Fault diagnosis method for dynamic industrial process based on gru deep neural network

Abstract

The invention discloses a dynamic industrial process fault diagnosis method based on the GRU deep neural network. The method divides the original data into several sequence units as the input of the GRU, and establishes the GRU network through the batch normalization algorithm, which can effectively obtain the sequence units from the sequence units. The dynamic features are extracted from the GRU, and the softmax regression method is used to classify the faults according to the dynamic features extracted by the GRU, and the probability explanation of the classification is given to make the diagnosis results more accurate, thereby avoiding the problem of "curse of dimensionality" and improving the accuracy of dynamic industrial process fault diagnosis. Accuracy.

Description

technical field [0001] The invention relates to a dynamic industrial process fault diagnosis method based on a GRU deep neural network. Background technique [0002] With the development of modern industrial technology and process control mechanisms, industrial processes have become more and more complex. To improve industrial process safety and product quality, industrial process monitoring and fault diagnosis have received extensive attention in the past decades. Data-driven multivariate statistical process monitoring (MSPM) has been widely used in the monitoring of industrial process operations and production results. Compared with knowledge-based and model-based methods, MSPM methods are easier to set up. Therefore, MSPM models such as Principal Component Analysis (PCA), Independent Component Analysis (ICA) are widely used in industrial process monitoring and fault diagnosis. The framework of traditional fault diagnosis mainly includes two steps: 1) feature extraction...

AI Technical Summary

Problems solved by technology

However, these vector-based augmentation methods may exacerbate the "curse of dimensionality" (a phenomenon in which the computation increases exponentially with the increase of dimensionality in problems involving vector computations) and destabilize feature extraction methods; moreover , the augmented structure is pre-fixed, i.e. the adoption of dynamic information is not adaptively learned from raw process data

Images