Identifying manufacturing operational conditions by physics-based feature extraction and ensemble clustering |
| |
| Affiliation: | 1. Department of Industrial and Systems Engineering, Rutgers, the State University of New Jersey, Piscataway, NJ 08854, USA;2. Global Data, Insight & Analytics, Ford Motor Company, Dearborn, MI 48126, USA;1. Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China;2. Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, Tsinghua University, Beijing 100084, China;1. Key Laboratory of Computer Integrated Manufacturing System, Guangdong University of Technology, Guangzhou, Guangdong, 510006, China;2. Department of Systems Engineering and Engineering Management, City University of Hong Kong, Hong Kong;3. Department of Electrical Engineering, City University of Hong Kong, Hong Kong;1. Department of Industrial & Systems Engineering, Rutgers University, 96 Frelinghuysen Road, Piscataway, NJ 08854-8018, USA;2. Department of Industrial and Manufacturing Engineering, The Pennsylvania State University, 310 Leonhard Building, University Park, PA 16802-4400, USA;1. Ulm University of Applied Sciences, Prittwitzstraße 10, 89075, Ulm, Germany;2. PROTECH –Institute for Production Technology, University of Siegen, Paul-Bonatz-Str. 9-11, 57076, Siegen, Germany;1. Applied Research Laboratory at The Pennsylvania State University, United States;2. The Pennsylvania State University, United States |
| |
| Abstract: | Manufacturing processes usually exhibit mixed operational conditions (OCs) due to changes in process/tool/equipment health status. Undesired OCs are direct causes of out-of-control production and thus need to be identified. Data-driven OC identification has been widely used for recognizing undesired OCs, yet most methods of this kind require labels indicating the OCs in model training. In industrial applications, such labels are rarely available due to delay, incompleteness or physical constraints in data collection. A typical case is the thermal images acquired by in-process infrared camera and pyrometer, which contain rich information about process health status but are unlabeled. To facilitate data-driven OC identification with unlabeled thermal images, this study proposes a feature extraction-clustering framework that characterizes the heat-affected zone by its temperature profile and performs ensemble clustering on the extracted features to label the data. Domain knowledge from plant manufacturing is incorporated in the framework to map cluster labels to OCs. Both offline OC recovery and online OC identification are studied. Thermal images from hot stamping in automotive manufacturing are used to demonstrate and validate the proposed method. The feasibility, effectiveness and generality are well justified by the case study results. |
| |
| Keywords: | Unsupervised learning Ensemble clustering Thermal image analysis Operational condition |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
