Analysis and modeling of a variable speed reciprocating compressor using ANN

• Extend the use of ANNs to analyze and model reciprocating compressors.
• The parameters to model are: mass flow, discharge temperature, and power consumption.
• Each energy parameter was separately modeled using one ANN.
• The number of neurons in the hidden layer was optimized to model the compressor.
• 3D plots were build using the ANN model to analyze the energy behavior of the compressor.

This work presents the empirical study of a reciprocating compressor using Artificial Intelligence to model it. Several artificial neural networks were used to model three energy parameters of the compressor with high precision. The number of neurons in each ANN was optimized to use the minimum number of neurons without compromising accuracy; very few neurons were used when comparing with other works. Computer simulations show that the ANN model for the mass flow rate has the highest accuracy when compared with the models for the discharge temperature and power consumption. These simulations also illustrate that the ANN model for the discharge temperature presented the lowest accuracy.Using the ANN model, 3D plots were built to analyze the energy behavior of the compressor.