To meet personalized user demands, customized and personalized production (CPP) has become an effective manufacturing paradigm. However, wired network connections inhibit flexible production line reconfiguration and current DRL methods cannot converge and obtain eligible scheduling results for CPP due to the high-dimensional solution space and the negligence of significant machine reconfiguration time. To address this challenge, we first propose a wireless manufacturing system framework to support ultra-flexible reconfiguration and resource scheduling. Next, we build a reconfiguration oriented scheduling model to reflect the significant impact of reconfiguration time. Then, we design a knowledge guided deep reinforcement learning algorithm to effectively solve the CPP scheduling problem facing the dimension explosion problem. The knowledge guidance incorporates reconfiguration time and machine workload to significantly reduce the feasible action space, enabling the rapid convergence of KGDRL. The experiment results show that our approach provides a robust and scalable solution and obtains shorter total makespan of whole production during scheduling.

With increasing pressure from customized demands, discrete manufacturing systems face challenges due to fluctuating resource requirements. These challenges hinder the synchronization of production logistics (PL), which is essential for coordinating resources and ensuring smooth production. Poor synchronization will result in resources waiting on each other, leading to delays and idle time. Accordingly, this paper proposes ChatSync, a framework leveraging large language model (LLM) and spatial-temporal knowledge reasoning to optimize resource allocation, delivery, and monitoring in industrial applications, particularly within the Industrial Internet of Things (IIoT) environment. First, the resource spatial-temporal graph (RSTG) is constructed by integrating real-time IIoT data and expert operational experience, enhancing the knowledge base of LLM through cross-domain knowledge fusion. Second, graph-based reasoning optimization is presented, incorporating spatial-temporal, contextual, and relational reasoning mechanisms, enabling LLM to achieve credible and responsible analysis and decision-making. Third, the PL-oriented ChatSync framework with knowledge and reasoning engines is proposed, supporting chat-based interactions for resilient resource allocation, personalized suggestion, and precise traceability. A case study in air conditioning manufacturing demonstrates that ChatSync outperforms existing benchmark methods in various PL phases, achieving a delivery punctuality rate of 91.2%.

Foundation models have demonstrated remarkable capabilities in various tasks such as natural language processing, content generation, and complex reasoning and have the potential to spark new technology and application revolutions in the industrial domain. However, Industrial Foundation Models (IFMs) remain almost unexplored, and the industrial sector has domain-specific issues and challenges to address when harnessing the capabilities of foundation models. Therefore, we introduce the concept and construction paradigm of IFMs and propose a 5-dimensional general framework of the IFMs. Moreover, we present the key research issues and technologies of IFMs and discuss some advanced and potential industrial applications. We hope this paper can serve as a useful resource for researchers seeking to innovate within the domain of IFMs.

In this article, we introduce the concept of edge computing power network (EdgeCPN) as a new paradigm to facilitate elastic integration and flexible scheduling of computing resources for task offloading in computing power networks (CPNs). Previous studies mainly focused on scheduling computing resources in the vertical dimension and may not effectively consider the computing resources selection in CPNs with increasingly diverse computing resources, which results in inefficient and unstable computing resource scheduling performance for task offloading. In this article, we design an on-demand computing resource scheduling model to enable efficient task offloading in EdgeCPNs. To improve the search efficiency and stability, we decouple the search for task offloading problems in EdgeCPNs into two stages and present a two-stage evolutionary search scheme (TESA). In stage-1, TESA first optimizes computing resources selection by searching a computing resources subset depending on the user budget, with the objective of maximizing the total gain. In stage-2, TESA jointly optimizes task offloading decisions and computing resources allocations based on the subset found in stage-1, with the objective of minimizing total delay. Numerical results confirm that the proposed scheme significantly enhances the efficiency and stability of the computing resources scheduling performance for task offloading in EdgeCPNs.

The offloading of computation-intensive tasks to an edge server near resource-constrained mobile devices can provide improved application performance and user experience. However, with the rapid growth of mobile devices connected to the edge server, it is challenging to directly obtain an optimal task offloading scheme due to increasing computational cost and problem scale. In this study, we model the costly task offloading problem (CTOP) in mobile edge computing networks to achieve efficient joint optimization of energy consumption and processing latency for mobile devices. Inspired by the success of evolutionary multitasking in solving complex optimization problems by leveraging the experience of simple optimization problems, we develop a novel multitasking framework whose effectiveness is demonstrated in solving the CTOP. In this framework, auxiliary tasks are created to optimize the local processing overhead and the edge processing overhead of task offloading. On this basis, we propose an effective multitask evolutionary algorithm that includes segmented knowledge transfer and auxiliary task update. Specifically, source and extended decision variables are considered as different knowledge to be utilized, while the auxiliary tasks are allowed to be updated dynamically. Related knowledge that is learned from cheap and simple auxiliary tasks promotes the evolutionary search for CTOP. Experimental results verify the effectiveness of knowledge transfer. Compared to existing multitasking and single-tasking algorithms, the proposed algorithm shows competitive performance in CTOP instances and achieves better comprehensive performance in terms of energy consumption and processing latency.

The deep learning based fault diagnosis methods show excellent performance. However, cost and delay factors make it difficult for their widespread industrial application. Microcontroller units (MCUs) in industrial equipment have the advantages of real-time response and high reliability and usually have some redundant computational resource. However, even lightweight deep learning models cannot be deployed in MCUs due to severely limited computational resources. This paper proposes an end-edge collaborative fault diagnosis framework, by combining real-time decision-making at the end with dynamic adaptive diagnosis at the edge to improve inference performance. The model’s minimum input size is deduced through theoretical analysis of the bearing working mechanism, and to make the model suitable for MCUs, we leverage the differential characteristics of the bearing vibration data and proposed a TinyML model based on stacked autoencoders. The pre-autoencoder extracts differential features, while the post-autoencoder performs fault diagnosis based on pooled differential features. Finally, the stacked-autoencoder model and collaborative framework were evaluated using the CWRU bearing dataset, achieving 384x compression in parameter size and 100% accuracy for binary fault classification, requiring only 6.44kB RAM. With the dynamic adaptive collaboration mechanism, the proposed fault diagnosis framework can reduce the edge load by approximately 94%.

Ethereum has received increasing attention as the first blockchain platform to support smart contracts. Data mining has become an important tool for analyzing Ethereum transactions. However, existing methods have the disadvantage of covering partial transactions and being vulnerable to privacy-enhancing techniques. In this paper, we propose a scheme for transaction correlation with the node as an entity, which can cover all transactions while being resistant to privacy-enhancing techniques. Utilizing timestamps relayed from N fixed nodes to describe the network properties of transactions, we cluster transactions that enter the network from the same source node. Experimental results show that our method can determine with 97% precision whether two transactions enter the network from the same source node.

In perishable supply chain logistics, even a small departure from the required storage conditions at any distribution link can compromise the quality of transported products, such as food, pharmaceuticals, and other bioproducts, resulting in big losses for the businesses involved or even threats to public health. To enhance quality management (QM) and consumer confidence, an edge-cloud blockchain and Internet of Everything (IoE)-enabled QM platform is proposed to achieve low delay and rapid response for sensor data acquisition, authentication, consistency, and transparency in cold supply chain logistics. Then, we design an adaptive data smoothing and compression (ADSC) mechanism to reduce IoE data size, and analyze and store those data in the edge gateways with limited computation and storage capacity for correctly characterizing logistics operations and transactions. Moreover, to ensure the data integrity during last-mile delivery, the mobile edge gateway is adopted when the goods are temporarily off the communication range of the fixed edge gateway in the truck. Then, we propose a synchronization engine with a formal workflow applied at mobile and fixed edge gateways where data blocks are generated, validated, and synchronized with the cloud. Finally, a real-life case study on vaccine logistics is introduced to verify our proposed approach with results presented.

With the increasingly developed industry and more comprehensive product offerings, customized and personalized products (CPPs) gradually become a main business model of many enterprises. However, the characteristics of CPPs, such as large differences in product modules and short product delivery cycles, put forward very high demands for the intelligence, flexibility and real-time performance of cloud manufacturing (CMfg). To satisfy the above typical demands, a cloud-edge-device collaborative framework of CMfg is proposed to support distributed data processing and fast decision-making. In the context of Cloud-edge-device collaboration, the vertically and horizontally distributed deployment and update mechanisms of deep learning models (DLMs) are brought forward and analyzed in detail to provide rapid response and high-performance decision-making services for CPPs. In addition, related key technologies are presented to provide references for the technical research direction.

With the extensive application of automated guided vehicles, real-time production scheduling considering logistics services in cloud manufacturing (CM) becomes an urgent problem. Thus, this study focuses on the distributed real-time scheduling (DRTS) of multiple services to respond to dynamic and customized orders. First, a DRTS framework with cloud–edge collaboration is proposed to improve performance and satisfy responsiveness, where distributed actors and one centralized learner are deployed in the edge and cloud layer, respectively. And, the DRTS problem is modeled as a semi-Markov decision process, where the processing services sequencing and logistics services assignment are considered simultaneously. Then, we developed a distributed dueling deep Q network (D3QN) with cloud–edge collaboration to optimize the weighted tardiness of jobs. The experimental results show that the proposed D3QN obtains lower weighted tardiness and shorter flow-time than other state-of-the-art algorithms. It indicates the proposed DRTS method has significant potential to provide efficient real-time decision-making in CM.

Traditional complex product design methods rely too much on the designer's experience and lack methodology, so they are susceptible to subjective factors. It is easy to overlook some critical influencing factors. The big data generated in the design process contains much knowledge and provides a new perspective for decision-making. This paper proposes a data-driven decision-making approach for complex product design based on deep neural network. Correlation analysis is used to find the critical dimensions of big data that affect decision-making. The big data generated in the complex product design process is analyzed through the deep neural network, and the value of design variables can be predicted. Finally, an experiment was conducted with a complex aerospace product, which proved the validity and accuracy of the approach proposed in this paper.

Security monitoring and analysis can help users to timely perceive threats faced by the host, thereby protecting and backup data and improving the host's security status. In the research domain of host security analysis, many feasible solutions have been proposed. However, real-time performance and accuracy still need improvement. This paper proposes a host security analysis method based on Dempster–Shafer (D-S) evidence theory. It adopts three models of support vector regression, logistic regression, and K-nearest neighbor regression, as sensors for multisource information fusion. Multiple sensors perform security analysis on the host, respectively, and use the analysis results as evidence of D-S evidence theory. Experiments show that the proposed method provides effective security protection for the host in terms of absolute error, root mean square error, and the average absolute percentage error.

Industrial trends and new generation information and communication technologies have become driving forces for advancement in the process control and manufacturing industry. This paper thoroughly investigates the future industrial trends from the perspectives of market, engineering system, product, innovation, etc., then incorporates the concept of software defined networking and proposes a new cloud based manufacturing model, Software Defined Cloud Manufacturing (SDCM). The key characteristics, reference architecture and emerging enabling technologies of SDCM are presented to support the SDCM's advantages in terms of real-time response, reconfiguration and operations of the manufacturing system. Resource virtualization and function programmability lie at the core of SDCM to empower the manufacturing sector. The paper is concluded with remarks and future work.

Multi-disciplinary virtual prototype (MDVP) based on modeling and computer simulation technology has been applied in a wide range of engineering applications, especially the design, testing and evaluation of complex products. Generally, a large set of parameters need to be optimized to improve the performance of the prototype, which comprises a number of heterogeneous models from multiple domains. This calls for numerous collaborative simulation experiments in heterogeneous computing environments, which are difficult to build and configure. Cloud simulation is a promising solution with the extremely large resource pool and dynamic construction of virtual computing environments. Thus this paper firstly proposed an optimization framework of MDVP which formulated the domain models, optimizer and the distributed interactive environment on cloud for multi-disciplinary engineers. Then we designed the procedure for conducting parallel optimization of MDVP in the cloud simulation system by con-current execution of MDVP simulation system. The method proposed in the paper has been applied to a MDVP in the aerospace industry, which indicates that the proposed method can support an efficient engineering methodology that can transform the traditional centralized, serial simulation optimization to the distributed collaborative and parallel simulation optimization.

The Internet of Things (IoT) envisions the seamless interconnection of the physical world and the cyber space. This provides a promising opportunity to build powerful services and applications for manufacturing. This paper provides an overview of key research issues to be addressed and the latest advances in the area of IoT-enabled manufacturing. We first introduce the core technologies of IoT, such as Radio Frequency Identification, Wireless Sensor Networks, Cloud computing, and Big Data. Then we discuss some key research issues of IoT-enabled manufacturing in term of architecture, deployment and business model, data acquisition and processing, model-based decision-making, dynamic service composition, user-centric pervasive environment and latency reduction with state-of-the-art reviews. Finally, we point out some potential application areas of IoT in manufacturing.

Cloud Manufacturing can provide mass manufacturing resources and capabilities as services via the Internet. Undoubtedly, multiple manufacturing clouds (MCs) will have extremely abundant services in terms of function, price, etc. The ability to leverage ample services hosted in MCs has direct relation to the success or failure of a manufacturer. Meanwhile, various uncertainties in today's highly-dynamic business environment can easily disrupt manufacturing activities, rendering original schedules ineffective or even obsolete. IoT's real-time sensing ability can be used to detect those uncertainties. However, little work has been done to take advantage of abundant services from MCs and to effectively deal with uncertainties. In order to address this issue, we propose a mathematical formulation for IoT-enabled dynamic Service Selection (SS) across multiple MCs. We consider three kinds of uncertainties (fluctuation of completion time, choices of manufacturing services, and runtime changes made by users) that come from both the user and market sides. The formulation can guide the dynamic SS and enable users to continuously adjust SS to be more effective and efficient.

Customized/personalized products are gaining more shares in today's product market. Such products need collective efforts from consumers, manufacturers and third parties. On the other side, the Internet of Things (IoT) with pervasive sensing/actuating/networking ability greatly facilitates remote operation of manufacturing activities and efficient collaboration among stakeholders. This provides great opportunities to the above demand. Thus we propose a full-connection model of product lifecycle in the IoT-enabled cloud manufacturing environment. The model uses social networks to connect multiple parties and facilitate open innovations, IoT to glue physical space to cyber space and cloud manufacturing to provide various elastic services, so that the on-demand workspace, interaction, information sharing or collective problem solving are enabled. We also propose a supporting infrastructure for this model using the latest information and communication technologies. Finally, we present a RFID (Radio-frequency identification) enabled production system for customized/personalized products with the ability to enable a new paradigm of “dynamic processes and close collaborations among different roles” and secure robust production.

Cloud Manufacturing (CMfg) adopts and extends the concept of cloud computing to make mass Manufacturing Resources and Capabilities (MR/Cs) more widely integrated and accessible to users through the Internet. However, a single manufacturing cloud (MC) only has relatively limited scalability and elasticity. Using the aggregated MR/Cs from multiple MCs is a natural evolution. To address this requirement, we propose an integration framework for multiple MCs, so that MCs can collaboratively cope with peak user demands for MR/Cs. The key functional modules and the business model of the proposed framework are presented to guide future integration of multiple MCs. The enabling technologies, such as semantic web and ontologies, intelligent agents, service oriented architecture, and material handling and logistics technologies are also discussed. An application example is given, showing the feasibility and rationality of the proposed approach.