含油海洋环境下316L仪表管点蚀深度预测模型研究
Research on Pitting Depth Prediction Model of 316L Instrument Tube in Oil-Bearing Marine Environment
骆正山 1刘月 1骆济豪 2王小完1
作者信息
- 1. 西安建筑科技大学管理学院,陕西 西安 710055
- 2. 北京理工大学睿信学院,北京 102488
- 折叠
摘要
为了提升316L不锈钢仪表管在含油海洋大气环境下点蚀深度的预测精度,建立了基于改进粒子群算法优化的直接离散灰色点蚀深度预测模型[SCPSO-DDGM(1,1,λ)].首先以暴露实验点蚀数据为例,建立DDGM(1,1)模型,并利用新信息变权弱化缓冲算子、等维灰数递补对模型进行动态改进;后采用非线性变化惯性权重和正弦余弦学习因子提高粒子群算法(PSO)的寻优能力和收敛速度,引入高斯扰动策略增强PSO跳出局部最优的能力,进而用SCPSO对改进后的DDGM(1,1,λ)模型中的权重参数λ进行寻优;最终在MATLAB中进行仿真计算,分析对比SCPSO-DDGM(1,1,λ)模型与GM(1,1)、DDGM(1,1)、PSO-DDGM(1,1,λ)模型的预测结果.结果表明:在研究的时间区间内,经优化的新模型预测深度与实际深度高度吻合,较于对比模型性能更优.证明SCPSO-DDGM(1,1,λ)模型能够有效预测仪表管点蚀深度,为仪表管的腐蚀研究提供了新的思路与方法.
Abstract
In order to improve the prediction accuracy of pitting depth of 316L stainless steel instrument pipe in oily marine atmosphere,a di-rect discrete grey pitting depth prediction model (SCPSO-DDGM (1,1,λ)) based on improved particle swarm algorithm optimization was es-tablished.First,using pitting corrosion data from exposure experiments as an example,the DDGM(1,1) model was established,and the model was dynamically improved by applying a new information-based variable weight weakening buffer operator and dimension-equivalent gray number supplementation.Then,a nonlinear variation inertia weight and sine-cosine learning factors were used to enhance the optimization abili-ty and convergence speed of the Particle Swarm Optimization(PSO) algorithm,while a Gaussian perturbation strategy was introduced to im-prove PSO's ability to escape local optima.The SCPSO was then employed to optimize the weight parameter λ in the improved DDGM (1,1,λ) model.Finally,simulation calculations were performed in MATLAB to analyze and compare the prediction results of the SCPSO-DDGM (1,1,λ) model with those of the GM (1,1),DDGM (1,1) and PSO-DDGM (1,1,λ) models.Results showed that during the time peri-od of the study,the predicted depth of the optimized new model was highly consistent with the actual depth,and its performance was better than that of the comparison model.Overall,it was proved that the SCPSO-DDGM (1,1,λ) model can effectively predict the pitting depth of instrument tubes,which provides new ideas and methods for the corrosion research of instrument tubes.
关键词
含油海洋大气环境/316L不锈钢仪表管/点蚀深度/改进粒子群优化算法(SCPSO)/DDGM(1,1,λ)模型Key words
oil-bearing marine atmospheric environment/316L stainless steel instrument tube/pitting depth/improved Particle Swarm Optimization (SCPSO)/DDGM (1,1,λ) model引用本文复制引用
出版年
2024
NETL
NSTL
万方数据