The transition from large data stacks obtained as a result of rapid development in computer technologies to meaningful information is only possible with data mining and statistics. In this study, a model has been developed to provide early fault detection and vehicle maintenance needs by using instant data obtained from Caterpillar Inc. construction vehicles. With the Early Warning System, primarily, the selected sensor data coming from the satellite related to the vehicles is used to predict the failure possibility of the vehicles in a certain time ahead remotely by using the methods of machine learning and using the internet of things and cloud technology. Then, prediction data are integrated into decision-making mechanisms in business processes. Finally, the information acquired by using data visualization technologies is made available for being reported and made traceable through summary data. The location of data mining on machine learning is illustrated by the necessary algorithms. In order to determine the correct fault in accordance with the data obtained from the sensors of the machines the gradient boosting, logistic regression and C5.0 algorithm is used. From the results obtained, the gradient boosting algorithm produced the best training results for all categories, while for the test data, the gradient boosting algorithm produced the best results for the categories C1000 and C3000, and logit regression for the C3030, C5070 and C5459 categories. The focus of the personalized product mentioned by Industry 4.0, the system developed in this study, can be easily adapted to the operation of different machines.

No abstract