Institutional Repository of Institute of Automation, CAS
Not a member yet
23433 research outputs found
Sort by
一种水下机器人用无刷电机控制器
No full text本实用新型涉及一种水下机器人用无刷电机控制器，包括600V直流电，稳压模块，三相全桥功率模块，电流检测模块，绝对值处理模块，转子位置检测模块，控制量死区控制模块和CPU控制模块。所述稳压模块、三相全桥功率模块、无刷直流电机依次连接；电流检测、绝对值处理模块、CPU控制模块依次连接；速度给定模块、正反转控制模块、绝对值处理模块、CPU控制模块依次连接；所述CPU控制模块还通过驱动电路与三相全桥功率模块连接。本实用新型结构简单，模拟量输入控制，自动换向，并能够进行过流保护，系统简单，可靠性高，成本低，本实用新型也可以用于其他水下机器人的推进器驱动系统
一种人机协作机器人铸件打磨控制方法
No full text本发明涉及一种人机协作机器人铸件打磨控制方法，通过两个手柄遥操作机器人打磨大型铸件，包括以下步骤：采集平动手柄的坐标，然后平滑处理采集的坐标；根据手柄的数据计算机器人各轴的位置偏移量，将其作为控制量控制机器人运动，实现对机器人的遥操作控制；在打磨时，以工具在工件坐标系中沿Z向的位移zcontrol为控制量，对工具与工件之间的接触力进行控制；在打磨时，将工具与工件之间的接触力实时反馈到操作人员的手上，使得操作人员在打磨过程中具有环境沉浸感。本发明能够实现对机器人的遥操作打磨控制，并对打磨时工具与工件之间的接触力进行控制与感知，可以实现对大型铸件表面任意可达位置的清理，提高铸件打磨效率并改善操作人员的作业环境
一种轮桨两栖机器人
No full text本发明涉及水陆两栖机器人，特别涉及一种轮桨两栖机器人。包括机械臂、控制电子舱、框架及多个轮桨复合一体结构，其中机械臂和控制电子舱均设置于框架上，且机械臂与控制电子舱连接；多个轮桨复合一体结构沿周向设置于框架上，用于实现水路两栖工作模式。轮桨复合一体结构包括水平螺旋桨固定架、全向轮、水平螺旋桨、齿轮传动及电机，其中电机安装在框架的底部，且输出端与全向轮连接，全向轮的轮轴通过齿轮传动与水平螺旋桨，水平螺旋桨通过水平螺旋桨固定架安装在框架的边缘部，且水平螺旋桨的轴线与全向轮的轴线垂直。本发明全向轮与推进器集成在一套动力系统中，复合机构节约动力源，减小机器人体积，提高空间使用效率
智能传感器主动协同的变电站机器人智能巡检系统及方法
No full text本发明提供了一种智能传感器主动协同的变电站机器人智能巡检系统及方法，本发明巡检系统包括：智能机器人协同巡检层、自主协同层和变电站智能传感层形成三层智能巡检架构。本发明巡检系统中，巡检机器人进行自主路径规划完成图像数据采集，智能传感器感知被检测设备的状态并进行数据预处理和分析，巡检机器人和智能传感器通过近场通信机制和智能执行器进行主动协同，协同服务器基于巡检机器人感知数据进行复杂场景识别，以及对巡检机器人感知数据和智能传感器感知数据进行多源数据融合分析。显著的提升了巡视的及时性，避免操作过程的人员安全风险.减少巡检时的人工干预，保证变电巡视任务顺利进行
GasHisSDB: A new gastric histopathology image dataset for computer aided diagnosis of gastric cancer
No full textBackground and objective: Gastric cancer is the fifth most common cancer globally, and early detection of gastric cancer is essential to save lives. Histopathological examination of gastric cancer is the gold standard for the diagnosis of gastric cancer. However, computer-aided diagnostic techniques are challenging to evaluate due to the scarcity of publicly available gastric histopathology image datasets. Methods: In this paper, a noble publicly available Gastric Histopathology Sub-size Image Database (GasHisSDB) is published to identify classifiers' performance. Specifically, two types of data are included: normal and abnormal, with a total of 245,196 tissue case images. In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation. Seven classical machine learning classifiers, three Convolutional Neural Network classifiers, and a novel transformerbased classifier are selected for testing on image classification tasks. Results: This study performed extensive experiments using traditional machine learning and deep learning methods to prove that the methods of different periods have discrepancies on GasHisSDB. Traditional machine learning achieved the best accuracy rate of 86.08% and a minimum of just 41.12%. The best accuracy of deep learning reached 96.47% and the lowest was 86.21%. Accuracy rates vary significantly across classifiers. Conclusions: To the best of our knowledge, it is the first publicly available gastric cancer histopathology dataset containing a large number of images for weakly supervised learning. We believe that GasHisSDB can attract researchers to explore new algorithms for the automated diagnosis of gastric cancer, which can help physicians and patients in the clinical setting
Microstructure and Properties of WC Particles Reinforced 316L Stainless Steel Composites Prepared by Additive and Subtractive Manufacturing
No full text基于自主研发的增减材复合工艺技术与装备,探索了激光功率和WC颗粒质量分数对316L不锈钢复合材料致密度、组织演变和表面耐磨性能的影响规律.结果表明:随着WC质量分数的增加,试样致密度呈现先升高后降低的趋势,而硬度和耐磨性能均逐渐提高,过多的WC颗粒会使工件内部产生热裂纹,同时降低了工件的表面质量;当激光功率由270 W提高到330 W时粉末充分熔化,凝固后未熔合缺陷明显减少.当WC颗粒质量分数为5%、激光功率为330 W时,增材件的致密度最高达到99.6%;相比未添加WC颗粒的工件,力学性能、耐磨性能和表面质量等指标均有明显提高.</p
Surface topography by water jet-guided laser texturing on wettability of monocrystalline silicon
No full textAt present, the use of microstructure to change the optical properties and wetting properties of the material itself has become the main means to improve the utilization rate of materials in the manufacturing industry. Due to the hydrophilicity of the material surface can achieve underwater self-cleaning, directional transportation function, it becomes an indispensable part of surface modification. Water jet-guide laser processing can significantly reduce the formation of the heat-affected zone and crack, and can clearly ablate the material, with higher precision and resolution. In this experiment, the effects of scan spacing, laser output power and channel aspect ratio are examined and processing conditions for achieving near superhydrophilicity are provided. Owing to the anaerobic processing environment, the surface chemical composition of the material does not change, and the hydrophilicity is increased by 8% to 43% compared with that before. Increasing the aspect ratio can increase the wettability, when the aspect ratio is more than 1.63, the wettability begins to rebound, and the wettability becomes worse. Using small laser power and multiple scanning processing scheme can make the surface covered with tiny small pillars of micro-nano particles layer beneficial to increase the droplet adhesion, and the minimum contact angle can reach 37.2°</p
Fabrication of Multi-Channel Nerve Guidance Conduits Containing Schwann Cells Based on Multi-Material 3D Bioprinting
No full textNerve guidance conduits (NGCs) are an essential solution for peripheral nerve repair and regeneration in tissue engineering and medicine. However, the ability of current NGCs is limited to repairing longer nerve gap (i.e., >20 mm) because it cannot meet the following two conditions simultaneously: (1) directional guidance of the axial high-density channels and (2) regenerative stimulation of the extracellular matrix secreted by Schwann cells (SCs). Therefore, we propose a multi-material 3D bioprinting process to fabricate multi-channel nerve guide conduits (MNGCs) containing SCs. In the article, cell-laden methacrylate gelatin (GelMA) was used as the bulk material of MNGCs. To improve the printing accuracy of the axial channels and the survival rate of SCs, we systematically optimized the printing temperature parameter based on hydrogel printability analysis. The multi-material bioprinting technology was used to realize the alternate printing of supporting gelatin and cell-laden GelMA. Then, the high-accuracy channels were fabricated through the UV cross-linking of GelMA and the dissolving technique of gelatin. The SCs distributed around the channels with a high survival rate, and the cell survival rate maintained above 90%. In general, the study on multi-material 3D printing was carried out from the fabricating technology and material analysis, which will provide a potential solution for the fabrication of MNGCs containing SCs.</p
Fabrication of flexible microfluidic pipes with embedded metal electrodes based on electrohydrodynamic jet printing
No full text微流控芯片在生物、化学、医学等领域受到了研究者们的广泛关注,尤其是含有金属电极的微流体管道在毛细电泳、电化学微量检测、生物医学工程和柔性电子领域具有广泛的需求前景.文章提出了一种简单按需制备阵列化嵌金属电极柔性微流体管道的方法.该方法基于电喷印直写技术并结合翻模和湿法刻蚀工艺,实现了嵌金属电极柔性微流体管道阵列的制备.首先,通过在线性转动接收基底上叠加直写聚乙烯醇(PVA)纤维,制备了可嵌入聚二甲基硅氧烷(PDMS)的表面光滑的线性凸起微结构(线宽为10～100μm,高宽比可大于1:2),并以此作为模板,实现了阵列化柔性微流体沟道的制造;其次,通过在平动接收基底上直写光刻胶作为保护层,并结合湿法刻蚀工艺,实现了在含有微流体沟道阵列的柔性基底上金属图案化导电电极(线宽低至5μm)的灵活制造;最后,对通入不同浓度盐溶液的微流体管道进行电学测试,验证了其管道的导通性和金属电极的导电性.结果表明:基于电喷印的集成制造流程可以灵活、简单、高效、低成本的按需加工阵列化嵌金属电极柔性微流体管道,有望应用在生物医学工程和柔性电子等领域.</p
Research on optimization method of routing buffer linkage based on Q-learning
No full textAbstract
According to the characteristics of the painting process of passenger car manufacturing enterprises, by formulating the routing buffer linkage rules based on the total renewal cost, the linkage process of the bus in the routing buffer is controlled, and an improved Q-learning (Q- The routing buffer of learning) algorithm quickly finds the optimal path method. According to the actual production situation, this method improves the dynamic parameters of the algorithm on the basis of the traditional Q-learning algorithm, and improves the optimization speed and accuracy of the algorithm by establishing the correlation between the work-in-process and its neighboring work-in-process in the current state. Through multiple sets of example simulation tests, the effectiveness of the Q-learning algorithm in solving the optimization problem of routing buffer linkage is verified