Yinhan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yinhan Wang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Jiang Wang
Beijing Institute of Technology
3 shared publications- Jiang Wang
Beijing Institute of Technology
3 shared publications - Shipeng Fan
Beijing Institute of Technology, Beijing, China
2 shared publications - Defu Lin
Beijing Institute of Technology
1 shared publication - Gangcheng Wu
State Key Laboratory of Food Science and Resources, School of Food Science and Technology, Jiangnan University, 214122, Wuxi, Jiangsu, China
1 shared publication Hongyan Li
Beijing Institute of Technology
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62, 13786-13800
Online Parameter Identification for an Incoming Interceptor With Observability Analysis
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62, 13786-13800
Online Parameter Identification for an Incoming Interceptor With Observability Analysis
- 31 October 2025
- Published by Springer Nature
- p. 354-373
Online Attack Intent Recognition for Aerial Vehicles Based on Interacting Multiple Models
- 31 October 2025
- Published by Springer Nature
- p. 354-373
Online Attack Intent Recognition for Aerial Vehicles Based on Interacting Multiple Models
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 17607-17621
Attack Intent Recognition for Incoming Vehicles Based on Deep Learning
Attack Intent Recognition (AIR) for incoming vehicles is crucial for the effective execution of defense strategies and enhances the overall air defense system performance. The problem is addressed in this paper by leveraging the Artificial Neural Network (ANN), Joint Probability Calculation (JPC), and Interacting Multiple Model (IMM). First, the swarm engagement scenario is decoupled into multiple one-on-one pairs, with each pair treated as an independent event. An ANN is employed to compute the probabilities of attack and non-attack for the vehicle in each pair. Subsequently, the joint probabilities of each pair are calculated based on the principle of mutually exclusive events. Finally, an interacting operation is adopted to normalize these joint probabilities. The proposed scheme decouples the multi-class problem into multiple binary classifications, simplifying the network's fitting challenge. By introducing the non-attack probabilities, the method is able to deal with the non-preset conditions. Numerical simulation results demonstrate the advantages of the proposed method over traditional Gated Recurrent Unit (GRU), Kalman Filter (KF), and eXtreme Gradient Boosting (XGBoost) methods in terms of convergence speed and recognition accuracy. Specifically, it achieves a mean accuracy of 96.16% in 1.5 seconds, outperforming the GRU (3 seconds, 93.11%), KF (3 seconds, 85.82%), and XGBoost(1.5 seconds, 77.75%). These advantages enhance its practicality for real-world applications, especially in the dynamic and unpredictable environments.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 17607-17621
Attack Intent Recognition for Incoming Vehicles Based on Deep Learning
Attack Intent Recognition (AIR) for incoming vehicles is crucial for the effective execution of defense strategies and enhances the overall air defense system performance. The problem is addressed in this paper by leveraging the Artificial Neural Network (ANN), Joint Probability Calculation (JPC), and Interacting Multiple Model (IMM). First, the swarm engagement scenario is decoupled into multiple one-on-one pairs, with each pair treated as an independent event. An ANN is employed to compute the probabilities of attack and non-attack for the vehicle in each pair. Subsequently, the joint probabilities of each pair are calculated based on the principle of mutually exclusive events. Finally, an interacting operation is adopted to normalize these joint probabilities. The proposed scheme decouples the multi-class problem into multiple binary classifications, simplifying the network's fitting challenge. By introducing the non-attack probabilities, the method is able to deal with the non-preset conditions. Numerical simulation results demonstrate the advantages of the proposed method over traditional Gated Recurrent Unit (GRU), Kalman Filter (KF), and eXtreme Gradient Boosting (XGBoost) methods in terms of convergence speed and recognition accuracy. Specifically, it achieves a mean accuracy of 96.16% in 1.5 seconds, outperforming the GRU (3 seconds, 93.11%), KF (3 seconds, 85.82%), and XGBoost(1.5 seconds, 77.75%). These advantages enhance its practicality for real-world applications, especially in the dynamic and unpredictable environments.
- 17 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. PP (00189251) , 1-11
Parameter Identification of a PN-Guided Incoming Missile Using an Improved Multiple-Model Mechanism
To accurately estimate the state of the incoming missile and effectively implement an evasion maneuver, the parameters of the incoming missile, including a guidance constant and a first-order lateral time constant, should be identified online. To this end, assuming that a missile with proportional navigation (PN) guidance law attempts to attack an aerial target with bang-bang evasion maneuvers, a parameter identification model based on the gated recurrent unit (GRU) neural network is built in this paper. The analytic identification solutions for the guidance law parameter and the first-order lateral time constant are derived and show that the identification of the latter parameter is more difficult. The inputs of the identification model are available kinematic information between the aircraft and the missile, while the outputs contain the regression results of the missile's parameters. To increase the training speed and identification accuracy of the model, an output processing method called the improved multiple-model mechanism (IMMM) is proposed in this paper. The effectiveness of IMMM and the performance of the established model are demonstrated through numerical simulations under various engagement scenarios.
- 17 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. PP (00189251) , 1-11
Parameter Identification of a PN-Guided Incoming Missile Using an Improved Multiple-Model Mechanism
To accurately estimate the state of the incoming missile and effectively implement an evasion maneuver, the parameters of the incoming missile, including a guidance constant and a first-order lateral time constant, should be identified online. To this end, assuming that a missile with proportional navigation (PN) guidance law attempts to attack an aerial target with bang-bang evasion maneuvers, a parameter identification model based on the gated recurrent unit (GRU) neural network is built in this paper. The analytic identification solutions for the guidance law parameter and the first-order lateral time constant are derived and show that the identification of the latter parameter is more difficult. The inputs of the identification model are available kinematic information between the aircraft and the missile, while the outputs contain the regression results of the missile's parameters. To increase the training speed and identification accuracy of the model, an output processing method called the improved multiple-model mechanism (IMMM) is proposed in this paper. The effectiveness of IMMM and the performance of the established model are demonstrated through numerical simulations under various engagement scenarios.
- 16 March 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 136
Online time-varying navigation ratio identification and state estimation of cooperative attack
- 16 March 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 136
Online time-varying navigation ratio identification and state estimation of cooperative attack
- 21 November 2022
- Published by Elsevier in Aerospace Science and Technology
- Vol. 132
Quick intention identification of an enemy aerial target through information classification processing
- 21 November 2022
- Published by Elsevier in Aerospace Science and Technology
- Vol. 132
Quick intention identification of an enemy aerial target through information classification processing
- Open Access
Process Modelling and Simulation of Key Volatile Compounds of Maillard Reaction Products Derived from Beef Tallow Residue Hydrolysate Based on Proxy Models
The hydrolysis time is directly related to the flavor of the Maillard reaction, but existing proxy models cannot simulate and model the variation curves of vital volatile components. This study developed a predictive model for modelling and simulating key volatile compounds of Maillard reaction products (MRPs) derived from beef tallow residue hydrolysate. Results showed the degree of hydrolysis increased with hydrolysis time, and the most significant improvement in the roast flavor and overall acceptance was when hydrolyzing 4 h. Based on flavor dilution value and the relative odor activity value, nine key volatile components were identified, and 2-ethyl-3,5-dimethylpyrazine with roast flavor was the highest. Compared with Polynomial Curve Fitting (PCF) and Cubic Spline Interpolation (CSI), key volatile compounds of MRPs could be better modeled and simulated by the Curve Prediction Model (CPM). All results suggested that CPM could predict the changes in key volatile components produced by MRPs.
Open AccessProcess Modelling and Simulation of Key Volatile Compounds of Maillard Reaction Products Derived from Beef Tallow Residue Hydrolysate Based on Proxy Models
The hydrolysis time is directly related to the flavor of the Maillard reaction, but existing proxy models cannot simulate and model the variation curves of vital volatile components. This study developed a predictive model for modelling and simulating key volatile compounds of Maillard reaction products (MRPs) derived from beef tallow residue hydrolysate. Results showed the degree of hydrolysis increased with hydrolysis time, and the most significant improvement in the roast flavor and overall acceptance was when hydrolyzing 4 h. Based on flavor dilution value and the relative odor activity value, nine key volatile components were identified, and 2-ethyl-3,5-dimethylpyrazine with roast flavor was the highest. Compared with Polynomial Curve Fitting (PCF) and Cubic Spline Interpolation (CSI), key volatile compounds of MRPs could be better modeled and simulated by the Curve Prediction Model (CPM). All results suggested that CPM could predict the changes in key volatile components produced by MRPs.