IET Collaborative Intelligent Manufacturing最新文献

The industrial Internet of Things (IIoT) is revolutionising manufacturing and production of small and medium enterprises (SMEs) by enhancing efficiency and product quality. While developed countries like the USA, UK, Canada, Finland, and Japan have widely adopted IIoT, developing nations such as Bangladesh, India, Pakistan, and Malaysia are still lagging. This study explores IIoT adoption in manufacturing SMEs, emphasising its potential for economic growth despite challenges like budget constraints and skill gaps in developing countries. It presents a novel model based on 17 factors from the TOEI (Technology, Organization, Environment, and Individual) framework to support decision-makers in integrating IIoT technologies. The model’s reliability and validity are confirmed through rigorous testing and a survey of three SMEs. This proposed model serves as a roadmap for SMEs, breaking down complex processes into manageable steps, and providing SMEs with a structured approach.

In human-centric smart manufacturing (HCSM), the robot's dynamic obstacle avoidance function is crucial to ensuring human safety. Unlike the static obstacle avoidance of manipulators or mobile robots, the dynamic obstacle avoidance in mobile manipulators presents challenges such as high-dimensional planning and motion deadlock. In this paper, an adaptive whole-body control approach for dynamic obstacle avoidance of the mobile manipulators for HCSM is proposed. Firstly, an adaptive global path planning method is proposed to reduce planning dimension. Secondly, lateral coupling effect term and nonlinear velocity damping constraints are formulated to alleviate motion deadlock. Then, a whole-body dynamic obstacle avoidance motion controller is presented. Through simulations and real-world experiments, the planning time is reduced by 18.65% on average, and the path length by 15.94%, compared to the global RRT benchmark algorithm. The dynamic obstacle avoidance experiment simulates the obstacle combinations such as pedestrians moving in opposite direction, traversing and forming a circle during the robot operation. The proposed motion controller can adjust robot movement in real time according to the change of its relative distance from obstacles, meanwhile maintaining an average safe distance of 0.45 m from dynamic obstacles. It is assumed that the proposed approach can benefit dynamic human–robot symbiotic manufacturing tasks from more natural and efficient manipulations.

Artificial intelligence is transforming the pharmaceutical sector through improvement in critical processes such as quality assurance (QA). However, in Kenya, technical problems in QA processes, including in-process quality control, equipment maintenance, and visual inspections exist. This paper aims to shed light on the potential of AI in improving pharmaceutical QA in Kenya and challenges associated with its integration. A literature search was thoroughly conducted by retrieving articles from Google Scholar. Articles and policy documents with information relevant to AI applications in QA, optimising pharmaceutical processes, and regulatory compliance in Kenya were reviewed and analysed. AI can improve efficiency and precision in various QA processes including warehousing, equipment maintenance, in-process quality control, and visual inspections, among others. Significant challenges to AI incorporation in QA of Kenya's pharma companies include a lack of technical expertise and understanding of AI outcomes, high implementation costs and fear of losing jobs. There should be strengthened collaborations among government, pharmaceutical manufacturers, AI companies, and researchers to address skill-based barriers and financial challenges.

The randomness and persistence of dynamic disturbances pose significant challenges to resource integration, task allocation, and goal setting within production logistics system. To maintain the optimal operational state of production logistics system over the long term, predictive planning and intervention must occur before disturbances arise, whereas adaptive adjustments are necessary to correct system states after disturbances occur. However, the effective implementation of these control strategies is hindered by several obstacles, such as a lack of comprehensive data and valuable knowledge, which impedes the support for opti-state control (OsC). Fortunately, with the advancements in information technologies such as the IoT and digital twins, it is now possible to collect and process vast amounts of real-time, full-lifecycle big data, thereby enabling more informed optimisation decisions. This paper proposes a digital twin and big data-based opti-state control system (DTBD-OsCS). The architecture integrates big data analytics and service-driven patterns, effectively addressing the aforementioned challenges. Within this framework, both predictive opti-state control (POsC) and adaptive opti-state control (AOsC) strategies are incorporated, along with the development of key technologies for implementing big data analysis. The proposed architecture's effectiveness is demonstrated through application scenarios, and experimental results and findings are thoroughly discussed. The results show that the proposed architecture significantly enhances the efficiency of production logistics systems and effectively reduces the cost impact of disturbances on the system.

This work presents a novel solution for multivariate time series anomaly detection in industrial control systems (ICSs), specifically tailored for resource-constrained environments. At its core, the quantized gated recurrent unit variational autoencoder (Q-GRU-VAE) architecture, a significant evolution from conventional methods, offers an extremely lightweight yet highly effective solution. By integrating gated recurrent units (GRUs) in place of long short-term memory (LSTM) cells within a variational autoencoder (VAE) framework, and employing channel-wise dynamic post-training quantization (DPTQ), this model dramatically reduces hardware resource demands. The proposed solution exhibits performance on par with existing methods on the widely used secure water treatment (SWaT) and water distribution (WADI) benchmarks, while being tailored towards applications where computational resources are limited. This dual achievement of minimal resource consumption and preserved model efficacy paves the way for deploying advanced anomaly detection in resource-constrained environments, marking a significant leap forward in enhancing the resilience and efficiency of ICSs.

Shop scheduling and machine layout are two important aspects of discrete manufacturing. There are strong coupling relationships between them, but they were conducted separately in the past, which significantly limits the production performance improvement of discrete manufacturing. At the same time, in the actual process of workshop production, uncertain events not only often occur but also may make the existing scheduling schemes no longer suitable. To address such issues, the integrated optimisation of shop scheduling and machine layout for discrete manufacturing considering uncertain events is proposed in this paper, where the minimum material handling cost, the maximum space utilisation rate and the minimum production completion time are selected as the optimisation objectives. An improved immune genetic algorithm is designed to solve the corresponding mathematical model efficiently by dual-layer encoding, which is good at global optimisation. Moreover, multistrategy redundancy-aware workshop rescheduling is performed to respond to uncertain events that are regarded as production disturbances. The rationality and superiority of the proposed method are verified by a numerical case study of a discrete manufacturing workshop for wood–plastic composite materials with its integrated optimisation of shop scheduling and machine layout, as well as its rescheduling schemes under machine failures.

This paper focuses on the dynamic flexible job shop scheduling problem with constrained maintenance resources (DFJSP-CMR), a pressing challenge in modern manufacturing systems. As traditional rigid scheduling models fall short in meeting the demands of today's dynamic production environments, there is a growing need for intelligent approaches that can seamlessly integrate production scheduling and maintenance planning under resource limitations. To tackle this challenge, we propose a novel hybrid algorithm aimed at minimising makespan while addressing machine deterioration, unexpected failures and constrained maintenance resources. The core of our approach is a deep Q-network with maintenance insertion algorithm (DQN-MI) specifically designed for efficient maintenance scheduling. The algorithm features a 5×3 action space, constructed as compound rules, along with a reward structure that balances machine utilisation efficiency with effective maintenance operations. Extensive computational experiments conducted on diverse problem instances demonstrate that DQN-MI delivers superior performance, further validating the effectiveness and versatility of the proposed method in addressing complex scheduling challenges while maintaining the stability and reliability of manufacturing systems. This research contributes to the advancement of intelligent manufacturing by presenting a robust and practical solution for the integrated management of production scheduling and maintenance planning.

The reentrant flowshop scheduling problems (RFSP) are ubiquitous in high-tech industries such as semiconductor manufacturing and liquid crystal display (LCD) production. Given the complexity of RFSP, it is significant to improve the production efficiency using effective intelligent optimisation techniques. In this study, four meta-heuristics assisted by two reinforcement learning (RL) algorithms are proposed to minimise the maximum completion time (makespan) for RFSP. First, a mathematical model for RFSP is established. Second, four meta-heuristics are improved. The Nawaz–Enscore–Ham (NEH) heuristic is utilised for population initialisation. Based on the problem characteristics, we design six local search operators, which are integrated into the four meta-heuristics. Third, two RL algorithms, Q-learning and state–action-reward–state–action (SARSA), are employed to select the appropriate local search operator during iterations to enhance the convergence in a local space. Finally, the results of solving 72 instances indicate that the proposed algorithms perform effectively. The RL-guided local search can significantly enhance the overall performance of the four meta-heuristics. In particular, the artificial bee colony algorithm (ABC) combined with SARSA-guided local search yields the highest performance.

Cognitive workload (CWL) assessment has gained increasing importance in Industry 4.0 and 5.0 settings where human–machine interactions are becoming more complex. Despite growing attention, a comprehensive CWL assessment that integrates methodologies, technologies and case studies is still lacking. This study reviews 69 articles related to the CWL assessment, selected from the Scopus database. The review identifies five primary methodologies for the CWL assessment: physiological measures, subjective evaluation (e.g., NASA-TLX), performance evaluation, cognitive load models and multimodal approaches. The analysis shows an increasing trend towards multimodal approaches that combine subjective assessment methods with physiological measures obtained from electroencephalography, eye tracking and heart rate monitoring devices. Additionally, emerging technologies such as advanced sensors and specialised equipment are increasingly considered in case studies that address the CWL assessment in current work environments. Results reveal significant advancements in physiological and multimodal assessment methods, particularly emphasising real-time monitoring capabilities and context-specific applications. Case studies underscore the key role of CWL management in assembly, maintenance and construction tasks, demonstrating its impact on performance, safety and adaptability in dynamic environments. This review establishes a framework for advancing CWL research by addressing methodological limitations and proposing future research directions, including the development of personalised, adaptive systems for real-time workload management.

Multiagent cooperative control enhances system efficiency through the facilitation of distributed collaboration, demonstrating significant applications in intelligent manufacturing. As a fundamental issue of cooperative control, multiagent consensus has been implemented extensively in numerous domains. Therefore, this paper studies the asymptotic consensus issue of a nonlinear system under switching topologies. The changeable topological structures hinder the system's ability to stabilise or require a substantial amount of time for stabilisation. To address this issue, we have incorporated topological information into the traditional Riccati equation. Subsequently, a topology-based dynamic event-triggered mechanism is presented by introducing an internal dynamic variable based on the solution of the Riccati equation. Furthermore, this research proposes a novel control protocol that utilises the full information of the switching topologies. This protocol contains a changeable control gain, which allows for the adjustment of the control law in response to the communication topology. Then, the Lyapunov stability theory guarantees that the nonlinear system reaches an asymptotic consensus under the proposed control law. This study also proves that the system does not exhibit Zeno behaviour. Ultimately, the simulation results confirm the viability of the control protocol.