RESUMO
The noise in sensor data has a substantial impact on the reliability and accuracy of (ML) algorithms. A comprehensive framework is proposed to analyze the effects of diverse noise inputs in sensor data on the accuracy of ML models. Through extensive experimentation and evaluation, this research examines the resilience of a LightGBM ML model to ten different noise models, namely, Flicker, Impulse, Gaussian, Brown, Periodic, and others. A thorough analytical approach with various statistical metrics in a Monte Carlo simulation setting was followed. It was found that the Gaussian and Colored noise were detrimental when compared to Flicker and Brown, which are identified as safe noise categories. It was interesting to find a safe threshold limit of noise intensity for the case of Gaussian noise, which was missing in other noise types. This research work employed the use case of changeover detection in (CNC) manufacturing machines and the corresponding data from the publicly funded research project (OBerA).
RESUMO
In recent years, the use of indoor localization techniques has increased significantly in a large number of areas, including industry and healthcare, primarily for monitoring and tracking reasons. From the field of radio frequency technologies, an ultra-wideband (UWB) system offers comparatively high accuracy and is therefore suitable for use cases with high precision requirements in position determination, for example for localizing an employee when interacting with a machine tool on the shopfloor. Indoor positioning systems with radio signals are influenced by environmental obstacles. Although the influence of building structures like walls and furniture was already analysed in the literature before, the influence of metal machine tools was not yet evaluated concerning the accuracy of the position determination. Accordingly, the research question for this article is defined: To what extent is the positioning accuracy of the UWB system influenced by a metal machine tool?The accuracy was measured in a test setup, which consists of a total of four scenarios in a production environment. For this purpose, the visual contact between the transmitter and the receiver modules, including the influence of further interfering factors of a commercially available indoor positioning system, was improved step by step from scenario 1 to 4. A laser tracker was used as the reference measuring device. The data was analysed based on the type A evaluation of standard uncertainty according to the guide to the expression of uncertainty in measurement (GUM). It was possible to show an improvement in standard deviation from 87.64cm±32.27cm to 6.07cm±2.24cm with confidence level 95% and thus provides conclusions about the setup of an indoor positioning system on the shopfloor.
Assuntos
Ondas de RádioRESUMO
Changeover times are an important element when evaluating the Overall Equipment Effectiveness (OEE) of a production machine. The article presents a machine learning (ML) approach that is based on an external sensor setup to automatically detect changeovers in a shopfloor environment. The door statuses, coolant flow, power consumption, and operator indoor GPS data of a milling machine were used in the ML approach. As ML methods, Decision Trees, Support Vector Machines, (Balanced) Random Forest algorithms, and Neural Networks were chosen, and their performance was compared. The best results were achieved with the Random Forest ML model (97% F1 score, 99.72% AUC score). It was also carried out that model performance is optimal when only a binary classification of a changeover phase and a production phase is considered and less subphases of the changeover process are applied.
