Performance evaluation method of oil and gas pipeline integrity management

The performance evaluation of integrity management has become the focus of attention because integrity management has become widely accepted by pipeline operators. This paper proposes a three-index system of pipeline integrity management performance evaluation (TISPIMPE), which includes system construction, implementation process, and pipeline health status, comprehensively evaluating the status, adequacy, and effectiveness of integrity management. It helps the pipeline operators to determine the weakness in each step. Based on the improved analytic hierarchy process (AHP), the different backgrounds of experts are fully considered, and experts' opinions are revised. The adjustment coefficient of performance evaluation is set up simultaneously, and the evaluation results are adjusted to make the results more reasonable. Taking the performance evaluation of pipeline integrity management of an oil and gas company as an example, it is shown that TISPIMPE has reasonable practicability and can accurately reflect the shortcomings of pipeline integrity management. TISPIMPE can effectively help pipeline managers comprehensively and systematically evaluate the performance of pipeline integrity management and gain an in-depth understanding of pipeline operation status.     

基于ISOA-RBPNN的埋地管道剩余强度预测*

为提高腐蚀管道剩余强度的预测精度，提出引入弹性梯度下降法改进BP神经网络，并融合改进海鸥优化算法(ISOA)，构建腐蚀管道剩余强度预测模型。关于改进BP神经网络模型的参数寻优，首先采用Cat混沌映射初始化改进海鸥优化算法(SOA)初始种群的分布，提升寻优能力，优化SOA的搜索方向和攻击形式，增强其全局搜索能力并提高收敛速度，然后用ISOA对弹性BP神经网络（RBPNN）模型中的权值和阈值进行寻优，最后构建ISOA-RBPNN预测模型。以管道爆破数据为例，利用MATLAB进行仿真模拟，并与PSO-BPNN模型和IFA-BPNN模型预测结果进行对比分析。研究结果表明:ISOA-RBPNN模型的各项评价指标均优于其他2个模型，预测结果较实际值误差更小，在预测腐蚀管道剩余强度领域具有更好的性能，可为后续研究腐蚀管道剩余寿命和制定维修策略提供参考依据。