管柱疲劳试验台算法评估策略研究

Research on Evaluation Method of Column Fatigue Test Bed Algorithm

针对管柱疲劳试验台测控系统不能实时预测和切换算法的问题,提出并实现了用BP神经网络模型来解决该问题的方法。根据BP神经网络的模型和工作原理,使用典型加载曲线在转向管柱疲劳试验机中进行了算法评估功能的验证,网络经过对加载曲线和加载算法的学习训练以后,实现了对5种加载算法的准确评估。

Aiming at the problem that the measurement and control system can’t predict and switch the algorithm in real time, the BP neural network model is used to solve the problem. According to the model and working principle of BP neural network, the typical loading curve is used to verify the algorithm in steering column fatigue testing machine. After the training of the loading curve and the loading algorithm, the network realized accurate evaluation of the five loading algorithms.