Incremental learning-based online updating method for security control Bayesian network model in dense medium coal preparation process

Abstract

The invention discloses a dense medium coal preparation process safety control Bayesian network model online updating method based on incremental learning, and belongs to the technical field of industrial safety operation intelligent control. The method mainly comprises the following steps: firstly, inputting a phenomenon variable of an abnormal working condition as evidence information into a security control Bayesian network model for reasoning; secondly, making a corresponding safety control decision according to a maximum posterior probability principle, and judging whether the safety control decision is reasonable or not according to domain expert knowledge; and if so, implementing the control decision. And if not, continuing to judge whether a new abnormal working condition occurs or not, and performing structure updating learning and parameter updating learning according to judgment conditions. And finally, using the updated security control Bayesian network model to obtain a security control decision again. According to the method for updating the safety control model in the dense medium coal preparation process, the capacity of adapting to coal preparation environment changes of the model can be improved, and safe and reliable control decisions are provided for operators.

Description

technical field [0001] The invention relates to an on-line updating method of a Bayesian network model for safety control of a heavy medium coal preparation process based on incremental learning, and belongs to the technical field of industrial safety operation intelligent control. Background technique [0002] At present, when an abnormal working condition occurs in the heavy medium coal preparation process, it mainly relies on the experience and knowledge of the operator to analyze the cause and location of the abnormal working condition, and give the corresponding operating variable values ​​to restore the production process to a stable operation state. However, this operation method is affected by the limitations of the operator's own experience and knowledge, and often cannot give reliable safety control decisions in time, causing certain losses to production. [0003] Now, with the development of big data technology, on the one hand, due to the improvement of sensor ac...

AI Technical Summary

Problems solved by technology

[0004] However, in the actual production process, the coal preparation processes are interrelated, the raw coal properties change frequently, and the coal preparation production environment is complex and changeable.

Therefore, new abnormal conditions are prone to occur. In the face of new abnormal conditions, the original safety control Bayesian model may not be able to adapt to environmental changes

If the safety control decision provided by the original model is still used, not only the abnormal working conditions cannot be eliminated, but even the life safety of the operator will be threatened

Images