Electromechanical equipment fault diagnosis method based on deep neural network

Abstract

The invention discloses an electromechanical equipment fault diagnosis method based on a deep neural network. The electromechanical equipment fault diagnosis method comprises the steps of data acquisition, data preprocessing, deep neural network training, electromechanical equipment fault online identification and unknown fault automatic learning. The electromechanical equipment fault diagnosis method does not depend on manual selection of fault features, and can learn information contained in the equipment state monitoring data comprehensively. The electromechanical equipment fault diagnosismethod can realize automatic fitting from the equipment state data to the fault category, can reduce the workload of fault diagnosis algorithm development, can realize continuous expansion of the fault diagnosis function through learning of unknown faults, and can improve the investment benefit of the system.

Description

technical field [0001] The invention belongs to the field of state monitoring of electromechanical equipment, and is particularly used for solving the field of state monitoring and fault diagnosis of electromechanical equipment in nuclear power and other fields. Background technique [0002] The health monitoring of electromechanical equipment has entered the era of big data, and big data of electromechanical equipment has become an important resource to reveal the evolution process and mechanism of mechanical failures. However, the complex structure and mechanism of mechanical equipment, coupled with the interference of its harsh operating environment, and the changes in working conditions brought about by its complex tasks, make it difficult to analyze, process and diagnose big data of mechanical equipment. The previous intelligent diagnosis algorithm is difficult to cope with the demand of big data processing. Therefore, artificial intelligence technology represented by ...

AI Technical Summary

Problems solved by technology

However, the complex structure and mechanism of mechanical equipment, coupled with the interference of its harsh operating environment, and the changes in working conditions brought about by its complex tasks, make the analysis, processing and diagnosis of mechanical equipment big data difficult.

The previous intelligent diagnosis algorithm is difficult to meet the needs of big data processing

Images