Yapay Sinir Ağı Kullanılarak Petrol Sektöründe Yaşanan İş Kazalarının İncelenmesi

Yıl 2024, Cilt: 14 Sayı: 3, 1000 - 1012, 01.09.2024

Önder Künteş Özlem Bezek Güre

https://doi.org/10.21597/jist.1502928

Öz

Türkiye’de her yıl birçok sektörde iş kazası yaşanmaktadır. Petrol sektöründe meydana gelen iş kazalarının değerlendirilmesini amaçlayan bu çalışmada yapay sinir ağları kullanılarak kaza tahminlemesi yapılmıştır. Petrol sektöründe faaliyet gösteren bir şirkette 2020-2023 yıllarında meydana gelmiş olan 2210 adet iş kazası verileri kullanılmıştır. Çalışmada; aylık kaza verileri ile yapay sinir ağı modellemesi yapılmıştır. Çalışmada ileri beslemeli ağlardan olan Çok Katmanlı Algılayıcı yapay sinir ağları (ÇKAYSA) ile Radyal Tabanlı Fonksiyon yapay sinir ağları (RTFYSA) kullanılmıştır. Çalışmada verilerin %70’i eğitim verisi diğerleri ise test verisi olarak kullanılmıştır. Analizler sonucunda; ÇKAYSA yönteminde %84.1 doğru sınıflama oranı, RTFYSA yöntemi ile %86.4 doğru sınıflama oranı elde edilmiştir. RTFYSA yönteminin ÇKAYSA yöntemine göre daha başarılı performans gösterdiği söylenebilir. Yöntemlerin iş kazalarının tahmini amacıyla kullanılması önerilmektedir

Anahtar Kelimeler

iş sağlığı ve güvenliği, iş kazaları, petrol sektörü, veri madenciliği, yapay sinir ağları

Investigation of Work Accidents Occuring in the Oil Industry using Artificial Neural Network

Öz

Occupational accidents occur in many sectors in Türkiye every year. In this study, which aims to evaluate occupational accidents occurring in the oil sector, accident estimation was made using artificial neural networks. Data on 2210 work accidents that occurred between 2020 and 2023 in a company operating in the oil sector were used. In this study; Artificial neural network modeling was done with monthly accident data. In the study, Multilayer Perceptron Artificial Neural Networks (MLPANN) and Radial Basis Function Artificial Neural Networks (RBFANN), which are feed-forward networks, were used. 70% of the data is divided as training data and 30% as test data. As a result of the analysis; An 84.1% correct classification rate was obtained with the MLPANN method, and an 86.4% correct classification rate was obtained with the RBFANN method. It can be said that the RBFANN method performs more successfully than the MLPANN method. lt is suggested to use the methods in order to estimate the occupational accidents .

Anahtar Kelimeler

occupational health and Safety, work accidents, oil industry, data mining, artificial neural networks

Teşekkür

Verileri paylaşan TPİC şirketine teşekkür ederiz.

Kaynakça

• Abdi-Khanghah, M., Bemani, A., Naserzadeh, Z., & Zhang, Z. (2018). Prediction of solubility of N-alkanes in supercritical CO2 using RBF-ANN and MLP-ANN. Journal of CO2 Utilization, 25, 108-119.
• Akbulut, M. C., 2017, Bankacılık ve Sigortacılık Programı Öğrencilerinin İş Sağlığı ve Güvenliğine Yönelik Tutumları: Beypazarı MYO Örneği. Bankacılık ve Sigortacılık Araştırmaları Dergisi, 2(10), 37-48.
• Akın, G. C., Duman, İ., ve Alkan, Ü. (2021). İnşaat sektöründe iş kazalarinin yapay sinir aği ile değerlendirilmesi: İstanbul İlinde Bir Örnek Uygulama. Ergonomi, 4(3), 162-167.
• Altındiş, B. (2023). Amasra taşkömürü işletmesinde iş kazalarının incelenmesi. Yüksek lisans tezi. Afyon Kocatepe Üniversitesi
• Altınel, H. (2013). İş Sağlığı ve İş Güvenliği, 3. Baskı, Ankara: Detay Yayıncılık.
• Ayanoğlu, C. C. ve Kurt, M. (2019). Metal sektöründe veri madenciliği yöntemleri ile bir iş kazasi tahmin modeli önerisi. Ergonomi, 2(2), 78-87.
• Baklacioglu, T. (2021). Predicting the fuel flow rate of commercial aircraft via multilayer perceptron, radial basis function and ANFIS artificial neural networks. The Aeronautical Journal, 125(1285), 453-471.
• Bayraç, H. N., 2009, Küresel Enerji Politikalari Ve Türkiye: Petrol Ve Doğal Gaz Kaynaklari Açisindan Bir Karşilaştirma. Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi, 10(1), 115-142.
• Billings, S.A., Zheng, G.L., 1994. Radial basis function network configuration using genetic algorithms. research report. ACSE Research Report 521.
• Bonini Neto, A., Moreira, A., dos Santos Batista Bonini, C., Campos, M., & Andrighetto, C. (2023). Fuzzy Logic and Artificial Neural Network Perceptron Multi-Layer and Radial Basis in Estimating Marandu Grass Yield in Integrated Systems. Communications in Soil Science and Plant Analysis, 54(21), 2965-2976.
• Cascallar, E., Musso, M., Kyndt, E., & Dochy, F. (2014). Modelling for Understanding AND for Prediction/Classification--The Power of Neural Networks in Research. Frontline Learning Research, 2(5), 67-81.
• Champati, B. B., Padhiari, B. M., Ray, A., Jena, S., Sahoo, A., Mohanty, S., ... & Nayak, S. (2023). Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks for predicting Shatavarin IV content in Asparagus racemosus accessions. Industrial Crops and Products, 191, 115968.
• Colak, M., & Cetin, T. (2017). Analysis of the Occupational Health and Safety at SMES. Research Journal of Business and Management, 4(3), 384-389.
• Delashmit, W. H., & Manry, M. T. (2005, May). Recent developments in multilayer perceptron neural networks. In Proceedings of the seventh annual memphis area engineering and science conference, MAESC (Vol. 7, p. 33).
• Deymi, O., Rezaei, F., Atashrouz, S., Nedeljkovic, D., Mohaddespour, A., & Hemmati-Sarapardeh, A. (2024). On the evaluation of mono-nanofluids’ density using a radial basis function neural network optimized by evolutionary algorithms. Thermal Science and Engineering Progress, 102750.
• Diler, A. İ. (2003). İMKB Ulusal-100 Endeksinin Yönünün Yapay Sinir Ağları Hata Geriye Yayma Yöntemi ile Tahmin Edilmesi. Türkiye’de Bankalar, Sermaye Piyasası ve Ekonomik Büyüme: Koentegrasyon ve Nedensellik Analizi (1989-2000), İMKB Dergisi, 7, 25-26.
• Eker, E., Kayri, M., Ekinci, S., & Izci, D. (2021). A new fusion of ASO with SA algorithm and its applications to MLP training and DC motor speed control. Arabian Journal for Science and Engineering, 46, 3889-3911.
• Eker, E., Kayri, M., Ekinci, S., & İzci, D. (2023). Comparison of swarm-based metaheuristic and gradient descent-based algorithms in artificial neural network training. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 12, e29969-e29969.
• Ergül, B. (2018). Türkiye’deki iş kazalarinin zaman serisi analiz teknikleri ve yapay sinir ağlari tekniği ile incelenmesi. Karaelmas Journal of Occupational Health and Safety, 2(2), 63-74.
• Fath, A. H., Madanifar, F., & Abbasi, M. (2020). Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks to predict solution gas-oil ratio of crude oil systems. Petroleum, 6(1), 80-91.
• Gardner, M. W., Dorling, S. R., 1998. Artificial Neural Networks (The Multilayer Perceptron). A Review of Applications in the Atmospheric Sciences. Atmospheric Environment, 32 (14/15): 2627—2636.
• Goh, A.T.C., 1995. Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 9: 143-151.
• Gullu, A., Yaşar, E., & Özdemir, A. (2021). Türkiye’deki Petrol ve Doğalgaz Sondaj Kuyularının Optimizasyonu. European Journal of Science and Technology, 27, 398-406.
• Güre, Ö. B., Kayri, M., & Erdoğan, F. (2019) Predicting Factors Affecting PISA 2015 Mathematics Literacy via Radial Based Artificial Neural Network. Journal of Engineering and Technology, 3(1), 1-11.
• Güre, Ö. B., Kayri, M., & Erdoğan, F. (2020). PISA 2015 matematik okuryazarlığını etkileyen faktörlerin eğitsel veri madenciliği ile çözümlenmesi. Eğitim ve Bilim, 45(202).
• Hagan, M.T.; Menhaj, M.B. Training Feed Forward Networks with the Marquardt Algorithm. IEEE Trans. NeuralNetw. 1994, 5, 989–993.
• Haykin, S. S. (2009). Neural Networks and Learning Machines (Vol. 3). Upper SaddleRiver, NJ, USA: Pearson. Hwang, Y. S., & Bang, S. Y. (1997). An efficient method to construct a radial basis function neural network classifier. Neural networks, 10(8), 1495-1503.
• Kayri, M. (2016). Predictive abilities of Bayesian regularization and Levenberg–Marquardt algorithms in artificial neural networks: a comparative empirical study on social data. Mathematical and Computational Applications, 21(2), 20.
• Kayri, M., 2015. An intelligent approach to educational data: performance comparison of the multilayer perceptron and the radial basis function artificial neural networks. Educational Sciences: Theory & Practice, 15 (5): 1247-1255.
• Köroğlu, F.B.(2023). Application Of Artificial Neural Networks to Structural Reliability Problems.İzmir Teknoloji Üniversitesi. Yüksek lisans tezi
• Kunduracioglu, I., & Pacal, I. (2024). Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases. Journal of Plant Diseases and Protection, 131(3), 1061-1080.
• Mahmoud, M. M. (2021). Comparison Between Tailor-Made-ANN Techniques and Fuzzy c-Mean Clustering Technique in Industrial Laborers' Accident-Rates Prediction Modelling Based on Human Factors.
• Nayak, N. R., Kumar, S., Gupta, D., Suri, A., Naved, M., & Soni, M. (2022). Network mining techniques to analyze the risk of the occupational accident via bayesian network. International Journal of System Assurance Engineering and Management, 13(Suppl 1), 633-641.
• Negnevitsky, M., 2005. Artificial Intelligence A Guide to Intelligent Systems Second Edition. Addison-Wesley Oğan, H., 2014, Sağlık çalışanları için işçi sağlığı ve güvenliği, Türk Tabipleri Birliği Yayınları, Ankara.
• Öztemel, E. (2003). Yapay Sinir Ağları. Papatya Yayıncılık, İstanbul.
• Özüpak, Y., & Aslan, E. (2024). Usıng artificial neural networks to improve the efficiency of transformers used in wireless power transmission systems for different coil positions. Revue Roumaine Des Sciences Techniques—Sérıe Électrotechnıque Et Énergétıque, 69(2), 195-200.
• Paçal, İ., & Kunduracıoğlu, İ. (2024). Data-Efficient Vision Transformer Models for Robust Classification of Sugarcane. Journal of Soft Computing and Decision Analytics, 2(1), 258-271.
• Pacal, I., Alaftekin, M., & Zengul, F. D. (2024). Enhancing Skin Cancer Diagnosis Using Swin Transformer with Hybrid Shifted Window-Based Multi-head Self-attention and SwiGLU-Based MLP. Journal of Imaging Informatics in Medicine, 1-19.
• Raitoharju, J., Kiranyaz, S., & Gabbouj, M. (2015). Training radial basis function neural networks for classification via class-specific clustering. IEEE transactions on neural networks and learning systems, 27(12), 2458-2471.
• Ramana, V. V., & Shanmugam, D. (2024). Different meta-heuristic optimized radial basis function neural network models for short-term power consumption forecasting. Advances in Engineering and Intelligence Systems, 3(02), 63-82.
• Rosenblatt, F. (1960). Perceptron simulation experiments. Proceedings of the IRE, 48(3), 301-309.
• Sabet, M. F. A., Dahroug, A., & Hegazy, A. F. (2021, December). A Proposed model for field workers Injuries’ prevention based on machine learning. In 2021 Tenth International Conference on Intelligent Computing and Information Systems (ICICIS) (pp. 383-388). IEEE.
• Sadeghi, G., Pisello, A. L., Nazari, S., Jowzi, M., & Shama, F. (2021). Empirical data-driven multi-layer perceptron and radial basis function techniques in predicting the performance of nanofluid-based modified tubular solar collectors. Journal of Cleaner Production, 295, 126409.
• Sahmutoglu, I., Temizçeri, F. T., & Bozkus, E. (2021). Evaluation of occupational accidents with artificial neural networks in occupational health and safety management systems. https://www.researchgate.net/profile/Emine-Bozkus-2/publication/357285118_evaluation_of_occupational_accidents_with_artificial_neural_networks_in_occupational_health_and_safety_management_systems/links/61c4ca320ae6751c882f2371/evaluation-of-occupational-accidents-with-artificial-neural-networks-in-occupational-health-and-safety-management-systems.pdf
• Saini, L. M. (2008). Peak Load Forecasting using Bayesian Regularization, Resilient and Adaptive Backpropagation Learning based Artificial Neural Networks. Electric Power Systems Research, 78(7), 1302-1310.
• Şen, H., Efe, Ö. F., & Efe, B. (2023). Estimatıon of occupational accidents in Turkey until 2030. Natural Resources and Technology, 17(1), 26-32.
• Seyman M N., Taşpınar N., 2009. Çok katmanlı yapay sinir ağları kullanarak ofdm sistemlerinde kanal dengeleme. 5.Uluslararası İleri Teknolojiler Sempozyumu (IATS’09). 13–15 Mayıs 2009, Karabük, Türkiye.
• Somers, M. J., & Casal, J. C. (2009). Using artificial neural networks to model nonlinearity: The case of the job satisfaction—job performance relationship. Organizational Research Methods, 12(3), 403-417.
• Stripling, E., Baesens, B., Chizi, B., & vanden Broucke, S. (2018). Isolation-based conditional anomaly detection on mixed-attribute data to uncover workers' compensation fraud. Decision Support Systems, 111, 13-26.
• Tokdemir, O. B. ve Ayhan, B. U., 2019, Keskin bir cisim ile temas sonucu yaralanma kazalarının analitik hiyerarşi prosesi ve yapay sinir ağları ile analizi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 10(1), 323-334.
• Türker, M., & Kanıt, R. (2020). Yapı üretim sürecindeki iş kazaları şiddetinin ön bilgilendirilmiş yapay öğrenme metodu ile tahmini. Konya Journal of Engineering Sciences, 8(4), 943-956.
• Yan, Z., Zhu, X., Wang, X., Ye, Z., Guo, F., Xie, L., & Zhang, G. (2023). A multi-energy load prediction of a building using the multi-layer perceptron neural network method with different optimization algorithms. Energy Exploration & Exploitation, 41(1), 273-305.
• Yu, X., Efe, M. O., & Kaynak, O. (2002). A General Backpropagation Algorithm for Feedforward Neural Networks Learning. IEEE Transactions on Neural Networks, 13(1), 251-254.
• Zanchettin, C., Ludermir, T. B., & Almeida, L. M. (2011). Hybrid training method for MLP: optimization of architecture and training. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 41(4), 1097-1109.
• Zhang, G. P. (2010). Neural networks for data mining. Data mining and knowledge discovery handbook. In Maimon and Rokach (Ed.) (pp. 419-444).