Jiatang 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
Jiatang Cheng has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
Yan Xiong
Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology) Guilin China
7 shared publications- Yan Xiong
College of Mechanical and Control Engineering, Guilin University of Technology
5 shared publications Kaike Tu
Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology) Guilin China
2 shared publications- Lei Wang
Xi’an University of Technology
2 shared publications - Qiuhong Lin
School of Artificial Intelligence, Hezhou University, Hezhou, 542899, People’s Republic of China
2 shared publications - Zhichao Feng
College of Electronic Engineering, Guilin Institute of Information Technology, Guilin 541100, Guangxi, P. R. China
2 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11116
Diagnosis-Oriented GNA–VMD Parameter Selection for Planetary Gearbox Fault Diagnosis: A Record-Level Cross-Condition Evaluation
Planetary gearbox diagnosis is challenged by nonstationary vibration, acquisition-condition variation, and noise. This study proposes a GNA-VMD temporal convolution–Transformer (GNA-VMD-TCT) method. The Geomagnetic Navigation Algorithm jointly optimizes the VMD mode count and penalty factor using a diagnosis-oriented fitness function that combines envelope entropy, modal redundancy, Fisher class separability, and a mode-count penalty. The resulting multi-channel intrinsic mode functions are processed by a temporal convolution–Transformer network integrating multi-scale convolution, gated temporal convolution, Transformer encoding, and cross-gated fusion. Under MAT-file-level splitting and source-validation-based checkpoint selection, five-seed cross-condition Macro-F1 was 31.33 ± 8.12% for Condition 1 → 2 and 29.68 ± 5.73% for Condition 2 → 1, with no consistent advantage over the baseline methods. Retrospective within-condition tests favored Raw-TCT, and operator-level ablations did not confirm consistent gains from every network component. Gaussian-noise tests using fixed seed-0 checkpoints and three noise realizations per SNR likewise showed no consistent robustness advantage. Although the revised runs excluded target data from GNA optimization, network training, and checkpoint selection, target results had been examined during earlier exploratory work, so the evaluation was not fully blind. These findings characterize the limitations of diagnosis-oriented VMD parameter selection under acquisition shifts and noise.
- 10 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11116
Open AccessDiagnosis-Oriented GNA–VMD Parameter Selection for Planetary Gearbox Fault Diagnosis: A Record-Level Cross-Condition Evaluation
Planetary gearbox diagnosis is challenged by nonstationary vibration, acquisition-condition variation, and noise. This study proposes a GNA-VMD temporal convolution–Transformer (GNA-VMD-TCT) method. The Geomagnetic Navigation Algorithm jointly optimizes the VMD mode count and penalty factor using a diagnosis-oriented fitness function that combines envelope entropy, modal redundancy, Fisher class separability, and a mode-count penalty. The resulting multi-channel intrinsic mode functions are processed by a temporal convolution–Transformer network integrating multi-scale convolution, gated temporal convolution, Transformer encoding, and cross-gated fusion. Under MAT-file-level splitting and source-validation-based checkpoint selection, five-seed cross-condition Macro-F1 was 31.33 ± 8.12% for Condition 1 → 2 and 29.68 ± 5.73% for Condition 2 → 1, with no consistent advantage over the baseline methods. Retrospective within-condition tests favored Raw-TCT, and operator-level ablations did not confirm consistent gains from every network component. Gaussian-noise tests using fixed seed-0 checkpoints and three noise realizations per SNR likewise showed no consistent robustness advantage. Although the revised runs excluded target data from GNA optimization, network training, and checkpoint selection, target results had been examined during earlier exploratory work, so the evaluation was not fully blind. These findings characterize the limitations of diagnosis-oriented VMD parameter selection under acquisition shifts and noise.
- 11 October 2026
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 38 (20)
Multi‐Strategy Snow Ablation Optimizer for Global Optimization
The snow ablation optimizer (SAO) is a novel meta‐heuristic algorithm inspired by the natural processes of snow melting and sublimation. SAO employs a dual‐population dynamic adjustment mechanism to balance exploration and exploitation, demonstrating significant performance in global optimization. However, when dealing with complex optimization problems, the SAO algorithm tends to suffer from low convergence accuracy and premature convergence. To address these issues, this paper proposes a multi‐strategy snow ablation optimizer (MSSAO). Firstly, it adopts an external archive mechanism to prevent convergence to local optima. Secondly, it utilizes an adaptive t ‐distribution perturbation strategy to achieve a balance between exploration and exploitation. Finally, it employs a mirror reflection learning strategy to maintain population diversity. Comprehensive experiments conducted on the CEC2017 and CEC2022 test suites demonstrate that MSSAO significantly enhances both global optimization performance and convergence accuracy. Furthermore, its effectiveness in engineering optimization is demonstrated through a DC motor control system.
- 11 October 2026
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 38 (20)
Multi‐Strategy Snow Ablation Optimizer for Global Optimization
The snow ablation optimizer (SAO) is a novel meta‐heuristic algorithm inspired by the natural processes of snow melting and sublimation. SAO employs a dual‐population dynamic adjustment mechanism to balance exploration and exploitation, demonstrating significant performance in global optimization. However, when dealing with complex optimization problems, the SAO algorithm tends to suffer from low convergence accuracy and premature convergence. To address these issues, this paper proposes a multi‐strategy snow ablation optimizer (MSSAO). Firstly, it adopts an external archive mechanism to prevent convergence to local optima. Secondly, it utilizes an adaptive t ‐distribution perturbation strategy to achieve a balance between exploration and exploitation. Finally, it employs a mirror reflection learning strategy to maintain population diversity. Comprehensive experiments conducted on the CEC2017 and CEC2022 test suites demonstrate that MSSAO significantly enhances both global optimization performance and convergence accuracy. Furthermore, its effectiveness in engineering optimization is demonstrated through a DC motor control system.
- 17 June 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (28) , 286001
A Multi-Strategy Integrated Starfish Optimization Algorithm and Its Applications in Wind Power Forecasting
The starfish optimization algorithm (SFOA) exhibits strong global-search capability and fast convergence but remains susceptible to premature convergence on high-dimensional, multimodal problems. A multi-strategy integrated starfish optimization algorithm (MSSFOA) is proposed in this paper. MSSFOA first constructs richer, more uniformly distributed collective-information vectors via fitness–distance balanced ranking and dimension grouping to boost population diversity and resist premature convergence. It then employs a dual-guided search that supplements global-best guidance with random particle perturbations, enabling a smooth transition from large-scale early exploration to fine-grained late exploitation. A dual-layer adaptive directional archive records historical positive and negative step sizes and adaptively generates new step lengths to balance local refinement with necessary exploratory jumps. It is shown by empirical studies on the CEC2013, CEC2017, and CEC2022 benchmark suites, using the Wilcoxon rank-sum and Friedman tests, that MSSFOA significantly improves convergence speed, solution accuracy, and robustness compared with mainstream algorithms. Both independent gains and synergistic effects of the proposed components are confirmed by ablation analyses. It is demonstrated through application to wind power forecasting that the MSSFOA-optimized model converges faster and achieves improved prediction accuracy, indicating strong potential for complex engineering optimizations.
- 17 June 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (28) , 286001
A Multi-Strategy Integrated Starfish Optimization Algorithm and Its Applications in Wind Power Forecasting
The starfish optimization algorithm (SFOA) exhibits strong global-search capability and fast convergence but remains susceptible to premature convergence on high-dimensional, multimodal problems. A multi-strategy integrated starfish optimization algorithm (MSSFOA) is proposed in this paper. MSSFOA first constructs richer, more uniformly distributed collective-information vectors via fitness–distance balanced ranking and dimension grouping to boost population diversity and resist premature convergence. It then employs a dual-guided search that supplements global-best guidance with random particle perturbations, enabling a smooth transition from large-scale early exploration to fine-grained late exploitation. A dual-layer adaptive directional archive records historical positive and negative step sizes and adaptively generates new step lengths to balance local refinement with necessary exploratory jumps. It is shown by empirical studies on the CEC2013, CEC2017, and CEC2022 benchmark suites, using the Wilcoxon rank-sum and Friedman tests, that MSSFOA significantly improves convergence speed, solution accuracy, and robustness compared with mainstream algorithms. Both independent gains and synergistic effects of the proposed components are confirmed by ablation analyses. It is demonstrated through application to wind power forecasting that the MSSFOA-optimized model converges faster and achieves improved prediction accuracy, indicating strong potential for complex engineering optimizations.
- 19 August 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (8) , 1-41
A multi-layered artificial electric field algorithm for numerical optimization and path planning
- 19 August 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (8) , 1-41
A multi-layered artificial electric field algorithm for numerical optimization and path planning
- 14 May 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 18 (3) , 1-23
Coverage optimization in wireless sensor network based on multi-strategy dung beetle optimization algorithm
- 14 May 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 18 (3) , 1-23
Coverage optimization in wireless sensor network based on multi-strategy dung beetle optimization algorithm
- 7 May 2025
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 37 (12-14)
Cuckoo Search Algorithm With Ensemble Strategy for Continuous Optimization Problems
Cuckoo search (CS) algorithm is a simple and effective optimization technique. However, CS algorithm may encounter the issue of premature convergence as the complexity of the problem increases. To address this challenge, a cuckoo search algorithm with ensemble strategy, called CSES, is presented in this paper. Specifically, three new search strategies with diverse properties are designed to boost the competitiveness. After that, according to the idea of selective ensemble, a priority roulette method is employed to select the appropriate search strategy at distinct phases of the evolution process, so as to produce more promising results. Furthermore, the effectiveness evaluation of CSES algorithm is carried out on 58 benchmark functions from CEC 2013 and CEC 2017 test suites and several real‐world problems including chaotic time series prediction and transformer fault classification. Simulation outcomes illustrate that the introduced CSES is superior to five recently developed CS variants in terms of search accuracy and robustness, for example it provides 10 and 12 better performance improvements on and optimization of the CEC 2013 benchmarks, and produces 19 and 11 better performance improvements on and optimization of the CEC 2017 benchmarks, respectively. Moreover, CSES also exhibits more superiority compared to several other advanced evolutionary methods, including butterfly optimization algorithm (BOA), dung beetle optimizer (DBO), electric eel foraging optimization (EEFO), jellyfish search (JS) and wild horse optimizer (WHO), and yields 25 better performance improvements on optimization of the CEC 2013 benchmarks.
- 7 May 2025
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 37 (12-14)
Cuckoo Search Algorithm With Ensemble Strategy for Continuous Optimization Problems
Cuckoo search (CS) algorithm is a simple and effective optimization technique. However, CS algorithm may encounter the issue of premature convergence as the complexity of the problem increases. To address this challenge, a cuckoo search algorithm with ensemble strategy, called CSES, is presented in this paper. Specifically, three new search strategies with diverse properties are designed to boost the competitiveness. After that, according to the idea of selective ensemble, a priority roulette method is employed to select the appropriate search strategy at distinct phases of the evolution process, so as to produce more promising results. Furthermore, the effectiveness evaluation of CSES algorithm is carried out on 58 benchmark functions from CEC 2013 and CEC 2017 test suites and several real‐world problems including chaotic time series prediction and transformer fault classification. Simulation outcomes illustrate that the introduced CSES is superior to five recently developed CS variants in terms of search accuracy and robustness, for example it provides 10 and 12 better performance improvements on and optimization of the CEC 2013 benchmarks, and produces 19 and 11 better performance improvements on and optimization of the CEC 2017 benchmarks, respectively. Moreover, CSES also exhibits more superiority compared to several other advanced evolutionary methods, including butterfly optimization algorithm (BOA), dung beetle optimizer (DBO), electric eel foraging optimization (EEFO), jellyfish search (JS) and wild horse optimizer (WHO), and yields 25 better performance improvements on optimization of the CEC 2013 benchmarks.
- 28 March 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Computational Intelligence and Applications
- Vol. 24 (02)
A Multi-Strategy Artificial Electric Field Algorithm for Numerical Optimization
Artificial electric field algorithm (AEFA) is a metaheuristic optimization algorithm proposed in recent years, which has been successfully applied to address various optimization problems. However, it is likely to converge prematurely or fall into local optima when solving complex problems. To overcome these disadvantages, a multi-strategy artificial electric field algorithm (MAEFA) is proposed in this paper. For the MAEFA algorithm, the global optimal solution information is utilized to improve the diversity of population and global search ability. Then, the adaptive Coulomb’s constant is configured to balance the global exploration and local search. Also, a restart strategy is designed to further alleviate the premature convergence. To validate the effectiveness of MAEFA, it is compared with three AEFA algorithms and several other evolutionary algorithms on 14 test problems presented in CEC 2005 and 13 basic benchmark functions. Furthermore, a wind power prediction model based on MAEFA algorithm and back-propagation (BP) neural network is established to investigate its application ability. Experiments show that MAEFA is significantly superior to other algorithms in tackling these benchmark functions with different dimensions. Furthermore, in terms of wind power prediction, the BP neural network model optimized by MAEFA algorithm also provides higher prediction accuracy.
- 28 March 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Computational Intelligence and Applications
- Vol. 24 (02)
A Multi-Strategy Artificial Electric Field Algorithm for Numerical Optimization
Artificial electric field algorithm (AEFA) is a metaheuristic optimization algorithm proposed in recent years, which has been successfully applied to address various optimization problems. However, it is likely to converge prematurely or fall into local optima when solving complex problems. To overcome these disadvantages, a multi-strategy artificial electric field algorithm (MAEFA) is proposed in this paper. For the MAEFA algorithm, the global optimal solution information is utilized to improve the diversity of population and global search ability. Then, the adaptive Coulomb’s constant is configured to balance the global exploration and local search. Also, a restart strategy is designed to further alleviate the premature convergence. To validate the effectiveness of MAEFA, it is compared with three AEFA algorithms and several other evolutionary algorithms on 14 test problems presented in CEC 2005 and 13 basic benchmark functions. Furthermore, a wind power prediction model based on MAEFA algorithm and back-propagation (BP) neural network is established to investigate its application ability. Experiments show that MAEFA is significantly superior to other algorithms in tackling these benchmark functions with different dimensions. Furthermore, in terms of wind power prediction, the BP neural network model optimized by MAEFA algorithm also provides higher prediction accuracy.
- 18 February 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015253
A parameter adaptive sine cosine algorithm for global optimization problems
Sine cosine algorithm (SCA) is a random search technique for global numerical optimization. However, SCA still exhibits low efficiency for some complex problems. In this paper, we develop a novel SCA variant (PASCA) by introducing a parameter adaptive mechanism. Specifically, the control parameter is produced based on a Cauchy distribution rather than the original linear decreasing scheme. After that, at the end of each generation, the successful historical information is utilized to dynamically update the control parameter, which helps to strengthen the search ability and reduce dependence on the problem to be solved. To verify the effectiveness of PASCA algorithm, comparison experiments are conducted on 43 benchmark functions including 13 classic problems and CEC 2017 test suite as well as a time series prediction problem. Simulation results demonstrate that PASCA is an efficient and promising optimization method compared with the classic SCA and its four recent strong variants.
- 18 February 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015253
A parameter adaptive sine cosine algorithm for global optimization problems
Sine cosine algorithm (SCA) is a random search technique for global numerical optimization. However, SCA still exhibits low efficiency for some complex problems. In this paper, we develop a novel SCA variant (PASCA) by introducing a parameter adaptive mechanism. Specifically, the control parameter is produced based on a Cauchy distribution rather than the original linear decreasing scheme. After that, at the end of each generation, the successful historical information is utilized to dynamically update the control parameter, which helps to strengthen the search ability and reduce dependence on the problem to be solved. To verify the effectiveness of PASCA algorithm, comparison experiments are conducted on 43 benchmark functions including 13 classic problems and CEC 2017 test suite as well as a time series prediction problem. Simulation results demonstrate that PASCA is an efficient and promising optimization method compared with the classic SCA and its four recent strong variants.
- 31 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015243
Multi-strategy hybrid dung beetle optimization algorithm for parameter identification in photovoltaic systems
The dung beetle optimization algorithm (DBO) is a novel meta-heuristic algorithm inspired by the behaviors of dung beetle populations, including rolling, dancing, foraging, breeding and stealing. As so far, the DBO algorithm has demonstrated success in addressing a wide range of complex engineering optimization problems. However, like many other meta-heuristic algorithms, it is also prone to certain limitations, such as slow convergence rates and the tendency to become trapped in local optima during the later stages of optimization. To overcome these limitations, this paper proposes a multi-strategy hybrid dung beetle optimization algorithm (MSDBO), which introduces the tangent flight strategy, golden sine search strategy, adaptive t-distribution sparrow perturbation strategy, and vertical crossover mutation strategy. To comprehensively evaluate the performance of MSDBO, simulations are conducted on 59 benchmark functions from CEC2014 and CEC2017. Experimental results demonstrate that MSDBO outperforms DBO, four advanced DBO variants, and several other popular algorithms in overall performance. Furthermore, MSDBO is employed for parameter identification in photovoltaic system models, further showcasing its effectiveness and reliability in real-world engineering applications.
- 31 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015243
Multi-strategy hybrid dung beetle optimization algorithm for parameter identification in photovoltaic systems
The dung beetle optimization algorithm (DBO) is a novel meta-heuristic algorithm inspired by the behaviors of dung beetle populations, including rolling, dancing, foraging, breeding and stealing. As so far, the DBO algorithm has demonstrated success in addressing a wide range of complex engineering optimization problems. However, like many other meta-heuristic algorithms, it is also prone to certain limitations, such as slow convergence rates and the tendency to become trapped in local optima during the later stages of optimization. To overcome these limitations, this paper proposes a multi-strategy hybrid dung beetle optimization algorithm (MSDBO), which introduces the tangent flight strategy, golden sine search strategy, adaptive t-distribution sparrow perturbation strategy, and vertical crossover mutation strategy. To comprehensively evaluate the performance of MSDBO, simulations are conducted on 59 benchmark functions from CEC2014 and CEC2017. Experimental results demonstrate that MSDBO outperforms DBO, four advanced DBO variants, and several other popular algorithms in overall performance. Furthermore, MSDBO is employed for parameter identification in photovoltaic system models, further showcasing its effectiveness and reliability in real-world engineering applications.
- 11 January 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modeling, Simulation, and Scientific Computing
- Vol. 16 (01)
An artificial electric field algorithm with a variable spiral search and an optimal solution mutation strategy
Artificial electric field algorithm (AEFA) inspired by Coulomb’s law of electrostatic force is a swarm intelligent optimization algorithm. It utilizes the electrostatic force to enable information transmission and evolution of individuals. The traditional AEFA has achieved some successful applications, but it still has problems with premature convergence and low search ability. To solve these problems, an AEFA with a variable spiral search strategy and an optimal solution mutation strategy (VOAEFA) is proposed. The variable spiral search strategy which includes spiral search and skip search can improve the global exploration capability and reduce the probability of the algorithm falling into local optima. The optimal solution mutation strategy can increase the diversity of population. To evaluate the performance of VOAEFA, it is compared with AEFA algorithms and other algorithms on 57 benchmark functions and three engineering design problems. The comparison results on benchmark functions indicate that VOAEFA is superior to its competitors. In addition, VOAEFA has the advantage of high accuracy in solving challenging problems.
- 11 January 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modeling, Simulation, and Scientific Computing
- Vol. 16 (01)
An artificial electric field algorithm with a variable spiral search and an optimal solution mutation strategy
Artificial electric field algorithm (AEFA) inspired by Coulomb’s law of electrostatic force is a swarm intelligent optimization algorithm. It utilizes the electrostatic force to enable information transmission and evolution of individuals. The traditional AEFA has achieved some successful applications, but it still has problems with premature convergence and low search ability. To solve these problems, an AEFA with a variable spiral search strategy and an optimal solution mutation strategy (VOAEFA) is proposed. The variable spiral search strategy which includes spiral search and skip search can improve the global exploration capability and reduce the probability of the algorithm falling into local optima. The optimal solution mutation strategy can increase the diversity of population. To evaluate the performance of VOAEFA, it is compared with AEFA algorithms and other algorithms on 57 benchmark functions and three engineering design problems. The comparison results on benchmark functions indicate that VOAEFA is superior to its competitors. In addition, VOAEFA has the advantage of high accuracy in solving challenging problems.