Yang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yang Liu has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Lei Bo
School of Mechanical Electronic & Information Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
14 shared publications - Zihang Zhang
School of Mechanical Electronic & Information Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
12 shared publications - Yiying Wang
College of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056000, China
7 shared publications - Yiying Wang
1 Handan Vocational College of Science and Technology, Handan, China
4 shared publications Shangqing Yang
School of Artificial Intelligence China University of Mining and Technology (Beijing) Beijing China
3 shared publications- Shangqing Yang
School of Mechanical Electronic & Information Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China
3 shared publications
Latest Publications
- 15 April 2025
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 35 (13) , 5438-5455
Consistent Cooperative Control of Multi‐Support Systems Using Multi‐Agent Reinforcement Learning With Attention Mechanism
The research aims to improve the coordinated management of solid filling support systems in mining to enhance efficiency, structural stability, and overall safety. Given the challenges posed by complex subterranean environments and stringent filling targets, current control methods are insufficient. This study proposes a cooperative control framework for multi‐filling support systems, modeling the consistency control problem as a multi‐agent reinforcement learning paradigm. Each filling unit acts as an agent, communicating its action state with others. A novel multi‐agent evaluation approach with an attention mechanism is introduced to facilitate path tracking and cooperative control. Considering constraints such as thrust, path deviation, and target position, simulation results show that the agents effectively collaborate to achieve the cooperative control of multi‐filling support groups in complex conditions, highlighting the significance of this approach.
- 15 April 2025
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 35 (13) , 5438-5455
Consistent Cooperative Control of Multi‐Support Systems Using Multi‐Agent Reinforcement Learning With Attention Mechanism
The research aims to improve the coordinated management of solid filling support systems in mining to enhance efficiency, structural stability, and overall safety. Given the challenges posed by complex subterranean environments and stringent filling targets, current control methods are insufficient. This study proposes a cooperative control framework for multi‐filling support systems, modeling the consistency control problem as a multi‐agent reinforcement learning paradigm. Each filling unit acts as an agent, communicating its action state with others. A novel multi‐agent evaluation approach with an attention mechanism is introduced to facilitate path tracking and cooperative control. Considering constraints such as thrust, path deviation, and target position, simulation results show that the agents effectively collaborate to achieve the cooperative control of multi‐filling support groups in complex conditions, highlighting the significance of this approach.
- Open Access
- 17 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Intelligent evaluation of coal mine solid filling effect using fuzzy logic and improved D-S evidence theory
Addressing the inherent fuzziness and uncertainty in filling outcomes, this paper proposes a novel method for evaluating the effectiveness of solid filling operations in coal mines by integrating Interval Type-2 Fuzzy Logic Systems (IT2FLS) with an improved Dempster-Shafer (D-S) evidence theory. Initially, local data fusion is conducted using IT2FLS-Adam, where interval type-2 fuzzy sets are employed to fuzzify input features, and the Adam optimizer is utilized for parameter optimization. This allows for preliminary judgments on filling effects from various perspectives based on local features. To overcome the limitations of local fusion, an improved D-S evidence theory is adopted, which effectively handles conflicting evidence by incorporating the Wasserstein distance and Deng entropy to combine the judgments from local features, achieving global data fusion. Experimental results demonstrate that the proposed method attains a remarkable accuracy of 92.9% in global fusion tasks, surpassing traditional methods. This study provides a data fusion framework for filling workfaces, integrating multi-sensor data and addressing the complexities and uncertainties associated with filling processes, thereby making a significant contribution to the intelligent monitoring and management of coal mine filling operations.
- 17 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Open AccessIntelligent evaluation of coal mine solid filling effect using fuzzy logic and improved D-S evidence theory
Addressing the inherent fuzziness and uncertainty in filling outcomes, this paper proposes a novel method for evaluating the effectiveness of solid filling operations in coal mines by integrating Interval Type-2 Fuzzy Logic Systems (IT2FLS) with an improved Dempster-Shafer (D-S) evidence theory. Initially, local data fusion is conducted using IT2FLS-Adam, where interval type-2 fuzzy sets are employed to fuzzify input features, and the Adam optimizer is utilized for parameter optimization. This allows for preliminary judgments on filling effects from various perspectives based on local features. To overcome the limitations of local fusion, an improved D-S evidence theory is adopted, which effectively handles conflicting evidence by incorporating the Wasserstein distance and Deng entropy to combine the judgments from local features, achieving global data fusion. Experimental results demonstrate that the proposed method attains a remarkable accuracy of 92.9% in global fusion tasks, surpassing traditional methods. This study provides a data fusion framework for filling workfaces, integrating multi-sensor data and addressing the complexities and uncertainties associated with filling processes, thereby making a significant contribution to the intelligent monitoring and management of coal mine filling operations.
- Open Access
- 6 January 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (2) , 026205
Optimized path planning for underground coal mine filling: an greedy adaptive directional bidirectional rapidly-exploring random tree
The technology of mining filling is of great significance in improving coal recovery rates, protecting the environment, and conserving land resources. The current efficiency of filling is constrained by single-method approaches. To address this issue, this study develops a path planning model based on underground fill space data, which comprehensively considers fill path length and material volume using a goal programming method, and designs corresponding constraints and adaptive weights. To further optimize search efficiency, an adaptive directional bidirectional rapidly-exploring random tree (AD-BIRRT) algorithm is proposed. This algorithm can intelligently adjust the optimal exploration direction based on current demand and state, significantly enhancing search efficiency and accuracy through the establishment of a dual-tree structure. Additionally, a novel greedy strategy is introduced to resolve path smoothing and redundancy issues. To verify the rationality and effectiveness of the proposed method, comparative tests were conducted in test scenarios, fill scenarios, and on experimental platforms against BIRRT, BIRRT*, Genetic algorithm, and artificial potential field algorithms. The results indicate that the proposed greedy AD-BIRRT algorithm exhibits significant advantages in terms of computation time, path quality, and material accumulation. This algorithm effectively enhances the efficiency and quality of the filling process.
- 6 January 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (2) , 026205
Open AccessOptimized path planning for underground coal mine filling: an greedy adaptive directional bidirectional rapidly-exploring random tree
The technology of mining filling is of great significance in improving coal recovery rates, protecting the environment, and conserving land resources. The current efficiency of filling is constrained by single-method approaches. To address this issue, this study develops a path planning model based on underground fill space data, which comprehensively considers fill path length and material volume using a goal programming method, and designs corresponding constraints and adaptive weights. To further optimize search efficiency, an adaptive directional bidirectional rapidly-exploring random tree (AD-BIRRT) algorithm is proposed. This algorithm can intelligently adjust the optimal exploration direction based on current demand and state, significantly enhancing search efficiency and accuracy through the establishment of a dual-tree structure. Additionally, a novel greedy strategy is introduced to resolve path smoothing and redundancy issues. To verify the rationality and effectiveness of the proposed method, comparative tests were conducted in test scenarios, fill scenarios, and on experimental platforms against BIRRT, BIRRT*, Genetic algorithm, and artificial potential field algorithms. The results indicate that the proposed greedy AD-BIRRT algorithm exhibits significant advantages in terms of computation time, path quality, and material accumulation. This algorithm effectively enhances the efficiency and quality of the filling process.
- 27 December 2024
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 33 (01)
NUMERICAL SIMULATION ON FLOW COUPLING IN A TRIPLE-FRACTURE NETWORK MODEL BASED ON FRACTAL GEOMETRY THEORY
This study presents numerical simulations on fluid flow under high stress and intense hydraulic activity and focuses on complex reservoirs with porous and fractured microstructures based on fractal geometry theory. A Triple-Fracture Network model, which includes pores, micro-fractures and macro-fractures, is categorized into fractal fracture networks and fractal pore systems based on fractal geometry theory. Using the Monte Carlo method, we construct macroscopic randomly distributed fractures to examine the impact of macro-fracture topological structures on flow dynamics. Fractal permeability models for micro-fracture and micro-pore systems are developed, incorporating variables such as fracture lengths and pore sizes. The proposed approach partitions porous media into macroscopically discrete fractures and microscopically characterized pores, utilizing fractal geometry theory to analyze hydro-mechanics coupling. The validity of the proposed model is confirmed through comparisons with analytical solutions and available models as well as the published field data. This results indicate that the spatial distribution of the effective stress and macroscopic fractures significantly affects the fractal dimensions of microscopic fractures and pores. It is found that the density of macro-fractures influences the fracture pressure, while the initial porosity and proportionality constant [ ] of micro-fractures impact the pressure distributions in the tested domains. It is found that the maximum length of micro-fractures correlates positively with permeability. This model introduces a novel perspective on random macro-fractures and fluid coupling in microstructures, enhancing the understanding of macro- and micro-hydrodynamics interactions.
- 27 December 2024
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 33 (01)
NUMERICAL SIMULATION ON FLOW COUPLING IN A TRIPLE-FRACTURE NETWORK MODEL BASED ON FRACTAL GEOMETRY THEORY
This study presents numerical simulations on fluid flow under high stress and intense hydraulic activity and focuses on complex reservoirs with porous and fractured microstructures based on fractal geometry theory. A Triple-Fracture Network model, which includes pores, micro-fractures and macro-fractures, is categorized into fractal fracture networks and fractal pore systems based on fractal geometry theory. Using the Monte Carlo method, we construct macroscopic randomly distributed fractures to examine the impact of macro-fracture topological structures on flow dynamics. Fractal permeability models for micro-fracture and micro-pore systems are developed, incorporating variables such as fracture lengths and pore sizes. The proposed approach partitions porous media into macroscopically discrete fractures and microscopically characterized pores, utilizing fractal geometry theory to analyze hydro-mechanics coupling. The validity of the proposed model is confirmed through comparisons with analytical solutions and available models as well as the published field data. This results indicate that the spatial distribution of the effective stress and macroscopic fractures significantly affects the fractal dimensions of microscopic fractures and pores. It is found that the density of macro-fractures influences the fracture pressure, while the initial porosity and proportionality constant [ ] of micro-fractures impact the pressure distributions in the tested domains. It is found that the maximum length of micro-fractures correlates positively with permeability. This model introduces a novel perspective on random macro-fractures and fluid coupling in microstructures, enhancing the understanding of macro- and micro-hydrodynamics interactions.
- Open Access
- 23 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 9673
Research on High-Frequency Isolated NPC Three-Level Inverter for Frequency Conversion and Speed Regulation
Mining frequency converters are the primary means for achieving variable frequency speed regulation of electromechanical equipment in coal mines, offering energy-saving benefits for coal mining enterprises. The common power supply method involves converting high voltage to low voltage using power frequency transformers before supplying equipment. However, this integration of power frequency transformers with supply devices occupies significant space, making it unsuitable for confined underground environments. Additionally, they suffer from poor output waveform quality and high harmonic content. To tackle these challenges, this paper presents a three-stage topology for high-frequency isolated frequency conversion and speed regulation, utilizing three-phase uncontrolled rectification, a single active isolated DC/DC converter, and an NPC three-level inverter. The control strategies for each stage are discussed in detail. Simulations and experimental results confirm the validity and feasibility of the proposed design, demonstrating enhanced stability and dynamic performance of the three-stage high-frequency isolated frequency converter.
- 23 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 9673
Open AccessResearch on High-Frequency Isolated NPC Three-Level Inverter for Frequency Conversion and Speed Regulation
Mining frequency converters are the primary means for achieving variable frequency speed regulation of electromechanical equipment in coal mines, offering energy-saving benefits for coal mining enterprises. The common power supply method involves converting high voltage to low voltage using power frequency transformers before supplying equipment. However, this integration of power frequency transformers with supply devices occupies significant space, making it unsuitable for confined underground environments. Additionally, they suffer from poor output waveform quality and high harmonic content. To tackle these challenges, this paper presents a three-stage topology for high-frequency isolated frequency conversion and speed regulation, utilizing three-phase uncontrolled rectification, a single active isolated DC/DC converter, and an NPC three-level inverter. The control strategies for each stage are discussed in detail. Simulations and experimental results confirm the validity and feasibility of the proposed design, demonstrating enhanced stability and dynamic performance of the three-stage high-frequency isolated frequency converter.
- Open Access
- 2 February 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (3) , 479
Research on Path Planning Method of Solid Backfilling and Pushing Mechanism Based on Adaptive Genetic Particle Swarm Optimization
This paper investigates the path planning problem of the coal mine solid-filling and pushing mechanism and proposes a hybrid improved adaptive genetic particle swarm algorithm (AGAPSO). To enhance the efficiency and accuracy of path planning, the algorithm combines a particle swarm optimization algorithm (PSO) and a genetic algorithm (GA), introducing the sharing mechanism and local search capability of the particle swarm optimization algorithm. The path planning of the pushing mechanism for the solid-filling scenario is optimized by dynamically adjusting the algorithm parameters to accommodate different search environments. Subsequently, the proposed algorithm’s effectiveness in the filling equipment path planning problem is experimentally verified using a simulation model of the established filling equipment path planning scenario. The experimental findings indicate that the improved hybrid algorithm converges three times faster than the original algorithm. Furthermore, it demonstrates approximately 92% and 94% better stability and average performance, respectively, than the original algorithm. Additionally, AGAPSO achieves a 27.59% and 19.16% improvement in path length and material usage optimization compared to the GA and GAPSO algorithms, showcasing superior efficiency and adaptability. Therefore, the AGAPSO method offers significant advantages in the path planning of the coal mine solid-filling and pushing mechanism, which is crucial for enhancing the filling effect and efficiency.
- 2 February 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (3) , 479
Open AccessResearch on Path Planning Method of Solid Backfilling and Pushing Mechanism Based on Adaptive Genetic Particle Swarm Optimization
This paper investigates the path planning problem of the coal mine solid-filling and pushing mechanism and proposes a hybrid improved adaptive genetic particle swarm algorithm (AGAPSO). To enhance the efficiency and accuracy of path planning, the algorithm combines a particle swarm optimization algorithm (PSO) and a genetic algorithm (GA), introducing the sharing mechanism and local search capability of the particle swarm optimization algorithm. The path planning of the pushing mechanism for the solid-filling scenario is optimized by dynamically adjusting the algorithm parameters to accommodate different search environments. Subsequently, the proposed algorithm’s effectiveness in the filling equipment path planning problem is experimentally verified using a simulation model of the established filling equipment path planning scenario. The experimental findings indicate that the improved hybrid algorithm converges three times faster than the original algorithm. Furthermore, it demonstrates approximately 92% and 94% better stability and average performance, respectively, than the original algorithm. Additionally, AGAPSO achieves a 27.59% and 19.16% improvement in path length and material usage optimization compared to the GA and GAPSO algorithms, showcasing superior efficiency and adaptability. Therefore, the AGAPSO method offers significant advantages in the path planning of the coal mine solid-filling and pushing mechanism, which is crucial for enhancing the filling effect and efficiency.
- Open Access
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 303-308
Research on filling effect determination of solid filling working face in coal mine based on multi-criteria decision analysis
The solid backfilling operation in coal mines constitutes a pivotal component of the coal industry, playing a crucial role in ensuring miner safety, enhancing coal extraction efficiency, and preserving ecological integrity. However, the determination of the efficacy of backfilling measures represents a pressing concern in the present context. Multiple Criteria Decision Analysis (MCDA) stands as a quantitative analytical approach tailored to address complex decision problems, capable of synthesizing diverse factors to furnish a scientific basis for decision-making. This paper endeavors to delve into the assessment of solid backfilling effectiveness in coal mine working faces using MCDA, with the aim of providing theoretical insight and practical guidance for pertinent domains.
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 303-308
Open AccessResearch on filling effect determination of solid filling working face in coal mine based on multi-criteria decision analysis
The solid backfilling operation in coal mines constitutes a pivotal component of the coal industry, playing a crucial role in ensuring miner safety, enhancing coal extraction efficiency, and preserving ecological integrity. However, the determination of the efficacy of backfilling measures represents a pressing concern in the present context. Multiple Criteria Decision Analysis (MCDA) stands as a quantitative analytical approach tailored to address complex decision problems, capable of synthesizing diverse factors to furnish a scientific basis for decision-making. This paper endeavors to delve into the assessment of solid backfilling effectiveness in coal mine working faces using MCDA, with the aim of providing theoretical insight and practical guidance for pertinent domains.
- Open Access
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 91-96
Motion trajectory planning of coal filling tamping mechanism based on improved DE algorithm
The filling and solidification method is employed in underground mines to backfill waste materials such as coal gangue, fly ash, and slag into the goaf, aiming to control strata movement and surface subsidence while addressing environmental pollution caused by solid waste. However, traditional filling methods suffer from low efficiency and excessive reliance on manpower. Therefore, this study conducts thorough research and planning on the motion trajectory of filling and compacting mechanisms. Firstly, we plan the environmental information of the filling area and establish a target function model for the critical point of materials. To solve this model, we employ the differential evolution algorithm for computation. However, the differential evolution algorithm is prone to falling into local optima. To address this issue, we adaptively improve the algorithm’s initialization method, scaling factor, and crossover probability. With the improved algorithm, we can more accurately calculate the target function for the critical point of materials and improve the algorithm’s accuracy and iteration speed. Through comparative analysis of simulation experiments, we find that our proposed method can effectively enhance filling efficiency and reduce manpower consumption compared to traditional approaches. Therefore, this research provides an effective method for the motion trajectory planning of filling and solidification mechanisms.
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 91-96
Open AccessMotion trajectory planning of coal filling tamping mechanism based on improved DE algorithm
The filling and solidification method is employed in underground mines to backfill waste materials such as coal gangue, fly ash, and slag into the goaf, aiming to control strata movement and surface subsidence while addressing environmental pollution caused by solid waste. However, traditional filling methods suffer from low efficiency and excessive reliance on manpower. Therefore, this study conducts thorough research and planning on the motion trajectory of filling and compacting mechanisms. Firstly, we plan the environmental information of the filling area and establish a target function model for the critical point of materials. To solve this model, we employ the differential evolution algorithm for computation. However, the differential evolution algorithm is prone to falling into local optima. To address this issue, we adaptively improve the algorithm’s initialization method, scaling factor, and crossover probability. With the improved algorithm, we can more accurately calculate the target function for the critical point of materials and improve the algorithm’s accuracy and iteration speed. Through comparative analysis of simulation experiments, we find that our proposed method can effectively enhance filling efficiency and reduce manpower consumption compared to traditional approaches. Therefore, this research provides an effective method for the motion trajectory planning of filling and solidification mechanisms.