TY - JOUR

T1 - Quantum machine learning based wind turbine condition monitoring

T2 - State of the art and future prospects

AU - Zhang, Zhefeng

AU - Wu, Yueqi

AU - Ma, Xiandong

PY - 2025/3/15

Y1 - 2025/3/15

N2 - Wind energy, as a popular renewable resource, has gained extensive development and application in recent decades. Effective condition monitoring and fault diagnosis are crucial for ensuring the reliable operation of wind turbines. While conventional machine learning methods have been widely used in wind turbine condition monitoring, these approaches often face challenges such as complex feature extraction, limited model generalization, and high computational costs when dealing with large-scale, high-dimensional, and complex datasets. The emergence of quantum computing has opened up a new paradigm of machine learning algorithms. Quantum machine learning combines the advantages of quantum computing and machine learning, with the potential to surpass classical computational capabilities. This paper firstly reviews applications and limitations of the state-of-the-art machine learning-based condition monitoring techniques for wind turbines. It then reviews the fundamentals of quantum computing, quantum machine learning algorithms and their applications, covering quantum-based feature extraction, classification and regression for fault detection and the use of quantum neural networks for predictive maintenance. Through comparison, it is observed that quantum machine learning methods, even without extensive optimization, can achieve accuracy levels comparable to those of optimized conventional machine learning approaches. The challenges of applying quantum machine learning are also addressed, along with the future research and development prospects. The objective of this review is to fill a gap in the published literature by providing a new paradigm approach for wind turbine condition monitoring. By promoting quantum machine learning in this field, the reliability and efficiency of wind power systems are ultimately sought to be enhanced.

AB - Wind energy, as a popular renewable resource, has gained extensive development and application in recent decades. Effective condition monitoring and fault diagnosis are crucial for ensuring the reliable operation of wind turbines. While conventional machine learning methods have been widely used in wind turbine condition monitoring, these approaches often face challenges such as complex feature extraction, limited model generalization, and high computational costs when dealing with large-scale, high-dimensional, and complex datasets. The emergence of quantum computing has opened up a new paradigm of machine learning algorithms. Quantum machine learning combines the advantages of quantum computing and machine learning, with the potential to surpass classical computational capabilities. This paper firstly reviews applications and limitations of the state-of-the-art machine learning-based condition monitoring techniques for wind turbines. It then reviews the fundamentals of quantum computing, quantum machine learning algorithms and their applications, covering quantum-based feature extraction, classification and regression for fault detection and the use of quantum neural networks for predictive maintenance. Through comparison, it is observed that quantum machine learning methods, even without extensive optimization, can achieve accuracy levels comparable to those of optimized conventional machine learning approaches. The challenges of applying quantum machine learning are also addressed, along with the future research and development prospects. The objective of this review is to fill a gap in the published literature by providing a new paradigm approach for wind turbine condition monitoring. By promoting quantum machine learning in this field, the reliability and efficiency of wind power systems are ultimately sought to be enhanced.

KW - Condition Monitoring (CM)

KW - Wind Turbine (WT)

KW - Machine Learning (ML)

KW - Deep Learning (DL)

KW - Quantum Machine Learning (QML)

KW - Fault detection

KW - Fault diagnosis

KW - Fault prognosis

U2 - 10.1016/j.enconman.2025.119694

DO - 10.1016/j.enconman.2025.119694

M3 - Review article

VL - 332

JO - Energy Conversion and Management

JF - Energy Conversion and Management

SN - 0196-8904

M1 - 119694

ER -