论文部分内容阅读
研制了一种通用型的变速箱在线检测试验台,该试验台利用工控机控制机械臂实现变速器的自动换挡。系统利用BP神经网络算法建立数据分析模型,通过梯度下降法完成神经网络训练,该网络可成功判别变速箱的优劣。利用建立好的专家系统解决换挡策略的非线性问题,可以准确的判断挡位参数。该试验台可进行疲劳测试、传动效率测试等多个测试项目,具有可靠性好、智能化高的特点,在变速箱自动检测与故障诊断方面有很好的应用价值。
Developed a universal transmission test-line test bed, the test bed using IPC control arm to achieve automatic transmission shift. The system uses the BP neural network algorithm to establish the data analysis model, completes the neural network training through the gradient descent method, and the network can judge the pros and cons of the gearbox successfully. Using the established expert system to solve the nonlinear problem of shift strategy, the gear parameters can be accurately judged. The test bench for fatigue test, transmission efficiency test and other test items, with good reliability, high intelligence features in gearbox automatic detection and fault diagnosis has a good value.