Xuanhao Hua
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuanhao Hua has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Meng Ma
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
3 shared publications - Jianfeng Yuan
Hangzhou Special Equipment Inspection and Science Research Institute, Hangzhou 310051, China
1 shared publication - Jing Zhang
Hangzhou Special Equipment Inspection and Science Research Institute, Hangzhou 310051, China
1 shared publication - Junjie Zhu
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
1 shared publication - Libin Wang
Hangzhou Special Equipment Inspection and Science Research Institute, Hangzhou 310051, China
1 shared publication Lin Gao
Intelligent Power Generation Technology Department, Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China
1 shared publication
Latest Publications
- Open Access
Physics-Topology-Anchored Learning: A Robust and Lightweight Framework for Time-Series Prediction and Anomaly Detection Under Data Scarcity
Health monitoring of complex systems is critical for ensuring reliability and achieving cost-effective reusability. However, deploying deep learning models in this domain is impeded by two primary constraints: the scarcity of high-quality fault samples and the restricted computational resources available on-board. To address these challenges, this paper proposes a Physics-Topology-Anchored Learning (PTAL) framework. The core innovation lies in the effective integration of physical inductive bias into the model architecture. Specifically, PTAL incorporates a predefined adjacency matrix, derived from the physical mechanism, as a structural prior. This design anchors the neural network to explicit physical causality, effectively constraining the hypothesis space and reducing the model’s dependency on large-scale data. Furthermore, by coupling this physics-informed structure with a lightweight recurrent attention mechanism, the model avoids the high computational overhead typical of generic large-scale networks. Experimental evaluations demonstrate that PTAL achieves a peak diagnostic accuracy of 97.8% and a low standard deviation of 0.1145, significantly outperforming baseline models in data-scarce regimes. The results confirm that the proposed model successfully leverages physical bias to maintain a favorable trade-off between diagnostic performance and computational efficiency, making it highly suitable for the resource-constrained environments of complex systems.
Open AccessPhysics-Topology-Anchored Learning: A Robust and Lightweight Framework for Time-Series Prediction and Anomaly Detection Under Data Scarcity
Health monitoring of complex systems is critical for ensuring reliability and achieving cost-effective reusability. However, deploying deep learning models in this domain is impeded by two primary constraints: the scarcity of high-quality fault samples and the restricted computational resources available on-board. To address these challenges, this paper proposes a Physics-Topology-Anchored Learning (PTAL) framework. The core innovation lies in the effective integration of physical inductive bias into the model architecture. Specifically, PTAL incorporates a predefined adjacency matrix, derived from the physical mechanism, as a structural prior. This design anchors the neural network to explicit physical causality, effectively constraining the hypothesis space and reducing the model’s dependency on large-scale data. Furthermore, by coupling this physics-informed structure with a lightweight recurrent attention mechanism, the model avoids the high computational overhead typical of generic large-scale networks. Experimental evaluations demonstrate that PTAL achieves a peak diagnostic accuracy of 97.8% and a low standard deviation of 0.1145, significantly outperforming baseline models in data-scarce regimes. The results confirm that the proposed model successfully leverages physical bias to maintain a favorable trade-off between diagnostic performance and computational efficiency, making it highly suitable for the resource-constrained environments of complex systems.
- Open Access
- 1 December 2025
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3163 (1)
Enhancing Main Steam Temperature Prediction With Global Spatial Dependencies and Local Temporal Dynamics
Main Steam Temperature (MST) prediction is crucial for the safety and efficiency of thermal power plants but remains challenging due to complex spatio-temporal coupling factors. This paper proposes a novel deep learning framework that enhances predictive performance by explicitly modeling Global Spatial Dependencies and Local Temporal Dynamics. We design a spatial clustering module to capture global relationships across sensors and integrate cyclical temporal patterns to learn local temporal evolution. Experiments on a real-world power plant dataset demonstrate that our method outperforms baseline models (e.g., DLinear, Informer, Autoformer) across multiple forecasting horizons, significantly reducing MAE and RMSE metrics. The results indicate that explicitly decoupling and fusing spatio-temporal features is an effective way to improve MST prediction accuracy.
- 1 December 2025
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3163 (1)
Open AccessEnhancing Main Steam Temperature Prediction With Global Spatial Dependencies and Local Temporal Dynamics
Main Steam Temperature (MST) prediction is crucial for the safety and efficiency of thermal power plants but remains challenging due to complex spatio-temporal coupling factors. This paper proposes a novel deep learning framework that enhances predictive performance by explicitly modeling Global Spatial Dependencies and Local Temporal Dynamics. We design a spatial clustering module to capture global relationships across sensors and integrate cyclical temporal patterns to learn local temporal evolution. Experiments on a real-world power plant dataset demonstrate that our method outperforms baseline models (e.g., DLinear, Informer, Autoformer) across multiple forecasting horizons, significantly reducing MAE and RMSE metrics. The results indicate that explicitly decoupling and fusing spatio-temporal features is an effective way to improve MST prediction accuracy.
- 24 September 2024
- Published by Springer Nature in Advances in Astronautics Science and Technology
- Vol. 7 (3-4) , 197-208
Video Information-Based Liquid Rocket Engine Fault Simulation Test Method under Complex Environment
- 24 September 2024
- Published by Springer Nature in Advances in Astronautics Science and Technology
- Vol. 7 (3-4) , 197-208
Video Information-Based Liquid Rocket Engine Fault Simulation Test Method under Complex Environment
- Open Access
Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data
Fault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM) is proposed for intelligent fault diagnosis of LREs. 1D-CNN is responsible for extracting sequential signals collected from multi sensors. Then the interpretable LSTM is developed to model the extracted features, which contributes to modeling the temporal information. The proposed method was executed for fault diagnosis using the simulated measurement data of the LRE mathematical model. The results demonstrate the proposed algorithm outperforms other methods in terms of accuracy of fault diagnosis. Through experimental verification, the method proposed in this paper was compared with CNN, 1DCNN-SVM and CNN-LSTM in terms of LRE startup transient fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (97.39%).
Open AccessIntelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data
Fault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM) is proposed for intelligent fault diagnosis of LREs. 1D-CNN is responsible for extracting sequential signals collected from multi sensors. Then the interpretable LSTM is developed to model the extracted features, which contributes to modeling the temporal information. The proposed method was executed for fault diagnosis using the simulated measurement data of the LRE mathematical model. The results demonstrate the proposed algorithm outperforms other methods in terms of accuracy of fault diagnosis. Through experimental verification, the method proposed in this paper was compared with CNN, 1DCNN-SVM and CNN-LSTM in terms of LRE startup transient fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (97.39%).