Intelligent Factory Research Articles

Innovative methods in the construction of digital twin factory

The digital twin factory is the digital twin model of the physical factory. It can accurately reflect the physical world. In the early stage of building an intelligent factory, it is very meaningful to design a digital twin model of a physical factory through process planning, logistics optimization, layout planning, and so on, to shorten the time of building and debugging a physical factory. This paper takes the construction of an intelligent factory for laptop assembly as an example. Firstly, construct the model of the laptop disassembly/assembly graph. Because assembly is the reverse process of disassembly, the algorithm is used to plan the assembly sequence of the laptop. After that, the digital twin model of the laptop assembly line according to the laptop assembly process sequence. Subsequently, time series optimization was used to optimize the bottleneck process of the model, resulting in a 424% increase in output. Lastly, we explain the modules and steps used to build the physical laptop factory. This paper innovatively takes the laptop assembly process sequence as the main line of factory construction and takes the bottleneck process time chain optimization as the breakthrough of capacity improvement, which verifies the important role and significance of digital twin factories in constructing intelligent factories. It provides a basis for the promotion and application of digital twin technology in constructing intelligent factories.

Intelligent Factory with Environment Quality Control Based on Fuzzy Method through Deep Reinforcement Learning

Intelligent Factory with Environment Quality Control Based on Fuzzy Method through Deep Reinforcement Learning

Research on AGV Path Planning Integrating an Improved A* Algorithm and DWA Algorithm

With the rapid development of the economy and the continuous improvement of people’s living standards, the printing and packaging industry plays an increasingly important role in people’s lives. The traditional printing industry is a discrete manufacturing industry, relying on a large amount of manpower and manual operation, low production efficiency, higher labor costs, wasting of resources, and other issues, so the realization of printing factory intelligence to improve the competitiveness of the industry is an important initiative. Automatic guided vehicles (AGVs) are an important part of an intelligent factory, serving the function of automatic transportation of materials and products. To optimize the movement paths of AGVs, enhance safety, and improve transportation efficiency and productivity, this paper proposes an alternative implementation of the A* algorithm. The proposed algorithm improves search efficiency and path smoothness by incorporating the grid obstacle rate and enhancing the heuristic function within the A* algorithm’s evaluation function. This introduces the evaluation subfunction of the nearest distance between the AGV, the known obstacle, and the unknown obstacle in the global path in the dynamic window approach (DWA algorithm), and reduces the interference of obstacles with the AGV in global path planning. Finally, the two improved algorithms are combined into a new fusion algorithm. The experimental results show that the search efficiency of the fusion algorithm significantly improved and the transportation time shortened. The path smoothness significantly improved, and the closest distance to obstacles increased, reducing the risk of collision. It can thus effectively improve the productivity of an intelligent printing factory and enhance its flexibility.

A human-centric methodology for the co-evolution of operators’ skills, digital tools and user interfaces to support the Operator 4.0

The concept of Operator 4.0 has been recently defined to evolve the modern industrial scenarios by defining a knowledge sharing process from/to operators and industrial systems, creating personalized skills, and introducing digital tools towards socially sustainable factories. In this context, dynamic and adaptive user interfaces can make humans part of the intelligent factory system, supporting human work contextually and providing specific contents when needed, preserving the human wellbeing. This paper defines a human-centric methodology for the symbiotic co-evolution of operators’ skills, assistive digital tools and user interfaces, developed within the Horizon Europe project titled “DaCapo - Digital assets and tools for Circular value chains and manufacturing products”. The project focuses on defining a new set of human-centric digital tools and services for the manufacturing industry capable of boosting the application of circular economy (CE) throughout the manufacturing value chains. The proposed methodology can link the specific needs of an industrial case to the definition of the most proper assistive digital tools and functionalities to drive the design of adaptive, proactive user interfaces for the Operator 4.0. The method has been applied and validated on one of the project use cases, involving a manufacturing company operating in warehousing and logistics.

Green flexible production and intelligent factory building structure design based on improved ant colony algorithm

Traditional factory production has limitations such as energy waste, emission pollution, etc., and there are also certain unreasonable structural aspects. Therefore, this article proposes a method that can make the factory building structure more green, flexible, and intelligent. It is hoped that by improving the ant colony algorithm and applying it to factory design and production, the goal of reducing energy consumption, maximizing resource utilization, and reducing environmental impact can be achieved. Transforming the design problem of factory building structure into an optimization problem using ant colony algorithm, that is, finding the optimal path and layout. In this process, the ant colony algorithm simulates the behavior of ants by continuously iterating and updating the concentration of pheromones, in order to achieve the global optimal solution. In order to achieve the combination of green design principles and flexible production needs, corresponding constraint conditions and objective functions were introduced, taking into account the flexibility and adjustability within the factory to meet different production needs. Ant colony algorithm can provide the best structural design solution for factory buildings by optimizing search, combining green design principles and flexible production requirements, and promoting the development of green and sustainable factory buildings.

A data and knowledge driven autonomous intelligent manufacturing system for intelligent factories

The non-ferrous metal industry is encountering several challenges, including production efficiency, manufacturing information fragmentation, and human health problems, which highlights the importance of implementing autonomous intelligent manufacturing systems (AIMS). Recently, the foundation model like GPT-4, has garnered attentions due to its exceptional capabilities and proficiency in diverse domains and tasks, facilitating the realization of AIMS. However, the existing foundation models can only address basic general-purpose tasks and are difficult to use for industrial applications. In this paper, we propose a data and knowledge driven AIMS with industrial-generative pretrained Transformer (Industrial-GPT) for intelligent factories. The paradigms and architecture of autonomous intelligent factories are firstly defined. Then, we explore the mechanism with knowledge graph, digital twin, and Industrial-GPT, including multi-level autonomous perception, cross layer and domain cognition, and event-driven collaborative decision-making. Finally, the detailed case study is based on the cooperation with a zinc smelting intelligent factory to achieve networked collaborative manufacturing, and explores the theory and realization mechanism of AIMS on a small scale. We explore the experimental analyses, evaluation mechanisms and platform applications of AIMS at the workshop level. We believe this will help to realize larger scale AIMS in the future.

Intelligent factory layout design framework through collaboration between optimization, simulation, and digital twin

Intelligent factory layout design framework through collaboration between optimization, simulation, and digital twin

Research on Real Time Data Monitoring Method for Intelligent Factory Equipment Based on Ethernet Communication

<p>This article focuses on the production and processing of sleeve parts, using Ethernet as a data transmission medium to complete data collection and monitoring of typical intelligent factory processing workshops. Firstly, the layout design of the intelligent factory equipment layer, communication layer, and system application layer was completed. Then, unified management of standard and non-standard protocols was implemented for communication between different devices. Then, based on the sensors and sensor data used in each production process, a data collection scheme was designed, and finally, the data collection system was designed, Real time monitoring of data between various devices in the system can guide enterprise production.</p> <p> </p>

The Competence in the Digital Era in Improving Public Service Performance

This study will explain the competence of human resources in the digital era to influence better performance. The human resources needed by the industry today are those who have competence in using digital technology. This competency is to realize intelligent factories, such as the Internet of Things (IoT). The era of the industrial revolution 4.0 opens opportunities for human resources (HR) to have skills following the latest technological developments. For this reason, civil servants who are state apparatus must be able to answer the challenges and master competencies in the digitalization era, including complex problem solving, critical thinking, creativity, human resource management, coordination with others, emotional intelligence, judgment and decision making, orientation service, Negotiation, and cognitive flexibility. This study uses quantitative research methods through the distribution of questionnaires or questionnaires to respondents who have been determined using sampling. The analytical technique used is structural equation modeling analysis. The results show that the appropriate competencies in the digitalization have a significant influence on the performance of public services.

Empirical analysis of key operational characteristics of lean six sigma and Industry 4.0 integration

PurposeTo achieve changing customer demands, organizations are striving hard to embrace cutting-edge technologies facilitating a high level of customization. Industry 4.0 (I4.0) implementation aids in handling big data that could help generate customized products. Lean six sigma (LSS) depends on data analysis to execute complex problems. Hence, the present study aims to empirically examine the key operational characteristics of LSS and I4.0 integration such as principles, workforce skills, critical success factors, challenges, LSS tools, I4.0 technologies and performance measures.Design/methodology/approachTo stay competitive in the market and quickly respond to market demands, industries need to go ahead with digital transformation. I4.0 enables building intelligent factories by creating smart manufacturing systems comprising machines, operators and information and communication technologies through the complete value chain. This study utilizes an online survey on Operational Excellence professionals (Lean/Six Sigma), Managers/Consultants, Managing Directors/Executive Directors, Specialists/Analysts/Engineers, CEO/COO/CIO, SVP/VP/AVP, Industry 4.0 professionals and others working in the field of I4.0 and LSS. In total, 83 respondents participated in the study.FindingsBased on the responses received, reliability, exploratory factor analysis and non-response bias analysis were carried out to understand the biasness of the responses. Further, the top five operational characteristics were reported for LSS and I4.0 integration.Research limitations/implicationsOne of the limitations of the study is the sample size. Since I4.0 is a new concept and its integration with LSS is not yet explored; it was difficult to achieve a large sample size.Practical implicationsOrganizations can utilize the study findings to realize the top principles, workforce skills, critical success factors, challenges, LSS tools, I4.0 tools and performance measures with respect to LSS and I4.0 integration. Moreover, these operational characteristics will help to assess the organization's readiness before and after the implementation of this integration.Originality/valueThe authors' original contribution is the empirical investigation of operational characteristics responsible for I4.0 and LSS integration.

Intelligent Factory Perception Ability Using Distributed Knowledge Graph

Intelligent Factory Perception Ability Using Distributed Knowledge Graph

Big Data Literature-based Bibliometric Mapping Analysis for Competences Adaptable to Industry 4.0 and 5.0: Implications for Career Orientation

This study recognizes the presence of a competence-based foundation in the career orientations of both graduate students and professionals. The career orientations of graduating students and professionals, encompassing their interests and objectives, are strongly influenced by their competencies. Competence is an essential foundation for making career choices and aligns with the firm-based competitive advantage that relies on competence (e.g., core competence and dynamic capability). Fundamentally, competence is also a structure of “career orientation” that delivers unique functions of a person or an organization, manifesting VRINO properties of differentiation (e.g., valuable, rare, inimitable, non-substitutable, and organized). Graduating students and professionals build know-why competencies (that relate to career motivation, personal meaning and identification, know-how competencies (functioning strengths that contribute to a firm’s repertoire of overall capabilities), and know-whom competencies, including communication capability. The concept of competence in career orientation is often overlooked, and only a select few deeply understand how competencies should be integrated with other aspects of career orientation. This study examines the typological characteristics of career orientation and its anchors, addressing the need for more knowledge in the current literature. Industry 4.0 and 5.0 exemplify the competencies that graduating students and professionals should possess. These industries and societies utilize intelligent cyber-physical interactions to impact various aspects such as lifestyles, product development, process controls, and industry advancement. This study utilizes the bibliometric analysis method within the limitations of research papers. It applies the Sciencedirect.com databases and focuses on the keywords “Industry 4.0 and Industry 5.0” to identify the competence clusters, essentially a thematic analysis of the interrelationships of a cluster of themes that explain the competence profile for Industry 4.0 and Industry 5.0. Six competence profiles are identified using the bibliometric method: (1) key driver cluster represented by the cyber-physical system, (2) intelligence infrastructure and intelligent factory, (3) intelligence system and resilience, (4) sustainable development goals, (5) supply chain management, stakeholders, sustainable economy, big data analytics, and digital technology, and (6) intelligent businesses. Three typological dimensions of career orientation are proposed: instrumentality (self-organization continuum), value (stability-flexibility continuum), and competence superimposition, which includes core competence in the stability segment and dynamic capability in the flexibility segment. In the context of I4 and I5, it is suggested that graduating students and professionals build a global mindset and technological competence to support globally competent organizations and their businesses.

Development of a cloud intelligent machine monitoring and control system

Facing the trend of Industry 4.0, the cloud-based supervisory control and data acquisition (SCADA) system employing cloud computing and IoT technology can help the manufacturing industry reduce software investment and system maintenance costs. However, manufacturers may need to install new sensors and controllers, the connection of SCADA system and shop floor machine controller, monitoring dashboard design and implementation usually need to outsource to an experienced system integration company, which may impede medium-sized manufacturing enterprises (SMEs). This paper aims to develop a cloud-based intelligent machine monitoring and control system (CIM-MCS) framework, the service structure, and approach to deploying the CIM-MCS in a public cloud infrastructure platform and service provider. The package diagram is proposed for building the CIM-MCS’s virtual factory model to improve modeling efficiency and data stability. CIM-MCS and its SCADA application in a leading automatic filling and packaging production line show that the CIM-MCS is easy to implement. The transmission time is short and acceptable for practical application. The integration of CIM-MCS with a cloud-based advanced planning scheduling system has the advantage of real-time monitoring, production progress reporting, scheduling, and dispatching and achieves the goal of anytime, anywhere, anyone, and any platform operating an intelligent factory.

Strip running deviation monitoring and feedback real-time in smart factories based on improved YOLOv5

The strip running deviation in steel production can cause significant economic losses by forcing a shutdown of the whole steel production line. However, due to the fast running speed (100–140 m/min) of the strip, it a difficult problem to accurately judge online whether the strip running deviation or not and control its deviation during operation. In this paper, a fast and accurate model for detecting strip running deviation is proposed, this model allows for real-time control of strip operation deviation according to the detection model’s results. In our model, the attention module is used to improve the detection accuracy. The rolling equipment’s pressing force can be real-time controlled to correct the strip running deviation. Compared with the original model, the proposed model in this paper achieves an increase in accuracy of 3 %, and the detection speed can reach 29 FPS, meeting the real-time requirements. This work can provide ideas for applying computer vision in construction of intelligent factories.

Development of hybrid surrogate model structures for design and optimization of CO2 capture processes: Part I. Vacuum pressure swing adsorption in a confined space

Design and optimization of CO2 capture processes have become a tremendously active area of research particularly in the past decade. In this context, development of intelligent techniques on the basis of first-principles models coupled with data-driven algorithms for such purpose looks very promising. In a series of works, we intend to present mechanism approaches in order to develop applicable structures for design and optimization of the CO2 capture processes of interest via hybrid models. A systematic method is presented for optimizing a process for capturing CO2 from a confined space through a Vacuum Pressure Swing Adsorption (VPSA) operation using a Hybrid Surrogate Model (HSM) and Non-dominated Sorting Genetic Algorithm (NSGA-III). The surrogate model is structured based on the VPSA process model offered in the Aspen Adsorption® environment and an artificial intelligence (AI) data-driven algorithm. The developed HSM is then used to predict the key process outputs including CO2 purity, air recovery ratio and energy consumption rate. Accordingly, the optimized parameters are re-substituted into the VPSA process simulator for further data processing. It is demonstrated that the proposed model architecture provides considerable computational efficiency for the process optimization with only 48 h to complete the corresponding evolutionary search, while the optimization time by the conventional NSGA-direct method is close to 1129 h. The optimization results also show that the CO2 purity changes from 1000 ppm to 399 ppm, the air recovery ratio remains at 93 %, and the energy consumption per unit product (ECP) decreases by 38.5 % to 99.7 kJ·Nm−3 air after an optimized air purification operation. The idea of chemical mechanism and industrial data twin modeling in this study holds substantial importance for the development of digital chemical twin systems and the process optimization of intelligent factory.

Hybrid traffic security shaping scheme combining TAS and CQSF of time-sensitive networks in smart grid

The new intelligent factory introduces Time-Sensitive Network into industrial Ethernet to provide real time and deterministic guarantee communication for production system. Since the problem pertaining to data leakage or damage during transmission has increasingly become pronounced, security protection technology has been introduced, but this technology will bring about a delay in user response and a decline in the quality of service. Meanwhile, ensuring the deterministic mixed transmission of time-sensitive and large-bandwidth data traffic supported by the same switching device is a still challenging problem. Therefore, this study proposes a hybrid security scheduling scheme which combines Time-Aware Shaper and cycle specified queuing and forwarding (CSQF). Specifically, the mechanism first adopts various encryption methods for different traffic, and afterward, it reduces its resource occupation by adjusting the sampling period of the time-sensitive traffic. At the same time, it adopts CSQF to schedule the large-bandwidth data traffic, thereby improving the scheduling success rate. According to the experimental results, this scheme enhances network security and network scheduling success rate by up to 51%. The scheduling of mixed traffic in the Time-sensitive Network is realized securely and efficiently.

Cooperative Dynamic Motion Planning for Dual Manipulator Arms Based on RRT*Smart-AD Algorithm.

Intelligent manufacturing requires robots to adapt to increasingly complex tasks, and dual-arm cooperative operation can provide a more flexible and effective solution. Motion planning serves as a crucial foundation for dual-arm cooperative operation. The rapidly exploring random tree (RRT) algorithm based on random sampling has been widely used in high-dimensional manipulator path planning due to its probability completeness, handling of high-dimensional problems, scalability, and faster exploration speed compared with other planning methods. As a variant of RRT, the RRT*Smart algorithm introduces asymptotic optimality, improved sampling techniques, and better path optimization. However, existing research does not adequately address the cooperative motion planning requirements for dual manipulator arms in terms of sampling methods, path optimization, and dynamic adaptability. It also cannot handle dual-manipulator collaborative motion planning in dynamic scenarios. Therefore, in this paper, a novel motion planner named RRT*Smart-AD is proposed to ensure that the dual-arm robot satisfies obstacle avoidance constraints and dynamic characteristics in dynamic environments. This planner is capable of generating smooth motion trajectories that comply with differential constraints and physical collision constraints for a dual-arm robot. The proposed method includes several key components. First, a dynamic A* cost function sampling method, combined with an intelligent beacon sampling method, is introduced for sampling. A path-pruning strategy is employed to improve the computational efficiency. Strategies for dynamic region path repair and regrowth are also proposed to enhance adaptability in dynamic scenarios. Additionally, practical constraints such as maximum velocity, maximum acceleration, and collision constraints in robotic arm applications are analyzed. Particle swarm optimization (PSO) is utilized to optimize the motion trajectories by optimizing the parameters of quintic non-uniform rational B-splines (NURBSs). Static and dynamic simulation experiments verified that the RRT*Smart-AD algorithm for cooperative dynamic path planning of dual robotic arms outperformed biased RRT* and RRT*Smart. This method not only holds significant practical engineering significance for obstacle avoidance in dual-arm manipulators in intelligent factories but also provides a theoretical reference value for the path planning of other types of robots.

AP-CDE: Cost-Efficient Authentication Protocol for Cross-Domain Data Exchange in IIoT

The Industrial Internet of Things (IIoT) is a new network paradigm emerging from the Internet of Things (IoT). It is primarily used in smart factories to promote smart manufacturing and increase productivity. Smart industrial devices collect real-time data from other domains (i.e., intelligent factories) that collaborate on the same transaction and transmit crucial data via a public internet channel. When applied to resource-constrained smart industrial communication devices, this process causes issues in communication security and privacy. Consequently, this study develops a cost-effective authentication protocol for cross-domain data exchange (AP-CDE) in IIoT. Anticollision hash functions, bitwise Exclusive- <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">or</small> operations, and Chebyshev polynomial operations are used in this protocol. AP-CDE security is achieved by using precise formal and nonmathematical (informal) analysis methods. The analysis results show that the developed protocol can withstand various well-known threatening attacks. Finally, a detailed comparative analysis between the AP-CDE and other interrelated protocols is used to verify that the AP-CDE outperforms other protocols in terms of security and functional characteristics, communication overheads, and computational costs.

The architecture evolution of intelligent factory logistics digital twin from planning, implement to operation

Digital twin is widely studied in the context of industry 4.0. It is expected that the application of digital twin in intelligent factory logistics can enrich connectivity, proactivity, and agility of the logistics. Architecture is one of the significant factors impacting on the selection of appropriate enabling technologies for constructing the intelligent logistics. This paper proposes a digital twin architecture for intelligent factory logistics. It mainly includes a physical layer, two cyber layers, and an interface layer. The architecture is in compliance with the architecture of the Human-Cyber-Physical System (HCPS). Moreover, the evolution of the architecture is elaborated during the planning, implement, and operation stages when construction of the digital twin. At the initial stage, human should participate in the decision-making process frequently to determine whether the results given by digital twin need to be changed. However, the data-driven model based digital twin will continually learn the human’s changing behaviors, thus constantly updating itself. It can evolution from digital model, digital shadow to digital twin with the continuous construction process. The ultimate digital twin should be able to assess operational key performance indicators (KPIs) and handle dynamic events.

Design of an improved intelligent optimization logistics path planning model for the background of the new industrial era

ABSTRACT In the context of the new industrial era, intelligent manufacturing, intelligent factories, and intelligent logistics have become hot topics during the industrial revolution. In order to meet the flexibility, flexibility, and efficiency of factory logistics in the era of Industry 4.0, and improve the punctuality of logistics distribution, a factory logistics path planning model is designed based on grid environment and Ant colony optimization algorithms. The algorithm optimizes and improves the search ability and adaptability of Ant colony optimization algorithms. The test results show that the Pheromone volatile number is 0.3, which is a moderate value. When the importance of Pheromone is 3 and the heuristic factor is 6, the average optimal cost and the average number of iterations are the minimum. As the variable increases, both evaluation indicators show a trend of decreasing first and then increasing. The improvement of the initial Pheromone can speed up the Rate of convergence of the algorithm, while the quality of the planned path results is better than that of the traditional planned path, and the shortest path length is reduced from 26.46 to 24.38. The path smoothed by B-spline curve is smooth and continuous. The algorithm proposed by the research institute converges quickly, with the shortest path value being 59.43, and the maximum reduction in path length reaching 18.44%. The optimized path length converges quickly after fluctuations, and the algorithm has strong adaptability to the environment. This model can achieve accurate logistics path planning, provide competitive solutions for the implementation of intelligent logistics in factories, and promote the 4.0 factory to build a truly intelligent factory.