Neural networks can enhance fuzzy corrosion modeling

Corrosion in the petroleum industry is one the major concerns of the managers and engineers. Both upstream and downstream industries face this problem and the companies spendbillions of dollars in this case. To remain competitive with the world market and win the game, this cost must be kept to a minimum and here the demands for a reliablecorrosion prediction model that can be used in decision making, do exist. On the other hand in manyengineering problems the available information is vague and sometimes measured data or export knowledge is too imprecise to justify the usenumbers. Fuzzy logic is a good solution here and helps us to compute with words. But the problem is that you can not train the fuzzy systems so neural networks may be useful here to add learning capability to fuzzy systems. This paper proposes a new approach to model and predict the corrosion in pipes with hybrid neurofuzzy approach. With pressure, temperature, oil and gas production rate, 2 CO and 2 H S content of the flow as the model inputs and the corrosion rate as the output, 3-D surfaces for the corrosion have been obtained and the accuracy of the model was studied against the field data. These graphs can be used as a powerful tool in corrosion prediction by managers and engineers

کلیدواژه ها:

Corrosion ، oil and gas ، fuzzy logic ، neural networks