Refrigerating system fault diagnosis method and refrigerating device

Abstract

The invention discloses a refrigeration system fault diagnosis method and a refrigeration device, and belongs to the field of fault diagnosis and artificial intelligence, and the method comprises the following steps: (1) constructing a BN network model; (2) obtaining prior probability values of a target signal node and a fault signal node; (3) collecting BN network information; (4) performing relaxation operation on the data of the conditional mutual information matrix, and constructing a TAN classifier model matched with the fault features; (5) recalculating the conditional probability matrix; (6) calculating the posterior probability between the fault signal node and the characteristic signal node; (7) checking a posterior probability value; and (8) sorting the posterior probability values in each state from large to small, and taking the state corresponding to the maximum posterior probability value as a priority diagnosis / prediction classification result of the target signal node. The method is simple in network model construction, stable in classification efficiency, capable of accurately processing various types of tasks, insensitive to missing data, high in diagnosis speed and high in efficiency.

Description

Technical field[0001]The present invention relates to a fault diagnosis and artificial intelligence field of refrigeration system, and more particularly to a refrigeration system fault diagnosis method and a refrigeration device.Background technique[0002]Once the refrigeration system has failed, the comfort of the environment or the required frozen temperature is not guaranteed, which will cause damage to the system equipment. Second, when the refrigeration system is running in a fault state, system energy consumption tends to increase, resulting in energy waste. Therefore, the failure mechanism of the refrigeration system is studied, establish effective and accurate fault diagnostic models to realize real-time online monitoring, failure of the refrigeration system, and is important.[0003]Fault diagnosis technology is an application-type marginal discipline. Its theoretical foundation involves multi-door disciplines, such as modern control theory, computer engineering, mathematical ...

AI Technical Summary

Problems solved by technology

Directly using the above method for fault detection and diagnosis of the refrigeration system requires more process variables to be measured, which means that more sensors are needed, which increases the cost, and the variable dimension is too large, which has a strong correlation with each other. Sex and redundancy, affecting the accuracy of recognition

In addition, the above-mentioned commonly used fault diagnosis methods have the following disadvantages: First, the classical expert system and the fuzzy mathematical fault tree method need to establish an accurate system model, and both rely heavily on professional knowledge bases, and their learning ability is not strong. Update, the cost of dealing with dynamic correlation systems is extremely high; second, for the BP network method, although it does not depend on the system model, has strong learning ability and strong noise resistance, it still has uncontrolled training time, relies heavily on training sample sets, and cannot Disadvantages of inference prediction (the parameter results of BP network training are different every time, if the training sample set changes, the learning results will also fluctuate)

However, in the process of network construction and data processing, this method does not eliminate characteristic signal nodes that are not related to faulty signal nodes, and the results of diagnosis and prediction are still not accurate enough.

Images