This work has as main objective the development of a soft-sensor to classify, in real time, the behaviors of drivers when they are at the controls of a vehicle. Efficient classification of drivers’ behavior while dri...
详细信息
The Russian energy sector underwent significant changes at the end of the 20th and the beginning of the 21st century [1]. The rapid development of engineering and technology in Russia inevitably led to a constant incr...
详细信息
The paper presents an analysis of fast selection of neural network for the purpose of visual analysis of mechanical wear on prism lenses of in-pavement airport navigational lighting systems. This issue is particularly...
The paper presents an analysis of fast selection of neural network for the purpose of visual analysis of mechanical wear on prism lenses of in-pavement airport navigational lighting systems. This issue is particularly important in terms of aviation safety and navigational lighting control, regulated by EASA and ICAO. The article is the next stage of the development of the system for the vision control of lamps, in which the concept of using a different neural network with an increased data set prepared by the authors is presented. The Deep Network Designer tool included in the Matlab 2022b environment was used. The solution using the GoogLeNet neural network allows for the classification of lamps with an accuracy of 88.37%.
The present paper introduces a mathematical model for the cross-talking between microRNA and Protein. Studying the qualitative properties of the proposed model, we infer that the microRNA is an inhibitor for the Prote...
详细信息
At the present time approximately 20% of 6-10 kV cable networks operate with resonant-grounded via arc-suppression coil (ASC) neutral point [1]. Meanwhile, an increasing number of experts note that resonant grounding ...
详细信息
Bayesian Optimization (BO) is a data-driven strategy for minimizing/maximizing black-box functions based on probabilistic surrogate models. In the presence of safety constraints, the performance of BO crucially relies...
详细信息
In this paper, the problem of time-varying aerodynamic parameters identification under measurement noises is studied. By analyzing the key aerodynamic parameters that affect the aircraft control system, a system model...
详细信息
In this paper, the problem of time-varying aerodynamic parameters identification under measurement noises is studied. By analyzing the key aerodynamic parameters that affect the aircraft control system, a system model with extended states for identifying equivalent aerodynamic parameters is established, and error parameters are extended to the system state, avoiding the difficulty caused by the unknown dynamic in the system. Furthermore, an identification algorithm based on extended state Kalman filter is designed, and it is proved that the algorithm has quasi-consistency, thus, the estimation error can be evaluated in real time. Finally, the simulation results under typical flight scenarios show that the designed algorithm can accurately identify aerodynamic parameters, and has desired convergence speed and convergence precision.
This paper develops a physics-informed neural network (PINN) for learning the parameters of commercially implemented adaptive cruise control (ACC) systems. The constant time-headway policy (CTHP) is adopted to emulate...
This paper develops a physics-informed neural network (PINN) for learning the parameters of commercially implemented adaptive cruise control (ACC) systems. The constant time-headway policy (CTHP) is adopted to emulate the core functionality of stock ACC systems (proprietary control logic and its parameters) which is not publicly available. Multi-layer artificial neural networks is a class of universal approximators, and thus the developed PINN can serve as a surrogate approximator to capture the longitudinal dynamics of ACC-engaged vehicles and efficiently learn the unknown parameters of the CTHP. The ability of the PINN to infer the unknown ACC parameters is tested on both synthetic and empirical data of space-gap and relative velocity involved ACC-engaged vehicles in platoon formation. The results have demonstrated the superior predictive ability of the proposed PINN to learn the unknown design parameters of stock ACC systems of different vehicle makes. The set of ACC model parameters obtained from the PINN revealed that the stock ACC system of the considered vehicles in three experimental campaigns is neither $\mathcal{L}_systems$ nor $\mathcal{L}_{\infty}$ string stable.
Robots for automated assembly are being progressively implemented in the aerospace manufacturing sector. The dim and complex internal structure of the aircrafts significantly complicates the operation of robotic arms ...
详细信息
ISBN:
(数字)9798350340266
ISBN:
(纸本)9798350340273
Robots for automated assembly are being progressively implemented in the aerospace manufacturing sector. The dim and complex internal structure of the aircrafts significantly complicates the operation of robotic arms through visual system. This paper proposes an assembly strategy based on force-feedback control for fuel probe installation inside the aircraft wings, enabling autonomous assembly of tubular objects under translational and rotational misalignments. Furthermore, the Bees Algorithm (BA) is employed in a simulation environment to optimise the parameters of this control strategy. The results demonstrate that BA can effectively decrease the overall installation time while simultaneously proving the effectiveness of this method and its potential applicability in aerospace manufacturing.
Medium-voltage distribution networks (6–10 kV in Russia) are the largest and at the same time the most problematic link in the power supply system of consumers. Improving the reliability of medium-voltage overhead di...
Medium-voltage distribution networks (6–10 kV in Russia) are the largest and at the same time the most problematic link in the power supply system of consumers. Improving the reliability of medium-voltage overhead distribution networks is still an urgent task. The task of improving the reliability of networks is directly related to the improvement of algorithms and devices for single-phase earth fault (SPEF) location. Researches of Ivanovo State Power engineering University (ISPEU) and an industrial partner developed automated power control and metering station (APCMS) based on digital measurement voltage and current transformers (DCVT). APCMS contains the function of detecting a damaged section (branch) of a 6–10 kV overhead power transmission line (OTL). In the installed APCMS sample the function works in the test mode, so additional studies of DCVT and APCMS for the tasks of fault location are relevant. The article presents the methodology for determining the faulted section in case of SPEF, considers the features of application of 6–10 kV DCVT and APCMS for determining the faulted section, and also presents the methodology for additional studies of DCVT during SPEFs, including arc faults.
暂无评论