IET Collaborative Intelligent Manufacturing最新文献

A distributed heterogeneous permutation flowshop scheduling problem with sequence-dependent setup times (DHPFSP-SDST) is addressed, which well reflects real-world scenarios in heterogeneous factories. The objective is to minimise the maximum completion time (makespan) by assigning jobs to factories, and sequencing them within each factory. First, a mathematical model to describe the DHPFSP-SDST is established. Second, four meta-heuristics, including genetic algorithms, differential evolution, artificial bee colony, and iterated greedy (IG) algorithms are improved to optimally solve the concerned problem compared with the other existing optimisers in the literature. The Nawaz-Enscore-Ham (NEH) heuristic is employed for generating an initial solution. Then, five local search operators are designed based on the problem characteristics to enhance algorithms' performance. To choose the local search operators appropriately during iterations, Q-learning-based strategy is adopted. Finally, extensive numerical experiments are conducted on 72 instances using 5 optimisers. The obtained optimisation results and comparisons prove that the improved IG algorithm along with Q-learning based local search selection strategy shows better performance with respect to its peers. The proposed algorithm exhibits higher efficiency for scheduling the concerned problems.

Workload control (WLC) is usually employed to make order release to attain workload balance, satisfactory delivery rate and high production efficiency. However, in the real production environment of printed circuit board (PCB) industries, slight modifications in the product process shifts the bottleneck resources which leads to misjudge the effect of WLC and may ultimately increase the lateness of orders. Therefore, this research focuses on the order release problem of PCB production system considering main process flow and shifting of bottlenecks. At first, certain improvements are proposed on the classic WLC method and two order release control strategies based on process switching are designed to generate order release plan on the basis of Lancaster University Management School Corrected Order Release method. Furthermore, different scheduling rules are investigated along with the upper workload limits on the PCB system simultaneously. Finally, a simulation model is developed to analyse the impact of order release methods on the system performance through simulation experiments. Furthermore, extensive simulation experiments for different scheduling rules on bottleneck resource and different workload upper limit ratios are also carried out in the current research. Simulation results show that the process order release control strategy based on process switching has a strong adaptability in PCB manufacturing system.

Significant attention has been given to low-carbon smart manufacturing (SM) as a strategy for promoting sustainability and carbon-free emissions in the manufacturing industry. The implementation of intelligent algorithms and procedures enables the attainment and enhancement of low-carbon clever manufacturing processes. These algorithms facilitate real-time monitoring and predictive maintenance, ensuring efficient and sustainable operations and data-driven decision-making, increasing resource utilisation, waste reduction, and energy efficiency. The research examines the utilisation of algorithms in the context of low-carbon smart manufacturing, encompassing machine learning, optimisation algorithms, and predictive analytics. A comprehensive literature evaluation spanning from 2011 to 2023 is conducted to assess the significance of low-carbon approaches in the context of smart manufacturing. An integrated approach is used using content analysis, network data analysis, bibliometric analysis, and cluster analysis. Based on the published literature the leading contributors to low-carbon manufacturing research are India, China, United States, United Kingdom, Singapore, and Italy. The results have shown five main themes—Low-carbon smart manufacturing and applications of Algorithms; Industry 4.0 technologies for low-carbon manufacturing; low carbon and green manufacturing; Low-carbon Manufacturing, and Product design and control; Lean Systems and Smart Manufacturing. The purpose of this study is to provide policymakers and researchers with a guide for the academic development of low-carbon manufacturing by evaluating research efforts in light of identified research deficits.

Small and Medium Enterprises (SMEs) are steadily moving in the direction of implementing digital and smart technologies, including the Industrial Internet of Things (IIoT) for improving their products and services. The adoption of IIoT allows manufactures and producers to make quick decisions for improving productivity and quality in real-time. For this purpose, the era of digital industrial revolution from IR 1.0 to IR 5.0 is briefly explained. In this research study, the authors have reviewed and analysed the existing reviews, surveys and technical research studies on IIoT technologies for the manufacturing and production SMEs to highlight the concern raised. Forty-seven (47) influencing factors are identified and classified into four groups based on the TOEI framework. Based on the identified influencing factors, IIoT adoption model is proposed for the manufacturing and production SMEs to adopt the new IIoT technologies in their business environments. Furthermore, a comparative analysis of the influencing factors has been done for the adoption of IIoT to increase efficiency, productivity and competitiveness for the manufacturing and production SMEs in developing countries. The proposed IIoT adoption model will help future policymakers and stakeholders to develop policies and strategies for the successful adoption and implementation of IIoT in manufacturing and production SMEs in developing countries. Also, recommendations are suggested to encourage IIoT adoption in production and manufacturing environments so that manufacturers and producers can respond easily and quickly to highly changing demands, product trends, skills gaps and other unexpected challenges in the future.

The medium-thick plate is an important type of steel product widely used in construction and engineering machinery. The orders are usually characterised by multiple specifications and small quantities. The plate design is an important part in the production process of medium-thick plate, which includes the combination of sub-plates and the size design of the motherboard. A multi-objective model for medium-thick plate design is proposed based on the 2D bin packing model, comprehensively considering spatial and size constraints of the plate production. A two-stage genetic algorithm (TSGA) is developed to solve the proposed model. In the first stage, an improved GA is used to optimise the corresponding relationship between the sub-plates and the slab, as well as the size of the motherboard. In the second stage, an exact algorithm based on the integer programming model is applied to calculate the order layout to minimise the surplus materials. To validate the proposed method, computational experiments are conducted based on actual production data from a steel plant. The experimental results show the effectiveness of the TSGA algorithm in solving the plate design problem.

Industrial defect detection is an important part of intelligent manufacturing, and Internet of things (IoT)-based defect detection is receiving more and more attention. Although deep learning (DL) can help defect detection reduce the cost and improve the accuracy of traditional manual quality inspection, DL requires huge computational resources and is difficult to be simply deployed on IoT devices with limited computational power and memory resources. Digital signal processor (DSP) is an important IoT device with small size, high performance and low energy consumption, which has been widely used in intelligent manufacturing. In order to perform accurate defect detection on DSP, the authors proposed various optimisation strategies and then used a parallel scheme to scale the model to execute on multiple cores. The authors’ method evaluated it on Northeastern University Surface Defect Dataset, Magnetic Tile Defect Dataset, Rail Surface Defect Dataset and Silk Cylinder Defect Dataset, and the experimental results showed that the authors’ method obtains faster speeds without accuracy loss compared to running the same Convolutional Neural Networks model on a mainstream desktop CPU. This means that the authors’ method can realise efficient and accurate defect detection on IoT devices with limited computational power and memory resources, which opens up new possibilities for future development in the field of smart manufacturing.

3D meshes simplification plays an important role in many industrial domains. The two goals of Delaunay mesh simplification are maintaining high geometric fidelity and reducing mesh complexity. However, they are conflicting and cannot solved by gradient. Such limitation prevents existing Delaunay mesh simplification to obtain a small enough number of vertices and promising fidelity at the same time. To address these issues, this paper proposes an evolutionary multi-objective approach for Delaunay mesh simplification. Firstly, the authors replace the previous fixed error-bound threshold by the designed adaptive segment-specific thresholds. Secondly, a constrained simplification is performed through a series of edge collapses that satisfy both Delaunay and error constraints. Next, the non-dominated sorting genetic algorithm II (NSGA-II) is employed to solve the multi-objective problem to search for the optimal trade-off threshold sequences. Finally, a fine-tuning method is designed to further enhance the geometric fidelity of the simplified mesh. Experimental results demonstrate that the authors’ method consistently achieves a satisfactory balance between the approximation error and number of vertices, outperforming existing state-of-the-art methods.

Nowadays, multi unmanned aerial vehicle (multi-UAV) systems have been widely used in battlefield. The rationality of mission plan can directly affect the effectiveness of multi-UAV system. The existing multi-UAV task allocation model lack a comprehensive modelling of task pre-allocation and task reallocation issues. However, in actual task execution, task pre-allocation and task reallocation are a holistic problem. Therefore, based on the background of multi-UAV cooperative reconnaissance, the authors establish a multi-UAV cooperative reconnaissance task pre-allocation and reallocation model (MCRTPR). There are two kinds of task allocation in MCRTPR model. One is task pre-allocation, which is a static task allocation before the mission begin. Another is task reallocation, that is a dynamic task allocation during the mission. For task pre-allocation, a particle swarm optimisation algorithm based on experience pool (EPPSO) is proposed. And for task reallocation, the authors design a partial task reallocation algorithm based on contract network protocol (CNP-PTR). The experimental results show that, compared with some state-of-the-art algorithms, EPPSO can get the lowest fitness value under various experimental conditions, and CNP-PTR is able to handle task reallocation problem caused by multiple kinds of dynamic events.

As a better alternative to the energy-intensive process of recycling waste sheet steel (WSS) from the exterior components of end-of-life vehicles to produce new steel, the feasibility of remanufacturing WSS into angle mesh steel (AMS) for construction applications is evaluated. A remanufacturing unit with a capacity of 1278 m²/day of WSS (30,000 vehicle/year) was evaluated using a triple-bottom-line sustainability analysis of the technological, economic, and environmental feasibilities by hybrid defuzzification–curve-fitting, solid-waste recoverability management, and weighting methods. Based on the remanufacturing productivity, an economic feasibility index was calculated considering the sales potential and profit, while the energy and CO₂ emission savings were used to evaluate the environmental feasibility. The technical feasibility considered machine parameters and topological properties of the WSS. The Volkswagen Passat has the best remanufacturability of 200 analysed vehicle models. Remanufacturability indexes of 0.61 and 0.86 were calculated, giving remanufacturing efficiencies of 58%–82%. All feasibility indexes exceed literature thresholds, indicating that the proposed remanufacturing process is a sustainable business strategy and contributes to the United Nations Sustainability Goals of climate action; responsible consumption and production; no poverty; and industry, innovation, and infrastructure.

OpenAI's ChatGPT (GPT-4) ushers in a superior mode of computer interaction through natural language dialogues. Notably, it generates not only engaging dialogues but also codes aligned to queries and requirements. The potential of ChatGPT in hardware implementation via natural language is implemented and a strategy for “asking the right questions” is outlined. The versatility of ChatGPT is demonstrated through three mainstream hardware designs – systolic array, ResNet and MobileNet accelerators – comparing these with hand-coded designs. The evaluation metrics include design quality, design efforts, and limitations of code generated by ChatGPT/GPT-4/Cursor against prevalent High-Level Synthesis or hand-coded HDL designs. Consequently, a novel design workflow is proposed and the constraints of using GPT, particularly in AI accelerators, are highlighted.