Predictive Maintenance Model Based on Fusion of Time Series and Supervised Learning Methods - A Case Study of Hydraulic Machine Health Status Prediction

• Main Authors: Chin-Hsuan Liang, 梁勤萱
• Other Authors: Chao-Lung Yang
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/23a4u2

碩士 === 國立臺灣科技大學 === 工業管理系 === 107 === Among the topics in industrial data analytics, one of the important topics is predictive maintenance. Predictive maintenance mainly focuses on the traceability of where the machine is broken or needed to maintain based on the improved prediction accuracy on the sensor data from machines or devices. In previous research works, time series data analysis of the health status of the machine under fixed maintenance mode or fixed recession cycle are studied. In this research, the proposed data fusion model is expected to improve the overall accuracy through the combination of the results and various-data driven technologies with the time series prediction method. At the same time, the size of data collection is an important factor to make the time series model have good quality. Moreover, the property of the initial model to explore the influence degree of each feature is used to facilitate the subsequent scheduling of production and maintenance plans. The experimental result shows that the proposed fusion model can provide a better maintenance decision making on the machine/device maintenance plan based on the relative small or not complete data.