An intelligent thrust prediction and real-time warning method for an aero-engine

By embedding a neural network architecture of digital engineering models into aero engines, the problem of inaccurate thrust prediction in traditional methods has been solved, enabling precise tracking and real-time early warning of engine thrust, and rapid adaptation to different engine types.

CN115688609BActive Publication Date: 2026-06-26NORTHWESTERN POLYTECHNICAL UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NORTHWESTERN POLYTECHNICAL UNIV
Filing Date
2022-12-19
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies cannot effectively and accurately predict the thrust of aero engines and provide real-time early warnings, due to limitations in traditional simulations based on mathematical equations, limitations in physical models based on human assumptions, and limitations in data-driven approaches based on a lack of physical rules.

Method used

By employing a digital engineering model-based approach, knowledge from the aero-engine field is embedded into a neural network to form a neural network architecture with embedded physical constraints. A thrust performance parameter prediction model is established through parameter selection, and combined with a real-time thrust early warning judgment method, real-time early warning information is provided.

Benefits of technology

It enables precise tracking of aero-engine thrust performance, rapid adaptation to different engine types, avoids the physical rule limitations of data-driven models, and improves prediction accuracy and speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115688609B_ABST
    Figure CN115688609B_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of aero-engine thrust prediction, and particularly relates to an intelligent thrust prediction and real-time early warning method for an aero-engine. The specific technical solution is as follows: the test parameter characteristics of the aero-engine are clustered according to measuring components and systems; feature selection is performed on the clustered parameters; component and system sub-networks are established; the component and system sub-networks are connected according to the actual working matching relationship of the aero-engine; a feature mapping network is added at the final output end of the aero-engine digital engineering model; the network model is trained using test data generated in the test process of the aero-engine, and a real-time thrust prediction model and a benchmark thrust prediction model are obtained. The physical architecture of the aero-engine is integrated into the intelligent network design, efficient fusion of multiple systems in the digital space can be achieved, the digital model can closely track the performance of the aero-engine and reflect individual differences, and thus the engine thrust performance can be accurately tracked.
Need to check novelty before this filing date? Find Prior Art