The Pacific Journal of Science and Technology –98– http://www.akamaiuniversity.us/PJST.htm Volume 14. Number 1. May 2013 (Spring) An Investigation into the Use of Artificial Neural Network to Monitor and Detect Leakage Point(s) along a select Pipeline. P.A. Adewuyi, B.Tech. 1 * and M.O. Okelola, M.Sc. 2 1 Department of Mechatronics Engineering, Bells University of Technology, Ota, Nigeria. 2 Department of Electronic and Electrical Engineering, Ladoke Akintola University, Ogbomoso, Nigeria. *E-mail: solaadewuyi@gmail.com ABSTRACT The problem of incessant leakages in oil pipeline from intentional or natural accident with its untold results of pollution, loss of lives from fire outbreak, and reduction in production output, spurred the burning desire to proffer a novel solution with the use of artificial neural network as a tool to detect oil leakage, pin-point the leakage spot and provide useful communication link with the supervisory control and data acquisition (SCADA). The data used for this work was obtained from Atlas Cove, Lagos, Nigeria under the NNPC- PPMC Mosinmi Area Depots. Pressure of oil flowing in pipelines between Atlas Cove Depot, Lagos and Mosinmi Area Depot in Ogun state, Nigeria were used for the training of artificial neural network. The data was randomly picked and divided into training data (50 constants), validation data (50 constants), and testing data (50 constants) as contained in the neural network training algorithm. The best network architecture that is, a four layer neural network (20-20-15-10) obtained from trials for this model was used. The use of graphical user interface, a tool in MATLAB ® , makes the analysis easy and interactive. Artificial neural network (ANN) approach to solving this identified oil leakage problem gives satisfactory results as the error between the ANN output and the target is very tolerable being 0.000566069 with a goal of 0.01. This could be implemented physically as an artificial intelligence unit in the monitoring of oil pipeline networks. (Keywords: pipeline leaks, pipeline right of way, oil flow pressure, artificial neural network, pipeline model) INTRODUCTION The most popular way of transporting petroleum products is by the use of pipelines. The use of pipelines eases the movement of petroleum products from one location to the other. The distances covered by these pipelines are in thousands of miles passing through cities and villages. Some pipelines are laid overhead when passing through frost prone areas. There is no denying the fact that pipelines have become indispensable occupants of especially dedicated land areas in Nigeria. However, as beneficial as petroleum products are to us as man, damages often occur to pipeline networks as a result of factors ranging from lack of proper maintenance of the network, ageing of the pipeline networks, pipeline vandalization, and accidents. Once there is any damage to the pipeline(s) by any form, leakages often occur which usually cause harm to both humans, animals, and the environment. In October 17, 1998 – a pipeline explosion occurred at Jesse in the Niger Delta region of Nigeria, killing about 1,200 villagers, some of whom were scavenging gasoline, so far the worst in the history of pipeline vandalization in Nigeria [1]. In May 12, 2006 – an oil pipeline vandalization or rupture occurred outside Lagos, Nigeria killing around 200 people. Year 2000 is the worst hit where three different pipelines vandalization led to explosion that killed hundreds of people [7]. Ijegun pipeline explosion occurred in May 16, 2008. The loss of human lives, damages to the natural habitat of plants and animals due to pollution, developing a cheap model for pipeline monitoring, and inability of relevant authorities to respond fast