Search

The increasing skill mismatch in manufacturing workforce is raising demand for training opportunities to cope with advanced manufacturing systems. To maintain production and adjust quickly to technological transformation, innovative work-based learning approaches are emphasized. Intelligent machines are becoming capable of interaction and collaboration with humans. They not only introduce a new type of learnable workforce to manufacturing but may open opportunities to enhance learning of all learners. Symbiotic relationships of humans and machines have wide potential for human-centric manufacturing (aka Industry 5.0). Moreover, connecting smart devices and deploying self-learning solutions is envisioned to increase flexibility of manufacturing, thus changing work division between humans and machines. Where humans and machines collaborate, the term Reciprocal Learning has been coined to describe the process of bidirectional learning. While a definition of Reciprocal Learning exists the boundary conditions of the concept are still ambiguous. In this paper, a framework for Reciprocal Learning in Human-Machine Collaboration for Industry 5.0 is presented to clarify what it is and what it isn’t. The approach is based on a multi-agent system perspective, comprising human and machine agents. Finally, an outlook on future research is presented.

The success of data-driven maintenance is strongly dependant on effective use of AI and multi-structured data sources. Introducing and integrating an AI-enhanced methodology in reliability-centred maintenance study of complex production systems leads to reducing failure rates and optimizing availability. In manufacturing enterprises, information about machine failures and expert knowledge are often stored in digital shift books (DSB). This paper introduces a transferable and scalable AI-enhanced methodology for DSB in automotive industry, which enhances Overall Equipment Efficiency (OEE) by optimizing availability through reducing the Mean Failure Detection Time (MFDT). Experimental investigations in the use-case suggest an OEE increase by over 5%.

The ongoing digitization of the industry leads to new opportunities in industrial maintenance. Several concepts for smart maintenance have been published in literature, however, their application remains limited in industrial practice. To close the existing gap between research and practice, a novel practice-oriented approach is presented. A modified Weibull model is developed and embodied into a digital assistance system to visualize and predict remaining service life and to forecast the required number of spare parts. The developed model has been implemented in the use case in the heat treatment industry, and the results are presented to demonstrate the effectiveness of the proposed approach.

Increasing number of AI-enhanced approaches provide helpful “know-how” for reproducing and imitating skills and finally substituting human jobs with algorithms and intelligent machines. However, complementarity of human and machine, especially in hybrid man-machine settings is still not sufficiently explored. The main objective of this paper is to establish a twofold qualitative and quantitative methodology for optimal selection of a competent jobholder(s) to perform a certain task by semantic modeling and analysis of jobholder (human and machine) profiles corresponding to the task characteristics and learning requirements including knowledge, skills and competences (KSCs). The proposed knowledge-based approach comprises semantic modeling and quantitative methods focusing on measuring and correlating the level of human competences and machine autonomy, and identifying the extent of human–machine complementarity in performing an assigned task. The Vector of Competence and Autonomy (VCA) is built for identifying the extent of human–machine collaboration. The quantitative analysis involves several human factors in association to various combinations of technological components of Digital Assistance Systems with different automation degrees, under certain aspects of complexity of products and workplaces. Applying a set of rules and considering jobholder profiles, VCA values are interpreted and the current state of complementarity is inferred. Furthermore, feasible radical or incremental managerial transition pathways are identified as an initial step to reach the optimal (desired) level of human–machine collaboration in the example of TU Wien Pilot Factory Industry 4.0.

In the era of Industry 4.0, predictive maintenance is regarded as a key factor for reaching business objectives. Cost-effective deployment of Cyber Physical Production Systems raises the question whether data-driven and knowledge-based maintenance affects profitability of smart factories. Several studies reveal that an appropriate data-driven maintenance strategy should not only focus on increasing availability but also should consider economic parameters. This paper presents a novel approach and a proof-of-concept demonstrator using Dynamic Bayesian Networks (DBN). The proposed DBN model enables identifying and predicting the economic impact of maintenance on profitability as well as support planning and monitoring of maintenance activities.

Recent empirical studies reveal that predictive maintenance is essential for accomplishing business objectives of manufacturing enterprises. Knowledge-based maintenance strategies for optimal operation of industrial machines and physical assets reasonably require explaining and predicting long term economic impacts, based on exploring historical data. This paper examines how supervised machine learning (ML) techniques may enhance anticipating the economic impact of maintenance on profitability (IMP). Planning and monitoring of maintenance activities supported by various statistical learning and supervised ML algorithms have been investigated in the literature of production management. However, data-driven prediction of IMP has not been largely addressed. A novel data-driven framework is proposed comprising cause-and-effect dependencies between maintenance and profitability, which constructs a set of appropriate features as independent variables.

Kurzfassung Eine hohe Prozessstabilitat und Produktqualitat ist fur viele Unternehmen entscheidend, um in einem sehr kompetitiven Markt konkurrenzfahig zu bleiben. Vor dem Hintergrund der digitalen...

Knowledge Management in the era of Industry 4.0 (KM 4.0) in both human- and technology-oriented perspectives is a strategic and operational function comprising exploration and exploitation processes. It is responsible to accomplish two major tasks. First, KM 4.0 should continuously support value generation through enhancing and balancing need- or opportunity-driven knowledge generation and knowledge utilization capacities. Second, KM 4.0 should persistently facilitate developing and protecting human-machine collective intelligence across manufacturing enterprises and in particular smart factories. Hence, KM 4.0 is an enabler to maximize competitive advantages and derive business values in the manufacturing enterprises. The revival of AI and emergence of autonomous and learnable technologies challenge the unique role of human as a knowledge actor, decision-maker, problem-solver and learner. What are the considerations on rethinking KM approaches in relation to the march of technological enhancements? This paper proposes a definition and discusses the theoretical foundation of KM 4.0 as well as related practical aspects that should be taken into consideration, especially in dynamic, data-driven and hybrid human-machine working environments in smart factories.

The digital transformation of manufacturing industries currently re-invents conventional production paradigms through the creation of cyber-physical production systems (CPPS) and smart manufacturing networks. Novel knowledge-based maintenance (KBM) strategies and models are regarded as a key enabler in order to manage the increasing complexity and automatization of CPPS. Thus, securing and improving machine availability and process stability are accomplished. Although industrial decision makers are willing to invest in renovating and enhancing their companies’ maintenance strategy, they lack knowledge regarding their readiness levels in realizing and deploying KBM. In particular, they doubt whether their companies hold fundamental competence and capacity (i.e. appropriate methods for data analytics and systematic guidance) towards realizing KBM. In this paper, the authors present a holistic procedure model that assesses a company´s individual status quo in KBM and enables the identification of strengths and weaknesses on operative, tactical and strategic level following a multidimensional analytical approach. The model thereby builds on the assessment of more than 35 quality indicators assigned to a maintenance execution and data management dimension. The indicators feed into a mathematical calculation of data, information, knowledge and maintenance quality factors. The authors present the model’s development and content. Applying the model to an Austrian manufacturing company, its KBM readiness and maturity level for the creation of a predictive maintenance strategy under the premise of supporting prompt and efficient decision making is assessed. Feedback and validation of the results reveals both scientifically valuable, systematic and transparent applicability in real production environments.

Autonomous production control (APC) is able to deal with challenges, inter alia, high delivery accuracy, shorter planning horizons, increasing product and process complexity, and frequent changes. However, several state-of-the-art approaches do not consider maintenance factors contributing to operational and tactical decisions in production planning and control. The incomprehensiveness of the decision models and related decision support tools cause inefficiency in production planning and thus lead to a low acceptance in the manufacturing enterprises. To overcome this challenge, this paper presents a conceptual cost-based model for integrating different maintenance strategies in autonomous production control. The model provides relevant decision aspects and a cost function for different maintenance strategies using on a market-based approach. The present work thus makes a positive contribution to cope with the high demands on flexibility and response times in planning while at the same time ensuring high plant productivity.

The ongoing digital transformation in manufacturing is raising the demand for skilling, re-skilling and upskilling of workforces. At the same time, it largely affects skill mismatches in socio-technical work systems. Industry 4.0’s enabling technologies, especially AI and collaborative robotics offer new ways of learning, which introduce innovative work-based learning (WBL) approaches. In this context, Learning Factories confront a challenge on how to cope with the pace of technological enhancement and increasing skill mismatches and competence gaps on the job market. This paper is to conduct a systematic and community-specific literature survey to elicit and cluster the current state of the art in WBL represented in the International Association of Learning Factories (IALF) over the past years. Of particular importance are articles i) emphasizing new ways of technology-enhanced WBL, and ii) examining research gaps regarding (reciprocal) learning among human and intelligent machines in collaborative work systems. Finally, the future pathways of research in WBL within and beyond IALF are identified.

Recent advances in autonomous production control (APC) enhance to cope with growing challenges of manufacturing industry regarding high delivery accuracy and short delivery dates, i.e. concurrently dealing with shorter planning horizons, increasing planning complexity and an increasing rate of changes in planning. However, the majority of APC approaches are based on idealized assumptions, lack integrative planning, and control mechanisms. In particular, the state-of-the-art APC approaches mainly ignore maintenance planning strategies, related decision factors, and maintenance measures. The ultimate practical implications are a reduced decision quality, and a resulting low acceptance of APC systems. In most cases, therefore, implementation of APC systems in industrial applications are not yet affordable. Pursuing this line of research, this paper presents a conceptual model for integrating maintenance strategies in APC. The focus is on evaluation of economic plausibility of the integrated approach, which deploys a cost function for a market-oriented decision-making. Using an agent-based simulation environment, the model is evaluated in an industrial use case in the automotive sector.