LNG深海输气管道可靠性分析
|
摘要
为降低海水腐蚀因素间的复杂度,有效分析LNG深海输气管道的可靠性,构建了KPCA融合改进Wiener的预测模型。运用KPCA法实现数据降维,结合改进的Wiener及加速方程建立退化模型,并将KPCA筛选的主成分作为输入,利用MCMC法对模型参数仿真求解,进而分析管道可靠性。结果表明,LNG深海输气管道初期状态相对稳定,后由于海水腐蚀作用,可靠性下降。
In order to reduce the complexity of seawater corrosion factors, and analysis the reliability of deep-sea LNG gas pipelines effectively, a prediction model based on KPCA and improved Wiener is constructed. The KPCA method was used to achieve data dimensionality reduction, and the improved Wiener and acceleration equations were used to establish the degradation model. Taking the principal components screened by KPCA as input, MCMC is used to calculate the model parameters, and then the reliability of the pipelines is analyzed. The results show that the initial state of the deep sea LNG gas pipeline is relatively stable, but it is suddenly reduced due to the corrosion of seawater.
In order to reduce the complexity of seawater corrosion factors, and analysis the reliability of deep-sea LNG gas pipelines effectively, a prediction model based on KPCA and improved Wiener is constructed. The KPCA method was used to achieve data dimensionality reduction, and the improved Wiener and acceleration equations were used to establish the degradation model. Taking the principal components screened by KPCA as input, MCMC is used to calculate the model parameters, and then the reliability of the pipelines is analyzed. The results show that the initial state of the deep sea LNG gas pipeline is relatively stable, but it is suddenly reduced due to the corrosion of seawater.
引文
[1]王小完,骆济豪,袁宏伟,等.海底天然气管道疲劳破坏泄漏灾害研究[J].消防科学与技术,2018,37(6):729-732.
[2]LEIRA B J,NAESS A,NAESS O E B.Reliability analysis of corroding pipelines by enhanced Monte Carlo simulation[J].International Journal of Pressure Vessels&Piping,2016,144:11-17.
[3]陈典斌,韩东霏,张二保,等.腐蚀管道剩余寿命预测及结构可靠度分析的VB/MATLAB程序实现[J].科技创新导报,2014,(12):83-86.
[4]OSSAI C I,BOSWELL B,DAVIES I.Markov chain modelling for time evolution of internal pitting corrosion distribution of oil and gas pipelines[J].Engineering Failure Analysis,2016,60:209-228.
[5]骆正山,蒋丽云.基于概率神经网络的油气管道的可靠性评估[J].消防科学与技术,2015,34(11):1517-1520.
[6]El-ABBASY M S,SENOUCI A,ZAYED T,et al.Artificial neural network models for predicting condition of offshore oil and gas pipelines[J].Automation in Construction,2014,45:50-65.
[7]王新颖,宋兴帅,杨泰旺,等.LS-SVM模型在城市燃气管道风险评估中的应用[J].消防科学与技术,2017,36(11):1598-1601.
[8]高凯.LNG海底输气管道腐蚀因素与防护技术探讨[J].上海煤气,2014,(4):34-37.
[9]胡舸.海底管线腐蚀检测与腐蚀预测的研究[D].重庆:重庆大学,2007.
[10]JIANG Q C,YAN X F.Weighted kernel principal component analysis based on probability density estimation and moving window and its application in nonlinear chemical process monitoring[J].Chemometrics and Intelligent Laboratory Systems,2013,127(15):121-131.
[11]毕傲睿,骆正山,王小完,等.基于土壤腐蚀主成分的金属管道退化维纳过程研究[J].材料保护,2018,51(1):37-42.
[12]吴晓辉,蔡忠义,李全祥.非线性和随机效应的加速退化过程建模方法[J].合肥工业大学学报:自然科学版,2017,40(10):1308-1311.
[2]LEIRA B J,NAESS A,NAESS O E B.Reliability analysis of corroding pipelines by enhanced Monte Carlo simulation[J].International Journal of Pressure Vessels&Piping,2016,144:11-17.
[3]陈典斌,韩东霏,张二保,等.腐蚀管道剩余寿命预测及结构可靠度分析的VB/MATLAB程序实现[J].科技创新导报,2014,(12):83-86.
[4]OSSAI C I,BOSWELL B,DAVIES I.Markov chain modelling for time evolution of internal pitting corrosion distribution of oil and gas pipelines[J].Engineering Failure Analysis,2016,60:209-228.
[5]骆正山,蒋丽云.基于概率神经网络的油气管道的可靠性评估[J].消防科学与技术,2015,34(11):1517-1520.
[6]El-ABBASY M S,SENOUCI A,ZAYED T,et al.Artificial neural network models for predicting condition of offshore oil and gas pipelines[J].Automation in Construction,2014,45:50-65.
[7]王新颖,宋兴帅,杨泰旺,等.LS-SVM模型在城市燃气管道风险评估中的应用[J].消防科学与技术,2017,36(11):1598-1601.
[8]高凯.LNG海底输气管道腐蚀因素与防护技术探讨[J].上海煤气,2014,(4):34-37.
[9]胡舸.海底管线腐蚀检测与腐蚀预测的研究[D].重庆:重庆大学,2007.
[10]JIANG Q C,YAN X F.Weighted kernel principal component analysis based on probability density estimation and moving window and its application in nonlinear chemical process monitoring[J].Chemometrics and Intelligent Laboratory Systems,2013,127(15):121-131.
[11]毕傲睿,骆正山,王小完,等.基于土壤腐蚀主成分的金属管道退化维纳过程研究[J].材料保护,2018,51(1):37-42.
[12]吴晓辉,蔡忠义,李全祥.非线性和随机效应的加速退化过程建模方法[J].合肥工业大学学报:自然科学版,2017,40(10):1308-1311.