IET Collaborative Intelligent Manufacturing最新文献

The occurrence of human errors significantly affects the performance and economic results of production systems. In this context, Human Reliability Analysis (HRA) methods play a key role in assessing the reliability of a man–machine system. Several HRA methods use Performance-Shaping Factors (PSFs), that is, all the aspects of human behaviour and environment that can affect human performance, to evaluate the Human Error Probability (HEP). However, despite the greater emphasis given by researchers to define of PSFs in recent years, the changes caused by the new enabling technologies implemented in manufacturing systems and derived from the Industry 4.0 paradigm have not yet been fully explored. Focussing on Human–Robot Collaboration (HRC) in production systems, the authors aim to define a PSF taxonomy that is useful for HEP evaluations in collaborative environments. To the best of the authors' knowledge, HRA approaches have not been investigated yet for HRC applications. The proposed taxonomy, which results from the integration of the most significant factors impacting workers' performance in HRC into the PSFs provided by an HRA method, can represent an important contribution for researchers and practitioners towards improving HRA methods and their applications in the context of Industry 4.0.

The field of Human-Robot Interaction (HRI) represents one of the fast-growing focus areas of Digital Twins (DTs). However, the role of DTs applications in human-robot collaborative systems is still uncertain. This review article provides a comprehensive perspective of DTs' critical design aspects (i.e. Objectives, associate technologies, and application scenarios) in the broad application areas of human-robot systems. This article uses a multi-faceted approach to comprehend 43 DTs' state-of-the-art applications in HRI. The study investigates the literature body across two dimensions (i.e. DT roles and HRI application characteristics). The conclusion of this work draws the attention of the relevant scientific community towards potential DTs' application scenarios and provides insights into DT's future research directions.

With the trend of supply chain globalisation, competition among enterprises is becoming more intense. Enterprises urgently need to improve their core competitiveness, and the enhancement of the competencies can depend on technologies services and the quality of suppliers. Since external factors are less controllable, this study starts with the quality of suppliers and proposes a supplier evaluation method that combines particle swarm optimisation with neural network algorithm to maximise the interests of enterprises. The particle swarm algorithm to lock the approximate location of the global optimum is first employed. Based on this, we establish an evaluation model of suppliers to train for the minimum errors between the desired and predicted values by constructing a back propagation (BP) neural network. Finally, the output results of the proposed method is compared with the BP neural network without the particle swarms optimisation. The proposed model is less empirically sensitive to the initialisation and can quickly converge to the local optimums, which overcomes the shortage of traditional neural networks and is more applicable to supplier evaluation.

Job shop scheduling problem (JSP) is a classical system resource optimisation problem and also an NP hard problem. The search algorithm based on Akers obstacle graph model is an effective algorithm to solve JSP, which first removes part of jobs from the original schedule, then constructs obstacle graph and finds the shortest path from the graph, and finally reinserts the jobs according to the shortest path decoding method to get the new schedule. Although the new scheduling can achieve good results, it is time-consuming to find the shortest path. Therefore, it is necessary to further study how to quickly plan the shortest path. This study presents a fast layered path search algorithm for solving the obstacle graph of job shop scheduling. The algorithm designs a node expansion method and a delay distance formula. The obstacles generated by different machines in the obstacle graph are layered. When the nodes expand, the extended nodes are compared with the parent layer nodes to quickly avoid closely arranged obstacles, and multiple child nodes are generated at one time through node expansion to improve the node expansion ability. At the same time, node expansion method and delay distance formula can be well integrated with A* algorithm. Finally, the test verifies that the algorithm can spend less time to find the shortest path.

Gear fault diagnosis (GFD) based on vibration signals is a popular research topic in industry and academia. This paper provides a comprehensive summary and systematic review of vibration signal-based GFD methods in recent years, thereby providing insights for relevant researchers. The authors first introduce the common gear faults and their vibration signal characteristics. The authors overview and compare the common feature extraction methods, such as adaptive mode decomposition, deconvolution, mathematical morphological filtering, and entropy. For each method, this paper introduces its idea, analyses its advantages and disadvantages, and reviews its application in GFD. Then the authors present machine learning-based methods for gear fault recognition and emphasise deep learning-based methods. Moreover, the authors compare different fault recognition methods. Finally, the authors discuss the challenges and opportunities towards data-driven GFD.

Current manufacturing systems are forced to meet the most dynamic market demands under sustainable factors. However, not only technical transformations will address the challenge but, to fully cover social needs, the analysis of the human role in highly interactive systems is still decisive, following a socially sustainable approach. To fully extract the most from both agents under a performance point of view, the main added value of agents in the work environment needs to be carefully analysed, captured, and boosted. The context shapes a specific operation or task, which consequently drives the final outcome according to individual necessities. Furthermore, a methodology that potentially helps a proper assessment of these performance-based interactions is still missing. The contribution focusses on the definition of a novel human-centric methodology under a holistic point of view to analyse performance-based interactions and to define appropriate indices and metrics that helps assessing the human-system interactions in the manufacturing domain. The methodology is applied in a case study to guide practitioners with its use.

Job shop scheduling problem is a classical scheduling problem, and it is very difficult to work out. To solve it well, the meta-heuristic algorithm is a good choice, and the evaluation method of neighbourhood solutions, which affects the efficiency of the algorithm and the quality of the solution, is one of the keys in the algorithm. We propose an approximate evaluation method by exploring domain knowledge in neighbourhood solutions. Firstly, we reduce the computational time of the evaluation by analysing the unnecessary computational operations. Secondly, according to the domain knowledge, we prove that the evaluated value of the neighbourhood solution is the exact value under certain conditions. At the same time, a set of critical parameters are calculated to correct the estimated value of the neighbourhood solutions that do not meet the conditions to improve the evaluation accuracy. With all of these, an approximate evaluation method for neighbourhood solutions in job shop scheduling problems is proposed. The experiments on different numerical instances show the superiority of the method proposed.

Data-driven fault diagnosis approaches have been widely adopted due to their persuasive performance. However, data are always insufficient to develop effective fault diagnosis models in real manufacturing scenarios. Despite numerous approaches that have been offered to mitigate the negative effects of insufficient data, the most challenging issue lies in how to break down the data silos to enlarge data volume while preserving data privacy. To address this issue, a vertical federated learning (FL) model, privacy-preserving boosting tree, has been developed for collaborative fault diagnosis of industrial practitioners while maintaining anonymity. Only the model information will be shared under the homomorphic encryption protocol, safeguarding data privacy while retaining high accuracy. Besides, an Autoencoder model is provided to encourage practitioners to contribute and then improve model performance. Two bearing fault case studies are conducted to demonstrate the superiority of the proposed approach by comparing it with typical scenarios. This present study's findings offer industrial practitioners insights into investigating the vertical FL in fault diagnosis.

The distributed blocking flowshop scheduling problem (DBFSP) with new job insertions is studied. Rescheduling all remaining jobs after a dynamic event like a new job insertion is unreasonable to an actual distributed blocking flowshop production process. A deep reinforcement learning (DRL) algorithm is proposed to optimise the job selection model, and local modifications are made on the basis of the original scheduling plan when new jobs arrive. The objective is to minimise the total completion time deviation of all products so that all jobs can be finished on time to reduce the cost of storage. First, according to the definitions of the dynamic DBFSP problem, a DRL framework based on multi-agent deep deterministic policy gradient (MADDPG) is proposed. In this framework, a full schedule is generated by the variable neighbourhood descent algorithm before a dynamic event occurs. Meanwhile, all newly added jobs are reordered before the agents make decisions to select the one that needs to be scheduled most urgently. This study defines the observations, actions and reward calculation methods and applies centralised training and distributed execution in MADDPG. Finally, a comprehensive computational experiment is carried out to compare the proposed method with the closely related and well-performing methods. The results indicate that the proposed method can solve the dynamic DBFSP effectively and efficiently.