An intelligent fault diagnosis method suitable for pipe expansion equipment

Abstract

The invention belongs to the technical field of intelligent fault diagnosis of tube expansion equipment, and discloses an intelligent fault diagnosis method suitable for tube expansion equipment. The method includes the following steps: (1) collecting pressure data of the tube expansion equipment in real time; (2) Preprocess the original pressure data, and divide the processed data into training set and test set; (3) Based on the Leacky linear rectification function improved stack denoising sparse autoencoder, construct a deep neural network fault diagnosis model, using Softmax The function is used as the activation function of the BP classifier of the deep neural network fault diagnosis model; then the training set is used to train the deep neural network fault diagnosis model, and then the test set is input into the deep neural network fault diagnosis model. The test set is diagnosed and classified to predict the type of fault, thereby completing the fault diagnosis of the tube expander. The invention improves the production efficiency and reduces the cost.

Description

technical field [0001] The invention belongs to the relevant technical field of intelligent fault diagnosis of tube expansion equipment, and more particularly relates to an intelligent fault diagnosis method suitable for tube expansion equipment. Background technique [0002] As we all know, the core of air-conditioning and refrigeration technology includes refrigeration compressors and heat exchangers (condensers and evaporators), and the expansion tube process is a key process in the production of air-conditioning heat exchangers. It has large batches and high requirements for quality consistency. , once the equipment is abnormal, if it cannot be found, it will often cause abnormal product quality in batches, or even product scrapping; and in the actual production process of the tube expansion process for the air-conditioning heat exchanger, there are mainly the following problems: [0003] (1) The quality assurance method of sampling inspection is not perfect. At present...

AI Technical Summary

Problems solved by technology

At present, the quality of products is mainly guaranteed through conventional pre-sampling methods, but the sampling method cannot guarantee the quality of all products, and post-processing compensation will bring about a large waste of manpower

[0004] (2) Manual monitoring is not timely

Due to accidental and sudden equipment failures, once equipment problems occur, if workers cannot actively observe product abnormalities, batch quality abnormalities will occur, and even batch waste will occur.

[0005] (3) Expansion equipment is not intelligent

As far as the expansion tube related equipment itself is concerned, the existing equipment cannot realize automatic and intelligent real-time monitoring of key molds and spare parts, so that problems such as equipment failure and product quality cannot be dealt with in a timely manner

[0006] However, since most tube expanders lack intelligent condition monitoring and health management modules, it is necessary to manually perform equipment maintenance and product sampling inspections in order to ensure product performance, which causes problems in the production process of tube expansion Faults cannot be dealt with in a timely manner, which may easily cause serious quality consistency problems

Images