Looseness detection of complex multi-bolted flange joints has long been an important problem to be focused on, especially for the scene of unknown multi-bolt loosening at the same time. In this study, a stable, efficient and robust guided wave recognition method for multi-bolt loosening is proposed for the first time by taking long-term monitoring data. This method studies the nonlinear characteristics of transmitted wave energy with bolt preload by formula. Then, a novel probability indicator reflecting the loosening position is proposed and a prior prediction model of bolt loosening degree is established. The prediction model is based on prior data fitting in a small number of working conditions, which has obvious advantages over deep learning. The simulation and experimental results based on flange pipes show that the proposed indicator can effectively determine the loosening positions of multiple bolts, and the prediction model also performs well in degree recognition. The proposed detection method has great potential in real-time monitoring applications by virtue of its high sensitivity to the loosening of multi-bolted joint structures.

中文翻译：

---

基于非线性波能传输的多螺栓法兰节点松动状态监测与识别


复杂多螺栓法兰接头的松动检测长期以来一直是一个需要关注的重要问题，尤其是对于同时发生未知多螺栓松动的场景。本文通过长期监测数据，首次提出了一种稳定、高效、鲁棒的多螺栓松动导波识别方法。该方法通过公式研究螺栓预紧力下透射波能的非线性特性。然后，提出反映松动位置的新型概率指标，建立螺栓松动程度的先验预测模型。该预测模型基于在少量工况下的先验数据拟合，与深度学习相比具有明显的优势。基于法兰管的仿真和实验结果表明，所提指标能够有效确定多个螺栓的松动位置，预测模型在度识别方面也表现良好。所提出的检测方法凭借其对多螺栓接头结构松动的高灵敏度，在实时监测应用中具有很大的潜力。