RELIABILITY ASSESSMENT OF FORKLIFT USING ARTIFICIAL NEURAL NETWORKS

Abstract

The reliability of a component or system is the likelihood that the component or system would operate satisfactorily for a defined period under specified operating conditions. The aim of this research is to evaluate the reliability of Forklift machinery using artificial neural networks (ANN). Maintaining machinery properly is essential to achieving optimal industrial efficiency. Novel machine learning models were developed for the assessment of the reliability of haulage machinery maintenance using pattern recognition artificial neural networks in this research. The choice of a classification model stemmed from the nature of available data. Hence, the input data variables for the forklift were gotten from Hyster H6.00XL. The artificial neural network model was developed using MATLAB. Trial and error was initially used to arrive at the neural network architecture that gave the lowest mean square error. The architecture that was finally selected consists of input layer, three hidden layers and an output layer. The first and the last hidden layers had a total of 10 neurons each, while the second hidden layer had a total of 20 neurons. However, the best prediction accuracy went to PRN-LMA with an accuracy of 92%, followed by PRN-CGF with an overall prediction accuracy of 81.7%. Next were PRN-OSS and PRN-BFG with prediction accuracies of 81.0% and 80.3% respectively, while PRN-BR was the least accurate, with an accuracy of 75.1%. Generally, the PRN-LMA models gave the highest prediction accuracy, while the Bayesian regularization models (PRN-BR) gave the least prediction accuracy. The model could also be implemented in other lifting and manufacturing machineries.