Fault evaluating and diagnosing method for evaporative circular refrigerating system

Abstract

The invention discloses a fault evaluating and diagnosing method for an evaporative circular refrigerating system. The method comprises the following steps of combining fuzzy control with a fault Petri net and carrying out fault evaluation by forward reasoning to determine a fault initiating path and a fault order of severity and a confidence level; and carrying out fault diagnosis by reverse reasoning to determine a fault source which are most likely to initiate faults and a fault preferred diagnosing sequence. Meanwhile, fault evaluating and diagnosing parameters are optimized by means of physicomimetics, so that the forward reasoning and reverse reasoning accuracy is improved, and the fault analyzing and diagnosing ability of the improved fuzzy fault Petri net is improved.

Description

Technical field [0001] The invention belongs to the field of thermodynamics and fault diagnosis, and particularly relates to a fault evaluation and diagnosis method of an evaporative cycle refrigeration system. Background technique [0002] With the improvement of aircraft performance requirements, more and more electronic devices are used, and their heating power is also increasing. Due to the lower performance of traditional air refrigeration cycles, engine bleed air and stamping will be increased under conditions of large thermal load. The amount of air used has caused a rapid increase in aircraft fuel compensation losses and also affected the aircraft's stealth performance. Compared with the air refrigeration cycle, the evaporative refrigeration cycle has a higher coefficient of performance, so the introduction of an integrated environmental control system for the evaporative refrigeration system is of great significance. Therefore, the failure of the evaporative cycle refri...

AI Technical Summary

Problems solved by technology

The neural network needs enough learning samples to ensure the reliability of the diagnosis; it is difficult for the expert system to acquire knowledge, and the knowledge of the expert system is inconsistent, incomplete and uncertain when acquiring knowledge, and the system cannot be self-improving; the fault tree method Building a tree is cumbersome and easy to make mistakes

[0004] At present, in the field of fault diagnosis, Petri net is mainly used to express the logical relationship of the system, complete the information table and diagnosis reasoning, it focuses on the representation of graphics, and lacks a clear description of the dynamic characteristics of the net

Images