Multi-stage fermentation process fault monitoring method of semi-supervised FCM and SAE based on information entropy

Abstract

The invention discloses a multi-stage fermentation process fault monitoring method of semi-supervised FCM and SAE based on information entropy. The method comprises the following steps: firstly, completing stable stage division on data in a fermentation process by using a semi-supervised fuzzy C-means clustering algorithm based on information entropy; and then a Silhouette coefficient is introduced to divide a transition stage of every two stable stages, and the fault monitoring comprises the steps of establishing a monitoring model for each stable stage and each transition stage by using a sparse automatic encoder, and constructing a reconstruction error as a statistic index. Then determining a control limit of each sample statistic index by using a kernel density estimation method; and finally, substituting test batch samples into the model, calculating a statistic index of the test batch samples, comparing the statistic index with a normal sample control limit, and if the control limit is exceeded, determining that the sample is a fault sample. The method is more sensitive to faults, enhances the robustness of a monitoring model, improves the accuracy of fault monitoring, and can reduce the occurrence of false alarms and missing alarms in process monitoring.

Description

technical field [0001] The invention relates to the field of data-driven fault monitoring technology, in particular to a fault monitoring technology for fermentation process. The data-driven method of the present invention is a specific application in the monitoring of fermentation process faults. Background technique [0002] With the rapid development of industrial automation technology, the integration and complexity of modern industrial systems are getting higher and higher. In order to enable the system to detect the occurrence of faults in time, it is particularly important to improve the reliability of system fault monitoring performance. Fermentation process is an industrial process mainly based on batch process, which refers to making raw materials into small batches and high value-added products within a limited time. Due to the high daily demand for these products, fault monitoring has been of high interest in the industry for the safe and orderly production of ...

AI Technical Summary

Problems solved by technology

However, when there are more AE hidden layer nodes than input nodes, the ability of AE to extract sample features will be greatly weakened, and the generalization ability of the model will also deteriorate.

Images