Boqiang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Boqiang Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jie Wang
School of Mechanical Engineering, Sichuan University, Chengdu, China
2 shared publications - Shentong Ni
School of Mechanical Engineering, Sichuan University
2 shared publications - Yupeng Zhang
School of Mechanical Engineering, Sichuan University, Chengdu, China
2 shared publications Chengming Huang
Neusoft (China)
1 shared publication- Feifan Zhu
Neusoft Institute Guangdong
1 shared publication Jiamin Chen
Neusoft (China)
1 shared publication
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 95-105
Design and Realization of ROS-based All-terrain Oil and Gas Pipeline Inspection Robot
- 2 September 2026
- Published by Springer Nature
- p. 95-105
Design and Realization of ROS-based All-terrain Oil and Gas Pipeline Inspection Robot
- Open Access
- 28 August 2026
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 13 (3)
An OpenHarmony-Based AI-Driven Edge Intelligence Framework for Manufacturing Disruption Monitoring and Resilient Response
INTRODUCTION: Delayed awareness of hazards and route restrictions can weaken manufacturing continuity. OBJECTIVES: To develop an OpenHarmony-based edge-intelligence framework for disruption monitoring and resilient patrol response. METHODS: A WS63 controller performs local sensing and PID control; SparkLink SLE transmits compact frames to a Jetson Nano running a GSConv- and MSAA-enhanced YOLOv10-N detector; an ArkTS/ArkUI application presents warnings and fallback status. RESULTS: At 3 m line of sight, SLE achieved 4.8 ± 1.2 ms RTT, 67.1% lower than matched Wi-Fi/UDP and 72.1% lower than BLE. The detector reached 83.96% mAP50, 51.74% mAP50:95, 28.3 FPS, and 3.08 FPS/W. In 500 trials, recognition accuracy was 94.0% and mean alert latency was 97.9 ± 22.6 ms. CONCLUSION: The prototype supports timely warning and continuity-oriented fallback, but evidence is limited to one robot, short-range line-of-sight tests, and traffic-sign-derived proxy events.
- 28 August 2026
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 13 (3)
Open AccessAn OpenHarmony-Based AI-Driven Edge Intelligence Framework for Manufacturing Disruption Monitoring and Resilient Response
INTRODUCTION: Delayed awareness of hazards and route restrictions can weaken manufacturing continuity. OBJECTIVES: To develop an OpenHarmony-based edge-intelligence framework for disruption monitoring and resilient patrol response. METHODS: A WS63 controller performs local sensing and PID control; SparkLink SLE transmits compact frames to a Jetson Nano running a GSConv- and MSAA-enhanced YOLOv10-N detector; an ArkTS/ArkUI application presents warnings and fallback status. RESULTS: At 3 m line of sight, SLE achieved 4.8 ± 1.2 ms RTT, 67.1% lower than matched Wi-Fi/UDP and 72.1% lower than BLE. The detector reached 83.96% mAP50, 51.74% mAP50:95, 28.3 FPS, and 3.08 FPS/W. In 500 trials, recognition accuracy was 94.0% and mean alert latency was 97.9 ± 22.6 ms. CONCLUSION: The prototype supports timely warning and continuity-oriented fallback, but evidence is limited to one robot, short-range line-of-sight tests, and traffic-sign-derived proxy events.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 3512911
A Fault Diagnosis Method for Incomplete Data via Feature Compensation and Weighted Pooling
Severe signal loss in industrial remote monitoring significantly degrades the performance of fault diagnosis models, particularly when data loss rates exceed 50%. To address this challenge, a Feature Compensation Weighted Pooling Network (FCWPN) is proposed, shifting the diagnostic paradigm from signal reconstruction to robust fault feature recovery. This method utilizes Feature Loss Localization (FLL) to identify missing data segments and a Bidirectional Restoration Fusion (BRF_FC) module to compensate for gaps using contextual information from both directions. Additionally, a Global Weighted Average Pooling (GWAP) mechanism dynamically prioritizes reliable original data over compensated estimates. Experimental results on the Case Western Reserve University (CWRU) dataset demonstrate superior robustness: even with an extreme Signal Loss Rate (SLR) of 80%, FCWPN maintains a diagnostic accuracy of 88.8%, significantly outperforming traditional WDCNN and LSTM models. Furthermore, generalization tests on the Paderborn University dataset confirm the model’s versatility. These findings indicate that bidirectional compensation and dynamic weighting offer a reliable solution for machinery fault diagnosis in information-sparse environments.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 3512911
A Fault Diagnosis Method for Incomplete Data via Feature Compensation and Weighted Pooling
Severe signal loss in industrial remote monitoring significantly degrades the performance of fault diagnosis models, particularly when data loss rates exceed 50%. To address this challenge, a Feature Compensation Weighted Pooling Network (FCWPN) is proposed, shifting the diagnostic paradigm from signal reconstruction to robust fault feature recovery. This method utilizes Feature Loss Localization (FLL) to identify missing data segments and a Bidirectional Restoration Fusion (BRF_FC) module to compensate for gaps using contextual information from both directions. Additionally, a Global Weighted Average Pooling (GWAP) mechanism dynamically prioritizes reliable original data over compensated estimates. Experimental results on the Case Western Reserve University (CWRU) dataset demonstrate superior robustness: even with an extreme Signal Loss Rate (SLR) of 80%, FCWPN maintains a diagnostic accuracy of 88.8%, significantly outperforming traditional WDCNN and LSTM models. Furthermore, generalization tests on the Paderborn University dataset confirm the model’s versatility. These findings indicate that bidirectional compensation and dynamic weighting offer a reliable solution for machinery fault diagnosis in information-sparse environments.