Random vector functional link network with L21 norm regularization for robot visual servo control with feature constraint

Zhiyu Zhou,Jiusen Guo,Yaming Wang,Zefei Zhu 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.9

Uncalibrated visual servoing control still encounters some challenges, such as calculating the interaction matrix with less cost and keeping the current image features within a camera’s field of view (FOV) in a noisy system environment. To solve these problems, we propose a new control method that uses a random vector functional link network with L21 norm regularization to calculate the interaction matrix and further estimate it with a robust information filter (RIF). L21 norm regularization can deal with the global sparsity of input weights and reduce the inherent complexity of a model. The RIF limits noise variance within a certain range to reduce the influence of uncertain noise on the servoing task. We also design a method that reacts to the control law in accordance with the coordinates of image features. It can adjust running speed in real time and keep image features within a camera’s FOV. We apply this method to a six-degrees-of-freedom eye-in-hand manipulator, and several simulations are performed. Simulation results show that the proposed algorithm performs well in the task and achieves good performance in terms of noise resistance. Image features barely escape from the camera’s FOV through the proposed constraint method.

Panting Fatigue of Trapezoidal Corrugated Steel Webs with Mixed-Mode Cracks

Zhiyu Wang,Xiafang Zhou,Zifeng Liu 한국강구조학회 2021 International Journal of Steel Structures Vol.21 No.2

Trapezoidal corrugated steel webs under panting fatigue are represented by repeated cyclical out-of-plane defl ections of their subpanel with mixed-mode cracks. Compared to stiff ened fl at webs, notable fatigue crack formation could take place along with local defl ection. Fatigue tests were conducted for nine composite girders with slender webs and varied corrugation dimensions. Nearly all test girders showed notable local and interactive shear buckling at the corrugated web panel and the panting fatigue cracks are formed under repeated cyclical defl ection while the compression and tension fl anges remain intact. Fatigue cracks are initiated at the junction between the vertical (longer) edge of the subpanel and the boundary of the out-of-plane defl ection region. The crack propagation paths appear to deviate from the original vertical edge due to buckling induced out-of-plane defl ection under mixed-mode stress condition. The test results demonstrate that the Category B’ and Category E suggested by the AASHTO LRFD bridge fatigue design provisions related to the principal stress range and the nominal membrane shear stress range respectively can be considered for the prediction of the fatigue life of trapezoidal Corrugated steel webs in test girders. An appropriate allowance of both the shear stress along the vertical web edge and tension stress from the diagonal plastifi ed tension band is given for the mixed-mode stress intensity factor. The proposed fatigue life prediction allowing for mixed-mode crack growth mostly compares well with test results and its further improvement for the case with higher web panel slenderness ratio is discussed.

Time-varying modal parameters identification of large flexible spacecraft using a recursive algorithm

Zhiyu Ni,Zhigang Wu,Shunan Wu 한국항공우주학회 2016 International Journal of Aeronautical and Space Sc Vol.17 No.2

In existing identification methods for on-orbit spacecraft, such as eigensystem realization algorithm (ERA) and subspace method identification (SMI), singular value decomposition (SVD) is used frequently to estimate the modal parameters. However, these identification methods are often used to process the linear time-invariant system, and there is a lower computation efficiency using the SVD when the system order of spacecraft is high. In this study, to improve the computational efficiency in identifying time-varying modal parameters of large spacecraft, a faster recursive algorithm called fast approximated power iteration (FAPI) is employed. This approach avoids the SVD and can be provided as an alternative spacecraft identification method, and the latest modal parameters obtained can be applied for updating the controller parameters timely (e.g. the self-adaptive control problem). In numerical simulations, two large flexible spacecraft models, the Engineering Test Satellite-VIII (ETS-VIII) and Soil Moisture Active/Passive (SMAP) satellite, are established. The identification results show that this recursive algorithm can obtain the time-varying modal parameters, and the computation time is reduced significantly.

Visual Tracking Using Improved Multiple Instance Learning with Co-training Framework for Moving Robot

( Zhiyu Zhou ),( Junjie Wang ),( Yaming Wang ),( Zefei Zhu ),( Jiayou Du ),( Xiangqi Liu ),( Jiaxin Quan ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.11

Object detection and tracking is the basic capability of mobile robots to achieve natural human-robot interaction. In this paper, an object tracking system of mobile robot is designed and validated using improved multiple instance learning algorithm. The improved multiple instance learning algorithm which prevents model drift significantly. Secondly, in order to improve the capability of classifiers, an active sample selection strategy is proposed by optimizing a bag Fisher information function instead of the bag likelihood function, which dynamically chooses most discriminative samples for classifier training. Furthermore, we integrate the co-training criterion into algorithm to update the appearance model accurately and avoid error accumulation. Finally, we evaluate our system on challenging sequences and an indoor environment in a laboratory. And the experiment results demonstrate that the proposed methods can stably and robustly track moving object.

Embedded spectral descriptors: learning the point-wise correspondence metric via Siamese neural networks

Zhiyu Sun,Yusen He,Andrey Gritsenko,Amaury Lendasse,Stephen Baek 한국CDE학회 2020 Journal of computational design and engineering Vol.7 No.1

A robust and informative local shape descriptor plays an important role in mesh registration. In this regard, spectral descriptors that are based on the spectrum of the Laplace–Beltrami operator have been a popular subject of research for the last decade due to their advantageous properties, such as isometry invariance. Despite such, however, spectral descriptors often fail to give a correct similarity measure for nonisometric cases where the metric distortion between the models is large. Hence, they are not reliable for correspondence matching problems when the models are not isometric. In this paper, it is proposed a method to improve the similarity metric of spectral descriptors for correspondence matching problems. We embed a spectral shape descriptor into a different metric space where the Euclidean distance between the elements directly indicates the geometric dissimilarity. We design and train a Siamese neural network to find such an embedding, where the embedded descriptors are promoted to rearrange based on the geometric similarity. We demonstrate our approach can significantly enhance the performance of the conventional spectral descriptors by the simple augmentation achieved via the Siamese neural network in comparison to other state-of-the-art methods.

Nanofire and scale effects of heat

Zhiyu Hu,Sebastiaan A. Meijer,Qiuchen Wang,Erzhen Mu,Gang Yang,Zhimao Wu 나노기술연구협의회 2019 Nano Convergence Vol.6 No.5

Combustion is a chemical reaction that emits heat and light. Nanofire is a kind of flameless combustion that occurs on the micro–nano scale. Pt/Al2O3 film with a thickness of 20 nm can be prepared as a catalyst by micro–nano processing. When the methanol-air mixture gas passes through the surface of the catalyst, a chemical reaction begins and a significant temperature rise occurs in the catalyst region. Compared to macroscopic combustion, Nanofire has many special properties, such as large temperature gradients, uniform temperature distribution, and fast temperature response. The large temperature gradient is the most important property of Nanofire, which can reach 1330 K/mm. Combined with thermoelectric materials, it can realize the efficient conversion of chemical energy to electric energy. Nanoscale thickness offers the possibility of establishing thermal gradient. On the other hand, large thermal gradient has an effect on the transport properties of phonons and electrons in film materials. From these we can get the scale effects of heat. This article will provide an overview of the preparation, properties and applications of Nanofire, and then a comprehensive introduction to the thermal scale and thermal scale effects.

Increased Risk of Recurrence of Non-Muscle Invasive Bladder Cancer Associated With Psychological Distress: A Prospective Cohort Study

Zhiyu Qian,Weihong Ding,Qidong Zhou,Shengyang Ge,Chuanyu Sun,Ke Xu 대한신경정신의학회 2021 PSYCHIATRY INVESTIGATION Vol.18 No.8

Objective The primary aim was to evaluate the influence of depressive and anxiety symptoms on the 1-year recurrence rate of non-muscle invasive bladder cancer (NMIBC) patients. The secondary aim was to examine the risk factors leading to psychological distress. Methods A total of 104 NMIBC patients were enrolled for interviews, and the Hospital Anxiety and Depression Scale (HADS) questionnaire survey was administered 1 month after their operation. Their cystoscopy results were followed up. The risk factors affecting their 1-year recurrence rate were evaluated through univariate analysis, Cox regression and Kaplan-Meier analysis. The risk factors causing depressive and anxiety symptoms were evaluated through univariate analysis and logistic regression. Results In addition to American Urological Association risk stratification, depressive symptoms were another independent risk factor for recurrence in NMIBC patients (HR: 2.493, 95% CI: 1.048-5.930, p=0.039), and the increase in the recurrence rate was highly significant in intermediate-risk patients (HR: 8.496, 95% CI: 2.178-33.138, p=0.019). Anxiety symptoms were not an independent risk factor for recurrence (HR: 1.655, 95% CI: 0.714-3.837, p=0.240). We also observed that the burden of medical expenses of NMIBC on the family was an independent risk factor for depressive symptoms (p=0.029) and anxiety symptoms (p=0.048); chronic pain was an independent risk factor for anxiety symptoms (OR: 3.447, 95% CI: 1.182-10.052, p=0.023). Conclusion Depression symptoms are an independent risk factor for recurrence in NMIBC patients. Moreover, the burden of medical expenses on the family is an independent risk factor for depressive and anxiety symptoms in NMIBC patients. Additionally, chronic pain is a risk factor for anxiety symptoms in NMIBC patients. This study provided a theoretical foundation for clinical oncologists to pay more attention to the mental health of NMIBC patients.

Exploring the Interplay: Academic Self-Efficacy as a Moderator in the Mediation of Future Time Perspective on Learning Engagement via Hope among Secondary Vocational Students

Zhiyue Ren,이창식 사단법인 한국융합기술연구학회 2024 아시아태평양융합연구교류논문지 Vol.10 No.3

With the continuous popularization of higher education, secondary vocational students also have the opportunity to enter universities, leading to an increasingly competitive learning environment. How to effectively improve their learning engagement is a question worthy of study. This study aims to investigate the moderated mediation effect of academic self-efficacy on the mediating effect of hope between future time perspective and learning engagement of secondary vocational students. The study subjects were purposefully sampled from a vocational school in Dongguan, China. Data was collected through a questionnaire survey to gather information on future time perspective, hope, academic self-efficacy, and learning engagement. A total of 310 responses were collected for analysis. The statistical tools used in this study were SPSS Ver.26 and PROCESS macro Ver.4.2. Conducted reliability analysis, frequency analysis, descriptive statistics, and correlation analysis. And the investigation of the moderated mediation effect was carried out utilizing model 14 within the PROCESS macro. The results of the study revealed that the notable positive correlation was observed among learning engagement, future time perspective, hope, and academic self-efficacy. Moreover, the academic self-efficacy moderated the pathway of future time perspective to learning engagement via hope. The results of this study provide suggestions for designing programs aimed at enhancing the learning engagement of secondary vocational students.

Fatigue Strength Evaluation of Welded Structural Details in Corrugated Steel Web Girders

Zhiyu Wang,Lianfei Tan,Qingyuan Wang 한국강구조학회 2013 International Journal of Steel Structures Vol.13 No.4

Fatigue strength evaluation of welded structural details is of practical significance in the design of corrugated steel webgirders in highway bridges and industrial structures. In this paper, the fatigue strengths of corrugated steel web girders withseveral welded structural details and welding methods are analytically examined by fatigue tests of corrugated web beams andsmall-size welded joints. The stress concentration & distribution characteristics of corrugated web beams were analysed usingfinite element analysis. The beam test results showed that the structure with scallops or notches in the flange has lower fatiguestrength and that with butt joints is prone to suffer from shear crack on the corrugated web. Within the inside range of thescallop, the stress concentration becomes greater with the increase of scallop radius and the tension flange contributessignificantly to the bending capacity of corrugated steel web beams. The tests for small-size welded joints indicated theirapplicability in the analysis and prediction of S-N relationship of the test corrugated steel web beams. Finally, the fatigue crackpropagation lives of weld joints were compared with those of test corrugated steel web beams with respect to related designCategories of the AASHTO LRFD Bridge Design Specifications.

Robot Manipulator Visual Servoing via Kalman Filter- Optimized Extreme Learning Machine and Fuzzy Logic

Zhiyu Zhou,Yanjun Hu,Jiangfei Ji,Yaming Wang,Zefei Zhu,Donghe Yang,Ji Chen 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.8

Visual servoing (VS) based on the Kalman filter (KF) algorithm, as in the case of KF-based image-based visual servoing (IBVS) systems, suffers from three problems in uncalibrated environments: the perturbation noises of the robot system, error of noise statistics, and slow convergence. To solve these three problems, we use an IBVS based on KF, African vultures optimization algorithm enhanced extreme learning machine (AVOA-ELM), and fuzzy logic (FL) in this paper. Firstly, KF online estimation of the Jacobian matrix. We propose an AVOA-ELM error compensation model to compensate for the sub-optimal estimation of the KF to solve the problems of disturbance noises and noise statistics error. Next, an FL controller is designed for gain adaptation. This approach addresses the problem of the slow convergence of the IBVS system with the KF. Then, we propose a visual servoing scheme combining FL and KF-AVOA-ELM (FL-KF-AVOA-ELM). Finally, we verify the algorithm on the 6-DOF robotic manipulator PUMA 560. Compared with the existing methods, our algorithm can solve the three problems mentioned above without camera parameters, robot kinematics model, and target depth information. We also compared the proposed method with other KF-based IBVS methods under different disturbance noise environments. And the proposed method achieves the best results under the three evaluation metrics.