Description:
Abstract Complex equipment in the process industry is the core productivity of automated manufacturing. Fault prediction, diagnosis, and health maintenance of such equipment are important factors to ensure continuous and reliable operation of production. However, how to adjust the fault judgment rules in time according to the changes in the operating conditions and process of the equipment is the core design content of the fault diagnosis platform. The platform of this paper presented is mainly based on stress wave condition monitoring technology, which combined with process monitoring to form an online monitoring data set of the equipment; Then use the data fusion technology to fuse the collected signals at the decision-making level, and finally combine principal component analysis and the BP neural network to predict the equipment’s health trend and fault type.