http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Zhiyuan Gao,Jiaqi Huang,Zhonghua Miao,Xiaojin Zhu 국제구조공학회 2020 Smart Structures and Systems, An International Jou Vol.25 No.5
Vibration at the tip of various flexible manipulators may affect their operation accuracy and work efficiency. To suppress such vibrations, the feasibility of using MFC actuators and sensors is investigated in this paper. Considering the convergence of the famous filtered-x least mean square (FXLMS) algorithm could not be guaranteed while it is employed for vibration suppression of plants with varying secondary path, this paper proposes a new multiple model switching adaptive control algorithm to implement the real time active vibration suppression tests with a new multiple switching strategy. The new switching strategy is based on a cost function with reconstructed error signal and disturbance signal instead of the error signal from the error sensor. And from a robustness perspective, a new variable step-size sign algorithm (VSSA) based FXLMS algorithm is proposed to improve the convergence rate. A cantilever beam with varying tip mass is employed as flexible manipulator model. MFC layers are attached on both sides of it as sensors and actuators. A co-simulation platform was built using ADAMS and MATLAB to test the feasibility of the proposed algorithms. And an experimental platform was constructed to verify the effectiveness of MFC actuators and sensors and the real-time vibration control performance. Simulation and experiment results show that the proposed FXLMS algorithm based multiple model adaptive control approach has good convergence performance under varying load conditions for the flexible cantilever beam, and the proposed FX-VSSA-LMS algorithm based multiple model adaptive control algorithm has the best vibration suppression performance.
Ying Zhou,Shiqiao Meng,Zhiyuan Gao,Bin He,Qingzhao Kong 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1
Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted highresolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The <i>Recall</i> reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The <i>IoU</i> of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The <i>IoU</i> of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the <i>IoU</i> by 2.9%. In general, our method is of great significance for crack detection.
Genetic Algorithm-based Optimal Design Strategy of a Continuum Surgical Manipulator
Haodong Wang,Zhijiang Du,Zhiyuan Yan,Yongzhuo Gao 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.10
A novel wire-driven continuum surgical robot for laryngeal surgery is presented. The surgical robot is composed of a power transmission interface, a continuum manipulator, a surgical forceps and motors. The motion of the surgical robot is obtained by causing a controlled deformation in the continuum manipulator, which is the core part of the surgical robot. Therefore, the structural design optimization problem of continuum manipulators is solved in this paper. Based on the structure of the continuum manipulator, optimization objectives which include loadcarrying capacity and secondary deformation are established. The non-dominant sorting genetic algorithm with elite strategy (NSGA-II) is adopted for multi-objective optimization. An experimental prototype is constructed based on the designed optimization results. The load-carrying and space-traversal capacity tests prove the effectiveness of the proposed optimization algorithm.