期刊文献+

基于DE-BPNN模型的含腐蚀缺陷管道失效压力预测 被引量:11

Prediction on failure pressure of pipeline containing corrosion defects based on DE-BPNN
下载PDF
导出
摘要 为提升含腐蚀缺陷管道失效压力预测精度,准确把控管道状态,建立基于DE-BPNN的含腐蚀缺陷管道失效压力预测模型,有效避免BPNN模型陷入局部最优问题,提升预测精度。基于61组管道爆破实验数据,分别用DE-BPNN与BPNN模型进行仿真计算。结果表明:DE-BPNN预测结果平均相对误差为3.26%,R^(2)为0.98585,预测精度较BPNN模型有明显提升。应用DE-BPNN模型预测含腐蚀缺陷的管道失效压力可为长输管道运输调配和检维修提供决策支持。 To improve the prediction accuracy of the failure pressure of pipeline containing corrosion defects,and accurately control the pipeline state,a failure pressure prediction model for the pipeline with corrosion defects based on DE-BPNN was established.DE performed an optimized search on the initial weights and thresholds of the BPNN,which effectively avoided the problem of BPNN model falling into the local optimum,thus improved its prediction accuracy.Taking 61 sets of pipeline blasting test data as example,the DE-BPNN and BPNN models were used to perform the simulation calculation in Matlab respectively.The results showed that the average relative error of DE-BPNN prediction results was only 3.26%,with R^(2) of 0.98585,and the prediction accuracy was significantly improved comparing with the BPNN model.The application of DE-BPNN model to predict the failure pressure of pipelines containing corrosion defects can provide decision support for the transportation deployment,inspection and maintenance of long-distance pipelines.
作者 徐鲁帅 凌晓 马娟娟 马贺清 付小华 XU Lushuai;LING Xiao;MA Juanjuan;MA Heqing;FU Xiaohua(College of Petroleum and Chemical Engineering,Lanzhou University of Technology,Lanzhou Gansu 730050,China;College of Sciences,Lanzhou University of Technology,Lanzhou Gansu 730050,China)
出处 《中国安全生产科学技术》 CAS CSCD 北大核心 2021年第3期91-96,共6页 Journal of Safety Science and Technology
基金 国家自然科学基金项目(51904138) 甘肃省自然科学基金项目(20JR5RA451) 甘肃省高等学校创新能力提升项目(2020A-019)。
关键词 腐蚀缺陷 管道 失效压力预测 机器学习 BP神经网络 差分进化算法 corrosion defect pipeline failure pressure prediction machine learning BP neural network differential evolutionary algorithm
  • 相关文献

参考文献8

二级参考文献53

  • 1熊云奇,卢海波.螺纹紧固件拧紧工艺技术及发展趋势[J].装备维修技术,2008(2):10-13. 被引量:8
  • 2吴宗之.国外危险评价软件研究进展[J].劳动保护科学技术,1994,14(3):24-29. 被引量:16
  • 3近年来尼日利亚发生的重大输油管爆炸事件[EB/OL].新华网.http://news.xinhuanet.com,2006,(5):13.
  • 4鲍丹.中石化青岛输油管道爆炸事故原因查明认定责任事故[N].人民日报,2014,(1):10.
  • 5Cozzani V,Aatonioni G,Spadom G.Quantitative assessment of domino scenarios by a GIS-based software tool[J].Journal of Loss Prevention in the Process Industries,2006,19(5):463-477.
  • 6Cozzani V,Gubinelli G,Salzano E.Escalation thresholds in the assessment of domino accidental events[J].Journal of Hazardous Materials,2006,(129):1-21.
  • 7Gubinelli G,Zanelli S,Cozzani V.A simplified model for the assessment of the impact probability of fragments[J].Journal of Hazardous Materials,2004,116(3):175-187.
  • 8Cozzani E.The quantitative assessment of domino effects caused by overpressure Part I.Probit models[J].Journal of Hazardous Materials,2003(107):67-80.
  • 9Cozzani V,Salzano E.Threshold values for domino effects caused by blast wave interaction with process equipment[J].Journal of Loss Prevention in the Process Industries,2004,17(6):437-447.
  • 10刘丽,徐亚博,刘振翼.化工事故多米诺效应定量风险评价研究[J].中国安全生产科学技术,2008,4(2):49-52. 被引量:17

共引文献137

同被引文献94

引证文献11

二级引证文献9

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部