摘要
针对柴油机二级可调增压系统机理建模复杂的问题,提出一种基于混沌粒子群优化极限学习机(CPSO-ELM)的柴油机二级可调增压系统性能预测方法。采用混沌粒子群算法优化极限学习机权值和阈值,解决网络参数随机生成造成的预测精度低的问题。以某型六缸二级可调增压柴油机不同海拔性能试验数据建模,利用CPSO-ELM方法训练得到柴油机二级增压系统预测模型。仿真结果表明:相比标准ELM,该方法的预测精度提高20%以上,预测结果的平均绝对误差百分比为5.62%,均方根误差为0.42,其预测精度均优于反向传播神经网络(BPNN)和遗传算法优化极限学习机(GA-ELM)。
Aiming at the problem of complex mechanism modeling of diesel engine two-stage adjustable turbocharging system,a performance prediction method based on chaotic particle swarm optimization extreme learning machine(CPSO-ELM)is proposed.The chaotic particle swarm algorithm is used to optimize the weight and thresholds of the extreme learning machine to solve the problem of low prediction accuracy caused by the random generation of network parameters.Taking the performance test data of six-cylinder two-stage adjustable turbocharged diesel engine at different altitudes as the modeling data,the prediction model of the two-stage turbocharging system is obtained by using CPSO-ELM method.The simulation results show that,compared with the standard ELM,the prediction accuracy of the CPSO-ELM method is improved by more than 20%,and the average absolute error percentage(MAPE)and root mean square error(RMSE)of the prediction results are 5.62%and 0.42 respectively.Meanwhile,the prediction accuracy is better than that of backpropagation neural network(BPNN)and the genetic algorithm optimization limit learning machine(GA-ELM).
作者
丁豪坚
刘瑞林
张众杰
杨春浩
王刚
DING Haojian;LIU Ruilin;ZHANG Zhongjie;YANG Chunhao;WANG Gang(Fifth Team of Cadets,Army Military Transportation University,Tianjin 300161,China;Military Vehicle Engineering Department,Army Military Transportation University,Tianjin 300161,China;Naval University of Engineering,Wuhan 430033,China)
出处
《军事交通学院学报》
2020年第12期30-35,共6页
Journal of Military Transportation University
基金
军队科研项目.
关键词
柴油机
二级可调增压系统
混沌粒子群
极限学习机
遗传算法
diesel engine
two-stage adjustable turbocharging system
chaotic particle swarm
extreme learning machine
genetic algorithm
