Advanced Wind Turbine Sensor Monitoring Technique Developed

Strategic Insights -

A new research study from Hunan University has made significant contributions to wind turbine sensor monitoring by proposing a technique based on multi-strategy optimization Harris Hawks optimization (MHHO) and deep belief network (DBN). This technique has been found to effectively monitor the state of wind turbine sensors and recognize sensor fault categories in real-time, improving the safety of wind turbine operation. The research was supported by the National Key Research & Development Program of China, National Natural Science Foundation of China (NSFC), and Hunan Provincial Education Department Youth Project.

Key Takeaways:

  • The proposed technique uses MHHO and DBN to monitor the status and fault identification of wind turbine sensors, which is crucial for the safe and economic operation of wind turbines.
  • The input and output parameters of wind speed sensor and temperature sensor are selected using the mixed correlation index.
  • The MHHO-DBN-based wind turbine sensor state monitoring and fault identification model is established, and the time sliding window performance evaluation index is constructed.
  • The threshold of the wind turbine sensor abnormality index is determined according to the interval estimation theory of statistics.
  • A mathematical model is established to identify the faults of sensors with abnormal states.
  • The MHHO-DBN model is used to monitor the actual sensor state, and the mathematical model is used to identify the fault.
  • The calculation results reveal that this technique can effectively monitor the state of the wind turbine sensors and recognize sensor fault categories in time.

Statistics:

  • The research was supported by the National Key Research & Development Program of China, National Natural Science Foundation of China (NSFC), and Hunan Provincial Education Department Youth Project.
  • The study was conducted by researchers from Hunan University, including Qiancheng Zhao, Anfeng Zhu, Tianlong Yang, Ling Zhou, and Bing Zeng.
  • The study was published in the journal Computers and Electrical Engineering, volume 125, in 2025.
  • The Pergamon-elsevier Science Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, England is the publisher of the journal.

Sources:

  • Qiancheng Zhao, et al. "A Hybrid Model Based On Advanced Optimization Algorithm, and Deep Learning Model for Wind Turbine Sensor Condition Monitoring and Fault Identification." Computers and Electrical Engineering, 2025;125.
  • NewsRx. "Researchers from Hunan University Describe Findings in Computers and Electrical Engineering (A Hybrid Model Based On Advanced Optimization Algorithm, and Deep Learning Model for Wind Turbine Sensor Condition Monitoring and Fault Identification)." Journal of Engineering. July 7, 2025; p 4253.