A Machine Intelligence Fault Prediction Method Based on Automatic Convolutional Neural Network

Abstract

The invention provides a mechanical intelligent fault prediction method based on an automatic convolutional neural network, which acquires equipment fault signals and preprocesses them to obtain preprocessed fault signals; constructs an automatic convolutional neural network ACNN fault diagnosis model; The ACNN fault diagnosis model includes a set of convolutional neural network CNN and a set of deep deterministic policy gradient network DDPG; the convolutional neural network CNN is used for equipment fault prediction, and the deep deterministic policy gradient network DDPG is used to realize the The learning rate of the convolutional neural network CNN, batch and three parameters of regularization are automatically adjusted; the ACNN fault diagnosis model is trained using the preprocessed fault signal to obtain the completed ACNN fault diagnosis model; the training The completed fault diagnosis model is applied to equipment fault diagnosis. The beneficial effect provided by the invention is that the automatic adjustment and optimization of the parameters of the convolutional neural network is realized, so that the convolutional neural network has a good ability to extract fault features.

Description

technical field [0001] The invention relates to the field of fault prediction, in particular to a machine intelligent fault prediction method based on an automatic convolutional neural network. Background technique [0002] With the improvement of equipment intelligence, knowledge-based fault diagnosis methods, also known as data-driven fault diagnosis methods, have gradually been studied by a large number of scholars, and have achieved a large number of application effects on a large number of equipment, such as bearings, aviation Engines, large wind turbines, etc. [0003] Deep learning is the core of the data-driven fault diagnosis method, which is mainly used for the analysis and processing of equipment signals, and realizes the mining and prediction of equipment abnormal states. However, the performance of data-driven fault diagnosis methods represented by deep learning directly depends on the choice of hyperparameters. Although a large number of default hyperparamete...

AI Technical Summary

Problems solved by technology

The reasonable selection of the three most important parameters of the convolutional neural network (learning rate, batch size, and regularization value) will directly affect the extraction effect of the convolutional neural network on fault features, thereby reducing the prediction accuracy and generalization of the fault diagnosis model. ability

At the same time, in the existing technology, the selection of the above three parameters is often modulated by manual experience or repeated experiments, which requires a lot of manual energy and has uncertainty.

Images