Manufacturing Quality Management Research Articles

Capability Indices for Digitized Industries: A Review and Outlook of Machine Learning Applications for Predictive Process Control

Leveraging machine learning applications for predictive process control signifies a decisive advancement in manufacturing quality management, transitioning from traditional descriptive to predictive capability indices. This review highlights the growing importance of predictive process control, essential for quality assurance and the dynamic adaptability of production lines, which is paramount in satisfying stringent quality standards and evolving consumer demands. The investigation into the integration of comprehensive sensor networks and sophisticated algorithmic analytics enriches continuous improvement strategies, markedly enhancing the accuracy and efficiency of production quality monitoring and control mechanisms. By moving beyond the limits of statistical process control to predictive methods enabled by machine learning algorithms, the study presents a transformative leap in manufacturing processes. The presented findings illustrate the critical role of predictive algorithms in navigating the complexities of process variability, thereby ensuring consistent adherence to established quality specifications. This approach not only facilitates immediate and accurate product quality categorization, increasing overall operational efficiency, but also equips manufacturers to swiftly respond to the variable nature of manufacturing requirements. Furthermore, this research delves into the multifaceted impacts of predictive process control on the manufacturing ecosystem. The ability to predict process quality decrease before it occurs, the optimization of resource allocation, and the anticipation of production bottlenecks before they impact output are among the notable benefits of this technological evolution. These developments to predictive process control is instrumental in propelling the manufacturing industry toward a more agile, sustainable, and customer-centric future. This shift not only complements the industry’s drive toward comprehensive digitization but also promises significant strides in achieving superior process improvements and maintaining a competitive edge on the global market.

A steel surface defect detection model using machine learning

For industries around the world that have adopted manufacturing quality management, finding steel surface flaws is one of the toughest difficulties. The conventional method of inspection of the steel's surface detection takes a long time. Steel faults detection is possible via image analysis through machine learning techniques, which could further helps to save the time of fault detection and enhances the steel fault detection process. This further helps to adopt the machine learning techniques in steel industries. The objective of this endeavour is to create models that can detect steel defects. Using the SEVERSTAL dataset, which includes 12,568 photographs of the steel surface, the models were created for binary categorization (defect and no defect). These models were then evaluated for multiclass classification. In this research, image pre-processing is used to enhance the detection of steel faults.

A YOLO-based Real-time Packaging Defect Detection System

Managing the quality of products is one of the primary concerns in manufacturing production to obtain better operational efficiency in factories. In recent years, there have been numerous different approaches for improving product quality management in manufacturing. Each method has certain advantages and limitations, and the common goal is to bring the best efficiency in managing product quality before delivering them to consumers. In this paper, we introduce an approach to creating a real-time packaging defect detection system based on deep learning techniques intending to automatically detect defective packaged products in industrial quality control of packages. To be more precise, we present a real-time defect detection system to help classify product quality automatically based on the YOLO (You only look once) algorithm. The system can be integrated into factories and production lines, helping to optimize efficiency and save operating costs.

Customer Feedback Analysis Engine for Manufacturing Quality Management

Customer Feedback Analysis Engine for Manufacturing Quality Management

Application Analysis of Prefabricated Highrise Building Construction

This paper analyzes the application of prefabricated high-rise building construction. Based on the quality of prefabricated buildings, this paper studies the theory and practice of quality management in manufacturing and construction industry at home and abroad. Based on the background of "integration of two modernizations", this paper combs the relevant research results of intelligent information transmission and collaborative management, and makes an in-depth study on the quality problem and improvement mechanism of prefabricated buildings as the core problem. This paper analyzes the performance and causes of quality problems in the construction process of prefabricated buildings by using arrangement diagram method and 4M1E method. This paper puts forward the quality problem improvement mechanism from four aspects: organization, culture, process control, technical guarantee and information collaborative management.

Deploying an Artificial Intelligence‐based defect finder for manufacturing quality management

AbstractThis paper describes how the Big Data Research Center of Kyung Hee University and Benple Inc. developed and deployed an artificial intelligence system to automate the quality management process for Frontec, an SME company that manufactures automobile parts. Various constraints, such as response time requirements and the limited computing resources available, needed to be considered in this project. Defect finders using large‐scale images are expected to classify weld nuts within 0.2 s with an accuracy rate of over 95%. Our system uses Circular Hough Transform for preprocessing as well as an adjusted VGG (Visual Geometry Group) model. Our convolutional neural network (CNN) system shows an accuracy of over 99% and a response time of about 0.14 s. To embed the CNN model into the factory, we reimplemented the preprocessing modules using LabVIEW and had the classification model server communicate with an existing vision inspector. We share our lessons from this experience by explaining the procedure and real‐world issues developing and embedding a deep learning framework in an existing manufacturing environment without implementing any hardware changes.

The Performance Analysis of Transfer Learning for Steel Defect Detection by Using Deep Learning

Detecting steel surface defects is one of the challenging problems for industries worldwide that had been used in manufacturing quality management. Manual inspection of the steel surface detects is a time-consuming process. This work aims at developing deep learning models that can perform steel defect detection and evaluating the potential of transfer learning for this task. In this paper, four types of transfer learning methods: ResNet, VGG, MobileNet, and DenseNet are experimentally evaluated to develop models for steel surface defect detection. The models were developed for binary classification (defect and no-defect) using the SEVERSTAL dataset from that contains 12,568 images of the steel surface. Then, these models were also assessed for multiclass classification using NEU dataset with 1800 images. In this work, image pre-processing is included to improve the result of steel defects detection. The experimental results have shown that the model developed by using the MobileNet method have the highest detection rate with 80.41% for the SEVERSTAL dataset and 96.94% for the NEU dataset compare to ResNet, VGG, and DenseNet transfer learning.

Nonparametric Phase-II control charts for monitoring high-dimensional processes with unknown parameters

Monitoring multivariate and high-dimensional data streams is often an essential requirement for quality management in manufacturing and service sectors in the Industry 4.0 era. Identifying a suitable distribution for a multivariate data set, especially when the number of variables is much larger than the sample size, is often challenging. Consequently, in a high-dimensional set-up, that is, when the number of variables under investigation exceeds sample size, parametric methods are generally not reliable in practice. There are various nonparametric schemes based on data depth for multivariate process monitoring, which are applicable only when the sample size is reasonably larger than the number of variables in the process but not in a high-dimensional set-up. We discuss that most of these charts are not robust when the true process parameters are unknown. There are, however, some nonparametric schemes for a high-dimensional process, when true process parameters are known. Nevertheless, when process parameters are unknown, a highly robust nonparametric scheme for monitoring high-dimensional processes is not yet available. In this paper, we propose some Shewhart-type nonparametric monitoring schemes based on specific distance metrics for surveillance of multivariate as well as high-dimensional processes. Our proposed charts are easy to implement, interpret and also advantageous in simultaneous monitoring of multiple aspects. We discuss the design and implementation issues in details. We carry out a performance study using Monte Carlo simulations and illustrate the proposed methods using a dataset related to industrial production.

The design of education in ‘Manufacturing Quality Management’ to enable quantifiable industrial improvements by students

Abstract Degree apprentices (DAs) undertake an exciting, alternative route to academic qualifications, combining real employment with University study. Here, we discuss their education in ‘Quality Improvement’ at WMG, focusing on the development of statistical expertise in Year 2 of their programme to procure real improvements in manufacturing and service operations. We show how the preparation for these in Year 1 and the further extension of these in Year 3, interleaved with work-based projects, ensure that DAs can make a significant impact during their apprenticeships. This provides a rapid return on investment for employers, and recognition and faster career progression for DAs.

Quality Management in Manufacturing and Technological Systems

This article discusses the peculiar features of quality management in modern manufacturing and technological systems with consideration for risk-based thinking, in particular, which characterizes quality as a measurable and estimable factor, its indices, existing major categories of quality management, how and when they are applied, as well as their distinctive features.

Activities of the Consortium for Medicine, Chemistry, and Physics at Osaka University

In the fall of 2015, the Graduate School of Science, Osaka University’s Graduate School of Science, the Graduate School of Medicine, and the Center for Nuclear Physics cooperated to establish the project “Formation of an International Medical Center for Advanced Cancer Therapy by Medical Collaboration” as an estimate request project. Currently, one-third of cancer patients in Japan have so-called “advanced cancer,” which has invaded neighboring organs or undergone distant metastasis at the time of initial consultation. Its 5-year survival rate is less than 15%; therefore, new treatment methods need to be developed. In this context, radiopharmaceuticals are beginning to attract the limelight. A radiopharmaceutical is a medicine using a radionuclide (RI), and since it uses a beta-ray nuclide which is frequent from RI, there has been a problem of side effects being generated due to the influence on surrounding normal tissues. It appeared in nuclear medicine treatment using alpha-ray nuclides. Since α-rays have a range of about one cell in the body, they can be used to minimize radiation damage to normal organs and can be easily shielded against, eliminating the need for a special treatment room and enabling the use of treatment in regular hospitals. In 2016, in Japan, radium 233 (233Ra, product name Zofigo) adapted to bone-metastasized prostate cancer was approved for the first time as a nuclear medicine remedy using alpha rays. This medicine is a radiopharmaceutical that can be administered on an outpatient basis. At Osaka University in Japan, the several medical collaboration project is being promoted to realize various advanced cancer treatments with drugs using α-ray nuclides. The option currently focused on the most is astatine 211 (211At). 211At is a short-lived nuclide that releases only α-rays with a half-life of 7.2 h, and it can be introduced into pharmaceutical molecules by covalent bonding since it is a halogen element. To date, studies have been undertaken to confirm the dynamics of 211At in the body of rats, to combine 211At with antibody drugs and virus-like particles used for cancer treatment, and with target compounds of amino acid transporters. All of these considerations can be carried out within the Osaka University Suita Campus. At the nuclear physics research center (RCNP) in the university, one of the leading accelerators in Japan is installed, so 211At can be efficiently manufactured. It is planned to be remodeled soon to be administered to people. In addition, it is close to the RI Center, which is a facility where purification and complexation of 211At can be performed, along with cell and animal experiments, as well as hospitals that can carry out clinical trials. It is a nuclear medicine remedy that is compliant with GMP manufacturing quality management regulations. Production planning is ongoing. It is expected that new medical innovations generated from such matching of science and medicine will lead to the development of drugs for dreams.

Analysis of the wind average speed in different Brazilian states using the nested GR&R measurement system

Brazil presents remarkable potential for wind power generation. This study aims to evaluate the behavior of wind average speed at the four major wind energy-producing states. The main contribution of this research is to use the NGR&R study (Nested Gage Repeatability & Reproducibility), generally applied on manufacturing quality management. Wind average speeds were collected for each month in four states, between the years of 2012 and 2015. Seasonality impact, measurements recurrence over the years and difference between states on wind average speed were assessed in this research. Time series, boxplot and control charts have been used to investigate not only wind average speed between months and states, but also range variation for each state by month. Study results show that the impact of these three factors is statistically significant and that the different location of these states presents the most relevant impact to wind mean speed variation in the country.

Interpretive structural modeling for integrating quality management in manufacturing and service counterparts

PurposeThe purpose of this paper is to identify and rank the contextual relationship among the quality management (QM) constructs for manufacturing and its related service organizations providing integrated value bundles, which has got limited research attention.Design/methodology/approachThe QM constructs of manufacturing and services are selected by performing the citation analysis. Studies related to manufacturing and service are selected by reviewing their citations index in the three major research databases namely ProQuest, Scopus and Google Scholar. The subjective responses from both industry and academia are taken in order to gain better understanding of the contextual relationship among the QM constructs. Finally, an integrated model is proposed using Micmac analysis and Interpretive Structural Modeling (ISM).FindingsThe citation analysis lead to identification of 12 QM constructs: top management commitment, supplier relationship management, human resource management, strategic focus, customer focus, quality of information sharing, process management, servicescape, employee involvement, service quality, supply chain flexibility and customer satisfaction. The expert opinions of executives in the automotive industry and academia resulted in the development of contextual relationships among the identified QM constructs for the development of an ISM model, which is a major contribution of this study.Originality/valueThe unique focus of this study is on analyzing the contextual relationship among QM aspects in manufacturing and services as clubbed offering. The researchers in the existing literature have so far differentiated between manufacturing and services but this study integrates the QM constructs for manufacturing and its associated services through expert feedback and proposes an ISM model.

Design and Development of Manufacturing Quality Management Information System for Auto Parts Enterprise

At the current auto parts manufacturing quality management present situation, this paper analyses the problems existing in the informatization, put forward from the specification quality data, and sets up quality management information platform, development and quality management information system development countermeasure, to help enterprises improve quality management level.

A new process capability analysis chart approach on the chip resistor quality management

Process capability indices have been extensively used to determine whether the quality characteristics of the product meet the preset targets of the customer in manufacturing industries. However, these existing process capability indices cannot categorically determine improvement priorities for substandard quality characteristics. Besides, process capability indices also cannot effectively identify and measure deficiencies in process capability owing to accuracy, precision, or both. In this study, we combine the process capability index Cpm, minimum individual process capability C0, accuracy A, and precision P to develop a new process capability analysis chart. Managers can apply process capability analysis chart to identify the substandard quality characteristics of the product. Furthermore, if the budget for all substandard quality characteristics improvements is limited, we use the discrimination distance method to measure and determine improvement priorities for substandard quality characteristics. Moreover, we construct an implementation flowchart of the process capability analysis chart to derive the results easily. Finally, an example of a chip resistor is presented to illustrate the applicability of the process capability analysis chart for manufacturing quality management.

Malcolm Baldridge award as strategic leverage for educational and other service-related institutions

Since its inception in 1987, the Malcolm Baldridge National Quality Award (MBNQA) is given to establishments in various industries for their achievements through improving quality. At first glance, the award appears to favour manufacturing facilities, having received 40% of the awards over its history. Based on the origination and importance of quality management in manufacturing, this should come as no surprise. The focus of the paper is to evaluate if manufacturing has ultimately favoured compared to other industries and how the award has impacted some of the other industries included in them, namely small business, healthcare, and education. Taking industry size into account an industry comparison revealed that education is well represented and healthcare is underrepresented. Small business has decreased slightly in awards due to the addition of new categories in 1999. Overall, the facilities that have won the awards have been stories of success. Therefore, quality management can help improve all establishments regardless of industry.

Flexibility and quality management in manufacturing: an alternative approach

The purpose of this current research is to investigate the impact that implementing quality improvement (QI) processes has on manufacturing flexibility. First, we analyse whether firms that introduce QI processes better adapt their manufacturing flexibility level to the requirements of the environment. Second, we look at whether there are significant differences in this fit in terms of the manufacturing flexibility dimensions between firms that implement QI processes and those that do not. Third, we concentrate on finding out how QI processes intervene as a mediating mechanism in the relationship between manufacturing flexibility fit and performance. In order to do this, we have made a wide-ranging, transnational study within the framework of the European Union, using data from 417 European firms. The results reveal that firms with QI programs achieve higher levels of manufacturing flexibility, though with a worse fit to the requirements of the environment. This is due, not to a lack of flexibility but, rather, to an excess of it, which is not reflected in better performance.

Total quality management in manufacturing: First snapshots from Malaysia

(1997). Total quality management in manufacturing: First snapshots from Malaysia. Total Quality Management: Vol. 8, No. 2-3, pp. 265-270.

Total quality management in manufacturing: A study in the Singapore context

The paper presents a total quality management (TQM) framework combining the concepts underlying the notions of total quality control (TQC), Just in Time (JIT), manufacturing resource planning (MRP), and quality control circles (QCCs). An integrative model, in which these notions and the related issues are complementarily connected on the same logical plane is presented and it is argued that this is akin to the total systems intervention (TSI) approach in its endeavor to seek manufacturing excellence. It also has similarities to creative problem solving, especially with regard to corporate strategy, but here with an emphasis on the role of manufacturing. However, TQM is an idea of its own, and not a conceptual derivative of systems theory.

Object-oriented expert system architectures for manufacturing quality management

Object-oriented expert system architectures for manufacturing quality management