FG Automatisierungstechnik
Refine
Document Type
Way of publication
- Open Access (1)
Language
- English (2)
Keywords
- milling (2) (remove)
Institute
- FG Automatisierungstechnik (2)
- FG Systeme (1)
Feature selection (FS) represents an essential step for many machine learning-based predictive maintenance (PdM) applications, including various industrial processes, components, and monitoring tasks. The selected features not only serve as inputs to the learning models but also can influence further decisions and analysis, e.g., sensor selection and understandability of the PdM system. Hence, before deploying the PdM system, it is crucial to examine the reproducibility and robustness of the selected features under variations in the input data. This is particularly critical for real-world datasets with a low sample-to-dimension ratio (SDR). However, to the best of our knowledge, stability of the FS methods under data variations has not been considered yet in the field of PdM. This paper addresses this issue with an application to tool condition monitoring in milling, where classifiers based on support vector machines and random forest were employed. We used a five-fold cross-validation to evaluate three popular filter-based FS methods, namely Fisher score, minimum redundancy maximum relevance (mRMR), and ReliefF, in terms of both stability and macro-F1. Further, for each method, we investigated the impact of the homogeneous FS ensemble on both performance indicators. To gain broad insights, we used four (2:2) milling datasets obtained from our experiments and NASA’s repository, which differ in the operating conditions, sensors, SDR, number of classes, etc. For each dataset, the study was conducted for two individual sensors and their fusion. Among the conclusions: (1) Different FS methods can yield comparable macro-F1 yet considerably different FS stability values. (2) Fisher score (single and/or ensemble) is superior in most of the cases. (3) mRMR’s stability is overall the lowest, the most variable over different settings (e.g., sensor(s), subset cardinality), and the one that benefits the most from the ensemble.
Industrial robots offer a good basis for machining from a conceptual point of view. However they are rarely utilized for machining applications in industry due to their low stiffness and the bad achievable work piece quality. Available solutions using position control of the tool require costly additional hardware and measurement equipment; force controlled solutions depend on low level controller access that is not commonly available for generic cell setups. This paper proposes a three-step approach to compensate for process force induced accuracy errors: (1) selection of appropriate milling strategies and cutting parameters, (2) an offline compensation of the force induced deviations and (3) a respective online compensation method. Experimental validation of the results has been performed for the first two steps.