An Experimental Study on the Self-propelled Locomotion System with Anisotropic Friction

Nguyen, Van-Du; Ho, Ky-Thanh; La, Ngoc-Tuan; Ngo, Quoc-Huy; Nguyen, Khac-Tuan

doi:10.1007/978-981-16-3239-6_40

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [5], the authors studied the influence of various friction types on the dynamic behavior of the vibro-impact locomotion system. Similar investigations with numerous experimental data are presented in [6]. The paper [7] is dedicated to the locomotion speed optimization problems and to the analysis of the reliability issues of the self-propelled capsule-type robot.…”

Section: Introductionmentioning

confidence: 60%

Experimental investigation of kinematic characteristics of a wheeled vibration-driven robot

Korendiy¹,

Kachur²,

Gursky³

et al. 2022

Vib. proced.

View full text Add to dashboard Cite

The presented research continues the authors’ previous investigations on the dynamics of a wheeled vibration-driven robot. The main purpose of this paper consists in conducting the experimental studies of the robot motion conditions. The methodology of research is divided into three basic stages: designing the 3D-model of the robot in the SolidWorks software and implementing its experimental prototype; experimental studying the motion conditions and carrying out the corresponding measurements; analyzing the obtained results and forming the conclusions. The main findings (results) are presented in the form of time response curves of the basic kinematic characteristics of the robot motion: displacements, velocities, and accelerations of the robot’s wheeled platform and of the disturbing (impact) body. The novelty of this research consists in substantiating the possibilities of applying the vibro-impact working regimes to improve the kinematic characteristics and operational efficiency of the wheeled vibration-driven robot. The obtained results can be profitably used by designers and researchers of mobile locomotion systems, particularly those for inspecting the pipelines.

show abstract

Section: Introductionmentioning

confidence: 60%

Experimental investigation of kinematic characteristics of a wheeled vibration-driven robot

Korendiy¹,

Kachur²,

Gursky³

et al. 2022

Vib. proced.

View full text Add to dashboard Cite

show abstract

“…Different types of the vibro-impact locomotion systems are thoroughly investigated in numerous scientific papers, e.g. [1]- [4]. The experimental investigations on the self-propelled vibro-impact locomotion system operating under anisotropic friction are presented in [1].…”

Section: Introductionmentioning

confidence: 99%

“…[1]- [4]. The experimental investigations on the self-propelled vibro-impact locomotion system operating under anisotropic friction are presented in [1]. The influence of dry and isotropic friction on the dynamic behavior of a vibro-impact locomotion system is studied in [2].…”

Section: Introductionmentioning

confidence: 99%

“…The analysis of numerous scientific papers (e.g. [1]- [8]) has shown that the problems of implementing the crank excitation mechanisms in the multi-mass vibro-impact locomotion systems are not thoroughly investigated. Therefore, the authors of the present paper have previously studied the improved design of the controllable eccentric-type excitation mechanism [9], investigated the motion conditions of the three-mass vibro-impact system with the crank-slider excitation mechanism [10], and analyzed the possibilities of implementing the proposed excitation mechanism in vibratory compacting equipment [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mathematical model and motion analysis of a wheeled vibro-impact locomotion system

Korendiy¹,

Gursky²,

Kachur³

et al. 2022

Vib. proced.

View full text Add to dashboard Cite

The paper is aimed at investigating the motion conditions of the wheeled vibro-impact locomotion system equipped with the twin crank-slider excitation mechanism and the additional braking mechanisms allowing only one-way rotation of the wheels. The novelty of the present research consists in the improved mathematical model describing the motion conditions of the vibro-impact system and the proposed parameters optimization technique that allows for maximizing the average translational velocity of the wheeled platform. The main idea of this technique is to provide the maximal velocities of internal bodies when they get in contact with the corresponding impact plates. The numerical modeling results describing the dynamic behavior of the vibro-impact system are obtained in Mathematica software and substantiate the correctness of the developed mathematical model and of the proposed parameters optimization technique. The paper can be of significant practical and scientific interest for researchers and engineers studying and improving the vibratory locomotion systems, e.g., for inspecting and cleaning the pipelines.

show abstract

“…As summarized by Song et al., 10 the noisy label problem has been addressed based on deep learning in five ways. (1) Sample selection: sample selection 12,18,19 aimed to identify true‐label samples from noisy training data. MentorNet 12 introduced a collaborative learning paradigm, where a pretrained MentorNet would supervise the training of StudentNet.…”

Section: Introductionmentioning

confidence: 99%

Bayesian statistics‐guided label refurbishment mechanism: Mitigating label noise in medical image classification

et al. 2022

View full text Add to dashboard Cite

Purpose Deep neural networks (DNNs) have been widely applied in medical image classification, benefiting from its powerful mapping capability among medical images. However, these existing deep learning‐based methods depend on an enormous amount of carefully labeled images. Meanwhile, noise is inevitably introduced in the labeling process, degrading the performance of models. Hence, it is significant to devise robust training strategies to mitigate label noise in the medical image classification tasks. Methods In this work, we propose a novel Bayesian statistics‐guided label refurbishment mechanism (BLRM) for DNNs to prevent overfitting noisy images. BLRM utilizes maximum a posteriori probability in the Bayesian statistics and the exponentially time‐weighted technique to selectively correct the labels of noisy images. The training images are purified gradually with the training epochs when BLRM is activated, further improving classification performance. Results Comprehensive experiments on both synthetic noisy images (public OCT & Messidor datasets) and real‐world noisy images (ANIMAL‐10N) demonstrate that BLRM refurbishes the noisy labels selectively, curbing the adverse effects of noisy data. Also, the anti‐noise BLRMs integrated with DNNs are effective at different noise ratio and are independent of backbone DNN architectures. In addition, BLRM is superior to state‐of‐the‐art comparative methods of anti‐noise. Conclusions These investigations indicate that the proposed BLRM is well capable of mitigating label noise in medical image classification tasks.

show abstract

An Experimental Study on the Self-propelled Locomotion System with Anisotropic Friction

Cited by 3 publications

References 12 publications

Experimental investigation of kinematic characteristics of a wheeled vibration-driven robot

Experimental investigation of kinematic characteristics of a wheeled vibration-driven robot

Mathematical model and motion analysis of a wheeled vibro-impact locomotion system

Bayesian statistics‐guided label refurbishment mechanism: Mitigating label noise in medical image classification

Contact Info

Product

Resources

About