An approach for composing predictive models from disparate knowledge sources in smart manufacturing environments

Published on Apr 1, 2019in Journal of Intelligent Manufacturing4.311
· DOI :10.1007/S10845-017-1366-7
Duck Bong Kim11
Estimated H-index: 11
(Tennessee Technological University)
This paper describes an approach that can compose predictive models from disparate knowledge sources in smart manufacturing environments. The capability to compose disparate models of individual manufacturing components with disparate knowledge sources is necessary in manufacturing industry, because this capability enables us to understand, monitor, analyze, optimize, and control the performance of the system made up of those components. It is based on the assumption that the component models and component sources used in any particular composition can be represented using the same collection of system ‘viewpoints’. With this assumption, creating this integrated collection is much easier than it would be. This composition capability provides the foundation for the ability to predict the performance of the system from the performances of its components—called compositionality. Compositionality is the key to solve decision-making/optimization problems related to that system-level prediction. For those problems, compositionality can be achieved using a three-tiered, abstraction architecture. The feasibility of this approach is demonstrated in an example in which a multi-criteria decision making method is used to determine the optimal process parameters in an additive manufacturing process.
📖 Papers frequently viewed together
3 Authors (Rene Lindorfer, ..., Georg Schwarz)
5 Citations
#1Katarzyna Rudnik (Opole University of Technology)H-Index: 4
#2Dariusz Kacprzak (Bialystok University of Technology)H-Index: 7
Display Omitted A MCDM method as the extension of the fuzzy TOPSIS (FTOPSIS) is described.An approach uses ordered fuzzy numbers (OFNs).Orientations of fuzzy numbers distinguish the type of criteria (benefit, cost).Flow controller in a manufacturing system is presented as application of the method.A simulation of a manufacturing system model and comparison of other methods are presented. The aim of the paper is to present a practical solution to a particular real-life problem of discrete flow co...
43 CitationsSource
#1Parag Sen (NIT DGP: National Institute of Technology, Durgapur)H-Index: 3
#2Mousumi Roy (NIT DGP: National Institute of Technology, Durgapur)H-Index: 12
Last. Parimal Pal (NIT DGP: National Institute of Technology, Durgapur)H-Index: 27
view all 3 authors...
Abstract Environmental management, being an important component in strategies for achieving sustainable development of processes and products, has emerged as a proactive approach in majority of the manufacturing organizations. From the strategic perspective environmentally conscious manufacturing (ECM) programs lead to better environmental management practice. The objective of the current paper is to present an integrated and holistic framework to evaluate ECM programs. This framework combines t...
10 CitationsSource
#1Gary W. AndersonH-Index: 1
16 CitationsSource
#1Michael P. GallaherH-Index: 10
#2Zachary T. OliverH-Index: 3
Last. Alan C. O'ConnorH-Index: 9
view all 4 authors...
6 CitationsSource
#1Peter Denno (NIST: National Institute of Standards and Technology)H-Index: 9
#2Duck Bong Kim (NIST: National Institute of Standards and Technology)H-Index: 11
This paper investigates the potential advantages and difficulties of integrating predictive model equations in models of unit manufacturing processes. The method described uses metamodels and semantic web technology to relate equations, as objects, to downstream activities. The potential advantages of this include enhanced knowledge refinement and reuse, traceability, model verification and agility in production activities. In an example usage, the authors apply the method to the development and...
6 CitationsSource
#1Miloš Madić (University of Niš)H-Index: 12
#2Jurgita Antucheviciene (VGTU: Vilnius Gediminas Technical University)H-Index: 27
Last. Dušan Petković (University of Niš)H-Index: 8
view all 4 authors...
Determination of the most suitable manufacturing process conditions for a given application is very complex task and requires consideration of a number of conflicting and diverse process performance characteristics (criteria). In this paper the application of a recent multi-criteria decision making (MCDM) method, i.e. weighted aggregated sum product assessment (WASPAS) for determination of manufacturing process conditions in laser cutting was discussed. Laser cutting experiment was conducted bas...
18 CitationsSource
#1Duck Bong Kim (NIST: National Institute of Standards and Technology)H-Index: 11
#2Peter Denno (NIST: National Institute of Standards and Technology)H-Index: 9
Last. Albert Jones (NIST: National Institute of Standards and Technology)H-Index: 20
view all 3 authors...
This article describes a model-based approach for defining and refining process parameters in dynamically changing, smart manufacturing environments. This approach uses equation-based models to predict how part quality will respond to changes in that environment. The results from these models provide the major inputs into a process-parameter-optimization technique, which is used to set the values for various process parameters. In developing these models, we integrated various concepts from proc...
8 CitationsSource
Dec 1, 2014 in IEEM (Industrial Engineering and Engineering Management)
#1Fadi Shrouf (Polytechnic University of Milan)H-Index: 6
#2J. Ordieres (UPM: Technical University of Madrid)H-Index: 1
Last. Giovanni Miragliotta (Polytechnic University of Milan)H-Index: 13
view all 3 authors...
The real and the virtual worlds are growing speedily and closely to form the Internet of Things (IoT). In fact, IoT has stimulated the factories and the governments to launch an evolutionary journey toward the fourth industrial revolution called Industry 4.0. Industrial production of the new era will be highly flexible in production volume and customization, extensive integration between customers, companies, and suppliers, and above all sustainable. Reviewing and analyzing the current initiativ...
399 CitationsSource
#1Douglas Eddy (UMass: University of Massachusetts Amherst)H-Index: 7
#2Sundar Krishnamurty (UMass: University of Massachusetts Amherst)H-Index: 19
Last. Kemper Lewis (UB: University at Buffalo)H-Index: 30
view all 5 authors...
A sustainable solution should holistically optimize all objectives related to the environment and a product’s cost and performance. As such, it should explicitly address material selection, which significantly affects environmental impacts and other objectives of a product design. While Life Cycle Assessment (LCA) provides credible methods to account for environmental impacts, current methods are not efficient enough for use at the early design stages to prune the entire design space without req...
4 CitationsSource
#1Yusri Yusof (UTHM: Universiti Tun Hussein Onn Malaysia)H-Index: 11
#2Kamran Latif (UTHM: Universiti Tun Hussein Onn Malaysia)H-Index: 7
Computer-aided process planning (CAPP) is the application of the computer to assist process planners in the planning functions. It is considered as the key technology for computer-aided design (CAD) and computer-aided manufacturing (CAM) integration. Nowadays, due to dynamic market and business globalization, CAPP research faces new challenges. In this article, an attempt is made to provide a comprehensive survey on CAPP based on features, knowledge, artificial neural networks, genetic algorithm...
79 CitationsSource
Cited By9
#1Xianyu Zhang (SJTU: Shanghai Jiao Tong University)H-Index: 11
#2Xinguo Ming (SJTU: Shanghai Jiao Tong University)H-Index: 25
Various countries in the world have issued policies on smart manufacturing and put forward relevant system architecture, including its hierarchy and component elements. However, from the perspective of implementation, it is necessary to further expand and study the relationship between the elements of the framework and the specific application scenarios. The focus of this study is to plan the specific implementation schemes from top-level planning for industrial practice in smart manufacturing o...
#1Chuan Sun (HNU: Huanggang Normal University)H-Index: 1
#1Chuan Sun (THU: Tsinghua University)H-Index: 2
Last. Tingxuan XuH-Index: 1
view all 8 authors...
As the complex driving scenarios bring about an opportunity for application of deep learning in safe driving, artificial intelligence based on deep learning has become a heatedly discussed topic in the field of advanced driving assistance system. This paper focuses on analysing vehicle active safety control of collision avoidance for intelligent connected vehicles (ICVs) in a real driving risk scenario, and driving risk perception is based on the ICV technology. In this way, trajectories of surr...
3 CitationsSource
2 CitationsSource
#1Wo Jae Lee (Purdue University)H-Index: 5
#2Kevin Xia (Purdue University)H-Index: 2
Last. John W. Sutherland (Purdue University)H-Index: 53
view all 5 authors...
The application of cutting-edge technologies such as AI, smart sensors, and IoT in factories is revolutionizing the manufacturing industry. This emerging trend, so called smart manufacturing, is a collection of various technologies that support decision-making in real-time in the presence of changing conditions in manufacturing activities; this may advance manufacturing competitiveness and sustainability. As a factory becomes highly automated, physical asset management comes to be a critical par...
6 CitationsSource
Due to the complexity of and variations in additive manufacturing (AM) processes, there is a level of uncertainty that creates critical issues in quality assurance (QA), which must be addressed by time-consuming and cost-intensive tasks. This deteriorates the process repeatability, reliability and part reproducibility. So far, many AM efforts have been performed in an isolated and scattered way over several decades. In this paper, a systematically integrated holistic view is proposed to achieve ...
#1Soonjo Kwon (KAIST)H-Index: 2
#1Soonjo Kwon (KAIST)H-Index: 2
Last. William Z. Bernstein (NIST: National Institute of Standards and Technology)H-Index: 15
view all 4 authors...
Abstract Realizing the digital thread is essential for linking and orchestrating data across the product lifecycle in smart manufacturing. Linking heterogeneous lifecycle data is critical to maintain associativity and traceability in a digital thread. Recently, researchers have successfully leveraged ontology models with knowledge graphs in engineering domains for threading different lifecycle data. One of the most successful of such efforts is OntoSTEP which enables the formal capture of inform...
7 CitationsSource
#1Andrea DíazH-Index: 1
#2Simón FernándezH-Index: 1
Last. Eleazar Díaz (Pontificia Universidad Católica del Ecuador)H-Index: 1
view all 4 authors...
This paper explores the feasibility of predicting manufacturing costs of a product with nonparametric methods through data mining. A dataset consisting of qualitative and quantitative attributes was collected from one of the largest menswear manufacturers in North America. Products with similar characteristics in this dataset were analyzed and clustered together using the k-medoids algorithm and a cost estimation regression model was established for each cluster. This allowed an assessment of th...
1 CitationsSource
#1Liane Mahlmann Kipper (UNISC: Universidade de Santa Cruz do Sul)H-Index: 8
#2Leonardo Bertolin Furstenau (UNISC: Universidade de Santa Cruz do Sul)H-Index: 1
Last. Sandra Elisia Lemões Iepsen (UNISC: Universidade de Santa Cruz do Sul)H-Index: 2
view all 5 authors...
Research in industry 4.0 is growing, driven by the innovations in production systems on a continuous basis. In this study, we identified the evolution of themes inherent in the industry 4.0 using a...
40 CitationsSource
#1Alfredo Cuzzocrea (University of Calabria)H-Index: 40
This paper focuses on big data management and analytics in intelligent smart environments, with particular regards to intelligent transportation and logistics systems, and provides relevant research directions that may represent a milestone for future years.