Predictive Maintenance System for Wafer Transport Robot Using K-Means Algorithm and Neural Network Model

• Published in: Electronics (Basel) Vol. 11; no. 9; p. 1324
• Main Authors: Yoo, Ji-Hyun, Park, Young-Kook, Han, Seung-Soo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2022
• Subjects: Algorithms; Artificial neural networks; Cameras; Cluster analysis; Clustering; Datasets; Economic impact; Equipment costs; Experiments; Failure; Feature extraction; Maintenance costs; Neural networks; Predictive maintenance; Robots; Sensors
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics11091324

Maintenance is the technology of continuously monitoring the conditions of equipment and predicting the timing of maintenance for equipment. Particularly in the field of semiconductor manufacturing, where processes are automated, various methods are being tried to minimize the economic losses and maintenance costs caused by equipment failure. A new Predictive Maintenance (PdM) technique, a new method of maintenance, is introduced in this paper to develop an algorithm for predicting the failure of wafer transfer robots in advance. The acceleration sensor data used in the experiment were obtained by installing a sensor onto the wafer transfer robot. To analyze these data, the data preprocessing and FFT process were performed. These data were divided into normal data, first error data, second error data, and third error data (failure data) in stages. By clustering the data using the K-means algorithm, the center point distribution of the clusters was analyzed, and the features of the error data and normal data were extracted. Using these features, an artificial neural network model was designed to predict the point of failure of the robot. Previous research on maintenance systems of the transfer robot used fewer than 50 error data, but 1686 error data were used in this experiment. The reliability of the model is improved by randomly selecting data from a total of 2248 data sets. In addition, it was confirmed that it was possible to classify normal data and error data with an accuracy of 97% and to predict equipment failure by applying neural network modeling.