Equipment fault intelligent diagnosis method based on artificial neural network

Abstract

The invention discloses an equipment fault intelligent diagnosis method based on an artificial neural network. The method comprises the following steps: S1, collecting equipment fault information through a test equipment fault diagnosis system; S2, establishing a neural network model, and training the neural network model by taking the fault information as a learning sample; S3, loading the trained neural network model to a neural network inference engine; s4, acquiring a signal of the test equipment in real time, and monitoring signal abnormality; and S5, taking the abnormal fault as a to-be-identified sample, inferring through a neural network inference engine, finding out a fault reason, positioning the fault and outputting a solution. According to the invention, a neural network systemis used for processing diagnosis of test equipment; the problems of 'bottleneck 'of knowledge acquisition, 'combined explosion' of reasoning and the like in a traditional system structure are solved,the range of state monitoring and fault diagnosis is expanded, the real-time requirement of state monitoring and fault diagnosis is met, and it is guaranteed that fault diagnosis and testing steps are synchronously carried out.

Description

technical field [0001] The invention relates to a device fault diagnosis method, in particular to an artificial neural network-based device fault intelligent diagnosis method. Background technique [0002] With the development of modern industry and science and technology, machinery, energy, chemical and other equipment are widely used in the national economy. Once the key equipment fails, it will often affect the normal production and operation of the enterprise, economic losses, and even some catastrophic consequences, such as fire, casualties, etc. Therefore, equipment fault diagnosis technology has been highly valued. Traditional fault diagnosis relies on regular maintenance, and regular maintenance will result in over-maintenance or under-maintenance. A lot of human and material resources are used in fault diagnosis, but the results are not satisfactory. At the same time, in order to avoid the problem of relying too much on domain experts in the current equipment fault...

AI Technical Summary

Problems solved by technology

Traditional fault diagnosis relies on regular maintenance, and regular maintenance will lead to over-maintenance or un

Images