A dlae-based fault monitoring method for fermentation process

Abstract

The invention discloses a novel method for carrying out real-time fault monitoring on a penicillin fermentation process. The method comprises two stages of off-line modeling and on-line monitoring. The off-line modeling comprises the following steps: firstly, processing three-dimensional data of a fermentation process; then respectively calculating a Laplacian matrix of the data of each fermentation batch to represent local structure information of the data in each batch; and finally, carrying out modeling by using a noise reduction Laplace automatic encoder (DLAE) to construct monitoring statistics, and determining a control limit by using a kernel density estimation method. The on-line monitoring comprises the following steps: processing newly collected data according to a model, calculating the statistical magnitude of the data, comparing the statistical magnitude with a control limit, and judging whether the fermentation process runs normally or not. According to the method, the local structure of data in batches can be effectively utilized, and meanwhile, the training cost and the hardware requirement of the Laplace automatic encoder are reduced. Meanwhile, the robustness of the model is enhanced by adopting a noise reduction training mode, and the fault monitoring accuracy is relatively high.

Description

technical field [0001] The invention relates to the field of data-driven fault diagnosis technology, in particular to a fault diagnosis technology for batch processes. The data-driven method of the present invention is a specific application in fault monitoring of a typical batch process—penicillin fermentation process. Background technique [0002] In recent decades, batch processes have attracted much attention because they can meet the demands of producing high value-added products. However, its mechanism is complicated, its operation complexity is high, and its product quality is easily affected by uncertain factors. As a typical batch process, the penicillin fermentation process has the characteristics of strong nonlinearity, dynamics, and mixed Gaussian distribution. In order to ensure the safety and stability of the fermentation process operating system, an effective process monitoring scheme is established to detect timely Anomalies are necessary. [0003] At pres...

AI Technical Summary

Problems solved by technology

However, AE is a feature extraction method based on the global structure of the data, and does not consider the local structure information of the data, and the hidden layer features are less robust and susceptible to noise interference

These greatly limit the fault monitoring performance of AE

Images