Artificial Neural Network and a Nonlinear Regression Model for Predicting Electrical Pole Crash


  • Cecilia Montt Pontificia Universidad Católica de Valparaiso
  • Juan Carlos Castro
  • Alejandra Valencia
  • Astrid Oddershede
  • Luis Quezada


artificial neural networks (ANN), Artificial neural networks, prediction,, prediction, nonlinear regression


This paper presents the investigation about a problem situation that Electric Distributor Companies are facing in Chile resulting from transit accidents. The number of vehicle crashes to power distribution poles and street lighting has grown. This situation causes discomfort to citizen and mainly to the neighbors due to power cuts and even on occasion , losses of human lives because of the accident that have occurred. Based on previous research, the accidents are not random nor chance dependent, but the majority of transit accident follow parameters or variables from the scenery where it occurs. In order to analyze the variables and the degree this variables affect the accidents, a model of Perceptron and Multipercetron Artificial Neural Networks and a Multiple Nonlinear Regression model are proposed. An empirical study was made; collecting data from a distributor company and from Chilean National Traffic Safety Commission, where the more frequent variables involved in accidents were determined to develop the mentioned models. These variables were investigated and also their influence on the occurrence of vehicle crashes to power distribution poles could be confirmed. With this data, the prediction of post crashes was developed, where through the application of the neural network and multiple nonlinear regression, revealed 95.7% of acceptable predictions. This study will bring benefits to power distribution companies considering a risk index in the streets, based on the number of crashes of poles per street; this will allow optimal decisions in future electrical distribution projects avoiding critical areas.

Author Biographies

Cecilia Montt, Pontificia Universidad Católica de Valparaiso

Ingenieria de Transporte, Reasearh

Juan Carlos Castro

Department of Electrical Engineering,
Pontificia Universidad Católica de Valparaí­so,
2340000 Valparaiso, Chile

Alejandra Valencia

Department of Transport Engineering,
Pontificia Universidad Católica de Valparaí­so,
2340000 Valparaiso, Chile

Astrid Oddershede

Department of Industrial Engineering,
Universidad de Santiago de Chile,
8320000 Santiago, Chile

Luis Quezada

Department of Industrial Engineering,
Universidad de Santiago de Chile,
8320000 Santiago, Chile


J.W.H. (Jan Hendrik) van Petegem Fred Wegman Analyzing road design risk factors for run-off-road crashes in the Netherlands with crash prediction models ; JouANNl of Safety Research pagh (121-127), (2014)

Gagne A. Evaluation of Utility Pole Placement and the Impact on Crash Rates, Proyecto de Tesis, Facultad de Ciencias, Worcester Polytechnic Institute. (2008)

Basogain X., Artificial Neural Networks and their applications. Higher School of Engineering of Bilbao, Department of systems and automatic engineering,EHU. (2008)

Rojas M. Traffic Accident Prediction Using Artificial Neural Networks and Cuckoo Search, Thesis Project, Faculty of Computer Engineering, Pontifical Catholic University of Valparaíso. (2015)

M.C. Good, J.C. Fox y P.N. Joubert, Depth Study of Accidents Related to Post Crash departament of Industrial and Mechanical Engineering, University of Melbourne. (1986)

Matlab (2018) Mathworks,. Available: last accessed (2018)

Olden, J.D., Joy, M.K., R.D., (2004) An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data, Ecological Modelling, Vol 178, issues 3-4 , pag. 389-397. (2004)

Montt, C., Rodriguez, N. y Valencia, A. Traffic accident prediction in the metropolitan region of Chile based on neural networks, Concepción, Proceedings of the XVII Chilean Congress of Transportation Enginee, Concepción, Chile. (2015)

Additional Files



Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.