IN4PL 2022 Abstracts

Area 1 - Industry 4.0

Full Papers

Paper Nr:	1
Title:	Rediscovering the Forgotten Field of Industrial Applications in Information Systems Research: A Literature Review of Industry 4.0
Authors:	John O’Sullivan, Brian O’Flaherty and Tom O’Kane
Abstract:	This paper is a literature review to determine if industrial applications are appropriately represented in information systems (IS) scholarship. The field of Industry 4.0 was used as a representative sample of industrial information systems and the Association for Information Systems (AIS) Senior Scholars’ Basket of Journals was used as a representative, albeit highly ranked, sample of IS literature. Keywords representing the eleven recognised technologies of Industry 4.0 were chosen and used to search the eight IS journals over a time period corresponding with the lifecycle of Industry 4.0. This resulted in 1305 papers being discovered. After calibrating the search terms, a second search yielded 770 papers. These papers were screened for relevance to Industry 4.0 and for use of a manufacturing application. The resulting 20 papers were queried in detail to establish the concepts used and a concept centric matrix was produced. The analysis shows that industrial information applications are rarely used to undertake IS research in the academic field. The dominant concept revealed was digital transformation resulting in changes to business processes. The contribution to the literature is to highlight that substantial research studies can be conducted in the industrial manufacturing arena, but very few have been conducted in the last decade. Therefore, it is an area worth exploring for future IS research.
Download

Paper Nr:	2
Title:	New Benchmarks and Optimization Model for the Storage Location Assignment Problem
Authors:	Johan Oxenstierna, Jacek Malec and Volker Krueger
Abstract:	The Storage Location Assignment Problem (SLAP) is of primary significance to warehouse operations since the cost of order-picking is strongly related to where and how far vehicles have to travel. Unfortunately, a generalized model of the SLAP, including various warehouse layouts, order-picking methodologies and constraints, poses a highly intractable problem. Proposed optimization methods for the SLAP tend to be designed for specific scenarios and there exists no standard benchmark dataset format. We propose new SLAP benchmark instances on a TSPLIB format and show how they can be efficiently optimized using an Order Batching Problem (OBP) optimizer, Single Batch Iterated (SBI), with a Quadratic Assignment Problem (QAP) surrogate model (QAP-SBI). In experiments we find that the QAP surrogate model demonstrates a sufficiently strong predictive power while being 50-122 times faster than SBI. We conclude that a QAP surrogate model can be successfully utilized to increase computational efficiency. Further work is needed to tune hyperparameters in QAP-SBI and to incorporate capability to handle more SLAP scenarios.
Download

Paper Nr:	4
Title:	Root Cause Classification of Temperature-related Failure Modes in a Hot Strip Mill
Authors:	Samuel Latham and Cinzia Giannetti
Abstract:	Data is one of the most valuable assets a manufacturing company can possess. Historical data in particular has much potential for use in automated data-driven decision-making which can result in more efficient and sustainable processes. Although the technology and research behind data-driven systems for Root Cause Analysis has developed vastly over decades, their use for real time automated detection of root causes within steel manufacturing has been limited. Typically, root cause analysis still involves a lot of human interaction both in the pre-processing and data analysis phases, which can lead to variability in results and cause delay when devising corrective actions. In this paper, an application for automated Root Cause Analysis in an Hot Strip Mill is proposed for the purpose of demonstrating the effectiveness of such an approach against a manual approach. The proposed approach classifies temperature defects of steel strip Width Pull using a variety of machine learning algorithms in conjunction with k-fold cross validation.
Download

Paper Nr:	7
Title:	TMRobot Series Toolbox: Interfacing Collaborative Robots with MATLAB
Authors:	João L. Pereira, Mauro Queirós, Nuno M. C. da Costa, S. Marcelino, José Meireles, Jaime C. Fonseca, António J. Moreira and João Borges
Abstract:	As collaborative robots rise in popularity in industrial and domestic environments, TECHMAN Robot developed the TMRobot series, a wide variety of smart, safe, and straightforward collaborative robots. This paper presents the TMRobot Series Toolbox, which contains functions and methods to interface with the TMRobot series cobots from an external device using MATLAB. By using these, the users have access to connection, kinematic, point motion, set, get, and simulation functionalities which run on a remote computer connected to the TMRobot controller via TCP/IP protocols. The toolbox is then validated with some application examples.
Download

Paper Nr:	8
Title:	Human-Robot Collaboration (HRC) with Vision Inspection for PCB Assembly
Authors:	Mauro Queirós, João L. Pereira, Nuno M. C. da Costa, S. Marcelino, José Meireles, Jaime C. Fonseca, António J. Moreira and João Borges
Abstract:	Flexibility and speed in the development of new industrial machines are essential factors for the success of capital goods industries. When assembling a printed circuit board (PCB), since all the components are surface-mounted devices (SMD), the whole process is automatic. However, in many PCBs, it is necessary to place components that are not SMDs, called pin through-hole components (PTH), having to be inserted manually, which leads to delays in the production line. This work proposes and validates a prototype work cell based on a collaborative robot and vision systems whose objective is to insert these components in a completely autonomous or semi-autonomous way. Different tests were made to validate this work cell, showing the correct implementation and the possibility of replacing the human worker on this PCB assembly task.
Download

Paper Nr:	9
Title:	Determing the Decentrality of Production Processes Due to Analysis of Their Communication Structure
Authors:	Hanna Theuer
Abstract:	This paper motivates the benefits of the analysis of the communication structure for process improvement. Therefore first, the paper presents a three-stage model for determining the decentralization of production processes. This is based on the analysis of the communication and decision structure of the process’ actors. In addition, it presents a way of visualizing communication relationships. To conclude, this paper presents a practical example and the results of a simulation study. It depicts the advantages of analyzing the communication structure.
Download

Paper Nr:	11
Title:	Industrial Controls and Asset Administration Shells: An Approach to the Synchronization of Plant Segments
Authors:	Stephan Schäfer, Dirk Schöttke, Thomas Kämpfe, Oliver Lachmann, Aaron Zielstorff and Bernd Tauber
Abstract:	The complexity of modular production plants is constantly increasing due to flexible functionalities. The need to be able to flexibly adjust processes to product requirements is thus becoming more relevant. Therefore, limiting production plants to their processes is no longer up-to-date and a division of processes into single, atomic capabilities, which are represented by a Asset Administration Shell (AAS), has proven to be useful. This article deals with the synchronization of individual capabilities at the field level via the use of the PackML State Machine. An approach is presented how individual capabilities can be combined into a composite capability using a higher-level state machine. This approach is similar to the group or control component presented in BaSyx. To be able to represent the data in the AAS, the PackML does not offer a direct interface. This is created via a template in the control layer to be able to represent data in the AAS. This allows the AAS to read data in one structure and independently manipulate parameters in another structure in a non-real-time manner.
Download

Paper Nr:	15
Title:	Machine Learning based Predictive Maintenance in Manufacturing Industry
Authors:	Nadeem Iftikhar, Yi-Chen Lin and Finn E. Nordbjerg
Abstract:	Predictive maintenance normally uses machine learning to learn from existing data to find patterns that can assist in predicting equipment failures in advance. Predictive maintenance maximizes equipment’s lifespan by monitoring its condition thus reducing unplanned downtime and repair cost while increasing efficiency and overall productive capacity. This paper first presents the machine learning based methods to predict unplanned failures before they occur. Afterwards, to confront the everlasting downtime problem, it discusses anomaly detection in greater detail. It also explains the selection criteria of these methods. In addition, the techniques presented in this paper have been tested by using well-known data-sets with promising results.
Download

Paper Nr:	16
Title:	Automatic Feature Extraction for Bearings’ Degradation Assessment using Minimally Pre-processed Time series and Multi-modal Feature Learning
Authors:	Antonio L. Alfeo, Mario A. Cimino and Guido Gagliardi
Abstract:	Maintenance activities can be better planned by employing machine learning technologies to monitor an asset’s health conditions. However, the variety of observable measures (e.g. temperature, vibration) and behaviours characterizing the health degradation process results in time-consuming manual feature extraction to ensure accurate degradation stage recognitions. Indeed, approaches able to provide automatic feature extraction from multiple and heterogeneous sources are more and more required in the field of predictive maintenance. This issue can be addressed in a data-driven fashion by using feature learning technology, enabling the transformation of minimally processed time series into informative features. Given its capability of discovering meaningful patterns in data while enabling data fusion, many feature learning approaches are based on deep learning technology (e.g. autoencoders). In this work, an architecture based on autoencoders is used to automatically extract degradation-representative features from minimally preprocessed time series of vibration and temperature data. Different autoencoder architectures are implemented to compare different data fusion strategies. The proposed approach is tested considering both the recognition performances and the quality of the learned features with a publicly available real-world dataset about bearings’ progressive degradation. The proposed approach is also compared against manual feature extraction and the state-of-the-art technology in feature learning.
Download

Short Papers

Paper Nr:	3
Title:	MLP-Supported Mathematical Optimization of Simulation Models: Investigation into the Approximation of Black Box Functions of Any Simulation Model with MLPs with the Aim of Functional Analysis
Authors:	Bastian Stollfuss and Michael Bacher
Abstract:	This paper contains results from a feasibility study. The optimization of manufacturing processes is an elementary part of economic thinking and acting. In many cases, complex processes have unknown analytical and mathematical methods. If mathematical functions for the behaviour of a process are missing, one often tries to optimize the process according to the trial-and-error principle in combination with expertise. However, this method requires a lot of time, computational resources, and trained personnel to validate the results. The method developed below can significantly reduce these cost factors by mathematically optimizing the unknown functions of a complex system in an automatic process. This is accomplished with discrete performance and behaviour measurements. For this purpose, an approximate prediction function is modelled using a multi-layer perceptron (MLP). The resulting continuous function can now be analysed with mathematical optimization methods. After formulating the learned prediction function, it is examined for minima using Newton’s method. It is not necessary to know the exact mathematical and physical context of the system that needs improving. Calculating a precise interpolation also results in further optimization and visualization options for the production plant.
Download

Paper Nr:	6
Title:	Product Configuration Automation: Digital Transformation Platform and Case Study
Authors:	Alexander Smirnov, Alexey Kashevnik, Nikolay Shilov, Nikolay Teslya, Mikhail Petrov, Mario Sinko, Jens Arneving, Michael Humpf and Thorsten Kolmer
Abstract:	The paper discusses more than 10-year experience in product configuration automation based on number of joint projects between an academic institution and an industrial partner. During the last years, the research and development in the era of digital transformation has enabled a shift from conventional company business processes to digital business processes. In the paper we present several business processes that have been successfully automated what in turn has significantly decreased the product configuration time as well as errors caused by the human factor. The following business processes are covered: identcode (product code) related procurement, product segmentation, delivery class specification, supply chain & production management; online & offline sales, and customer guidance. We present the developed platform to support these business processes that consists of 10 workflows. We have integrated the developed workflows to the company production processes and show that business process execution time in average has decreased by 2 times and for some processes by more than 10 times. At the moment, the developed platform is being successfully used by the company.
Download

Paper Nr:	10
Title:	Speed, the Double-edged Sword of the Industry 4.0
Authors:	Marion Toussaint, Sylvere Krima, Allison B. Feeney and Herve Panetto
Abstract:	The recent and ongoing digital transformation of the manufacturing world has led to numerous benefits, from higher quality products to increased productivity and reduced time to market. In this digital world, data has become a critical element in many essential decisions and processes within and across organizations. Data exchange is now a key process for the organizations’ communication, collaboration, and efficiency. Industry 4.0/Industry of the Future adoption of modern communication technologies has made data available and shareable at a speed faster than we can consume or track it. This speed is a double edge sword and comes with key challenges, such as data interoperability and data traceability, which manufacturers need to understand in order to adopt the best mitigation strategies. This paper is a summarized introduction to these challenges, their origins, and what they mean to manufacturers.
Download

Paper Nr:	14
Title:	Knowledge Extraction in Cyber-Physical Systems Meta-models: A Formal Concept Analysis Application
Authors:	Yasamin Eslami, Sahand Ashouri, Chiara Franciosi and Mario Lezoche
Abstract:	Industry 4.0, also known as the “Fourth Industrial Revolution”, “smart manufacturing”, “industrial internet” or “Factory of the Future” is a trend and highly discussed topic nowadays. Therefore, this topic drew attention to research and practice and opened many doors to shed light on the future path of engineering approaches. Cyber-Physical Systems (CPSs) play an important role as one of the core components in the industry 4.0 approach, as they connect the physical objects in production systems to the virtual ones. Indeed, CPSs are the main sources in Industry 4.0 through which data can be transformed into information and consequently extracted as knowledge. To be able to derive the required knowledge from the transformed information, it is essential to excavate the concept of CPS and associate its characteristics by which the system is identified. However, the current literature lacks a systematic study which analyses the characteristics of CPSs and the relationships among them. And so forth, this study will focus on CPS meta-models and their characteristics. Formal Concept Analysis (FCA), as a clustering technique, will be used to investigate any hypothetical relationship among the characteristics.
Download

Paper Nr:	17
Title:	Condition based Maintenance on Data Streams in Industry 4.0
Authors:	Nadeem Iftikhar and Adrian M. Dohot
Abstract:	An asset failure is costly for the manufacturing industry as it causes unplanned downtime. Unplanned downtime halts production lines, and can lead to productivity loss. One of the widely used methods to reduce downtime is to make use of condition based maintenance. The goal of condition based maintenance is to monitor as well as detect present and/or upcoming asset failures and thus reduce unplanned downtime. A newly emerged phenomena is to monitor the asset condition at real-time. Thus, this paper presents the techniques to process data-in-motion in order to monitor the health and condition of industrial assets in real-time. The techniques presented in this paper require no historical and/or labeled data and work well on streaming data.
Download

Paper Nr:	18
Title:	Edge Containerized Architecture for Manufacturing Process Time Series Data Monitoring and Visualization
Authors:	Ander Garcia, Xabier Oregui, Javier Franco and Unai Arrieta
Abstract:	Pushed by the Industry 4.0 paradigm, the volume of data being captured from manufacturing lines is continuously increasing. To get a deeper insight of manufacturing processes, time series data from key variables of the processes has to be captured, monitored and visualized. This implies that more data variables must be monitored and data must be captured at a higher frequency: from one value of a few key variables to values of several variables captured at frequencies of seconds. Traditional Manufacturing Execution Systems (MES) were not designed for this scenario and cannot cope with these requirements. Thus, new architectures and tools are required to merge Information Technology (IT) and Operation Technology (OT) fields. This paper proposes a lightweight architecture based on micro-services and time series data requirements to connect to manufacturing process controllers, and to capture, store, monitor and visualize relevant data about the process. Moreover, a reference implementation based on Open Source tools is presented and validated.
Download

Paper Nr:	20
Title:	Impacts of Industry 4.0 Technologies on Supply Chain Resilience
Authors:	Saeed Albeetar, Concetta Semeraro and Giovanni F. Massari
Abstract:	Disruptions in the supply chain are among the most dangerous events. Supply chains increasingly face a turbulent environment characterized by unpredictable disruptions that threaten the stability of industrial operations. Most companies face challenges in their supply chains. Resilience will help organizations transform and adapt their business to dynamic environments and recover quickly from difficulties and toughness. Recent technological progress, primarily Industry 4.0 (I4.0) technologies, indicates promising possibilities to mitigate supply chain risk. This paper will study the impact of Industry 4.0 technologies on supply chain resilience.
Download

Paper Nr:	21
Title:	Is MLOps different in Industry 4.0? General and Specific Challenges
Authors:	Leonhard Faubel, Klaus Schmid and Holger Eichelberger
Abstract:	An important part of the Industry 4.0 vision is the use of machine learning (ML) techniques to create novel capabilities and flexibility in industrial production processes. Currently, there is a strong emphasis on MLOps as an enabling collection of practices, techniques, and tools to integrate ML into industrial practice. However, while MLOps is often discussed in the context of pure software systems, Industry 4.0 systems received much less attention. So far, there is no specialized research for Industry 4.0 in this regard. In this position paper, we discuss whether MLOps in Industry 4.0 leads to significantly different challenges compared to typical Internet systems. We identify both context-independent MLOps challenges (general challenges) as well as challenges particular to Industry 4.0 (specific challenges) and conclude that MLOps works very similarly in Industry 4.0 systems to pure software systems. This indicates that existing tools and approaches are also mostly suited for the Industry 4.0 context.
Download

Paper Nr:	22
Title:	Digital Twin Architecture of a Cyber-physical Assembly Transfer System
Authors:	Matteo De Marchi, Rafael A. Rojas, Benedikt G. Mark, Tanel Aruväli, Erwin Rauch and Dominik T. Matt
Abstract:	In recent years, the introduction of Internet of Things ready devices set new standards in the exploitation of Industry 4.0 related concepts. The growing complexity of Cyber-Physical Systems makes industrial machinery to be more connected, interoperable, and controllable. Hereby, topics such as edge/cloud computing, cyber security, and sustainability are gaining considerable importance. In this scenario, the Digital Twin paradigm aims at establishing a safe and seamless integrated data flow from the physical world to the virtual one and vice versa, ensuring a constant optimization of the system and its real-time monitoring. This work aims to design and implement a DT architecture for a cyber-physical intelligent manufacturing line. The implementation of a DT node for a flexible transfer line allows users to simply interface it with other systems, such as collaborative and traditional industrial robots as well as to enable the smart routing and tracing of shuttles. The development of the technological demonstrator has been conducted at the Smart Mini Factory laboratory of the Free University of Bolzano.
Download

Paper Nr:	23
Title:	Application of an Industry 4.0 Assessment Model: A Case Study Application in Material Supply for Assembly
Authors:	Matthias Horvath, Matteo De Marchi, Erwin Rauch and Dominik T. Matt
Abstract:	Material supply in production companies is currently facing numerous challenges. This paper therefore pursues the goal of analysing the potential of single Industry 4.0 concepts for the further development and efficiency optimization of material supply in assembly in an industrial case study. The determination of potentials in the context of the individual case study at an internationally active rail vehicle manufacturer is done by using a maturity level based Industry 4.0 assessment. Subsequent semi-structured interviews have been conducted to further explore the potential and feasibility of the identified Industry 4.0 measures for optimizing efficiency of material supply in assembly. This study represents an application oriented research for validation of a previously developed Industry 4.0 assessment model.
Download

Paper Nr:	24
Title:	Expert-based Classification of Worker Assistance Systems in Manufacturing Considering the Human
Authors:	Benedikt G. Mark, Matteo De Marchi, Erwin Rauch and Dominik T. Matt
Abstract:	The transformation process of manufacturing industry into a more digitalized world is a key challenge of the fourth industrial revolution. Advantages of new technologies must be used effectively, and therefore employees need to be prepared to deal with these new technologies and the complexity and speed that today’s production entails. Worker assistance systems offer the possibility to simplify the interaction between humans and complex machines and to reinforce physical and cognitive skills of employees. Although worker assistance systems are available on the market, methods focusing on the classification of appropriate worker assistance systems for specific work tasks and worker types are missing. This work presents an expert-based classification of worker assistance systems in manufacturing based on classification attributes and capabilities.
Download