Online anomaly monitoring and diagnosis method and system

Abstract

The invention provides an online anomaly monitoring and diagnosis method and system. The method comprises the steps that the causal relation and conditional relation among all signals are defined based on a directed graph model; based on definitions of the signals by the directed graph model, the signals in acquired historical data are classified, and a training set of the historical data is established to perform model training and determine model parameters; and based on real-time data theoretical values of the signals in real-time data obtained after the real-time data acquired through online monitoring is input into a trained model, whether the signals in the real-time data are abnormal is determined. The system adopting the method and a computer readable medium storing a program executing the method are also included. Through the method, the system and the computer readable medium, a complete logic relation and casual relation are constructed for the whole process of industrial production and operation through the directed graph model, and more reasonable, more correct, more accurate and efficient production online anomaly diagnosis prediction is realized in combination with machine learning.

Description

technical field [0001] The present application relates to abnormal diagnosis when a fault occurs in industrial production, and in particular to an online abnormal monitoring and diagnosis method and system. Background technique [0002] In industrial production, the existing abnormal monitoring and fault diagnosis are usually based on a large amount of production data, and the logical causal relationship is discovered through algorithms, so as to help administrators realize monitoring and diagnosis. The practicability of monitoring and diagnosis is not strong, and the false alarm rate is extremely high, sometimes even reaching more than 99%. [0003] Taking the coal mill system of the power plant system as an example, usually, the operation monitoring of the coal mill system is carried out by using the centralized and distributed control system DCS. DCS installs sensors on the terminal equipment of the coal mill system, and the sensors convert the collected signals through ...

AI Technical Summary

Problems solved by technology

[0007] The main purpose of this application is to provide an online abnormality monitoring and diagnosis method and system to solve the problem of building a complete logical relationship and causal relationship for the entire process of industrial production and operation through a directed graph model, and combine machine learning to achieve a more reasonable, more correct, More accurate and efficient diagnosis of predicted problems

Images