Neural Network Modeling for Monitoring Petroleum Pipelines

It is common occurrence that the transportation of petroleum products via pipelines is susceptible to failure either naturally or intentionally. A diagnostic problem having continuous inputs of pattern recognition used in predicting pipeline failures is analysed. Our problem is to design a neural network that will recognize failure events in pipelines when fed with an input pattern denoting such a scenario. A neural network paradigm is selected, and encoding of input is done to obtain the input pattern. The selected model is simulated and trained to recognize the output pattern, which in our scenario after training, goes into operational mode. The neural network is fully implemented on a Pentium II MMX computer with a Borland C++ builder.