Refrigerant charge fault diagnosis method and device for multi-split air conditioner

Abstract

The invention discloses a refrigerant charge fault diagnosis method and device for a multi-split air conditioner. The method comprises the steps that S1, operation data of the multi-split air conditioner with different refrigerant charge are collected; S2, the collected operation data are processed through a principal component analysis (PCA) method to obtain characteristic operation data; S3, aBP neural network is trained by using the characteristic operation data to obtain a refrigerant charge fault detection model; and S4, whether the refrigerant charge of the multi-split air conditionermeets a preset standard or not is judged by utilizing the fault detection model. According to the refrigerant charge fault diagnosis method and device for the multi-split air conditioner, redundant parts in original data can be removed, so that the input data dimension is reduced; and the nonlinear modeling capability of the BP neural network can be exerted, so that the generalization capability and learning stability of the model are improved, and the convergence of the neural network is greatly improved.

Description

technical field [0001] The invention relates to the field of energy technology, in particular to a method and device for diagnosing faults of charging amount of refrigerant in multiple units. Background technique [0002] Today, with the depletion of energy resources, how to improve energy efficiency and reduce energy consumption has become a research topic of great significance. At present, refrigeration and air-conditioning systems account for as high as 30% to 45% of the total energy consumption of building systems. Effectively reducing air-conditioning energy consumption and improving the efficiency of refrigeration and air-conditioning can reduce energy consumption and improve energy utilization. The refrigerant charge is one of the important parameters affecting the performance of the refrigeration system. If a fault occurs and is not eliminated in time, it will lead to increased energy consumption of the system, shortened equipment life, physical discomfort and even a...

AI Technical Summary

Problems solved by technology

[0004] However, direct use of BP neural network for fault diagnosis has defects such as difficult to understand network weights, easy to fall into local minimum, poor network stability and slow convergence speed, weak generalization ability, etc.

Images