Diagnostic method for pump station unit based on composite characteristic index and depth limit learning machine

Abstract

The invention discloses a diagnostic method for a pump station unit based on a composite characteristic index and a depth limit learning machine and relates to the technical field of fault diagnosis of hydraulic machinery. The diagnostic method can directly decompose nonstationary time series from original vibrating signals by adopting self-adaptive iterative filtering, so that the nonstationary characteristic of the unit can be extracted effectively. A time domain statistics signal, a frequency domain statistics signal, an energy signal, a sample entropy signal and an arrangement entropy signal are extracted based on each nonstationary signal component. Characteristic learning is performed quickly and effectively by means of the depth limit learning machine, implicit fault information ofeach characteristic is extracted and boundedness of a manual design and characteristic extraction and a complex parameter adjusting process based on an artificial neural network are avoided, so that intelligent diagnosis of faults of a water pump unit is achieved, and therefore the accuracy and the effectiveness of fault diagnosis of the water pump unit are improved.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of hydraulic machinery, in particular to a method for diagnosing a pumping station unit based on a composite feature index and a deep extreme learning machine. Background technique [0002] As one of the most important components in the pumping station, the pumping station unit is widely used in long-distance water diversion projects, urban drainage water supply, power generation and other industries. It is an important water supply equipment in the South-to-North Water Diversion Project. Situation plays a vital role. However, the unit of the pumping station has been affected by harsh factors such as heavy load, strong impact, high speed, and large background noise for a long time on site, and there are many faults such as hydraulic, electrical, and mechanical. If the type of fault cannot be accurately identified and corresponding measures are taken, it will affect the The safe operation ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for diagnosing pumping station units based on composite feature indicators and deep extreme learning machines, so as to solve the aforementioned problems in the prior art

Images