CAJ | 학술논문

在数控液压伺服激振试验台上进行滚珠丝杠式惯容器力学性能试验，获得惯容器在不同惯容系数及不同激振输入下力学响应，通过分析惯容器存在的非线性因素及试验结果，揭示非线性因素影响惯容器的实际性能。考虑建立惯容器自适应神经网络模型，进行惯容器力学性能预测。由于BP算法易陷入局部最优且泛化能力弱，用遗传算法优化BP网络训练过程。基于非线性因素对惯容器力学性能影响机理，选惯容系数及惯容器在多个瞬态时间点位移、速度及加速度为神经网络输入，惯容器输出力为网络输出，并将试验所得1020组数据用于网络训练及预测，网络预测结果与试验结果吻合良好，说明所用方法正确合理，可为惯容器力学性能预测提供参考。
재수공액압사복격진시험태상진행곤주사강식관용기역학성능시험，획득관용기재불동관용계수급불동격진수입하역학향응，통과분석관용기존재적비선성인소급시험결과，게시비선성인소영향관용기적실제성능。고필건립관용기자괄응신경망락모형，진행관용기역학성능예측。유우BP산법역함입국부최우차범화능력약，용유전산법우화BP망락훈련과정。기우비선성인소대관용기역학성능영향궤리，선관용계수급관용기재다개순태시간점위이、속도급가속도위신경망락수입，관용기수출력위망락수출，병장시험소득1020조수거용우망락훈련급예측，망락예측결과여시험결과문합량호，설명소용방법정학합리，가위관용기역학성능예측제공삼고。
The testing on ball-screw inerters with different inertances and different excitation inputs was carried out by using a CNC hydraulic servo exciting test-platform.The experimental results show that the dynamic characteristics of inerter are influenced by the nonlinear factors.In order to master the dynamic performance of inerter,a neural network for mechanical properties prediction was constructed.To solve the problem that the BP algorithm is prone to fall into local optimum,the genetic algorithm was used to optimize the training process and improve the generalization ability of the neural network.According to the influencing mechanism of the nonlinear factors on the mechanical properties of inerter, the inertance and the displacement,velocity and acceleration of inerter at multiple transient time points were taken as the input variables of the neural network.1020 groups of test data were used for network training and prediction and the prediction results are in good agreement with the test results.It is shown that the method can be successfully used to predict mechanical properties of inerters.