Search

With the development of informatization and digitalization, the transformation of intelligent manufacturing has become the focus. This paper builds an evaluation system based on the scientific evaluation method of the development level of smart manufacturing and the real demand situation. It establishes an evaluation model of intelligent manufacturing MES systems by combining the GA-BP algorithm. Then, a SeqGAN generative adversarial network is used to expand the real samples. The evaluation model was trained and validated by constructing a training model through the BP neural network, taking the sample data of evaluation indexes as the network input and the seven labels from Industry 1.0 to Industry 4.0 as the network output. The results show that the classification accuracy of the model is above 98%, and all of them have achieved good results. In the actual case evaluation, it is judged that the intelligent manufacturing MES system of Company Z is in the range of industry 3.0 to 3.5, and this result is very close to the manual evaluation of the factory field survey. The synthesis shows that the model is reasonable and effective and has important guiding significance for the evaluation of enterprise intelligent manufacturing MES systems.

Background: The incidence and mortality of colorectal cancer (CRC) have been rising steadily. Early diagnosis and precise treatment are essential for improving patient survival outcomes. Over the past decade, the integration of artificial intelligence (AI) and medical imaging technologies has positioned radiomics as a critical area of research in the diagnosis, treatment, and prognosis of CRC. Methods: We conducted a comprehensive review of CRC-related radiomics literature published between 1 January 2013 and 31 December 2023 using the Web of Science Core Collection database. Bibliometric tools such as Bibliometrix, VOSviewer, and CiteSpace were employed to perform an in-depth bibliometric analysis. Results: Our search yielded 1,226 publications, revealing a consistent annual growth in CRC radiomics research, with a significant rise after 2019. China led in publication volume (406 papers), followed by the United States (263 papers), whereas the United States dominated in citation numbers. Notable institutions included General Electric, Harvard University, University of London, Maastricht University, and the Chinese Academy of Sciences. Prominent researchers in this field are Tian J from the Chinese Academy of Sciences, with the highest publication count, and Ganeshan B from the University of London, with the most citations. Journals leading in publication and citation counts are Frontiers in Oncology and Radiology. Keyword and citation analysis identified deep learning, texture analysis, rectal cancer, image analysis, and management as prevailing research themes. Additionally, recent trends indicate the growing importance of AI and multi-omics integration, with a focus on improving precision medicine applications in CRC. Emerging keywords such as deep learning and AI have shown rapid growth in citation bursts over the past 3 years, reflecting a shift toward more advanced technological applications. Conclusions: Radiomics plays a crucial role in the clinical management of CRC, providing valuable insights for precision medicine. It significantly contributes to predicting molecular biomarkers, assessing tumor aggressiveness, and monitoring treatment efficacy. Future research should prioritize advancing AI algorithms, enhancing multi-omics data integration, and further expanding radiomics applications in CRC precision medicine. [ABSTRACT FROM AUTHOR]

Extracting lithium resources from seawater and brine can promote the development of the new energy materials industry. The electrochemical method is green and efficient. Iron phosphate (FePO4) crystal, with its 1D ion channel, holds significant potential as a primary lithium extraction electrode material. Li+ encounters a substantial concentration disadvantage in brines, and the co‐intercalation of Na+ diminishes Li+ selectivity. To address this issue, this work enhances the energy barrier for Na+ insertion through prelithiation strategies applied to the 1D channels of FePO4 crystal, thereby improving Li+ selectivity, and further investigating the prelithiation effect with particle size and morphology control. The results indicate that the Li(4C‐40%)FePO4// Activated carbon(AC) system enhances selectivity of lithium. The Li(4C‐40%)FePO4 with size diameter of 2500 nm demonstrates an energy consumption of 0.79 Wh mol−1 and a purity of 97.94% for lithium extraction at a unit lithium extraction of 5.93 mmol g−1 in simulated brine. Li(4C‐40%)FePO4‐nanoplates demonstrate the most optimal lithium extraction performance among the three morphologies due to their lamellar structure's short ion diffusion path in the [010] channel, favoring Li+ diffusion. The diffusion energy barriers of Li+ and Na+ are calculated using Density Functional Theory (DFT) before and after prelithiation, showing good agreement with experimental results. [ABSTRACT FROM AUTHOR]