With the intensive development and implementation of information and communication technologies in manufacturing, large amounts of heterogeneous data are now being generated, gathered and stored. Handling large amounts of complex data - often referred to as big data - represents a challenge as there are many new approaches, methods, techniques, and tools for data analytics that open up new possibilities for exploiting data by converting them into useful information and/or knowledge. However, the application of advanced data analytics in manufacturing lags behind in terms of penetration and diversity in comparison with other domains such as marketing, healthcare and business, meaning that the available data often remain unexploited. This paper proposes a new conceptual framework for systematically introducing big-data analytics into manufacturing systems. To this end, the paper defines a new stepwise procedure that identifies what knowledge and skills, and which reference models, software and hardware tools, are needed for the development, implementation and operation of data-analytics solutions in manufacturing systems. The feasibility of the proposed conceptual framework is demonstrated in a case study from an engineer-to-order company and by mapping the framework to several previous data-analytics projects.

In this paper the concepts of advanced production systems based on the challenges that bring the new industrial revolution named - Industry 4.0 are presented. The presented concept of socio-cyber-physical work systems is based on connecting social, cyber and physical working environments into a single functional, productive entity of the appointed elementary socio-cyber-physical work system.The elementary socio-cyber-physical work system is a basic building block of the cyber-physical production systems at the manufacturing level. The cyber system of the elementary socio-cyber-physical work system enables autonomous decision-making and cooperation in the network system. The possibility of implementing the proposed concept is based on the introduction of agency technologies in the domain of modern production systems and the development of information-communication technologies for the advanced management and control of cyber-physical production systems. Some illustrative examples reflect the experimental results of a research work in the field of cyber-physical systems and demonstrate the potential possibilities of implementing the concept of sociocyber-physical work systems in the real industrial environment.

Cyber-physical systems (CPSs) open up new perspectives for the design, development, implementation, and operation of manufacturing systems and will enable a paradigm shift in manufacturing.The objective of this research is to develop a new concept of cyber-physical production systems (CPPSs) and, on this basis, to address the issue of management and control, which is crucial for the effective and efficient operation of manufacturing systems.A new model of CPPS is proposed.The model integrates digitalized production planning, scheduling, and control functions with a physical part of manufacturing system and enables the self-organization of the elements in production.A case study demonstrates feasibility of the approach through the use of simulation experiments, which are based on real industrial data collected from a company that produces industrial and energy equipment.

Material flow management is an increasingly difficult activity in today's ever-more-complex manufacturing systems. New approaches are offered by the industrial internet of things (IoT), which is envisioned as a network of active devices that are capable of wireless communication. However, the dependence of IoT devices on battery energy presents a maintenance challenge. The paper proposes a self-organisation-based approach to improve the overall energy efficiency of workpiece localisation using IoT devices. A simulation study is performed to show the effects of transmitter effectiveness, material flow dynamics, and system scale on the energy efficiency.

In manufacturing processes the automated identification of faulty operating conditions that might lead to insufficient product quality and reduced availability of the equipment is an important and challenging task. This paper proposes a data mining approach to the identification of complex faults, i.e. unplanned machine stops in plastic injection molding. Several data mining methods are considered, with a focus on the abilities to reveal patterns of faulty operating conditions and on the interpretation of the induced models with the objective to find the data mining method that best corresponds to the nature of the plastic-injection-molding process and the related data. Well-known data mining methods, i.e. J48, random forests, JRip rules, naïve Bayes, and k-nearest neighbors are applied to real industrial data. The results show that tested data mining methods can be effectively used to reveal patterns related to faulty operating conditions. The interpretation capacity of the tested methods, their ability to describe the operating conditions, and to reveal patterns related to faulty operating conditions, are demonstrated and discussed.

Industrial Internet of Things (IIoT) is a new concept denoting extensive use of ubiquitous connected devices on the manufacturing shop floor. While most recent research in this area focuses on the monitoring capabilities of IIoT and on the resulting data analysis, IIoT also presents an opportunity from the perspective of distributed control. The paper suggests that agent based control of an industrial process can be realized by a multiagent system in which each agent is able to learn the influence of its actions on the behaviour of the system and to communicate with other agents in its proximity. Influence of the communication structure on performance, robustness, and resilience are analysed for a case of an industrial compressed air system. The simulation results suggest that in such systems, communication between the supply and the demand side improves resilience, while the robustness is improved through learning.

People, companies, and institutions form networks as part of their technical, economic, and social activities. As a consequence, these networks have an influence on how companies conduct business. Recently, the Internet, professional, and scientific social networks have contributed to the ease and simplicity of the network forming process and the public availability of the corresponding data. We investigate whether useful information about the relationships between individuals, companies, and institutions for the domain of production can be extracted from publicly available, structured and unstructured data that is merged from various Internet sources. We demonstrate that relevant information about the structures of these networks can be obtained by merging publicly available data using a combination of advanced computational methods including web crawling, machine learning, and creating mash-ups of publicly available services. The feasibility and the applicability of the approach are shown for a case in the automotive domain. A potential use case of the resulting data is demonstrated, showing how the approach can be used to find specific skills and expertise for a scientific community consisting of people from industry and academia. The proposed approach can be used for the modelling and analysis of various forms of collaboration between and within businesses. As a tool, it could be used for the purposes of strategic networking, to facilitate the creation of project consortia, to identify competitors and other stakeholders in a certain domain, to pinpoint communication channels, to search for specific expertise, or to identify organisational and social structures within organisations.

The growing generation of solid waste is one of the environmental problems that have most affected the world population in recent years. The solid waste generated from home appliances and information technology devices are one of the classes that concern the international community, since they have high toxicity and high potential of environmental pollution. This article presents the design, implementation and testing of a model aimed to evaluate the possibility of their remanufacturingfrom the waste originated from household equipment. In the case developed for the article the waste of printers (inkjet and laser), scanners and computerswere evaluated forthe development of a three dimensional printer (3D Printer). The System Dynamics methodology was used to implement the model, and to verify and validate it.There experiments using three scenarios were developed: an uncertainty scenario with a random rate between 25% and 75% of waste reuse; thegrowth scenario with a rate from 25% to 75% of waste reuse (growth of 5% per year) and; static scenario with a rate of 50% of waste reuse during the simulated time.Results generated by the simulation modelshow that the remanufacturing is a viable alternative for the reutilization of the discarded household equipment.

Digital twins are digital representations of physical products or systems that consist of multiple models from various domains describing them on multiple scales. By means of communication, digital twins change and evolve together with their physical counterparts throughout their lifecycle. Domain-specific partial models that make up the digital twin, such as the CAD model or the degradation model, are usually well known and provide accurate descriptions of certain parts of the physical asset. However, in complex systems, the value of integrating the partial models increases because it facilitates the study of their complex behaviours which only emerge from the interactions between various parts of the system. The paper proposes that the partial models of the digital twin share a common model space that integrates them through a definition of their interrelations and acts as a bridge between the digital twin and the physical asset. The approach is illustrated in a case of a mechatronic product - a differential drive mobile robot developed as a testbed for digital twin research. It is demonstrated how the integrated models add value to different stages of the lifecycle, allowing for evaluation of performance in the design stage and real-time reflection with the physical asset during its operation.

Identification of expertise of people, academic societies, companies, and institutions is an important professional and social activity for nurturing professional networks, forming project consortia, etc. Today, a lot of information about the skills and expertise is openly available from websites and public personal profiles on professional and scientific social networks. With computerised methods, such as web crawling, text mining, and keyword classification, it is possible to identify expertise networks from the raw unstructured data. The paper presents and analyses the extended expertise network of the CIRP scientific community and proposes a web-based tool for the structuring and management of the community’s expertise.

Manufacturing data offers big potential for improving management of manufacturing operations. The paper addresses an approach to data analytics in engineer-to-order (ETO) manufacturing systems where the product quality and due-date reliability play a key role in management decisionmaking. The objective of the research is to investigate manufacturing data which are collected by a manufacturing execution system (MES) during operations in an ETO enterprise and to develop tools for supporting scheduling of operations. The developed tools can be used for simulation of production and forecasting of potential resource overloads.

Cyber-physical production systems are transforming traditional, hierarchical control structures into distributed ones in which the elements offer and consume services with a high degree of autonomy. This paper proposes an agent-based approach to distributed control for production environments in which the agents are only able to interact with a part of the whole system. It hypothesises that the performance of the agent network can be improved through learning and communication. A description of the approach is presented and illustrated with a simulation case of distributed control for an industrial compressed-air system.

Models of distributed manufacturing systems cannot be consistent without a formal ontology. In this paper, the ontology formulation and maintenance are addressed in the scope of a collaborative modelling environment – in which concurrency, consistency, and model life cycle management should be supported. Thus, an extensible foundational ontology for manufacturing – system modelling is proposed in which the formal definitions of the modelling environment itself enable the definition of the manufacturing system’s elements. The presented approach ensures the consistency of ever-changing models. The ontology is integrated into a modelling framework through the concept of description layers that assist in the management of the model description’s complexity. The feasibility of the approaches is illustrated in an industrial case study that models of a manufacturing system for material processing.

The intensive development of information and communication technologies in recent years has led to an increase in data size and complexity. Conventional approaches, with associated methods of analysis based on descriptive and inductive statistics, may no longer be suitable for extracting the valuable information that is hidden in the available data.Computer-controlled manufacturing systems are becoming rich sources of data. Plastic injection moulding and die casting systems are typical examples of such manufacturing systems where the parts are produced by repeating the same sequence of steps that make up a manufacturing cycle. For each cycle, similarly structured data is generated.In this work a method for systematic data analysis for cyclic manufacturing processes is presented. The proposed data-analysis method integrates well-known heuristic algorithms, i.e., decision trees and clustering, with the purpose of identifying types of faulty operating conditions. The result of the analysis is an interpretable model for decision support that can be used for fault identification, to search for root causes, and to develop prognostic systems. A holistic approach of applying the proposed data-analysis method, along with suggestions and guidelines for implementation, is presented. A case study is presented in which the proposed method is applied to real industrial data from a plastic injection-moulding process.

The complexity of manufacturing systems is increasing due to the increased requirements related to the variety and quality of the products, their complexity, and due to the general technological developments. In turn, the data related to the manufacturing processes is growing in size and in complexity. This presents new challenges for real-time monitoring, diagnostics, and prognostics of the processes. The challenges are addressed by new tools, methodologies, and concepts, collectively referred to as Big Data. The paper deals with the use of advanced methods for prognostics of infrequent faults on available but highly dimensional manufacturing process data. A holistic approach, which includes data generation, acquisition, storage, processing, and prognostics, is shown in a case of a plastic injection moulding process. Real industrial data acquired from five injection moulding machines and the Manufacturing Execution System within a period of six months is used. It is shown how the approach is able to tackle the high dimensionality and the large size of the data to create and evaluate prediction models for prognostics of the unplanned machine stops.

In most manufacturing processes the defect rate is very low. Sometimes, only a few parts per million are defective because of a faulty process. For this reason, fault diagnostics is faced with extremely imbalanced data sets and requires large volumes of data to achieve a reasonable performance. This paper explores whether a machine-to-machine approach can be used, in which several work systems share the process data to improve the accuracy of the fault-detection model. The model is based on machine learning and is applied to industrial data from approximately two million process cycles performed on several injection moulding work systems.

In the context of advanced manufacturing, new models inspired by Internet technologies are being developed. The cloud manufacturing model strives to offer a similar experience for seekers of manufacturing services as cloud computing does for the users of the web: manufacturing clouds intend to offer manufacturing resources as services, much like processing power and storage space are available as services in cloud computing. The resulting business situation is favourable for both the service providers and the service end-users, especially in a highly dynamic manufacturing environment. Existing cloud manufacturing models operate in a centralised way through a cloud manufacturing platform, the management of which is identified as a critical part of the manufacturing cloud operation. In the article, a decentralised network architecture for cloud manufacturing is proposed. The architecture builds upon the concept of autonomous work systems for use as service providers. The operation of the system based on the architecture is described, wherein special attention is given to the communication within the emerged networks of service providers. Technical feasibility of the approach is also demonstrated. It is expected that the decentralised approach will enable a more flexible and scalable manufacturing cloud, which will have the ability to actively co-evolve with its environment.

Janez Peklenik was one of the outstanding scientists and engineers of the twentieth century, who left visible trails in manufacturing engineering research and education. He contributed to the advancement of manufacturing from soft empirical science into pure hard science. As a practitioner he was striving toward perfection and toward implementation of research ideas and results in real life. He was also a great scholar who was aware of the needs of industry on one side and of the problems that young students were confronted with on the other side, while trying to bridge over these two worlds. Janez Peklenik was recognized far over the Slovenian borders. His numerous invited lectures all over the globe confirm this fact. He was also a very active and distinguished member of The International Academy for Production Engineering - CIRP and, in the year 1979/80, its president. Fifty years ago he, as a young scientist with a vision, proposed the idea of organizing The International Seminar on Manufacturing Systems as a platform for exchanging ideas and experiences especially among young researchers and engineers. This idea attracted his CIRP colleagues and friends, Bertil Colding from Sweden, Toshio Sata from Japan and Gunter Spur from Germany, and they founded together the CIRP Conference on Manufacturing Systems, the CIRP conference series with the longest tradition. The contribution brings forward a brief review of Janez Peklenik life milestones and major achievements. (C) 2017 The Authors. Published by Elsevier B.V.