Development of Fatigue Load Prediction Algorithm for Wind Turbines

• DOI: 10.7836/kses.2021.41.4.093
• Publication Date: 2021-09-09T04:30:58Z
• Authors: Jungchul Choi; Eunkuk Son; Gwangse Lee; Minsang Kang; Jinjae Lee; Sungmok Hwang; Sail Park
• Keywords: Disconnection; Structural Health Monitoring

Continuous fatigue information is essential for the structural health monitoring (SHM) of wind turbines. Faults, such as sensor failure, data loss, and cable disconnection, can result in a total loss SHM. To avoid malfunction, machine learning algorithms polynomial curve fitting are suggested to predict missing from otherwise known measurement data. Artificial neural networks showed best prediction performance. Decision trees regularized linear regression also powerful alternatives.