Jun Tao’s research while affiliated with Fudan University and other places

Condition monitoring plays an important role in the safety and reliability of aero-engine. In this paper, a novel deep multimodal information fusion (MIF) method is proposed, which integrates information from the physical-based model and the data-driven model. Two deep Boltzmann machines are constructed for feature extraction from sensor data and model simulation data, respectively. Whereby information from these two modalities is mapped into a high-dimensional space and forms a joint representation, and then combined with a multi-layer feedforward neural network to form the MIF model for real-time performance simulation and prediction. Compared with the traditional single-modality method, the proposed method fuses the information of two key modalities. The experimental results indicate that proposed method improves the accuracy of engine parameters prediction.

With the rapid development of artificial intelligence technology, data-driven advanced models have provided new ideas and means for airfoil aerodynamic optimization. As the advanced models update and iterate, many useful explorations and attempts have been made by researchers on the integrated application of artificial intelligence and airfoil aerodynamic optimization. In this paper, many critical aerodynamic optimization steps where data-driven advanced models are employed are reviewed. These steps include geometric parameterization, aerodynamic solving and performance evaluation, and model optimization. In this way, the improvements in the airfoil aerodynamic optimization area led by data-driven advanced models are introduced. These improvements involve more accurate global description of airfoil, faster prediction of aerodynamic performance, and more intelligent optimization modeling. Finally, the challenges and prospect of applying data-driven advanced models to aerodynamic optimization are discussed.

In this study, a multi-objective aerodynamic optimization is performed on the rotor airfoil via an improved MOPSO (multi-objective particle swarm optimization) method. A database of rotor airfoils containing both geometric and aerodynamic parameters is established, where the geometric parameters are obtained via the CST (class shape transformation) method and the aerodynamic parameters are obtained via CFD (computational fluid dynamics) simulations. On the basis of the database, a DBN (deep belief network) surrogate model is proposed and trained to accurately predict the aerodynamic parameters of the rotor airfoils. In order to improve the convergence rate and global searching ability of the standard MOPSO algorithm, an improved MOPSO framework is established. By embedding the DBN surrogate model into the improved MOPSO framework, multi-objective and multi-constraint aerodynamic optimization for the rotor airfoil is performed. Finally, the aerodynamic performance of the optimized rotor airfoil is validated through CFD simulations. The results indicate that the aerodynamic performance of the optimized rotor airfoil is improved dramatically compared with the baseline rotor airfoil.

In this study, a prognostics and health management (PHM) framework is proposed for aero-engines, which combines a dynamic probability (DP) model and a long short-term memory neural network (LSTM). A DP model based on Gaussian mixture model-adaptive density peaks clustering algorithm, which has the advantages of an extremely short training time and high enough precision, is employed for modelling engine fault development from the beginning of engine service, and principal component analysis is introduced to convert complex high-dimensional raw data into low-dimensional data. The model can be updated from time to time according to the accumulation of engine data to capture the occurrence and evolution process of engine faults. In order to address the problems with the commonly used data driven methods, the DP + LSTM model is employed to estimate the remaining useful life (RUL) of the engine. Finally, the proposed PHM framework is validated experimentally using NASA’s commercial modular aero-propulsion system simulation dataset, and the results indicate that the DP model has higher stability than the classical artificial neural network method in fault diagnosis, whereas the DP + LSTM model has higher accuracy in RUL estimation than other classical deep learning methods.

Sensor fault diagnosis and performance degradation estimation (SFDPDE) play a critical role in the operation and maintenance of aero-engine. In this study, a modified fusion model driven by sensor measurements is proposed to overcome the drawbacks of single data-driven and single model-based methods. Two types of on-board models are established based on augmented state space equations, and a data-driven model based on extreme learning machine (ELM) is constructed for residual correction of the on-board model. A bidirectional information transmission algorithm is designed in the SFDPDE framework in order to include the function coordination. Kalman filter (KF) is employed as the optimal algorithm in the SFDPDE framework containing the standardized sensor parameter selection process. The experimental results indicate that, the proposed fusion model improves the accuracy of sensor fault diagnosis, reduces the mean square error (MSE) of health parameter (HP) estimations, while the information sharing module expands the application scope of SFDPDE and improves its accuracy as well as stability.

In recent decades, deep learning (DL) has become a rapidly growing research direction, redefining the state-of-the-art performances in a wide range of techniques, such as object detection and speech recognition. In the aircraft design, dynamics, and control field, many works hinge on the information-rich data-driven approach, which includes the fusion-based prognostic and health management, the airliner's flight safety monitoring, intelligent sensing, and flight control systems development. While DL provides great potentials to solve these data-driven problems, a systematic review and discussion as to how the DL has been/can be used for these problems are still missing in relation to the rapidly developing and widely used DL techniques. In this article, we aim to address this urgent issue to provide a timely overview of the state-of-the-art for applying DL to the aircraft design, dynamics, and control field. In particular, we briefly introduce five representative DL methods, i.e., deep neural network, deep autoencoder, deep belief network, convolutional neural network, and recurrent neural network. Mathematical definitions for each method are presented, and illustrative applications are also discussed. We then review the existing DL-based works that have appeared in the aircraft design, dynamics, and control field. The review efforts are divided into two major groups, i.e., the own-ship aircraft modeling, wherein the works have been/can be implemented online for the aircraft design/dynamics/control, and other airplanes research works, wherein DL-based schemes provide offline monitoring of the aircraft operation. We then summarize the data sources and DL architectures. Referring to the experiences of DL research works/techniques development in other related fields, future opportunities, challenges, and potential solutions for implementing DL in the aircraft design, dynamics, and control field are also discussed.

Stall is an important cause closely associated with the flight accidents of commercial aircrafts, and stall lift robustness of HLD (high-lift devices) plays a significant role in flight safety issues. In this study, stall characteristics of the HLD of a wide-body commercial aircraft are simulated and analyzed via DES (detached eddy simulation) method, and the impacts of geometric parameters of the HLD on stall lift characteristics are investigated. Afterwards, stall lift robustness design for the HLD is performed via a proposed inverse method which combines the GRNN (generalized regression neural network) method and PCA (principal component analysis) method. Then the inverse design model is established with the aerodynamic parameters as input and the geometric parameters as output. The PCA method is introduced to reduce the dimension of the input data, while the GRNN is employed to predict the geometric parameters. The design process is iterated with new sample points added in. The validated results via DES method indicate that the finally designed HLD configuration conforms with the design targets very well, and thus the stall lift robustness is improved obviously. More specifically, the average lift coefficient near the stall AoA (angle of attack) is improved by 1.4%, and the variance of the lift coefficients near the stall AoA is reduced by 79%, while the stall AoA remains unchanged.

In this study, variable camber technology is applied to improve the fuel efficiency of high-aspect-ratio aircraft with aeroelasticity considered. The nonlinear static aeroelastic analyses are conducted for CFD/CSD (computational fluid dynamics/computational structural dynamics) numerical simulations. The RBF (radial basis function) method is adopted for the transmission of aerodynamic loads and structural displacements, the diffusion smoothing method is employed for grid deformation in each iteration of CFD/CSD coupling, and the FFD (free-form deformation) method is introduced for the parameterization of variable camber wing. Based on the aerodynamic characteristic curves under different cambers, the discrete variable camber control matrix for the high-aspect-ratio aircraft during the cruise phase is established. The Fibonacci method is employed to optimize the fuel efficiency by utilizing the control matrix. The results indicate that the drag during the cruise phase is reduced obviously and the fuel efficiency is improved evidently comparing to the original configuration.