【摘要】 为提高系统的开发效率和功能完整性,以. NET为开发平台,实现C#和Matlab混合编程;同时,C#通过XAMPP与MySQL数据库进行通信,实现实时数据的存储。针对轴承故障信号非平稳性问题,采用小波包分解(WPD)和自回归(AR)谱分析方法进行特征提取;考虑到神经网络具有强大的自学习能力,采用反向传播(BP)神经网络实现故障诊断。采用美国凯斯西储大学提供的旋转轴承数据集进行轴承故障诊断实验。实验结果表明,系统可以有效地实现特征提取、故障诊断以及数据存储,从而验证了故障诊断算法的可行性及系统的有效性。更多还原

【Abstract】 In order to improve the functional integrity and development efficiency of the system, the mixed programming of C# and Matlab was realized based on the. NET development platform. Simultaneously, C # communicated with MySQL database through XAMPP, realizing real-time data storage. In view of the non-stationary problem of bearing signal, Wavelet Packet Decomposition( WPD) and Auto-Regressive( AR) spectrum analysis method were adopted to carry out feature extraction. Considering the strong self-learning ability of neural networks, a Back Propagation( BP) neural network was adopted to realize fault diagnosis. The bearing fault diagnosis experiment was carried out by using the rotating bearing data sets provided by the Case Western Reserve University in the United States. The experimental results show that the system can effectively implement feature extraction, fault diagnosis and data storage, verifying the feasibility of the algorithm and the effectiveness of the system.更多还原