Conference Paper

Image Mining for Real Time Quality Assurance in Rapid Prototyping

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

The development of new products could be a powerful engine for the success of an organization. In order to efficiently design prototypes using Additive Manufacturing techniques, it is advisable to perform Quality Assurance in real time. This can result in saving resources and increasing efficiency. However, it is important that configurations within the printable file and the calibration of 3d printer are without errors. A potential solution to avoid errors and low-quality prototypes is the use of Image Mining for a Real Time Quality Assurance of the printed prototype. As part of this paper, we developed such an Image Mining application using a design science research approach. Thereby, a supervised machine learning approach is considered to assign a quality class to the prototype in production. As a result, we identified the contribution Image Mining can make to Quality Assurance and the relationship between the accuracy of classification and the latency.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

Article
Full-text available
Additive manufacturing (AM) offers the advantage of producing complex parts more efficiently and in a lesser production cycle time as compared to conventional subtractive manufacturing processes. It also provides higher flexibility for diverse applications by facilitating the use of a variety of materials and different processing technologies. With the exceptional growth of computing capability, researchers are extensively using machine learning (ML) techniques to control the performance of every phase of AM processes, such as design, process parameters modeling, process monitoring and control, quality inspection, and validation. Also, ML methods have made it possible to develop cybermanufacturing for AM systems and thus revolutionized Industry 4.0. This paper presents the state-of-the-art applications of ML in solving numerous problems related to AM processes. We give an overview of the research trends in this domain through a systematic literature review of relevant journal articles and conference papers. We summarize recent development and existing challenges to point out the direction of future research scope. This paper can provide AM researchers and practitioners with the latest information consequential for further development.
Conference Paper
The combined use of image processing and data analytics methods and technologies is highly relevant for a high number of application scenarios. Supporting systems in healthcare or the full automation of autonomous vehicles based on this combination. Thereby, the most popular concept in this field of tension is named computer vision, but also image mining considers the combined use of image processing and data analytics. Nevertheless, there is no clear distinction between these two concepts in the current scientific discussion. This is disadvantageous since it is not to determine which concept is more beneficial under which conditions, situations and, cases. Therefore, the paper aims to clarify the concepts of computer vision and image mining and analyzes which concept is more suitable in which scenarios. To address this need, a structured literature review was done. As a result, differences between the concepts in terms of application area, process, and characteristics are identified. A clarification of the positioning of the concepts could be done. Also, the findings provide advice on which concept is beneficial under what conditions.
Article
Full-text available
Qualitative uncertainties are a key challenge for the further industrialization of additive manufacturing. To solve this challenge, methods for measuring the process states and properties of parts during additive manufacturing are essential. The subject of this review is in-situ process monitoring for material extrusion additive manufacturing. The objectives are, first, to quantify the research activity on this topic, second, to analyze the utilized technologies, and finally, to identify research gaps. Various databases were systematically searched for relevant publications and a total of 221 publications were analyzed in detail. The study demonstrated that the research activity in this field has been gaining importance. Numerous sensor technologies and analysis algorithms have been identified. Nonetheless, research gaps exist in topics such as optimized monitoring systems for industrial material extrusion facilities, inspection capabilities for additional quality characteristics, and standardization aspects. This literature review is the first to address process monitoring for material extrusion using a systematic and comprehensive approach.
Chapter
Systeme zur Defekterkennung und Qualitätssicherung in der Produktion verfolgen das Ziel, Ausschussraten zu minimieren und Qualitätsstandards einzuhalten. Die dadurch angestrebte Reduktion der Produktionskosten folgt dem übergeordneten Ziel, der Maximierung der Wertschöpfung. Zu diesem Zweck lassen sich bildbasierende- sowie analytische Methoden und Techniken kombinieren. Die Konzepte Computer Vision und Image Mining bilden hierbei die Grundlage, um aus Bilddaten einen Wissensgewinn im Hinblick auf die Produktqualität zu generieren. Im Rahmen dieses Beitrages wurde ein Design Artefakt in Form eines Prototyps zur Defekterkennung und Qualitätssicherung im Bereich der Additiven Fertigung mittels eines gestaltungsorientierten Forschungsansatzes entwickelt. Die Wissensbasis für diesen Ansatz wurde innerhalb einer strukturierten Literaturanalysen erarbeitet. Der Fokus hierbei liegt auf der Identifikation und Analyse von besagten Systemen in den verschiedenen Bereichen und Branchen der Produktion. Dabei ließen sich eine Reihe von Techniken und Methoden identifizieren, die sich in den Sektor der Additiven Fertigung übertragen und gewinnbringend einsetzen lassen. Es handelt sich dabei um Methoden aus den Bereichen der Bildaufnahme, der Vorverarbeitung sowie der algorithmischen Analyse. Es konnten zudem keine Barrieren für den Einsatz von Computer-Vision- und Image-Mining-Techniken identifiziert werden, die einen Einsatz auf bestimmte Bereiche der Produktionen und Produktionsszenarien begrenzen. Die Ergebnisse dieses Beitrags stellen somit grundlegende Erkenntnisse für die Entwicklung anwendungsbezogener Defekterkennungs- und Qualitätssicherungssysteme in verschiedenen Branchen und Bereichen der Produktion dar.
Research
Full-text available
Technology of 3D-Printer based on fused deposition material has developed intensively with varying qualities. However, default setting of printing process parameters provided by the manufacturer in some cases does not guarantee quality (dimension error and strength) of the printed part, since there are several process parameters that need to be considered. A 3DPrinter with poly-lactic acid filament material has been applied in this study. A specimen standard has been used as a tensile strength and dimension error test to represent printed part quality. Three printing process parameters: layer thickness, layer speed and infill density have been optimized using Taguchi L9 Orthogonal Array method. In a recent project, we have thus investigated possibilities to increase the printability of especially flexible filament. The presentation will give an overview of the modifications and their effect on the most frequently used elastic filaments, offering suggestions to modify common 3D FDM printers in similar ways for increased printing results with or without integrated fibres or filaments.
Article
Full-text available
Additive manufacturing is a technology rapidly expanding on a number of industrial sectors. It provides design freedom and environmental/ecological advantages. It transforms essentially design files to fully functional products. However, it is still hampered by low productivity, poor quality and uncertainty of final part mechanical properties. The root cause of undesired effects lies in the control aspects of the process. Optimization is difficult due to limited modelling approaches. Physical phenomena associated with additive manufacturing processes are complex, including melting/solidification and vaporization, heat and mass transfer etc. The goal of the current study is to map available additive manufacturing methods based on their process mechanisms, review modelling approaches based on modelling methods and identify research gaps. Later sections of the study review implications for closed-loop control of the process.
Article
Full-text available
A current challenge in additive manufacturing (commonly known as 3D printing) is the detection of defects. Detection of defects (or the lack thereof) in bespoke industrial manufacturing may be safety critical and reduce or eliminate the need for testing of printed objects. In consumer and prototype printing, early defect detection may facilitate the printer taking corrective measures (or pausing printing and alerting a user), preventing the need to re-print objects after the compounding of a small error occurs. This paper considers one approach to defect detection. It characterizes the efficacy of using a multi-camera system and image processing software to assess printing progress (thus detecting completion failure defects) and quality. The potential applications and extrapolations of this type of a system are also discussed.
Article
Full-text available
Image mining refers to a data mining technique where images are used as data. It supports a large field of applications like medical diagnosis, agriculture, industrial work, space research and obviously the educational field. The image mining technique can extract knowledge and exciting patterns which are not stored in the database by analyzing the images using various tools. The new era of advanced technology and high storage capability supports the growth of large and detailed image database. This review paper presents a detailed view on the existing research works in the area of image mining and also summarized the different techniques used in. http://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijim
Article
Full-text available
Additive manufacturing processes take the information from a computer-aided design (CAD) file that is later converted to a stereolithography (STL) file. In this process the drawing made in the CAD software is approximated by triangles and sliced containing the information of each layer that is going to be printed. There is a discussion of the relevant additive manufacturing processes and their applications. The aerospace industry employs them because of the possibility of manufacturing lighter structures to reduce weight. Additive manufacturing is transforming the practice of medicine, and making work easier for architects. In 2004, the Society of Manufacturing Engineers did a classification of the various technologies and there are at least four additional significant technologies in 2012. Studies are reviewed which were about the strength of products made in additive manufacturing processes. However there is still a lot of work and research to be accomplished before additive manufacturing technologies become standard in the manufacturing industry because not every commonly-used manufacturing material can be handled. The accuracy needs improvement to eliminate the necessity of a finishing process. The continuous and increasing growth experienced since the early days and the successful results up to the present time allow for optimism that additive manufacturing has a significant place in the future of manufacturing.
Article
Full-text available
The analysis and characterization of biomedical image data is a complex procedure involving several processing phases, like data acquisition, preprocessing, segmentation, feature extraction and classification. The proper combination and parameterization of the utilized methods are heavily relying on the given image data set and experiment type. They may thus necessitate advanced image processing and classification knowledge and skills from the side of the biomedical expert. In this work, an application, exploiting web services and applying ontological modeling, is presented, to enable the intelligent creation of image mining workflows. The described tool can be directly integrated to the Rapid-Miner, Taverna or similar workflow management platforms. A case study dealing with the creation of a sample workflow for the analysis of kidney biopsy microscopy images is presented to demonstrate the functionality of the proposed framework.
Conference Paper
Full-text available
Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Fields ranging from Commercial to Military need to analyze these data in an efficient and fast manner. Presently, tools for mining images are few and require human intervention. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a critical step in the entire scenario of Image Mining. Our approach to mine from Images - to extract patterns and derive knowledge from large collections of images, deals mainly with identification and extraction of unique features for a particular domain. Though there are various features available, the aim is to identify the best features and thereby extract relevant information from the images. We have tried various methods for extraction; the features extracted and the techniques used are evaluated for their contribution to solving the problem. Experimental results show that the features used are sufficient to identify the patterns from the Images. The extracted features were evaluated for goodness and tested on test images. An interactive system was developed which allows the user to define new features and to resolve uncertain regions.
Article
Full-text available
Digitization in every sector leads to the growth of digital data in a tremendous amount. Digital data are not only available in the form of text but it is also available in the form of images, audio andvideo. Decision making people in every field like business, public sector, hospital, etc. are trying to get useful and implicit information from the already existing digital data bases. Image mining is the concept used to extract implicit and useful data from images stored in the large data bases. Image mining is used in variety of fields like medical diagnosis, space research, remote sensing, agriculture, industries and even in the educational field. This paper elaborates the research works already done in image mining and also summarizes different tool developed, algorithms emerged and the applications of image mining used to extract the useful images in various fields.
Conference Paper
Quality management in real time enables increased efficiency of a production process. A multitude of sensors make it possible to collect a large amount of data and builds the basis for a real time fault detection in the Smart Factory. Hence, it is important that this data, the resulting information, and the knowledge generated by the algorithmic analysis is available at the right time. Therefore, appropriate network architectures such as Edge Computing are required for efficient data transfer. In this context, the paper deals with the challenges of analyzing data gathered by an image sensor in production. The consideration is based on the implementation of an Image-Mining-Application for real time error detection in production, which was developed by a design science research approach. In addition to identifying the challenges in this area, algorithms with a high accuracy of fit could be identified. Thus, the results obtained form an important basis for the use of Image-Mining-Applications in Smart Factories .
Chapter
This paper presents the analysis and comparison of existing literature relevant to various image mining process and the mechanisms associated with it. Though, the literature consists of a lot many research contributions, but, here, we have critically and exhaustively analyzed forty research and review papers. Based on the basic concepts used in their mechanisms, the existing approaches are categorized into three types, image analysis and pattern recognition related work, image mining through various approaches, and graph theory based related work in image mining. The emphasis is on the concept used by the concerned authors, the database used for experimentations and the performance evaluation parameters. The claims of the researchers are also highlighted. Our findings from the exhaustive literature review are mentioned along with the identified problems. This paper is very important for the comparative study of various image mining approaches which is prerequisite for solving image mining problem.
Article
The creation of value in a factory is transforming. The spread of sensors, embedded systems, and the development of the Internet of Things (IoT) creates a multitude of possibilities relating to upcoming Real Time Analytics (RTA) application. However, already the topic of big data had rendered the use of analytical solutions related to a processing in real time. Now, the introduced methods and concepts can be transferred into the industrial area. This paper deals with the topic of the current state of RTA having the objective to identify applied methods. In addition, the paper also includes a classification of these methods and contains an outlook for the use of them within the area of the smart factory.
Book
Additive Manufacturing (AM) technologies are developing impressively and are expected to bring about the next revolution. AM is gradually replacing traditional manufacturing methods in some applications because of its unique properties of customisability and versatility. This book provides a very comprehensive and updated text about different types of AM technologies, their respective advantages, shortcomings and potential applications. 3D Printing and Additive Manufacturing: Principles and Applications is a comprehensive textbook that takes readers inside the world of additive manufacturing. This book introduces the different types of AM technologies, categorised by liquid, solid and powder-based AM systems, the common standards, the trends in the field and many more. Easy to understand, this book is a good introduction to anyone interested in obtaining a better understanding of AM. For people working in the industry, this book will provide information on new methods and practices, as well as recent research and development in the field. For professional readers, this book provides a comprehensive guide to distinguish between the different technologies, and will help them make better decisions regarding which technology they should use. For the general public, this book sheds some light on the fast-moving AM field. In this edition, new AM standards (e.g. Standard of Terminology and Classification of AM systems) and format standards will be included, Furthermore, the listing of new machines and systems, materials, and software; as well as new case studies and applications in industries that have recently adopted AM (such as the Marine and Offshore industry) have also been incorporated. © 2017 by World Scientific Publishing Co. Pte. Ltd. All rights reserved.
Chapter
Wie können bekannte Unternehmensprozesse von neuen Technologien profitieren und neue Perspektiven geschaffen werden? Welche Vorteile ergeben sich aus der Digitalisierung von Prozessen? Diesen und anderen Fragen werden wir in diesem Kapitel nachgehen. Zunächst einmal soll ein potenzieller Informationsfluss betrachtet werden, um Einblicke in mögliche Szenarien zu erhalten, die durch neue Technologien eröffnet werden. Ziele können beispielsweise eine höhere Transparenz und Prozesszuverlässigkeit, ein besseres Verständnis von Problemursachen, Prozess(teil)automatisierungen, Prozessbeschleunigungen, höhere Agilität und Flexibilität, Kostenreduktionen, höhere Prozessrobustheit, vorhersagbarere Produktqualität, Prognose und Vermeidung von Maschinen- und Produktionsausfällen oder eine Bedarfs-, Bestellmengen und Preisprognose sein.
Conference Paper
In order for factories to stay competitive in the current open global market, there should be efforts to put on optimizing the value stream of producing goods. Within this context, Industrial Internet of Things (IIoT) has been emerged as a technology aiming at achieving high productivity performance in manufacturing. A smart manufacturing approach also requires a smart maintenance management as it plays a crucial role in securing the productivity. IIoT applications are traditionally completed by the cloud computing technology to serve the required services. In this paper, we argue that maintenance processes have requirements that cannot be accomplished by solely the cloud computing technology. We identify several of these requirements. Then, we propose a platform using the fog computing technology, as a recently raised technology in IIoT, to enhance the smart maintenance management. We also discuss the ability of the platform in fulfilling the identified requirements.
Conference Paper
The development of the Internet of Things (IoT) creates a multitude of new Real Time Analytics (RTA) application possibilities, also in the area of industry. However, already the topic of big data forced the use of analytical solutions which were processed in real time. In order to consider the possible applications of RTA, it is necessary to gather the current state of them. Thereby, the term RTA is not separable with regard to the other concepts, rather it may be viewed as the application of those analytics concepts, based on current data. The application of analytics in real time demands a clarification about analytics itself to gain an understanding of possible application scenarios. This paper introduces the term RTA and depicts related concepts
Chapter
The main postulate of the Internet of things (IoT) is that everything can be connected to the Internet, at anytime, anywhere. This means a plethora of objects (e.g. smart cameras, wearables, environmental sensors, home appliances, and vehicles) are ‘connected’ and generating massive amounts of data. The collection, integration, processing and analytics of these data enable the realisation of smart cities, infrastructures and services for enhancing the quality of life of humans. Nowadays, existing IoT architectures are highly centralised and heavily rely on transferring data processing, analytics, and decision-making processes to cloud solutions. This approach of managing and processing data at the cloud may lead to inefficiencies in terms of latency, network traffic management, computational processing, and power consumption. Furthermore, in many applications, such as health monitoring and emergency response services, which require low latency, delay caused by transferring data to the cloud and then back to the application can seriously impact their performances. The idea of allowing data processing closer to where data is generated, with techniques such as data fusion, trending of data, and some decision making, can help reduce the amount of data sent to the cloud, reducing network traffic, bandwidth and energy consumption. Also, a more agile response, closer to real-time, will be achieved, which is necessary in applications such as smart health, security and traffic control for smart cities. Therefore, this chapter presents a review of the more developed paradigms aimed to bring computational, storage and control capabilities closer to where data is generated in the IoT: fog and edge computing, contrasted with the cloud computing paradigm. Also an overview of some practical use cases is presented to exemplify each of these paradigms and their main differences.
Book
Standards, Quality Control and Measurement Sciences in 3D Printing and Additive Manufacturing addresses the critical elements of the standards and measurement sciences in 3D printing to help readers design and create safe, reliable products of high quality. With 3D printing revolutionizing the process of manufacturing in a wide range of products, the book takes key features into account, such as design and fabrication and the current state and future potentials and opportunities in the field. In addition, the book provides an in-depth analysis on the importance of standards and measurement sciences. With self-test exercises at the end of each chapter, readers can improve their ability to take up challenges and become proficient in a number of topics related to 3D printing, including software usage, materials specification and benchmarking. Helps the reader understand the quality framework tailored for 3D printing processes Explains data format and process control in 3D printing Provides an overview of different materials and characterization methods Covers benchmarking and metrology for 3D printing.
Chapter
Every product development process involving an Additive Manufacturing machine requires the operator to go through a set sequence of tasks. Easy-to-use “desktop” or “3D printing” machines emphasize the simplicity of this task sequence. These desktop machines are characterized by their low cost, simplicity of use, and ability to be placed in an office environment. For these machines each step is likely to have few options and require minimal effort. However, this also means that there are generally fewer choices, with perhaps a limited range of materials and other variables to experiment with. The larger and more versatile machines are more capable of being tuned to suit different user requirements and therefore are more difficult to operate, but with a wider variety of possible results and effects that may be put to good use by an experienced operator. Such machines also usually require more careful installation in workshop environments. This chapter will take the reader through the different stages of the process that were described in much less detail in Chap. 1. Where possible, the different steps in the process will be described with reference to different processes and machines. The objective is to allow the reader to understand how these machines may differ and also to see how each task works and how it may be exploited to the benefit of higher quality results. As mentioned before, we will refer to eight key steps in the process sequence.
Chapter
The technology described in this book was originally referred to as rapid prototyping. The term rapid prototyping (RP) is used in a variety of industries to describe a process for rapidly creating a system or part representation before final release or commercialization. In other words, the emphasis is on creating something quickly and that the output is a prototype or basis model from which further models and eventually the final product will be derived. Management consultants and software engineers both use the term rapid prototyping to describe a process of developing business and software solutions in a piecewise fashion that allows clients and other stakeholders to test ideas and provide feedback during the development process. In a product development context, the term rapid prototyping was used widely to describe technologies which created physical prototypes directly from digital data. This text is about these latter technologies, first developed for prototyping, but now used for many more purposes.
RapidMiner: Data mining use cases and business analytics applications
  • M Hofmann
  • R Klinkenberg
M. Hofmann and R. Klinkenberg, RapidMiner: Data mining use cases and business analytics applications., Boca Raton: CRC Press, 2014.
A review of additive manufacturing
  • K V Wong
  • A Hernandez
K. V. Wong and A. Hernandez, "A review of additive manufacturing," ISRN Mechanical Engineering, 2012.
Image Analysis and Image Mining Techniques: A Review
  • V R Parihar
  • R S Nage
  • A S Dahane
V. R. Parihar, R. S. Nage and A. S. Dahane, "Image Analysis and Image Mining Techniques: A Review," Journal of Image Processing and Artificial Intelligence, vol. 3, no. 2,3, 2017.
Enzyklopaedie der Wirtschaftsinformatik
  • C Felden
C. Felden, "Klassifikation, statistische Methoden. Enzyklopaedie der Wirtschaftsinformatik.," [Online]. Available: http://www.enzyklopaedie-derwirtschaftsinformatik.de/lexikon/technologien-methoden/Statistik/
Information Mining: Methoden, Algorithmen und Anwendungen intelligenter Datenanalyse
  • R Ta
R. TA, Information Mining: Methoden, Algorithmen und Anwendungen intelligenter Datenanalyse., Berlin Heidelberg: Springer, 2013.
Künstliche Intelligenz, Enzyklopaedie der Wirtschaftsinformatik
  • felden
C. Felden, "Künstliche Intelligenz, Enzyklopaedie der Wirtschaftsinformatik," 28 11 2016. [Online].
Advanced Analytics mit Big Data
  • lanquillon
C. Lanquillon and H. Mallow, "Advanced Analytics mit Big Data," in n Praxishandbuch Big Data: Wirtschaft-Recht-Technik, Gabler, Wiesbaden, 2015, pp. 55-89.
Zukunftsweisende Informations-und Kommunikations-Technologien
  • R Klinkenberg
  • P Schlunder
  • E Klapic
  • T Lacker
Klassifikation, statistische Methoden. Enzyklopaedie der Wirtschaftsinformatik
  • C Felden
  • Klassifikation
  • Statistische Methoden
Klassifikation, statistische Methoden. Enzyklopaedie der Wirtschaftsinformatik
  • felden