Training method and device of pipeline stress prediction model and computing equipment

• Main Authors: CAO GUOFEI, TU HUAIPENG, ZHANG ZHAOXU, YANG HONGBING, DING JIANGQIANG, ZHAO DONGYE, HE BAIYI, XIU LINRAN, JIAO QINGJUN, HU ZIQIU, TAN YUTONG, SONG YI, MA SAI, MAO JIAN, QIU CHUNBIN
• Format: Patent
• Language: Chinese; English
• Published: 02.02.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to a training method and device of a pipeline stress prediction model and computing equipment, and relates to the technical field of pipeline monitoring. The method comprises the following steps: based on section axial maximum tensile stress and section axial maximum pressure stress corresponding to each of a plurality of pipeline sections at each of a plurality of moments, a circumferential angle corresponding to the section axial maximum tensile stress, a circumferential angle corresponding to the section axial maximum pressure stress, a circumferential angle corresponding to the section axial maximum pressure stress, and a circumferential angle corresponding to the section axial maximum pressure stress; and the pipeline stress prediction model is trained according to the pipeline operation pressure and the conveying medium temperature, and the trained pipeline stress prediction model is obtained. According to the method, the sample data can be obtained, the neural network model is tra