Thermographic Non-Invasive Inspection Modelling of Fertilizer Pipelines Using Neural Networks

Industry pipeline fault, like blockage can create major problems for engineers and financial loss for the company. The blockage detection is necessary for smooth functioning of an industry and safety of the environment. This work presents a model for non-invasive inspection of pipes. It proposes the use of a neural network to identify the obstruction stage in fertilizer industry, using external thermal images obtained from the pipelines. A dataset capable of mapping the external thermal behavior in profile of the internal deposit is developed. The Multilayer Perceptron neural network was able to learn the thermal pixel mapping in a deposit profile, obtaining satisfactory results.