In this study, an anomaly detection and prediction method for high‐tension bolts is proposed by using the measured strain of tower shell. The finite element models (FEMs) for the high‐tension bolts and tower‐top are built and validated with measurement data. An algorithm of anomaly detection and prediction is then developed by applying Mahalanobis‑Taguchi system. The threshold of abnormal condition for high‐tension bolts is proposed, and the formula for the prediction of remaining axial bolt force is derived by using the strain of tower shell obtained from the FEM model. Finally, onsite measurements are performed at Taikoyama wind farm to investigate the relationship between the strain of tower shell and the remaining axial bolt force. It is found that the proposed threshold based on the FEM model succeeds in detecting abnormal bolt by the Mahalanobis‑Taguchi system, and the proposed formula accurately predicts the remaining axial bolt force.

中文翻译：

---

塔筒应变对高压螺栓的异常检测与预测

本文利用实测塔架应变，提出了一种高强度螺栓的异常检测与预测方法。建立了高压螺栓和塔顶的有限元模型（FEM），并通过测量数据进行了验证。然后，通过应用Mahalanobis-Taguchi系统开发了异常检测和预测算法。提出了高强度螺栓异常状态的阈值，并利用有限元模型得到的塔身应变推导了残余轴向螺栓力的预测公式。最后，在太鼓山风电场进行了现场测量，以研究塔架应变与剩余轴向螺栓力之间的关系。