基于BPNN和MOOGA的高速联轴器多目标优化方法  

Multi-objective optimization of high-speed coupling based on BPNN and MOOGA

作　　者：王艺琳 王维民[1,2,3] 李维博 王珈乐 张帅 WANG Yilin;WANG Weimin;LI Weibo;WANG Jiale;ZHANG Shuai(School of Mechanical and Electrical Engineering,Beijing University of Chemical Technology,Beijing 100029,China;Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery,Beijing University of Chemical Technology,Beijing 100029,China;State Key Laboratory of High-End Compressor and System Technology,Beijing University of Chemical Technology,Beijing 100029,China)

机构地区：[1]北京化工大学机电工程学院,北京100029 [2]北京化工大学高端机械装备健康监控与自愈化北京市重点实验室,北京100029 [3]北京化工大学高端压缩机及系统技术国家重点实验室,北京100029

出　　处：《机电工程》2024年第2期236-244,共9页Journal of Mechanical & Electrical Engineering

基　　金：国家重点研发计划项目(2020YFB2010803)。

摘　　要：针对高转速、复合工况下膜盘联轴器难以保证其强度特性问题,对已有膜盘联轴器强度及动力学特性进行了研究,提出了一种基于反向传播神经网络(BPNN)和多目标优化遗传算法(MOOGA)的高速联轴器多目标优化方法。首先,为了得到优化所需的关键参数,采用了正交实验结合多因素方差分析的方法,选取了联轴器优化参数;然后,基于已选取的关键参数,采用BPNN方法构建了截面应力和弯曲刚度的目标函数,并将其与多项式拟合方法进行了对比,对BPNN方法的精确性进行了验证;最后,采用MOOGA方法对目标函数进行了多目标优化,并将优化前后结果进行了对比分析。研究结果表明:采用BPNN结合MOOGA的方法对联轴器设计参数进行优化,在满足联轴器刚度需求的情况下,可有效降低联轴器膜盘的危险截面应力;优化后,联轴器危险应力减小了18.2%,弯曲刚度降低了5.05%,联轴器角向补偿能力增加了0.1°,从而证明了仿真的有效性。该结果可以为挠性联轴器参数优化设计提供参考。Aiming at the problem of difficult to ensure the strength and dynamic characteristics of diaphragm coupling under high speed and compound working conditions,the strength and dynamic characteristics of the existing disc coupling were studied,an optimization method based on back-propagation neural network(BPNN)and multi-objective optimization genetic algorithm(MOOGA)was proposed.Firstly,in order to obtain the key parameters required for optimization,based on the method of orthogonal experiment combined with multivariate analysis of variance,the key parameters were selected.Then,based on the BPNN model,the objective function of the key parameters and cross-sectional stress was constructed,as well as the objective function of the key parameters and bending stiffness was constructed,the accuracy of the polynomial solution objective function was compared,and the accuracy of the BPNN method in solving the objective function was verified.Finally,multi-objective optimization of the coupling design parameters was carried out through MOOGA,the optimization results were compared with those before optimization.The research results indicate that the proposed method is used to optimize the design parameters of the coupling,and the dangerous cross-sectional stress of the disc can be effectively reduced under the condition of meeting the stiffness requirements of the coupling.After optimization,the dangerous stress of the coupling is reduced by 18.2%,the bending stiffness of the coupling is reduced by 5.05%,and the angular compensation capacity of the coupling is increased by 0.1°.The effectiveness of the simulation is proved and a reference is provided for the parameter optimization design of flexible couplings.

关 键 词：膜盘联轴器 机械强度 动力学特性 反向传播神经网络 多目标优化遗传算法 参数优化 

分 类 号：TH133.4[机械工程—机械制造及自动化]