A neural network developed in a Foundation Fieldbus environment to calculate flow rates for compressible fluid

Abstract This paper proposes the development of an artificial neural network multilayer perceptron, implemented in a Foundation Fieldbus environment, to calculate the flow rate of natural gas by using an orifice plate in a closed pipe. The principal benefit of using neural networks lies in their low computational cost and simplicity of implementation, which allows just standard blocks to be used, making the technology independent of the Foundation Fieldbus system manufacturer. To perform the calculation, the proposed methodology relies on static pressure, temperature and differential pressure measurements, which are typically available in industrial plants. The developed methodology generates highly accurate results, and this approach can be implemented at a relatively low cost for Foundation Fieldbus system users.