Hongye Su

Hongye Su

Zhejiang University

H-index: 82

Asia-China

About Hongye Su

Hongye Su, With an exceptional h-index of 82 and a recent h-index of 57 (since 2020), a distinguished researcher at Zhejiang University,

His recent articles reflect a diverse array of research interests and contributions to the field:

Nonlinear sparse variational Bayesian learning based model predictive control with application to PEMFC temperature control

Predictor-Based ADRC for Dynamic Wireless Power Transfer System with Voltage Fluctuation Damping and Measurement Noise Filtering

Distributed Least-Squares Optimization Solvers with Differential Privacy

Deep Reinforcement Learning for Autonomous Driving with an Auxiliary Actor Discriminator

Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Perspectives

Dynamic fault detection and diagnosis for alkaline water electrolyzer with variational Bayesian Sparse principal component analysis

Optimal Output Regulation for EV Dynamic Wireless Charging System via Internal Model-Based Control

Detection of Oscillations in Process Control Loops from Visual Image Space Using Deep Convolutional Networks

Hongye Su Information

University

Zhejiang University

Position

___

Citations(all)

24703

Citations(since 2020)

13368

Cited By

17440

hIndex(all)

82

hIndex(since 2020)

57

i10Index(all)

390

i10Index(since 2020)

250

Email

University Profile Page

Zhejiang University

Top articles of Hongye Su

Nonlinear sparse variational Bayesian learning based model predictive control with application to PEMFC temperature control

Authors

Qi Zhang,Lei Wang,Weihua Xu,Hongye Su,Lei Xie

Journal

arXiv preprint arXiv:2404.09519

Published Date

2024/4/15

The accuracy of the underlying model predictions is crucial for the success of model predictive control (MPC) applications. If the model is unable to accurately analyze the dynamics of the controlled system, the performance and stability guarantees provided by MPC may not be achieved. Learning-based MPC can learn models from data, improving the applicability and reliability of MPC. This study develops a nonlinear sparse variational Bayesian learning based MPC (NSVB-MPC) for nonlinear systems, where the model is learned by the developed NSVB method. Variational inference is used by NSVB-MPC to assess the predictive accuracy and make the necessary corrections to quantify system uncertainty. The suggested approach ensures input-to-state (ISS) and the feasibility of recursive constraints in accordance with the concept of an invariant terminal region. Finally, a PEMFC temperature control model experiment confirms the effectiveness of the NSVB-MPC method.

Predictor-Based ADRC for Dynamic Wireless Power Transfer System with Voltage Fluctuation Damping and Measurement Noise Filtering

Authors

Jiawang Yue,Zhitao Liu,Hongye Su

Journal

IEEE Transactions on Transportation Electrification

Published Date

2024/1/22

This paper investigates a novel active disturbance rejection control (ADRC) scheme for the dynamic wireless power transfer (DWPT) system of electric vehicles (EVs) by designing a composite observer. In the benchmark ADRC framework, high-gain extended state observers (ESOs) are commonly employed to estimate unknown uncertainties. However, this scheme can lead the controller to be sensitive to high-frequency measurement noise, which may limit the control performance and potentially decrease the lifespan of the DWPT system. To address these limitations, a composite observer is proposed by combining a state predictor and an ESO to recover low-frequency state information and unknown uncertainties, respectively. Subsequently a state error feedback control law is proposed based on the estimated information to generate the desired control signal for the DWPT system. Stability analysis demonstrates …

Distributed Least-Squares Optimization Solvers with Differential Privacy

Authors

Weijia Liu,Lei Wang,Fanghong Guo,Zhengguang Wu,Hongye Su

Journal

arXiv preprint arXiv:2403.01435

Published Date

2024/3/3

This paper studies the distributed least-squares optimization problem with differential privacy requirement of local cost functions, for which two differentially private distributed solvers are proposed. The first is established on the distributed gradient tracking algorithm, by appropriately perturbing the initial values and parameters that contain the privacy-sensitive data with Gaussian and truncated Laplacian noises, respectively. Rigorous proofs are established to show the achievable trade-off between the ({\epsilon}, {\delta})-differential privacy and the computation accuracy. The second solver is established on the combination of the distributed shuffling mechanism and the average consensus algorithm, which enables each agent to obtain a noisy version of parameters characterizing the global gradient. As a result, the least-squares optimization problem can be eventually solved by each agent locally in such a way that any given ({\epsilon}, {\delta})-differential privacy requirement can be preserved while the solution may be computed with the accuracy independent of the network size, which makes the latter more suitable for large-scale distributed least-squares problems. Numerical simulations are presented to show the effectiveness of both solvers.

Deep Reinforcement Learning for Autonomous Driving with an Auxiliary Actor Discriminator

Authors

Bangalore Ravi Kiran,Ibrahim Sobh,Victor Talpaert,Patrick Mannion,Ahmad A. Al Sallab,Senthil Yogamani,Patrick Pérez

Journal

IEEE Transactions on Intelligent Transportation Systems

Published Date

2021/2/9

With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.

Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Perspectives

Authors

Runze Lin,Junghui Chen,Lei Xie,Hongye Su,Biao Huang

Journal

arXiv preprint arXiv:2404.00247

Published Date

2024/3/30

This paper provides insights into deep reinforcement learning (DRL) for process control from the perspective of transfer learning. We analyze the challenges of applying DRL in the field of process industries and the necessity of introducing transfer learning. Furthermore, recommendations and prospects are provided for future research directions on how transfer learning can be integrated with DRL to empower process control.

Dynamic fault detection and diagnosis for alkaline water electrolyzer with variational Bayesian Sparse principal component analysis

Authors

Qi Zhang,Weihua Xu,Lei Xie,Hongye Su

Journal

Journal of Process Control

Published Date

2024/3/1

Electrolytic hydrogen production serves as not only a vital source of green hydrogen but also a key strategy for addressing renewable energy consumption challenges. For the safe production of hydrogen through Alkaline water electrolyzer (AWE), dependable process monitoring technology is essential. However, random noise can easily contaminate the AWE process data collected in industrial settings, presenting new challenges for monitoring methods. In this study, we develop the variational Bayesian sparse principal component analysis (VBSPCA) method for process monitoring. VBSPCA methods based on Gaussian prior and Laplace prior are derived to obtain the sparsity of the projection matrix, which corresponds to ℓ 2 regularization and ℓ 1 regularization, respectively. The correlation of dynamic latent variables is then analyzed by sparse autoregression and fault variables are diagnosed by fault …

Optimal Output Regulation for EV Dynamic Wireless Charging System via Internal Model-Based Control

Authors

Mengting Zhang,Zhitao Liu,Hongye Su

Journal

IEEE Transactions on Industrial Electronics

Published Date

2024/1/19

This article proposes an effective optimal control method to achieve constant output voltage for the dynamic wireless charging (DWC) system subject to the time-varying mutual inductance caused by the movement of the electric vehicle (EV). Different from the existing literature, the induced voltage of the receiver coil due to the mutual inductance fluctuation is treated as a sinusoid-like disturbance, which can be described by a predefined exosystem and be well compensated by an internal model (IM)-based controller. An optimal linear state feedback control scheme is developed using the IM-based output regulation theory and the linear quadratic regulator technique. Integral action is also introduced by state augmentation to eliminate the steady-state errors. Finally, comparisons among the proposed IM-based optimal state feedback controller and the conventional proportional–integral (PI) controller are conducted in …

Detection of Oscillations in Process Control Loops from Visual Image Space Using Deep Convolutional Networks

Authors

Tao Wang,Qiming Chen,Xun Lang,Lei Xie,Peng Li,Hongye Su

Journal

IEEE/CAA Journal of Automatica Sinica

Published Date

2024/3/27

Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability. Although numerous automatic detection techniques have been proposed, most of them can only address part of the practical difficulties. An oscillation is heuristically defined as a visually apparent periodic variation. However, manual visual inspection is labor-intensive and prone to missed detection. Convolutional neural networks (CNNs), inspired by animal visual systems, have been raised with powerful feature extraction capabilities. In this work, an exploration of the typical CNN models for visual oscillation detection is performed. Specifically, we tested MobileNet-V1, ShuffleNet-V2, EfficientNet-B0, and GhostNet models, and found that such a visual framework is well-suited for oscillation detection. The feasibility and validity of this framework are verified …

Surrogate empowered Sim2Real transfer of deep reinforcement learning for ORC superheat control

Authors

Runze Lin,Yangyang Luo,Xialai Wu,Junghui Chen,Biao Huang,Hongye Su,Lei Xie

Journal

Applied Energy

Published Date

2024/2/15

The Organic Rankine Cycle (ORC) is widely used in industrial waste heat recovery due to its simple structure and easy maintenance. However, in the context of smart manufacturing in the process industry, traditional model-based optimization control methods are unable to adapt to the varying operating conditions of the ORC system or sudden changes in operating modes. Deep reinforcement learning (DRL) has significant advantages in situations with uncertainty as it directly achieves control objectives by interacting with the environment without requiring an explicit model of the controlled plant. Nevertheless, direct application of DRL to physical ORC systems presents unacceptable safety risks, and its generalization performance under model-plant mismatch is insufficient to support ORC control requirements. Therefore, this paper proposes a Sim2Real transfer learning-based DRL control method for ORC …

Hot rolled prognostic approach based on hybrid Bayesian progressive layered extraction multi-task learning

Authors

Shuxin Zhang,Zhitao Liu,Tao An,Xiyong Cui,Xianwen Zeng,Ning Shi,Hongye Su

Journal

Expert Systems with Applications

Published Date

2024/9/1

Hot-rolled strip products have diverse applications, and enhancing the detection, diagnostics, and prognostics of product quality during hot rolling is essential. Nevertheless, the multivariable, strong coupling, nonlinear, and time-varying nature of the production process poses a rigorous challenge for accurate hot-rolled prognostics. This paper implements a progressive layered extraction (PLE) multi-task learning (MTL) framework to simultaneously estimate multiple quality indicators, such as strip crown, center line deviation, exit temperature, wedge, width, and symmetry flatness. Additionally, the paper proposes the implements of Hybrid Bayesian Neural Network (HBNN) experts and a gating network with attention mechanism to integrate private and shared task features. It also puts forth an auxiliary task involving a Variational Autoencoder with Generative Adversarial Networks (VAE-GAN) to extract latent states from …

Distributed non‐linear model predictive control with Gaussian process dynamics for two‐dimensional motion of vehicle platoon

Authors

Xiaorong Hu,Yao Shi,Lei Xie,Hongye Su

Journal

IET Intelligent Transport Systems

Published Date

2024/1

The platoon control of connected and automated vehicles is an important topic in transportation research. The characteristics of non‐linearities, external disturbances, and strong coupling are non‐negligible in two‐dimensional motion control. An integrated longitudinal and lateral vehicle dynamics is required. A Gaussian Process‐based Distributed Stochastic Model Predictive Control (GP‐DSMPC) for two‐dimensional motion is proposed. It achieves global longitudinal stability and lateral error suppression. Gaussian process (GP) regression is employed to approximate the unknown model error. For the two‐norm chance constraints, over‐approximating the confidence ellipse to an outer polyhedron is an effective way to reduce the conservativeness and coupling effect in longitudinal and lateral motion. A neighbour‐average target trajectory is designed with an upper‐level optimization for adjustable target …

Metal object detection with high sensitivity and blind-zone free for DD coil-based wireless electric vehicle chargers

Authors

Junren Ye,Zhitao Liu,Shan Lu,Hongye Su

Journal

Green Energy and Intelligent Transportation

Published Date

2024/2/9

In this paper, a metal object detection (MOD) for wireless electric vehicle charger (WEVC) employing DD coils is proposed. Conventional single-layer symmetric coils exhibit reduced sensitivity near the coils and blind-zone along their symmetry axis. To address these limitations, we propose a dual-layer MOD coil configuration. And in this configuration, the second coil layer features rectangular coils in the less sensitive regions, and an optimal concave-convex coil design is given. By using the configuration, the proposed design can enhance the sensitivity and overcome the blind-zone challenges. Finally, simulation and experimental results also show the effectiveness and robustness of the proposed design, which can also be used to improve the detection capability in wireless power transmission applications.

Towards efficient filter pruning via adaptive automatic structure search

Authors

Xiaozhou Xu,Jun Chen,Zhishan Li,Hongye Su,Lei Xie

Journal

Engineering Applications of Artificial Intelligence

Published Date

2024/7/1

Filter pruning is a critical technique for compressing large convolutional neural networks, making it possible to deploy deep networks on resource-limited edge devices. However, previous pruning methods typically concentrate on removing filters with rule-of-thumb designs and empirically set the pruning rate per layer, which is prone to produce sub-optimal pruning. To address this issue, we develop a Filter Pruning method via Adaptive Automatic Structure Search (FP-AASS), which treats filter pruning as a structure optimization task. In FP-AASS, we employ the artificial bee colony algorithm to automatically search for the optimal pruned structure that meets the FLOPs and parameters constraints. The structure search process is divided into two stages through an additional adjustment phase to reduce the time consumption caused by the large search space. We also adopt adaptive batch normalization in the …

GeoPro-VO: Dynamic Obstacle Avoidance with Geometric Projector Based on Velocity Obstacle

Authors

Jihao Huang,Xuemin Chi,Jun Zeng,Zhitao Liu,Hongye Su

Journal

arXiv preprint arXiv:2403.10043

Published Date

2024/3/15

Optimization-based approaches are widely employed to generate optimal robot motions while considering various constraints, such as robot dynamics, collision avoidance, and physical limitations. It is crucial to efficiently solve the optimization problems in practice, yet achieving rapid computations remains a great challenge for optimization-based approaches with nonlinear constraints. In this paper, we propose a geometric projector for dynamic obstacle avoidance based on velocity obstacle (GeoPro-VO) by leveraging the projection feature of the velocity cone set represented by VO. Furthermore, with the proposed GeoPro-VO and the augmented Lagrangian spectral projected gradient descent (ALSPG) algorithm, we transform an initial mixed integer nonlinear programming problem (MINLP) in the form of constrained model predictive control (MPC) into a sub-optimization problem and solve it efficiently. Numerical simulations are conducted to validate the fast computing speed of our approach and its capability for reliable dynamic obstacle avoidance.

Tampering attack detection for remote interval observer

Authors

Tao Chen,Zhitao Liu,Hongye Su

Journal

Journal of the Franklin Institute

Published Date

2024/1/1

In cyber–physical systems (CPSs), secure estimation observes the states of a physical plant remotely with potentially attacked data. Most attacks in CPSs are carefully designed such that they can not only ruin the estimation but also bypass the detector. These attacked estimations would corrupt decision-making and control, leading to decreased production efficiency and even equipment damage. Therefore, detecting these attacks is of great importance. It is noted that one of the reasons that these attacks can be successfully launched is that attackers can inject arbitrary false data into the communication channel at any time step, which makes it possible that the transmission data is tampered with by any designed attack sequences. In this paper, a modified data transmission mechanism is deployed to limit the attacker’s ability, and attack detectors are designed for detecting tampering attacks. Specifically, first of all, a …

Decentralized Zeno-Free Event-Triggered Control For Multiple Networks Subject to Stochastic Network Delays and Poisson Pulsing Attacks

Authors

Dandan Zhang,Sandra Hirche,Stefan Sosnowski,Xin Jin,Hongye Su

Journal

arXiv preprint arXiv:2401.14750

Published Date

2024/1/26

By designing the decentralized time-regularized (Zeno-free) event-triggered strategies for the state-feedback control law, this paper considers the stochastic stabilization of a class of networked control systems, where two sources of randomness exist in multiple decentralized networks that operate asynchronously and independently: the communication channels are constrained by the stochastic network delays and also by Poisson pulsing denial-of-service (Pp-DoS) attacks. The time delay in the network denotes the length from a transmission instant to the corresponding update instant, and is supposed to be a continuous random variable subject to certain continuous probability distribution; while the attacks' cardinal number is a discrete random variable supposed to be subject to Poisson distribution, so the inter-attack time, i.e., the time between two consecutive attack instants, is subject to exponential distribution. The considered system is modeled as a stochastic hybrid formalism, where the randomness enters through the jump map into the reset value (the inter-attack time directly related) of each triggered strategy. By only sampling/transmitting state measurements when needed and simultaneously by taking the specific medium access protocols into account, the designed event-triggered strategies are synthesized in a state-based and decentralized form, which are robust (tolerable well) to stochastic network delays, under different tradeoff-conditions between the minimum inter-event times, maximum allowable delays (i.e., potentially tolerable delays) and the frequencies of attacks. Using stochastic hybrid tools to combine attack-active parts with …

Dynamic fault detection and diagnosis of industrial alkaline water electrolyzer process with variational Bayesian dictionary learning

Authors

Qi Zhang,Shan Lu,Lei Xie,Weihua Xu,Hongye Su

Journal

International Journal of Hydrogen Energy

Published Date

2024/5/2

Alkaline Water Electrolysis (AWE) is one of the simplest green hydrogen production method using renewable energy. AWE system typically yields process variables that are serially correlated and contaminated by measurement uncertainty. A novel robust dynamic variational Bayesian dictionary learning (RDVDL) monitoring approach is proposed to improve the reliability and safety of AWE operation. RDVDL employs a sparse Bayesian dictionary learning to preserve the dynamic mechanism information of AWE process which allows the easy interpretation of fault detection results. To improve the robustness to measurement uncertainty, a low-rank vector autoregressive (VAR) method is derived to reliably extract the serial correlation from process variables. The effectiveness of the proposed approach is demonstrated with an industrial hydrogen production process, and RDVDL can efficiently detect and diagnose …

Chaotic Masking Protocol for Secure Communication and Attack Detection in Remote Estimation of Cyber-Physical Systems

Authors

Tao Chen,Andreu Cecilia,Daniele Astolfi,Lei Wang,Zhitao Liu,Hongye Su

Journal

arXiv preprint arXiv:2403.09076

Published Date

2024/3/14

In remote estimation of cyber-physical systems (CPSs), sensor measurements transmitted through network may be attacked by adversaries, leading to leakage risk of privacy (e.g., the system state), and/or failure of the remote estimator. To deal with this problem, a chaotic masking protocol is proposed in this paper to secure the sensor measurements transmission. In detail, at the plant side, a chaotic dynamic system is deployed to encode the sensor measurement, and at the estimator side, an estimator estimates both states of the physical plant and the chaotic system. With this protocol, no additional secure communication links is needed for synchronization, and the masking effect can be perfectly removed when the estimator is in steady state. Furthermore, this masking protocol can deal with multiple types of attacks, i.e., eavesdropping attack, replay attack, and stealthy false data injection attack.

Adaptive multi-scale TF-net for high-resolution time–frequency representations

Authors

Tao Chen,Qiming Chen,Qian Zheng,Zhishan Li,Ziyi Zhang,Lei Xie,Hongye Su

Journal

Signal Processing

Published Date

2024/1/1

A novel adaptive multi-scale time–frequency network (AMTFN) is proposed to provide high-resolution time–frequency representations for nonstationary signals. AMTFN is an end-to-end deep network, which firstly adaptively learns the comprehensive basis functions to produce time–frequency (TF) feature maps through multi-scale 1D convolutional kernels. Then, the channel attention mechanism is embedded into AMTFN to rescale the TF feature maps selectively. Thus, the subsequent residual encoder–decoder block’s energy concentration performance is greatly improved with these rescaled TF feature maps. Besides, this paper designs a new training strategy to elegantly enable the model to pay more attention to the intersections of instantaneous frequency trajectories. In the end, a series of simulations as well as real-world cases, are studied to demonstrate the effectiveness and advantages of the proposed …

Backstepping control of an underactuated hyperbolic-parabolic coupled PDE system

Authors

Guangwei Chen,Rafael Vazquez,Zhitao Liu,Hongye Su

Journal

IEEE Transactions on Automatic Control

Published Date

2023/5/25

This article considers a class of hyperbolic–parabolic partial differential equation (PDE) system with some interior mixed-coupling terms, a rather unexplored family of systems. The family of systems we explore contains several interior-coupling terms, which makes controller design more challenging. Our goal is to design a boundary controller to exponentially stabilize the coupled system. For that, we propose a controller whose design is based on the backstepping method. Under this controller, we analyze the stability of the closed loop in the sense. A set of (highly coupled) backstepping kernel equations is derived, and their well-posedness is shown in the appropriate spaces by an infinite induction energy series, which has not been used before in this setting. Moreover, we show the invertibility of transformations by displaying the inverse transformations, as required for closed-loop well-posedness and stability …

See List of Professors in Hongye Su University(Zhejiang University)

Hongye Su FAQs

What is Hongye Su's h-index at Zhejiang University?

The h-index of Hongye Su has been 57 since 2020 and 82 in total.

What are Hongye Su's top articles?

The articles with the titles of

Nonlinear sparse variational Bayesian learning based model predictive control with application to PEMFC temperature control

Predictor-Based ADRC for Dynamic Wireless Power Transfer System with Voltage Fluctuation Damping and Measurement Noise Filtering

Distributed Least-Squares Optimization Solvers with Differential Privacy

Deep Reinforcement Learning for Autonomous Driving with an Auxiliary Actor Discriminator

Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Perspectives

Dynamic fault detection and diagnosis for alkaline water electrolyzer with variational Bayesian Sparse principal component analysis

Optimal Output Regulation for EV Dynamic Wireless Charging System via Internal Model-Based Control

Detection of Oscillations in Process Control Loops from Visual Image Space Using Deep Convolutional Networks

...

are the top articles of Hongye Su at Zhejiang University.

What is Hongye Su's total number of citations?

Hongye Su has 24,703 citations in total.

    academic-engine

    Useful Links