Search Results (198)

Automatic component recognition plays a crucial role in intelligent ship manufacturing, but existing methods suffer from low recognition accuracy and high computational cost in industrial scenarios involving small samples, component stacking, and diverse categories. To address the requirements of shipbuilding industrial applications, a Triplet Spatial Reconstruction Attention (TSA) mechanism that combines threshold-based feature separation with triplet parallel processing is proposed, and a lightweight You Only Look Once Ship (YOLO-Ship) detection network is constructed. Unlike existing attention mechanisms that focus on either spatial reconstruction or channel attention independently, the proposed TSA integrates triplet parallel processing with spatial feature separation–reconstruction techniques to achieve enhanced target feature representation while significantly reducing parameter count and computational overhead. Experimental validation on a small-scale actual ship component dataset demonstrates that the improved network achieves 88.7% mean Average Precision (mAP), 84.2% precision, and 87.1% recall, representing improvements of 3.5%, 2.2%, and 3.8%, respectively, compared to the original YOLOv8n algorithm, requiring only 2.6 M parameters and 7.5 Giga Floating-point Operations per Second (GFLOPs) computational cost, achieving a good balance between detection accuracy and lightweight model design. Future research directions include developing adaptive threshold learning mechanisms for varying industrial conditions and integration with surface defect detection capabilities to enhance comprehensive quality control in intelligent manufacturing systems. Full article

Achieving sustainable development goals remains a core issue in global development. In response, China has proposed the development of new quality productive forces (NQPFs) through innovative thinking, emphasizing that fostering NQPFs is both an intrinsic requirement and a pivotal focus for advancing high-quality development. Concurrently, the intelligent transformation of the manufacturing sector serves as a critical direction for China’s economic restructuring and upgrading. This paper places “new quality productive forces” and “intelligent transformation of manufacturing” within the same analytical framework. Starting from the logical chain of “new quality productive forces—three major mechanisms—intelligent transformation of manufacturing,” it concretizes the value implications of new quality productive forces into a systematic conceptual framework driven by the synergistic interaction of three major mechanisms: the mechanism of revolutionary technological breakthroughs, the mechanism of innovative allocation of production factors, and the mechanism of deep industrial transformation and upgrading. This study constructs a “3322” evaluation index system for NQPFs, based on three formative processes, three driving forces, two supporting systems, and two-dimensional characteristics. Simultaneously, it builds an evaluation index system for the intelligent transformation of manufacturing, encompassing intelligent technology, intelligent applications, and intelligent benefits. Using national time-series data from 2012 to 2023, this study assesses the development levels of both NQPFs and the intelligent transformation of manufacturing during this period. The study further analyzes the impact of NQPFs on the intelligent transformation of the manufacturing sector. The research results indicate the following: (1) NQPFs drive the intelligent transformation of the manufacturing industry through the three mechanisms of innovative allocation of production factors, revolutionary breakthroughs in technology, and deep transformation and upgrading of industries. (2) The development of NQPFs exhibits a slow upward trend; however, the outbreak of the pandemic and Sino-US trade frictions have caused significant disruptions to the development of new-type productive forces. (3) The level of intelligent manufacturing continues to improve; however, from 2020 to 2023, due to the impact of the COVID-19 pandemic and Sino-US trade conflicts, the level of intelligent benefits has slightly declined. (4) NQPFs exert a powerful driving force on the intelligent transformation of manufacturing, exerting a significant positive impact on intelligent technology, intelligent applications, and intelligent efficiency levels. Full article

Background: Digital transformation is increasingly present in modern logistics, especially in the context of sustainability and circularity pressures. The integration of technologies such as Internet of Things (IoT), Radio Frequency Identification (RFID), and automated platforms involves not only infrastructure but also a strategic vision, a flexible organizational culture, and the ability to support decisions through artificial intelligence (AI)-based systems. Methods: This study proposes an extended conceptual model using structural equation modelling (SEM) to explore the relationships between five constructs: technological change, strategic and organizational readiness, transformation environment, AI-enabled decision configuration, and operational redesign. The model was validated based on a sample of 217 active logistics specialists, coming from sectors such as road transport, retail, 3PL logistics services, and manufacturing. The participants are involved in the digitization of processes, especially in activities related to operational decisions and sustainability. Results: The findings reveal that the analysis confirms statistically significant relationships between organizational readiness, transformation environment, AI-based decision processes, and operational redesign. Conclusions: The study highlights the importance of an integrated approach in which technology, organizational culture, and advanced decision support collectively contribute to the transition to digital and circular logistics chains. Full article

Achieving the dual carbon goal and addressing escalating environmental challenges requires that manufacturing enterprises in China must pursue sustainability via green innovation strategies. A key rationale for green innovation is to overcome boundaries and acquire knowledge through boundary-spanning search. Additionally, leveraging artificial intelligence (AI) capabilities provides technical support throughout the innovation process. Thus, both boundary-spanning search and AI capabilities are crucial for achieving sustainability objectives. Drawing on organizational search and knowledge management theories, this paper aims to analyze how dual boundary-spanning search affects sustainability performance and green innovation. It also examines the moderating role of AI capabilities and constructs a moderated mediation model. We analyzed questionnaire data collected from 171 Chinese manufacturing companies over a 13-month period, employing hierarchical regression and bootstrap sampling methods using SPSS 27.0. Our findings reveal that both prospective and responsive boundary-spanning searches significantly enhance corporate sustainability performance. Furthermore, green innovation acts as a positive partial mediator between dual boundary-spanning search and corporate sustainability performance. Notably, AI capabilities positively moderate the relationship between dual boundary-spanning search and green innovation. They also strengthen the mediating effect of green innovation on the link between dual boundary-spanning search and corporate sustainability performance. Based on these findings, more resources should be allocated to boundary-spanning search while encouraging enterprises to pursue green innovation and develop AI capabilities. These efforts will provide robust support for sustainability performance in the manufacturing sector. Full article

With the rapid advancement of artificial intelligence and smart manufacturing technologies, the penetration of industrial robots into Chinese markets has profoundly reshaped the structure of the labor market. However, existing studies have largely concentrated on the employment substitution effect and the diffusion path of these technologies, while systematic analyses of how industrial robots affect labor resource allocation efficiency across different regional and industrial contexts in China remain scarce. In particular, research on the mechanisms and heterogeneity of these effects is still underdeveloped, calling for deeper investigation into their transmission channels and policy implications. Drawing on panel data from 280 prefecture-level cities in China from 2006 to 2023, this paper employs a Bartik-style instrumental variable approach to measure the level of industrial robot penetration and constructs a two-way fixed effects model to assess its impact on urban labor misallocation. Furthermore, the analysis introduces two mediating variables, industrial upgrading and urban innovation capacity, and applies a mediation effect model combined with Bootstrap methods to empirically test the underlying transmission mechanisms. The results reveal that a higher level of industrial robot adoption is significantly associated with a lower degree of labor misallocation, indicating a notable improvement in labor resource allocation efficiency. Heterogeneity analysis shows that this effect is more pronounced in cities outside the Yangtze River Economic Belt, in those experiencing severe population aging, and in areas with a relatively weak manufacturing base. Mechanism tests further indicate that industrial robots indirectly promote labor allocation efficiency by facilitating industrial upgrades and enhancing innovation capacity. However, in the short term, improvements in innovation capacity may temporarily intensify labor mismatch due to structural frictions. Overall, industrial robots not only exert a direct positive impact on the efficiency of urban labor allocation but also indirectly contribute to resource optimization through structural transformation and innovation system development. These findings underscore the need to account for regional disparities and demographic structures when advancing intelligent manufacturing strategies. Policymakers should coordinate the development of vocational training systems and innovation ecosystems to strengthen the dynamic alignment between technological adoption and labor market restructuring, thereby fostering more inclusive and high-quality economic growth. Full article

Frequent and complex boarding operations require an effective management process for specialized tools. Traditional manual statistical analysis exhibits low efficiency, poor accuracy, and a lack of electronic records, making it difficult to meet the demands of modern aviation manufacturing. In this study, we propose an efficient and lightweight network designed for the recognition and analysis of professional tools. We employ a combination of knowledge distillation and pruning techniques to construct a compact network optimized for the target dataset and constrained deployment resources. We introduce a self-attention mechanism (SAM) for multi-scale feature fusion within the network to enhance its feature segmentation capability on the target dataset. In addition, we integrate a large language model (LLM), enhanced by retrieval-augmented generation (RAG), to analyze tool detection results, enabling the system to rapidly provide relevant information about operational tools for management personnel and facilitating intelligent monitoring and control. Experimental results on multiple benchmark datasets and professional tool datasets validate the effectiveness of our approach, demonstrating superior performance. Full article

Under the background of globalization and the latest technological changes, many enterprises ensure corporate competitiveness and sustainable development by deploying production globalization and transforming production modes. This paper proposes a task-based enterprise model to study how enterprises’ production mode transformation toward intelligent manufacturing affects corporate offshoring production. Intelligent manufacturing forms relative push–pull forces on corporate offshoring production through reshoring effects and offshoring effects on the extensive margin of task sets while promoting corporate offshoring production through productivity effects on the intensive margin. Empirically, this paper constructs a staggered quasi-natural experiment using China’s Intelligent Manufacturing Pilot Demonstration Projects (IMPDP), adopts the heterogeneity-robust nonlinear Difference-in-Differences (DID) method, and confirms that intelligent manufacturing has significant positive causal effects on Chinese manufacturing enterprises’ offshoring production. The reshoring effect of intelligent manufacturing is stronger than the offshoring effect, but its powerful productivity effect masks the reshoring effect in overall empirical results. The positive effects of intelligent manufacturing are more significant in non-state-owned enterprises (non-SOEs) and capital-intensive enterprises. Further considering host country selection for corporate offshoring, this study finds that intelligent manufacturing simultaneously promotes corporate offshoring production to both developed and developing countries, but enterprises prefer Belt and Road Initiative countries. Additionally, intelligent manufacturing also promotes corporate offshore trade activities while causing the reshoring of offshore R&D activities. Overall, the transition of production modes toward intelligent manufacturing in Chinese manufacturing enterprises generally leads to a further expansion of corporate offshoring production. Full article

Magnetorheological finishing is widely used in the high-precision processing of optical components, but due to the influence of multi-source system errors, the convergence of single-pass magnetorheological finishing (MRF) is limited. Although iterative processing can improve the surface accuracy, repeated tool paths tend to deteriorate mid-spatial frequency textures, and for complex surfaces such as aspheres, traditional manual alignment is time-consuming and lacks repeatability, significantly restricting the processing efficiency. To address these issues, firstly, this study systematically analyzes the effect of six-degree-of-freedom positioning errors on convergence behavior, establishes a positioning error-normal contour error transmission model, and obtains a workpiece positioning error tolerance threshold that ensures that the relative convergence ratio is not less than 80%. Further, based on these thresholds, a hybrid self-positioning method combining machine vision and a probing module is proposed. A composite data acquisition method using both a camera and probe is designed, and a stepwise global optimization model is constructed by integrating a synchronous iterative localization algorithm with the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The experimental results show that, compared with the traditional alignment, the proposed method improves the convergence ratio of flat workpieces by 41.9% and reduces the alignment time by 66.7%. For the curved workpiece, the convergence ratio is improved by 25.7%, with an 80% reduction in the alignment time. The proposed method offers both theoretical and practical support for high-precision, high-efficiency MRF and intelligent optical manufacturing. Full article

Thickness inspection of thermal barrier coatings is crucial to safeguard the reliability of high-temperature components of aero-engines, but traditional destructive inspection methods are difficult to meet the demand for rapid assessment in the field. In this study, a new non-destructive testing method integrating terahertz time-domain spectroscopy and machine learning algorithms is proposed to systematically study the thickness inspection of 8YSZ coatings prepared by two processes, namely atmospheric plasma spraying (APS) and electron beam physical vapor deposition (EB-PVD). By optimizing the preparation process parameters, 620 sets of specimens with thicknesses of 100–400 μm are prepared, and three types of characteristic parameters, namely, time delay Δt, frequency shift Δf, and energy decay η, are extracted by combining wavelet threshold denoising and time-frequency joint analysis. A CNN-RF cascade model is constructed to realize coating process classification, and an attention-LSTM and SVR weighted fusion model is developed for thickness regression prediction. The results show that the multimodal feature fusion reduces the root-mean-square error of thickness prediction to 8.9 μm, which further improves the accuracy over the single feature model. The classification accuracy reaches 96.8%, of which the feature importance of time delay Δt accounts for 62%. The hierarchical modeling strategy reduces the detection mean absolute error from 6.2 μm to 4.1 μm. the method provides a high-precision solution for intelligent quality assessment of thermal barrier coatings, which is of great significance in promoting the progress of intelligent manufacturing technology for high-end equipment. Full article

Industrial image anomaly detection plays a critical role in intelligent manufacturing by automatically identifying defective products through visual inspection. While unsupervised approaches eliminate dependency on annotated anomaly samples, current teacher–student framework-based methods still face two fundamental limitations: insufficient discriminative capability for structural anomalies and suboptimal anomaly feature decoupling efficiency. To address these challenges, we propose a Synthetic-Anomaly Contrastive Distillation (SACD) framework for industrial anomaly detection. SACD comprises two pivotal components: (1) a reverse distillation (RD) paradigm whereby a pre-trained teacher network extracts hierarchically structured representations, subsequently guiding the student network with inverse architectural configuration to establish hierarchical feature alignment; (2) a group of feature calibration (FeaCali) modules designed to refine the student’s outputs by eliminating anomalous feature responses. During training, SACD adopts a dual-branch strategy, where one branch encodes multi-scale features from defect-free images, while a Siamese anomaly branch processes synthetically corrupted counterparts. FeaCali modules are trained to strip out a student’s anomalous patterns in anomaly branches, enhancing the student network’s exclusive modeling of normal patterns. We construct a dual-objective optimization integrating cross-model distillation loss and intra-model contrastive loss to train SACD for feature alignment and discrepancy amplification. At the inference stage, pixel-wise anomaly scores are computed through multi-layer feature discrepancies between the teacher’s representations and the student’s refined outputs. Comprehensive evaluations on the MVTec AD and BTAD benchmark demonstrate that our method is effective and superior to current knowledge distillation-based approaches. Full article

Micro smart factories (MSFs) represent a new way for small and medium-sized enterprises (SMEs) to build smart factories. Intelligence and manufacturing are two important dimensions of intelligent manufacturing. However, there is still a gap in the research on the coordinated development of intelligence and manufacturing in MSF. Based on survey data from 93 SMEs in Liaoning Province, a dynamic coupling model of the intelligence dimensions (ID) and manufacturing dimensions (MD) of MSF was constructed. Stock increment was used to simulate the development level of the fusion and dynamically evaluate the degree of coupling coordination. The results show that both ID and MD have different advantages in terms of stock and incremental resources, and that the development of intelligence and manufacturing is imbalanced. In addition, in the transformation process of SMEs, the impact of stock factors is significant and the driving force of incremental factors in intelligent manufacturing is insufficient. Finally, SMEs lack comprehensive planning for the development of intelligent manufacturing processes. Full article

Modular construction has the potential to transform the construction industry, as most (80–95%) of the modules, which are considered prefabricated buildings, are manufactured off-site, which is more efficient, safe, cost-effective, sustainable, productive, and faster than traditional construction. It is not without challenges, however, as it requires detailed and comprehensive planning, high initial costs, and navigating transportation and design constraints. The goal of this study was to identify and categorize the benefits and challenges of modular construction and offer strategies for resolving the challenges. This study also provides a comprehensive review of modular construction methods, including permanent modular construction (PMC), movable modular construction (RMC), volumetric modular construction (VMC), and panelized construction, and examines the connectivity of the modules, as well as the integration of advanced technologies like artificial intelligence (AI). The results revealed that the most frequently cited benefits of modular construction were reducing construction time by up to 50%, 20% cost savings, and material waste reduction of up to 83%. The most common challenges included transportation complexity, limited design flexibility, and high initial costs. The results of this study will assist project managers, construction professionals, and company owners in evaluating modular construction by providing quantified benefits and challenges, a comparative analysis of different modular methods, and insights into effective mitigation strategies, allowing them to assess its suitability based on project timelines, budgets, design requirements, and logistical constraints. Full article

Currently, the global technological competition pattern is accelerating its restructuring, and chip technology, as a core technology for national strategic security and industrial competition, faces a serious bottleneck that seriously restricts the construction of China’s industrial chain security and innovation ecology. A “recognition-evolution” collaborative analysis system was proposed in this study using patent data as a carrier. Firstly, a PKCN-BERT-LDA fusion module was constructed to identify the core technologies of chip design, manufacturing, and packaging testing. Secondly, the traditional main path analysis method was improved by innovatively introducing information entropy theory to construct a dynamic evolution model, and the technological evolution path in the chip field during 2010–2024 was systematically tracked based on the Derwent patent database. According to this study, the field of chip design exhibited a bidirectional innovation feature of “system optimization regional deep cultivation”, while the manufacturing process highlights the non-linear accumulation law of process complexity. Packaging and testing technology tended to develop in synergy with integration and intelligence. Full article

Additive Manufacturing (AM), as a revolutionary breakthrough in advanced manufacturing paradigms, leverages its unique layer-by-layer construction advantage to exhibit significant technological superiority in the fabrication of complex structural components for aerospace, biomedical, and other fields. However, when addressing industrial-grade precision manufacturing requirements, key challenges such as the multi-scale characteristics of surface damage precursors, interference from background noise, and the scarcity of high-quality training samples severely constrain the intelligent transformation of AM quality monitoring systems. This study proposes an innovative microscopic polarization YOLOv11-LSF intelligent inspection framework, which establishes an automated non-destructive testing methodology for AM device micro-nano damage precursors through triple technological innovations, effectively breaking through existing technical bottlenecks. Firstly, a multi-scale perception module is constructed based on the Large Separable Kernel Attention mechanism, significantly enhancing the network’s feature detection capability in complex industrial scenarios. Secondly, the cross-level local network VoV-GSCSP module is designed utilizing GSConv and a one-time aggregation method, resulting in a Slim-neck architecture that significantly reduces model complexity without compromising accuracy. Thirdly, an innovative simulation strategy incorporating physical features for damage precursors is proposed, constructing a virtual and real integrated training sample library and breaking away from traditional deep learning reliance on large-scale labeled data. Experimental results demonstrate that compared to the baseline model, the accuracy (P) of the YOLOv11-LSF model is increased by 1.6%, recall (R) by 1.6%, mAP50 by 1.5%, and mAP50-95 by 2.8%. The model hits an impressive detection accuracy of 99% for porosity-related micro-nano damage precursors and remains at 94% for cracks. Its unique small sample adaptation capability and robustness under complex conditions provide a reliable technical solution for industrial-grade AM quality monitoring. This research advances smart manufacturing quality innovation and enables cross-scale micro-nano damage inspection in advanced manufacturing. Full article

Improvement in the intelligence and reliability of traditional complex machinery in service (TCMIS) is a prerequisite to guarantee the safety and stable production of these manufacturing enterprises. Existing studies on condition monitoring of TCMIS typically suffer from an insufficient volume of data, incomplete consideration of issues, low monitoring accuracy, and lack of long-term validity. This paper proposes to utilize Digital Twin (DT) technology to construct a new generation of intelligent condition monitoring systems and take the coal mill of a coal-fired power plant as an example for practical illustration. The results of the study show that the method used in this paper is 96% for fault diagnosis, which is higher than the level in existing studies, and the practical application effect in coal-fired power plants also proves the effectiveness of this study. This study can provide program references for the development of intelligent transformation of TCMIS, and also provide technical support for the application and promotion of DT technology in this field. Full article