Zhiqiang Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhiqiang Zhao has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Bo Li
Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524091, China
4 shared publications - Jin Xu
Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524088, China
4 shared publications - Long Ma
Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524088, China
3 shared publications - Xinxiang Pan
Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, China
3 shared publications - Fang Lin
Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524088, China
2 shared publications - Haixia Wang
Navigation College, Dalian Maritime University, Dalian 116026, China
2 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (21) , 3700
Unsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework
Marine oil spill accidents pose serious threats to marine ecosystems and coastal economic development. X-band marine radar provides an effective means for nearshore oil spill monitoring, yet accurate oil film segmentation remains challenging because of grayscale overlap between oil films and sea clutter, range-dependent echo attenuation, and noise interference. To address these challenges, an unsupervised oil spill detection method integrating HBA-AE ROI extraction with IAEA fine segmentation is proposed. In the coarse detection stage, an autoencoder (AE) maps pixel grayscale intensity, local mean, and local standard deviation into a compact two-dimensional latent space. The AE-derived latent representation is further optimized by HBA to enhance oil film–sea clutter separability, after which K-Means clustering identifies candidate oil spill ROIs. In the subsequent fine segmentation stage, the extracted ROI constrains the search domain, while the Improved Alpha Evolution Algorithm (IAEA) maximizes the three-class Otsu between-class variance to determine the optimal dual thresholds for oil film delineation. Experiments using X-band marine radar data collected during the Dalian 7·16 oil spill accident were conducted against seven representative methods. The proposed framework achieved a Precision of 97.20%, an F1-score of 86.60%, and an IoU of 76.40%, demonstrating superior oil film segmentation accuracy and effective false-alarm suppression under complex sea-clutter conditions. It also maintained a favorable balance between segmentation accuracy and computational efficiency, demonstrating its potential for marine oil spill monitoring under the investigated radar observation conditions.
- 28 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (21) , 3700
Open AccessUnsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework
Marine oil spill accidents pose serious threats to marine ecosystems and coastal economic development. X-band marine radar provides an effective means for nearshore oil spill monitoring, yet accurate oil film segmentation remains challenging because of grayscale overlap between oil films and sea clutter, range-dependent echo attenuation, and noise interference. To address these challenges, an unsupervised oil spill detection method integrating HBA-AE ROI extraction with IAEA fine segmentation is proposed. In the coarse detection stage, an autoencoder (AE) maps pixel grayscale intensity, local mean, and local standard deviation into a compact two-dimensional latent space. The AE-derived latent representation is further optimized by HBA to enhance oil film–sea clutter separability, after which K-Means clustering identifies candidate oil spill ROIs. In the subsequent fine segmentation stage, the extracted ROI constrains the search domain, while the Improved Alpha Evolution Algorithm (IAEA) maximizes the three-class Otsu between-class variance to determine the optimal dual thresholds for oil film delineation. Experiments using X-band marine radar data collected during the Dalian 7·16 oil spill accident were conducted against seven representative methods. The proposed framework achieved a Precision of 97.20%, an F1-score of 86.60%, and an IoU of 76.40%, demonstrating superior oil film segmentation accuracy and effective false-alarm suppression under complex sea-clutter conditions. It also maintained a favorable balance between segmentation accuracy and computational efficiency, demonstrating its potential for marine oil spill monitoring under the investigated radar observation conditions.
- 13 August 2025
- Published by Springer Nature
- p. 189-202
Application and Optimization in Ship Inspection and Intelligent Maintenance
- 13 August 2025
- Published by Springer Nature
- p. 189-202
Application and Optimization in Ship Inspection and Intelligent Maintenance
- Open Access
- 22 March 2023
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 11 (3) , 670
Preliminary Investigation on Marine Radar Oil Spill Monitoring Method Using YOLO Model
Due to the recent rapid growth of ocean oil development and transportation, the offshore oil spill risk accident probability has increased unevenly. The marine oil spill poses a great threat to the development of coastal cities. Therefore, effective and reliable technologies must be used to monitor oil spills to minimize disaster losses. Based on YOLO deep learning network, an automatic oil spill detection method was proposed. The experimental data preprocessing operations include noise reduction, gray adjustment, and local contrast enhancement. Then, real and synthetically generated marine radar oil spill images were used to make slice samples for training the model in the YOLOv5 network. The detection model can identify the effective oil spill monitoring region. Finally, an adaptive threshold was applied to extract the oil slicks in the effective oil spill monitoring regions. The YOLOv5 detection model generated had the advantage of high efficiency compared with existing methods. The offshore oil spill detection method proposed can support real-time and effective data for routine patrol inspection and accident emergency response.
- 22 March 2023
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 11 (3) , 670
Open AccessPreliminary Investigation on Marine Radar Oil Spill Monitoring Method Using YOLO Model
Due to the recent rapid growth of ocean oil development and transportation, the offshore oil spill risk accident probability has increased unevenly. The marine oil spill poses a great threat to the development of coastal cities. Therefore, effective and reliable technologies must be used to monitor oil spills to minimize disaster losses. Based on YOLO deep learning network, an automatic oil spill detection method was proposed. The experimental data preprocessing operations include noise reduction, gray adjustment, and local contrast enhancement. Then, real and synthetically generated marine radar oil spill images were used to make slice samples for training the model in the YOLOv5 network. The detection model can identify the effective oil spill monitoring region. Finally, an adaptive threshold was applied to extract the oil slicks in the effective oil spill monitoring regions. The YOLOv5 detection model generated had the advantage of high efficiency compared with existing methods. The offshore oil spill detection method proposed can support real-time and effective data for routine patrol inspection and accident emergency response.
- Open Access
- 14 August 2022
- Published by MDPI AG in Nanomaterials
- Vol. 12 (16) , 2790
Ultra−Wide Range Vibration Frequency Detection Sensors Based on Elastic Steel Triboelectric Nanogenerators for Intelligent Machinery Monitoring
Vibration measurement and analysis play an important role in diagnosing mechanical faults, but existing vibration sensors are limited by issues such as dependence on external power sources and high costs. To overcome these challenges, the use of triboelectric nanogenerator (TENG)−based vibration sensors has recently attracted attention. These vibration sensors measure a small range of vibration frequencies and are not suitable for measuring high-frequency vibrations. Herein, a self-powered vibration sensor based on an elastic steel triboelectric nanogenerator (ES−TENG) is proposed. By optimizing the elastic steel sheet structure and combining time-frequency transformation and filtering processing methods, the measurement of medium- and high-frequency vibrations is achieved. These results demonstrate that the ES−TENG can perform vibration measurements in the range of 2–10,000 Hz, with a small average error (~0.42%) between the measured frequency and external vibration frequency values. Therefore, the ES−TENG can be used as a self-powered, highly-accurate vibration sensor for intelligent machinery monitoring.
- 14 August 2022
- Published by MDPI AG in Nanomaterials
- Vol. 12 (16) , 2790
Open AccessUltra−Wide Range Vibration Frequency Detection Sensors Based on Elastic Steel Triboelectric Nanogenerators for Intelligent Machinery Monitoring
Vibration measurement and analysis play an important role in diagnosing mechanical faults, but existing vibration sensors are limited by issues such as dependence on external power sources and high costs. To overcome these challenges, the use of triboelectric nanogenerator (TENG)−based vibration sensors has recently attracted attention. These vibration sensors measure a small range of vibration frequencies and are not suitable for measuring high-frequency vibrations. Herein, a self-powered vibration sensor based on an elastic steel triboelectric nanogenerator (ES−TENG) is proposed. By optimizing the elastic steel sheet structure and combining time-frequency transformation and filtering processing methods, the measurement of medium- and high-frequency vibrations is achieved. These results demonstrate that the ES−TENG can perform vibration measurements in the range of 2–10,000 Hz, with a small average error (~0.42%) between the measured frequency and external vibration frequency values. Therefore, the ES−TENG can be used as a self-powered, highly-accurate vibration sensor for intelligent machinery monitoring.
- Open Access
- 3 August 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (15) , 3715
Marine Oil Spill Detection with X-Band Shipborne Radar Using GLCM, SVM and FCM
Marine oil spills have a significant adverse impact on the economy, ecology, and human health. Rapid and effective oil spill monitoring action is extraordinarily important for controlling marine pollution. A marine oil spill detection scheme based on X-band shipborne radar image with machine learning is proposed here. First, the original shipborne radar image collected on Dalian 7.16 oil spill accident was transformed into a Cartesian coordinate system and noise suppressed. Then, texture features and SVM were used to indicate the effective monitoring location of ocean waves. Third, FCM was applied to classify the oil films and ocean waves. Finally, the oil spill detection result was transformed back to a polar coordinate system. Compared with an improved active contour model and another oil spill detection method with SVM, our method performed more intelligently. It can provide data support for marine oil spill emergency response.
- 3 August 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (15) , 3715
Open AccessMarine Oil Spill Detection with X-Band Shipborne Radar Using GLCM, SVM and FCM
Marine oil spills have a significant adverse impact on the economy, ecology, and human health. Rapid and effective oil spill monitoring action is extraordinarily important for controlling marine pollution. A marine oil spill detection scheme based on X-band shipborne radar image with machine learning is proposed here. First, the original shipborne radar image collected on Dalian 7.16 oil spill accident was transformed into a Cartesian coordinate system and noise suppressed. Then, texture features and SVM were used to indicate the effective monitoring location of ocean waves. Third, FCM was applied to classify the oil films and ocean waves. Finally, the oil spill detection result was transformed back to a polar coordinate system. Compared with an improved active contour model and another oil spill detection method with SVM, our method performed more intelligently. It can provide data support for marine oil spill emergency response.
- Open Access
- 21 February 2022
- Published by MDPI AG in Nanomaterials
- Vol. 12 (4) , 721
An Array of Flag-Type Triboelectric Nanogenerators for Harvesting Wind Energy
Harvesting wind energy from the ambient environment is a feasible method for powering wireless sensors and wireless transmission equipment. Triboelectric nanogenerators (TENGs) have proven to be a stable and promising technology for harvesting ambient wind energy. This study explores a new method for the performance enhancement and practical application of TENGs. An array of flag-type triboelectric nanogenerators (F-TENGs) for harvesting wind energy is proposed. An F-TENG consists of one piece of polytetrafluoroethylene (PTFE) membrane, which has two carbon-coated polyethylene terephthalate (PET) membranes on either side with their edges sealed. The PTFE was pre-ground to increase the initial charge on the surface and to enhance the effective contact area by improving the surface roughness, thus achieving a significant improvement in the output performance. The vertical and horizontal arrays of F-TENGs significantly improved the power output performance. The optimal power output performance was achieved when the vertical parallel distance was approximately 4D/15 (see the main text for the meaning of D), and the horizontal parallel distance was approximately 2D. We found that the peak output voltage and current of a single flag-type TENG of constant size were increased by 255% and 344%, respectively, reaching values of 64 V and 8 μA, respectively.
- 21 February 2022
- Published by MDPI AG in Nanomaterials
- Vol. 12 (4) , 721
Open AccessAn Array of Flag-Type Triboelectric Nanogenerators for Harvesting Wind Energy
Harvesting wind energy from the ambient environment is a feasible method for powering wireless sensors and wireless transmission equipment. Triboelectric nanogenerators (TENGs) have proven to be a stable and promising technology for harvesting ambient wind energy. This study explores a new method for the performance enhancement and practical application of TENGs. An array of flag-type triboelectric nanogenerators (F-TENGs) for harvesting wind energy is proposed. An F-TENG consists of one piece of polytetrafluoroethylene (PTFE) membrane, which has two carbon-coated polyethylene terephthalate (PET) membranes on either side with their edges sealed. The PTFE was pre-ground to increase the initial charge on the surface and to enhance the effective contact area by improving the surface roughness, thus achieving a significant improvement in the output performance. The vertical and horizontal arrays of F-TENGs significantly improved the power output performance. The optimal power output performance was achieved when the vertical parallel distance was approximately 4D/15 (see the main text for the meaning of D), and the horizontal parallel distance was approximately 2D. We found that the peak output voltage and current of a single flag-type TENG of constant size were increased by 255% and 344%, respectively, reaching values of 64 V and 8 μA, respectively.
- 31 March 2021
- Published by Wiley in Advanced Materials Technologies
- Vol. 6 (5) , 2001270
A Triboelectric‐Nanogenerator‐Based Gas–Solid Two‐Phase Flow Sensor for Pneumatic Conveying System Detecting
The particle concentration and the mass flow rate are the most important parameters describing the gas–solid two‐phase flow. Herein, a novel method based on triboelectric nanogenerator is proposed for measuring a particle concentration and the mass flow rate in a gas–solid two‐phase pipe flow. The as‐fabricated gas–solid two‐phase flow triboelectric nanogenerator (GS‐TENG) consists of one acrylic base plate, one copper electrode, and one stripe of polytetrafluoroethylene (PTFE) membrane. Different materials can be detected by the GS‐TENG, including organic material, such as flour, and inorganic materials, such as copper and soil. PTFE surface morphology is modified to improve the output performance of the GS‐TENG in the experiments in order to detect the output electrical signal more efficiently. The peak output current generated by the gas–solid two‐phase flow in the GS‐TENG shows a mostly linear relationship with the concentration and mass flow rate. In addition, the transferred charge in the process of the flow also shows a highly linear relationship with the concentration and the mass flow rate, which is consistent with the theoretical derivation for the single electrode TENG. The experimental results demonstrate that the measurement error of the GS‐TENG is less than 2%.
- 31 March 2021
- Published by Wiley in Advanced Materials Technologies
- Vol. 6 (5) , 2001270
A Triboelectric‐Nanogenerator‐Based Gas–Solid Two‐Phase Flow Sensor for Pneumatic Conveying System Detecting
The particle concentration and the mass flow rate are the most important parameters describing the gas–solid two‐phase flow. Herein, a novel method based on triboelectric nanogenerator is proposed for measuring a particle concentration and the mass flow rate in a gas–solid two‐phase pipe flow. The as‐fabricated gas–solid two‐phase flow triboelectric nanogenerator (GS‐TENG) consists of one acrylic base plate, one copper electrode, and one stripe of polytetrafluoroethylene (PTFE) membrane. Different materials can be detected by the GS‐TENG, including organic material, such as flour, and inorganic materials, such as copper and soil. PTFE surface morphology is modified to improve the output performance of the GS‐TENG in the experiments in order to detect the output electrical signal more efficiently. The peak output current generated by the gas–solid two‐phase flow in the GS‐TENG shows a mostly linear relationship with the concentration and mass flow rate. In addition, the transferred charge in the process of the flow also shows a highly linear relationship with the concentration and the mass flow rate, which is consistent with the theoretical derivation for the single electrode TENG. The experimental results demonstrate that the measurement error of the GS‐TENG is less than 2%.