Generation Of Production Systems Research Articles

Recent trends and advances in machine learning challenges and applications for industry 4.0

AbstractThis editorial summarizes and analyzes 17 articles selected for a special issue on machine learning advances for Industry 4.0 applications. The diverse articles cover fault detection, deep learning optimisation, IoT networking, vehicle control, recommendation systems and domain knowledge integration. Key methods represented include neural networks, deep learning, reinforcement learning and explainable AI. Real‐world industrial case studies showcase machine learning's versatility in enabling intelligent automation, control, and decision‐making across manufacturing, healthcare, transportation and other sectors. While highlighting theoretical innovations, the contributions also demonstrate machine learning's transformative potential for intelligent, connected, self‐optimising next generation production systems. This editorial concisely overviews the latest trends represented in this special issue.

Technical-economic and environmental protection performance evaluation of a novel hybrid solar-nuclear thermally coupled power and desalination plant.

Clean energy complementary system can reduce environmental pollution effectively and is considered as a future energy development direction. In this paper, an innovative solar-nuclear thermally coupled power and desalination plant for electricity and freshwater productions is proposed. As solar power and nuclear power are combined, this multi-energy system is a clean energy system and basically has no emissions of soot, sulfur oxides, carbon dioxide, and nitrogen oxides. The operating behavior assessment results of the multi-energy system show that the power generation and freshwater production systems can operate synergistically. The electric power and corresponding efficiency of the multi-energy system are 290.7 MW and 38.2%, in which the solar proportion is about 38.1%. The daily freshwater production of the multi-energy system is 3761.3 t. The economic assessment results reveal that the levelized costs of electricity and freshwater of the multi-energy system are 0.361 yuan/(kWh) and 1.645 yuan/t. The environmental protection analysis results show that in contrast with a coal-fired system, the annual emission reductions of soot, sulfur oxides, carbon dioxide, and nitrogen oxides of the multi-energy system are 7350.94 t, 12,634.42 t, 513,034.14 t, and 11,945.28 t, revealing a significant environmental protection performance.

A detailed review on sole and hybrid solar chimney based sustainable ventilation, power generation, and potable water production systems

In this review article, the potential of solar chimney technologies for building ventilation, power generation and potable water generation in sole, hybrid and poly-generation modes has been reviewed extensively by highlighting their optimal configuration, pros, cons and economics. Solar chimney ventilation system in combination with evaporative cooler and earth-air heat exchanger can save at least 20 to 75% of the energy consumed for space conditioning activity. Sole solar chimney power plant occupies huge land area and has efficiency of only 1.0%. However, under hybrid and poly-generation operation modes its efficiency has improved to 55%. Solar PV modules seem to be a suitable partner for solar chimney technologies and it enhances utilization factor by providing extra electric power output. Solar PV modules have been suggested as absorber for ventilation system and canopy for solar chimney power plants. However, proper thermal management of PV modules is essential for proper functioning under the conditions inside the former system. Geo-thermal energy, waste heat energy from thermal power plants and flared gas from oil extraction sites can be utilized in solar chimney power plants to increase its operation time even after sun-set hours without any major modifications. Solar chimney based atmospheric water extraction systems enhances the micro-climate of sites and is highly suitable for applications in arid regions. Solar chimney ventilation systems are commercial and form an integral part of green buildings and net-zero buildings. On contrary, most of the literatures on power generation and water production with solar chimney technology are theoretical hence more practical studies are needed to justify their reliability.

Production and Economic Assessment of Synthetic Fuels in Agriculture—A Case Study from Northern Germany

A climate-friendly and CO2-neutral energy supply for agricultural farms is the subject of investigation of this study. The supply concerns the internal economy (buildings and animal husbandry) as well as the production of synthetic fuels for outdoor work (cultivation of the fields). This energy is in demand with many customers, e.g., the dairy cooperative Arla Foods, whose goal is the production of cow’s milk with net-zero CO2 emissions by the year 2050. The operational energy system considered here included renewable electricity generation, covering electricity consumption in the cowshed, battery storage for times without electricity generation, the production of synthetic fuels and feeding into the public power grid. Fluctuations depending on the day and the season were taken into account for electricity at 15-min intervals and for fuel per calendar week for one year. The aim was to determine the necessary capacities of renewable energy (RE) generation systems and production systems for synthetic fuel, as well as an economic evaluation with the calculation of the energy costs per kWh and the break-evens for the capital expenses (CapEx). Two different scenarios were developed using the example of a survey dairy farm with an annual electricity consumption of approximately 80,000 kWh in the cowshed and an annual diesel consumption of 35,000 L, corresponding to 350,000 kWh for field work. To ensure the energy supply, Scenario 1 required a photovoltaic system (PV) on the roof with an output of 125 kWp, a 250 kW small wind turbine, a battery with a storage capacity of 2 kWh and synthetic fuel production with an output of 210 kW. Scenario 2 required a 200 kWp PV system on the roof and a 520 kWp PV system in the open fields, a battery with a 105 kWh storage capacity and a synthetic fuel production facility with an output of 385 kW to cover the farm’s energy needs. The results showed that a farm’s own electricity production is currently profitable; however, a farm’s production of synthetic fuel still has comparatively high costs and therefore is not yet profitable. Further technical advances, rising prices of fossil fuels and economies of scale, e.g., larger cooperatively-operated plants, could help new technology to make a breakthrough.

Human in the Loop: Industry 4.0 Technologies and Scenarios for Worker Mediation of Automated Manufacturing

Industry 4.0 derived technologies have the potential to enable a new wave of digital manufacturing solutions for semi and fully automated production. In addition, this paradigm encompasses the use of communication technologies to transmit data to processing stations as well as the utilization of cloud based computational resources for data mining. Despite the rise in automation, future manufacturing systems will initially still require humans in the loop to provide supervisory level mediation for even the most autonomous production scenarios. Through a structured review, this paper details a number of key technologies that are most likely to shape this future and describes a range of scenarios for their use in delivering human mediated automated and autonomous production. This paper argues that in all cases of future manufacturing management it is key that the human has oversight of critical information flows and remains an active participant in the delivery of the next generation of production systems.

Industry 4.0: contributions of holonic manufacturing control architectures and future challenges

The flexibility claimed by the next generation production systems induces a deep modification of the behaviour and the core itself of the control systems. Over-connectivity and data management abilities targeted by Industry 4.0 paradigm enable the emergence of more flexible and reactive control systems, based on the cooperation of autonomous and connected entities in the decision-making process. From most relevant articles extracted from existing literature, a list of 10 key enablers for Industry 4.0 is first presented. During the last 20 years, the holonic paradigm has become a major paradigm of Intelligent Manufacturing Systems. After the presentation of the holonic paradigm and holon properties, this article highlights how historical and current holonic control architectures can partly fulfil I4.0 key enablers. The remaining unfulfilled key enablers are then the subject of an extensive discussion on the remaining research perspectives on holonic architectures needed to achieve a complete support of Industry4.0.

A human-in-the-loop manufacturing control architecture for the next generation of production systems

In recent years, the introduction of Industry 4.0 technologies in the manufacturing landscape promoted the development of smart factories characterised by relevant socio-technical interactions between humans and machines. In this context, understanding and modelling the role of humans turns out to be crucial to develop efficient manufacturing systems of the future. Grounding on previous researches in the field of Human-in-the-Loop and Human Cyber-Physical Systems, the paper aims at contributing to a deep reflection about human-machine interaction in the wider perspective of Social Human-in-the-Loop Cyber-Physical Production Systems, in which more agents collaborate and are socially connected. After presenting an evolution of manufacturing control organisations, an architecture to depict social interactions in smart factories is proposed. The proposed architecture contributes to the representation of different human roles in the smart factory and the exploration of both hierarchical and heterarchical data-driven decision-making processes in manufacturing.

A manufacturing cost analysis framework to evaluate machining and fused filament fabrication additive manufacturing approaches

The goal of this research is to develop a costing framework and explore opportunities for fabricating components using additive manufacturing (AM) and machining approaches. The examples target plastic machining, and the fused deposition modeling AM process, but the general model structure is applicable for other AM processes as process knowledge is developed. The question “when is machining more cost-effective than AM” has not been comprehensively addressed. The purpose of this work is to develop a costing framework to provide insight on whether to use machining or AM. An estimation model which considers the process planning, setup, and fabrication time-cost elements is developed in a structured manner. This is challenging due to the machining process planning complexity, the decision-making, and the skill set required, especially for complex surface finish machining. This framework can be readily adapted to suit specific environments. The estimation time models are linked to a cost model, and comparisons are drawn, based on the form complexity and manufacturing quantity. An effective combination of AM and machining technologies could bring about a new hybrid manufacturing approach that meets the requirements of the next generation of production systems, especially for short-run production. A cost-benefit analysis is performed to illustrate solution approaches for designing additive, subtractive, or hybrid operation sets for a variety of components to highlight the merits of the presented approach. Exploring a larger solution space of processing options and their processing time and costs will allow designers to generate more cost-competitive solutions.

Production scheduling and nesting in additive manufacturing

Abstract Additive manufacturing AM – 3D printing – is evolving and is currently experiencing its phase of industrialization. Applications are multiple and some are starting to have a real impact on the supply chain. With the use of layer-by-layer additive construction manner, AM changed the way of designing and manufacturing parts. AM technologies are planned to be the core of the next generation of production systems. Still, only few planning and scheduling approaches are proposed in the literature in order to operate AM systems efficiently. In this work, the planning, nesting and scheduling problem in additive manufacturing is introduced. The aim is to satisfy the orders received from different distributed customers by due dates. The rising interest comes as AM’s reaching a threshold level of maturity and the existing production planning and scheduling approaches have to be adapted and further developed in order to meet the technical and the organizational requirements of the additive manufacturing technologies. The mathematical formulation of the problem is presented, and a heuristic approach is proposed and developed in Python in order to solve it. The proposed heuristic solution is explained step by step, and illustrated using a numerical example. Experimental tests using the proposed heuristic are carried out, underlining the importance of planning/scheduling for an optimized production with AM.

Evolution of holonic control architectures towards Industry 4.0: A short overview

The flexibility claimed by the next generation production systems induces a deep modification of the behavior and the core itself of the control systems. Overconnectivity and data management abilities targeted by Industry 4.0 paradigm enable the emergence of more flexible and reactive control systems, based on the cooperation of autonomous and connected entities in the decision making process. For the last 20 years, holonic paradigm has become the core paradigm of those evolutions, and evolved in itself. This contribution aims at emphasizing the conceptual evolutions in the application of holonic paradigm in the control architectures of manufacturing systems and highlighting the current research trends in this field.

Ubiquitous manufacturing system based on Cloud: A robotics application

Modern manufacturing industry calls for a new generation of production system with better interoperability and new business models. As a novel information technology, Cloud provides new service models and business opportunities for manufacturing industry. In this research, recent Cloud manufacturing and Cloud robotics approaches are reviewed. Function block-based integration mechanisms are developed to integrate various types of manufacturing facilities. A Cloud-based manufacturing system is developed to support ubiquitous manufacturing, which provides a service pool maintaining physical facilities in terms of manufacturing services. The proposed framework and mechanisms are evaluated by both machining and robotics applications. In practice, it is possible to establish an integrated manufacturing environment across multiple levels with the support of manufacturing Cloud and function blocks. It provides a flexible architecture as well as ubiquitous and integrated methodologies for the Cloud manufacturing system. A ubiquitous manufacturing system based on Cloud manufacturing.Industrial robots utilized as implementation applications in the Ubiquitous manufacturing environment.Systematic analysis and guidelines for adpoting advanced manufacturing technologies.Multiple deployment models for private, community and public scenarios.Proposed system is implemented and evaluated in the near-real manufacturing environment.

Developing and Harnessing the Potential of SMEs for Eco-efficient Flexible Production

Production-oriented ICT solutions, offering an intelligent networking of value adding systems, which are interconnected and able to communicate with each other and with the Internet, are seen as key enablers for next generation production systems in “Industry 4.0” scenarios. These future manufacturing systems will be more energy efficient, saving limited resources and having a minimized negative impact on the environment. They also will be able to adapt to new requirements and conditions, incorporating and harnessing human flexibility, creativity and problem-solving capabilities. That's why, apart from ready-to-use technical systems and adequate organizational structure, competent employees, qualified to interact with and to make use of those technologies are of major importance for the success of “Industry 4.0”. Especially SMEs with limited R&D capabilities have to overcome significant obstacles in order to implement the elements mentioned above. The paper introduces the “E3ResearchFactory” located at Fraunhofer IWU in Chemnitz and demonstrates on several examples, which specific solutions and use cases are developed and transferred towards small and medium-sized production companies.

Process Planning and Decentralised Process Control for Cybertronic Production Systems

Cybertronic systems which augment mechatronic basis systems by means of communication, collaboration and intelligence are proposed to be utilised to develop next generation production systems. A model-based development process is proposed to enable integrated design and development of the product and the production system. This paper will highlight the importance of process planning as collaborative activity within the integrated design and development process. A concept will be introduced how process planning can be conducted for cybertronic production systems, considering decentralised production planning and control already during the design phase.

The IDEAS project: plug & produce at shop‐floor level

PurposeCurrent major roadmapping efforts have all clearly underlined that true industrial sustainability will require far higher levels of systems' autonomy and adaptability. In accordance with these recommendations, the Evolvable Assembly Systems (EAS) has aimed at developing such technological solutions and support mechanisms. Since its inception in 2002 as a next generation of production systems, the concept is being further developed and tested to emerge as a production system paradigm. The essence of evolvability resides not only in the ability of system components to adapt to the changing conditions of operation, but also to assist in the evolution of these components in time. Characteristically, Evolvable systems have distributed control, and are composed of intelligent modules with embedded control. To assist the development and life cycle, a methodological framework is being developed. After validating the process‐oriented approach (EC FP6 EUPASS project), EAS now tackles its current major challenge (FP7 IDEAS project) in proving that factory responsiveness can be improved using lighter multi‐agent technology running on EAS modules (modules with embedded control). The purpose of this paper is to detail the particular developments within the IDEAS project, which include the first self re‐configuring system demonstration and a new mechatronic architecture.Design/methodology/approachThe paper covers the development of a plug & produce system for FESTO AG. The work covers the background methodology and details its constituents: control system, architecture, design methodology, and modularity. Specific detail is reserved for the configuration approach which integrates several tools, and the commercially available control boards. The latter have been specifically developed for distributed control applications.FindingsThe paper details probably the first self‐configuring assembly system at shop‐floor level. This is one of the very first industrial plug & produce systems, in which equipment may be added/removed with no programming effort at all.Research limitations/implicationsThe paper reports the findings and development carried out within the framework of a single project. It also clarifies that the solution is not a general panacea for all the issues within assembly.Practical implicationsThe implications are quite large as the work proves the validity of an approach that could change our way of designing and building assembly systems. In the words of an industrial partner, this is “a new way of engineering assembly systems”.Social implicationsShould this approach be used in industry then the implications could be huge. It would, for example, mean that new services are created, whereby assembly system modules are leased to users through a network of depots, rather than bought at a high cost. The system modules also have a far longer lifespan, implying very good ecological solutions.Originality/valueThe highly original paper describes what is probably one of the very first projects to show that distributed control at shop‐floor level is viable and technologically feasible.

Evolvable systems: an approach to self-X production

Current major road mapping efforts, such as ManuFuture, FutMan and EUPASS, have all clearly underlined that true industrial sustainability will require far higher levels of systems' autonomy and adaptability. In accordance with these recommendations, the Evolvable Production Systems (EPS) has aimed at developing such technological solutions and support mechanisms. Since its inception in 2002 (Onori, M., 2002. In: ISR2002 – 33rd International Symposium on Robotics, Stockholm, 617–621) as a next generation of production systems, the concept is being further developed and tested to emerge as a production system paradigm. The essence of evolvability resides not only in the ability of system components to adapt to the changing conditions of operation but also to assist in the evolution of these components in time such that processes may become self-X, X standing for one or more desirable properties of a system subjected to a variable operation condition such as self-evolvable, self-reconfigurable, self-tuning, self-diagnosing, and so on. Characteristically, evolvable systems have distributed control and are composed of integrated intelligent modules. To assist the development and life cycle issues, comprehensive methodological framework is being developed. A concerted effort is being exerted through European research projects in collaboration with European manufacturers, technology/equipment suppliers and universities. After briefly stating the fundamental concepts of EPS, this article presents current developments and applications.

EVOLVABLE PRODUCTION SYSTEMS : MECHATRONIC PRODUCTION EQUIPMENT WITH PROCESS-BASED DISTRIBUTED CONTROL

Current major roadmapping efforts have all clearly underlined that true industrial sustainability will require far higher levels of systems’ autonomy and adaptability. In accordance with these recommendations, the Evolvable Production Systems (EPS) has aimed at developing such technological solutions and support mechanisms. Since its inception in 2002 as a next generation of production systems, the concept is being further developed and tested to emerge as a production system paradigm. The essence of evolvability resides not only in the ability of system components to adapt to the changing conditions of operation, but also to assist in the evolution of these components in time such that processes may become self-evolvable, self-reconfigurable, self-tuning, self-diagnosing, etc. Characteristically, Evolvable systems have distributed control, and are composed of intelligent modules with embedded control. To assist the development and life cycle issues, a comprehensive methodological framework is being developed. A concerted effort is being exerted through European research projects in collaboration with European manufacturers, technology/equipment suppliers, and universities. After briefly stating the fundamental concepts of EPS, this paper presents current developments and applications.

Application of Artificial Intelligence in Computer Integrated Manufacturing

Being understood as a new generation production systems, computer integrated manufacturing (CIM) should comprise artificial intelligence (AI). However, studies in the field of CIM do not centre around any overall concept of AI. Still, it is important to view AI as a CIM-oriented structure. The rapid development of knowledge-handling tools and systems may soon bring the appearance of numerous “islands of automation” in the factory, that will be difficult to integrate. These considerations motivate the present study, starting from a multy-layer and a multy-aspect functional CIM-model with given properties. In general, two points are considered: the application of existing AI-forms in the structure of CIM, and the problems of the development of the necessary distributed and integrated knowledge-handling computer environment for the factory of the future. As a result, principles are defined that may guide the development, delivery and implementation of AI in CIM.