Rank Predictions of Internal Corrosion of Gathering Pipelines in a Natural Gas Field With a Multi-Kernel SVM Method

2020 ◽  
Author(s):  
Yuejiao Li ◽  
Weiguo Zeng ◽  
Xiufeng Li ◽  
Fajun Ren ◽  
Haijun Hu
Keyword(s):  
Natural Gas ◽  
Gaussian Kernel ◽  
Polynomial Kernel ◽  
Linear Kernel ◽  
Gas Field ◽  
Internal Corrosion ◽  
H2s Corrosion ◽  
Corrosion Risk ◽  
Internal Co2 ◽  
Kernel Svm

Abstract Internal CO2/H2S corrosion of gathering pipelines is a serious problem in natural gas plant. It is important for field engineers to assess the corrosion degree and control corrosion risk. A multi-kernel support-vector-machine (SVM) method is presented to rank internal corrosion of gathering pipelines according to the NACE RP-0775-91 standard. By considering the nonlinear indivisibility between data, we combined three kinds of kernels (linear kernel, polynomial kernel, and Gaussian kernel) into a multi-kernel SVM to rank the internal CO2/H2S corrosion of gathering pipelines. The method was applied to a natural gas field in northwest China. Corrosion data were collected and analyzed. The prediction accuracy of the multi-kernel SVM method for ranking CO2/H2S corrosion was 66%, which is higher than the results of the single-kernel SVM methods (linear kernel, polynomial kernel and Gaussian kernel), whose prediction accuracies are 50%, 48% and 54% respectively. These findings could help field engineers rank corrosion and reduce the corrosion risk.

scholarly journals Membrane-Based Electrochemical Sensors for Detecting Internal Corrosion Risk of Natural Gas Pipelines

2020 ◽  
Vol MA2020-01 (28) ◽  
pp. 2140-2140
Author(s):  
Margaret Ziomek-Moroz ◽  
Timothy Duffy ◽  
Derek M. Hall ◽  
Serguei N. Lvov
Keyword(s):  
Natural Gas ◽  
Electrochemical Sensors ◽  
Gas Pipelines ◽  
Internal Corrosion ◽  
Natural Gas Pipelines ◽  
Corrosion Risk

GA_SVM

2017 ◽  
pp. 359-397 ◽  
Author(s):  
Dilip Kumar Choubey ◽  
Sanchita Paul
Keyword(s):  
Diagnostic System ◽  
Computation Time ◽  
Modern Society ◽  
Attribute Selection ◽  
Polynomial Kernel ◽  
Sigmoid Function ◽  
Linear Kernel ◽  
Rbf Kernel ◽  
Life Threatening ◽  
Kernel Svm

The modern society is prone to many life-threatening diseases which if diagnosis early can be easily controlled. The implementation of a disease diagnostic system has gained popularity over the years. The main aim of this research is to provide a better diagnosis of diabetes. There are already several existing methods, which have been implemented for the diagnosis of diabetes. In this manuscript, firstly, Polynomial Kernel, RBF Kernel, Sigmoid Function Kernel, Linear Kernel SVM used for the classification of PIDD. Secondly GA used as an Attribute selection method and then used Polynomial Kernel, RBF Kernel, Sigmoid Function Kernel, Linear Kernel SVM on that selected attributes of PIDD for classification. So, here compared the results with and without GA in PIDD, and Linear Kernel proved better among all of the noted above classification methods. It directly seems in the paper that GA is removing insignificant features, reducing the cost and computation time and improving the accuracy, ROC of classification. The proposed method can be also used for other kinds of medical diseases.

scholarly journals Particle Swarm Optimized Hybrid Kernel-Based Multiclass Support Vector Machine for Microarray Cancer Data Analysis

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Davies Segera ◽  
Mwangi Mbuthia ◽  
Abraham Nyete
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm ◽  
Gaussian Kernel ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Linear Kernel ◽  
Penalty Factor ◽  
Multiclass Support Vector Machine ◽  
Factor C ◽  
Hybrid Kernel

Determining an optimal decision model is an important but difficult combinatorial task in imbalanced microarray-based cancer classification. Though the multiclass support vector machine (MCSVM) has already made an important contribution in this field, its performance solely depends on three aspects: the penalty factor C, the type of kernel, and its parameters. To improve the performance of this classifier in microarray-based cancer analysis, this paper proposes PSO-PCA-LGP-MCSVM model that is based on particle swarm optimization (PSO), principal component analysis (PCA), and multiclass support vector machine (MCSVM). The MCSVM is based on a hybrid kernel, i.e., linear-Gaussian-polynomial (LGP) that combines the advantages of three standard kernels (linear, Gaussian, and polynomial) in a novel manner, where the linear kernel is linearly combined with the Gaussian kernel embedding the polynomial kernel. Further, this paper proves and makes sure that the LGP kernel confirms the features of a valid kernel. In order to reveal the effectiveness of our model, several experiments were conducted and the obtained results compared between our model and other three single kernel-based models, namely, PSO-PCA-L-MCSVM (utilizing a linear kernel), PSO-PCA-G-MCSVM (utilizing a Gaussian kernel), and PSO-PCA-P-MCSVM (utilizing a polynomial kernel). In comparison, two dual and two multiclass imbalanced standard microarray datasets were used. Experimental results in terms of three extended assessment metrics (F-score, G-mean, and Accuracy) reveal the superior global feature extraction, prediction, and learning abilities of this model against three single kernel-based models.

scholarly journals Membrane-Based Electrochemical Sensors for Detecting Internal Corrosion Risk of Natural Gas Pipelines

2021 ◽  
Vol MA2021-01 (56) ◽  
pp. 1461-1461
Author(s):  
Malgorzata Ziomek-Moroz ◽  
Timothy Duffy ◽  
Derek M Hall ◽  
Serguei Lvov
Keyword(s):  
Natural Gas ◽  
Electrochemical Sensors ◽  
Gas Pipelines ◽  
Internal Corrosion ◽  
Natural Gas Pipelines ◽  
Corrosion Risk

Integrity Assessment of Non-Piggable Pipeline Through Direct Assessment

2013 ◽  
Author(s):  
Jai Prakash Sah ◽  
Mohammad Tanweer Akhter
Keyword(s):  
Hydrostatic Pressure ◽  
Natural Gas ◽  
Stress Corrosion ◽  
Health Assessment ◽  
Assessment Method ◽  
Pipeline System ◽  
Internal Corrosion ◽  
Integrity Assessment ◽  
Direct Assessment ◽  
External Corrosion

Managing the integrity of pipeline system is the primary goal of every pipeline operator. To ensure the integrity of pipeline system, its health assessment is very important and critical for ensuring safety of environment, human resources and its assets. In long term, managing pipeline integrity is an investment to asset protection which ultimately results in cost saving. Typically, the health assessment to managing the integrity of pipeline system is a function of operational experience and corporate philosophy. There is no single approach that can provide the best solution for all pipeline system. Only a comprehensive, systematic and integrated integrity management program provides the means to improve the safety of pipeline systems. Such programme provides the information for an operator to effectively allocate resources for appropriate prevention, detection and mitigation activities that will result in improved safety and a reduction in the number of incidents. Presently GAIL (INDIA) LTD. is operating & maintaining approximately 10,000Kms of natural gas/RLNG/LPG pipeline and HVJ Pipeline is the largest pipeline network of India which transports more than 50% of total gas being consumed in this country. HVJ pipeline system consists of more than 4500 Kms of pipeline having diameter range from 04” to 48”, which consist of piggable as well as non-piggable pipeline. Though, lengthwise non-piggable pipeline is very less but their importance cannot be ignored in to the totality because of their critical nature. Typically, pipeline with small length & connected to dispatch terminal are non-piggable and these pipelines are used to feed the gas to the consumer. Today pipeline industries are having three different types of inspection techniques available for inspection of the pipeline. 1. Inline inspection 2. Hydrostatic pressure testing 3. Direct assessment (DA) Inline inspection is possible only for piggable pipeline i.e. pipeline with facilities of pig launching & receiving and hydrostatic pressure testing is not possible for the pipeline under continuous operation. Thus we are left with direct assessment method to assess health of the non-piggable pipelines. Basically, direct assessment is a structured multi-step evaluation method to examine and identify the potential problem areas relating to internal corrosion, external corrosion, and stress corrosion cracking using ICDA (Internal Corrosion Direct Assessment), ECDA (External Corrosion Direct Assessment) and SCCDA (Stress Corrosion Direct Assessment). All the above DA is four steps iterative method & consist of following steps; a. Pre assessment b. Indirect assessment c. Direct assessment d. Post assessment Considering the importance of non-piggable pipeline, integrity assessment of following non piggable pipeline has done through direct assessment method. 1. 30 inch dia pipeline of length 0.6 km and handling 18.4 MMSCMD of natural gas 2. 18 inch dia pipeline of length 3.65 km and handling 4.0 MMSCMD of natural gas 3. 12 inch dia pipeline of length 2.08 km and handling 3.4 MMSCMD of natural gas In addition to ICDA, ECDA & SCCDA, Long Range Ultrasonic Thickness (LRUT-a guided wave technology) has also been carried out to detect the metal loss at excavated locations observed by ICDA & ECDA. Direct assessment survey for above pipelines has been conducted and based on the survey; high consequence areas have been identified. All the high consequence area has been excavated and inspected. No appreciable corrosion and thickness loss have observed at any area. However, pipeline segments have been identified which are most vulnerable and may have corrosion in future.

Integrated Unit Technology for Gas Field Surface Gathering and Transmission

2012 ◽  
Vol 271-272 ◽  
pp. 1328-1345
Author(s):  
Jin Li ◽  
Jian Yang Zhao
Keyword(s):  
Natural Gas ◽  
Power Consumption ◽  
New Technologies ◽  
Ball Valve ◽  
Gas Field ◽  
Pneumatic Control ◽  
Initial Application ◽  
Design Idea

In combination with the author's experiences in design for integrated unit for natural gas field gathering and transmission, this paper describes conventional practices and technical characteristics of integrated unit in the processes of standardization design and modularization establishment and analyzes the initial application of pneumatic control ball valve, wedge-shaped flowmeter and other new technologies for surface facilities in the gas field. As a result, a new design idea is proposed in this paper, i.e., to improve the integration level of surface facilities, to minimize power consumption and maintenance works and to realize unattended work mode.

scholarly journals Light hydrocarbon geochemical characteristics and their application in Upper Paleozoic, Shenmu gas field, Ordos Basin

2016 ◽  
Vol 35 (1) ◽  
pp. 103-121 ◽  
Author(s):  
Wenxue Han ◽  
Shizhen Tao ◽  
Guoyi Hu ◽  
Weijiao Ma ◽  
Dan Liu ◽  
...  
Keyword(s):  
Natural Gas ◽  
Ordos Basin ◽  
Light Hydrocarbon ◽  
Source Rocks ◽  
Higher Plant ◽  
Gas Field ◽  
Gas Source ◽  
Upper Paleozoic ◽  
Methyl Cyclohexane ◽  
Normal Stage

Light hydrocarbon has abundant geochemical information, but there are few studies on it in Shenmu gas field. Taking Upper Paleozoic in Shenmu gas field as an example, authors use gas chromatography technology to study light hydrocarbon systematically. The results show that (1) The Shenmu gas field is mainly coal-derived gas, which is mixed by partial oil-derived gas due to the experiment data. (2) Based on K1, K2 parameter and Halpern star chart, the Upper Paleozoic gas in Shenmu gas field belongs to the same petroleum system and the depositional environment of natural gas source rocks should be homologous. (3) The source rocks are mainly from terrestrial higher plant origins and belong to swamp facies humic due to methyl cyclohexane index and Mango parameter intersection chart, which excluded the possibility of the Upper Paleozoic limestone as source rocks. (4) The isoheptane ranges from 1.45 to 2.69 with an average of 2.32, and n-heptane ranges from 9.48 to 17.68% with an average of 11.71%, which is below 20%. The maturity of Upper Paleozoic gas in Shenmu gas field is low-normal stage, which is consistent with Ro data. (5) The Upper Paleozoic natural gas in the Shenmu gas field did not experience prolonged migration or secondary changes, thus can be analyzed by light hydrocarbon index precisely.

Sign in / Sign up

Export Citation Format

Share Document