Xinyu Liu
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
Research Subjects
Research Interests
Xinyu Liu has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Hao Jiang
College of Electrical Engineering and Automation, Fuzhou University, Fuzhou, China
13 shared publications - Jing Chen
Huaqiao University
12 shared publications - Xiren Miao
Fuzhou University
10 shared publications Xiren Miao
College of Electrical Engineering and Automation Fuzhou University Fuzhou 350108 China
9 shared publicationsJing Chen
7 shared publicationsHao Jiang
6 shared publications
Latest Publications
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (3) , 550-565
Anomaly Detection for Self-Powered Neutron Detectors Using the Burnup-Adaptive Spatial-Temporal Model
Self-powered neutron detectors (SPNDs) are critical instruments in nuclear power plants (NPPs), yet their malfunctions may result in misperception and misdiagnoses. Plentiful SPNDs are deployed at various locations and reflect neutron fluence rate in nuclear reactors, empirically derived spatial correlations via Wasserstein distance. However, existing detection methods seldom consider gradual shifts in data distribution and spatial correlations induced by reactor burnup. Hence, this study proposes an SPND-oriented anomaly detection scheme named the burnup-adaptive spatial-temporal model (BA-STM). The scheme abstracts the SPND topology as a graph structure and utilizes a mix-hop temporal convolutional network (MTCN) to extract spatial-temporal interdependencies among overall SPNDs. To alleviate discrepancies across different burnup stages, BA-STM consists of the adversarial discriminator for driving MTCN to learn domain-invariant spatial-temporal features and the lightweight attention reconstructor for filtrating pivotal information in complicated features, further obtaining reconstructed SPND signals and residuals. Through variable-boundary detection, BA-STM quantifies SPND abnormal behavior based on residual statistics exceeding the variable boundaries, enabling effective detection. Experiments on SPND data from a real-world NPP with simulated anomalies verify that the BA-STM exhibits superior performance, reaching optimal F1 scores of 97.915% and 97.671% for single-SPND anomaly detection as well as 97.741% and 97.067% for multi-SPND anomaly detection.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (3) , 550-565
Anomaly Detection for Self-Powered Neutron Detectors Using the Burnup-Adaptive Spatial-Temporal Model
Self-powered neutron detectors (SPNDs) are critical instruments in nuclear power plants (NPPs), yet their malfunctions may result in misperception and misdiagnoses. Plentiful SPNDs are deployed at various locations and reflect neutron fluence rate in nuclear reactors, empirically derived spatial correlations via Wasserstein distance. However, existing detection methods seldom consider gradual shifts in data distribution and spatial correlations induced by reactor burnup. Hence, this study proposes an SPND-oriented anomaly detection scheme named the burnup-adaptive spatial-temporal model (BA-STM). The scheme abstracts the SPND topology as a graph structure and utilizes a mix-hop temporal convolutional network (MTCN) to extract spatial-temporal interdependencies among overall SPNDs. To alleviate discrepancies across different burnup stages, BA-STM consists of the adversarial discriminator for driving MTCN to learn domain-invariant spatial-temporal features and the lightweight attention reconstructor for filtrating pivotal information in complicated features, further obtaining reconstructed SPND signals and residuals. Through variable-boundary detection, BA-STM quantifies SPND abnormal behavior based on residual statistics exceeding the variable boundaries, enabling effective detection. Experiments on SPND data from a real-world NPP with simulated anomalies verify that the BA-STM exhibits superior performance, reaching optimal F1 scores of 97.915% and 97.671% for single-SPND anomaly detection as well as 97.741% and 97.067% for multi-SPND anomaly detection.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 41 (4) , 5103-5114
A Magnetic Core Loss Modeling Method Based on Domain Adaptation Using Multiple Kernel Maximum Mean Discrepancy
Core loss is a crucial performance indicator for magnetic materials, significantly influencing the operational stability of electrical equipment regarding efficiency, dependability, and compactness. Traditional core loss calculation models are not very accurate since core loss depends on many different characteristics and operating conditions. In addition, there are numerous kinds of core materials used in engineering applications, which makes gathering a lot of information about them all challenging. This article proposes a magnetic core loss modeling approach based on multikernel maximum mean discrepancy domain adaptation to overcome these drawbacks. The method achieves cross-domain feature alignment by quantifying the differences in feature distributions across diverse magnetic core material datasets, enabling rapid adaptation to new magnetic core materials. In this article, experiments are conducted for three core materials, including N27, 3C94, and 78, in a small-sample scenario with 5% of the conventional training data size. The results demonstrate a 6.28% performance improvement compared to traditional data-driven methods without domain adaptation, indicating that the proposed approach achieves high computational accuracy while significantly reducing the required sample size for magnetic core materials.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 41 (4) , 5103-5114
A Magnetic Core Loss Modeling Method Based on Domain Adaptation Using Multiple Kernel Maximum Mean Discrepancy
Core loss is a crucial performance indicator for magnetic materials, significantly influencing the operational stability of electrical equipment regarding efficiency, dependability, and compactness. Traditional core loss calculation models are not very accurate since core loss depends on many different characteristics and operating conditions. In addition, there are numerous kinds of core materials used in engineering applications, which makes gathering a lot of information about them all challenging. This article proposes a magnetic core loss modeling approach based on multikernel maximum mean discrepancy domain adaptation to overcome these drawbacks. The method achieves cross-domain feature alignment by quantifying the differences in feature distributions across diverse magnetic core material datasets, enabling rapid adaptation to new magnetic core materials. In this article, experiments are conducted for three core materials, including N27, 3C94, and 78, in a small-sample scenario with 5% of the conventional training data size. The results demonstrate a 6.28% performance improvement compared to traditional data-driven methods without domain adaptation, indicating that the proposed approach achieves high computational accuracy while significantly reducing the required sample size for magnetic core materials.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Fault Detection for Ex-Core Neutron Detectors in Nuclear Power Plants Using Global-Fused Dynamic Detection Model
In nuclear power plants (NPPs), ex-core neutron detectors are deployed around reactor cores and are essential for reactor stability, but their deterioration and malfunction can cause misperceptions and misdiagnoses. Existing fault detection seldom accounts for global spatial-temporal coupling relationships implied among overall detectors and uncertainty under transient operations. Thus, we propose a novel detector-oriented fault detection scheme called the global-fused dynamic detection (GFDD) model, established by the global spatial-temporal graph (GSTG), moving-global graph convolution (MGGC), and uncertainty-quantified dynamic detection (UQDD). To enrich informational sources and disperse faulty propagation, we specifically design the GSTG for characterizing the spatial-temporal relationships among overall detectors and the MGGC for efficiently capturing global high-level features, further generating multi-detector reconstructed signals and residuals. Through calculating dynamic statistics and quantifying uncertainty under varying operating conditions, the UQDD identifies faulty detectors and corrects erroneous signals. Experiments on steady and transient states from a real-world NPP with simulated faults validate that the GFDD model outperforms various state-of-the-art methods with regard to signal reconstruction and fault detection.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Fault Detection for Ex-Core Neutron Detectors in Nuclear Power Plants Using Global-Fused Dynamic Detection Model
In nuclear power plants (NPPs), ex-core neutron detectors are deployed around reactor cores and are essential for reactor stability, but their deterioration and malfunction can cause misperceptions and misdiagnoses. Existing fault detection seldom accounts for global spatial-temporal coupling relationships implied among overall detectors and uncertainty under transient operations. Thus, we propose a novel detector-oriented fault detection scheme called the global-fused dynamic detection (GFDD) model, established by the global spatial-temporal graph (GSTG), moving-global graph convolution (MGGC), and uncertainty-quantified dynamic detection (UQDD). To enrich informational sources and disperse faulty propagation, we specifically design the GSTG for characterizing the spatial-temporal relationships among overall detectors and the MGGC for efficiently capturing global high-level features, further generating multi-detector reconstructed signals and residuals. Through calculating dynamic statistics and quantifying uncertainty under varying operating conditions, the UQDD identifies faulty detectors and corrects erroneous signals. Experiments on steady and transient states from a real-world NPP with simulated faults validate that the GFDD model outperforms various state-of-the-art methods with regard to signal reconstruction and fault detection.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 17854-17868
SR-STM: Simulation–Reality Spatial–Temporal Model for Early Warning of Power Tilt in Nuclear Power Plants
Balanced in-core power levels in nuclear power plants (NPPs) are critical for safety, whereas power tilt disrupts this balance, reducing safety margins and posing risks.0Early warning for power tilt offers an effective way of optimizing monitoring. Due to abnormal-sample scarcity and security concerns, common data-driven models train on the simulated data generated by simulators. However, achieving a satisfactory effect in practices is difficult because simulators imperfectly emulate reality. Thus, we propose a power tilt-oriented early warning method called simulation-reality spatial-temporal model (SR-STM).0Motivated by the physical model in NPPs, a knowledge-guided hierarchical graph is designed to characterize spatial correlations among local power levels for SR-STM’s input. The SR-STM uses a lightweight spatial-temporal network (LST-Net) as a feature extractor, balancing precision and efficiency. To bridge sim-real inter-domain discrepancies, SR-STM utilizes node-alignment adversarial learning for fine weight tuning in subdomain, and eigenvalue-based scale alignment for sim-real feature proximity. Forecasting local power levels using the SR-STM, dynamic metrics and alarm limits are calculated and compared to perform the early warning task. The online experimental prototype verifies that SR-STM surpasses various state-of-the-art methods in terms of early warning and sim-real cross-domain tasks.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 17854-17868
SR-STM: Simulation–Reality Spatial–Temporal Model for Early Warning of Power Tilt in Nuclear Power Plants
Balanced in-core power levels in nuclear power plants (NPPs) are critical for safety, whereas power tilt disrupts this balance, reducing safety margins and posing risks.0Early warning for power tilt offers an effective way of optimizing monitoring. Due to abnormal-sample scarcity and security concerns, common data-driven models train on the simulated data generated by simulators. However, achieving a satisfactory effect in practices is difficult because simulators imperfectly emulate reality. Thus, we propose a power tilt-oriented early warning method called simulation-reality spatial-temporal model (SR-STM).0Motivated by the physical model in NPPs, a knowledge-guided hierarchical graph is designed to characterize spatial correlations among local power levels for SR-STM’s input. The SR-STM uses a lightweight spatial-temporal network (LST-Net) as a feature extractor, balancing precision and efficiency. To bridge sim-real inter-domain discrepancies, SR-STM utilizes node-alignment adversarial learning for fine weight tuning in subdomain, and eigenvalue-based scale alignment for sim-real feature proximity. Forecasting local power levels using the SR-STM, dynamic metrics and alarm limits are calculated and compared to perform the early warning task. The online experimental prototype verifies that SR-STM surpasses various state-of-the-art methods in terms of early warning and sim-real cross-domain tasks.
- Open Access
- 10 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 792-799
A survey on oriented object detection for aerial power inspection
- 10 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 792-799
Open AccessA survey on oriented object detection for aerial power inspection
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (2) , 1110-1119
ST-SAM: Spatial-Temporal State Adaptation Model for Neutron Detector Fault Detection and Isolation in Nuclear Power Plants
Neutron detectors in nuclear power plants (NPPs) are critical for system stability, yet their malfunctions may lead to false alerts and misdiagnoses. Multidetectors deployed in diverse positions vary with the nuclear reactor states contained spatial-temporal variations of neutron fluxes. Existing methods seldom concurrently consider intricate spatial-temporal correlations and gradual state variations among detectors. This study proposes a detector-oriented fault detection and isolation method named the spatial-temporal state adaptation model (ST-SAM). The method introduces a local-global spatial-temporal network that captures the potential interdependencies within the detector topology. To minimize cross-state discrepancies in reactors, ST-SAM integrates three submodules: a signal reconstructor to enhance the specific-state variation representation; a correlation alignment to mitigate interstate feature discrepancies; and an adversarial discriminator to extract spatial-temporal state-invariant features. Leveraging the parallel detection strategy, ST-SAM effectively detects and isolates faulty detectors, preventing fault propagation on subsequent diagnosis. Experiments on ex-core and in-core neutron detectors in real-world NPPs with simulated faults verify that the ST-SAM outperforms various state-of-the-art methods in terms of signal reconstruction and fault detection.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (2) , 1110-1119
ST-SAM: Spatial-Temporal State Adaptation Model for Neutron Detector Fault Detection and Isolation in Nuclear Power Plants
Neutron detectors in nuclear power plants (NPPs) are critical for system stability, yet their malfunctions may lead to false alerts and misdiagnoses. Multidetectors deployed in diverse positions vary with the nuclear reactor states contained spatial-temporal variations of neutron fluxes. Existing methods seldom concurrently consider intricate spatial-temporal correlations and gradual state variations among detectors. This study proposes a detector-oriented fault detection and isolation method named the spatial-temporal state adaptation model (ST-SAM). The method introduces a local-global spatial-temporal network that captures the potential interdependencies within the detector topology. To minimize cross-state discrepancies in reactors, ST-SAM integrates three submodules: a signal reconstructor to enhance the specific-state variation representation; a correlation alignment to mitigate interstate feature discrepancies; and an adversarial discriminator to extract spatial-temporal state-invariant features. Leveraging the parallel detection strategy, ST-SAM effectively detects and isolates faulty detectors, preventing fault propagation on subsequent diagnosis. Experiments on ex-core and in-core neutron detectors in real-world NPPs with simulated faults verify that the ST-SAM outperforms various state-of-the-art methods in terms of signal reconstruction and fault detection.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (1) , 513-523
Tower Masking MIM: A Self-Supervised Pretraining Method for Power Line Inspection
For intelligent inspection of power lines, a core task is to detect components in aerial images. Currently, deep supervised learning, a data-hungry paradigm, has attracted great attention. However, considering real-world scenarios, labeled data are usually limited, and the utilization of abundant unlabeled data is rarely investigated in this field. This study deploys a pretrained model for power line component detection based on a self-supervised pretraining approach, which exploits useful information from unannotated data. Concretely, we design a new masking strategy based on the structural characteristic of power lines to guide the pretraining process with meaningful semantic content. Meanwhile, a Siamese architecture is proposed to extract complete global features by using dual reconstruction with semantic targets provided by the proposed masking strategy. Then, the knowledge distillation is utilized to enable the pretrained model to learn both domain-specific and general representations. Moreover, a feature pyramid mechanism is adopted to capture multiscale features, which can benefit the detection task. Experimental results show that the proposed approach can successfully improve the performance of a variety of detection frameworks for power line components, and outperforms other self-supervised pretraining methods.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (1) , 513-523
Tower Masking MIM: A Self-Supervised Pretraining Method for Power Line Inspection
For intelligent inspection of power lines, a core task is to detect components in aerial images. Currently, deep supervised learning, a data-hungry paradigm, has attracted great attention. However, considering real-world scenarios, labeled data are usually limited, and the utilization of abundant unlabeled data is rarely investigated in this field. This study deploys a pretrained model for power line component detection based on a self-supervised pretraining approach, which exploits useful information from unannotated data. Concretely, we design a new masking strategy based on the structural characteristic of power lines to guide the pretraining process with meaningful semantic content. Meanwhile, a Siamese architecture is proposed to extract complete global features by using dual reconstruction with semantic targets provided by the proposed masking strategy. Then, the knowledge distillation is utilized to enable the pretrained model to learn both domain-specific and general representations. Moreover, a feature pyramid mechanism is adopted to capture multiscale features, which can benefit the detection task. Experimental results show that the proposed approach can successfully improve the performance of a variety of detection frameworks for power line components, and outperforms other self-supervised pretraining methods.
- 30 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-10
Fault Diagnosis in Power Line Inspection Using Normalized Multihierarchy Embedding Matching
For maintenance of power lines, a core task is to diagnose the fault of different components from the aerial inspection images. Currently, deep learning models trained on defect samples have achieved promising performances for the automatic fault diagnosis. However, the slow accumulation process of fault data leads to a long-term challenge of data insufficiency in this field. In this article, a normalized multi-hierarchy embedding matching (NMHEM) based anomaly detection method is proposed to inspect power line faults, which only utilizes defect-free samples during training. To impart the NMHEM with the ability to detect anomalous patterns in images, three main modules are introduced. First, the embedding generation module is employed to extract deep hierarchical representations. Next, hierarchy-wise anomaly scores are calculated through the embedding matching module to measure the anomalous degree, which can make the model more discriminative at different hierarchies. Finally, a normalizing module is developed and served as a credible scoring function indicating the probability of anomaly occurring, thus boosting the performance of the fault diagnosis. The proposed NMHEM adaptively aggregates local spatial and global semantic information which leverages the available nominal knowledge from normal data, achieving effective fault diagnosis of power lines. Experiments are conducted on the dataset that contains five key components. Results show that our method achieves 88.4% AUC and 80.5% F1-score, which outperforms other supervised and semi-supervised methods.
- 30 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-10
Fault Diagnosis in Power Line Inspection Using Normalized Multihierarchy Embedding Matching
For maintenance of power lines, a core task is to diagnose the fault of different components from the aerial inspection images. Currently, deep learning models trained on defect samples have achieved promising performances for the automatic fault diagnosis. However, the slow accumulation process of fault data leads to a long-term challenge of data insufficiency in this field. In this article, a normalized multi-hierarchy embedding matching (NMHEM) based anomaly detection method is proposed to inspect power line faults, which only utilizes defect-free samples during training. To impart the NMHEM with the ability to detect anomalous patterns in images, three main modules are introduced. First, the embedding generation module is employed to extract deep hierarchical representations. Next, hierarchy-wise anomaly scores are calculated through the embedding matching module to measure the anomalous degree, which can make the model more discriminative at different hierarchies. Finally, a normalizing module is developed and served as a credible scoring function indicating the probability of anomaly occurring, thus boosting the performance of the fault diagnosis. The proposed NMHEM adaptively aggregates local spatial and global semantic information which leverages the available nominal knowledge from normal data, achieving effective fault diagnosis of power lines. Experiments are conducted on the dataset that contains five key components. Results show that our method achieves 88.4% AUC and 80.5% F1-score, which outperforms other supervised and semi-supervised methods.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (9) , 9280-9290
Component Detection for Power Line Inspection Using a Graph-Based Relation Guiding Network
Detecting the components in aerial images is a crucial task in automatic visual inspection for power lines. Currently, deep learning models guided by external knowledge have achieved promising performances compared to directly applying the benchmark detectors. However, the component relationship, as human commonsense knowledge for object reasoning, is rarely investigated in this field. This study presents a graph-based relation guided network for power line component detection, which exploits correlations of regions, images, and categories. The visual relation module is employed to learn region-to-region relationship and enhance the visual features of each proposal that may contain components. Meanwhile, two guidance modules are proposed to capture image-to-region correlation and distinctively facilitate the category classification and position regression, which has not been considered in previous methods. Moreover, the category graphs built in these two modules are able to explore category-to-category dependencies that can further promote the network ability. Experimental results demonstrate that the proposed method can achieve more accurate and reasonable component detection compared to previous methods, which verifies the effectiveness of the proposed model incorporated with relation knowledge.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (9) , 9280-9290
Component Detection for Power Line Inspection Using a Graph-Based Relation Guiding Network
Detecting the components in aerial images is a crucial task in automatic visual inspection for power lines. Currently, deep learning models guided by external knowledge have achieved promising performances compared to directly applying the benchmark detectors. However, the component relationship, as human commonsense knowledge for object reasoning, is rarely investigated in this field. This study presents a graph-based relation guided network for power line component detection, which exploits correlations of regions, images, and categories. The visual relation module is employed to learn region-to-region relationship and enhance the visual features of each proposal that may contain components. Meanwhile, two guidance modules are proposed to capture image-to-region correlation and distinctively facilitate the category classification and position regression, which has not been considered in previous methods. Moreover, the category graphs built in these two modules are able to explore category-to-category dependencies that can further promote the network ability. Experimental results demonstrate that the proposed method can achieve more accurate and reasonable component detection compared to previous methods, which verifies the effectiveness of the proposed model incorporated with relation knowledge.