Zhenbo Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhenbo Cheng has a total of 98 co-authors. Here are the top co-authors by number of shared publications:
Gang Xiao
Zhejiang University of Technology
6 shared publications- Gang Xiao
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
5 shared publications Diting Zhou
Zhejiang University of Technology
3 shared publications- Tianming Yang
Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences
3 shared publications Xuesong Xu
Zhejiang University of Technology
3 shared publications- Yuanming Zhang
Zhejiang University of Technology
3 shared publications
Latest Publications
- 15 July 2026
- Published by Springer Nature
- p. 559-570
Neural TSP Solver with Translation-Invariant and Clustering-Aware Mechanisms
- 15 July 2026
- Published by Springer Nature
- p. 559-570
Neural TSP Solver with Translation-Invariant and Clustering-Aware Mechanisms
- 3 January 2026
- Published by Springer Nature
- p. 64-75
Node Classification and Link Prediction Methods Based on Hybrid Teacher Models
- 3 January 2026
- Published by Springer Nature
- p. 64-75
Node Classification and Link Prediction Methods Based on Hybrid Teacher Models
- 2 January 2026
- Published by Springer Nature
- p. 201-211
Prompt Optimization Method Based on Explicit Multi-step Reasoning Paths
- 2 January 2026
- Published by Springer Nature
- p. 201-211
Prompt Optimization Method Based on Explicit Multi-step Reasoning Paths
- 2 January 2026
- Published by Springer Nature
- p. 147-155
Two Level Index Generation Method Based on Multi-Granularity Retrieval Unit Fusion
- 2 January 2026
- Published by Springer Nature
- p. 147-155
Two Level Index Generation Method Based on Multi-Granularity Retrieval Unit Fusion
- 2 January 2026
- Published by Springer Nature
- p. 337-346
Elevator Wire Rope Condition Monitoring Framework Based on Parallel Projection and Shape-Adaptive Convolution
- 2 January 2026
- Published by Springer Nature
- p. 337-346
Elevator Wire Rope Condition Monitoring Framework Based on Parallel Projection and Shape-Adaptive Convolution
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SAAB: Enhancing Action Segmentation via Spatial Attention Pooling and Action-Background Classifier
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSAAB: Enhancing Action Segmentation via Spatial Attention Pooling and Action-Background Classifier
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1358-1366
EPNet: Efficient Part Segmentation for Dense Point Clouds
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1358-1366
Open AccessEPNet: Efficient Part Segmentation for Dense Point Clouds
- Open Access
- 11 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (6) , 932
Flexible Job Shop Dynamic Scheduling and Fault Maintenance Personnel Cooperative Scheduling Optimization Based on the ACODDQN Algorithm
In order to address the impact of equipment fault diagnosis and repair delays on production schedule execution in the dynamic scheduling of flexible job shops, this paper proposes a multi-resource, multi-objective dynamic scheduling optimization model, which aims to minimize delay time and completion time. It integrates the scheduling of the workpieces, machines, and maintenance personnel to improve the response efficiency of emergency equipment maintenance. To this end, a self-learning Ant Colony Algorithm based on deep reinforcement learning (ACODDQN) is designed in this paper. The algorithm searches the solution space by using the ACO, prioritizes the solutions by combining the non-dominated sorting strategies, and achieves the adaptive optimization of scheduling decisions by utilizing the organic integration of the pheromone update mechanism and the DDQN framework. Further, the generated solutions are locally adjusted via the feasible solution optimization strategy to ensure that the solutions satisfy all the constraints and ultimately generate a Pareto optimal solution set with high quality. Simulation results based on standard examples and real cases show that the ACODDQN algorithm exhibits significant optimization effects in several tests, which verifies its superiority and practical application potential in dynamic scheduling problems.
- 11 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (6) , 932
Open AccessFlexible Job Shop Dynamic Scheduling and Fault Maintenance Personnel Cooperative Scheduling Optimization Based on the ACODDQN Algorithm
In order to address the impact of equipment fault diagnosis and repair delays on production schedule execution in the dynamic scheduling of flexible job shops, this paper proposes a multi-resource, multi-objective dynamic scheduling optimization model, which aims to minimize delay time and completion time. It integrates the scheduling of the workpieces, machines, and maintenance personnel to improve the response efficiency of emergency equipment maintenance. To this end, a self-learning Ant Colony Algorithm based on deep reinforcement learning (ACODDQN) is designed in this paper. The algorithm searches the solution space by using the ACO, prioritizes the solutions by combining the non-dominated sorting strategies, and achieves the adaptive optimization of scheduling decisions by utilizing the organic integration of the pheromone update mechanism and the DDQN framework. Further, the generated solutions are locally adjusted via the feasible solution optimization strategy to ensure that the solutions satisfy all the constraints and ultimately generate a Pareto optimal solution set with high quality. Simulation results based on standard examples and real cases show that the ACODDQN algorithm exhibits significant optimization effects in several tests, which verifies its superiority and practical application potential in dynamic scheduling problems.
- Open Access
- 30 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 31-36
Research on Steel Belt Elevator Technology Based on Patentometric Analysis
Using the Patsnap patent database as a data source, this study analyzes the research and development trends of steel belt elevator technology from the perspectives of time distribution, geographic distribution, technological direction, and research themes. The analysis aims to clarify China's position in the global elevator technology landscape and provide a basis for addressing technological gaps. The study focuses on three key areas: steel belt materials, steel belt structures, and steel belt damage detection. The results indicate that: 1) The number of global patents related to steel belt elevators has been steadily increasing; 2) The major patent-holding countries are China, the United States, Switzerland, Finland, Japan, and Germany. China leads in the number of patents, but its innovation impact is relatively low, while the United States and Switzerland are at the forefront of technological innovation; 3) The main target regions for these patents are China, the United States, and Iran, with several elevator companies having already established patent portfolios in China and Iran; 4) Current research primarily covers steel belt materials, structures, and damage detection, with the critical challenge being the need for more efficient, accurate, and convenient methods for detecting steel belt damage.
- 30 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 31-36
Open AccessResearch on Steel Belt Elevator Technology Based on Patentometric Analysis
Using the Patsnap patent database as a data source, this study analyzes the research and development trends of steel belt elevator technology from the perspectives of time distribution, geographic distribution, technological direction, and research themes. The analysis aims to clarify China's position in the global elevator technology landscape and provide a basis for addressing technological gaps. The study focuses on three key areas: steel belt materials, steel belt structures, and steel belt damage detection. The results indicate that: 1) The number of global patents related to steel belt elevators has been steadily increasing; 2) The major patent-holding countries are China, the United States, Switzerland, Finland, Japan, and Germany. China leads in the number of patents, but its innovation impact is relatively low, while the United States and Switzerland are at the forefront of technological innovation; 3) The main target regions for these patents are China, the United States, and Iran, with several elevator companies having already established patent portfolios in China and Iran; 4) Current research primarily covers steel belt materials, structures, and damage detection, with the critical challenge being the need for more efficient, accurate, and convenient methods for detecting steel belt damage.
- Open Access
- 2 August 2024
- Published by Elsevier in SSRN Electronic Journal
Review of Fault Modes and Fault Diagnosis Methods for Elevator Systems
With the development of large-scale urbanization and the proliferation of high-rise buildings, the use of elevators has become an indispensable part of life. Scientifically managing elevator operation safety and ensuring the efficient diagnosis and predictive maintenance of elevator failures is a problem that must be considered in the transition of the elevator industry into an intelligent industry. In this paper, the main elevator parts prone to fault are discussed, starting from the structure of the elevator, and the fault characteristics are analyzed. The current research in the field of elevator fault diagnosis and prediction is summarized, as are the application scope, operating conditions, and model effects of various methods. The methods of collecting elevator fault data and the latest progress in elevator fault diagnosis and prediction are reviewed. Finally, future research directions for developing diagnosis methods for elevator faults are proposed.
- 2 August 2024
- Published by Elsevier in SSRN Electronic Journal
Open AccessReview of Fault Modes and Fault Diagnosis Methods for Elevator Systems
With the development of large-scale urbanization and the proliferation of high-rise buildings, the use of elevators has become an indispensable part of life. Scientifically managing elevator operation safety and ensuring the efficient diagnosis and predictive maintenance of elevator failures is a problem that must be considered in the transition of the elevator industry into an intelligent industry. In this paper, the main elevator parts prone to fault are discussed, starting from the structure of the elevator, and the fault characteristics are analyzed. The current research in the field of elevator fault diagnosis and prediction is summarized, as are the application scope, operating conditions, and model effects of various methods. The methods of collecting elevator fault data and the latest progress in elevator fault diagnosis and prediction are reviewed. Finally, future research directions for developing diagnosis methods for elevator faults are proposed.