YAPI ÜRETİM SÜRECİNDEKİ İŞ KAZALARI ŞİDDETİNİN ÖN BİLGİLENDİRİLMİŞ YAPAY ÖĞRENME METODU İLE TAHMİNİ

Year 2020, Volume: 8 Issue: 4, 943 - 956, 01.12.2020

Mustafa Türker , Recep Kanıt

https://doi.org/10.36306/konjes.764952

Cited By: 2

Abstract

Bu çalışmada, yapı üretim sürecinde meydana gelen iş kazalarında, kaza şiddeti ile kaza önlemleri arasındaki ilişki araştırılmıştır. Bunun için geçmiş kaza verileri kullanılarak, ilerideki iş kazalarında hangi önlemlerin alınması gerektiği ve bu önlemlerin alınmaması halinde kaza sonucunun ne olabileceğini tahmin edebilen bütünleşmiş bir model geliştirilmiştir. Bu tahmin modeli, günümüzde araştırmacıların sıklıkla kullandığı AHP (Analitik Hiyerarşi Prosesi) ve YSA (Yapay Sinir Ağları) metotlarının zayıf kaldıkları noktada birbirlerini tamamlaması amacıyla, birbirine entegre edilerek oluşturulmuştur.
Modelin anlamlılığı bir saha çalışması yapılarak gerçek veriler ile test edilmiştir. Örneklem için en çok ölümle sonuçlanan 4 (dört) tür iş kazası seçilmiş ve bu iş kazaları için, aynı kurumda, 35 (otuz beş) geçmiş kaza verileri toplanmıştır. YSA metodu giriş katmanını önceden anlamlandıran AHP metodu için ikili kıyaslama verileri, profesyonel bir anket firması tarafından sektörde görev yapan İSG (İş sağlığı ve güvenliği) uzmanlarından, anket yöntemi ile elde edilmiştir. Elde edilen bu verilerden 120 adedi ağların eğitilmesinde, 20 adedi de test edilmesinde kullanılmıştır. Sonuçta risk azaltıcı önlemler ile kaza şiddeti arasında ilişkinin, toplanan kaza verileriyle sınırlı olmak kaydıyla, %90 oranında anlamlı olduğu görülmüştür.

Keywords

iş kazaları, yapay sinir ağları, Tahmin Modeli, İnşaat Sektörü, PIAIM

Estimation of the Severity of Occupational Accidents in the Building Process with Pre-Informed Artificial Learning Method

Abstract

In this study, the relationship between accident severity and accident measures in the occupational accidents that occurred during the building process was investigated. By using past accident data, an integrated model has been developed which can predict what measures should be taken in future occupational accidents and what the outcome of the accident would be if these measures are not taken.
This estimation model was developed by integrating the AHP (Analytical Hierarchy Process) and ANN (Artificial Neural Networks) methods, which are frequently used by researchers, to complement each other at the point where they are weak. The significance of the model was tested with real data by conducting a field study. For the sample, 4 (four) types of occupational accidents that caused the most deaths were selected, and 35 (thirty-five) past accident data were collected for each of these occupational accident types. For AHP method, which weighting the input layer of the ANN method, the binary comparison data was obtained through the survey method from the OHS (Occupational Health and Safety) experts working in the sector by a professional survey firm. From the data obtained, 120 data were used to train network, 20 data were used to test it. As a result, the relationship between risk reducing measures and accident severity was found to be 90% significant, provided that it is limited to the accident data collected.

Keywords

Occupational Accidents, Artificial Neural Networks, Prediction Model, Construction Sector, PIAIM

References

• Alizadeh, S. S., Mortazavi, S. B. ve Mehdi Sepehri, M. (2015). Assessment of accident severity in the construction industry using the bayesian theorem. International Journal of Occupational Safety and Ergonomics, 21(4), 551-557.
• Aminbakhsh, S., Gunduz, M. ve Sonmez, R. (2013). Safety risk assessment using analytic hierarchy process (ahp) during planning and budgeting of construction projects. Journal of Safety Research, 46, 99-105.
• Chen, F., Wang, H., Xu, G., Ji, H., Ding, S. ve Wei, Y. (2020). Data-driven safety enhancing strategies for risk networks in construction engineering. Reliability Engineering & System Safety, 197.
• Clarivate Analytics. (2020). Web of science [v.5.35] - web of science core collection. Erişim Tarihi: 14.06.2020, Adres: https://www.webofknowledge.com/
• Cox, S. ve Flin, R. (1998). Safety culture: Philosopher's stone or man of straw? Work & Stress, 12(3), 189- 201.
• Gomathi, K. ve Shanmuga Priyaa, D. (2017). A fuzzy analytic hierarchy attribute weighting and deep learning for improving chd prediction of optimized semi parametric extended dynamic bayesian network. 2017, 7(1.1), 8.
• Gurcanli, G. E., Bilir, S. ve Sevim, M. (2015). Activity based risk assessment and safety cost estimation for residential building construction projects. Safety Science, 80, 1-12.
• Gurcanli, G. E. ve Mungen, U. (2013). Analysis of construction accidents in turkey and responsible parties. Industrial Health, 51(6), 581-595.
• Hamid, A. R. A., Noor Azmi, M. R. A., Aminudin, E., Jaya, R. P., Zakaria, R., Zawawi, A. M. M., . . . Saar, C. C. (2019). Causes of fatal construction accidents in malaysia. IOP Conference Series: Earth and Environmental Science, 220, 012044.
• Ilbahar, E., Karasan, A., Cebi, S. ve Kahraman, C. (2018). A novel approach to risk assessment for occupational health and safety using pythagorean fuzzy ahp & fuzzy inference system. Safety Science, 103, 124-136.
• Karadal, H., Merdan, E. ve Abubakar, M. (2019). Güvenlik İklimi ve güvenlik kültürünün İşyeri yaralanmaları üzerine etkisinde güvenlik davranışlarının aracılık rolü: Döküm sanayinde bir araştırma. Anemon Muş Alparslan Üniversitesi Sosyal Bilimler Dergisi, 7(6), 329-339.
• Lasdon, L. S., Fox, R. L. ve Ratner, M. W. (1974). Nonlinear optimization using the generalized reduced gradient method. Revue française d'automatique, informatique, recherche opérationnelle. Recherche opérationnelle, 8(V3), 73-103.
• Li, W.-G., Yu, Q. ve Luo, R.-C. (2012). Application of fuzzy analytic hierarchy process and neural network in power transformer risk assessment. Journal of Central South University, 19(4), 982-987.
• Meng, W.-L., Shen, S. ve Zhou, A. (2018). Investigation on fatal accidents in chinese construction industry between 2004 and 2016. Natural Hazards, 94(2), 655-670.
• Mohammadfam, I., Soltanzadeh, A., Moghimbeigi, A. ve Savareh, B. A. (2015). Use of artificial neural networks (anns) for the analysis and modeling of factors that affect occupational injuries in large construction industries. Electronic physician, 7(7), 1515-1522.
• Öztemel, E. (2006). Yapay sinir ağları. İstanbul: Papatya Yayıncılık.
• Pinto, A., Ribeiro, R. A. ve Nunes, I. L. (2012). Fuzzy approach for reducing subjectivity in estimating occupational accident severity. Accid Anal Prev, 45, 281-290.
• Saaty, T. L. (1980). The analytic hierarchy process : Planning, priority setting, resource allocation. New York; London: McGraw-Hill International Book Co.
• Shafique, M. ve Rafiq, M. (2019). An overview of construction occupational accidents in hong kong: A recent trend and future perspectives. Applied Sciences, 9(10).
• Sosyal Guvenlik Kurumu. (2018). Sgk İstatistik yıllıkları. Erişim Tarihi: 14.06.2020, Adres: http://www.sgk.gov.tr/wps/portal/sgk/tr/kurumsal/istatistik/sgk_istatistik_yilliklari
• Winge, S. ve Albrechtsen, E. (2018). Accident types and barrier failures in the construction industry. Safety Science, 105, 158-166.
• Winge, S., Albrechtsen, E. ve Mostue, B. A. (2019). Causal factors and connections in construction accidents. Safety Science, 112, 130-141.
• Yilmaz, M. ve Kanıt, R. (2018). A practical tool for estimating compulsory ohs costs of residential building construction projects inTurkey. Safety Science, 101, 326-331.
• Zohar, D. (1980). Safety climate in industrial organizations: Theoretical and applied implications. Journal of Applied Psychology, 65(1), 96-102.