Abstract
Artificial neural network-based models were developed for assessing the reliability of two types of machinery: cranes and forklifts. This was done to be able to predict the operating conditions of the machinery. It entails the ability to predict the functional days of the machinery without failures and the exact days on which they would experience failure given a number of input variables. The input variables considered in these models were an easy-start variable, hours run per day and cumulative time between failure, while the output variable was failure potential for a given day. The output variable assesses whether the machinery would fail on a given working day or not. Hence, the input data variables for cranes were obtained from Hyster RS45-27 CH and Konecranes Liftace TFC 45 97-2002, while forklift input data was from Hyster H6.00XL. The data was gotten from machines which were found in a Lagos seaport. The neural network models were later developed, trained, tested and validated using MATLAB. From the results, the PRN-LMA models for both crane and forklifts gave the highest prediction accuracy.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call