Chenghao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chenghao Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jie Li
State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China
1 shared publication - Junlong Li
State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China
1 shared publication - Kaiqiang Feng
State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China
1 shared publication - Li Qin
State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan, China
1 shared publication - Songhao Zhang
State Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China
1 shared publication - Xi Zhang
College of Electrical and Control Engineering, North University of China, Taiyuan 030051, China
1 shared publication
Latest Publications
- Open Access
High-Speed Flight Vehicle Strong Interference Data-Driven Control Based on Self-Organizing Map and Improved Moth-Flame Optimization
Owing to their reliance on detailed mathematical modeling, traditional control methods encounter challenges such as high control complexity and low precision when applied to high-speed flight vehicle control under strongly disturbed atmospheric conditions. To address this limitation, this study introduces a data-driven neural network mapping approach into the field of flight vehicle control. By excavating the underlying patterns in operational data and leveraging the nonlinear mapping capability of neural networks, accurate prediction and generation of control commands are achieved, thereby eliminating the dependence on precise mathematical models and offering a novel solution for complex control problems. Building on this foundation, a self-organizing map (SOM) radial basis function (RBF) neural network is proposed. Leveraging the competitive learning mechanism of SOM, it performs adaptive clustering on input samples, dynamically optimizes the number of clusters to determine the number of hidden-layer nodes in RBF, and adopts the SOM cluster centers as the centers of RBF basis functions. This design enables the one-click data-driven determination of both the number of nodes and their corresponding center vectors, significantly simplifying the network structure design process. Meanwhile, to address inherent limitations of this network, such as suboptimal output weights, unoptimized width functions, and the inherent drawbacks of the traditional Moth-Flame Optimization (MFO) algorithm, an Adaptive Enhanced Moth-Flame Optimization (AEMFO) algorithm is developed, drawing inspiration from biological swarm intelligence. By integrating strategies such as adaptive spiral update and elite opposition-based learning, it balances the global exploration and local exploitation capabilities, and performs targeted optimization of the RBF width parameters and output-layer weights. This optimization significantly enhances the accuracy of the network in mapping attitude-control commands in strongly disturbed environments, providing robust support for the stable attitude control of high-speed flight vehicles. Finally, simulation results demonstrate that the proposed method achieves high control accuracy for flight vehicle attitude control under strongly disturbed environments.
Open AccessHigh-Speed Flight Vehicle Strong Interference Data-Driven Control Based on Self-Organizing Map and Improved Moth-Flame Optimization
Owing to their reliance on detailed mathematical modeling, traditional control methods encounter challenges such as high control complexity and low precision when applied to high-speed flight vehicle control under strongly disturbed atmospheric conditions. To address this limitation, this study introduces a data-driven neural network mapping approach into the field of flight vehicle control. By excavating the underlying patterns in operational data and leveraging the nonlinear mapping capability of neural networks, accurate prediction and generation of control commands are achieved, thereby eliminating the dependence on precise mathematical models and offering a novel solution for complex control problems. Building on this foundation, a self-organizing map (SOM) radial basis function (RBF) neural network is proposed. Leveraging the competitive learning mechanism of SOM, it performs adaptive clustering on input samples, dynamically optimizes the number of clusters to determine the number of hidden-layer nodes in RBF, and adopts the SOM cluster centers as the centers of RBF basis functions. This design enables the one-click data-driven determination of both the number of nodes and their corresponding center vectors, significantly simplifying the network structure design process. Meanwhile, to address inherent limitations of this network, such as suboptimal output weights, unoptimized width functions, and the inherent drawbacks of the traditional Moth-Flame Optimization (MFO) algorithm, an Adaptive Enhanced Moth-Flame Optimization (AEMFO) algorithm is developed, drawing inspiration from biological swarm intelligence. By integrating strategies such as adaptive spiral update and elite opposition-based learning, it balances the global exploration and local exploitation capabilities, and performs targeted optimization of the RBF width parameters and output-layer weights. This optimization significantly enhances the accuracy of the network in mapping attitude-control commands in strongly disturbed environments, providing robust support for the stable attitude control of high-speed flight vehicles. Finally, simulation results demonstrate that the proposed method achieves high control accuracy for flight vehicle attitude control under strongly disturbed environments.