Construction of online monitoring and fault diagnosis system for mechanical equipment based on BP neural network

In view of the problems of ambiguous symptoms of faults and data and overlapping fault features in the process of mechanical equipment fault diagnosis, this paper will take the deep learning model as the core, adopt the method of BP neural network and information fusion, and complete the construction and training of mechanical equipment fault diagnosis model with the help of class libraries such as Numpy and Matplotlib in Python environment, so as to form an intelligent module that can support the call of Web server. At the same time, this paper will also combine Django framework, use Pycharm tool to complete the development of Web server, improve the definition and deployment of functions and data interfaces, and generate a Web-based online monitoring and fault diagnosis system for mechanical equipment. The overall design of the system chooses B/S architecture, which supports users to remotely operate and visit the Web server to monitor the operation of mechanical equipment, and can classify the historical data of mechanical equipment with the characteristic values of fault frequency domain, and make corresponding predictions to realize the diagnosis of mechanical equipment faults. The construction of the system not only effectively improves the accuracy of mechanical equipment fault diagnosis, but also makes a beneficial attempt for the intelligent reform of the overall operation mode.