On-Board Real-Time Optimization Control for Turbo-Fan Engine Life Extending

Fang

et al. 2019

IEEE Access

Self Cite

A new on-board turbo-fan engine modeling method based on a batch normalize (BN) minibatch gradient descent (MGD) deep neural network (NN) is proposed. This new method adopts BN algorithm, which accelerates the network training speed and overcomes the gradient vanish problem. Hence, using the BN algorithm, the neural network adopts the deeper structure, which means the network has a stronger representation capacity. This mini-batch gradient descent (MGD-NN) algorithm that consumes much less time to update the NN parameters is adopted. Therefore, it is more suitable for training big dataset and establishing a high-accuracy engine model in a large flight envelope. Finally, to verify whether the proposed method could be applied to larger flight envelope, the conventional NN also adopts MGD (called MGD-NN). The turbo-fan engine models based on these two modeling methods are both conducted within a sub-sonic cruise envelope. The simulation results show that the proposed modeling method has much higher accuracy than the MGD-NN. Moreover, the proposed method has the characteristics of less data storage, low computation complexity, and good real-time performance, which are the most importance indices for model realize on-board. INDEX TERMS Aero-engine model, batch normalize, deep neural network, turbo-fan on-board model, mini-batch gradient descent, data storage.

Section: Introductionmentioning

confidence: 99%

Aero-Engine On-Board Model Based on Batch Normalize Deep Neural Network

Fang

et al. 2019

IEEE Access

Self Cite

“…The CLM has better accuracy, but it has poor real-time performance. Therefore, many scholars proposed support vector machine (SVM) [19][20][21] and neural network (NN) 22,23 for engine modeling. The accuracy and real time of these two methods are a compromise between the PLM and the CLM.…”

Section: Introductionmentioning

confidence: 99%

A study on global optimization and deep neural network modeling method in performance-seeking control

Proceedings of the Institution of Mechanical Engineers, Part I:

Wang

et al. 2019

Self Cite

In this article, a novel performance-seeking control method based on deep neural network and interval analysis is proposed to obtain a better engine performance. A deep neural network modeling method which has stronger representation capability than conventional neural network and can deal with big training data is adopted to establish an on-board model in the subsonic and supersonic cruising envelops. Meanwhile, a global optimization algorithm interval analysis is applied here to get a better engine performance. Finally, two simulation experiments are conducted to verify the effectiveness of the proposed methods. One is the on-board model modeling which compares the deep neural network with the conventional neural network, and the other is the performance-seeking control simulations comparing interval analysis with feasible sequential quadratic programming, particle swarm optimization, and genetic algorithm, respectively. These two experiments show that the deep neural network has much higher precision than the conventional neural network and the interval analysis gets much better engine performance than feasible sequential quadratic programming, particle swarm optimization, and genetic algorithm.

“…The CLM has high accuracy, but its real-time performance is poor. For this reason, some scholars propose onboard model based on support vector machine 9–11 and neural network, 12–15 whose real-time performance and accuracy are between PLM and CLM. However, the curse of dimensionality is hard to solve based on these data-driven modeling method.…”

Section: Introductionmentioning

confidence: 99%

Research on aero-engine steady model based on an improved compact propulsion system model

Proceedings of the Institution of Mechanical Engineers, Part I:

Yong

Sun

et al. 2019

Self Cite

The aero-engine steady model is the basis of the modern advanced control method such as performance seeking control. An improved compact propulsion system model is proposed to improve the steady model accuracy. The improved compact propulsion system model mainly contains linear model, such as steady-state variable model, and physical-based models, such as inlet model, nonlinear model, and nozzle model. The improved compact propulsion system model applied to full envelop by parameter corrections. The basepoint control vector and basepoint output vector of improved compact propulsion system model are four-dimensional interpolation instead of two-dimensional interpolation as conventional compact propulsion system modeling does. The improved compact propulsion system model not only considers the change of engine state but also take the flight parameter into account. The simulations of the conventional compact propulsion system modeling and the improved compact propulsion system model are conducted in subsonic and transonic flight envelop. The simulations show that, compared with the conventional compact propulsion system modeling, the relative testing errors of the improved compact propulsion system model decrease greatly. Moreover, the testing time of the conventional compact propulsion system modeling and the improved compact propulsion system model are both almost equal to 0.027 ms.