Deep Neural Network Anomaly Detection and Statistical Estimation of High Pressure Liquefied Natural Gas Pipe

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Sep 4, 2023
Dabin Yang Jongsoo Lee

Abstract

Anomaly detection method using neural network is performed for diagnosis. Liquefied natural gas pipeline is designed using finite element method. To consider abnormal condition, a damage was applied to the model. Then failure mode and effect analysis are performed to determine if the location of damage is acceptable. The designed system was validated through literatures and showed that the model is suitable to replace the actual model. Data collection was done by changing each design variables in certain range from the designed model. Designable generative adversarial network was used for data augmentation and anomaly detection with adversarial network was used for anomaly detection. The performance of anomaly detection of the proposed model showed 95% of accuracy before data augmentation and 99% of accuracy after data augmentation. The result provides statistical estimation of diagnosis range for each design variables, which clearly showed the difference of performing data augmentation. By diagnosis result, the variables are used back to the designed model for validation of the result and showed accuracy of 85%.  

Abstract 103 | PDF Downloads 148

##plugins.themes.bootstrap3.article.details##

Keywords

Liquefied Natural Gas Pipeline, Failure Mode and Effect Analysis, Anomaly Detection-Designable Generative Adversarial Network, Statistical Estimation

References
Aljameel, S. S., Alomari, D. M., Alismail, S., Khawaher, F., Alkhudhair, A. A., Aljubran, F., & Alzannan R. M., (2022). An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning. Computation, 10(8), pp. 138. doi: 10.3390/computation10080138.

Animah, I., & Shafiee, M., (2020). Application of risk analysis in the liquefied natural gas (LNG) sector: An overview. Journal of Loss Prevention in the Process Industries, 63. doi: 10.1016/j.jlp.2019.103980.

Jeong, W., Park, G., Koo, Y., Yoo, S., & Jo, Y., (2018). City Gas Pipeline Pressure Prediction Model. The Journal of Society for e-Business Studies, 23(2), pp. 33-47. doi: 10.7838/jsebs.2018.23.2.033.

Jo, C., Kim, M., Jo, S., & Hwang. S., (2015). A Study on Internal Flow Characteristics of T Branch using CFD Analysis. The Korean Hydrogen and New Energy Society, 26(5), pp. 438-444. doi: 10.7316/KHNES.2015.26.5.438.

Shin, K., Yoon, K., & Kim, Y., (2006). Reference Stress Based Stress Analysis for Local Creep Rupture of a T- pipe. Transactions of the Korean Society of Mechanical Engineers A, 30(8), pp. 873-879. doi: 10.3795/KSME- A.2006.30.8.873.

Sierra, E. F. Z., Bates, C. J., & Doherty, T. O., (2000). Turbulent flow in a 90° pipe junction: Part 2: Reverse flow at the branch exit. Computers and Fluids. 29(2), pp. 215-230. doi: 10.1016/S0045-7930(99)00005-5.

Yoo, Y., Jung, U., Han, J., & Lee, J., (2021). Data Augmentation-Based Prediction of System Level Performance under Model and Parameter Uncertainties: Role of Designable Generative Adversarial Networks (DGAN). Reliability Engineering and System Safety, 206. doi: 10.1016/j.ress.2020.107316.

Yuhui, Z., Shiyu, L., Lijing, Z., & et al., (2018). Natural Gas Pipeline Network Risk Assessment Based on FMECA- Fuzzy Comprehensive Analysis. IEEE International Conference of Safety Produce Informatization (IICSPI). Dec 10-12, Chongqing, China. doi: 10.1109/IICSPI.2018.8690464.
Section
Special Session Papers