Application of Neural Networks for Water Meter Body Assembly Process Optimization

Abstract

The proposed model of the neural network (NN) describes the optimization task of the water meter body assembly process, based on 18 selected production parameters. The aim of this network was to obtain a certain value of radial runout after the assembly. The tolerance field for this parameter is 0.2 mm. The repeatability of this value is difficult to achieve during production. To find the most effective networks, 1000 of their models were made (using various training methods). Ten NN with lowest errors of the output value prediction were chosen for further analysis. During model validation the best network achieved the efficiency of 93%, and the sum of squared residuals (SSR) was 0.007. The example of the prediction of the value of radial runout of machine parts presented in this paper confirms the adopted statement about the usefulness of the presented method for industrial conditions and is based on the analysis of hundreds of thousands of parametric and descriptive data on the process flow collected to create an effective network model.