Industrial Big Data and Process Modelling for Smart Manufacturing

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Engineering Mathematics".

Deadline for manuscript submissions: 31 March 2024 | Viewed by 19889

Special Issue Editors

Data analytics Group, Haute Ecole Arc, University of Applied Sciences and Arts Western Switzerland, Rue de la Serre 7, 2610 St. Imier, Switzerland
Interests: artificial intelligence; machine learning; industry 4.0
Project Engineering Area, University of Oviedo C/Independencia 13, 33004 Oviedo, Spain
Interests: data science and engineering; smart manufacturing; process modeling and optimization; project management
Data analytics Group, Haute Ecole Arc, University of Applied Sciences and Arts Western Switzerland, Rue de la Serre 7, 2610 St. Imier, Switzerland
Interests: artificial intelligence; machine learning; natural language processing; industry 4.0
Institute of Informatics, Slovak Academy of Sciences, Dúbravská cesta 9, 845 07 Bratislava, Slovakia
Interests: applied informatics; discrete systems modeling and simulation; multi agent systems; artificial intelligence; ontology engineering
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Industry and manufacturing are in the process of unprecedented transformations. The goals of these transformations are to enable production with a higher yield, higher quality, lower costs, lower environmental impact and increased flexibility moving from mass production to mass personalization. The availability of big data and the recent advances in artificial intelligence and process modelling are the keys to these changes. The emergence of techniques such as deep learning and the spreading of technologies such as the Internet of Things has boosted this evolution, actively supported by new achievements in mathematics and artificial intelligence methods focused on the formalisms and algorithm development.

This Special Issue will gather a collection of articles reflecting the latest developments in artificial intelligence and smart manufacturing, including machine (deep) learning, process modelling, big data, soft computing techniques, cyber-physical systems, reinforcement learning, intelligent multi-agent systems, and others.

Contributions are welcome on both theoretical and practical models. The selection criteria consider the formal and technical soundness, experimental support, and the relevance of the contribution.

Prof. Stefano Carrino
Assoc. Prof. Vicente Rodríguez Montequín
Prof. Hatem Ghorbel
Dr. Ivana Budinská
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Industry 4.0 
  • Smart manufacturing 
  • Process modelling 
  • Process optimization 
  • Computational Intelligence 
  • Artificial intelligence 
  • (Deep) Machine learning 
  • Multi-agent systems 
  • Reinforcement learning
  • Soft Computing 
  • Nature Inspired Computing 
  • Knowledge Base 
  • Ontology 
  • Big data 
  • Cyber-physical systems
  • Internet of Things

Published Papers (9 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

25 pages, 7232 KiB  
Article
An Icon-Based Methodology for the Design of a Prototype of a Multi-Process, Multi-Product, Aggregated Production Planning Software
Mathematics 2024, 12(2), 336; https://doi.org/10.3390/math12020336 - 19 Jan 2024
Viewed by 422
Abstract
This paper proposes an icon-based methodology for the design of prototype aggregated production planning software that addresses the complexity of multi-process and multi-product production. Aggregate planning is a critical task in production management, which involves coordinating the production of multiple products in different [...] Read more.
This paper proposes an icon-based methodology for the design of prototype aggregated production planning software that addresses the complexity of multi-process and multi-product production. Aggregate planning is a critical task in production management, which involves coordinating the production of multiple products in different processes to meet demand efficiently. The approach focuses on the use of visual icons to represent key elements of the production process, such as products, processes, resources, and constraints. These icons allow an intuitive representation of information and facilitate communication between production team members. In addition, this paper presents a conceptual structure that defines the relationships between the icons and how they are used to model and simulate aggregate production planning. The prototype software based on a conceptual foundation allows planners to easily create and adjust production plans in a visual environment. This method improves the ability to make informed and rapid decisions in response to changes in demand or production capacity. The prototype is based on icons and programmed in Excel spreadsheets to facilitate the planner’s planning. At the end of the document, the application of a case study is shown. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

12 pages, 1848 KiB  
Article
Causality-Driven Efficient Feature Selection for Deep-Learning-Based Surface Roughness Prediction in Milling Machines
Mathematics 2023, 11(22), 4682; https://doi.org/10.3390/math11224682 - 17 Nov 2023
Cited by 1 | Viewed by 521
Abstract
This paper studies the application of artificial intelligence to milling machines, focusing specifically on identifying the inputs (features) required for predicting surface roughness. Previous studies have extensively reviewed and presented useful features for surface roughness prediction. However, applying research findings to actual operational [...] Read more.
This paper studies the application of artificial intelligence to milling machines, focusing specifically on identifying the inputs (features) required for predicting surface roughness. Previous studies have extensively reviewed and presented useful features for surface roughness prediction. However, applying research findings to actual operational factories can be challenging due to the additional costs of sensor installations and the diverse environments present in each factory setting. To address these issues, in this paper, we introduced effective features for predicting surface roughness in situations where additional sensors are not installed in the existing environment. These features include feed per tooth, Fz; material removal rate, Q; and the load information. These features are suitable for use in highly constrained environments where separate sensor installation is not required, making it possible to apply the research findings in various factory environments. Additionally, to efficiently select the optimal subset for surface roughness prediction among subsets formed by available features, we apply causality to the feature selection method, proposing an approach called causality-driven efficient feature selection. The experimental results demonstrate that the features introduced in this paper are quite suitable for predicting surface roughness and that the proposed feature selection approach is more effective and efficient compared to existing selection methods. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

24 pages, 4680 KiB  
Article
AdaBoost Algorithm Could Lead to Weak Results for Data with Certain Characteristics
Mathematics 2023, 11(8), 1801; https://doi.org/10.3390/math11081801 - 10 Apr 2023
Cited by 2 | Viewed by 1435
Abstract
There are many state-of-the-art algorithms presented in the literature that perform very well on some evaluation data but are not studied with the data properties on which they are applied; therefore, they could have low performance on data with other characteristics. In this [...] Read more.
There are many state-of-the-art algorithms presented in the literature that perform very well on some evaluation data but are not studied with the data properties on which they are applied; therefore, they could have low performance on data with other characteristics. In this paper, the results of comprehensive research regarding the prediction with the frequently applied AdaBoost algorithm on real-world sensor data are presented. The chosen dataset has some specific characteristics, and it contains error and failure data of several machines and their components. The research aims to investigate whether the AdaBoost algorithm has the capability of predicting failures, thus providing the necessary information for monitoring and condition-based maintenance (CBM). The dataset is analyzed, and the principal characteristics are presented. Performance evaluations of the AdaBoost algorithm that we present show a prediction capability below expectations for this algorithm. The specificity of this study is that it indicates the limitation of the AdaBoost algorithm, which could perform very well on some data, but not so well on others. Based on this research and some others that we performed, and actual research from worldwide studies, we must outline that the mathematical analysis of the data is especially important to develop or adapt algorithms to be very efficient. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

21 pages, 3230 KiB  
Article
Global Value Chains and Industry 4.0 in the Context of Lean Workplaces for Enhancing Company Performance and Its Comprehension via the Digital Readiness and Expertise of Workforce in the V4 Nations
Mathematics 2023, 11(3), 601; https://doi.org/10.3390/math11030601 - 24 Jan 2023
Cited by 27 | Viewed by 2553
Abstract
Industry 4.0 affects nearly every aspect of life by making it more technologically advanced, creative, environmentally friendly and ultimately, more interconnected. It also represents the beginning of the interconnectedness and metaverse associated with Industry 5.0. This issue is becoming decisive for advancement in [...] Read more.
Industry 4.0 affects nearly every aspect of life by making it more technologically advanced, creative, environmentally friendly and ultimately, more interconnected. It also represents the beginning of the interconnectedness and metaverse associated with Industry 5.0. This issue is becoming decisive for advancement in all areas of life, including science. The primary goal of this study is to concisely explain how current Industry 4.0 trends might interact with existing work systems in global value chains to accelerate their operational activity in the context of firms from the Visegrad Four (V4) nations. Through an examination of the digital abilities in these nations, the purpose of the study is also to demonstrate how well citizens, employees, and end users are able to comprehend the problem at hand. The most recent resources for the topics are covered in the first section of the work. The next one uses graphic analysis and mutual comparison methods, generally comparing existing data over time; it is secondary research, and through these methods the Industry 4.0 applications can significantly speed up the work process itself when compared to the traditional lean process, primarily because of its digital structure. It is difficult to predict which of the V4 will be digitally prepared, as the precedent shifts are based on distinct indicators; therefore, it is crucial that all V4 nations expand their digital adaptability dramatically each year, primarily as a result of spending on scientific research, and education that is organised appropriately. The extra value of this effort may be attributed to how lean processes are intertwined with the Industry 4.0 trend’s digital experience, which already includes the Industry 5.0 trend’s artificial intelligence and metaverse, which represent the potential for further research in the future. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

22 pages, 3938 KiB  
Article
Manufacturing Maps, a Novel Tool for Smart Factory Management Based on Petri Nets and Big Data Mini-Terms
Mathematics 2022, 10(14), 2398; https://doi.org/10.3390/math10142398 - 08 Jul 2022
Cited by 5 | Viewed by 1728
Abstract
This article defines a new concept for real-time factory management—manufacturing maps. Manufacturing maps are generated from two fundamental elements, mini-terms and Petri nets. Mini-terms are sub-times of a technical cycle, the time it takes for any component to perform its task. A mini-term, [...] Read more.
This article defines a new concept for real-time factory management—manufacturing maps. Manufacturing maps are generated from two fundamental elements, mini-terms and Petri nets. Mini-terms are sub-times of a technical cycle, the time it takes for any component to perform its task. A mini-term, by definition, is a sub-cycle time and it would only make sense to use the term in connection with production improvement. Previous studies have shown that when the sub-cycle time worsens, this indicates that something unusual is happening, enabling anticipation of line failures. As a result, a mini-term has dual functionality, since, on the one hand, it is a production parameter and, on the other, it is a sensor used for predictive maintenance. This, combined with how easy and cheap it is to extract relevant data from manufacturing lines, has resulted in the mini-term becoming a new paradigm for predictive maintenance, and, indirectly, for production analysis. Applying this parameter using big data for machines and components can enable the complete modeling of a factory using Petri nets. This article presents manufacturing maps as a hierarchical construction of Petri nets in which the lowest level network is a temporary Petri net based on mini-terms, and in which the highest level is a global view of the entire plant. The user of a manufacturing map can select intermediate levels, such as a specific production line, and perform analysis or simulation using real-time data from the mini-term database. As an example, this paper examines the modeling of the 8XY line, a multi-model welding line at the Ford factory in Almussafes (Valencia), where the lower layers are modeled until the mini-term layer is reached. The results, and a discussion of the possible applications of manufacturing maps in industry, are provided at the end of this article. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

22 pages, 10459 KiB  
Article
Holistic Fault Detection and Diagnosis System in Imbalanced, Scarce, Multi-Domain (ISMD) Data Setting for Component-Level Prognostics and Health Management (PHM)
Mathematics 2022, 10(12), 2031; https://doi.org/10.3390/math10122031 - 11 Jun 2022
Cited by 6 | Viewed by 1465
Abstract
In the current Industry 4.0 revolution, prognostics and health management (PHM) is an emerging field of research. The difficulty of obtaining data from electromechanical systems in an industrial setting increases proportionally with the scale and accessibility of the automated industry, resulting in a [...] Read more.
In the current Industry 4.0 revolution, prognostics and health management (PHM) is an emerging field of research. The difficulty of obtaining data from electromechanical systems in an industrial setting increases proportionally with the scale and accessibility of the automated industry, resulting in a less interpolated PHM system. To put it another way, the development of an accurate PHM system for each industrial system necessitates a unique dataset acquired under specified conditions. In most circumstances, obtaining this one-of-a-kind dataset is difficult, and the resulting dataset has a significant imbalance, a lack of certain useful information, and contains multi-domain knowledge. To address those issues, this paper provides a fault detection and diagnosis system that evaluates and preprocesses imbalanced, scarce, multi-domain (ISMD) data acquired from an industrial robot, utilizing signal processing (SP) techniques and deep learning-based (DL) domain knowledge transfer. The domain knowledge transfer is used to produce a synthetic dataset with a high interpolation rate that contains all the useful information about each domain. For domain knowledge transfer and data generation, continuous wavelet transform (CWT) with a generative adversarial network (GAN) was used, as well as a convolutional neural network (CNN), to test the suggested methodology using transfer learning and categorize several faults. The proposed methodology was tested on a real experimental bench that included an industrial robot created by Hyundai Robotics. This test had a satisfactory outcome with a 99.7% (highest) classification accuracy achieved by transfer learning on several CNN benchmark models. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

23 pages, 5252 KiB  
Article
A Sustainable Methodology Using Lean and Smart Manufacturing for the Cleaner Production of Shop Floor Management in Industry 4.0
Mathematics 2022, 10(3), 347; https://doi.org/10.3390/math10030347 - 24 Jan 2022
Cited by 36 | Viewed by 6267
Abstract
The production management system in Industry 4.0 is emphasizes the improvement of productivity within limited constraints by sustainable production planning models. To accomplish this, several approaches are used which include lean manufacturing, kaizen, smart manufacturing, flexible manufacturing systems, cyber–physical systems, artificial intelligence, and [...] Read more.
The production management system in Industry 4.0 is emphasizes the improvement of productivity within limited constraints by sustainable production planning models. To accomplish this, several approaches are used which include lean manufacturing, kaizen, smart manufacturing, flexible manufacturing systems, cyber–physical systems, artificial intelligence, and the industrial Internet of Things in the present scenario. These approaches are used for operations management in industries, and specifically productivity maximization with cleaner shop floor environmental management, and issues such as worker safety and product quality. The present research aimed to develop a methodology for cleaner production management using lean and smart manufacturing in industry 4.0. The developed methodology would able to enhance productivity within restricted resources in the production system. The developed methodology was validated by production enhancement achieved in two case study investigations within the automobile manufacturing industry and a mining machinery assembly unit. The results reveal that the developed methodology could provide a sustainable production system and problem-solving that are key to controlling production shop floor management in the context of industry 4.0. It is also capable of enhancing the productivity level within limited constraints. The novelty of the present research lies in the fact that this type of methodology, which has been developed for the first time, helps the industry individual to enhance production in Industry 4.0 within confined assets by the elimination of several problems encountered in shop floor management. Therefore, the authors of the present study strongly believe that the developed methodology would be beneficial for industry individuals to enhance shop floor management within constraints in industry 4.0. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

25 pages, 1538 KiB  
Article
Automatic Path Planning Offloading Mechanism in Edge-Enabled Environments
Mathematics 2021, 9(23), 3117; https://doi.org/10.3390/math9233117 - 03 Dec 2021
Cited by 3 | Viewed by 1621
Abstract
The utilization of edge-enabled cloud computing in unmanned aerial vehicles has facilitated advances in autonomous control by employing computationally intensive algorithms frequently related to traversal among different locations in an environment. A significant problem remains in designing an effective strategy to offload tasks [...] Read more.
The utilization of edge-enabled cloud computing in unmanned aerial vehicles has facilitated advances in autonomous control by employing computationally intensive algorithms frequently related to traversal among different locations in an environment. A significant problem remains in designing an effective strategy to offload tasks from the edge to the cloud. This work focuses on creating such a strategy by employing a network evaluation method built on the mean opinion score metrics in concoction with machine learning algorithms for path length prediction to assess computational complexity and classification models to perform an offloading decision on the data provided by both network metrics and solution depth prediction. The proposed system is applied to the A* path planning algorithm, and the presented results demonstrate up to 94% accuracy in offloading decisions. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

31 pages, 4807 KiB  
Article
Distributed Mechanism for Detecting Average Consensus with Maximum-Degree Weights in Bipartite Regular Graphs
Mathematics 2021, 9(23), 3020; https://doi.org/10.3390/math9233020 - 25 Nov 2021
Cited by 12 | Viewed by 2222
Abstract
In recent decades, distributed consensus-based algorithms for data aggregation have been gaining in importance in wireless sensor networks since their implementation as a complementary mechanism can ensure sensor-measured values with high reliability and optimized energy consumption in spite of imprecise sensor readings. In [...] Read more.
In recent decades, distributed consensus-based algorithms for data aggregation have been gaining in importance in wireless sensor networks since their implementation as a complementary mechanism can ensure sensor-measured values with high reliability and optimized energy consumption in spite of imprecise sensor readings. In the presented article, we address the average consensus algorithm over bipartite regular graphs, where the application of the maximum-degree weights causes the divergence of the algorithm. We provide a spectral analysis of the algorithm, propose a distributed mechanism to detect whether a graph is bipartite regular, and identify how to reconfigure the algorithm so that the convergence of the average consensus algorithm is guaranteed over bipartite regular graphs. More specifically, we identify in the article that only the largest and the smallest eigenvalues of the weight matrix are located on the unit circle; the sum of all the inner states is preserved at each iteration despite the algorithm divergence; and the inner states oscillate between two values close to the arithmetic means determined by the initial inner states from each disjoint subset. The proposed mechanism utilizes the first-order forward and backward finite-difference of the inner states (more specifically, five conditions are proposed) to detect whether a graph is bipartite regular or not. Subsequently, the mixing parameter of the algorithm can be reconfigured the way it is identified in this study whereby the convergence of the algorithm is ensured in bipartite regular graphs. In the experimental part, we tested our mechanism over randomly generated bipartite regular graphs, random graphs, and random geometric graphs with various parameters, thereby identifying its very high detection rate and proving that the algorithm can estimate the arithmetic mean with high precision (like in error-free scenarios) after the suggested reconfiguration. Full article
(This article belongs to the Special Issue Industrial Big Data and Process Modelling for Smart Manufacturing)
Show Figures

Figure 1

Back to TopTop