Institutional Repository of Institute of Automation, CAS
Not a member yet
23433 research outputs found
Sort by
Unsupervised learning of depth estimation from imperfect rectified stereo laparoscopic images
No full textBackground: Learning-based methods have achieved remarkable performances on depth estimation. However, the premise of most self-learning and unsupervised learning methods is built on rigorous, geometrically-aligned stereo rectification. The performances of these methods degrade when the rectification is not accurate. Therefore, we explore an approach for unsupervised depth estimation from stereo images that can handle imperfect camera parameters. Methods: We propose an unsupervised deep convolutional network that takes rectified stereo image pairs as input and outputs corresponding dense disparity maps. First, a new vertical correction module is designed for predicting a correction map to compensate for the imperfect geometry alignment. Second, the left and right images, which are reconstructed based on the input image pair and corresponding disparities as well as the vertical correction maps, are regarded as the outputs of the generative term of the generative adversarial network (GAN). Then, the discriminator term of the GAN is used to distinguish the reconstructed images from the original inputs to force the generator to output increasingly realistic images. In addition, a residual mask is introduced to exclude pixels that conflict with the appearance of the original image in the loss calculation. Results: The proposed model is validated on the publicly available Stereo Correspondence and Reconstruction of Endoscopic Data (SCARED) dataset and the average MAE is 3.054 mm. Conclusion: Our model can effectively handle imperfect rectified stereo images for depth estimation
An optimal method based on HOG-SVM for fault detection
No full textIn this paper, an improved method based on HOG-SVM (histogram of oriented gradient characteristic and support vector machine) is proposed for fault diagnosis. First, by converting mechanical vibration signals to 3-D (three dimensional) images, this proposed method can extract the T-HOG (improved HOG) feature of 3-D images precisely. With the optimal method, all characteristic information of mechanical vibration signal, including fault characteristic signal and health characteristic signal, are converted into characteristic 3-D image. Then, fault information can be accurately recognized though R-SVM's (optimal SVM) classification. Furthermore, the new method which is tested on two kinds of field tests, including rail and gear box fault diagnosis, has achieved high detection accuracy of 97.3% and 96.7% respectively. Finally, compared with other ML and signal feature extraction methods, the proposed method shows superiority in fault diagnosis, which is significant for industry safety and reliability.</p
A multiagent deep deterministic policy gradient-based distributed protection method for distribution network
No full textRelay protection system plays an important role in the safe and stable operation of distribution network (DN), and the traditional model-based relay protection algorithms are difficult to solve the impact of the increasing uncertainty caused by distributed generation (DG) access on the security of DN. To solve this issue, first, the relay protection characteristics of DN under DG access are analyzed; second, the DN relay protection problem is transformed into multiagent reinforcement learning (RL) problem; third, a DN distributed protection method based on multiagent deep deterministic policy gradient (MADDPG) is proposed. The advantage of this method is that there is no need to build a DN security model in advance; therefore, it can effectively overcome the impact of uncertainty caused by DG access on DN security . Extensive experiments show the effectiveness of the proposed algorithm.</p
一种甘蔗收获机割台仿形装置
No full text本发明属于甘蔗收获机技术领域，特别涉及一种甘蔗收获机割台仿形装置。包括触地部件、连接套筒、固定连接板、横梁及角位移传感器，其中固定连接板连接在横梁上，连接套筒可转动地安装在固定连接板上，触地部件与连接套筒连接，角位移传感器安装在连接套筒的一侧，角位移传感器用于采集触地部件的转动角度变化，从而检测地形高度的起伏变化。本发明可以实现甘蔗收获机对作业地形高度的实时性检测，能够将割台仿形装置模块化，安装简易，使用寿命长
一种包络形深海软体手指及深海软体抓手
No full text本发明涉及软体机器人的软体手指，具体地说是一种包络形深海软体手指及深海软体抓手。软体手指设有手指指尖、包络结构板、小压力囊、大压力囊、密封夹紧片、压力管道等结构，软体手指内部设有两个压力通道，当向压力通道充入液体时，充入的液体通过压力通道导入到小压力囊和大压力囊中，压力囊充液膨胀使得手指实现弯曲。本发明通过手指、夹紧件、直角宝塔接头与三指手掌组装，能够得到三指深海软体抓手。本发明设置的大小压力囊能够在加压时让软体手指不同位置均达到合适的弯曲角度，包络结构板相互配合能够牢牢地包裹住被抓物体，压力管道与直角宝塔接头相互配合能够实现水下密封
一种2A50锻造铝合金的激光增材制造与修复工艺
No full text本发明公开了一种2A50锻造铝合金的激光增材制造与修复工艺，属于铝合金激光增材制造技术领域。该工艺首先根据所采用激光增材设备的功率实际情况确定激光功率、送粉速率和扫描速率的拟定参数范围；然后拟定参数范围内选择多个参数值进行组合，并选择离焦量、扫描方式、搭接率和激光入射偏转角度进行试验测试；试验后，择激光加工后试样外观无明显气孔、未出现坍塌、显微组织均匀细小、力学性能略低于或高于原料锻铝的试样所对应的工艺参数为最优工艺参数。本发明通过对激光功率、送粉速率和扫描速率的大致范围、离焦量、扫描方式、搭接率、激光入射偏转角度的调整，使2A50锻铝合金适用于激光增材及修复
超高压输电线路绝缘子检测机器人
No full text本实用新型涉及绝缘子检测技术领域，特别涉及一种超高压输电线路绝缘子检测机器人。包括控制箱体、自适应导向模块、环抱导向执行机构、环抱导向驱动机构、移动机构、检测夹爪机构、绝缘子电阻检测仪及电源，其中自适应导向模块与移动机构设置于控制箱体的顶部；环抱导向执行机构为两组且对称设置于控制箱体两侧；环抱导向驱动机构设置于控制箱体端部，用于驱动环抱导向执行机构张开或闭合；绝缘子电阻检测仪和电源设置于环抱导向执行机构上；检测夹爪机构为两组，一组固定于控制箱体顶部，另一组设置于移动机构上，两对检测夹爪机构用于爬行及绝缘子串电阻检测。本实用新型结构简单，行走连续，爬行平稳，检测效率高，安全可靠
基于动力学分析的双倾转旋翼无人机模式过渡控制方法
No full text本发明涉及基于动力学分析的双倾转旋翼无人机模式过渡控制方法，针对无人机的非线性动力学模型，抽取了对各个运动自由度具有解耦控制作用的虚拟控制量；结合虚拟控制量对非线性模型的解耦简化，分析了模式过渡过程中的时变动力学特性；设计了增益调度策略处理上述动力学特性的变化，以获得实现飞行模式解耦的直升机模式与固定翼飞机模式虚拟控制量；之后，为上述两组虚拟控制量开展了典型控制律的设计，并基于李雅普诺夫理论与无源性进行了模式过渡过程中的稳定性分析。本发明设计了符合双倾转旋翼无人机模式过渡过程动力学特性的增益调度策略，为具有解耦控制效果的虚拟控制量设计了控制律，实现了典型并列式双倾转旋翼无人机的模式过渡控制
基于工业边缘计算系统的多维异构资源量化方法及装置
No full text本发明属于工业互联网领域，具体说是一种基于工业边缘计算系统的多维异构资源量化方法及装置。包括：获取多维异构资源信息与混合任务流信息；根据多维异构资源，分析多维资源与边缘计算设备实时算力的关系；根据任务流信息，分析不同种类任务执行所需算力；判断任务算力需求与异构边缘计算设备实时算力供给契合程度，实时算力供给是否满足任务算力需求，对多维资源与边缘计算设备实时算力的关系进行增量学习，不断提高量化准确度。本发明提高了工业边缘计算系统中零散异构资源的整体利用率，降低了网络通信负载及私密数据交互，对工业互联网个性化柔性生产起到支撑作用
Isolation method of Saccharomyces cerevisiae from red blood cells based on the optically induced dielectrophoresis technique for the rapid detection of fungal infections
No full textSaccharomyces cerevisiae (S. cerevisiae) has been classically used to treat diarrhea and diarrhea-related diseases. However, in the past two decades, fungal infections caused by S. cerevisiae have been increasing among immunocompromised patients, and it takes too long to isolate S. cerevisiae from blood to diagnose it in time. In this paper, a new method for the isolation and selection of S. cerevisiae from red blood cells (RBC) is proposed by designing a microfluidic chip with an optically-induced dielectrophoresis (ODEP) system. It was verified by theory and experiments that the magnitude and direction of the dielectrophoresis force applied on RBCs and S. cerevisiae are different, which determine that the S. cerevisiae can be isolated from RBCs by the ODEP system. By designing the specific light images and the dynamic separation mode, the optimal operating conditions were experimentally achieved for acquiring higher purity of S. cerevisiae. The purity ranges were up to 95.9%-97.3%. This work demonstrates a promising tool for efficient and effective purification of S. cerevisiae from RBCs and provides a novel method of S. cerevisiae isolation for the timely diagnosis of fungal infections