Narrow Results

Support vector machine is a very classical and popular model for data prediction. Traditional support vector machines use grid search to determine its parameters. In order to improve the accuracy of prediction, more and more frameworks are proposed. Among them, the combination of support vector machine and intelligent optimization algorithm is the most commonly used solution at present. The optimization objective is to determine the optimal penalty factor and kernel parameters of support vector machine to improve the prediction performance. In this paper, 10 intelligent optimization algorithms that are widely used at present are used for the optimization research of support vector machine. The performance of these optimization algorithms in support vector machine parameter optimization is analyzed in detail. Short-term wind speed and network traffic are chosen as the research object, and detailed performance indicators are given to judge the advantages and disadvantages of these intelligent optimization algorithms in optimizing support vector machine performance. Finally, the performance indicators, optimization speed, running memory usage, optimization success rate of different optimized SVM models, and impact of data distribution are analyzed in detail, and some conclusions are drawn. For the parameters optimization of support vector machine, various indicators are comprehensively considered, grey wolf optimizer algorithm and squirrel search algorithm are recommended.

Laser texturing assisted with electrochemical machining (LT-ECM) is combined the high efficiency of laser machining and the high surface quality of electrochemical machining. The light-trapping structures are mainly formed by laser action and the slag produced in laser texturing is removed by electrochemical machining. In order to obtain the better textured quality, parameters optimization for LT-ECM has been carried out in this paper. Three important parameters such as pulse laser energy and applied electrochemical have been optimized to improve the optical property of mc-Si. The textured surface reflectance (TSR) and the slag removal rate (SRR) have been used as the evaluation indicators to evaluate the textured results on mc-Si by LT-ECM. The experiments were performed on 30×30mm² mc-Si wafer with pulsed Nd:YAG laser at second harmonic wavelength and NaOH solution. The experimental results showed that pulse laser energy has the most significant influence on TSR. Applied electrochemical voltage has significant influence on SRR. Optimized parameters for LT-ECM are: pulse laser energy is about 30mJ; electrochemical applied voltage is about 15V.

In order to acquire the most energy-saving luminaire installation parameters (LIPs) of highway tunnel interior zone, a parameters optimization model (POM) of symmetric luminaire distribution (SLD) lighting for tunnel interior zone was established. It includes luminaire installation height, longitudinal installation spacing, crosswise installation spacing, elevation angle and power as optimization parameters, and with minimum total power of the SLD lighting system as objective function. Yanlieshan tunnel of Jiujing highway was used as an example for the optimization. The optimal LIPs of the SLD lighting system of tunnel interior zone were obtained by the POM. A comparison between the optimization results and that of Yanlieshan tunnel lighting system is performed, which demonstrates that the optimized SLD lighting system with LED lamps installed according to the optimized LIPs has remarkable energy-saving effect even under full capacity lighting condition. Illuminance and illuminance uniformity of the tunnel road surface still meet the traffic lighting requirements. Even the LED lamps’ luminance decreases by 30%. A SLD lighting simulation experiment with the optimized SLD lighting LIPs for Yanlieshan tunnel was carried out by the software Dialux. The simulation results primarily agree with the optimization calculated results from the POM, which proves the correctness of the SLD lighting POM.

Taking an electric vehicle as the research object, based on the MATLAB established the pure electric vehicle power system components and vehicle simulation model. The transmission parameters as the optimized goal, in ISIGHT, the response surface method is used to construct the design variables and the optimized target approximation model. The genetic algorithm is used to optimize the parameters of the powertrain of the vehicle. Analysis and comparison of the dynamic performance and economic simulation of the vehicle before and after optimization. The results show that under the condition of satisfying the vehicle dynamic design target, the optimization of the vehicle driving range increased by 20.1% in the NEDC driving conditions.