Refine
Year of publication
Document Type
- Conference Proceeding (106)
- Part of a Book (13)
- Contribution to a Periodical (5)
- Article (3)
- Lecture (2)
Language
- English (129) (remove)
Is part of the Bibliography
- no (129)
Keywords
- 02 (11)
- 03 (10)
- 04 (1)
- 5G (2)
- AI (2)
- APMS (1)
- APS (1)
- Adaptability (1)
- Advanced Planning System (1)
- Anomaly detection (1)
Institute
With the development of publicly accessible broker systems within the last decade, the complexity of data-driven ecosystems is expected to become manageable for self-managed digitalisation. Having identified event-driven IT-architectures as a suitable solution for the architectural requirements of Industry 4.0, the producing industry is now offered a relevant alternative to prominent third-party ecosystems. Although the technical components are readily available, the realisation of an event-driven IT-architecture in production is often hindered by a lack of reference projects, and hence uncertainty about its success and risks. The research institute FIR and IT-expert synyx are thus developing an event-driven IT-architecture in the Center Smart Logistics' producing factory, which is designed to be a multi-agent testbed for members of the cluster. With the experience gained in industrial projects, a target IT-architecture was conceptualised that proposes a solution for a self-managed data-ecosystem based on open-source technologies. With the iterative integration of factory-relevant Industry 4.0 use cases, the target is continuously realised and validated. The paper presents the developed solution for a self-managed event-driven IT-architecture and presents the implications of the decisions made. Furthermore, the progress of two use cases, namely an IT-OT-integration and a smart product demonstrator for the research project BlueSAM, are presented to highlight the iterative technical implementability and merits, enabled by the architecture.
The European Commission set out the goal of carbon neutrality by 2050, which shall be achieved by fostering the twin transition - sustainability through digitalization. A keystone in this transition is the implementation of a prospering Circular Economy (CE). However, product information required to establish a flourishing CE is hardly available or even accessible. The Digital Product Passport (DPP) offers a solution to that problem but in the current discussion, two separate topics are focused on: its architecture and its application on batteries. The content of the DPP has not been an essential part of the discussion, although access to high-quality data about a product's state, composition and ecological footprint is required to enable sustainable decision-making. Therefore, this paper presents a classification of product data for circularity in the manufacturing industry to emphasize the discussion about the DPP's content. Developed through a systematic literature review combined with a case-study-research based on common operational information systems, the classification comprises three levels with 62 data points in four main categories: (1) Product information, (2) Utilization information, (3) Value chain information and (4) Sustainability information. In this paper, the potential content structure of a DPP is demonstrated for a use case in the machinery sector. The contribution to the science and operations community is twofold: Building a guideline for DPP developers that require scientific input from available real-world data points as well as motivating manufacturers to share the presented data points enabling a circular product information management.
In short-term production management of the Internet of Production (IoP) the vision of a Production Control Center is pursued, in which interlinked decision-support applications contribute to increasing decision-making quality and speed. The applications developed focus in particular on use cases near the shop floor with an emphasis on the key topics of production planning and control, production system configuration, and quality control loops.
Within the Predictive Quality application, predictive models are used to derive insights from production data and subsequently improve the process- and product-related quality as well as enable automated Root Cause Analysis. The Parameter Prediction application uses invertible neural networks to predict process parameters that can be used to produce components with desired quality properties. The application Production Scheduling investigates the feasibility of applying reinforcement learning to common scheduling tasks in production and compares the performance of trained reinforcement learning agents to traditional methods. In the two applications Deviation Detection and Process Analyzer, the potentials of process mining in the context of production management are investigated. While the Deviation Detection application is designed to identify and mitigate performance and compliance deviations in production systems, the Process Analyzer concept enables the semi-automated detection of weaknesses in business and production processes utilizing event logs.
With regard to the overall vision of the IoP, the developed applications contribute significantly to the intended interdisciplinary of production and information technology. For example, application-specific digital shadows are drafted based on the ongoing research work, and the applications are prototypically embedded in the IoP.
Manufacturing companies face the challenge of managing vast amounts of unstructured data generated by various sources such as social media, customer feedback, product reviews, and supplier data. Text-mining technology, a branch of data mining and natural language processing, provides a solution to extract valuable insights from unstructured data, enabling manufacturing companies to make informed decisions and improve their processes. Despite the potential benefits of text mining technology, many manufacturing companies struggle to implement use cases due to various reasons. Therefore, the project VoBAKI (IGF-Project No.: 22009 N) aims to enable manufacturing companies to identify and implement text mining use cases in their processes and decision-making processes. The paper presents an analysis of text mining use cases in manufacturing companies using Mayring's content analysis and case study research. The study aims to explore how text mining technology can be effectively used in improving production processes and decision-making in manufacturing companies.
Long-term production management defines the future production structure and ensures the long-term competitiveness. Companies around the world currently have to deal with the challenge of making decisions in an uncertain and rapidly changing environment. The quality of decision-making suffers from the rapidly changing global market requirements and the uniqueness and infrequency with which decisions are made. Since decisions in long-term production management can rarely be reversed and are associated with high costs, an increase in decision quality is urgently needed. To this end, four different applications are presented in the following, which support the decision process by increasing decision quality and make uncertainty manageable. For each of the applications presented, a separate digital shadow was built with the objective of being able to make better decisions from existing data from production and the environment. In addition, a linking of the applications is being pursued:
The Best Practice Sharing App creates transparency about existing production knowledge through the data-based identification of comparable production processes in the production network and helps to share best practices between sites. With the Supply Chain Cockpit, resilience can be increased through a data-based design of the procurement strategy that enables to manage disruptions. By adapting the procurement strategy for example by choosing suppliers at different locations the impact of disruptions can be reduced. While the Supply Chain Cockpit focuses on the strategy and decisions that affect the external partners (e.g., suppliers), the Data-Driven Site Selection concentrates on determining the sites of the company-internal global production network by creating transparency in the decision process of site selections. Different external data from various sources are analyzed and visualized in an appropriate way to support the decision process. Finally, the issue of sustainability is also crucial for successful long-term production management. Thus, the Sustainable Footprint Design App presents an approach that takes into account key sustainability indicators for network design. [https://link.springer.com/referenceworkentry/10.1007/978-3-030-98062-7_15-1]
Companies in the manufacturing sector are confronted with an increasingly dynamic environment. Thus, corporate processes and, consequently, the supporting IT landscape must change. This need is not yet fully met in the development of information systems. While best-of-breed approaches are available, monolithic systems that no longer meet the manufacturing industry's requirements are still prevalent in practical use. A modular structure of IT landscapes could combine the advantages of individual and standard information systems and meet the need for adaptability. At present, however, there is no established standard for the modular design of IT landscapes in the field of manufacturing companies' information systems. This paper presents different ways of the modular design of IT landscapes and information systems and analyzes their objects of modularization. For this purpose, a systematic literature research is carried out in the subject area of software and modularization. Starting from the V-model as a reference model, a framework for different levels of modularization was developed by identifying that most scientific approaches carry out modularization at the data structure-based and source code-based levels. Only a few sources address the consideration of modularization at the level of the software environment-based and software function-based level. In particular, no domain-specific application of these levels of modularization, e.g., for manufacturing, was identified. (Literature base: https://epub.fir.de/frontdoor/index/index/docId/2704)
Digital technologies have gained significant importance in the course of the 4th Industrial Revolution and these technologies are widely implemented, nowadays. However, it is necessary to bear in mind that an ill-considered use can quickly have a negative impact on the environment in which the technology is used. For more responsible and sustainable use, the regulation of digital technologies is therefore necessary today. Since the government is taking a very slow response, as the example of the AI Act shows, companies need to take action themselves today. In this context, one of the central questions for companies is: "Which digital technologies are relevant for manufacturing companies in terms of regulation? This paper conducted a quantitative Delphi study to answer this question. The results of the Delphi study are presented and evaluated within the framework of a data analysis. In addition, it will be discussed how to proceed with the results so that manufacturing companies can benefit from them. Furthermore, the paper contributes to the development of an AI platform in the German research project PAIRS by investigating the compliance relevance of artificial intelligence applications.
Digital technologies such as 5G, augmented reality, and artificial intelligence (AI) are currently being used in various ways by manufacturing companies. As the fourth industrial revolution progresses, it has become apparent that reckless use and inadequate regulation of these technologies have a detrimental effect on the environment in which they are utilized. Therefore, regulation of digital technologies is imperative today to ensure more responsible and sustainable use. While governments usually establish regulations, progress is not keeping pace with the demands and hazards of employing digital technologies. The European AI law serves as an example of the considerable distance yet to be covered before binding guidelines are established. Consequently, companies must take proactive measures today to ensure that they use digital technologies responsibly in their environments. In this context, identifying which digital technologies are pertinent to manufacturing companies in terms of regulation is crucial. Furthermore, a comprehensive approach is required to design compliance holistically for digital technologies and to systematically derive the corresponding guidelines. This paper introduces a set of models that not only determine the importance of
compliance in the application of different technologies but also present a framework for methodically designing compliance. Furthermore, the paper contributes to the development of an AI platform in the German research project PAIRS by investigating the compliance relevance of applications such as artificial intelligence.
Industrial companies are moving to a solution driven business by offering smart product service systems (Smart PSS). In addition to an existing portfolio of physical goods and technical services, companies develop new digital services and combine all three offerings to an integrated digital solution business. While the development of new digital services does not pose any major challenges for companies, the successful sale of Smart PSS does. Due to changing customer requirements and value propositions of a solution, the sale of Smart PSS requires new design principles for the sales organization compared to the simple sale of physical goods or technical services. While there are already many publications on the topic of industrial sales in research, the description of Smart PSS in particular represents a new field of research. The combination of both topics is therefore not only interesting from a theoretical point of view, but also has a particularly high practical relevance and impact for industrial companies. This paper therefore describes on the one hand, which characteristics can be used to derive customer requirements for Smart PSS and on the other hand, which effects these requirements have on the sales organization of the industrial company. The design principles give recommendations for the organizational structure, the resources, the information systems and the culture of the company depending on the targeted customer type. In order to identify and describe both the customer requirements and the design principles, two morphological boxes were developed based on a literature research and semi-structured interviews with industrial companies. The paper gives an outlook on the different characteristics of the design recommendations and describes first best practices for the successful transformation of the sales organization.
Competitive differentiation in the manufacturing sector is no longer based on product and service innovations alone but on the ability to monetize the usage phase of products and services. To this end, manufacturers are increasingly looking at so-called subscription business models as a way of supplementing the traditional sale of products and services. Since supplier success in the subscription business is directly dependent on customer success, the setup and expansion of a so-called Customer Success Management (CSM) is required. While CSM has already been established in the software industry for several years, companies in the manufacturing sector are often still in the conceptual phase of a CSM, parallel to the setup and expansion of their subscription business. Therefore, this paper aims to support the set-up of a CSM by providing a reference data model, based on case study research, that can be used to support the organizational or daily CSM tasks and to serve as a blueprint for conceptualizing CSM-specific IT systems.
Systematisation Approach
(2023)
Current megatrends such as globalisation and digitalisation are increasing complexity, making systems for well-founded and short-term decision support indispensable. A necessary condition for reliable decision-making is high data quality. In practice, it is repeatedly shown that data quality is insufficient, especially in master and transaction data. Moreover, upcoming approaches for data-based decisions consistently raise the required level of data quality. Hence, the importance of handling insufficient data quality is currently and will remain elementary. Since the literature does not systematically consider the possibilities in the case of insufficient data quality, this paper presents a general model and systematic approach for handling those cases in real-world scenarios. The model developed here presents the various possibilities of handling insufficient data quality in a process-based approach as a framework for decision support. The individual aspects of the model are examined in more detail along the process chain from data acquisition to final data processing. Subsequently, the systematic approach is applied and contextualised for production planning and supply chain event management, respectively. Due to their general validity, the results enable companies to manage insufficient data quality systematically.
Pricing is one of the most important, but underestimated tools, to enhance a company's profitability. Especially in the furniture sector, customers place a special interest in cost-efficient products and easy processes. Individualised and sustainable furniture can help to create a unique selling point and deliver real value to the customers. Therefore, a platform to create designs together is needed and can involve several stakeholders in the design and production phase. However, in order to include several stakeholders, the pricing and revenue model need to reflect individual needs and be a benefit to all. In this paper, the initial situation and potential revenue model options will be presented. Furthermore, multiple scenarios for practical use will be discovered and an overview given.
Methods of machine learning (ML) are notoriously difficult for enterprises to employ productively. Data science is not a core skill of most companies, and acquiring external talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratising machine learning by introducing elements such as low-code / no-code functionalities into its model creation process. Multiple applications are possible for Auto-ML, such as Natural Language Processing (NLP), predictive modelling and optimization. However, employing Auto-ML still proves difficult for companies due to the dynamic vendor market: The solutions vary in scope and functionality while providers do little to delineate their offerings from related solutions like industrial IoT-Platforms. Additionally, the current research on Auto-ML focuses on mathematical optimization of the underlying algorithms, with diminishing returns for end users. The aim of this paper is to provide an overview over available, user-friendly ML technology through a descriptive model of the functions of current Auto-ML solutions. The model was created based on case studies of available solutions and an analysis of relevant literature. This method yielded a comprehensive function tree for Auto-ML solutions along with a methodology to update the descriptive model in case the dynamic provider market changes. Thus, the paper catalyses the use of ML in companies by providing companies and stakeholders with a framework to assess the functional scope of Auto-ML solutions.
Methods of machine learning (ML) are difficult for manufacturing companies to employ productively. Data science is not their core skill, and acquiring talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratizing machine learning by introducing elements such as low-code or no-code functionalities into its model creation process. Due to the dynamic vendor market of Auto-ML, it is difficult for manufacturing companies to successfully implement this technology. Different solutions as well as constantly changing requirements and functional scopes make a correct software selection difficult. This paper aims to alleviate said challenge by providing a longlist of requirements that companies should pay attention to when selecting a solution for their use case. The paper is part of a larger research effort, in which a structured selection process for Auto-ML solutions in manufacturing companies is designed. The longlist itself is the result of six case studies of different manufacturing companies, following the method of case study research by Eisenhardt. A total of 75 distinct requirements were identified, spanning the entire machine learning and modeling pipeline.
Companies are transforming from transactional sales to providing solutions for their customers. Mostly, smart products, enabling companies to enhance their products by providing smart services to their customers, are a key building block in this transformation. However, the development of a smart product requires many digital skills and knowledge, which regular companies do not have. To facilitate the design and conceptualization of smart products, this paper presents a use-case-based information systems architecture prototype for smart products. Furthermore, the paper features the application and evaluation of the architecture on two different smart product projects. The use of such an architecture as a reference in smart product development serves as a huge advantage and accelerator for inexperienced companies, allowing faster entry into this new field of business. [https://link.springer.com/chapter/10.1007/978-3-031-14844-6_16]
Manufacturing companies (MFRs) are increasingly extending their
portfolios with services and data-driven services (DDS) to differentiate themselves from competitors, tap new revenue potential, and gain competitive advantages through digitization and the subsequently generated data. Nonetheless, DDS fail more often than traditional industrial services and products within the first year on the market. Particularly, companies are failing to sell DDS successfully and efficiently with their existing (multi-level) distribution structures. Surprisingly, there is a lack of scientific research addressing this issue. Since there are currently no holistic models for an end-to-end description of distribution-tasks for DDS in the manufacturing industry, this paper contributes to a task-oriented reference model for mapping interactions in the multi-level distribution management. Therefore, a case study research approach is used, to identify and describe the interactions in the multi-level distribution management of DDS, as well as to develop a regulatory framework for MFRs and their multi-level distribution management. This research uses the established theoretical framework of Service-Dominant-Logic to address the co-creation in multi-level distribution management of DDS. As a result, this paper identifies different interaction variants as well as the need for a new management function with 4 main and 14 basic tasks.
Ongoing digitalization and Industry 4.0 enable the development of new business models due to the increase in available data and digital connected products. A promising business model type for the machinery and plant engineering industry are subscription models, consisting of products and services offered in return for continuous payments. However, subscription-based business models are associated with extensive changes in the traditional machinery and plant engineering industry, in particular, for small and medium-sized companies (SMEs). Established concepts for the development of value propositions and business models neglect important aspects, such as the integrated development and optimization of products and services across the entire life cycle or the data infrastructure. This paper presents a concept for a methodology to support SMEs developing value propositions within subscription models. Therefore, the systematic identification of customer benefits, the determination and prioritization of subscription relevant functionalities as well as the design of product and service elements addressing those functionalities are the main aspects on which the focus is placed on. The result is a subscription value proposition canvas for SMEs to address the impact of subscription models on products and services.
More and more manufacturing companies are starting to transform the transaction-based business model into a customer value-based subscription business to monetize the potential of digitization in times of saturated markets. However, historically evolved, linear acquisition processes, focusing the transactionoriented product sales, prevent this development substantially. Elemental features of the subscription business such as recurring payments, short-term release cycles, data-driven learning, and a focus on customer success are not considered in this approach. Since existing transactional-driven acquisition approaches are not successfully applicable to the subscription business, a systematic approach to an acquisition cycle of the subscription business in the manufacturing industry is presented, aiming at a long-term participative business. Applying a grounded theory approach, a task-oriented model for themanufacturing industry was developed.
The model consisting of five main tasks and 14 basis tasks serves as best practice to support manufacturing companies in adapting or redesigning acquisition activities for their subscription business models.
Due to shorter product life cycles and the increasing internationalization of competition, companies are confronted with increasing complexity in supply chain management. Event-based systems are used to reduce this complexity and to support employees' decisions. Such event-based systems include tracking & tracing systems on the one hand and supply chain event management on the other. Tracking & tracing systems only have the functions of monitoring and reporting deviations, whereas supply chain event management systems also function as simulation, control, and measurement. The central element connecting these systems is the event. It forms the information basis for mapping and matching the process sequences in the event-based systems. The events received from the supply chain partner form the basis for all downstream steps and must, therefore, contain the correct data. Since the data quality is insufficient in numerous use cases and incorrect data in supply chain event management is not considered in the literature, this paper deals with the description and typification of incorrect event data. Based on a systematic literature review, typical sources of errors in the acquisition and transmission of event data are discussed. The results are then applied to event data so that a typification of incorrect event types is possible. The results help to significantly improve event-based systems for use in practice by preventing incorrect reactions through the detection of incorrect event data.
Industry 4.0 and Smart Maintenance represent a great opportunity to make manufacturing and maintenance more effective, safer, and reliable. However, they also represent massive change and corresponding challenges for industrial companies, as many different options and starting points have to be weighed and the individual right paths for achieving Smart Maintenance need to be identified. In our paper, we describe our approach to evaluating maintenance organizations in a case study for the oil and gas industry, developing a shared vision for the future, and deriving economical and effective measures. We will demonstrate our approach, by showcasing a specific example from the oil and gas industry, where a need for action on HSE-relevant critical flanges in the company's piping systems was identified. We describe the steps, that were taken to identify the need for action, the specifications of the project and the criticality analysis of the piping system. This resulted in the derivation of a digitalization measure for critical flanges, which was first commercially analyzed and then the flanges were equipped with a continuous monitoring solution. Finally, a conclusion is drawn on the performed procedure and the achieved improvements.