergence rate is limited， a parallel quantum genetic algorithm(QGA) is proposed to optimize the weights of the neural network. The concept of quantum computing is firstly introduced. In the process of quantum computation， the quantum rotation gate is used to train the chromosomes. Then the quantum cross is introduced to overcome the precocious convergence and to avoid the cumbersome cross and mutation process in the genetic algorithm. Finally， the parallel convolution neural network is designed and implemented. The parallel quantum genetic algorithm is used to optimize the weights of the convolution neural network， and a facial recognition system based on parallel quantum genetic neural network is realized. Experimental results show that compared with the original genetic algorithm， the quantum genetic neural network algorithm has obvious improvements in terms of robustness and processing speed. [ABSTRACT FROM AUTHOR]

Based on the principle of heat transfer， a parametric model of thermal structure of blast furnace(BF)bosh with shaped tube copper cooling stave(ellipse， rectangle， double circle， three circle and hexagon)for heat transfer is presented. From the heat transfer analysis of copper cooling stave， the optimal choice of cooling water tubes is achieved. Stimulating the normal working condition of BF， the coupled thermal and structural analysis of the model at the initial stage of furnace opening， with the hot and cast-in-brick surface of cooling stave not covered by slag， is conducted to obtain the mutual influencing rules between parameters and its mechanical properties. The response surface method combined with genetic algorithm(NSGA-Ⅱ)is applied to optimize the structural parameters and longevity technology of bosh. The optimized bosh structure has been significantly improved in heat transfer characteristics and mechanical properties. The model and the parametric calculation program can be applied to assess and optimize the design of longevity technology of bosh. [ABSTRACT FROM AUTHOR]

Based on the panel data of China’s capital market， the financial fraud companies from 2006 to 2015， together with the same number of non-fraud companies were selected as the research samples. Twenty-seven financial and non-financial indexes were analyzed， after which the dimension of the indexes was reduced through the test of independence and eight indexes were retained as the modeling parameters. The grid search algorithm， genetic algorithm and particle swarm optimization(PSO)were used respectively to optimize the parameters， and three support vector machine(SVM)models with the parameters optimized by the proposed methods were established respectively for financial fraud detection. The results showed that the SVM model with the parameters optimized by PSO has a higher detection rate than the other two models. [ABSTRACT FROM AUTHOR]

A customer churn prediction model based on BP neural network(BPNN)has achieved well enough results. However， it has relatively weak global search ability and is very sensitive to the initial network weights. A prediction algorithm based on improved genetic algorithm(IGA)and BPNN(IGA-BP)is proposed by analyzing users’communication behavior， where the weights and thresholds of BPNN are initialized with IGA， thus improving the accuracy of the prediction model. The improved algorithm adopts a self-adapting probability of crossover and mutation， which enhances the global optimum search ability of GA. The proposed IGA-BP model has obvious improvement on customer churn prediction， compared with existing algorithms. [ABSTRACT FROM AUTHOR]

Focusing on the optimization problem of schedule risk control in information technology(IT)outsourcing project， a two-level hybrid genetic algorithm(TLHGA)is proposed. The TLHGA incorporates simulated annealing， adaptive mechanism and the two-level feature of optimization problem to improve the traditional genetic algorithm(TGA)， which could overcome the shortcomings of TGA such as early mature and weak local searching ability. In the experimental analyses， the management meanings of the two-level mathematical model in IT outsourcing schedule risk control is analyzed. Next， the simulation results of TLHGA are compared with the TGA and two-level particle swarm optimization algorithm， which verifies the rationality and effectiveness of the improved algorithm. [ABSTRACT FROM AUTHOR]

In viewof the drawbacks of the traditional bending force preset model and the characteristics of hot strip rolling, a bending force prediction model is built based on genetic algorithm(GA) and artificial neural network(ANN) and the prediction is carried out on the end stand of finishing mill using a large amount of production data from 1 580 mm hot rolling line in a steel corp. The features of the model are as follows: a large number of actual data is used as input for the ANN training, the influence of various input parameters are fully considered, the framework of the model is relatively simple and easy to implement, and the overall performance is evaluated by the mean absolute percentage error, root mean square error and correlation coefficient. By comparing the predicted results with the experimental ones, the prediction accuracy of the model is verified. It shows that the GA-ANN prediction model of roll bending force can realize a high nonlinear fitting, which is suitable for improving the accuracy to control head shape of hot strip rolling. This study provides guidance and test foundation for the actual bending force setting. [ABSTRACT FROM AUTHOR]

An intelligent method is proposed to complete the contact fatigue reliability analysis of aviation bearings. The temperature field is approximated using quadratic polynomial with intercrossing term， and the stress model under thermal elastohydrodynamic lubrication (EHL) is set up. Considering the randomness of the thermal EHL， material properties and fatigue strength correction factors， the probabilistic reliability analysis model is established using artificial neural network (ANN)， and the reliability sensitivity analysis is completed based on the advanced first order second moment (AFOSM). The numerical example shows that the established probabilistic reliability analysis model could correctly reflect the effect of the thermal EHL on contact fatigue of aviation bearings， and the proposed intelligent method has an excellent global search capability as well as a highly efficient computing performance compared with the traditional Monte Carlo method， and then the results are verified with the fatigue life test of rolling bearings considering the non-interacting variance analysis. [ABSTRACT FROM AUTHOR]

The paper proposed a research model based on the CSM model， which was deduced by Colorado School of Mines， to minimize the unbalanced radial force and overturning moment. The model followed the principle of cutterhead minimum specific energy and utilized the normal genetic algorithm to optimize the spacing of the center cutters， the normal cutters and the gage cutters， and in turn， to improve the polar angle of the normal cutters and the gage cutters. Taking the TB880E cutterhead as an object， the research revealed that when the cutter spacing of center cutters and the normal cutters have been improved， the specific energy can be reduced by about 1.53%. Similarly， when the tilt angles of the gage cutters have been optimized， the specific energy can be reduced by about 1.10%. When the polar angles of the normal cutters and the gage cutters have been improved， the unbalanced radial force can be reduced to 0.1265 N， and the overturning moment can be reduced to 0.7591 N/m， which may decrease the deformation of the cutterhead. The present research can be applied in the optimization design of the locations of the disc cutters on the cutterhead and in the prediction of the energy consumption of rock fragmentation process， which can reduce the energy of the rock fragmentation and improve the boring efficiency. [ABSTRACT FROM AUTHOR]

The cutting process parameters of dicing saw are difficult to get in actual production， an optimization method was thus proposed to establish the best cutting parameters based on genetic algorithm of Matlab. The scope of the cutting process parameters was selected by avoiding the natural frequency of every order， and the root mean square of the axis vibration was used as the evaluation index. The regression equation was established between parameters of vibration and cutting processes by regression orthogonal design. The best cutting parameters according to the minimum vibration were obtained by using the Matlab genetic algorithm to make iterative optimization for the regression equation. The optimization result was verified by experiments. [ABSTRACT FROM AUTHOR]

A new map matching algorithm was proposed on the basis of the hidden Markov model and the genetic algorithm. Firstly， the HMM probability matrix was initialized. Then， the parameters were learned by using the forward-backward algorithm， and a set of road sections was predicted by using the Viterbi algorithm. Finally， taking section sequence as population， the optimal section sequence was obtained by using the genetic algorithm. By using the taxi GPS data from Beijing in 2012 to test the traditional algorithm based on hidden Markov model and the proposed algorithm， the results showed that the traditional algorithm based on hidden Markov model has a matching accuracy below 90% and the proposed algorithm has a matching accuracy above 90%. [ABSTRACT FROM AUTHOR]

Aiming at the limitation of disperse exclusive lane locating, a two level optimization model was presented for the location of the continuous exclusive bus lane based on public transit corridor. Realistic conditions, planning and construction practice of exclusive bus lanes locations were explicitly taken into account in the proposed model. The upper-level of the proposed model was the locating model to minimize the total travel time of the whole road network, and the lower-level was the allocation model of car and bus to minimize the generalized travel cost. The genetic algorithm based on the method of successive averages was developed to solve the problem. The test of the effectiveness and practicability of the model and the sensitivity analysis of the key parameters were carried out through a case study, and the continuous exclusive bus lane locations have more superiority than discrete exclusive bus lane locations. [ABSTRACT FROM AUTHOR]

Quantitative structure-activity relationships (QSAR) of 13 kinds of hydroximic acid collectors were studied to predict the flotation selectivity of cassiterite flotation separation based on genetic algorithm. Using fast descriptor and quantum chemical descriptor, two kinds of two-parameter models were developed, i. e., Model 5 for selectivity index 1 and Model 6 for selectivity index 2 . The correlative coefficients of Model 5 and Model 6 were 0. 868 and 0. 796 , with R2cv of 0. 779 and 0. 590,respectively. For the two models,internal reliability was validated using the leave-one-out approach, with R2 =0. 785 for Model 5 and R2 =0. 615 for Model 6, and an external validation was also performed using test sets and the mean absolute deviations were 0. 137 and 1. 939, respectively. The results show that Model 5 for selectivity index 1 has better predictability, and can effectively predict flotation selectivity of hydroximic acid collectors. [ABSTRACT FROM AUTHOR]

In order to get the optimum parameters of flocculating sedimentation， back propagation neural network and genetic algorithm were applied to establish the flocculation sedimentation parameters prediction model of the crude tailings. The flocculating agent and tailings concentration consumption were used as the input data and the sedimentation speed was confirmed to be the output data. The learning and training samples were received by the orthogonal experiments to build neural network prediction model. Then， the optimum parameters of flocculating sedimentation were received after using genetic algorithm finding optimal in parameters prediction model of the crude tailings. The selected parameters prediction model was used in Hemushan iron mine. The results showed that the flocculating agent consumption is 12g/t and tailings concentration is 17%， the sedimentation speed is 1.31m/h， these parameters meet the production requirements. The flocculating agent consumption required is 20% less than the original production when using these flocculating sedimentation parameters. The application of the model indicates that it provides a new method to optimize the flocculating sedimentation parameters with a good effect. [ABSTRACT FROM AUTHOR]

With respect to consecutive drainage， aggressive internal conditions and varying lining profile during production process in blast furnace hearth， a simple method is proposed for representing the lining profile by a set of lining profile vectors. It can convert the solving of a complicated inverse heat transfer problem with unknown geometries at a specified-temperature boundary into searching the optimal set of profile vectors in an optimization problem. Integrating numerical heat transfer theory and finite element method with genetic algorithm， an inverse problem oriented mathematical model has been developed， which can predict the lining profile of blast furnace hearth accurately. A testing example of elephant-foot erosion pattern on the basis of an intact ceramic cup synthetic hearth， is employed to examine the effectiveness， stability and accuracy of the model. The results indicate that the model would have a broad prospect of practical applications. [ABSTRACT FROM AUTHOR]

In order to achieve a set of nondominated solutions for multiobjective optimization problems quickly and accurately， a Species-based genetic algorithm for multiobjecitve optimization problems was proposed. Firstly， a certain number of subproblems were developed with the Tchebycheff approach. Then multiple subpopulations were constructed based on the Species mechanism to solve all the subproblems simultaneously， which can improve the exploration and exploitation ability by using multiple individuals to search one optimal solution. Finally， a set of benchmark multiobjective functions were examined， and the experimental results showed that the proposed algorithm can obtain a certain number of nondominated solutions quickly and accurately. [ABSTRACT FROM AUTHOR]

The changing trend of surface hardness with process parameters was analyzed， and the surface hardness was tested by grinding low expansion glass in quick-point. Based on BP neural network and single factor tests in quick-point grinding， a series of one-dimensional models were built for surface hardness and process parameters by the least-squares fitting. The accuracy of the model was tested by coefficient of correlation. The results show that the model has high accuracy. The multivariate models about surface hardness and process parameters were proposed after analyzing one-dimensional models. Based on the genetic algorithm， the multivariate numerical models were built for surface hardness according to the results of orthogonal experiments. The accuracy of multivariate model was tested by the verification experiment. The test results indicate that the model has high accuracy. [ABSTRACT FROM AUTHOR]

In view of helical drill point grinding， the theoretical and experimental bases for grinding the required geometrical parameters of helical drill points are presented in this paper based on the optimization of biglide parallel machine grinding parameters. A method of grinding the involute helical surface based on the biglide parallel machine is introduced， and then the mathematical model is derived for the helical drill flank. Moreover， the relationship between the geometric parameters and grinding parameters is analyzed， and the optimal grinding parameters are acquired based on genetic algorithm. The results showed that the optimized grinding parameters improve the grinding precision with the experiment on the biglide parallel machine， and the biglide parallel machine can satisfy clients' demands of drill grinding. [ABSTRACT FROM AUTHOR]

For the problem of the lack of guiding principle of production schedule in the case of non-full production in steelmaking plant， the optimization method of production schedule based on ladle running stability was proposed. First， the computational method of the number of online operation ladle was proposed by analyzing ladle turnaround process. Second， the impact of production schedule on ladle running was analyzed for the production schedule of single casting machine and two casting machine， and the computational model was proposed. Finally， the method was used to optimize actual production schedule of a steelmaking plant. The results showed that using genetic algorithm based on ladle running stability， the fluctuation of the number of ladle is reduced， the fluctuation of ladle thermal state is reduced， baking gas is saved， the temperature of BOF endpoint is reduced and the level of control the temperature of molten steel is improved. [ABSTRACT FROM AUTHOR]