Because thermowells are prone to fatigue damage in petroleum cracking gas pipelines, in this paper, the LES method is used to simulate the flow around thermowells through two‐way thermal‐fluid‐solid coupling, the internal causes of thermowell damage are explored, and measures for improving the thermowell safety are proposed. According to this study, when high‐speed, high‐temperature gas passes the thermocouple bushing, the main factors affecting the structural safety of the thermocouple bushing are the alternating stress caused by the vortex falling off, the thermal stress cycle due to the temperature gradient, and the pressure gradient impacted by the gas. Furthermore, this paper proposes improving the thermowell safety by installing the interference devices and optimizing the installation angle. The improvement measures were studied by conducting a two‐way thermal fluid‐structure coupling simulation. The results of this study show that after installing the interference device and optimizing the installation angle the displacement deformation of the thermowell and the equivalent stress is reduced by 57.2% and 72.1%, respectively, which indicates the safety improvement of the thermowell structure and the effectiveness of the method. The research contents of this paper can provide guidance for the installation and use of thermocouple bushing.

In order to assess the degradation state of rolling bearings and accurately grasp the remaining life information of rolling bearings, a bearing remaining life prediction method based on the grey wolf optimization algorithm to improve the BP neural network model is proposed. The method consists of two steps, firstly, using the craggy value and root mean square value to determine the first failure time of rolling bearings so as to approximate the input features, and secondly, using the Grey Wolf optimization algorithm to optimize the BP neural network to construct the degradation model of the bearings through machine learning. The method reduces the prediction error compared with conventional techniques, indicating that the method can effectively simulate the bearing degradation process and predict the remaining useful life (RUL) of the bearing.