IET Collaborative Intelligent Manufacturing最新文献

Agritech uses advanced technologies to boost the efficiency, sustainability, and productivity of farming. The Internet of Things (IoT) in agriculture has brought sensors and networked technology to gather and analyse environmental and crop data, enabling precision farming that optimises resource usage and increases yields. Yet, current agricultural methods suffer from unsecured and decentralised data management, causing inefficiencies and complicating traceability across the supply chain. The integration of IoT with blockchain technology is seen as a promising solution to enhance data-driven agriculture. Blockchain provides a secure, decentralised, and transparent ledger that enhances data integrity, reduces fraud, and improves traceability, which complements IoT applications. The authors detail the development of an innovative system that orchestrates IoT and blockchain technologies to facilitate the adoption of new technologies in agriculture and overcomes the lacked of comprehensive data connectivity. It outlines a conceptual framework and its preliminary empirical implementation. The system consists of three integrated layers: the IoT layer, which creates digital twins of field crops; the blockchain layer, which secures and manages data from the field and external stakeholders for dynamic applications such as track and tracing; and the orchestration layer, which fuses physical and digital data to optimise business models, enhance supply chain productivity, and support governmental policy-making, thereby improving field productivity and food sector innovation.

Nuclear power turbine fault diagnosis is an important issue in the field of nuclear power safety. The numerous state parameters in the operation and maintenance of nuclear power turbines are collected, forming a complex high-dimensional feature space. These high-dimensional feature spaces contain redundant information, which increases the training cost and reduces the recognition accuracy and efficiency of the fault diagnosis model. To address the aforementioned challenges, a vibration fault diagnosis algorithm in nuclear power turbines is proposed. First, a long short-term memory-based denoising autoencoder (LDAE) is designed to enhance the capability of uncertainty awareness. Then, a feature extraction method integrating variational mode decomposition (VMD), L-cliffs-based effective mode selection, and sample entropy is devised to extract the latent features from the complex high-dimensional feature space. Furthermore, using extreme gradient boosting (XGBoost) as the classifier, LDAE-VMD-XGBoost model is constructed for fault diagnosis of nuclear power turbines. Considering the impact of multiple hyperparameters of LDAE-VMD-XGBoost model on the performance, the pathfinder algorithm is used to optimise the model hyperparameter settings and improve the fault diagnosis accuracy. Experimental results demonstrate the performance of the proposed improved LDAE-VMD-XGBoost in accurate nuclear power turbine vibration fault diagnosis.

Decentralised federated learning (DFL) transforms collaborative energy consumption prediction using distributed computation across a large network of edge nodes, ensuring data confidentiality by eliminating central data aggregation. Preserving individual privacy in energy forecasting is paramount, as it safeguards personal data from unauthorised examination. This highlights the importance of effectively handling local data to provide privacy protection. The authors proposed a DFL framework for residential energy forecasting, focusing on improving the performance and convergence of the collaborative model. The proposed framework enables local training of the long short-term memory model with real-time household energy data in a ring topology. Importantly, the framework addresses the issue of straggler nodes, nodes that lag in computation or communication, by proposing a heuristic straggler identification and mitigation mechanism to reduce their negative impact on overall system performance and communication efficiency. This approach improves collaborative energy prediction performance and ensures an overall reduction in waiting time, thus improving the convergence performance. Experimental results consistently demonstrate a low mean absolute error ranging from 3 to 3.2 across all edge nodes. The empirical findings unequivocally illustrate the efficiency of the proposed DFL architecture, highlighting its ability to improve communication efficiency and concurrently enhance performance.

Moth-flame optimisation (MFO) algorithm has received a lot of attention recently, due to its simple structure and easy coding. Researchers have demonstrated that the original MFO algorithm suffers from the drawbacks of insufficient variety, slow convergence speed, and readily sliding into local optimum, which are brought about by the imbalance between local and global search. Reinforcement learning driven moth-flame optimisation (RLMFO) algorithm is designed to correct these issues. Opposition learning is employed to broaden the variety of the initial population. Reinforcement learning is introduced to direct the local and global search process of the algorithm. A strategy pool containing Gaussian mutation (GM), Cauchy mutation (CM), Lévy mutation (LM), and elite strategy (ES) is created to hold strategies with various functions. RLMFO is verified on the benchmark test suite in CEC 2017. RLMFO performs better than cutting-edge algorithms according to experimental findings.

Object detection techniques have been widely used in power system equipment maintenance. However, in power systems, the accuracy of object detection is limited by the scarcity of publicly available datasets and the lack of scene pertinence. In order to solve these problems, an object detection method based on cloud data fusion and transfer learning (YOLO-DFT) for power system equipment maintenance is proposed. Illustratively, YOLO-DFT focuses on the object detection task involving birds and humans, generating a substantial and resilient human-bird dataset through cloud-based data fusion to compensate for the dearth of public datasets in the power system domain. By seamlessly integrating the YOLOv5 algorithm with a transfer learning strategy, a targeted detection mechanism for specific locations is meticulously formulated. The experimental results demonstrate that YOLO-DFT effectively addresses object detection challenges in power systems, achieving a Mean Average Precision (MAP) measure of 0.925 across all classes, thereby providing a valuable reference for the maintenance of power system equipment.

Early fault detection (EFD) of rolling bearings aims at detecting the early symptoms of faults by monitoring small deviations of health states. Accurate EFD enables predictive maintenance and contributes to the stability of mechanical systems. In recent years, machine learning based methods have shown impressive performance on EFD. Most of the current machine learning-based methods assume the availability for a large amount of data. However, in practice, the authors may only have a very limited amount of training data, which makes it hard to learn a reliable machine learning model. To address this concern, in this work, the authors propose to tackle EFD via meta learning. Specifically, the authors first formulate EFD as a few-shot learning problem and then propose to tackle this problem with a metric-based meta learning method. Furthermore, ensemble learning is further leveraged to improve the detection robustness. For the proposed method, the distribution difference from the working conditions and the bearings are considered. The experimental results on two bearing datasets show that the proposed method can achieve better EFD performance, that is, detecting incipient faults earlier while bringing in lower false alarms, compared with several frequently used EFD methods.

The authors investigate new Automated Guided Vehicle (AGV) Routing Problem with Simultaneous Pickup and Delivery with Mixed Time Windows (VRPSPDMTW) in smart workshops, a variation of the classic Vehicle Routing Problem (VRP). A mixed time window vehicle routing model was developed for simultaneous deliveries. This model reduces the cost of AGVs used and distribution cost, along with time window penalties. To address this complex challenge, a Hybrid Adaptive Genetic Algorithm using Variable Neighbourhood Search (AGA-VNS) is proposed. This algorithm enhances the genetic algorithm's local search capabilities while preserving solution diversity, thereby improving both efficiency and quality of solutions. Comprehensive computational experiments are conducted, which include both VRPSPDTW test benchmark and real-world smart factory instance studies. The outcomes reveal that the AGA-VNS algorithm outperforms both professional solver software and advanced heuristic methods significantly. Moreover, the newly developed mixed time window model is more aligned with the requirements of real-world production processes compared to the traditional time window model. Thus, this research not only presents novel insights into the domain of vehicle routing problems but also demonstrates its significant applicability and potential in the background of intelligent workshops.

Sensor fusion is very important for collaborative intelligent systems. A regional feature fusion network called ReFuNet for detecting 3D Object is proposed. It is difficult to detect distant or small objects accurately for the sparsity of LiDAR point cloud. The LiDAR point cloud and camera image information to solve the problem of point cloud sparsity is used, which can integrate image-rich semantic information to enhance point cloud features. Also, the authors’ ReFuNet method segments the possible areas of objects by the results of 2D image detection. A cross-attention mechanism adaptively fuses image and point cloud features within the areas. Then, the authors’ ReFuNet uses fused features to predict the 3D bounding boxes of objects. Experiments on the KITTI 3D object detection dataset showed that the authors’ proposed fusion method effectively improved the performance of 3D object detection.

In the multi-variety and large-scale order production mode, enterprises must balance delivery deadlines and maintain customer satisfaction while also considering the health status of machines. Therefore, the authors propose a method for jointly optimising production scheduling and machine maintenance. Before machine processing, an order value grading and sorting model and a machine health-status group partitioning model are constructed to classify orders into different production value levels and machines into different health-status groups, respectively. During machine processing, based on the Weibull distribution theory, a ‘health evaluation function value’ constraint machine preventive maintenance (PM) model and PM strategy are proposed to account for the changing health status of machines; these are integrated with the order allocation machine strategy as decision-making elements in the production schedule. Finally, two case studies are used to verify the effectiveness of this proposed model and method. The results show that compared to general scheduling schemes, the proposed method can reduce total delay and improve customer satisfaction. Additionally, the PM plan proposed in this method can improve production efficiency and line stability compared to periodic maintenance.

The Circulatory System Based Optimisation (CSBO) stands as a nascent metaheuristic optimisation algorithm known for its proficiency in tackling global optimisation problems. The authors introduce the Multi-strategy Enhanced CSBO (MECSBO), an algorithm designed for global optimisation and Reliability-based Design Optimisation (RBDO). MECSBO integrates adaptive inertia weight, golden sine operator and chaos strategy to augment the convergence capacity and efficiency of the original CSBO. Furthermore, MECSBO-based RBDO algorithm is presented to address RBDO problem. The comparative analysis utilising standard real-world benchmark functions has been carried out to validate the effectiveness of the proposed MECSBO. Several RBDO problems, including three typical numerical examples and three engineering cases, are used to show abilities of the proposed MECSBO-based RBDO algorithm. The results demonstrated that MECSBO is outperformed comparing to the state-of-the-art algorithms in terms of accuracy, efficiency, and robustness in RBDO problems.