[1]肖斌,张恒宾,刘宏伟.改进PSO-BPNN算法在管道腐蚀预测中的应用[J].郑州大学学报(工学版),2022,43(01):27-33.[doi:10.13705/j.issn.1671-6833.2022.01.008]
　XIAO Bin,ZHANG Hengbin,LIU Hongwei.Application of Improved PSO-BPNN Algorithm in Corroded Pipelines Prediction[J].Journal of Zhengzhou University (Engineering Science),2022,43(01):27-33.[doi:10.13705/j.issn.1671-6833.2022.01.008]
点击复制

改进PSO-BPNN算法在管道腐蚀预测中的应用()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年01期
页码:
27-33
栏目:
出版日期:
2022-01-09

文章信息/Info

Title:
Application of Improved PSO-BPNN Algorithm in Corroded Pipelines Prediction
作者:
肖斌; 张恒宾; 刘宏伟
西南石油大学计算机科学学院;

Author(s):
XIAO Bin;  ZHANG Hengbin;  LIU Hongwei
School of Computer Science, Southwest Petroleum University, Chengdu 610500, China
关键词:
Keywords:
particle swarm optimization;  nonlinear decreasing inertia weight;  neural network;  corroded pipelines;  residual strength
分类号:
TE973.6；TP183
DOI:
10.13705/j.issn.1671-6833.2022.01.008
文献标志码:
A
摘要:
针对腐蚀管道的剩余强度预测中公式计算准确性较低和有限元分析（FEA）过于繁琐的问题，提出了一种改进的粒子群算法优化的神经网络模型（IPSO-BPNN）来预测腐蚀管道剩余强度。首先，在传统粒子群算法的基础上，提出了一种双向递减惯性权重，引入了遗传交叉算子，形成了改进的粒子群算法（IPSO）。其次，采用IPSO算法对神经网络的权重和阈值进行优化，建立IPSO-BPNN模型。最后，在真实的管道测试爆破数据集上进行实验，分别使用线性回归(LR)、FEA、BPNN、PSO-BPNN以及IPSO-BPNN模型对腐蚀管道剩余强度进行预测。结果表明，IPSO-BPNN模型的预测精度较LR、FE、BPNN和PSO-BPNN有明显提升。
Abstract:
Due to the impact of buried environment and medium transported, oil pipelines will be gradually corroded with the increasing of service life. Traditional methods for calculating the residual strength of corroded pipelines included formula calculation and finite element analysis, etc. Aiming at the problems of low calculation accuracy of formulas and too complicated finite element analysis (FEA) in the prediction of the residual strength of corroded pipelines, an improved particle swarm optimization neural network model (IPSO-BPNN) was proposed to predict the residual strength of corroded pipelines. Firstly, based on the traditional particle swarm optimization, a new nonlinear decreasing inertia weight was proposed to update the velocity and location of elements quickly, and the genetic crossover operator was introduced to increase the diversity of particles, then form an improved particle swarm optimization algorithm (IPSO). Secondly, the IPSO algorithm was used to optimize the weights and thresholds of the neural network, and initialize the neural network with optimized weights and thresholds to establish the IPSO-BPNN model. Finally, the linear regression(LR),FEA, back-propagation neural network(BPNN), particle swarm optimization back-propagation neural network(PSO-BPNN) and IPSO-BPNN model were experimented on real pipelines test blasting data sets to predict the residual strength of the corroded pipelines. MAE, RMSE and MAPE were used as indicators to evaluate the predic-tability of the models. The results on the test set of two data sets showed that the MAE of the IPSO-BPNN model was 0.525 4, 0.718 5; the MAPE was 3.77%, 2.68%; the RMSE was 0.672 6, 0.947 2, respectively. The three indicators were significantly improved compared to LR, FEA, BPNN and PSO-BPNN. It showed that this method could improve the accuracy of predicting the residual strength of corroded pipelines, and could provide a more accurate basis for pipeline inspection.

参考文献/References:

［1］ ABDALLA F J E，MACHADO Ｒ D，BEＲTIN Ｒ J，et al． On the failure pressure of pipelines containing wall reduction and isolated pit corrosion defects ［J］． Computers ＆ structures，2014，132: 22－33． 

［2］ WANG N Y，ZAＲGHAMEE M S． Evaluating fitnessfor-service of corroded metal pipelines: structural reliability bases［J］．Journal of pipeline systems engineering and practice，2014，5( 1) : 04013012． 
［3］ 臧雪瑞，顾晓婷，王秋妍，等．含腐蚀缺陷高钢级输 气管道的失效压力模型［J］． 油 气 储 运，2019，38 ( 3) : 285－290，296． 
［4］ 马钢，李俊飞，白瑞，等．基于 PCA-SVＲ 模型的油气 管道剩余强度预测［J］．油气储运，2019，38 ( 10) : 1119－1124． 
［5］ 梁静，刘睿，瞿博阳，等．进化算法在大规模优化问 题中 的 应 用 综 述［J］． 郑 州 大 学 学 报 ( 工 学 版) ， 2018，39( 3) : 15－21． 
［6］ KENNEDY J，EBEＲHAＲT Ｒ． Particle swarm optimization ［C］/ /Proceedings of ICNN’ 95-International Conference on Neural Networks． Piscataway: IEEE， 1995: 1942－1948． 
［7］ SHI Y，EBEＲHAＲT Ｒ．A modified particle swarm optimizer［C］/ /1998 IEEE International Conference on Evolutionary Computation Proceedings． Piscataway: IEEE，1998: 69－73．
 ［8］ SHI Y B． Optimization of PID parameters of hydroelectric generator based on adaptive inertia weight PSO ［C］/ /2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference ( ITAIC ) ． Piscataway: IEEE，2019: 1854 －1857． 
［9］ LIANG M Y，CAI X H，CAO B Y． Ｒandom inertia weight PSO based MPPT for solar PV under partial shaded condition［J］．IOP conference series: earth and environmental science，2020，585: 012028． 
［10］ NKWANYANA T B，WANG Z H． Improved particle swarm optimization base on the combination of linear decreasing and chaotic inertia weights［C］/ /2020 12th International Conference on Computational Intelligence and Communication Networks ( CICN) ． Piscataway: IEEE，2020: 460－465． 
［11］ CHANG J，HU Z G，TAO Y，et al． Task scheduling based on dynamic non-linear PSO in cloud environment ［C］/ /2018 IEEE 9th International Conference on Software Engineering and Service Science ( ICSESS) ． Piscataway: IEEE，2018: 877－880． 
［12］ 丁承君，王鑫，冯玉伯，等．基于粒子群优化算法的 AGV 路径规划［J］．传感器与微系统，2020，39( 8) : 123－126．
 ［13］ SAXENA S，POHIT M．A new non linear inertia weight approach in PSO for faster rigid image registration ［C］/ /2019 6th International Conference on Signal Processing and Integrated Networks ( SPIN) ． Piscataway: IEEE，2019: 607－612． 
［14］ 高飞．MATLAB 智能算法超级学习手册［M］．北京: 人民邮电出版社，2014: 259－260． 
［15］ YUAN X F，LIU Z A，MIAO Z M，et al．Fault diagnosis of analog circuits based on IH-PSO optimized support vector machine［J］． IEEE access，2019，7: 137945 －137958． 
［16］ MA B，SHUAI J，LIU D X，et al．Assessment on failure pressure of high strength pipeline with corrosion defects ［J］．Engineering failure analysis，2013，32: 209－219． 
［17］ 崔铭伟，曹学文．腐蚀缺陷对中高强度油气管道失 效压力 的 影 响［J］． 石 油 学 报，2012，33 ( 6) : 1086 －1092．
 ［18］ 武琳，方清，粟紫葳，等．中高强度压力管道腐蚀缺 陷剩余强度评估方法的对比研究［J］．内蒙古石油 化工，2014，40( 23) : 10－11． 
［19］ FＲEIＲE J L F，VIEIＲA Ｒ D，CASTＲO J T P，et al． Part 3: burst tests of pipeline with extensive longitudinal metal loss［J］． Experimental techniques， 2006，30( 6) : 60－65． 
［20］ 王战辉，马向荣，李瑞瑞．高钢级油气管道剩余强度 评价方 法 研 究［J］． 当 代 化 工，2019，48 ( 8) : 1853 －1857． 
［21］ 杨燕华，顾晓婷，张旭，等．高级 X100 输气管道含双 点腐蚀 缺 陷 的 剩 余 强 度研 究［J］． 腐 蚀 与 防 护， 2021，42( 4) : 48－53． 
［22］ 贾俊平．统计学概论［M］．北京: 中国人民大学出版 社，2011．

更新日期/Last Update: 2022-01-09