| Autor: |
Abdallah M; Computer and Information Technology, Indiana University-Purdue University Indianapolis, Indianapolis, IN 46202, USA., Joung BG; Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA., Lee WJ; Environmental and Ecological Engineering, Purdue University, West Lafayette, IN 47907, USA., Mousoulis C; Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA., Raghunathan N; Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA., Shakouri A; Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA., Sutherland JW; Environmental and Ecological Engineering, Purdue University, West Lafayette, IN 47907, USA., Bagchi S; Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA. |
| Abstrakt: |
Smart manufacturing systems are considered the next generation of manufacturing applications. One important goal of the smart manufacturing system is to rapidly detect and anticipate failures to reduce maintenance cost and minimize machine downtime. This often boils down to detecting anomalies within the sensor data acquired from the system which has different characteristics with respect to the operating point of the environment or machines, such as, the RPM of the motor. In this paper, we analyze four datasets from sensors deployed in manufacturing testbeds. We detect the level of defect for each sensor data leveraging deep learning techniques. We also evaluate the performance of several traditional and ML-based forecasting models for predicting the time series of sensor data. We show that careful selection of training data by aggregating multiple predictive RPM values is beneficial. Then, considering the sparse data from one kind of sensor, we perform transfer learning from a high data rate sensor to perform defect type classification. We release our manufacturing database corpus (4 datasets) and codes for anomaly detection and defect type classification for the community to build on it. Taken together, we show that predictive failure classification can be achieved, paving the way for predictive maintenance. |
