Estimation of Washing Performance in Washing Machines with Neural Networks

Abstract

There are many standard procedures that washing machines must provide. One of them is the washing performance, which shows the cleanliness of the laundry. This measurement, called the washing performance index, must meet the criteria determined according to the relevant standard in repeated tests. However, the washing and cleaning process is a complex process affected by many parameters such as mechanical effects, chemical effects, temperature, and amount of water. We propose an approach to determine the effect of these multi-parameter effects on washing performance and estimate the washing performance of the washing machine without the need for trial tests before the algorithm design. The approach uses artificial neural network algorithms to estimate washing performance by varying the relevant input parameters accurately. In order to establish the structure of the neural network, we have performed experimental tests on washing machines with different features and different input parameters and used them for training, validation, and test sets. According to the results obtained, it has been shown that it is possible to predict the washing performance index with neural networks accurately.