scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Linking data science to lean production: a model to support lean practices

TL;DR: The literature discusses data science (DS) as a very promising set of techniques and tools to support lean production (LP) practices.
Abstract: The literature discusses data science (DS) as a very promising set of techniques and tools to support lean production (LP) practices. DS could aid manufacturing companies in transforming massive re...
Citations
More filters
09 Dec 2008
TL;DR: In this paper, the authors investigate the definition of Lean Production and the methods and goals associated with the concept as well as how it differs from other popular management concepts, and conclude that Lean Production is not clearly defined in the reviewed literature.
Abstract: Purpose - This paper aims to investigate the definition of Lean Production and the methods and goals associated with the concept as well as how it differs from other popular management concepts. Methodology/Approach - The paper is based on a review of the contemporary literature on Lean Production, both journal articles and books. Findings - It is shown in the paper that there is no consensus on a definition of Lean Production between the examined authors. The authors also seem to have different opinions on which characteristics that should be associated with the concept. Overall it can be concluded that Lean Production is not clearly defined in the reviewed literature. This divergence can cause some confusion on a theoretical level, but is probably more problematic on a practical level when organizations aim to implement the concept. This paper argues that it is important for an organization to acknowledge the different variations, and to raise the awareness of the input in the implementation process. It is further argued that the organization should not accept any random variant of Lean, but make active choices and adapt the concept to suit the organization-s needs. Through this process of adaptation, the organization will be able to increase the odds of performing a predictable and successful implementation. Originality/Value - This paper provides a critical perspective on the discourse surrounding Lean Production, and gives an input to the discussion of the implementation of management models. Keywords - Lean Production, Definition, Construct Validity, Total Quality Management Paper type - Conceptual paper

525 citations

Journal ArticleDOI
TL;DR: This paper identifies eight digital waste reduction mechanisms that illustrate how digital technologies can support lean practices and identifies a cluster of mechanisms that augment operational execution in terms of speed and precision of execution, as well as flexibility in space and time.

31 citations

Journal ArticleDOI
TL;DR: In view of the growing availability of data and advances in big data analytics techniques, there have been more and more applications of data analytics to deal with the problems in production and distribution management as mentioned in this paper .
Abstract: Production and distribution are two key constituents of a supply chain. In view of the growing availability of data and advances in big data analytics techniques, there have been more and more applications of data analytics to deal with the problems in production and distribution management. With this in mind, we proposed a special issue on ‘Big Data Analytics in Production and Distribution Management' to report the latest development in this field. In this editorial, we first introduce the background and examine the existing review works on the applications of data analytics to operations management. We then introduce the papers accepted in the issue, and discuss how different types of big data analytics techniques are applied to production and distribution management, including demand forecasting, production scheduling, distribution management, manufacturing management, and supply chain management. Finally, we conclude the paper with a discussion of future research.

4 citations

Posted ContentDOI
14 Apr 2023
TL;DR: In this paper , the authors evaluated various CNN-based image classification algorithms, including MobileNet, ShuffleNet, DenseNet, RegNet, and NasNet, in classifying steel surface defects in the NEU-CLS-64 dataset.
Abstract: Abstract The global steel demand continues to increase, with steel being used in various industries, including construction, automobile, national defense, and machinery. However, steel production is a delicate process that can result in different defects on the steel surface, negatively affecting the quality of the steel products. Therefore, recognizing metal surface defects is critical in the metal production industry. Manual detection of these defects is the standard method, but it is time-consuming, labor-intensive, and prone to subjective factors, leading to low accuracy and unreliable results. Automated defect detection using computer vision methods can replace or supplement manual detection. In recent years, machine learning algorithms, particularly Convolutional Neural Networks (CNNs), have shown great promise in achieving high accuracy rates in this task. In addition, image classification algorithms can contribute to Lean metal production by identifying defects or anomalies in the manufacturing process, which can be used to reduce waste and increase efficiency. However, the performance and cost of different CNN architectures can vary widely, making it challenging for decision-makers to select the most suitable model. This paper analyzes various CNN-based image classification algorithms, including MobileNet, ShuffleNet, DenseNet, RegNet, and NasNet, in classifying steel surface defects in the NEU-CLS-64 dataset. We evaluate their performance using metrics such as accuracy, precision, sensitivity, specificity, F1 score, and G-mean, and benchmark these models against each other. Our findings revealed that RegNet achieved the highest accuracy, precision, sensitivity, specificity, F1 score, and G-mean performance but at a higher cost than other models. Meanwhile, MobileNet had the lowest performance. The results provide decision-makers with valuable insights into selecting the most suitable CNN model for steel surface defect detection based on their performance.

1 citations

Journal ArticleDOI
TL;DR: In this paper , three different computer-based vision approaches detect damaged packages to prevent them from moving to shipping operations that would otherwise incur waste in the form of wasted operating hours, wasted resources and lost customer satisfaction.
Abstract: Modern manufacturing is the world's largest and most automated industrial sector. The rise of Industry 4.0 technologies such as Big Data, Internet of Things (IoT) devices, and Machine Learning has enabled a better connection with machines and factory systems. Data harvesting allowed for a more seamless and comprehensive implementation of the knowledge-based decision-making process. New models that provide a competitive edge must be created by combining the Lean paradigm with the new technologies of Industry 4.0. This paper presents novel computer-based vision models for automated detection and classification of damaged packages from intact packages. In high-volume production environments, the package manual inspection process through the human eye consumes inordinate amounts of time poring over physical packages. Our proposed three different computer-based vision approaches detect damaged packages to prevent them from moving to shipping operations that would otherwise incur waste in the form of wasted operating hours, wasted resources and lost customer satisfaction. The proposed approaches were carried out on a data set consisting of package images and achieved high precision, accuracy, and recall values during the training and validation stage, with the resultant trained YOLO v7 model.
References
More filters
Journal ArticleDOI
TL;DR: It is argued that certain duties of patients counterbalance an otherwise unfair captivity of doctors as helpers and that vulnerability does not exclude obligation.
Abstract: There has been a shift from the general presumption that “doctor knows best” to a heightened respect for patient autonomy. Medical ethics remains one-sided, however. It tends (incorrectly) to interpret patient autonomy as mere participation in decisions, rather than a willingness to take the consequences. In this respect, medical ethics remains largely paternalistic, requiring doctors to protect patients from the consequences of their decisions. This is reflected in a one-sided account of duties in medical ethics. Medical ethics may exempt patients from obligations because they are the weaker or more vulnerable party in the doctor-patient relationship. We argue that vulnerability does not exclude obligation. We also look at others ways in which patients’ responsibilities flow from general ethics: for instance, from responsibilities to others and to the self, from duties of citizens, and from the responsibilities of those who solicit advice. Finally, we argue that certain duties of patients counterbalance an otherwise unfair captivity of doctors as helpers.

17,373 citations

Journal ArticleDOI
TL;DR: It is demonstrated that the algorithms proposed are highly effective at discovering community structure in both computer-generated and real-world network data, and can be used to shed light on the sometimes dauntingly complex structure of networked systems.
Abstract: We propose and study a set of algorithms for discovering community structure in networks-natural divisions of network nodes into densely connected subgroups. Our algorithms all share two definitive features: first, they involve iterative removal of edges from the network to split it into communities, the edges removed being identified using any one of a number of possible "betweenness" measures, and second, these measures are, crucially, recalculated after each removal. We also propose a measure for the strength of the community structure found by our algorithms, which gives us an objective metric for choosing the number of communities into which a network should be divided. We demonstrate that our algorithms are highly effective at discovering community structure in both computer-generated and real-world network data, and show how they can be used to shed light on the sometimes dauntingly complex structure of networked systems.

12,882 citations

Journal ArticleDOI
TL;DR: In this article, the authors used a unique international data set from a 1989-90 survey of 62 automotive assembly plants, and they tested two hypotheses: innovative HR practices affect performance not individually but as interrelated elements in an internally consistent HR bundle or system.
Abstract: Using a unique international data set from a 1989–90 survey of 62 automotive assembly plants, the author tests two hypotheses: that innovative HR practices affect performance not individually but as interrelated elements in an internally consistent HR “bundle” or system; and that these HR bundles contribute most to assembly plant productivity and quality when they are integrated with manufacturing policies under the “organizational logic” of a flexible production system. Analysis of the survey data, which tests three indices representing distinct bundles of human resource and manufacturing practices, supports both hypotheses. Flexible production plants with team-based work systems, “high-commitment” HR practices (such as contingent compensation and extensive training), and low inventory and repair buffers consistently outperformed mass production plants. Variables capturing two-way and three-way interactions among the bundles of practices are even better predictors of performance, supporting the integrati...

3,977 citations

Journal ArticleDOI
TL;DR: In this paper, the effects of three contextual factors, plant size, plant age and unionization status, on the likelihood of implementing 22 manufacturing practices that are key facets of lean production systems are examined.

2,576 citations

Book
01 Jan 2011
TL;DR: This book provides real-world techniques for monitoring and analyzing processes in real time and is a powerful new tool destined to play a key role in business process management.
Abstract: The first to cover this missing link between data mining and process modeling, this book provides real-world techniques for monitoring and analyzing processes in real time It is a powerful new tool destined to play a key role in business process management

2,287 citations