Data mining for fault diagnostics: A case for plastic injection molding

Kozjek, Dominik; Vrabič, Rok; Kralj, David; Butala, Peter; Lavrač, Nada

doi:10.1016/j.procir.2019.03.204

Cited by 17 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Industry 4.0 concept involves collection, storage, management, and analysis of the data generated by production systems to manage (for automated identification of failures, assessment of operating conditions and quality of products, identification of the unplanned stops, etc.). However, many companies refuse to apply DM because of the poor quality of the outcomes, which is mainly due to the reasons raised in this paper (Schuh et al, 2019;Kozjeka et al, 2019).…”

Section: Literature Reviewmentioning

confidence: 97%

Data mining as a cognitive tool: Capabilities and limits

Polyakov

Khanin

Shevchenko

et al. 2021

Knowledge and Performance Management

View full text Add to dashboard Cite

Due to the large volumes of empirical digitized data, a critical challenge is to identify their hidden and unobvious patterns, enabling to gain new knowledge. To make efficient use of data mining (DM) methods, it is required to know its capabilities and limits of application as a cognitive tool. The paper aims to specify the capabilities and limits of DM methods within the methodology of scientific cognition. This will enhance the efficiency of these DM methods for experts in this field as well as for professionals in other fields who analyze empirical data. It was proposed to supplement the existing classification of cognitive levels by the level of empirical regularity (ER) or provisional hypothesis. If ER is generated using DM software algorithm, it can be called the man-machine hypothesis. Thereby, the place of DM in the classification of the levels of empirical cognition was determined. The paper drawn up the scheme illustrating the relationship between the cognitive levels, which supplements the well-known schemes of their classification, demonstrates maximum capabilities of DM methods, and also shows the possibility of a transition from practice to the scientific method through the generation of ER, and further from ER to hypotheses, and from hypotheses to the scientific method. In terms of the methodology of scientific cognition, the most critical fact was established – the limitation of any DM methods is the level of ER. As a result of applying any software developed based on DM methods, the level of cognition achieved represents the ER level.

show abstract

Section: Literature Reviewmentioning

confidence: 97%

Data mining as a cognitive tool: Capabilities and limits

Polyakov

Khanin

Shevchenko

et al. 2021

Knowledge and Performance Management

View full text Add to dashboard Cite

show abstract

“…Indeed, the virtual part of CPPS usually lives inside the cloud, which makes everything accessible from almost everywhere, putting in place the kind of sharing required in Industry 4.0 for a reduced cost [29]. In some works, information sharing is presented as the key to extend conclusions drawn for one system, to similar systems [30] The kind of sharing discussed in these works, is the one incorporated in the integration and virtualization design principles [31], [32]. In more dept, horizontal integration is inter-companies, while vertical integration is intra-company [33], and both strongly relies upon information availability to several interested users and entities.…”

Section: Data Sharingmentioning

confidence: 99%

One datum and many values for sustainable Industry 4.0: a prognostic and health management use case

Sabbatini

Belli²,

Palma³

et al. 2023

IJECE

View full text Add to dashboard Cite

<span>Industrial context of today, driven by the Industry 4.0 paradigm, is overwhelmed by data. Decreasing cost of innovative technologies, and recent market dynamics have pushed and pulled respectively for those architectures and practices in which data are the masters. While advancing, we have to take care of waste, even though intangibility of data makes them hardly connected to waste. In this paper we are going to reflect on data intensive context of today, focusing on the industrial sector. A smart approach for fully exploiting data collecting infrastructures is proposed, and its declination in a prognostic and health management (PHM) use case set inside an automatic painting system is presented. The contributions of this papers are mainly two: first of all, the general conceptual take-away of "data re-use" is presented and discussed. Moreover, a PHM solution for painting system's number plates, based on optical character recognition (OCR), is proposed and tested as a proof-of-concept for the "data re-use" concept. Summarizing, the already-in-use data sharing principle for achieving transparency and integration inside Industry 4.0, is presented as complementary with the proposed "data re-use", in order to develop a really sustainable shift toward the future.</span>

show abstract

“…Ramkumar et al (2015) followed a simulation-based approach for the cycle time prediction problem for the heating process in rotational molding. Kozjek et al (2019) handled the fault detection problem in the plastic injection molding process with data mining approaches. The authors labeled the unscheduled machine stoppage observations in their dataset as faulty and the rest observations as normal, and aimed to identify these categories using several parameters, including cycle time.…”

Section: High Cycle Time Predictionmentioning

confidence: 99%

Prediction of High Cycle Times in Wheel Rim Molding With Artificial Neural Networks

Kabasakal

Keskin

2022

Verimlilik Dergisi

View full text Add to dashboard Cite

This study proposes a two-stage approach to determine a cycle-time threshold and predict high cycle times by examining sample molding process data obtained from a wheel-rim manufacturer. Methodology: Our study firstly determines thresholds for high cycle times with two alternate approaches. Subsequently, data were labeled regarding the cycle-time threshold. Alternate models based on Artificial Neural Networks (ANNs) were developed in R to predict high cycle times. Findings: Our findings include a comparison of cycle-time threshold approaches through a distance-based metric. After labeling of high cycle times, our study presents the performance of alternate predictive models. The performance of models was compared in terms of accuracy, recall and precision. Originality: Process mining in wheel rim molding has been found meager in prior research, despite the abundance of process mining applications and cycle-time prediction models. Another distinctive aspect of the study is cycle-time threshold determination with multiple methods to eliminate manual labeling of processes.

show abstract

Data mining for fault diagnostics: A case for plastic injection molding

Cited by 17 publications

References 8 publications

Data mining as a cognitive tool: Capabilities and limits

Data mining as a cognitive tool: Capabilities and limits

One datum and many values for sustainable Industry 4.0: a prognostic and health management use case

Prediction of High Cycle Times in Wheel Rim Molding With Artificial Neural Networks

Contact Info

Product

Resources

About