Peng Liang
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
Peng Liang has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Jianhua Guo
Guangdong Polytechnic Normal University
3 shared publications Hai-Dong Yang
School of Mechanical Engineering, Guangdong University of Technology, Guangzhou, China
2 shared publications- Huihui Li
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2 shared publications Wa He
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, People's Republic of China
2 shared publications- Xiangling Xiao
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2 shared publications - Xiaoyong Liu
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2 shared publications
Latest Publications
- 18 May 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (25) , 15705-15720
Hybrid Shunted Transformer embedding UNet for remote sensing image semantic segmentation
- 18 May 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (25) , 15705-15720
Hybrid Shunted Transformer embedding UNet for remote sensing image semantic segmentation
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Research on Flatness Measurement of Large-Size Parts Based on 3-D Machine Vision
Measuring geometric properties for large-sized parts is faced with various challenges. This study established a novel method for measuring the flatness of large-scale annular workpieces, with the flange of a wind turbine tower as an example. The proposed method is based on three-dimensional (3D) machine vision and precision motion control technology, aiming to address issues such as distorted measurements, long measurement times, and significant safety risks. The study primarily focused on the development of algorithms for measuring the flatness of large-sized annular workpieces through region-based measurement and vertical centering. The system employs a rotating arm equipped with a 3D vision sensor driven by a precision motion control system. A constant-speed laser line scans the surface of the large-sized flange to acquire precise point cloud data. The obtained point cloud data are then processed to determine the flatness of the flange surface. A verification test was conducted on a wind turbine tower flange with a diameter of 4.2 m to validate the functionality of the system. The results indicated that the proposed system enables stable and accurate measurement of flange flatness, and the measurement uncertainty was analyzed using the guide to the uncertainty in the measurement method, yielding an expanded uncertainty of 0.072 mm. The results indicated that the developed flatness measurement system can efficiently, accurately, and consistently measure the flatness of large annular flanges. This provides valuable insights for the geometric measurement of large annular parts in various fields such as wind power, engineering machinery, ships, and military industries.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Research on Flatness Measurement of Large-Size Parts Based on 3-D Machine Vision
Measuring geometric properties for large-sized parts is faced with various challenges. This study established a novel method for measuring the flatness of large-scale annular workpieces, with the flange of a wind turbine tower as an example. The proposed method is based on three-dimensional (3D) machine vision and precision motion control technology, aiming to address issues such as distorted measurements, long measurement times, and significant safety risks. The study primarily focused on the development of algorithms for measuring the flatness of large-sized annular workpieces through region-based measurement and vertical centering. The system employs a rotating arm equipped with a 3D vision sensor driven by a precision motion control system. A constant-speed laser line scans the surface of the large-sized flange to acquire precise point cloud data. The obtained point cloud data are then processed to determine the flatness of the flange surface. A verification test was conducted on a wind turbine tower flange with a diameter of 4.2 m to validate the functionality of the system. The results indicated that the proposed system enables stable and accurate measurement of flange flatness, and the measurement uncertainty was analyzed using the guide to the uncertainty in the measurement method, yielding an expanded uncertainty of 0.072 mm. The results indicated that the developed flatness measurement system can efficiently, accurately, and consistently measure the flatness of large annular flanges. This provides valuable insights for the geometric measurement of large annular parts in various fields such as wind power, engineering machinery, ships, and military industries.
- 10 August 2022
- Published by Springer Nature in The Visual Computer
- Vol. 39 (10) , 4709-4720
Heuristic objective for facial expression recognition
- 10 August 2022
- Published by Springer Nature in The Visual Computer
- Vol. 39 (10) , 4709-4720
Heuristic objective for facial expression recognition
- Open Access
A GAPN Approach for the Flexible Job-Shop Scheduling Problem with Indirect Energy and Time-of-Use Electricity Pricing
The flexible job-shop scheduling problem with indirect energy and time-of-use (ToU) electricity pricing (FJSP-IT) is investigated. Considering the production cost, which includes the indirect energy cost, direct energy cost and time cost, the cost evaluation model under ToU pricing is built. To minimize the total production cost of the FJSP-IT, an approach based on a genetic algorithm and Petri nets (GAPN) is presented. Under this approach, indirect energy and direct energy are modeled with Petri net (PN) nodes, the operation time is evaluated through PN simulation, and resource allocation is fine-tuned through genetic operations. A group of heuristic operation time policies, especially the exhausting subsection policy and two mixed policies, are presented to adapt to the FJSP-IT with vague cost components. Experiments were performed on a data set generated from the banburying shop of a rubber tire plant, and the results show that the proposed GAPN approach has good convergence. Using the proposed operation time policies makes it possible to save 10.81% on the production cost compared to using the single off-peak first or passive delay policy, and considering indirect energy makes it possible to save at least 2.09% on the production cost compared to ignoring indirect energy.
Open AccessA GAPN Approach for the Flexible Job-Shop Scheduling Problem with Indirect Energy and Time-of-Use Electricity Pricing
The flexible job-shop scheduling problem with indirect energy and time-of-use (ToU) electricity pricing (FJSP-IT) is investigated. Considering the production cost, which includes the indirect energy cost, direct energy cost and time cost, the cost evaluation model under ToU pricing is built. To minimize the total production cost of the FJSP-IT, an approach based on a genetic algorithm and Petri nets (GAPN) is presented. Under this approach, indirect energy and direct energy are modeled with Petri net (PN) nodes, the operation time is evaluated through PN simulation, and resource allocation is fine-tuned through genetic operations. A group of heuristic operation time policies, especially the exhausting subsection policy and two mixed policies, are presented to adapt to the FJSP-IT with vague cost components. Experiments were performed on a data set generated from the banburying shop of a rubber tire plant, and the results show that the proposed GAPN approach has good convergence. Using the proposed operation time policies makes it possible to save 10.81% on the production cost compared to using the single off-peak first or passive delay policy, and considering indirect energy makes it possible to save at least 2.09% on the production cost compared to ignoring indirect energy.
- Open Access
- 1 April 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1518 (1) , 012042
Using Darts to Improve Mold ID Recognition Model Based on MASK R-CNN
Mask R-CNN model is an excellent image segmentation model, but cannot perform well on the task of mold ID recognition. To address the aboved problem, this paper improves the classification branch of Mask R-CNN model by applying DARTs, making the improved classification branch more suitable for mold ID recognition task. Firstly, DARTs is employed to obtain network cell structure. Secondly, the network cell structure is used to improve the classification branch. Moreover, we make the model converge under 2GPU days based on transfer learning. Finally, the experimental results show that the improved model can achieve higher accuracy with IOU of 0.5 (increased by 1.02%) and 0.75 (increased by 2.42%).
- 1 April 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1518 (1) , 012042
Open AccessUsing Darts to Improve Mold ID Recognition Model Based on MASK R-CNN
Mask R-CNN model is an excellent image segmentation model, but cannot perform well on the task of mold ID recognition. To address the aboved problem, this paper improves the classification branch of Mask R-CNN model by applying DARTs, making the improved classification branch more suitable for mold ID recognition task. Firstly, DARTs is employed to obtain network cell structure. Secondly, the network cell structure is used to improve the classification branch. Moreover, we make the model converge under 2GPU days based on transfer learning. Finally, the experimental results show that the improved model can achieve higher accuracy with IOU of 0.5 (increased by 1.02%) and 0.75 (increased by 2.42%).
- 11 November 2019
- Published by European Society of Computational Methods in Sciences and Engineering in Journal of Computational Methods in Sciences and Engineering
- Vol. 19 (4) , 929-941
Job-shop scheduling problem considering power cost and makespan under time-of-use electricity price
In order to solve the problem of minimizing power cost and makespan with time-of-use electricity. A genetic algorithm based on individual concentration and similarity vector distance strategy is proposed. The proposed genetic algorithm overcomes prem
- 11 November 2019
- Published by European Society of Computational Methods in Sciences and Engineering in Journal of Computational Methods in Sciences and Engineering
- Vol. 19 (4) , 929-941
Job-shop scheduling problem considering power cost and makespan under time-of-use electricity price
In order to solve the problem of minimizing power cost and makespan with time-of-use electricity. A genetic algorithm based on individual concentration and similarity vector distance strategy is proposed. The proposed genetic algorithm overcomes prem
- 28 June 2018
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 35 (4) , 4215-4224
Network resource information scheduling based on non-convex function optimization algorithm
When the network resource information is scheduled with the current algorithm, the execution time of the resource scheduling task cannot be improved. The utilization of network resources is reduced in the case of the heavy scheduling task. To address this problem, a network resource information scheduling based on non-convex function optimization algorithm is proposed in this paper. The network resource is modeled as a non-convex function. The execution interval of task is divided into subspaces of multiple units. Task density is introduced into network resource scheduling model. In this model, computing resources and storage resources of the network are considered. Ant colony particle swarm optimization algorithm is used for scheduling with the built network resource scheduling model. The initial solution is obtained by initial search with the particle swarm algorithm. Then the initial solution is transformed into the initial pheromone distribution of the ant colony. The resource information is searched by using ant colony algorithm until the optimal solution is found, so as to achieve network resource information scheduling. Experimental results show that the proposed algorithm can reduce the execution time of task and improve the utilization rate of network resource information.
- 28 June 2018
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 35 (4) , 4215-4224
Network resource information scheduling based on non-convex function optimization algorithm
When the network resource information is scheduled with the current algorithm, the execution time of the resource scheduling task cannot be improved. The utilization of network resources is reduced in the case of the heavy scheduling task. To address this problem, a network resource information scheduling based on non-convex function optimization algorithm is proposed in this paper. The network resource is modeled as a non-convex function. The execution interval of task is divided into subspaces of multiple units. Task density is introduced into network resource scheduling model. In this model, computing resources and storage resources of the network are considered. Ant colony particle swarm optimization algorithm is used for scheduling with the built network resource scheduling model. The initial solution is obtained by initial search with the particle swarm algorithm. Then the initial solution is transformed into the initial pheromone distribution of the ant colony. The resource information is searched by using ant colony algorithm until the optimal solution is found, so as to achieve network resource information scheduling. Experimental results show that the proposed algorithm can reduce the execution time of task and improve the utilization rate of network resource information.
- 24 August 2017
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 31 (4-5) , 396-405
Transfer learning for aluminium extrusion electricity consumption anomaly detection via deep neural networks
Effective anomaly detection can reduce the electricity consumption and carbon emissions in aluminium extrusion processes. The following two steps identify anomalies: electricity consumption forecasting and anomaly detection. Data-driven modelling is typical paradigm for building an accurate forecasting model. For a new extruding machine, there is insufficient extruded data for model training. The research objective of this work is to determine whether a forecasting model can be trained by transferring knowledge from a data-sufficient domain to a data-insufficient domain. A shared connected deep neural network is proposed for electricity consumption time-series anomaly forecasting. Anomalies are detected by the difference of predicted and measured values at a confidence interval. The experimental results show that the proposed approach can identify electricity anomaly events in real time. Furthermore, it is shown that transferring learning knowledge between domains significantly improves the forecasting results.
- 24 August 2017
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 31 (4-5) , 396-405
Transfer learning for aluminium extrusion electricity consumption anomaly detection via deep neural networks
Effective anomaly detection can reduce the electricity consumption and carbon emissions in aluminium extrusion processes. The following two steps identify anomalies: electricity consumption forecasting and anomaly detection. Data-driven modelling is typical paradigm for building an accurate forecasting model. For a new extruding machine, there is insufficient extruded data for model training. The research objective of this work is to determine whether a forecasting model can be trained by transferring knowledge from a data-sufficient domain to a data-insufficient domain. A shared connected deep neural network is proposed for electricity consumption time-series anomaly forecasting. Anomalies are detected by the difference of predicted and measured values at a confidence interval. The experimental results show that the proposed approach can identify electricity anomaly events in real time. Furthermore, it is shown that transferring learning knowledge between domains significantly improves the forecasting results.
- Open Access
- 1 January 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-8
An Ant Optimization Model for Unrelated Parallel Machine Scheduling with Energy Consumption and Total Tardiness
This research considers an unrelated parallel machine scheduling problem with energy consumption and total tardiness. This problem is compounded by two challenges: differences of unrelated parallel machines energy consumption and interaction between job assignments and machine state operations. To begin with, we establish a mathematical model for this problem. Then an ant optimization algorithm based on ATC heuristic rule (ATC-ACO) is presented. Furthermore, optimal parameters of proposed algorithm are defined via Taguchi methods for generating test data. Finally, comparative experiments indicate the proposed ATC-ACO algorithm has better performance on minimizing energy consumption as well as total tardiness and the modified ATC heuristic rule is more effectively on reducing energy consumption.
- 1 January 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-8
Open AccessAn Ant Optimization Model for Unrelated Parallel Machine Scheduling with Energy Consumption and Total Tardiness
This research considers an unrelated parallel machine scheduling problem with energy consumption and total tardiness. This problem is compounded by two challenges: differences of unrelated parallel machines energy consumption and interaction between job assignments and machine state operations. To begin with, we establish a mathematical model for this problem. Then an ant optimization algorithm based on ATC heuristic rule (ATC-ACO) is presented. Furthermore, optimal parameters of proposed algorithm are defined via Taguchi methods for generating test data. Finally, comparative experiments indicate the proposed ATC-ACO algorithm has better performance on minimizing energy consumption as well as total tardiness and the modified ATC heuristic rule is more effectively on reducing energy consumption.