Deep reinforcement learning for selecting demand forecast models to empower Industry 3.5 and an empirical study for a semiconductor component distributor

A semiconductor distributor that plays a third-party role in the supply chain will buy diverse components from different suppliers, warehouse and resell them to a number of electronics manufacturers with vendor-managed inventories, while suffering both risks of oversupply and shortage due to demand uncertainty. However, demand fluctuation and supply chain complexity are increasing due to shortening product life cycle in the consumer electronics era and long lead time for capacity expansion for high-tech manufacturing. Focusing realistic needs of a leading distributor for semiconductor components and modules, this study aims to construct a UNISON framework based on deep reinforcement learning (RL) for dynamically selecting the optimal demand forecast model for each of the products with the corresponding demand patterns to empower smart production for Industry 3.5. Deep RL that integrates deep learning architecture and RL algorithm can learn successful policies from the dynamic and complex real world. The reward function mechanism of deep RL can reduce negative impact of demand uncertainty. An empirical study was conducted for validation showing practical viability of the proposed approach. Indeed, the developed solution has been in real settings.     

An empirical study of demand forecasting of non-volatile memory for smart production of semiconductor manufacturing

As high-speed computing is crucial to empower intelligent manufacturing for Industry 4.0, non-volatile memory (NVM) is critical semiconductor component of the cloud and data centre for the infrastructures. The NVM manufacturing is capital intensive, in which capacity utilisation significantly affects the capital effectiveness and profitability of semiconductor companies. Since capacity migration and expansion involve long lead times, demand forecasting plays a critical role for smart production of NVM manufacturers for revenue management. However, the shortening product life cycles of integrated circuits (IC), the fluctuations of semiconductor supply chains, and uncertainty involved in demand forecasting make the present problem increasingly difficult in the consumer electronics era. Focusing on the realistic needs of NVM demand forecasting, this study aims to develop a decision framework that integrates an improved technology diffusion model and a proposed adjustment mechanism to incorporate domain insights. An empirical study was conducted in a leading semiconductor company for validation. A comparison of alternative approaches is also provided. The results have shown the practical viability of the proposed approach.     

Determinants of information and digital technology implementation for smart manufacturing

This study aims to identify and analyse factors that determine the implementation of Information and Digital Technologies (IDT) of smart manufacturing. By performing a state-of-the-art and content-driven review of literature, consulting a group of experts from academia and industry, and implementing interpretive structural modelling methodology, the study identified eleven enabling factors and mapped the contextual interrelationships among them. The study further explained the complex precedence relationships that exist among determinants of smart manufacturing IDT adoption. Results showed that perceived benefits and management support are the two driver determinants that act as stepping-stones in the implementation of smart manufacturing IDT. Operations technology maturity and cybersecurity maturity were found to be the dependent determinants of smart manufacturing IDT implementation and highly driven by the linkage and driver determinates. The findings are expected to assist academicians, industrialists, and the policymakers with achieving a detailed understanding of smart manufacturing transformation processes, and conditions that facilitate the manufacturing digitalisation in the Industry 4.0 era.     

Implementation of Industry 4.0 and lean production in Brazilian manufacturing companies

The adoption of Industry 4.0 technologies has been deemed as a strategy to increase product quality and make manufacturing processes more efficient. However, the way that these technologies are integrated into existing production systems and which processes they can support is still under investigation. Thus, this paper aims to examine the relationship between lean production (LP) practices and the implementation of Industry 4.0 in Brazilian manufacturing companies. To achieve that we use data from a survey carried out with 110 companies of different sizes and sectors, at different stages of LP implementation. Data collected were analysed by means of multivariate analysis. Our findings indicate that LP practices are positively associated with Industry 4.0 technologies and their concurrent implementation leads to larger performance improvements. Further, the contextual variables investigated do matter to this association, although not all aspects matter to the same extent and effect.     

A framework for operator – workstation interaction in Industry 4.0

We draw on cognitive and behavioural theories and on the artificial intelligence literature in order to propose a framework of future operator – workstation interaction in the ‘Industry 4.0’ era. We name the proposed framework ‘Operator – Workstation Interaction 4.0’. The latter’s capabilities permit an adaptive, ongoing interaction that aims to improve operator safety, performance, well-being, and satisfaction as well as the factory’s production measures. The framework is composed of three subsystems: (1) the observation subsystem which observes the operator and the processes occurring in the workstation, (2) the analysis subsystem which generates understanding and implications of the observations output, (3) the reaction subsystem which determines if and how to respond. The paper describes these elements and illustrate them using an example of a fatigued worker. The contributions, implications, and limitations of the proposed framework are discussed, and future research directions are presented.     

A smart manufacturing adoption framework for SMEs

Smart Manufacturing (SM) a revolutionary paradigm that aims to improve production systems’ performance in terms of quality, time, cost, and flexibility, as well as human and machine decision-making capabilities. Most large enterprises have already taken first steps towards adopting SM. Small and Medium-sized Enterprises (SMEs) on the other hand, are struggling with developing a SM adoption roadmap. Our research builds on the real and perceived needs and challenges faced by manufacturing SMEs and advances the field by developing and evaluating an SME-specific ‘SM adoption framework’. We have employed a multiple case study approach to acknowledge the lessons learned by selected early-adopter SMEs that have recently implemented and deployed SM tools and practices. We propose an SM adoption framework with five vital steps that SMEs interested in SM should follow: (i) identify manufacturing data available within the SME, (ii) readiness assessment of the SME data-hierarchy steps, (iii) developing SM awareness of SME leadership and staff, (iv) develop a SM tailored vision for the SMEs, and (v) identify appropriate SM tools and practices necessary to realise the tailored SM vision. Moreover, the results of the case study analysis enabled us to formulate many generalisations.     

IoT patent roadmap for smart logistic service provision in the context of Industry 4.0

Abstract

Industry 4.0 enables the management of factories manufacturing products with complexity and flexibility. The corresponding logistic services must provide greater accuracy and efficiency in logistic operations. The Internet of Things (IoT) is an important aspect for smart logistics in the context of Industry 4.0. For instance, intelligent logistics models use IoT integrated technologies, e.g. radio frequency identification (RFID), wireless sensor network (WSN) and cloud computing, to enhance the traceability and decision supports of logistic processes in real-time speed, high accuracy, and flexibility. This research focuses on analyzing the related technology roadmaps for the adoption of IoT technologies in smart logistic services. A case research is conducted specifically to identify the relationship between IoT-oriented technologies and deployed advanced logistic services. The logistic operations are organized into an ontology schema based on a four level service framework. The research proposes a roadmap approach to visualize the patent allocations and evolutions corresponding to logistic services at each level. Although the patent roadmap methodology is generic, this research focuses on the two industry leaders, which are UPS and IBM. Using the roadmap methodology, the IoT enabled smart logistic patents are analyzed to identify technology-related business strengths and strategies.     

A rework-based dispatching algorithm for module process in TFT-LCD manufacture

This paper presents development of a scheduling methodology for module processing in thin film transistor liquid crystal display (TFT-LCD) manufacturing. The problem is a parallel machine scheduling problem with rework probabilities, sequence-dependent setup times and due dates. It is assumed that rework probability for each job on a machine can be given through historical data acquisition. The dispatching algorithm named GRPD (greedy rework probability with due-dates) is proposed in this paper focusing on the rework processes. The performance of GRPD is measured by the six diagnostic indicators. A large number of test problems are randomly generated to evaluate the performance of the proposed algorithm. Computational results show that the proposed algorithm is significantly superior to existing dispatching algorithms for the test problems.     

Industry 4.0: Architecture and Equipment Revolution

The development of science and technology has led to the era of Industry 4.0. The core concept is the combination of “material and informationization”. In the supply chain and manufacturing process, the “material” of the physical entity world is realized by data, identity, intelligence, and information. Industry 4.0 is a disruptive transformation and upgrade of intelligent industrialization based on the Internet-of-Things and Big Data in traditional industrialization. The goal is “maximizing production efficiency, minimizing production costs, and maximizing the individual needs of human beings for products and services.” Achieving this goal will surely bring about a major leap in the history of the industry, which will lead to the “Fourth Industrial Revolution.” This paper presents a detailed discussion of industrial big data, strategic roles, architectures, characteristics, and four types of innovative business models that can generate profits for enterprises. The key revolutionary aspect of Industry 4.0 is explained, which is the equipment revolution. Six important attributes of equipment are explained under the Industry 4.0 perspective.     

Sensing,smart and sustainable product development (S3 product) reference framework

Enterprises must become ‘sensing, smart and sustainable (S³)’ to face global challenges related to local, national and global market dynamics. Therefore, reconceptualisation and redesign in these enterprises must accommodate emergent technologies, new practices and strategies. In this sense, enterprises have used new product development as a strategy for remaining competitive in the marketplace; thus, they can provide a new generation of products offering solutions to contemporary social problems and responding to changing consumer demands. These new-generation products are mostly technology-based and consider sustainable objectives. In this context, concepts such as sensing, smart and sustainable products (S³ products) have emerged to satisfy different social requirements. Therefore, this work focuses on providing a reference framework that presents a systematic process for the development of S³ products. This reference framework is based on the integrated product, process and manufacturing system development reference model. The main objective of this work is to fill the gap vis-à-vis the current lack of design roadmaps that permit the development of this new generation of products in S³ enterprises. The development of a reconfigurable micro-machine tool is presented as that of an S³ product.     

Intelligent Manufacturing in the Context of Industry 4.0: A Review

Our next generation of industry—Industry 4.0—holds the promise of increased flexibility in manufacturing, along with mass customization, better quality, and improved productivity. It thus enables companies to cope with the challenges of producing increasingly individualized products with a short lead-time to market and higher quality. Intelligent manufacturing plays an important role in Industry 4.0. Typical resources are converted into intelligent objects so that they are able to sense, act, and behave within a smart environment. In order to fully understand intelligent manufacturing in the context of Industry 4.0, this paper provides a comprehensive review of associated topics such as intelligent manufacturing, Internet of Things (IoT)-enabled manufacturing, and cloud manufacturing. Similarities and differences in these topics are highlighted based on our analysis. We also review key technologies such as the IoT, cyber-physical systems (CPSs), cloud computing, big data analytics (BDA), and information and communications technology (ICT) that are used to enable intelligent manufacturing. Next, we describe worldwide movements in intelligent manufacturing, including governmental strategic plans from different countries and strategic plans from major international companies in the European Union, United States, Japan, and China. Finally, we present current challenges and future research directions. The concepts discussed in this paper will spark new ideas in the effort to realize the much-anticipated Fourth Industrial Revolution.     

The industrial management of SMEs in the era of Industry 4.0

Industry 4.0 provides new paradigms for the industrial management of SMEs. Supported by a growing number of new technologies, this concept appears more flexible and less expensive than traditional enterprise information systems such as ERP and MES. However, SMEs find themselves ill-equipped to face these new possibilities regarding their production planning and control functions. This paper presents a literature review of existing applied research covering different Industry 4.0 issues with regard to SMEs. Papers are classified according to a new framework which allows identification of the targeted performance objectives, the required managerial capacities and the selected group of technologies for each selected case. Our results show that SMEs do not exploit all the resources for implementing Industry 4.0 and often limit themselves to the adoption of Cloud Computing and the Internet of Things. Likewise, SMEs seem to have adopted Industry 4.0 concepts only for monitoring industrial processes and there is still absence of real applications in the field of production planning. Finally, our literature review shows that reported Industry 4.0 projects in SMEs remained cost-driven initiatives and there in still no evidence of real business model transformation at this time.     

The link between Industry 4.0 and lean manufacturing: mapping current research and establishing a research agenda

In recent years, Industry 4.0 has emerged as one of the most discussed concepts and has gained significant popularity in both academia and the industrial sector. Both Industry 4.0 and lean manufacturing utilise decentralised control and aim to increase productivity and flexibility. However, there have been few studies investigating the link between these two domains. This article explores this novel area and maps the current literature. This is achieved through a systematic literature review methodology, investigating literature published up to and including August 2017. This article identifies four main research streams concerning the link between Industry 4.0 and lean manufacturing, and a research agenda for future studies is proposed.     

Sustainable manufacturing in Industry 4.0: an emerging research agenda

This systematic review intends to identify how sustainable manufacturing research is contributing to the development of the Industry 4.0 agenda and for a broader understanding about the links between the Industry 4.0 and Sustainable Manufacturing by mapping and summarising existing research efforts, identifying research agendas, as well as gaps and opportunities for research development. A conceptual framework formed by the principles and technological pillars of Industry 4.0, sustainable manufacturing scope, opportunities previously identified, and sustainability dimensions, guided analysis of 35 papers from 2008–2018, selected by a systematic approach. Bibliometrics data and social network analysis complement results identifying how research is being organised and its respective research agendas, relevant publications, and status of the research lifecycle. Results point to that the current research is aligned with the goals defined by different national industrial programs. There are, however, research gaps and opportunities for field development, becoming more mature and having a significant contribution to fully developing the agenda of Industry 4.0.     

Scopus scientific mapping production in industry 4.0 (2011–2018): a bibliometric analysis

Research in industry 4.0 is growing, driven by the innovations in production systems on a continuous basis. In this study, we identified the evolution of themes inherent in the industry 4.0 using a bibliometric software, namely SciMAT (Science Mapping Analysis Software Tool). The analyses included 1882 documents, 4231 keywords, and the relevant information was extracted based on frequency of co-occurrence of keywords. The clusters were plotted in two-dimensional strategic diagrams and analysed using the bibliometric indicators such as the number of publications, number of associated documents, and h-index. The results revealed that 2017 had the largest number of publications. Expert authors in the field and the periodicals that published the most were identified. The science mapping presented 31 clusters in which the most representative motor themes were CPS (Cyber-Physical System), IoT (Internet of Things), and Big Data. In addition, it was possible to identify fields with high investment of efforts by the scientific community such as the union between lean production and industry 4.0, production-centered CPS (CPPS), IoT (Industrial Internet of Things - IIoT), among others. The overlapping map showed an increase in the number of keywords from 338 to 1231 over the period of data. The map of scientific developments supported by an exhaustive research, it was possible to show the state of the art, the main challenges and perspectives for future research in the field of industry 4.0 such as Technology, Collaboration/Integration, Management and Implementation.     

Cyber-based design for additive manufacturing using artificial neural networks for Industry 4.0

Additive Manufacturing (AM) requires integrated networking, embedded controls and cloud computing technologies to increase their efficiency and resource utilisation. However, currently there is no readily applicable system that can be used for cloud-based AM. The objective of this research is to develop a framework for designing a cyber additive manufacturing system that integrates an expert system with Internet of Things (IoT). An Artificial Neural Network (ANN) based expert system was implemented to classify input part designs based on CAD data and user inputs. Three ANN algorithms were trained on a knowledge base to identify optimal AM processes for different part designs. A two-stage model was used to enhance the prediction accuracy above 90% by increasing the number of input factors and datasets. A cyber interface was developed to query AM machine availability and resource capability using a Node-RED IoT device simulator. The dynamic AM machine identification system developed using an application programme interface (API) that integrates inputs from the smart algorithm and IoT interface for real-time predictions. This research establishes a foundation for the development of a cyber additive design for manufacturing system which can dynamically allocate digital designs to different AM techniques over the cyber network.     

Industry 4.0 and lean manufacturing practices for sustainable organisational performance in Indian manufacturing companies

The current literature claims the direct effects of industry 4.0 technologies (I4?T) on lean manufacturing practices (LMP) and sustainable organisational performance (SOP). LMP are also found to have a positive influence on SOP. However, the integrated effect of I4?T and LMP on SOP has not been empirically investigated. To address this gap, this research study investigates the indirect effects of I4?T on SOP with LMP as the mediating variable; furthermore, it aims to confirm or not the direct effects of I4?T on LMP and SOP. The study is based on data collected from 205 managers, working in 115 manufacturing firms. The findings suggest significant direct and indirect effects of I4?T on SOP and confirm the presence of LMP as a strong mediating variable. The results of the study extend the literature on I4?T by identifying I4?T as an enabler of LMP, leading to enhancement of the SOP. Implications and future research directions for academicians, practitioners, and consultants are provided.     

Lean-pull strategy in a re-entrant manufacturing environment: a pilot study for TFT-LCD array manufacturing

The increase of a panel's size in thin film transistor – liquid crystal display (TFT-LCD), results in an increase in stock space and increased cost from work-in-process (WIP). This paper proposes a lean-pull strategy, combining buffers with CONWIP (CONstant work-in-process), which results in shared resources to a re-entrant process in TFT-LCD manufacturing. The buffer size and CONWIP levels are the decision variables and are solved by simulation optimisation. The proposed procedure is applied to a factory that manufactures TFT-LCD. The study shows that the proposed lean-pull strategy can reduce the cycle time and achieve a reduction of 34.57% in WIP. The automated material handling systems (AMHS) stocker utilisation can be reduced from 62.13% to 18.49% without additional investment or facilities. Sensitivity analysis indicates the maximum daily throughput will achieve over 10% improvement. The empirical results from this pilot study provide useful managerial insights for the production control of array manufacturing.     

Big data and machine learning: A roadmap towards smart plants

Industry 4.0 aims to transform chemical and biochemical processes into intelligent systems via the integration of digital components with the actual physical units involved. This process can be thought of as addition of a central nervous system with a sensing and control monitoring of components and regulating the performance of the individual physical assets (processes, units, etc.) involved. Established technologies central to the digital integrating components are smart sensing, mobile communication, Internet of Things, modelling and simulation, advanced data processing, storage and analysis, advanced process control, artificial intelligence and machine learning, cloud computing, and virtual and augmented reality. An essential element to this transformation is the exploitation of large amounts of historical process data and large volumes of data generated in real-time by smart sensors widely used in industry. Exploitation of the information contained in these data requires the use of advanced machine learning and artificial intelligence technologies integrated with more traditional modelling techniques. The purpose of this paper is twofold: a) to present the state-of-the-art of the aforementioned technologies, and b) to present a strategic plan for their integration toward the goal of an autonomous smart plant capable of self-adaption and self-regulation for short- and long-term production management.     

Design of smart connected manufacturing resources to enable changeability,reconfigurability and total-cost-of-ownership models in the factory-of-the-future

The fourth industrial revolution requires higher capabilities of changeability and reconfigurability (C–R) of the future factories (FoF), as well as a higher focus on business models that are based on total-cost-of-ownership (TCO) paradigm. Up to date, there are little scientific contributions to deploy C–R into TCO models, as well as to systematic plan and design manufacturing resources such as to facilitate FoF ecosystem. In order to address this issue, this paper introduces research results that show how to deploy C–R, connectivity, smartness and TCO requirements into the technical solutions of manufacturing resources of FoF. Contributions emerging from this research include an index to measure C–R capability of manufacturing resources, a model to assess economic feasibility of a FoF over its lifecycle, as well as a methodology and related tools to design smart connected manufacturing resources with embedded features to facilitate changeability and reconfigurability in a FoF. Theoretical contributions are explained through a case study of a fast reconfigurable robotic manufacturing cell. Preliminary results demonstrate that it is possible to rapid design smart connected manufacturing resources and integrate them into FoF architectures that support convertibility, integrability, modifiability, adaptability, serviceability, scalability, integration of resources from various producers, service clustering and cloud-based services.