Forecasting of Product Quality Through Anomaly Detection

2020
Dinç, Mehmet
Ertekin Bolelli, Şeyda
Özkan, Hadi
Meydanlı, Can
Atalay, Mehmet Volkan
Forecasting of product quality by means of anomaly detection is crucial in real-world applications such as manufacturing systems. In manufacturing systems, the quality is assured through tests performed on sample units randomly chosen from a batch of manufactured units. One of the major issues is to detect defective units among the sample test units as early as possible in terms of test time and of course as accurate as possible. Traditional way of detecting defective units is to make use of human experts during test. However, human intervention is prone to errors and it is time consuming. On the other hand, automated systems are efficient alternatives and of assistance to human experts. There are on-line and off-line approaches for automated systems. Our ultimate aim is to design a system that automates the detection of defective units among the sampled freezer units manufactured in high volumes in a factory of one of the leading home appliances manufacturers. We start by analyzing the data of the test units sampled from the batches of freezer units. For analysis, we first embedded data in two-dimensional space to observe if there are any structures exist in the data. Clustering was then applied to see if the data can be grouped into two classes without their labels. As off-line approaches, state-of-the-art classifier methods including one-class-classifier are employed. Finally, a deep learning method for time-series analysis combined with a classifier is applied as an on-line method.
ECML/PKDD 2019 Workshop on IoT Stream for Data Driven Predictive Maintenance

Suggestions

Monitoring reliability for a three-parameter Weibull distribution
Sürücü, Barış (Elsevier BV, 2009-02-01)
Control charts are widely used to monitor production processes in the manufacturing industry and are also useful for monitoring reliability. A method to monitor reliability has recently been proposed when the distributions of inter-failure times are exponential and Weibull with known parameters. This method has also been extended to monitor the cumulative time elapsed between a fixed number of failures for the exponential distribution. In this paper, we consider a three-parameter Weibull distribution to mod...
Sliding Mode Control of a Power Screw Driven Positioning Table
BAYAR, Gokhan; Konukseven, Erhan İlhan; Koku, Ahmet Buğra (2010-09-10)
Precise positioning and trajectory tracking control applications are important for industrial manufacturing and scientific research. Ball-screw, worm-gear, and power-screw driven systems are widely used for this purpose. Since power screw driven systems provide long range and allow precise servo control, they are commonly preferred. The control strategy developed for power screw driven systems is expected to be robust, to respond rapidly for fast tracking performance and to reject disturbances. These system...
Empirical evaluation of a decision support model for adopting software product line engineering
Tuzun, Eray; Tekinerdogan, Bedir; Kalender, Mert Emin; Bilgen, Semih (2015-04-01)
Context: The software product line engineering (SPLE) community has provided several different approaches for assessing the feasibility of SPLE adoption and selecting transition strategies. These approaches usually include many rules and guidelines which are very often implicit or scattered over different publications. Hence, for the practitioners it is not always easy to select and use these rules to support the decision making process. Even in case the rules are known, the lack of automated support for st...
Comparison of methods for robust parameter design of products and processes with an ordered categorical response
Bacanlı Karabulut, Gonca; Köksal, Gülser; Department of Industrial Engineering (2013)
Robust design of products or processes with categorical response has more momentous role in industrial experiments for quality improvements, because ordinal categorical quality characteristics are encountered more frequent than continuous ones in industry. In this study, five optimization methods for an ordered categorical response are compared with each other: Logistic Regression Model Optimization (LRMO), Accumulation Analysis (AA), Weighted Signal-to-noise Ratio (WSNR), Scoring Scheme (SS), and Weighted ...
Hierachical variability management in software product lines
Atasoy, Mehmet Erdem; Doğru, Ali Hikmet; Department of Computer Engineering (2013)
Software product lines (SPL) aim is to analyze commonality and variability of product family although SPLE describes much kind of processes in different abstraction levels. In this respect, numbers of variations are increasing for the types of products so that may result in increasing cost of the managing variability process. So that variability models is used to manage variabilities in software product lines. Representing solution space variability in an understandable way in software product line engineer...
Citation Formats
M. Dinç, Ş. Ertekin Bolelli, H. Özkan, C. Meydanlı, and M. V. Atalay, “Forecasting of Product Quality Through Anomaly Detection,” Würzburg, Almanya, 2020, p. 357, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/88471.