Engine surge fault prediction system and method based on fusion neural network model

Abstract

The invention discloses an engine surge fault prediction system and method based on a fusion neural network model, which belongs to the technical field of time series data prediction. The system includes: a prediction module, which is used to generate a prediction time series of a specified length from the three-dimensional structural time series data of the engine; The feature extraction module is used to extract the local features of the predicted time series, the semantic relationship between data, and the overall sequence trend features; the classification module is used to predict the local features of the time series, the semantic relationship between data, and the overall sequence trend features Determine whether it is a surge fault. The present invention first generates a predicted time series of a specified length, that is, realizes the prediction of the working state data of the engine in a period of time in the future, and then judges whether the working state data of the engine in a period of time in the future includes surge fault data, so as to diagnose the surge fault of the engine Make more accurate and faster forecasts in advance.

Description

technical field [0001] The invention relates to the technical field of time series data prediction, in particular to an engine surge fault prediction system and method based on a fusion neural network model. Background technique [0002] The aero engine is the "heart" of the aircraft, and engine failure accounts for a considerable proportion of flight failures, and once a failure occurs, it will be very fatal. Therefore, how to predict aeroengine failure in advance is a difficult problem that needs to be solved for current flight safety. Aeroengine surge failure is a common abnormal working state, which will cause violent vibration of engine parts and overheating of hot end, and even endanger flight safety in severe cases. Therefore, when the engine is about to experience surge, it is one of the important prerequisites to avoid flight accidents by discovering and identifying the surge phenomenon in time, and then taking anti-surge measures. [0003] The research on fault p...

AI Technical Summary

Problems solved by technology

Although these methods can meet the real-time requirements, but because the engine itself is a complex nonlinear vibration system, it is very difficult to establish a predictive model

[0005] 2. Knowledge-based prediction; knowledge-based prediction does not require precise mathematical models, and can give full play to the knowledge and experience of experts in various disciplines of the engine. However, due to the limited failure modes covered by the expert knowledge base, there are still many in practical applications. problem to be solved

Among them, there are very few solutions that use machine learning algorithms or establish deep learning models based on data to make predictions. Most of them are based on models or knowledge to make predictions, which is not only time-consuming and labor-intensive, but also has low prediction accuracy.

Images