The paper focuses on using Deep Learning (DL) and Computer Vision (CV) techniques to detect surface defects in rolled metal products. By utilizing a Convolutional Neural Network (CNN), various surface defects can be d...
The paper focuses on using Deep Learning (DL) and Computer Vision (CV) techniques to detect surface defects in rolled metal products. By utilizing a Convolutional Neural Network (CNN), various surface defects can be detected and recognized, ultimately improving production standards and certification of the metal products. Two types of lighting, diffuse and side, are used to improve defect detection, and image preprocessing methods are employed to enhance the quality of the input data. The purpose of this work is to develop a method for recognizing and classifying defects in metal surfaces from their images in real time.
This article presents the results of processing full-scale acoustic emission signals obtained at selective laser melting (SLM) process. During the recording of acoustic emission signals during the SLM process, electri...
This article presents the results of processing full-scale acoustic emission signals obtained at selective laser melting (SLM) process. During the recording of acoustic emission signals during the SLM process, electrical noise and continuous noise arise. For filtering these noises, their frequencies are identified. Noise suppression was carried out on the basis of the previously developed and proposed method for filtering the acoustic emission signal. The scheme of bi-directional filtering and their convolution in the frequency domain is presented. An increase in the efficiency of acoustic emission signal processing has been established. Descriptive analysis of the results before and after filtering the signal parameter shows a statistically significant difference. This difference characterizes the increase in the information content of the measurement results.
The paper is devoted to the problem of Input-to-State Stability (ISS) analysis for descriptor (singular) homogeneous systems. In particular, sufficient conditions for descriptor homogeneous systems to be ISS are propo...
The paper is devoted to the problem of Input-to-State Stability (ISS) analysis for descriptor (singular) homogeneous systems. In particular, sufficient conditions for descriptor homogeneous systems to be ISS are proposed. It is shown that to verify the ISS property it is enough to establish asymptotic stability of a homogeneous descriptor system in disturbance-free case and check provided algebraic conditions. Based on this result it was shown that existing homogeneity-based finite-time controls and observers for linear descriptor systems provide the ISS property with respect to additive disturbances and measurement noise. The results are supported with numerical simulations of the generator system.
The theoretical foundations of the dynamic indentation method for assessing the mechanical characteristics of a material are presented. Computer simulations were performed using the Solid Mechanics, AC/DC, and Moving ...
The theoretical foundations of the dynamic indentation method for assessing the mechanical characteristics of a material are presented. Computer simulations were performed using the Solid Mechanics, AC/DC, and Moving Mesh interfaces in the Comsol Multiphysics software. When modeling the process of registering the motion of an indenter in the course of contact-impact interaction, a primary transducer with a differential circuit for switching on inductors was taken as the basis, which implements the magnetic induction method and the elastic-plastic model of the deformation of the test object. The obtained results were processed, conclusions were drawn about the efficiency of the model, ways of further optimization of the model were proposed, and goals for future research were formulated.
This work proposes the first derivation, implementation, and experimental validation of magnetic-based proprioceptive sensing method for soft robotic applications. In our proposed approach, the magnetic sensing system...
详细信息
ISBN:
(数字)9798331520205
ISBN:
(纸本)9798331520212
This work proposes the first derivation, implementation, and experimental validation of magnetic-based proprioceptive sensing method for soft robotic applications. In our proposed approach, the magnetic sensing system measures gradient tensor contractions that can be directly related to the shape of a deformable plastering tool. Custom-designed and 3D-printed plastering tool embeds two identical permanent magnets that generate a non-symmetric magnetic field tracked by the proposed sensor. Seamless real-time control is enabled with the sensor sampling rate of 1 kHz. Classical linear control is synthesized for the scraper bending angle and orientation control. The tool, sensor, and the proposed control system are validated on robotic plastering and painting tasks.
This paper presents a decentralized graph-based exploration and inspection framework for Multi-Robot systems, designed to address challenges in subterranean and largescale environments. Unlike prior works that focus s...
详细信息
ISBN:
(数字)9798331513283
ISBN:
(纸本)9798331513290
This paper presents a decentralized graph-based exploration and inspection framework for Multi-Robot systems, designed to address challenges in subterranean and largescale environments. Unlike prior works that focus solely on exploration or inspection, this framework integrates volumetric exploration, semantic inspection, and dynamic task allocation into a unified decentralized system. A key novelty of this work is the seamless integration of these modules in a multi-robot setting, allowing UAVs to autonomously coordinate their tasks without relying on centralized control. The framework employs a hierarchical graph structure, utilizing a dense local graph for immediate navigation and a sparse global graph for long-term planning and repositioning. Extensive simulations in large-scale complex-shaped environments demonstrate that the proposed approach improves the completeness of the generated maps, reduces inconsistencies in the constructed mesh, and accelerates the overall exploration-inspection process compared to existing decentralized strategies.
This article presents the application possibilities of unmanned aerial vehicles (UAVs) for the rapid and efficient determination of carbonyl compounds: formaldehyde and acetaldehyde concentrations in gaseous environme...
详细信息
Modern acoustic emission (AE) diagnostic systems are sensitive instruments for detecting developing defects. A significant limitation of the AE method is the difficulty of isolating signals against the background of i...
详细信息
ISBN:
(数字)9798331518752
ISBN:
(纸本)9798331518769
Modern acoustic emission (AE) diagnostic systems are sensitive instruments for detecting developing defects. A significant limitation of the AE method is the difficulty of isolating signals against the background of interference, which significantly reduces the signal-to-interference ratio. Therefore, in this article a cascade filtering scheme for visualizing acoustic signatures through a scalogram is proposed to isolate AE signals that characterize the process of defect formation. Acoustic portraits of the isolated signals characterizing the process of defect formation are given. It is shown that the amplitude of the AE signal from a defective structure during crack formation is characterized by the highest values of the signal amplitude and has a rich frequency-time structure, the signal shape of which is determined by discrete AE.
This paper deals with consensus control for a multi-agent system, where agents are represented via state-space models. It is assumed that they are subjected to sinusoidal disturbances with unknown parameters in the in...
详细信息
This paper deals with consensus control for a multi-agent system, where agents are represented via state-space models. It is assumed that they are subjected to sinusoidal disturbances with unknown parameters in the input channel. The connections between the agents are represented by a cycle-free graph containing a spanning tree. An adaptive distributed control algorithm is proposed, guaranteeing asymptotic convergence of the agents’ states towards consensus, provided that the agent model satisfies the controllability condition. The control algorithm consists of a distributed observer, a distributed control law, and an adaptation law. The theoretical results are proven using LaSalle's invariance principle. Finally, a simulation example is presented to demonstrate the theoretical findings.
This paper introduces a novel approach to the optimal control of linear discrete-time systems subject to bounded disturbances. Our approach is based on the newly established duality between ellipsoidal approximations ...
详细信息
暂无评论