Automated Root Cause Analysis of Non-Conformities With Machine Learning Algorithms

Mueller, Tobias; Greipel, Jonathan; Weber, Tobias; Schmitt, Robert

doi:10.5604/01.3001.0012.7633

Cited by 3 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To sum up, detecting root causes of defected parts in the production process is a highly demanding task in the manufacturing industry and needs extensive knowledge from experts to perform analyses. However, this demands high costs and offers low flexibility (Mueller et al, 2018). In this direction, ML-based techniques are able to model a vast amount of process data empirically, contributing to an automated root cause analysis, also reducing the costs and the necessary expert knowledge.…”

Section: Resultsmentioning

confidence: 99%

A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing

Παπαγεωργίου

Theodosiou

Rapti

et al. 2022

Front. Manuf. Technol.

View full text Add to dashboard Cite

The identification of defect causes plays a key role in smart manufacturing as it can reduce production risks, minimize the effects of unexpected downtimes, and optimize the production process. This paper implements a literature review protocol and reports the latest advances in Root Cause Analysis (RCA) toward Zero-Defect Manufacturing (ZDM). The most recent works are reported to demonstrate the use of machine learning methodologies for root cause analysis in the manufacturing domain. The popularity of these technologies is then summarized and presented in the form of visualizing graphs. This enables us to identify the most popular and prominent methods used in modern industry. Although artificial intelligence gains more and more attraction in smart manufacturing, machine learning methods for root cause analysis seem to be under-explored. The literature survey revealed that only limited reviews are available in the field of RCA towards zero-defect manufacturing using AI and machine learning; thus, it attempts to fill this gap. This work also presents a set of open challenges to determine future developments.

show abstract

Section: Resultsmentioning

confidence: 99%

A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing

Παπαγεωργίου

Theodosiou

Rapti

et al. 2022

Front. Manuf. Technol.

View full text Add to dashboard Cite

show abstract

“…Decision tree (DT) adalah salah satu teknik data mining untuk pencarian akar masalah membantu memperbaiki kualitas produk. Sebagaimana (Mueller, Greipel, Weber, & Schmitt, 2018) melakukan simulasi automatisasi pencarian akar masalah menggunakan DT.…”

Section: Pendahuluanunclassified

Analisa Akar Masalah Radial Run Out Ban Menggunakan Decision Tree

Biantoro

Hernadewita

2021

JMSTKIK

View full text Add to dashboard Cite

Problem solving in the multistage production process is a challenge for the industry. The use of modern techniques such as machine learning in solving quality problems continues to be developed. One of the machine learning is decision tree. The tire industry entered the era of industrial revolution 4.0 with the use of information technology. Utilizing data using machine learning in finding the root cause of the problem can support the tire industry in industrial competition. This study aims to explore the process data in the tire industry to solve one of the tire quality problems, namely radial run-out tires. The technique of finding the root of the problem in this research is done using Classification and Regression Tree (CART) technique. Input variables involve 60 factors in the production process. From the research, it was found that the factors that influence the radial run out value are the lot of the Tread, Bead and Sidewall components. The factors causing the high radial run-out of the tires are the variations in the lot of the tire components Tread and Bead. The decision tree model that was formed has a precision level of 74.7% in detecting high radial run-out events. The effects of improvement on the lot tread and bead components resulting from the decision tree can reduce the defect of radial run out rate by 99.9%. Keywords: Decision tree; Root cause analysis; Radial run-out Tire; Data mining AbstrakPemecahan masalah pada proses produksi multistage merupakan tantangan untuk indusri. Pemanfaatan teknik modern seperti machine learning dalam pemecahan masalah kualitas terus dikembangkan. Salah satu machine learning adalah decision tree. Industri ban memasuki era industri revolusi 4.0 dengan adanya pemakaian teknologi informasi seperti barcode atau radio frequency identification. Pemanfaataan data dengan menggunakan machine learning dalam pencarian akar masalah bisa mendukung industri ban dalam kompetisi industri. Penelitian ini bertujuan untuk mengekplorasi data proses pada industri ban untuk memecahkan permasalahan kualitas ban yaitu radial run-out ban. Teknik pencarian akar masalah dilakukan menggunakan Clasification and Regression Tree (CART). Variabel input melibatkan 60 faktor dalam proses produksi. Dari penelitian didapatkan faktor yang mempengaruhi nilai radial run out adalah lot komponen Tread, Bead dan Sidewall. Untuk faktor penyebab tingginya radial run-out ban adalah variasi lot komponen Tread dan Bead. Model decision tree yang terbentuk memiliki tingkat presisi 74,7% dalam mendeteksi kejadian radial run-out berkategori tinggi. Efek perbaikan pada komponen lot Tread dan Bead yang dihasilkan dari decision tree dapat menurunkan tingkat defect radial run- out ban sebesar 99,9%.

show abstract

“…Root cause analysis (RCA), refers to the process of identifying and delimiting the elements originating the anomaly [9]. RCA process aims at allocating the root cause by analyzing fault information with observed data [9]. In Manufacturing Industry, RCA is a highly effective technique for product design engineers and production managers to help in innovative problem-solving.…”

Section: Unsupervised Techniquesmentioning

confidence: 99%

“…In [9], The authors introduced a procedure for an automated root cause analysis using machine learning algorithms. They named the anomaly points as parts outside the tolerance limits, and they proposed a supervised and unsupervised approach to detect root causes of these anomalies' parts.…”

Section: A Root Cause Analysismentioning

confidence: 99%

Assembly Line Anomaly Detection and Root Cause Analysis Using Machine Learning

Abdelrahman

Keikhosrokiani

2020

IEEE Access

View full text Add to dashboard Cite

Anomaly detection is becoming widely used in Manufacturing Industry to enhance product quality. At the same time, it plays a great role in several other domains due to the fact that anomaly may reveal rare but represent an important phenomenon. The objective of this paper is to detect anomalies and identify the possible variables that caused these anomalies on historical assembly data for two series of products. Multiple anomaly detection techniques were performed; HBOS, IForest, KNN, CBLOF, OCSVM, LOF, and ABOD. Moreover, we used AUROC and Rank Power as performance metrics, followed by Boosting ensemble learning method to ensure the best anomaly detectors robustness. The techniques that gave the highest performance are KNN, ABOD for both product series datasets with 0.95 and 0.99 AUROC respectively. Finally, we applied a statistical root cause analysis on the detected anomalies with the use of Pareto chart to visualize the frequency of the possible causes and its cumulative occurrence. The results showed that there are seven rejection causes for both product series, whereas the first three causes are responsible for 85% of the rejection rates. Besides, assembly machines engineers reported a significant reduction in the rejection rates in both assembly machines after tuning the specification limits of the rejection causes identified by this research results.

show abstract

Automated Root Cause Analysis of Non-Conformities With Machine Learning Algorithms

Cited by 3 publications

References 8 publications

A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing

A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing

Analisa Akar Masalah Radial Run Out Ban Menggunakan Decision Tree

Assembly Line Anomaly Detection and Root Cause Analysis Using Machine Learning

Contact Info

Product

Resources

About