Abstract. This paper presents the extension of an empirical study in which a universally applicable fault diagnosis method is used to analyse vibration data of bearings measured with accelerometers.
The motivation for extending the previously published results was to provide a profound analysis of the proposed approach with regard to a more feasible training scenario for real applications.
For a detailed assessment of the method, data were acquired on two different test beds: a gearbox test bed equipped with various bearings at different health states and an accelerated lifetime (ALT) test bed to degrade a bearing and introduce an operational fault.
Features were extracted from the raw data of two different accelerometers and used to monitor the actual health state of the bearings.
For that purpose, feature selection and classifier training are performed in a supervised-learning approach.
The accuracy is estimated using an independent test dataset.
The results of the gearbox test bed data show that the training of the method can be performed with non-steady-state data and that the same feature set can be used for different revolution speeds if a small decrease in accuracy is acceptable.
The results of the ALT test bed show that the same features that were identified in the gearbox test start to change significantly when the bearing starts to degrade.
Thus, it is possible to observe the identified features for applying predictive maintenance.
The digital world offers ample availability of data, both historic and real-time. While this capability has the potential for a better decision-making, the contrary can be the case for a human actuator. Information overflow causes mental overload rather than empowerment of choice. In the context of the traditional supermarket shopping for example, customers are exposed to unstructured and complex product information including ingredients, nutrition facts, product labels, and more. Processing all this information in the context of multiple sustainability aspects requires expert knowledge. On the other hand, the rise of digitalization and the Internet of Things can be used to assist and empower customers during this shopping process. However, an integrated solution is required to provide a high grade of usability and the crucial complexity reduction for customers. Therefore, we outline an IoT decision-support system which assists customers on the sales floor and enables a better decision-making according to personal preferences and sustainable consumption. It integrates an indoor localization system, a product information database and a ranking system considering the individual shopping preferences, where the latter is specified by the customer within an interactive smartphone application. The discussed IoT decision support system was deployed and tested in two retail stores. Its interaction with non-expert test participants was observed over months and the results are summarized in this contribution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.