Chemical fault detection method based on particle swarm optimization and a noise reduction sparse coding machine

Abstract

The invention discloses a chemical fault detection method based on particle swarm optimization and a noise reduction sparse coding machine. The method comprises the following steps of carrying out unsupervised feature learning on standardized and whitened training data by using a plurality of stacked noise reduction sparse autocoders; carrying out Softmax classifier model training in a supervisedmanner; and finally, finely adjusting the weight parameters of the whole network through supervision, and introducing a particle swarm optimization algorithm into the key adjustable hyper-parameters for automatic optimization to obtain a trained chemical process fault detection intelligent model for fault detection of process real-time data. According to the invention, the greedy layer-by-layer training method of the deep neural network is adopted to adaptively and intelligently learn knowledge implied by original data in the chemical process; Compared with a traditional method, the method hasthe advantages that the method is more intelligent, the fault detection performance can be improved, and due to the fact that an automatic optimization algorithm is added, much time is saved comparedwith manual parameter tuning.

Description

technical field [0001] The invention relates to the field of chemical process fault detection and diagnosis, in particular to a chemical fault detection method based on particle swarm optimization and noise reduction sparse coding machine. Background technique [0002] As one of the most powerful tools for the management of abnormal working conditions in chemical process, chemical process fault detection provides a certain guarantee for process safety early warning and saves a lot of economic losses. According to the estimates of the US National Safety Regulatory Agency, abnormal working conditions cause economic losses of at least US$20 billion per year to the US petroleum and chemical industries. In the UK, the annual losses caused by abnormal working conditions are as high as US$27 billion. The method of fault detection in chemical process is very important in actual chemical production. [0003] Chemical process data has the characteristics of nonlinear, high-dimensiona...

AI Technical Summary

Problems solved by technology

Although the popular traditional methods such as PCA, ICA, KPCA, KICA, and MICA can effectively detect some faults, the detection rate of some disturbance faults is extremely low, indicating that the traditional methods still cannot fully and accurately extract Information about these faults, which requires the development of some new methods to improve the detection rate of faults

Due to the characteristics of nonlinearity, high noise, and non-Gaussian distribution of complex chemical processes, traditional chemical process fault detection methods do not show excellent diagnostic performance. Therefore, it is necessary to develop fault monitoring methods suitable for complex nonlinear chemical processes.

Images