Accurate prediction of welding state is essential for ensuring the quality of aluminum alloy pulsed gas tungsten arc welding (GTAW). While multimodal fusion approaches have advanced welding state prediction, complex environmental noise often introduces interference, reducing prediction accuracy. To address this, we propose a novel multimodal fusion network based on multispectral channel attention mechanism (MFCA-Net). First, our model employs a parallel feature mapping strategy to capture both local and global dependencies within each modality, enhancing receptive field interaction and improving global modeling capabilities. Second, a multispectral channel attention mechanism emphasizes informative features across channels, refining the fusion of local high-frequency and global low-frequency features within each mode and reducing redundancy. Finally, these multimodal features are fused to accurately predict welding state. Experimental results demonstrate that MFCA-Net accurately identifies five typical welding states-lack of penetration, normal penetration, over penetration, misalignment, and burn through-with an accuracy of 98.8 %, and 96.1 % on public datasets. Compared with state-of-the-art methods, MFCA-Net significantly enhances prediction performance, showing strong potential for real-world welding applications.

In situ bioprinting enables precise 3D printing inside the human body using modified bioprinters with thermosensitive bioinks such as gelatin methacrylate (GelMA). However, these devices lack refined temperature-regulated mechanisms essential for ensuring bioink viscosity, as compared to traditional bio-3D printers. Addressing this challenge, this study presents a temperature-regulated printhead designed to improve the fabrication of thermosensitive bioink scaffolds in in situ bioprinting, integrated into a UR5 robotic arm. Featuring a closed-loop system, it achieves a temperature steady error of 1 °C and a response time of approximately 1 min. The effectiveness of the printer was validated by bioprinting multilayer lattice 3D bioscaffolds. Comparisons were made with or without temperature control using different concentrations of GelMA + LAP. The deformation of the bioscaffolds under both conditions was analyzed, and cell culture tests were conducted to verify viability. Additionally, the rheology and mechanical properties of GelMA were tested. A final preliminary in situ bioprinting experiment was conducted on a model of a damaged femur to demonstrate practical application. The fabrication of this printhead is entirely open source, facilitating easy modifications to accommodate various robotic arms. We encourage readers to advance this prototype for application in increasingly complex in situ bioprinting situations, especially those utilizing thermosensitive bioinks.

Welding defect prediction is the foundation for ensuring welding quality in gas tungsten arc welding (GTAW). In the prediction process, method based on molten pool vision is the most effective. Since the classification of molten pool defects relies on a substantial volume of labeled data, it is challenging for the models to be applied industrially. This paper presents an algorithm, FS-Classifier, that can achieve high prediction accuracy based on a limited amount of labeled data. The FS-Classifier comprises two stages: Firstly, an unsupervised training approach named RaP is designed to pre-train the feature extractor using extensive unlabeled daily datasets. The RaP consists of a rotation angle prediction task and a position prediction task, which ensure that the network focuses on salient features and precise elements, respectively. Secondly, the support vectors constructed from limited labeled data are used for the feature classifier. The input data is classified to certain class by computing its distances to support vector. The model achieves an accuracy of 94.5 % on the private dataset and 92.8 % on the public dataset for the six classes of defects using 5 % of labeled data volume. In addition, comparative experiments show that our method only requires 5 % of labeled data to achieve accuracy comparable to traditional supervised learning methods. The proposed algorithm addresses the issue of relying on a substantial amount of labeled data in welding process defect classification.

Objective:This study analyzes the risk points in the quality control of bioink and the main processes of bioprinting, clarifies and explores the quality control and supervision model for bioprinting medical devices, and provides theoretical and practical guidance to ensure the safety and effectiveness of bioprinting medical devices.Methods:The quality control risk points throughout the bioprinting process were comprehensively analyzed, with a particular focus on bioprinting materials and key processes. The regulatory model and methods for bioprinting medical devices were examined. This research concentrated on critical technologies such as extrusion, laser-assisted, and in situ bioprinting, assessing their potential for clinical applications and regulatory challenges.Results:Bioink from different sources should meet regulatory requirements. It is essential to ensure aseptic handling of raw materials and to validate sterilization under "worst-case" conditions.Conclusion:As bioprinting technology advances rapidly, corresponding research into materials, processes, and quality risk control should be conducted to ensure the concurrent development of the regulatory system. This will continuously contribute to the orderly progression of the entire industry and human health.

Arc welding is the common method used in traditional welding, which constitutes the majority of total welding production. The traditional manual and manual teaching welding method has problems with high labor costs and limited efficiency when faced with mass production. With the advancement in technology, intelligent welding technology is expected to become a solution to this problem in the future. To achieve the intelligent welding process, modern sensing technology can be employed to effectively simulate the welder’s sensory perception and cognitive abilities. Recent studies have advanced the application of sensing technologies, leading to the advancement in intelligent welding process. The review is divided into two aspects. First, the theory and applications of various sensing technologies (visual, sound, arc, spectral signal, etc.) are summarized. Then, combined with the generalization of neural networks and attention mechanisms, the development trends in welding sensing information processing and modeling technology are discussed. Based on the existing research results, the feasibility, advantages, and development direction of attention mechanisms in the welding field are analyzed. In the end, a brief conclusion and remarks are presented.

背景:脑卒中是危害中国国民健康的重大疾病之一,具有高发病率、高致残率、高死亡率及高复发率的特点.步态功能障碍或损害被认为是脑卒中最常见和最具破坏性的生理后果之一,积极的下肢康复训练可以促进步态功能的恢复,提高日常生活活动能力,改善患者的生活质量.目的:文章旨在回顾和总结适用于脑卒中后步态量化和分析的研究成果,重点是分析最新的步态分析系统、脑卒中后步态数据处理与分析技术,以及在临床环境中的可行性和潜在价值.方法:以"卒中、步态分析、评估、下肢、时空、运动学、动力学、足底压力、肌电图、机器学习、统计学"为中文检索词,以"stroke,gait analysis,assessment,lower limb,spatiotemporal,kinematics,kinetics,plantar pressure,Electromyography(EMG),machine learning,statistical"为英文检索词,分别检索中国知网及PubMed数据库.检索时间范围为2000年1月至2021年12月.通过阅读文题和摘要进行初步筛选,排除中英文文献重复性研究、低质量期刊及内容不相关的文献,最终纳入60篇文献进行综述.结果 与结论:①传统的定性步态分析主要基于观察步态,具有主观性,在很大程度上受观察者经验的影响,而仪器化步态分析提供了测量的参数,具有良好的准确性和重复性,可用于整个康复过程中的诊断和评估.②快速崛起的智能可穿戴技术和人工智能,正日益引起步态研究者的更多关注:虽然它们在临床环境中的使用还没有得到很好的利用,但这些工具有望改变卒中步态量化的现状,因为它们提供了获取、存储和分析多因素复杂步态数据的手段,同时捕获了其非线性动态可变性,并提供了预测分析的宝贵好处.③在步态分析中,常通过一些特殊参数来描述步态正常与否,包括时空、运动学、动力学及肌电图参数等.了解与步行功能相关的因素可以帮助临床医生和研究人员确定在评估步行功能时应重点关注的步态相关参数.④由于常规统计方法已不能逐渐满足处理仪器化步态分析产生的具有高异质性高复杂性的大数据量,并且步态分析涉及大量相互依赖的参数,由于大量的数据及其相互关系,这些参数很难解释,为了简化评估,将机器学习应用在脑卒中后下肢步态分析中是一个很有前途的解决方案.

通过构建膝关节与定制式增材制造膝关节矫形器有限元模型,模拟膝骨关节炎(KOA)患者佩戴矫形器前后的膝关节生物力学变化,验证矫形器的间室减荷效果,针对矫形器治疗效果开展定量化研究,可用于膝关节矫形器的临床疗效评价.实验经过上海交通大学医学院附属第九人民医院伦理委员会审批通过,招募一名膝骨关节炎的女性,对其膝关节进行光学体表及 CT 扫描,根据单侧减荷原理设计定制式增材制造膝关节矫形器,通过网格划分、材料赋值、边界设置等步骤,利用ANSYS等软件构建包括膝关节与定制式增材制造膝关节矫形器有限元模型,沿下肢负重轴方向对膝关节施加 1100 N的压缩载荷,进行仿真及应力分析,研究定制式增材制造膝关节矫形器对膝关节间室的减荷效果.针对KOA特性进行有限元分析,验证软骨、韧带及下肢皮肤对膝关节承载能力的影响.相较于未佩戴任何矫形器情况,佩戴定制式膝关节矫形器后,膝关节内翻角度减少、内侧压力向外侧转移且内侧间室压力明显降低.定制式增材制造膝关节矫形器可降低早中期内侧间室型膝骨关节炎患者在步行过程中膝关节内侧间室所产生的压力,减荷效果显著.

背景:经皮神经电刺激具有无创、便捷等优点,是治疗慢性颈痛的常用物理因子治疗之一,但目前临床上使用的经皮神经电刺激设备仪器成本高、有特定的场所需求,因此有必要积极探索经济便捷有效的颈痛治疗方法.目的:观察小型贴附式经皮神经电刺激联合颈椎健康宣教对于慢性颈痛的临床疗效.方法:选择2020年11月至2021年7月期间在上海交通大学医学院附属第九人民医院康复科就诊的22例慢性颈痛患者为研究对象,男5例,女17例,年龄18-60岁,在给予颈椎姿势宣教和颈部肌肉居家牵伸训练的基础上,同时每日使用小型贴附式经皮神经电刺激器15 min,持续2周.观察治疗前及治疗后即刻及治疗1,2周后的疼痛目测类比评分、肌肉压痛阈值和颈部功能障碍指数变化情况.结果 与结论:①与治疗前相比,22例患者治疗后即刻及治疗1,2周后的右侧颈部疼痛评分均降低(P<0.05),治疗后即刻与治疗2周后的左侧颈部疼痛评分均降低(P<0.05);②与治疗前相比,22例患者治疗2周后的左侧与右侧斜方肌压痛阈值均提高(P<0.05),治疗2周后左侧与右侧C5C6棘突旁1 cm处压痛阈值均提高(P<0.05);③与治疗前相比,22例患者治疗2周后的颈部功能障碍指数评分降低(P<0.05);④结果表明,小型贴附式经皮神经电刺激结合居家训练在治疗后即刻和短期可明显改善慢性颈痛患者的颈部疼痛情况,短期内也可提高颈部压痛阈值和颈部功能.

背景:随着信息技术发展,3D打印在数字医学领域的应用越来越广泛.目前医学3D打印的研究与应用主要集中在以下方面:①打印器官病理模型与导板帮助术前规划和辅助治疗;②创建定制的假体或内置物支架;③制作个性化的矫形器与支具;④制造具备活性的组织或类器官.目的:通过概述3D打印数字医疗的应用与优势,并针对3D打印数字医疗中心的国内外建设现状、3D打印医疗器械的注册审批等展开总结,为3D打印数字医疗行业的发展提供借鉴.方法:以"3D打印技术,3D打印矫形器,生物3D打印,医疗应用,医疗中心"为中文检索词,以"3D Printing Technology,3D Printed Orthoses,3D Bioprinting,Medical Applications,Medical Center"为英文检索词,分别检索万方数据库、中国知网及PubMed数据库.检索时间范围重点为2010年1月至2022年2月,同时纳入少数经典远期文献.通过阅读文题和摘要进行初步筛选;排除中英文文献重复性研究、低质量期刊及内容不相关的文献,最后纳入60篇文献进行综述.结果 与结论:3D打印技术与临床医学紧密结合,通过跨学科创新应用实现了"医工结合"交叉创新,取得众多科研创新成果.建设3D打印数字化医疗中心将为医院系统性培训医工交叉人员,并提供图像处理与云服务系统建设、在线器械打印等服务,整合数字医学技术,将3D打印应用于临床推向一个崭新的高度.

Knee osteoarthritis is a common disease that affects the activities and participation of the elderly. At present, its clinical diagnosis and follow-up mainly rely on X-ray and Kellgren/Lawrence (K/L) grade, and lack of follow-up and scientific research of biomechanical dimensions, which is difficult to predict the progression and functional changes of knee osteoarthritis. The paper reviewed contribution of the distance and angle measurement based on X-ray, X-ray image processing and the biomechanical markers based on biomechanical parameters for prediction of knee osteoarthritis progress. To show the biomechanical markers' effectiveness and limitations to predict knee osteoarthritis progress and effectiveness of the current limitations and help for further research.

As one of the common internal defects in the aluminum welding process, porosity defect is still challenging for real-time control due to the complexity and diversity of the welding process. Arc spectrum contains large amount of welding process information and is effective for the detection of internal defects. This paper proposed a real-time porosity defect detection method for aluminum alloy in gas tungsten arc welding (GTAW) based on the improved gradient boosting decision tree and arc spectrum. The line and continuum spectrum are separated, and the arc blackbody radiation energy and electron temperature are extracted based on the new spectral separation algorithm. Considering the long-tail distribution characteristic of the training samples, a porosity-focus loss function and a parallel training structure were proposed. More targeted line spectrum features were extracted. The defect recall rate increased by 8.6 %, and the area under the receiver operating characteristic curve (AUC) increased by 5 %, without affecting the detection accuracy and response speed. The confidence level of the prediction results was improved. The model shows better robustness through testing experiments in the face of complex welding conditions and is of great importance to the internal quality monitoring of GTAW.

Intelligent welding robots can perceive changes in the welding process and achieve control over welding quality through various sensing methods. Among these, visual sensors have become the most promising due to their non-contact nature, rich information content, and strong adaptability. This article reviews the development of automatic calibration technology for sensing systems, autonomous guidance methods for robots, and adaptive seam tracking algorithms in intelligent welding robot systems based on visual sensors. Finally, it looks forward to the future of intelligent welding based on visual sensing technology which includes digital twin technology, high-performance algorithm development, discussion on algorithm security issues and hardware advancements in vision.

The gas tungsten arc welding (GTAW) is a classic traditional welding method for aluminum alloys. However, the strong reflection of the welding area illuminated by arc light and the weld pool surface of aluminum alloy work piece determines the difficulty of making the visual sensor disturbed and sensitive during the welding process. The high sensitivity of aluminum alloys to heat input is the difficulty in determining the real-time and stability control of heat input adjustment. Online defect detection in aluminum alloy welding is significantly more difficult compared to materials like low-carbon steel. This paper focuses on intelligent technology in GTAW for aluminum alloys, specifically highlighting multi-information acquisition, defect prediction and quality control of weld formation, penetration state, and pore generation. Firstly, the paper reviews and discusses the development and application of multi-information sensing technology in aluminum alloy GTAW. Subsequently, different modeling methods for defect prediction related to penetration, weld formation, and porosity defects are summarized and compared. Additionally, the application of intelligent control methods in the aluminum alloy welding process is categorized. Finally, existing scientific and technical issues and further research directions are proposed.

背景:肌腱炎目前保守治疗和手术治疗都难以达到治愈效果,临床尚未有可广泛应用的微创便捷的治疗手段.目的:通过建立跟腱炎兔模型探究应用超声乳化仪治疗跟腱炎的可行性.方法:使用胶原酶注射法构建新西兰白兔右下肢跟腱炎模型,将30只新西兰白兔随机分为3组:对照组注射生理盐水,不治疗;模型组注射胶原酶造模,不治疗;治疗组注射胶原酶造模,造模后3周应用超声引导下的超声乳化法治疗跟腱炎病灶.治疗后3周取3组兔的跟腱组织进行生物力学测试、测定组织羟脯氨酸含量及苏木精-伊红染色观察跟腱修复情况.结果 与结论:经超声乳化治疗3周后,苏木精-伊红染色显示治疗组胶原纤维杂乱排列及细胞聚集的情况较模型组有所改善,但生物力学分析及羟脯氨酸含量测定无明显改善.说明超声乳化在治疗肌腱炎方面具有应用前景,但还需对治疗参数和模式进一步探索与优化以多方面提高应用效果.

The real-time detection of porosity in welding process is an important problem to be solved in intelligent welding manufacturing.A new on-line detection method for porosity of aluminum alloy in robotic arc welding based on arc spectrum is proposed in this paper.First,k-shape and the improved k-means were used for the initial feature selection of the preprocessed arc spectrum to reduce the data dimension.Second,the secondary feature selection was carried out based on the importance of features to further reduce feature redundancy.Then,the optimal sample label library was established by combining the final characteristic parameters and the X-ray pictures of welds.Finally,an on-line detection method of porosity in gas tungsten arc welding of aluminum alloy based on light gradient boosting machine(LightGBM)was proposed.Compared with extreme gradient boosting(XGBoost)and categorical boosting(CatBoost),this method can achieve better detection performance.The new method proposed in this paper can be used to detect other welding defects,which is helpful to the development of intelligent welding technology.

Vascularization is vital for the survival and functionality of complex tissue-engineered organs, and immune microenvironment is pivotal for effective vascularization. 3D bioprinting is a powerful technique for manufacturing engineered tissues. However, the reconstruction of functionalized vascular scaffolds with immunomodulatory properties through 3D bioprinting has rarely been reported. In this study, we fabricated scaffolds with immunomodulatory properties by incorporating INF-γ loaded laponite into the mixtures of gelatin methacrylate (GelMA)/alginate/4-arm poly(ethylene glycol) acrylate (PEG) (GAP) through coaxial bioprinting method with a sequential cross-linking mechanism that allows for stable production of 3D microfibrous scaffolds. Laponite addition optimized the hydrogel's physical and chemical performance, improved the rheological properties and printing feasibility while enhancing mechanical stress, making the direct fabrication of scaffolds with increased porosity and decreased filament diameter possible. Furthermore, new scaffolds facilitated the expression of chemotactic factors and accelerated EPC migration toward the microfiber peripheries to form a layer of confluent endothelium. Meanwhile, the scaffolds were capable of releasing IFN-γ in the early stage to stimulate macrophage M1 polarization, followed by induction of M2 polarization via the release of Si4+, Mg2+ as the degradation of laponite occurred, which successfully improved the sprouting and mature of newly formed vasculature, as well as vascularized bone regeneration. Our results suggested that a combination of GAP-IFN-γ@Lap bioink with a dual-step cross-linking procedure could regulate the local immune microenvironment, aiding the formation of a confluent endothelium, promoting angiogenesis and tissue regeneration, which potentially provides an efficient and simple strategy for developing complex vascularized tissues.

Three-dimensional (3D) bioprinting is an emerging research direction in bio-manufacturing, a landmark in the shift from traditional manufacturing to high-end manufacturing. It integrates manufacturing science, biomedicine, information technology, and material science. In situ bioprinting is a type of 3D bioprinting which aims to print tissues or organs directly on defective sites in the human body. Printed materials can grow and proliferate in the human body; therefore, the graft is similar to the target tissues or organs and could accurately match the defective site. This article mainly summarizes the current status of robotic applications in the medical field and reviews its research progress in in situ 3D bioprinting.

The digitalization of medicine promises great advances for global health. Combined with three-dimensional (3D) printing technology, noncontact optical scanner, and computer-aided design, we can make personalized 3D printing scoliosis orthosis for patients across the country - with better diagnostics, personalized treatments, and early disease prevention. We hope optimize the production process of scoliosis orthotics, improve the production efficiency of orthotics, and promote the clinical transformation of 3D-printed scoliosis orthosis. To standardize the design, manufacture, materials, and clinical applications of 3D printing technology in the scoliosis orthosis, Chinese experts in relevant fields were organized to formulate this expert consensus.

背景:许多国外文献对足姿指数的信度进行了研究,但国内少有研究足姿指数应用于扁平足患者中的信度,也未有探讨足姿指数在3D打印矫形鞋垫中的应用.目的:探讨足姿指数(FPI-6)在扁平足患者足部姿势中的信度,对扁平足患者足踝姿势、功能、损伤进行预测,为3D打印个性化矫形鞋垫的设计提供理论依据.方法:选取2020年5至11月就诊于上海交通大学医学院附属第九人民医院骨科的40例6-60岁的扁平足患者,根据年龄分为2组:6-18岁儿童组20例;19-60岁成人组20例.设定FPI-6评定者2名(评定者1、评定者2)经过FPI-6系统学习,熟练后对其足部姿势进行第1次评估,在第1次评估后的7 d内再由评定者1进行第2次评估.计算组内相关系数,对重测信度和评分者间信度进行评价.该研究方案的实施符合《赫尔辛基宣言》和上海交通大学医学院附属第九人民医院对研究的相关伦理要求(医院伦理批件号:2016-124-T73,审批时间:2016-10-26),所有受试者及监护人在参与之前都阅读并签订了知情同意书.结果 与结论:①儿童FPI-6各项及总分重测信度除了外踝上下曲率外ICC均大于0.75,高度可信,其中外踝上下曲率的ICC值在0.4-0.74之间,中等信度(P<0.05);评分者间信度足姿指数各项及总分显示ICC除了外踝上下曲率外均大于0.75,高度可信,其中外踝上下曲率的ICC值在0.4-0.74之间,中等信度(P<0.05);②成人足姿指数各项及总分显示重测信度及评分者间信度为中度到高度可信(P<0.05);③结果 显示,FPI-6在成人和儿童扁平足患者中信度是中度到高度可信,足姿指数可用于评估中国儿童及成年扁平足患者并进行严重程度分级,足姿指数的高可靠性可为后期3D打印鞋垫的设计及治疗效果的评估提供理论依据.

With the development of artificial intelligence, the need for accurate, efficient, and convenient gesture recognition techniques has become more pressing. Traditional EMG (electromyogram) algorithms usually use pre-emptive enhancement when doing data enhancement but do not consider whether the enhanced samples are valid. At the same time, adversarial attack gives new ideas to the model. This paper combines the adversarial attack with data augmentation and proposes the “find valid augmented samples” algorithm. Compared to the noise of 82.25% for the original signal GRU model and 75.11% for the ELM model, the results using our method increase to 87.66% and 88.11% respectively. The experimental results show that this algorithm improves the accuracy of the model compared to other algorithms and contributes to gesture recognition technology.