Search

This paper explores the application and development trends of artificial intelligence (AI) technology, particularly machine learning and natural language processing in the field of failure analysis. Failure analysis is a crucial method for ensuring the reliability and safety of equipment, and is widely used in aerospace, automotive manufacturing, electronic devices, and other fields. Traditional failure analysis methods often rely on expert experience, which is time-consuming and laborious. By integrating AI’s powerful data processing capabilities with traditional methods, the accuracy and efficiency of analysis have been significantly enhanced. In terms of failure mode diagnosis, AI can rapidly and accurately identify various fault modes and provide precise diagnostic results. In failure cause diagnosis, AI integrates data from multiple sources to uncover complex failure factors and potential causal relationships, improving diagnostic reliability. In failure prediction, machine learning can accurately forecast material lifespan and strength, reducing experimental time and costs. In failure prevention, AI offers new approaches to effectively reduce the risk of failure and lower product maintenance costs. The paper also looks forward the future development prospects of AI in failure analysis and highlights challenges and recommendations in the areas, such as data quality improvement, model optimization, interdisciplinary collaboration, and ethical and safety issues.

Effects of hot isostatic pressing (HIP) temperature on the microstructural evolution of a nickel-based K002 superalloy containing Hf element after long-term service were investigated using three different soaking temperatures during HIP. The degraded γ′ precipitates represented coarse and irregular morphology after long-term service. These γ′ precipitates still were of coarse and irregular shape, but the size and volume fraction of γ′ precipitates were markedly reduced under HIP condition of 1,190°C/200 MPa/4 h, indicating that the γ′ precipitates were experiencing a dissolution process. Meanwhile, the concentrically oriented N-type γ′ rafting structure around the cavities was formed. With HIP temperature increase to 1,220°C and 1,250°C, the small-sized, cubic and regular γ′ precipitates were re-precipitated, and the concentrically oriented γ′ structure vanished. The unstable morphology induced by the nucleation and growth of γ matrix was found near the creep cavities, indicating that the solute atoms diffused inward the creep-induced cavities during HIP. However, at HIP temperature of 1,220°C and 1,250°C, a large number of blocky MC(2)-type carbides containing amounts of Hf elements were precipitated, demonstrating that HIP treatment at higher temperatures can result in the formation of a large number of blocky MC(2)-type carbides.

The exploitation of fatigue life prediction methods based on fatigue indicator parameters revealed the influence of the defect size, position, and morphology on the fatigue life and fatigue behavior of additively manufactured metals. Meanwhile, Data‐driven life prediction methods are time‐efficient but inexplainable. Current machine learning‐based fatigue life prediction methods call for not only the accuracy but also the interpretability and stability of prediction results. Thus, the fusion of physical methods and machine learning methods has been a prevailing research topic in fatigue life prediction. In this study, a novel physics‐informed neural network framework is proposed by integrating a fatigue indicator parameter based on defects into the physical constraints term of a loss function. This method outperforms conventional machine learning methods in high‐cycle and very high‐cycle regimes, exhibiting superior prediction performance and generalization ability. Furthermore, the prediction results can be explained from a physical standpoint, correlating with the applicability range of the introduced physical equation describing defect positions. Highlights: A novel machine learning framework integrating a fatigue index parameter is proposed.The physics‐informed neural network has the best fatigue life prediction results.The prediction can be partially interpreted by the introduced physical model. [ABSTRACT FROM AUTHOR]

Bactrocera dorsalis (Hendel), a very destructive insect pest of many fruits and vegetables, is widespread in the tropical and subtropical zones of Asia. However, the northward extension of B. dorsalis has been reported in China recently. It is crucial to determine the origin of new populations and to investigate the invasive potential of the species. Here, we investigated B. dorsalis in Nanyang, Henan Province and Heze, Shandong Province using a combined methodological approach. We first detected the hydrogen stable isotope ratios (δ2H) of B. dorsalis samples. The results showed that the δ2H values for B. dorsalis from Nanyang were consistent with those of the local rainwater. In contrast, the samples from Heze were inconsistent with those of the rainwater in Heze. We then sequenced the complete mitochondrial cytochrome oxidase I (mtDNA COI) from the same fruit fly samples for haplotype diversity and phylogenetic analyses. We found a close genetic relationship between the Heze population and Nanyang, Hefei, Sanya, Fuyang and Wuhan populations. Besides, we surveyed the fruit's origin in the wholesale market, and concluded that B. dorsalis trapped in Heze might have come from Hainan and Zhejiang in China. Finally, overwintering potential experiments showed that a small number of pupae could survive during the test periods in Nanyang, whereas no pupae could survive in Heze. Overall, this study reveals that the Nanyang population of B. dorsalis were resident, whereas the Heze population did not colonize and were repeated entries from other areas every spring. [ABSTRACT FROM AUTHOR]

Primary Sjogren's syndrome (pSS) is a complex chronic autoimmune disease in which local tissue damage in exocrine glands is combined with broader systemic involvement across the body in tissues including the skin. These combined manifestations negatively impact patient health and quality of life. While studies have previously reported differences in immune cell composition in the peripheral blood of pSS patients relative to healthy control subjects, a detailed immune cell landscape of the damaged exocrine glands of these patients remains lacking. Through single-cell transcriptomics and repertoire sequencing of immune cells in paired peripheral blood samples and salivary gland biopsies, we present here a preliminary picture of adaptive immune response in pSS. We characterize a number of points of divergence between circulating and glandular immune responses that have been hitherto underappreciated, and identify a novel population of CD8+ CD9+ cells with tissue-residential properties that are highly enriched in the salivary glands of pSS patients. Through comparative analyses with other sequencing data, we also observe a potential connection between these cells and the tissue-resident memory cells found in cutaneous vasculitis lesions. Together, these results indicate a potential role for CD8+ CD9+ cells in mediating glandular and systemic effects associated with pSS and other autoimmune disorders. [ABSTRACT FROM AUTHOR]

Throughout the past century, the global spread of Bactrocera pests has continued to pose a significant threat to the commercial fruit and vegetable industry, resulting in substantial costs associated with both control measures and quarantine restrictions. The increasing volume of transcontinental trade has contributed to an escalating rate of Bactrocera pest introductions to new regions. To address the worldwide threat posed by this group of pests, we first provide an overview of Bactrocera. We then describe the global epidemic, including border interceptions, species diagnosis, population genetics, geographical expansion, and invasion tracing of Bactrocera pests. We further consider the literature concerning the invasion co-occurrences, life-history flexibility, risk assessment, bridgehead effects, and ongoing implications of invasion recurrences, as well as a case study of Bactrocera invasions of California. Finally, we call for global collaboration to effectively monitor, prevent, and control the ongoing spread of Bactrocera pests and to share experience and knowledge to combat it. [ABSTRACT FROM AUTHOR]