Data-driven aero-engine remaining useful life (RUL) estimation is a key technology to monitor engine’s degradation. However, due to the difficulties of extracting the time information from data, the accuracy of data-driven methods remains low. Aiming at the problem, this article proposes a novel multi-head structure to wrap time information into the network structure and training processes. Multi-head networks are designed to take the time sequence information of inputs in the feedforward process. Meanwhile, the time loss function takes full consideration of the time prior information of the outputs (estimated RUL) and directs the backward process of the networks to converge to the real aero-engine operating situation. Experiments on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) aero-engine’s RUL estimation dataset are conducted to validate the effectiveness of the proposed method. The result and comparisons with other state-of-the-art methods show that the proposed multi-head structure and time loss function can improve the accuracy significantly. This suggests that the proposed method is a promising approach in aero-engine degradation evaluation.
The non-convergence and low efficiency of the thermodynamic model make them difficult to be used in the aero-engines degradation evaluation, while the negligence of the thermodynamics process of data-driven degradation evaluation methods makes them inaccurate and hard to analyze the actual degradation of air path components. So, we propose a thermodynamic-based and data-driven hybrid model for aero-engine degradation evaluation. Different from thermodynamic-based methods, the iteration calculation is converted to the forward flow in the proposed neural network, thus improving convergence. Moreover, a multi-objective loss function considering the components co-operation process and fusion training process fully taking advantage of simulation and degradation trajectory datasets are proposed to improve the degradation evaluation accuracy. The test case is carried out on NASA’s benchmark for aero-engine degradation evaluation. The result shows that the proposed method can improve the accuracy significantly, which suggests its effectiveness.
A low bypass ratio turbofan engine operates in a hostile environment, resulting in performance degradation. This seriously affects the security and reliability of the engine. Therefore, a performance degradation evaluation method for engines based on flight data is proposed. The method expands the equation system to solve the underdetermined problem caused by the lack of engine sensors based on multiple operating point analysis. The improved evolution algorithm is employed to solve the equation system, which relieves the problem of insufficient precision. The engine performance degradation dataset is established based on the engine performance calculation model to verify the reliability of the degradation evaluation method. The results show that the method is applicable to the dataset. Finally, the method is applied to the actual flight data to study the law of the performance degradation of the researched engine, which indicates that the engine’s fan efficiency and high-pressure compressor flow capacity have an apparent downward trend over time.
Traditional thermodynamic models for military turbofans suffer from non-convergence and inaccuracy due to inaccuracy of the component maps and the instability of the iterative process. To address these problems, a thermodynamically oriented and neural network-based hybrid model for military turbofans is proposed. Different from iteration-based thermodynamic models, the proposed hybrid model transforms the iteration process into a multi-objective optimization and training process for a component-level neural network in order to improve convergence and modeling accuracy. The experiment shows that the accuracy of the proposed hybrid model can reach about 7%, 5% better than the map-fitting-based thermodynamic model and 8% better than the purely data-driven method, with a similar number of network neutrons, verifying its effectiveness. The contributions of this work mainly lie in the following aspects: a new component-level neural network structure is proposed to improve convergence and computational efficiency; a multi-objective loss function based on component co-working is proposed to direct the model to converge toward the physical thermodynamic process; a fusion training method of multiple data sources is established to train the model with good convergence and high computational accuracy.
4 December 2023 in IEEE Transactions on Aerospace and Electronic Systems
This paper presents significant advancements in the domain of aero-engine degradation evaluation by introducing an amalgamation of state transition functions, Gaussian mapping networks, and Kalman filtering. Conventional thermodynamic models, when applied to military turbofan engines, often encounter issues related to convergence and computational efficiency. To overcome these challenges, we introduce a first-order state transition function designed specifically for degradation assessment, taking degradation rate into consideration. Furthermore, we propose a pioneering Gaussian mapping network-based measurement function to address convergence challenges and enhance computational efficiency. To seamlessly integrate a degradation prior with measurement regression, we introduce an innovative Kalman filtering iteration method. This paper provides a comprehensive exposition of the mathematical models, derivation processes, and practical implementation of these techniques. Our approach demonstrates precise degradation evaluation on a simulated degradation dataset, capitalizing on the precision of first-order transition functions and Kalman iterative process and the computational efficiency achieved through the combination of Gaussian mapping networks. Additionally, this innovative framework exhibits substantial potential for real-world applications in aero-engine performance evaluation, as exemplified by the actual flight dataset test case.