Fault detection method for penicillin fermentation process

Abstract

The invention provides a fault detection method for a penicillin fermentation process. The method comprises the following main steps that: collecting production data under various working conditions,wherein the production data comprises normal production data and fault data, and multiple batches of integral production data are collected under each working condition; carrying out data preprocessing on collected three-dimensional data; on the basis of a principal component analysis theory, further extracting the data, and extracting data features; applying the obtained feature space to data projection detection and sub-space analysis; and therefore, carrying out fault detection. The statistical control limits of the fault detection are formulated by multiple batches of integral batch data under the normal working condition; during practical detection, whether the statistical amount of the sub-spaces of the production data exceeds a fusion statistical control limit or not is finely detected, and whether the product of the batch is affected by faults or not is judged so as to finish the fault detection. By use of the detection method, the fusion statistical control limit is adopted todetect the faults of the penicillin fermentation process, faults in a batch production process can be more accurately detected, and detection efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of industrial process fault detection, and relates to a fault detection method in intermittent industrial processes, in particular to a fault detection method in a penicillin fermentation process. Background technique [0002] With the development of science and the advancement of technology, the scale and complexity of modern industrial processes are increasing day by day. At the same time, people have put forward higher requirements for the safety performance of industrial process operation and product quality, and process monitoring and fault diagnosis technology are especially important. Fault detection and diagnosis technology is usually used in the development and design of computer-based automation systems to help humans solve many practical problems, such as industrial process monitoring and disease diagnosis. [0003] As the earliest operation mode used by people to carry out life and production ac...

AI Technical Summary

Problems solved by technology

[0004] In order to improve the problem of inaccurate statistical control limit and low fault detection effect in fault detection of intermittent industrial process, the present invention provides a more efficient and accurate statistical control limit and applies it to the fault detection method of penicillin fermentation process, which can more accurately Detect faults in intermittent production processes and improve detection efficiency

Images