Predicting the Cycle Time at a Production Line Through the Development of the 3-3-1 Multilayer Perceptron Artificial Neural Networks with Formulated Momentum Rate

The uncertainty of cycle time due to manpower performance, material availability and machine constraint could affect the efficiency of completion time. Hence, the cycle time of a specific task must coordinate efficiently to ensure the smoothness of production operation. Thus, predicting cycle time is an essential issue in production operation and is deemed crucial to be foreseen. From previous studies, various techniques have been utilised to predict cycle time. It is found several works show that the smallest measurement error has been achieved through their proposed Artificial Neural Networks (ANN) models compared to the other predictive techniques. In this regard, the objective of this research is to develop an ANN model to predict the cycle time of a product based on several factors. A feed-forward multilayer perceptron (MLP) network was established and subsequently trained by the developed Backpropagation (BP) learning algorithm to predict cycle time. As a result, the predicted cycle time of the new audio products is 5 s based on the collected data at a selected case company in manufacturing audio speaker products. Consequently, the ANN model could assist production planner in predicting cycle time from historical data for producing new audio speaker products.