Guang-Lin Zhuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guang-Lin Zhuo has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chun-Yao Lee
Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan
11 shared publications - Truong-An Le
Department of Electrical and Electronics Engineering Thu Dau Mot University Binh Duong Vietnam
3 shared publications - Chun-Chi Chen
Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan
1 shared publication - Chung‐Hao Huang
Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan
1 shared publication - Kuan-Yu Huang
Department of Electrical Engineering, Chung Yuan Christian University, No. 200, Zhongbei Road, Zhongli District, Taoyuan City 320, Taiwan
1 shared publication - Kuan-Yu Huang
Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan
1 shared publication
Latest Publications
- Open Access
- 23 June 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (13) , 2244
A Hybrid Method of Binary Grey Wolf Optimization and Equilibrium Optimization for Feature Selection in Diagnosing Bearing Faults
Diagnosing bearing faults remains a crucial challenge, particularly in effectively extracting fault information and achieving high diagnostic accuracy. To address this issue, this study presents a model for diagnosing bearing faults, which comprises three primary stages: feature extraction, feature selection, and classification. In the feature extraction stage, features are extracted from raw motor signals using empirical mode decomposition (EMD) and fast Fourier transform (FFT). In the feature selection stage, an effective method based on binary grey wolf optimization (BGWO) and the equilibrium optimizer (EO) is developed to remove redundant and irrelevant features. Finally, k-nearest neighbours (KNNs) and support vector machine (SVM) classifiers are used to identify bearing fault conditions. The proposed model is evaluated using four datasets: the University of California, Irvine (UCI) benchmark datasets, a motor bearing fault current-signal dataset, the Case Western Reserve University (CWRU) benchmark dataset, and the Machinery Failure Prevention Technology (MFPT) benchmark dataset. The experimental results show that the proposed method improves bearing fault diagnosis accuracy and demonstrates strong robustness compared with conventional methods.
- 23 June 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (13) , 2244
Open AccessA Hybrid Method of Binary Grey Wolf Optimization and Equilibrium Optimization for Feature Selection in Diagnosing Bearing Faults
Diagnosing bearing faults remains a crucial challenge, particularly in effectively extracting fault information and achieving high diagnostic accuracy. To address this issue, this study presents a model for diagnosing bearing faults, which comprises three primary stages: feature extraction, feature selection, and classification. In the feature extraction stage, features are extracted from raw motor signals using empirical mode decomposition (EMD) and fast Fourier transform (FFT). In the feature selection stage, an effective method based on binary grey wolf optimization (BGWO) and the equilibrium optimizer (EO) is developed to remove redundant and irrelevant features. Finally, k-nearest neighbours (KNNs) and support vector machine (SVM) classifiers are used to identify bearing fault conditions. The proposed model is evaluated using four datasets: the University of California, Irvine (UCI) benchmark datasets, a motor bearing fault current-signal dataset, the Case Western Reserve University (CWRU) benchmark dataset, and the Machinery Failure Prevention Technology (MFPT) benchmark dataset. The experimental results show that the proposed method improves bearing fault diagnosis accuracy and demonstrates strong robustness compared with conventional methods.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Barycenter-Based Optimal Transport Neighborhood Learning Network for Multisource Cross-Machine Bearing Fault Diagnosis
In recent years, leveraging data from related machines to learn fault knowledge has emerged as a promising approach to address faulty data scarcity in bearing fault diagnosis, i.e. multi-source cross-machine bearing fault diagnosis. However, variations in machine structure, operating condition, and measurement introduce huge domain discrepancies, often leading to significant performance degradation in diagnostic models. To address this challenge, this article proposes a signal-processing module that leverages prior diagnostic knowledge to mitigate the impact of these discrepancies. Furthermore, we propose the barycenter-based optimal transport neighborhood learning network (BOTNLN). Within BOTNLN, Wasserstein barycenter-based partial optimal transport (POT) is employed to integrate knowledge from multiple source domains, ensuring effective diagnostic knowledge transfer to the target domain. Additionally, self-adaptive neighborhood learning is incorporated to minimize intra-class variations, thereby improving inter-class distinguishability and clustering compactness. Extensive experiments conducted on four benchmark-bearing fault diagnosis datasets demonstrate that BOTNLN significantly enhances multi-source cross-machine fault diagnosis performance, consistently outperforming state-of-the-art (SOTA) methods.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Barycenter-Based Optimal Transport Neighborhood Learning Network for Multisource Cross-Machine Bearing Fault Diagnosis
In recent years, leveraging data from related machines to learn fault knowledge has emerged as a promising approach to address faulty data scarcity in bearing fault diagnosis, i.e. multi-source cross-machine bearing fault diagnosis. However, variations in machine structure, operating condition, and measurement introduce huge domain discrepancies, often leading to significant performance degradation in diagnostic models. To address this challenge, this article proposes a signal-processing module that leverages prior diagnostic knowledge to mitigate the impact of these discrepancies. Furthermore, we propose the barycenter-based optimal transport neighborhood learning network (BOTNLN). Within BOTNLN, Wasserstein barycenter-based partial optimal transport (POT) is employed to integrate knowledge from multiple source domains, ensuring effective diagnostic knowledge transfer to the target domain. Additionally, self-adaptive neighborhood learning is incorporated to minimize intra-class variations, thereby improving inter-class distinguishability and clustering compactness. Extensive experiments conducted on four benchmark-bearing fault diagnosis datasets demonstrate that BOTNLN significantly enhances multi-source cross-machine fault diagnosis performance, consistently outperforming state-of-the-art (SOTA) methods.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Optimal Transport Deep Clustering Network for Universal-Set Transfer Bearing Fault Diagnosis
In recent years, the challenge of domain adaptation (DA) for bearing fault diagnosis using deep learning has garnered significant attention from researchers. Most existing DA methods typically rely on prior assumptions about the label sets of the source and target domains. However, in real-world diagnosis, both the source and target domains often contain unique private categories, which is a universal domain adaptation (UDA) diagnosis problem. DA methods based on these assumptions may not perform effectively in the UDA scenario, and their performance can decline sharply when faced with multiple private categories. To address this issue, this paper proposes a UDA deep network diagnosis method. Specifically, partial optimal transport (POT) is employed to partially align the distributions of cross-domain common categories, effectively avoiding negative transfer. A common cluster score is then introduced to generate optimal target clusters, with optimization achieved through target cluster-based contrastive learning. Finally, a sparse index function is used to optimize feature learning based on the physical characteristics of bearing faults. Extensive experiments conducted on a benchmark dataset for bearing fault diagnosis demonstrate that the proposed method significantly improves UDA diagnostic performance, outperforming existing cross-domain fault diagnosis methods.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Optimal Transport Deep Clustering Network for Universal-Set Transfer Bearing Fault Diagnosis
In recent years, the challenge of domain adaptation (DA) for bearing fault diagnosis using deep learning has garnered significant attention from researchers. Most existing DA methods typically rely on prior assumptions about the label sets of the source and target domains. However, in real-world diagnosis, both the source and target domains often contain unique private categories, which is a universal domain adaptation (UDA) diagnosis problem. DA methods based on these assumptions may not perform effectively in the UDA scenario, and their performance can decline sharply when faced with multiple private categories. To address this issue, this paper proposes a UDA deep network diagnosis method. Specifically, partial optimal transport (POT) is employed to partially align the distributions of cross-domain common categories, effectively avoiding negative transfer. A common cluster score is then introduced to generate optimal target clusters, with optimization achieved through target cluster-based contrastive learning. Finally, a sparse index function is used to optimize feature learning based on the physical characteristics of bearing faults. Extensive experiments conducted on a benchmark dataset for bearing fault diagnosis demonstrate that the proposed method significantly improves UDA diagnostic performance, outperforming existing cross-domain fault diagnosis methods.
- Open Access
Electricity Management Policy Applying Data Science and Machine Learning Techniques to Improve Electricity Costs
This paper studies the actual electricity case of a national university in northern Taiwan, pointing out that many schools will face certain asymmetrical information and practical problems in the development of power systems, such as energy-savings and carbon-reduction policies, collecting electricity fees in each division, reducing the loss of power outages, expanding the power system capacity, and maintaining power distribution equipment. These problems are closely related to electricity costs, which include general electricity fees, unexpected losses caused by power outages, purchases of replacement power equipment, and maintenance fees of distribution equipment. This paper proposes corresponding improvement plans for each of the problems in the above-mentioned actual case studies and assists school power managers in using symmetrical information to formulate the best strategies to improve electricity costs.
Open AccessElectricity Management Policy Applying Data Science and Machine Learning Techniques to Improve Electricity Costs
This paper studies the actual electricity case of a national university in northern Taiwan, pointing out that many schools will face certain asymmetrical information and practical problems in the development of power systems, such as energy-savings and carbon-reduction policies, collecting electricity fees in each division, reducing the loss of power outages, expanding the power system capacity, and maintaining power distribution equipment. These problems are closely related to electricity costs, which include general electricity fees, unexpected losses caused by power outages, purchases of replacement power equipment, and maintenance fees of distribution equipment. This paper proposes corresponding improvement plans for each of the problems in the above-mentioned actual case studies and assists school power managers in using symmetrical information to formulate the best strategies to improve electricity costs.
- Open Access
- 6 October 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (19) , 3659
Defects Classification of Hydro Generators in Indonesia by Phase-Resolved Partial Discharge
This paper proposed a phase-resolved partial discharge (PRPD) shape method to classify types of defect generator units by using offline partial discharge (PD) measurement instruments. In this paper, the experimental measurement was applied to two generators in the Inalum hydropower plant, located in North Sumatera, Indonesia. The recorded PRPD using the instrument MPD600 can illustrate the PRPD patterns of generator defects. The proposed PRPD shape method is used to mark auxiliary lines on the PRPD patterns. Moreover, four types of defects refer to the IEC 60034-27 standard, which are microvoid (S1), delamination tape layer (S2), slot defect (S3), and internal delamination (S4) and are used to classify the defect types of the generators. The results show that the proposed method performs well to classify types of defect generator units.
- 6 October 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (19) , 3659
Open AccessDefects Classification of Hydro Generators in Indonesia by Phase-Resolved Partial Discharge
This paper proposed a phase-resolved partial discharge (PRPD) shape method to classify types of defect generator units by using offline partial discharge (PD) measurement instruments. In this paper, the experimental measurement was applied to two generators in the Inalum hydropower plant, located in North Sumatera, Indonesia. The recorded PRPD using the instrument MPD600 can illustrate the PRPD patterns of generator defects. The proposed PRPD shape method is used to mark auxiliary lines on the PRPD patterns. Moreover, four types of defects refer to the IEC 60034-27 standard, which are microvoid (S1), delamination tape layer (S2), slot defect (S3), and internal delamination (S4) and are used to classify the defect types of the generators. The results show that the proposed method performs well to classify types of defect generator units.
- Open Access
- 27 June 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (13) , 2250
Application of ANN in Induction-Motor Fault-Detection System Established with MRA and CFFS
This paper proposes a fault-detection system for faulty induction motors (bearing faults, interturn shorts, and broken rotor bars) based on multiresolution analysis (MRA), correlation and fitness values-based feature selection (CFFS), and artificial neural network (ANN). First, this study compares two feature-extraction methods: the MRA and the Hilbert Huang transform (HHT) for induction-motor-current signature analysis. Furthermore, feature-selection methods are compared to reduce the number of features and maintain the best accuracy of the detection system to lower operating costs. Finally, the proposed detection system is tested with additive white Gaussian noise, and the signal-processing method and feature-selection method with good performance are selected to establish the best detection system. According to the results, features extracted from MRA can achieve better performance than HHT using CFFS and ANN. In the proposed detection system, CFFS significantly reduces the operation cost (95% of the number of features) and maintains 93% accuracy using ANN.
- 27 June 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (13) , 2250
Open AccessApplication of ANN in Induction-Motor Fault-Detection System Established with MRA and CFFS
This paper proposes a fault-detection system for faulty induction motors (bearing faults, interturn shorts, and broken rotor bars) based on multiresolution analysis (MRA), correlation and fitness values-based feature selection (CFFS), and artificial neural network (ANN). First, this study compares two feature-extraction methods: the MRA and the Hilbert Huang transform (HHT) for induction-motor-current signature analysis. Furthermore, feature-selection methods are compared to reduce the number of features and maintain the best accuracy of the detection system to lower operating costs. Finally, the proposed detection system is tested with additive white Gaussian noise, and the signal-processing method and feature-selection method with good performance are selected to establish the best detection system. According to the results, features extracted from MRA can achieve better performance than HHT using CFFS and ANN. In the proposed detection system, CFFS significantly reduces the operation cost (95% of the number of features) and maintains 93% accuracy using ANN.
- Open Access
A Robust Deep Neural Network for Rolling Element Fault Diagnosis under Various Operating and Noisy Conditions
This study proposes a new intelligent diagnostic method for bearing faults in rotating machinery. The method uses a combination of nonlinear mode decomposition based on the improved fast kurtogram, gramian angular field, and convolutional neural network to detect the bearing state of rotating machinery. The nonlinear mode decomposition based on the improved fast kurtogram inherits the advantages of the original algorithm while improving the computational efficiency and signal-to-noise ratio. The gramian angular field can construct a two-dimensional image without destroying the time relationship of the signal. Therefore, the proposed method can perform fault diagnosis on rotating machinery under complex operating conditions. The proposed method is verified on the Paderborn dataset under heavy noise and multiple operating conditions to evaluate its effectiveness. Experimental results show that the proposed model outperforms wavelet denoising and the traditional adaptive decomposition method. The proposed model achieves over 99.6% accuracy in all four operating conditions provided by this dataset, and 93.8% accuracy in a strong noise environment with a signal-to-noise ratio of −4 dB.
Open AccessA Robust Deep Neural Network for Rolling Element Fault Diagnosis under Various Operating and Noisy Conditions
This study proposes a new intelligent diagnostic method for bearing faults in rotating machinery. The method uses a combination of nonlinear mode decomposition based on the improved fast kurtogram, gramian angular field, and convolutional neural network to detect the bearing state of rotating machinery. The nonlinear mode decomposition based on the improved fast kurtogram inherits the advantages of the original algorithm while improving the computational efficiency and signal-to-noise ratio. The gramian angular field can construct a two-dimensional image without destroying the time relationship of the signal. Therefore, the proposed method can perform fault diagnosis on rotating machinery under complex operating conditions. The proposed method is verified on the Paderborn dataset under heavy noise and multiple operating conditions to evaluate its effectiveness. Experimental results show that the proposed model outperforms wavelet denoising and the traditional adaptive decomposition method. The proposed model achieves over 99.6% accuracy in all four operating conditions provided by this dataset, and 93.8% accuracy in a strong noise environment with a signal-to-noise ratio of −4 dB.
- Open Access
- 18 September 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (18) , 2302
Localization of Rolling Element Faults Using Improved Binary Particle Swarm Optimization Algorithm for Feature Selection Task
The accurate localization of the rolling element failure is very important to ensure the reliability of rotating machinery. This paper proposes an efficient and anti-noise fault diagnosis model for rolling elements. The proposed model is composed of feature extraction, feature selection and fault classification. Feature extraction is composed of signal processing and signal noise reduction. Signal processing is carried out by local mean decomposition (LMD), and signal noise reduction is performed by product function (PF) selection and wavelet packet decomposition (WPD). Through the steps of signal noise reduction, high-frequency noise can be effectively removed, and the fault information hidden under the noise can be extracted. To further improve the effectiveness of the diagnostic model, an improved binary particle swarm optimization (IBPSO) is proposed to find the most important features from the feature space. In IBPSO, cycling time-varying inertia weight is introduced to balance exploitation and exploration and improve the capability to escape from local solutions, and crossover and mutation operations are also introduced to improve exploration and exploitation capabilities, respectively. The main contributions of this research are briefly described as follows: (1) The feature extraction process applied in this research can effectively remove noise and establish a high-accuracy feature set. (2) The proposed feature selection algorithm has higher accuracy than the other state-of-the-art feature selection algorithms. (3) In a strong noise environment, the proposed rolling element fault diagnosis model is compared with the state-of-the-art fault diagnosis model in terms of classification accuracy. Experimental results show that the model can maintain high classification accuracy in a strong noise environment. Therefore, it can be proved that the fault diagnosis model proposed in this paper can be effectively applied to the fault diagnosis of rotating machinery.
- 18 September 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (18) , 2302
Open AccessLocalization of Rolling Element Faults Using Improved Binary Particle Swarm Optimization Algorithm for Feature Selection Task
The accurate localization of the rolling element failure is very important to ensure the reliability of rotating machinery. This paper proposes an efficient and anti-noise fault diagnosis model for rolling elements. The proposed model is composed of feature extraction, feature selection and fault classification. Feature extraction is composed of signal processing and signal noise reduction. Signal processing is carried out by local mean decomposition (LMD), and signal noise reduction is performed by product function (PF) selection and wavelet packet decomposition (WPD). Through the steps of signal noise reduction, high-frequency noise can be effectively removed, and the fault information hidden under the noise can be extracted. To further improve the effectiveness of the diagnostic model, an improved binary particle swarm optimization (IBPSO) is proposed to find the most important features from the feature space. In IBPSO, cycling time-varying inertia weight is introduced to balance exploitation and exploration and improve the capability to escape from local solutions, and crossover and mutation operations are also introduced to improve exploration and exploitation capabilities, respectively. The main contributions of this research are briefly described as follows: (1) The feature extraction process applied in this research can effectively remove noise and establish a high-accuracy feature set. (2) The proposed feature selection algorithm has higher accuracy than the other state-of-the-art feature selection algorithms. (3) In a strong noise environment, the proposed rolling element fault diagnosis model is compared with the state-of-the-art fault diagnosis model in terms of classification accuracy. Experimental results show that the model can maintain high classification accuracy in a strong noise environment. Therefore, it can be proved that the fault diagnosis model proposed in this paper can be effectively applied to the fault diagnosis of rotating machinery.
- Open Access
- 24 June 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (13) , 1477
A Hybrid Whale Optimization Algorithm for Global Optimization
This paper proposes a hybrid whale optimization algorithm (WOA) that is derived from the genetic and thermal exchange optimization-based whale optimization algorithm (GWOA-TEO) to enhance global optimization capability. First, the high-quality initial population is generated to improve the performance of GWOA-TEO. Then, thermal exchange optimization (TEO) is applied to improve exploitation performance. Next, a memory is considered that can store historical best-so-far solutions, achieving higher performance without adding additional computational costs. Finally, a crossover operator based on the memory and a position update mechanism of the leading solution based on the memory are proposed to improve the exploration performance. The GWOA-TEO algorithm is then compared with five state-of-the-art optimization algorithms on CEC 2017 benchmark test functions and 8 UCI repository datasets. The statistical results of the CEC 2017 benchmark test functions show that the GWOA-TEO algorithm has good accuracy for global optimization. The classification results of 8 UCI repository datasets also show that the GWOA-TEO algorithm has competitive results with regard to comparison algorithms in recognition rate. Thus, the proposed algorithm is proven to execute excellent performance in solving optimization problems.
- 24 June 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (13) , 1477
Open AccessA Hybrid Whale Optimization Algorithm for Global Optimization
This paper proposes a hybrid whale optimization algorithm (WOA) that is derived from the genetic and thermal exchange optimization-based whale optimization algorithm (GWOA-TEO) to enhance global optimization capability. First, the high-quality initial population is generated to improve the performance of GWOA-TEO. Then, thermal exchange optimization (TEO) is applied to improve exploitation performance. Next, a memory is considered that can store historical best-so-far solutions, achieving higher performance without adding additional computational costs. Finally, a crossover operator based on the memory and a position update mechanism of the leading solution based on the memory are proposed to improve the exploration performance. The GWOA-TEO algorithm is then compared with five state-of-the-art optimization algorithms on CEC 2017 benchmark test functions and 8 UCI repository datasets. The statistical results of the CEC 2017 benchmark test functions show that the GWOA-TEO algorithm has good accuracy for global optimization. The classification results of 8 UCI repository datasets also show that the GWOA-TEO algorithm has competitive results with regard to comparison algorithms in recognition rate. Thus, the proposed algorithm is proven to execute excellent performance in solving optimization problems.
- Open Access
Effective Rotor Fault Diagnosis Model Using Multilayer Signal Analysis and Hybrid Genetic Binary Chicken Swarm Optimization
This article proposes an effective rotor fault diagnosis model of an induction motor (IM) based on local mean decomposition (LMD) and wavelet packet decomposition (WPD)-based multilayer signal analysis and hybrid genetic binary chicken swarm optimization (HGBCSO) for feature selection. Based on the multilayer signal analysis, this technique can reduce the dimension of raw data, extract potential features, and remove background noise. To compare the validity of the proposed HGBCSO method, three well-known evolutionary algorithms are adopted, including binary-particle swarm optimization (BPSO), binary-bat algorithm (BBA), and binary-chicken swarm optimization (BCSO). In addition, the robustness of three classifiers including the decision tree (DT), support vector machine (SVM), and naive Bayes (NB) was compared to select the best model to detect the rotor bar fault. The results showed that the proposed HGBCSO algorithm can obtain better global exploration ability and a lower number of selected features than other evolutionary algorithms that are adopted in this research. In conclusion, the proposed model can reduce the dimension of raw data and achieve high robustness.
Open AccessEffective Rotor Fault Diagnosis Model Using Multilayer Signal Analysis and Hybrid Genetic Binary Chicken Swarm Optimization
This article proposes an effective rotor fault diagnosis model of an induction motor (IM) based on local mean decomposition (LMD) and wavelet packet decomposition (WPD)-based multilayer signal analysis and hybrid genetic binary chicken swarm optimization (HGBCSO) for feature selection. Based on the multilayer signal analysis, this technique can reduce the dimension of raw data, extract potential features, and remove background noise. To compare the validity of the proposed HGBCSO method, three well-known evolutionary algorithms are adopted, including binary-particle swarm optimization (BPSO), binary-bat algorithm (BBA), and binary-chicken swarm optimization (BCSO). In addition, the robustness of three classifiers including the decision tree (DT), support vector machine (SVM), and naive Bayes (NB) was compared to select the best model to detect the rotor bar fault. The results showed that the proposed HGBCSO algorithm can obtain better global exploration ability and a lower number of selected features than other evolutionary algorithms that are adopted in this research. In conclusion, the proposed model can reduce the dimension of raw data and achieve high robustness.