Integrated avionics equipment fault intelligent diagnosis system

Abstract

The invention discloses an integrated avionics equipment fault intelligent diagnosis system, and aims to provide a diagnosis system which is accurate in fault positioning, high in fault identificationcapability and strong in robustness. The system is realized through the following technical scheme: a data preprocessing module converts acquired equipment data into a difference value of equipment fault timestamps, and the two columns of data are stored into a first database as a fault event sequence; a Hawkes process module periodically sends a detection signal, judges whether the system has afault and the type of the system fault, diagnoses the fault type, the fault part and the reason, and sends the detected fault signal to a survival analysis and prediction module to identify the faultsize and the time-varying characteristic, a time dependent variable is introduced, a proportional risk regression model COX regression model is constructed by taking survival outcome and survival timeas dependent variables, a survival function is obtained from the Hawkes process module, and fault analysis is performed according to units of different fault timestamps to complete a fault diagnosistask.

Description

technical field [0001] The invention belongs to the field of time series point process in the field of machine learning, and relates to a system for diagnosing the fault of integrated avionics equipment through survival analysis based on Hawkes Process. Background technique [0002] With the rapid development of large-scale integrated circuit technology and its increasingly wide application, in order to maintain various devices and equipment, people must use computers to find circuit faults. Analog circuit fault diagnosis has become an eye-catching topic in large-scale integrated circuits. of a subject. The problem of fault diagnosis and location of analog circuits has not only attracted widespread attention, but is also a major problem in the design and use of electronic systems by experts at home and abroad. Among them, the fault diagnosis of large-scale nonlinear complex circuits, that is, soft fault diagnosis, is also a problem that plagues the masses. Problems for scie...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of existing fault diagnosis methods, solve the problems of complicated case representations in complex systems, difficult fault diagnosis caused by modeling difficulties, no unified method, etc., as well as the shortcomings of cumbersome and complicated processes, the purpose of the invention is to: For the above existing problems, it is necessary to provide an integrated avionics fault intelligent diagnosis system with accurate fault location, low false alarm rate and missed alarm rate, high fault identification ability, and strong robustness, so as to overcome the fuzzy reasoning process of traditional fault diagnosis methods , threshold uncertainty and other issues

Images