In the era of Industry 4.0, distributed manufacturing (DM) paradigms, exemplified by cloud manufacturing (CMfg), have garnered significant attention from both academia and industry. These paradigms aim to achieve the precise matching of geographically dispersed manufacturing resources with personalized demands. However, existing research on service configuration predominantly relies on centralized information architectures, which pose critical challenges such as single point of failure (SPoF), data privacy leakage risks, and limited scalability. To address these issues, this paper investigates how blockchain technology can be leveraged to enable trustworthy collaboration and distributed decision-making in DM systems. Specifically, we propose a Blockchain-enabled Cyber-Physical Network (BCPN) architecture and design a complete and executable business process tailored to service configuration requirements. Furthermore, a systematic solution is developed that integrates several key components, including a reputation evaluation contract, a service pre-screening contract, a proof of reputation (PoR) consensus mechanism, a distributed service configuration contract, and a backward time propagation smart contract based on breadth-first search (BFS). Simulation results validate the superiority of the proposed BCPN solution in trust establishment, privacy preservation, and system scalability, providing a novel theoretical framework and methodological pathway for the distributed governance of DM systems.

In the context of mass customization, manufacturing services require frequent adjustment and configuration of resources. Enterprises lack a unified model to describe the reliability of manufacturing service encapsulation under complex resource combinations. Meanwhile, during the encapsulation process, the latent relationships between heterogeneous resources are challenging to extract, making it difficult to guarantee the reliability of manufacturing services, ultimately resulting in production efficiency and product quality failing to meet customer demands. To address the issues above, this paper proposes A novel adaptive optimization method for reliable encapsulation of manufacturing service based on a graph convolution network with multi-dimensional feature fusion. First, a novel adaptive optimization method for manufacturing service reliability encapsulation (AO-MSRE) is constructed to characterize encapsulation reliability under diverse resource combinations. Subsequently, based on the characteristics of this model, the graph convolutional network (GCN) algorithm was improved, and the improved GCN algorithm was combined with the edge graph neural network (EGNN). A novel multi-dimensional feature fusion graph convolutional network (MFFGCN) framework-specifically, the reliability characterization network (RCN)-was designed. This framework integrates node, edge, and edge-graph feature information to comprehensively analyze the impacts of heterogeneous resources, resource relationships, and implicit interference between relationships on encapsulation reliability. Experimental results demonstrate that RCN achieves outstanding performance in optimizing manufacturing service reliability encapsulation, with a mean absolute percentage error (MAPE) as low as 1.95% while maintaining robustness under noise interference. This work provides a theoretical foundation and practical tools for reliable manufacturing service encapsulation in dynamic production environments.

This paper addresses a challenging variant of the two-dimensional variable-sized bin packing problem, characterized by multiple bin sizes, the guillotine-cut constraint, rotatable items, and few item types with high demand quantities. This problem is motivated by industrial application of insulating pressboard cutting in transformers. A hybrid evolutionary algorithm is proposed to solve the problem. The method encodes only sheet types to optimize their usage sequence and generates packing patterns by a heuristic algorithm via processing the encoding. Packing pattern is represented as multitree and constructed using a cutting-based principle. During item placement, a randomization strategy selects from top candidate items to avoid local optima, while compactness is enhanced by replicating individual items. Extensive experiments on three datasets show the proposed approach’s superiority in obtaining high-quality and robust solution. The algorithm substantially outperforms competing metaheuristics, achieving reductions of 4% to 25% across minimum, average, and maximum metrics. Crucially, it exhibits unprecedented solution stability, with standard deviations an order of magnitude lower than competitors. In addition, the randomization strategy yields significant improvements (2.9%-7.2%) over a deterministic variant. Statistical tests confirm all advantages are significant.

The two-dimensional irregular bin packing problem is a pervasive challenge in industrial manufacturing, where maximizing material utilization directly impacts cost and environmental sustainability. While existing methods, predominantly based on local search, have achieved notable success, they often struggle with the immense combinatorial complexity of permutation spaces, especially in large-scale scenarios. This paper introduces a permutation-coded evolutionary algorithm that leverages global search mechanisms for comprehensive solution space exploration. The proposed algorithm integrates a direct permutation encoding with a deterministic double-scanline decoder, effectively translating sequences into compact layouts. To overcome premature convergence, the algorithm incorporates probabilistic mutation operator selection with an adaptive inferior-solution acceptance criterion, and an identical-fitness replacement strategy. Extensive tests on standard benchmarks demonstrate that the approach outperforms state-of-the-art methods in 59 out of 69 instances, achieving an average improvement of 4.37% to 32.74% across different bin sizes. A detailed analysis reveals that the algorithm consistently generates high-quality, economical layouts across diverse problem types, including real-world instances from apparel production, with the potential to generate substantial cost savings and enhance operational efficiency in diverse manufacturing sectors.

The magnetic induction sorting system is an automated intelligent system designed specifically for magnetite ore, which can effectively separate low-grade ores. However, the magnetic induction signals detected by this system are vulnerable to noise interference, posing a significant challenge for accurate signal acquisition, thus affecting both the sorting range and accuracy. To address this issue, this study proposes a denoising method integrating the Sparrow Search Algorithm (SSA)-optimized Variational Mode Decomposition (VMD) with Wavelet Thresholding (WT). Firstly, SSA is employed to optimize the parameter configuration of VMD to achieve optimal signal decomposition. Subsequently, intrinsic mode functions (IMFs) are selectively filtered based on sample entropy analysis, and the retained IMFs undergo WT denoising. Finally, the IMFs are reconstructed to yield the denoised signal. The effectiveness of the proposed method is verified comprehensively through experiments performed with a laboratory-developed magnetic induction sorting system. Experimental results demonstrate substantial performance improvements when compared to four alternative algorithms, achieving an average improvement of 3.3% in Noise Mode (NM) and a reduction of 14.9% in Root of Variance Ratio (RVR). Moreover, the denoising algorithm led to a 38.8% increase in detectable magnetite ores and a 12.5% improvement in sorting accuracy. These results demonstrate that the proposed method effectively suppresses noise interference during the Hall sensor's collection of magnetic signals, significantly enhancing the grade sorting range and accuracy of magnetite ore.

In separation of magnetite, Hall-effect sensors (HS) have been adopted to measure magnetic signal intensity for classifying magnetite grade. Different grades of ore are then rapidly separated via an air-blowing operation, providing an effective strategy for efficient resource utilization and environmental protection. However, in separation of low-grade magnetite, severe overlapping interference is observed in the magnetic signals collected by the sensors, which hinders accurate determination of ore position and consequently leads to a high misblowing rate. To address this issue, an intelligent separation system based on dynamic magnetic field imaging and deep peak detection is developed. To overcome the incorrect identification of ore signals, a method is proposed that fuses one-dimensional time-series magnetic signals acquired by multiple Hall-effect sensors to construct a two-dimensional magnetic field intensity distribution map for each magnetite particle. An improved YOLOv11-Pose network is employed for keypoint detection, enabling accurate extraction of peak point coordinates from the distribution map and thus precise localization of magnetite particles. Furthermore, an adaptive blowing control scheme is designed, allowing dynamic selection of the blowing channel based on the real-time detected ore position. Experimental results demonstrate that the proposed method reduces the misblowing rate of waste ore in separation of adjacent magnetite by 43%. It significantly improves both the recovery rate and separation accuracy of magnetite particles, offering a low-cost, high-precision technical solution for the efficient utilization of low-grade mineral resources.

In the increasingly fierce market competition, the demand for mass personalized production in the printed circuit board (PCB) manufacturing industry is rapidly increasing. To address these needs, enterprises integrate and pack age workshop manufacturing resources into manufacturing services, and carry out a series of operations, such as matching, optimization, combination, and scheduling, to complete related tasks. However, with the exponential growth of personalized customer orders, manufacturing services must undergo frequent restructuring to generate new solutions to complete the tasks. A lack of effective collaboration between services can lead to poor task-service alignment, ultimately compromising PCB quality and failing to meet customer expectations. Therefore, this article proposes a reliable collaborative optimization method for manufacturing services based on a cascade effect integrated graph convolutional network (CGCN), which considers the dynamic changes of PCB workshop resources and solves the problem of manufacturing service collaboration. Firstly, a manufacturing service col laboration network (MSC-Net) was constructed to characterize the physical properties of workshop production. Then, the graph data on MSC-Net are used to quantify the dynamic changes in service collaboration. Finally, the global embedding features of MSC-Net are processed through CGCN, and regression prediction is performed to optimize the service collaboration. The experimental results show that, taking the production process of PCB as an example, the performance of CGCN is superior to other typical algorithms.

In semiconductor manufacturing, a multifunctional process module (MPM) can perform multiple processing steps by adjusting its functional settings. This enhances the reconfigurability of cluster tools and allows them to flexibly adapt to diverse production requirements. However, the different function settings of the MPM change the number of processing modules and generate multiple alternative processing routes. Deadlocks occur more frequently in wafer manufacturing processes with flexible routes. The flexible configuration of MPM function leads to a highly complex and large-scale model. Proper configuration of MPM can optimize lot scheduling and improve processing efficiency. Thus, based on the functional setting of MPM, process-oriented Petri nets (POPNs) are established to describe the transient and steady state processing of the system, and control explanations are developed to avoid the system deadlock. Then, based on the evolving mechanism of the Petri nets, the temporal properties of the system under the earliest starting strategy (ESS) are analyzed. An algorithm based on ESS is developed to compute the makespan of wafers in a lot and optimize the settings of the MPM function. Experimental results demonstrate that for scheduling problems unsolvable by the mixed-integer programming (MIP) model, the algorithm can adaptively minimize system lot completion time by reasonably setting the function of MPM.

Interpenetrating lattice structures offer superior tailorability in physical and mechanical properties compared to single-phase structures. To achieve high strength and moderate elastic modulus, herein, gyroid-based interpenetrating lattice scaffolds for dental implants with different interpenetrating parameter (omega) were designed. The finite element simulation results showed that the interpenetrating lattice scaffold (volume fraction rho* = 40%, omega = 0.3) achieved the comparable elastic modulus as the single-phase structure (rho* = 30%), while improving yield strength by 10.11%. This is due to the mutual constraint and support between the inner and outer lattices of the interpenetrating structure, resulting in superior mechanical properties compared to the single-phase lattice structure. The maximum stress and strain values of the bone around lattice scaffolds with interpenetrating parameters of 0.3-0.8 (rho* = 40%) fell within the range of 2-60 MPa and 1000-3000 mu epsilon, respectively, both of which are favorable for bone regeneration. The permeability of the interpenetrating lattice scaffolds all remained within the permeability limits of human bone. In addition, lattice scaffolds with interpenetrating parameters of 0.3-0.8 did not exhibit toxic effects on HBMSCs cultured in vitro. This work offers a feasible design method for regulating the mechanical compatibility and biocompatibility of oral implants.

To address the challenge of poor separation performance exhibited by conventional magnetic separation equipment when processing coarse-grained, low-grade magnetite ore, this paper proposes a novel ore recognition method that integrates empirical mode decomposition (EMD) with a convolutional neural network (CNN). First, the original signal undergoes standardization to suppress sensor baseline drift. Then, it is decomposed by using EMD to obtain a series of intrinsic mode functions (IMFs). Subsequently, based on scaling exponents and kurtosis values, IMFs containing significant feature information are selected and fused, resulting in a reconstructed signal with substantially reduced noise. To preserve effective features, the absolute values of the reconstructed signal are taken, followed by normalization and dimensional transformation to convert it into a two-dimensional matrix format, thereby constructing training, validation, and test sets. Finally, a CNN is designed and optimized to automatically extract discriminative features from the preprocessed samples, enabling accurate classification of magnetite ore grades. Experimental results demonstrate that the proposed comprehensive identification method achieves effective and stable classification performance across different ore grades. Specifically, the implementation of standardization and EMD-based denoising has been demonstrated to enhance the accuracy of CNNs in recognizing diverse ores.

This article proposes a Data-Driven Physical Model (DDPM) to access shop floor manufacturing service reliability for the uncertain manufacturing collaboration process on the workshop. Firstly, based on the matching of manufacturing services in the workshop, consider the failure modes of the manufacturing service collaboration chain, and quantify the efficiency of manufacturing task execution. Secondly, manufacturing service nodes contain rich information that matches the structural information of graph data, a graph convolutional neural network (GCN) method is used. Finally, GCN is used to extract features from a large amount of historical high-frequency data for reliability prediction of the workshop manufacturing service process. The experimental results show that, the performance of GCN is superior to other typical algorithms.

Minerals are non-renewable resources that are indispensable for contemporary industrial production. The advent of intelligent ore sorting technologies has been pivotal in enhancing mineral utilization, a phenomenon that has been further propelled by the advent of YOLO (You Only Look Once) object detection models for end-to-end detection. However, intelligent ore sorting equipment deployed at mining sites has more exacting requirements regarding the parameters, computational complexity, and inference speed of deep learning networks. Accordingly, this paper proposes a lighter and faster ore sorting YOLO model, namely LFOS-YOLO, derived from the configuration of the YOLO model. The model incorporates partial convolution, parameter-free attention mechanisms, and redundant channel pruning strategies with the objective of achieving an accuracy-lightweight tradeoff that meets the requirements for deployment in a mining site. The experimental results demonstrate that LFOS-YOLO is capable of accomplishing the task of sorting ore samples from a mine in Liaoning, China, with fewer parameters (1.46M), lower GFLOPs (Giga Floating-Point Operations per Second) (3.4), and higher FPS (Frames per Second) (74), achieving the highest mAP (mean Average Precision) (95.4%), which outperforms other models in the YOLO series.

The printed circuit board (PCB) industry is currently facing the challenge of mass customization demands, which places an urgent need for efficient scheduling in PCB production. Due to the production process’s complexity and the environment’s variability, traditional scheduling algorithms often fail to achieve optimal performance in practical applications. This paper establishes a dynamic multi-objective flexible PCB shop scheduling model to address the challenges above. The model uses total tardiness, maximum completion time, and average machine utilization as optimization objectives. Moreover, a rule-embedded deep Q-network (R-DMDQN) algorithm is developed to address the complex dynamic characteristics of the PCB production process. The algorithm integrates characteristics of PCB production, extracting seven selected features to describe the system state. Simultaneously, it embeds six composite scheduling rules developed and guided by specialized knowledge to enhance the interpretability of learned strategies, and to augment the adaptability and flexibility of the algorithm. Through extensive experimental verification, the results show that the R-DMDQN model proposed in this study has significant superiority and stability in improving scheduling performance compared to the existing well-known scheduling rules and the NSGA-II algorithm. The research provides an innovative approach to the automation and optimization of scheduling in the PCB industry. It is expected to promote the application of related technologies in other complex production systems.

Laser powder bed fusion (LPBF) has revolutionized modern manufacturing by enabling high design freedom, rapid prototyping, and tailored mechanical properties. However, optimizing process parameters remains challenging due to the trial-and-error approaches required to capture subtle parameter-microstructure relationships. This study employed a multi-physics computational framework to investigate the melting and solidification dynamics of magnesium alloy. By integrating the discrete element method for powder bed generation, finite volume method with volume of fluid for melt pool behavior, and phase-field method for microstructural evolution, the critical physical phenomena, including powder melting, molten pool flow, and directional solidification were simulated. The effects of laser power and scanning speed on temperature distribution, melt pool geometry, and dendritic morphology were systematically analyzed. It was revealed that increasing laser power expanded melt pool dimensions and promoted columnar dendritic growth, while high scanning speeds reduced melt pool stability and refined dendritic structures. Furthermore, Marangoni convection and thermal gradients governed solute redistribution, with excessive energy input risking defects such as porosity and elemental evaporation. These insights establish quantitative correlations between process parameters, thermal history, and microstructural characteristics, providing a validated roadmap for LPBF-processed magnesium alloy with tailored performance.

In this paper, a Simulated Annealing Self-Organizing Map (SA-SOM) algorithm is proposed to solve the Printed Circuit Board (PCB) drilling path optimization problem. First, the PCB hole types are analyzed, and it is found that the key to solving the PCB drilling path optimization problem (PDPO) lies in planning the paths of pad holes and through holes. After that, the SA-SOM algorithm is proposed to plan the paths. The SA-SOM algorithm is based on the Self-Organizing Map (SOM) algorithm, with targeted modifications of the learning rate and the neighborhood function, and the SA-SOM algorithm is more suitable for the PDPO. The experimental results show that the optimal distance of the SA-SOM algorithm is about 15% better than the comparison algorithm, and the solution time is better than the comparison algorithm when the borehole size is larger than 1000.

In modern industry, iron plays an indispensable role as a vital pillar material (Wang et al. 2023). However, Magnetite ore, one of the primary raw materials of iron, is a valuable non-renewable resource (Sahu et al 2022). Therefore, it is particularly urgent to improve the effective use of magnetite ore. The refined sorting of magnetite ore is no longer limited to the simple distinction between good and waste ore but is accurately sorted into several grades according to industrial needs. It not only helps to improve the quality of magnetite ore but also reduces the production of tailings, which contributes to the rational use of resources and the protection of the environment.

In semiconductor manufacturing, to ensure the stability of the wafer processing environment, wafer fabrication plants tend to adopt cluster tools with equipment front-end module (EFEM) for wafer processing. Cluster tools typically integrate an EFEM, a load lock module (LLM), and a vacuum module (VM). As a shared module between EFEM and VM, the LLM introduces new challenges in coordinating with the robots in both modules. This paper focuses on investigating the impact of the LLM task and its collaborative scheduling with robot task in EFEM and VM. A Petri net (PN) model is established to depict the coordinated operation of EFEM, VM, and LLM. Based on the proposed PN model, the situation in which the LLM-related circuit ratios become tool bottlenecks is analyzed. Accordingly, two algorithms are developed to rationally allocate the robot waiting times, thereby achieving optimal collaborative scheduling among the EFEM, LLM, and VM. The performance and efficiency of the proposed algorithm are validated through experimental verification.

Wafer fabrication is a critical process in semiconductor manufacturing. Cluster tools with Equipment Front-End Module (EFEM) are widely used in wafer fabrication. These tools consist of a Vacuum Module (VM), LoadLock Module (LLM), and EFEM. The function of the LLM to switch between the atmospheric and vacuum environments increases the complexity of collaborative scheduling. The dynamic variation of the workload during the start-up transient process also makes the problem even more difficult. To address these issues, this study focuses on their collaborative scheduling mechanisms between robots and the LLM. A scheduling sequence is proposed to coordinate a single-arm robot in EFEM and a dual-arm robot in VM with the LLM. Based on this sequence, a Linear Programming Model (LPM) is developed to optimize the start-up transient process. Finally, experiments are conducted to verify the effectiveness of the proposed method.

Addressing the hybrid flow shop scheduling problem (HFSP) of printed circuit boards, this paper presents an adaptive variable neighborhood differential evolution algorithm based on Long Short-Term Memory (LSTM). The approach employs integer coding and plug-in greedy decoding strategies to simplify the problem's complexity; By incorporating a variable neighborhood search mechanism, it enhances the convergence speed and solution quality; LSTM is utilized to dynamically adjust mutation and crossover factors, it further balances the algorithm's global exploration and local exploitation capabilities. The experimental results demonstrate that Adaptive variable neighborhood search differential evolution (AVNSDE) algorithm outperforms the traditional variable neighborhood search differential evolution (VNSDE) algorithm in PCB scheduling, effectively reducing completion time, cost, and premature convergence. This solution offers both theoretical value and practical application for the multi-objective optimization of HFSP.

The existing magnetite sorting equipment is afflicted with two significant deficiencies: high energy consumption and a lack of intelligence. Accordingly, a set of high-efficiency intelligent magnetite sorting equipment was designed. The device employs Hall sensors to identify the magnetic induction signal of magnetite and transmits commands to a solenoid valve via a STM32 controller, thereby enabling precise sorting through a blowing device. However, in practice, the sensors mounted on the rack are susceptible to interference from vibration noise. Consequently, a comprehensive examination of the intrinsic and prestressed modes of the equipment frame was conducted, revealing a notable decline in the intrinsic frequency of the frame, averaging approximately 0.018 Hz, following the application of the prestressing force. Moreover, the fifth intrinsic frequency exhibited a strong correlation with the operating frequency of the air compressor motor, potentially leading to resonance and resulting in damage to the sensors' normal functionality. Accordingly, the structural design of the equipment frame was optimized, particularly in the deformable area, and square steel tubes were employed to enhance its stability. The optimized frame's inherent frequency successfully avoids the operating range of the air compressor motor, effectively avoiding the resonance problem and ensuring the stable operation of the sensor.