Heat exchanger early fault diagnosis method based on BP neural network

Abstract

The invention relates to the technical field of heat exchanger fault diagnosis, and discloses a heat exchanger early fault diagnosis method based on a BP neural network. The method comprises the stepsof: A) collecting key parameters of a heat exchanger in a normal working state; B) dividing the acquired key parameters into a training set, a verification set and a test set; C) constructing a BP neural network model; D) obtaining a mean value [mu] and a standard deviation [sigma] of a test output error; E) predicting the outlet data of the heat exchanger by using the trained BP neural network model to obtain predicted output of the outlet data of the heat exchanger; and F) performing fault diagnosis, and determining whether the predicted output error is continuously out of a normal error range within the error determination time length T. According to the method, the BP neural network model is established with no need for fault samples, the model can be established only by adopting thedata of the heat exchanger in the normal working state, then the fault of the heat exchanger is diagnosed through the determination standard, and the fault diagnosis accuracy is high.

Description

technical field [0001] The invention relates to the technical field of heat exchanger fault diagnosis, in particular to an early fault diagnosis method of a heat exchanger based on a BP neural network. Background technique [0002] Heat exchangers are mainly used for heat exchange in various productions. The most common failures of heat exchangers are leakage, fouling and blockage. Due to the influence of its own structural characteristics, the heat exchanger is prone to fouling and clogging, resulting in a decrease in heat exchange capacity, increased energy consumption, and high operation and maintenance costs. Blockage failure is a manifestation of scaling problems, and leakage problems are not uncommon in industrial sites. However, there are not many heat exchanger diagnosis systems at present. The methods proposed mainly for the heat exchanger of the aircraft environmental control system or the heat pump air conditioner need to establish a relatively complicated equipm...

AI Technical Summary

Problems solved by technology

[0004] The present invention is to solve the problem of complex construction of the heat exchanger early fault diagnosis mechanism model, and provides a heat exchanger early fault diagnosis method based on BP neural network

Images