[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,et al.CCFAI:Application of IPSO-BPNN Algorithm with Dual-phase Decreasing Weight 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卷
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:
CCFAI:Application of IPSO-BPNN Algorithm with Dual-phase Decreasing Weight 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, University of Petroleum University; School of Computer Science;

关键词:
Keywords:
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:
Aiming at the problems that the low calculation accuracy of the formulas and the finite element analysis (FEA) is too complicated in the prediction of the residual strength of the corroded pipelines. An improved particle swarm optimization neural network model (IPSO-BPNN) was proposed to predict the residual strength of corroded pipelines. First, ba<x>se on traditional particle swarm optimization, a new Dual-phase decreasing inertia weight was proposed, and the genetic crossover operator was introduced to form an improved particle swarm optimization algorithm (IPSO). Second, the IPSO algorithm was used to optimize the weights and thresholds of the neural network, and the IPSO-BPNN model was established. Finally, the linear regression(LR),FEA,BPNN, PSO-BPNN and IPSO-BPNN model were experimented on real pipelines test blasting data sets to predict the residual strength of the corroded pipelines. The results show that prediction accuracy of the IPSO-BPNN model is significantly improved compared to LR, FEA, BPNN and PSO-BPNN.
更新日期/Last Update: 2022-01-09