Name
Abstract | ||
|---|---|---|
In this paper, we propose a method to adjust the maintenance interval of equipment by modifying the bandit algorithm. Some facilities and equipment (assembling apparatuses, generators, elevators, etc.) require maintenance or replacement to prevent failure or similar problems. Extending the interval between maintenance of the equipment increases the risk of failure but lowers maintenance costs. Our goal is to set the maintenance interval that minimizes the total cost, which is the sum of maintenance costs and the cost to fix failures. To obtain the maintenance interval that minimizes total cost, a process of trial and error is required to gather data, using an interval longer than the current interval. We consider this problem as a special bandit problem and propose a method that applies the bandit algorithm. Specifically, we regard the problem of adjusting the maintenance interval as a bandit problem with an inclusive relation in which one can know the cost of both the selected interval and also the costs of shorter intervals. As a result, the proposed method can utilize all available cost information and automatically calculate a proper maintenance interval after only a small number of trials. We perform numerical experiments with virtual scenarios and real equipment conditions and show that this method can reduce the total cost of the equipment. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ICIT.2019.8755002 | 2019 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT) |
Keywords | Field | DocType |
maintenance, replacement, interval adjustment, bandit algorithm | Small number,Trial and error,Algorithm,Elevator,Engineering,Total cost | Conference |
ISSN | Citations | PageRank |
2643-2978 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daiki Kiribuchi | 1 | 0 | 0.34 |
| Myungsook Ko | 2 | 0 | 0.34 |
| Takeichiro Nishikawa | 3 | 2 | 0.75 |