Air conditioning system sensor fault error re-learning method and system

Abstract

The invention discloses an air conditioning system sensor fault error re-learning method and system. The method comprises the steps: building a basic neural network through employing the historical data of a sensor as training data, and obtaining a prediction error; because the prediction error data is relatively small, outlier data is deleted through standard deviation after proportional expansion processing is carried out on the prediction error, so that data distribution is stable; after re-learning is carried out by utilizing the stably distributed data, the obtained prediction structure is more accurate; finally, regression is carried out on the data after re-learning to obtain real error data, so that the prediction data is closer to the actual data, the negative influence generatedby residual error fault recognition is reduced, the fault recognition accuracy is higher, error recognition with a small error degree is met, and the method has wide applicability. According to the method, on the basis of accepting the existence of the error, the fault is predicted through the re-learning neural network, so that the effects of eliminating the error and improving the accuracy are achieved, and the fault prediction precision is relatively high.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of air-conditioning sensors, and in particular relates to a method and system for re-learning fault errors of air-conditioning system sensors. Background technique [0002] Most modern air-conditioning systems rely on automatic control to meet user comfort and specified energy consumption requirements; when the air-conditioning control system fails, it will cause unnecessary energy waste and affect user comfort requirements; therefore, testing and diagnosis of air-conditioning systems faults appear to be extremely important. As an important part of the air-conditioning control system, the sensor directly determines the accuracy and precision of the fault diagnosis of the air-conditioning system; therefore, the fault diagnosis of the sensor is particularly important, especially for some small faults, and some current detection methods are difficult. Detected, however, these minor failures ...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the technical problems existing in the prior art, the present invention provides an air-conditioning system sensor fault error re-learning method, system and storage medium to solve the problem that the existing BP neural network has a large error value in the prediction data, and then Technical issues leading to reduced accuracy of air conditioner sensor system fault diagnosis

Images