From Descriptive to Predictive Six Sigma: Machine Learning for Predictive Maintenance

Schäfer, Franziska; Schwulera, Erik; Otten, Heiner; Franke, Jörg

doi:10.1109/ai4i46381.2019.00017

Cited by 14 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Six Sigma is a data-driven improvement cycle used for optimising business processes and reducing the number of defects (Knowles, 2011), and the combination of Six Sigma with data mining tools could enhance the existing limited statistical experimental design as part of Six Sigma (Schafer et al , 2018). Schafer et al (2019) suggested that the combination of Six Sigma and data mining methods could help to move analytics from being purely descriptive to predictive. Therefore, it scored 3 for the applicability criterion.…”

Section: Methodsmentioning

confidence: 99%

Data-driven quality improvement approach to reducing waste in manufacturing

Clancy¹,

O’Sullivan²,

Bruton³

2021

TQM

View full text Add to dashboard Cite

PurposeData-driven quality management systems, brought about by the implementation of digitisation and digital technologies, is an integral part of improving supply chain management performance. The purpose of this study is to determine a methodology to aid the implementation of digital technologies and digitisation of the supply chain to enable data-driven quality management and the reduction of waste from manufacturing processes.Design/methodology/approachMethodologies from both the quality management and data science disciplines were implemented together to test their effectiveness in digitalising a manufacturing process to improve supply chain management performance. The hybrid digitisation approach to process improvement (HyDAPI) methodology was developed using findings from the industrial use case.FindingsUpon assessment of the existing methodologies, Six Sigma and CRISP-DM were found to be the most suitable process improvement and data mining methodologies, respectively. The case study revealed gaps in the implementation of both the Six Sigma and CRISP-DM methodologies in relation to digitisation of the manufacturing process.Practical implicationsValuable practical learnings borne out of the implementation of these methodologies were used to develop the HyDAPI methodology. This methodology offers a pragmatic step by step approach for industrial practitioners to digitally transform their traditional manufacturing processes to enable data-driven quality management and improved supply chain management performance.Originality/valueThis study proposes the HyDAPI methodology that utilises key elements of the Six Sigma DMAIC and the CRISP-DM methodologies along with additions proposed by the author, to aid with the digitisation of manufacturing processes leading to data-driven quality management of operations within the supply chain.

show abstract

Section: Methodsmentioning

confidence: 99%

Data-driven quality improvement approach to reducing waste in manufacturing

Clancy¹,

O’Sullivan²,

Bruton³

2021

TQM

View full text Add to dashboard Cite

show abstract

“…As in Descriptive Six Sigma, Predictive Six Sigma also aims for the quality improvement in products and processes leading to superior performance (studyonline.unsw.edu.au, 2020). However, in Predictive Six Sigma, new questions, such as what will happen or what happens next, are answered (Schäfer et al , 2019). Also, in Predictive Six Sigma the emphasis is placed on predicting future process outputs to be able to adapt process parameters or machine maintenance in a proactive way (Schäfer et al , 2019).…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, in Predictive Six Sigma, new questions, such as what will happen or what happens next, are answered (Schäfer et al, 2019). Also, in Predictive Six Sigma the emphasis is placed on predicting future process outputs to be able to adapt process parameters or machine maintenance in a proactive way (Schäfer et al, 2019). Therefore today, traditional statistical Six Sigma tools are attempted to be enriched through additional ML applications such as ANNs or k-NNs (Larose, 2015;Uluskan, 2020a).…”

Section: Literature Review 21 Predictive Versus Descriptive Six Sigma...mentioning

confidence: 99%

Predictive Six Sigma for Turkish manufacturers: utilization of machine learning tools in DMAIC

Uluskan

Karşı²

2022

IJLSS

View full text Add to dashboard Cite

Purpose This study aims to emphasize utilization of Predictive Six Sigma to achieve process improvements based on machine learning (ML) techniques embedded in define, measure, analyze, improve, control (DMAIC). With this aim, this study presents selection and utilization of ML techniques, including multiple linear regression (MLR), artificial neural network (ANN), random forests (RF), gradient boosting machines (GBM) and k-nearest neighbors (k-NN) in the analyze and improve phases of Six Sigma DMAIC. Design/methodology/approach A data set containing 320 observations with nine input and one output variables is used. To achieve the objective which was to decrease the number of fabric defects, five ML techniques were compared in terms of prediction performance and best tools were selected. Next, most important causes of defects were determined via these tools. Finally, parameter optimization was conducted for minimum number of defects. Findings Among five ML tools, ANN, GBM and RF are found to be the best predictors. Out of nine potential causes, “machine speed” and “fabric width” are determined as the most important variables by using these tools. Then, optimum values for “machine speed” and “fabric width” for fabric defect minimization are determined both via regression response optimizer and ANN surface optimization. Ultimately, average defect number was decreased from 13/roll to 3/roll, which is a considerable decrease attained through utilization of ML techniques in Six Sigma. Originality/value Addressing an important gap in Six Sigma literature, in this study, certain ML techniques (i.e. MLR, ANN, RF, GBM and k-NN) are compared and the ones possessing best performances are used in the analyze and improve phases of Six Sigma DMAIC.

show abstract

“…Their study is meaningful in that they discussed how to take the link with production scheduling to achieve ZDM using advanced maintenance. Schafer et al (2019) proposed steps to be taken to transform from descriptive to predictive Six Sigma for the zero defect goal within production lines. However, there was also a limit to the specific methodology for implementing ZDM.…”

Section: Procedures and Standards For Phmmentioning

confidence: 99%

A Review on the Advanced Maintenance Approach for Achieving the Zero-Defect Manufacturing System

Jun

2022

Front. Manuf. Technol.

View full text Add to dashboard Cite

Recently, a revolutionary change is taking place in manufacturing and production systems thanks to the development of various advanced technologies such as IIoT (Industrial Internet of Things), CPPS (Cyber-Physical Production System), digital twins, big data analytics, AI (Artificial Intelligence), and so on. One of the change is that manufacturing and production systems are now trying to transform into the ZDM (Zero-Defect Manufacturing) system. For a manufacturing company, quality takes precedence over any other competitive factors, so the implementation of a ZDM system is very important. For the implementation of ZDM, many fundamental technologies are required. Among them, the advanced maintenance approach for the facilities/equipment of the manufacturing and production system is much more important because it could support the zero-defect and high-efficiency operation of manufacturing and production systems. The advanced maintenance approach, which is often called by various terms such as predictive maintenance, condition-based maintenance plus (CBM+), and PHM (Prognostics and Health Management), requires various interdisciplinary knowledge and systematic integration. In this study, we will review previous works mainly focusing on advanced maintenance subject among ZDM research works, and briefly discuss the challenging issues for applying PHM technologies to the ZDM.

show abstract

From Descriptive to Predictive Six Sigma: Machine Learning for Predictive Maintenance

Cited by 14 publications

References 6 publications

Data-driven quality improvement approach to reducing waste in manufacturing

Data-driven quality improvement approach to reducing waste in manufacturing

Predictive Six Sigma for Turkish manufacturers: utilization of machine learning tools in DMAIC

A Review on the Advanced Maintenance Approach for Achieving the Zero-Defect Manufacturing System

Contact Info

Product

Resources

About