IET Collaborative Intelligent Manufacturing最新文献

Meeting customer time requirements poses a major challenge in the context of high-variety make-to-order companies. Companies need to reduce the lead time and process urgent jobs in time, while realising high delivery reliability. The key decision stages within Workload Control (WLC) are order release and shop floor dispatching. To the best of our knowledge, recent research has mainly focused on order release stage and inadvertently ignored shop floor dispatching stage. Meanwhile, urgency of job is not only related to its due date, but also affected by the dynamics of shop floor. Specifically, urgency of jobs may decrease at downstream operations in the job's routing, since priority dispatching for urgent jobs accelerates production speed at the upstream operations. And occupying production resources increases the waiting time of non-urgent jobs at workstation. This phenomenon leads to the change of urgency of jobs. Misjudgement of urgent jobs therefore may result in actual urgent jobs not being processed in time. In response, the authors focus on shop floor dispatching stage and consider the transient status of urgent operations in the context of WLC. The urgency of jobs is rejudged at the input buffer of each workstation, which is firstly defined as urgent operations and non-urgent operations. Using simulation, the results show that considering the transient status of urgent operations contributes to speeding up production for actual urgent jobs and meeting delivery performance both in General Flow Shop and Pure Job Shop. In addition, percentage tardy performance is greatly affected by norm levels, especially at the severe urgent level. These have important implications on how urgent operations should be designed and how norm level should be set at shop floor dispatching stage.

Digital servitization is a business model transformation process enabled by the use of digital technologies to create or improve industrial services and product-service offerings by creating value and competitive advantage increasing customer satisfaction and loyalty as well as company revenue streams. 5G networks can enable digital servitization of manufacturing by providing faster, more secure, and more reliable communications between machines, devices, and humans. This paper explores the impact of adopting 5G technologies on servitization and identifies the services that can benefit most from 5G networks. The research consists of two parts: a literature review of the technologies currently used in the design and provision of industrial services that could benefit from 5G networks and an exploratory survey involving manufacturing companies that have started the digital servitization journey. The main results emerging from the research suggest that 5G can profoundly impact services supported by Augmented Reality, Cloud computing, and Cyber-physical systems, mainly concerning maintenance, workforce training, machine diagnosis and monitoring.

In modern industrial systems, diagnosing faults in time and using the best methods becomes increasingly crucial. It is possible to fail a system or to waste resources if faults are not detected or are detected late. Machine learning and deep learning (DL) have proposed various methods for data-based fault diagnosis, and the authors are looking for the most reliable and practical ones. A framework based on DL and reinforcement learning (RL) is developed for fault detection. The authors have utilised two algorithms in their work: Q-Learning and Soft Q-Learning. Reinforcement learning frameworks frequently include efficient algorithms for policy updates, including Q-learning. These algorithms optimise the policy based on the predictions and rewards, resulting in more efficient updates and quicker convergence. The authors can increase accuracy, overcome data imbalance, and better predict future defects by updating the RL policy when new data is received. By applying their method, an increase of 3%–4% in all evaluation metrics by updating policy, an improvement in prediction speed, and an increase of 3%–6% in all evaluation metrics compared to a typical backpropagation multi-layer neural network prediction with comparable parameters is observed. In addition, the Soft Q-learning algorithm yields better outcomes compared to Q-learning.

Bipedal gait control has always been a very challenging issue due to the multi-joint and non-linear structure of humanoid robots and frequent robot–environment interactions. To realise stable and robust bipedal walking, many aspects including robot modelling, gait stability and environmental adaptivity should be considered to design the gait control method. In this paper, a general description of bipedal gait and the corresponding evaluation indicators are introduced. Moreover, the existing bipedal gait control methods are classified into model-based gait, stability criterion-based gait and learning strategy-based gait and a comprehensive review is conducted. Finally, the existing challenges and development trends of bipedal gait control are presented.

Cyberspace has continued to change throughout the 1990s and 2000s, when the Internet became widely used. The concept of a massive, integrated, sustainable, and interconnected cyber world is the heart of the metaverse. The aim of the metaverse is to create a digital world that is analogous to the existing world. Thus, the most recent metaverse development is investigated in light of cutting-edge technologies and metaverse ecosystems. To this end, a pilot survey to provide a first overview of upcoming challenges and opportunities of the metaverse is presented. The results provide researchers with a direction for future study as well as potential applications in the metaverse.

Manufacturing enterprises are facing how to utilise industrial knowledge and continuously accumulating massive unlabelled data to achieve human-cyber-physical collaborative and autonomous intelligence. Recently, artificial intelligence-generative content has achieved great performance in several domains and scenarios. A new concept of industrial generative pre-trained Transformer (Industrial-GPT) for intelligent manufacturing systems is introduced to solve various scenario tasks. It refers to pre-training with industrial datasets, fine-tuning with industrial scenarios, and reinforcement learning with domain knowledge. To enable Industrial-GPT to better empower the manufacturing industry, Model as a Service is introduced to cloud computing as a new service mode, which provides a more efficient and flexible service approach by directly invoking the general model of the upper layer and customising it for specific businesses. Then, the operation mechanism of the Industrial-GPT driven intelligent manufacturing system is described. Finally, the challenges and prospects of applying the Industrial-GPT in the manufacturing industry are discussed.

The Industrial Internet of Things (IIoT), along with 5G and beyond networks, is driving a new era of revolution in intelligent manufacturing. However, the integration of more heterogeneous entities and intricate communication protocols complicates the enhanced manufacturing system, posing challenges for quantitatively assessing its complexity. To tackle this issue, a complexity assessment framework for the IIoT-enabled collaborative manufacturing system is proposed by combining the complex network and information entropy theory. Firstly, industrial entities in the physical space are mapped into a two-tier complex network taking into account the weights of various access communications. Secondly, an importance-aware structure entropy is introduced to capture the complexity of industrial networks from the communication perspective in the system. The experiments conducted on various network topological structures validate the proposed method and provide guidance for system design.

With the rapid development of China's economy, enterprises need to plan their logistics transportation routes reasonably in advance. This will make the transportation service more efficient. For the supplier's transportation service problem, an analysis method of critical path nodes is provided and a multi-supplier collaborative transportation strategy is designed in this article. First, a model for minimising the transportation cost was established, then a path diagram was simulated and the optimal and alternative transportation paths of suppliers based on the k-shortest path algorithm were calculated. In addition, path node availability during COVID-19 is used as a research context in this article. A multi-stage path analysis method was provided by discussing different cases of critical path nodes, which can make a reasonable selection of paths in a timely and effective manner. Finally, simulations of collaborative transportation for suppliers were performed in three scenarios and the results verified the effectiveness of the collaborative transportation strategy. The proposed collaborative transportation strategy of suppliers not only strengthened the synergistic cooperation among suppliers, but also cultivated the potential customer for suppliers in this article. Furthermore, the strategy could improve the flexibility of the supply chain, maximise the overall efficiency and also provide a new solution for the development of logistics and transportation services.

An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas for addressing challenging problems in manufacturing systems. We collect the literature targeting three aspects: scheduling, packing, and routing, which correspond to three pivotal cooperative production links of today's manufacturing system, that is, production, packing, and logistics respectively. For each aspect, we first present and discuss the state-of-the-art research. Then we summarise and analyse the development trends and point out future research opportunities and challenges.

Disassembly is an important step in remanufacturing products. Robotic disassembly helps to improve disassembly efficiency. However, the end-of-life products often have the parts with uncertain quality, which is manifested as wear, fracture, deformation, corrosion, and other failure features. The parts failure features always have impacts on disassembly process. First, the evaluation method of parts failure features is researched, and the quantitative model of parts failure features is constructed using fuzzy models. Then, the disassembly information model is established by considering the influence of different failure degrees on the robotic disassembly process. Afterwards, to generate the optimal disassembly solution, deep reinforcement learning (DRL) is used to solve robotic disassembly sequence planning problem which considers parts failure features. Considering the influence of parts failure features on robotic disassembly time, the states, actions and rewards and environment are designed in DRL. Finally, a case study of the double shaft coupling as a waste product is carried out, and the proposed method is compared with the other methods to verify the effectiveness.