Fault prediction method based on air data

Abstract

The invention discloses a fault prediction method based on air data. The method comprises the following steps of: establishing an air database for storing air data; establishing a knowledge base for storing a rule for fault analysis; removing noise of the air data by using a singular value decomposition method; performing chaotic characteristic judgment on the air data from which the noise is removed by using a maximum Lyapunov index method; realizing prediction of the air data by using a prediction algorithm; and performing fault analysis according to a predicted value and knowledge in the knowledge base, and finally outputting a predicted result. Due to the adoption of the fault prediction method, the influence of noise on prediction accuracy is reduced, selection of a more suitable prediction model is facilitated, high prediction accuracy is achieved, and the serviceable range of the method is widened.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and relates to fault prediction technology, noise processing technology, time series prediction technology and data mining technology, and specifically refers to a fault prediction method. Background technique [0002] As aircraft become more automated and intelligent, their potential for failure increases. Once the airborne equipment fails, it will reduce the performance and affect the flight safety, and the equipment will be damaged and the aircraft will be destroyed. The existing scheduled maintenance and reactive diagnosis and maintenance methods are not suitable for the development requirements of the aviation industry due to lag, outdated methods, poor pertinence and economy, heavy workload, and low efficiency. Therefore, fault prediction and health management (Prognostics and Health Management, PHM) technology came into being. PHM is based on advanced sensor acquisition technology, ...

AI Technical Summary

Problems solved by technology

The working status and environmental factors of these flight parameters are different, resulting in large differences in their respective data characteristics. If all of them use the same prediction method, it will inevitably affect the accuracy and reliability of the prediction.

Therefore, before making predictions, it is necessary to analyze the characteristics of flight parameters, but there is no method that can fully consider the above problems and realize fault prediction based on flight data

Images