نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
One of the requirements and necessities of the rail transportation industry is proper and preventive maintenance, which is done by properly and correctly assigning locomotives to trains. The Internet of Things, with the ability to connect all devices to the Internet, has provided the conditions for optimizing preventive maintenance and repairs and preventing corrective maintenance and repairs. In the present study, an attempt is made as a pioneering research, using the Internet of Things and machine learning algorithms, instead of randomly assigning locomotives to trains, in order to prevent their breakdowns, based on past data as the big data of the rail transportation industry and also machine learning algorithms. Using four algorithms, random forest, support vector machine, decision tree and nearest neighbor, the evaluation of the presented model was carried out and the results showed that the random forest algorithm with 97 percent and the decision tree algorithm with 96 percent have the highest accuracy in optimally assigning locomotives to trains in the rail transportation industry. The two algorithms, support vector machine and nearest neighbor, are also in the next ranks of importance.
کلیدواژهها English
