Turbofan engines are known as the heart of the aircraft. The turbofan’s health state determines the aircraft’s operational status. Therefore, the equipment monitoring and maintenance of the engine is an important part of ensuring the healthy and stable operation of the aircraft, and it is vital to monitor the remaining useful life (RUL) of the engine. The monitored data of turbofan engines have high dimensions and a long time span, which cause difficulties in predicting the remaining useful life of the engine. This paper proposes a residual life prediction model based on Autoencoder and a Temporal Convolutional Network (TCN). Among them, Autoencoder is used to reduce the dimension of the data and extract features from the engine monitoring data. The TCN network is trained on the obtained low-dimensional data to predict the remaining useful life. The model mentioned in this article is verified on the NASA public data set (C-MAPSS) and compared with common machine learning methods and other deep neural networks. The SAE-TCN model achieved better scores on the FD001 independent testing data set with an RMSE of 18.01 and a score of 161. The average relative error of the model relative to other common learning models is 0.9499 in RMSE and 0.2656 in Scoring Function. The experimental results show that the model proposed in this paper performs the best in the evaluation, and this conclusion has important implications for engine health.
The functional requirements of the control system in aero‐engine are increasing due to the multiple objectives. The typical aero‐engine control system is equipped with a multi‐loop control system and switches the controllers to achieve the different performance requirements. However, the aero‐engine fuel flow may be oscillated due to the controllers switch; this phenomenon can seriously damage the performance of the aero‐engine, even its stability. Therefore, the transient switching stability and performance should be concerned. This paper investigates a bumpless compensator design problem for aero‐engine multi‐loop control system. First, a description of the aero‐engine transient bump phenomenon is given, and the design problem is also formulated. Then, we propose a controller compensator method that can smooth the control signal for eliminating the control error. Furthermore, we give the sufficient conditions to guarantee the stability and L1 control problem by using the LMI configuration technique. Moreover, the structure of closed‐loop system with compensators is provided. Finally, a semi‐physical simulation has shown the feasibility of the proposed method.
16 September 2021 in International Journal of Aerospace Engineering
Due to the aero-engines in a high temperature, pressure, and spool speed environment, the concurrent faults in actuator/sensor combined with degradation of the aero-engine could arise the problem of closed-loop instability during the flight. For this purpose, an improved hybrid fault-tolerant control (FTC) technique has been studied in this paper to deal with simultaneous failure of actuators and sensors associated with health parameters of the typical components’ degradation in aero-engines. The improved hybrid FTC structure combined with the nonlinear thermodynamic component-level (NCL) model-based estimation method merges fault estimation of actuators/sensors and typical components’ degradation estimation process into the FTC process. A robust state feedback controller under the disturbance of simultaneous actuator and sensor faults is designed in the proposed method, together with the switching algorithm serving for the fault estimation and improved hybrid FTC channels. In order to show the feasibility of the proposed method, several semiphysical experiments are engaged to illustrate that the improved hybrid FTC structure can save the tolerant-control time and improve performance of the control system.