Mô Hình Phát Hiện Anomaly Cho Các Đường Ống Dầu Và Khí Sử Dụng Machine Learning

Computation - Tập 10 Số 8 - Trang 138
Sumayh S. Aljameel1, Dorieh M. Alomari2, Shatha Alismail2, Fatimah Khawaher2, Aljawharah A. Alkhudhair2, Fatimah Aljubran2, Razan Alzannan2
1Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia
2Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia

Tóm tắt

Việc phát hiện các rò rỉ nhỏ trong các đường ống dẫn dầu hoặc khí là một vấn đề quan trọng và dai dẳng trong ngành công nghiệp dầu khí. Nhiều tổ chức đã lâu dựa vào phần cứng cố định hoặc các đánh giá thủ công để theo dõi rò rỉ. Với sự công nghiệp hóa nhanh chóng và những tiến bộ công nghệ, các công nghệ kỹ thuật đổi mới, hiệu quả về chi phí, nhanh hơn và dễ dàng triển khai là điều cần thiết. Trong bài viết này, các mô hình phát hiện anomaly dựa trên machine learning được đề xuất để giải quyết vấn đề rò rỉ trong các đường ống dẫn dầu và khí. Năm thuật toán machine learning, cụ thể là, random forest, support vector machine, k-nearest neighbour, gradient boosting, và decision tree, đã được sử dụng để phát triển các mô hình phát hiện rò rỉ trong đường ống. Thuật toán support vector machine, với độ chính xác đạt 97.4%, đã vượt trội hơn các thuật toán khác trong việc phát hiện rò rỉ đường ống và do đó chứng minh hiệu quả của nó như một mô hình chính xác để phát hiện rò rỉ trong các đường ống dẫn dầu và khí.

Từ khóa


Tài liệu tham khảo

Nooralishahi, P., López, F., and Maldague, X. (2021). A Drone-Enabled Approach for Gas Leak Detection Using Optical Flow Analysis. Appl. Sci., 11.

Meribout, 2020, Leak detection systems in oil and gas fields: Present trends and future prospects, Flow Meas. Instrum., 75, 101772, 10.1016/j.flowmeasinst.2020.101772

(2022, June 03). What Is Artificial Intelligence (AI)? Oracle Saudi Arabia. Available online: https://www.oracle.com/sa/artificial-intelligence/what-is-ai/.

Wang, 2021, (INVITED)Oil and Gas Pipeline Leakage Recognition Based on Distributed Vibration and Temperature Information Fusion, Results Opt., 5, 100131, 10.1016/j.rio.2021.100131

Xiao, 2019, Leak detection of gas pipelines using acoustic signals based on wavelet transform and Support Vector Machine, Measurement, 146, 479, 10.1016/j.measurement.2019.06.050

(2022, March 30). A Convolutional Neural Network Based Solution for Pipeline Leak Detection (PDF). Available online: https://www.researchgate.net/publication/337060339_A_Convolutional_Neural_Network_Based_Solution_for_Pipeline_Leak_Detection.

De Kerf, T., Gladines, J., Sels, S., and Vanlanduit, S. (2020). Oil Spill Detection Using Machine Learning and Infrared Images. Remote Sens., 12.

(2022, March 30). IEEE Xplore Full-Text PDF. Available online: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9226415.

Lu, 2020, Feature extraction based on variational mode decomposition and support vector machine for natural gas pipeline leakage, Trans. Inst. Meas. Control, 42, 759, 10.1177/0142331219874161

Melo, 2020, Applying convolutional neural networks to detect natural gas leaks in wellhead images, IEEE Access, 8, 191775, 10.1109/ACCESS.2020.3031683

(2021, November 21). Abimbola-Ai/Oil-and-Gas-Pipeline-Leakage. Available online: https://github.com/Abimbola-ai/Oil-and-gas-pipeline-leakage.

Kotsiantis, 2011, Data preprocessing for supervised leaning, Int. J., 60, 143

(2022, March 02). Binarize Label Hivemall User Manual. Available online: https://hivemall.apache.org/userguide/ft_engineering/binarize.html.

(2021, November 21). Machine Learning: When to Perform a Feature Scaling—Atoti. Available online: https://www.atoti.io/when-to-perform-a-feature-scaling/.

(2021, November 21). Feature Scaling Standardization vs. Normalization. Available online: https://www.analyticsvidhya.com/blog/2020/04/feature-scaling-machine-learning-normalization-standardization/.

(2021, November 19). Splitting a Dataset. Here I Explain How to Split Your Data… by Nischal Madiraju towards Data Science. Available online: https://towardsdatascience.com/splitting-a-dataset-e328dab2760a.

(2021, November 19). Train-Test Split for Evaluating Machine Learning Algorithms. Available online: https://machinelearningmastery.com/train-test-split-for-evaluating-machine-learning-algorithms/.

(2021, November 19). OpenML. Available online: https://www.openml.org/a/estimation-procedures/1.

Jakkula, V. (2022, July 01). Tutorial on Support Vector Machine (SVM). Available online: https://course.ccs.neu.edu/cs5100f11/resources/jakkula.pdf.

(2021, November 23). Support Vector Machine—Introduction to Machine Learning Algorithms by Rohith Gandhi Towards Data Science. Available online: https://towardsdatascience.com/support-vector-machine-introduction-to-machine-learning-algorithms-934a444fca47.

Negoita, M., and Reusch, B. (2005). Real World Applications of Computational Intelligence, Springer.

(2021, November 22). A Quick Introduction to Neural Networks—The Data Science Blog. Available online: https://ujjwalkarn.me/2016/08/09/quick-intro-neural-networks/.

(2022, March 02). Decision Tree Algorithm, Explained—KDnuggets. Available online: https://www.kdnuggets.com/2020/01/decision-tree-algorithm-explained.html.

So, A., Hooshyar, D., Park, K.W., and Lim, H.S. (2017). Early Diagnosis of Dementia from Clinical Data by Machine Learning Techniques. Appl. Sci., 7.

(2022, April 11). Visualization of a Random Forest Model Making a Prediction Download Scientific Diagram. Available online: https://www.researchgate.net/figure/21-Visualization-of-a-random-forest-model-making-a-prediction_fig20_341794164.

(2021, November 21). Understanding Random Forest. How the Algorithm Works and Why It Is… by Tony Yiu towards Data Science. Available online: https://towardsdatascience.com/understanding-random-forest-58381e0602d2.

(2021, November 21). Random Forest—Wikipedia. Available online: https://en.wikipedia.org/wiki/Random_forest.

(2021, November 21). Random Forest Algorithms: A Complete Guide Built in. Available online: https://builtin.com/data-science/random-forest-algorithm.

(2022, March 02). K-Nearest Neighbor Algorithm in Java GridDB: Open Source Time Series Database for IoT by Israel Imru GridDB Medium. Available online: https://medium.com/griddb/k-nearest-neighbor-algorithm-in-java-griddb-open-source-time-series-database-for-iot-6bf934eb8c05.

(2022, March 02). K-Nearest Neighbor (KNN) Algorithm for Machine Learning—Javatpoint. Available online: https://www.javatpoint.com/k-nearest-neighbor-algorithm-for-machine-learning.

(2022, March 02). A Beginner’s Guide to Supervised Machine Learning Algorithms by Soner Yıldırım Towards Data Science. Available online: https://towardsdatascience.com/a-beginners-guide-to-supervised-machine-learning-algorithms-6e7cd9f177d5.

(2022, March 02). Hyperparameter Tuning for Machine Learning Models. Available online: https://www.jeremyjordan.me/hyperparameter-tuning/.

(2022, March 02). An Introduction to Grid Search CV What Is Grid Search. Available online: https://www.mygreatlearning.com/blog/gridsearchcv/.

(2021, November 19). Performance Metrics in Machine Learning [Complete Guide]—Neptune.ai. Available online: https://neptune.ai/blog/performance-metrics-in-machine-learning-complete-guide.

(2021, November 20). Understanding Confusion Matrix by Sarang Narkhede towards Data Science. Available online: https://towardsdatascience.com/understanding-confusion-matrix-a9ad42dcfd62.

(2022, May 11). Confusion Matrix: Let’s Clear This Confusion by Aatish Kayyath Medium. Available online: https://medium.com/@aatish_kayyath/confusion-matrix-lets-clear-this-confusion-4b0bc5a5983c.

(2021, November 19). Performance Metrics for Classification Problems in Machine Learning by Mohammed Sunasra Medium. Available online: https://medium.com/@MohammedS/performance-metrics-for-classification-problems-in-machine-learning-part-i-b085d432082b.

(2022, February 28). Classification: ROC Curve and AUC Machine Learning Crash Course Google Developers. Available online: https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc.

Thông tin
Thông tin xuất bản

Computation

Tập 10 Số 8

138

Thông tin tác giả