End-of-line fault detection for combustion engines using one-class classification

Leitner, Lukas; Lagrange, Antoine; Endisch, Christian

doi:10.1109/aim.2016.7576768

Cited by 9 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Devices that pass the quality test are considered as devices with correct functions (see Figure 9). The decision on the state of product after a quality test was performed and was previously left to the experience of domain experts [85]. However, with the introduction of mass customization, shorter product life cycles and digital supply chains, this approach has reached its limits, and the need for new approaches has become clear.…”

Section: Predictive Maintenancementioning

confidence: 99%

Towards Flexible and Cognitive Production—Addressing the Production Challenges

et al. 2022

View full text Add to dashboard Cite

Globalization in the field of industry is fostering the need for cognitive production systems. To implement modern concepts that enable tools and systems for such a cognitive production system, several challenges on the shop floor level must first be resolved. This paper discusses the implementation of selected cognitive technologies on a real industrial case-study of a construction machine manufacturer. The partner company works on the concept of mass customization but utilizes manual labour for the high-variety assembly stations or lines. Sensing and guidance devices are used to provide information to the worker and also retrieve and monitor the working, with respecting data privacy policies. Next, a specified process of data contextualization, visual analytics, and causal discovery is used to extract useful information from the retrieved data via sensors. Communications and safety systems are explained further to complete the loop of implementation of cognitive entities on a manual assembly line. This deepened involvement of cognitive technologies are human-centered, rather than automated systems. The explained cognitive technologies enhance human interaction with the processes and ease the production methods. These concepts form a quintessential vision for an effective assembly line. This paper revolutionizes the existing industry 4.0 with an even-intensified human–machine interaction and moving towards cognitivity.

show abstract

Section: Predictive Maintenancementioning

confidence: 99%

Towards Flexible and Cognitive Production—Addressing the Production Challenges

et al. 2022

View full text Add to dashboard Cite

show abstract

“…An ensemble of these one-class classifiers can be used for fault classification (Carino, et al, 2018), so that each type of fault will be classified by its model. Using one-class support vector machines (SVM) is common (Khan & Madden, 2014) and can be used with hand-crafted features in an end-of-line test (Leitner, Lagrange, & Endisch, 2016). But also a reduction of the raw data can be used as input (Fernández-Francos, Martı ńez-Rego, Fontenla-Romero, & Alonso-Betanzos, 2013).…”

Section: One-class-classifier For Anomaly Detectionmentioning

confidence: 99%

Automate Quality Prediction in an End-of-Line Test of a Highly Variant Production of Geared Motors – Discussion of a Full Concept

Wissbrock¹,

Pelkmann

Tölle

2021

PHME_CONF

View full text Add to dashboard Cite

In the production of complex and modular mechanical components such as geared motors the diversity of variants is rising continuously. At the same time the requirement for good sound quality of the product is increasing. In a batch-size-one production it is hard for the assembly operator to determine the product quality consistent. Automation of the end-of-line test leads to several problems. Classical vibration and sound measurements take a lot of time and the features have to be defined individually for every single product configuration. This paper presents a full concept for automation or semi-automation of the end-of-line test in a highly variant production of geared motors. It is shown how acoustic measurement can be done in a common industrial production and gives an overview of typically used machine learning methods and their features for quality prediction of geared motors. Further a concept for dealing with the lack of labeled examples is addressed to analyze historically unknown product configurations. Finally it is discussed how to structure classifiers to capture of all known and unknown faults. The end-of-line concept is a basic module for industry 4.0 and can be generalized to all modern industrial productions where batch-size-one and a high diversity of variants are typical.

show abstract