To address the issue of inaccurate modeling in onboard electro-hydrostatic actuator (EHA) systems, particularly the neglecting of the impact of motor driver input filtering circuits and parasitic line parameters on sy...
详细信息
ISBN:
(数字)9798350349252
ISBN:
(纸本)9798350349269
To address the issue of inaccurate modeling in onboard electro-hydrostatic actuator (EHA) systems, particularly the neglecting of the impact of motor driver input filtering circuits and parasitic line parameters on system input current, a comprehensive mathematical model for the EHA load and onboard generation system is developed This model incorporates feedforward control based on position error compensation to ensure precise tracking of the reference signal by the actuator. Under step input position conditions, the input current waveform and DC bus voltage fluctuations are analyzed. The developed model enables accurate assessment of the impact of high-power actuators like EHA on the aircraft power supply system, providing a basis for optimizing dynamic performance.
Timely and accurate anomaly detection is of great importance for the safe operation of the drilling process. To detect bit bounce during the drilling process, this paper proposes a method based on interval augmentatio...
详细信息
This paper uses ChatGPT to assist traffic manager in traffic signal control and verifies the possibility of applying ChatGPT in traffic control scenarios. We believe ChatGPT has four capabilities, including: knowledge...
详细信息
The proceedings contain 86 papers. The special focus in this conference is on New Technologies, Development and Application. The topics include: Simulation of the Structure and Formation Kinetics of a Metastable Modif...
ISBN:
(纸本)9783031310652
The proceedings contain 86 papers. The special focus in this conference is on New Technologies, Development and Application. The topics include: Simulation of the Structure and Formation Kinetics of a Metastable Modification of Cerium Upon Quenching from a Liquid State;designing the Optimal Geometry of Multi-stage Tools;research of the Surface Oil Absorption processed by Vibration Rolling and Deforming Broaching;genetic Algorithams modeling of Cutting Forces During Turning Hard Steel for Economic Sustanable Production;analysis of Some Parameters in Explosive Forming;design and Manufacturing of Conformal Cooling Channels for Injection Molding: A Review;mind Maps for Key Points of a Reverse Engineering Project;heuristic Search for the Design of Silent Chain Transmissions Using Graphs;Kinesthetic Trajectory Learning of a Collaborative Robot UR 10e with APLC S7-1500;continuous Improvement and Performance Assessment in Knowledge-Based Organizations;cognitive Cyber-Physical Production Systems: A New Concept of Manufacturing Systems on the Route to Industry 5.0;construction of an Automated Door as a Smart Device;improvement of the Technique of Optimal Technological Routes Planning for Machining of the Machine Parts Surfaces;3D Printed Souvenir with Mechanical Iris;Multi-response Optimization of FDM process Parameters Using Taguchi Based Grey Relational analysis Method;development and Design of Air Purifier Device Prototype;the Influence of Technological Parameters on the Geometric Product Specification of the Parts Manufactured by the Fused Deposition modeling;Dimensional and Positional control of Industrial Workpiece Using CMM and Optical 3D Scanner;3D Printed Toys for Children with Disabilities – Study Case in Montenegro;mobile Application mScheduler.
Systems Engineering has evolved interdisciplinary, collaborative approaches to product and process development to manage the development of increasingly complex systems. Architecture definition is a key part of the Sy...
详细信息
ISBN:
(数字)9798350358803
ISBN:
(纸本)9798350358810
Systems Engineering has evolved interdisciplinary, collaborative approaches to product and process development to manage the development of increasingly complex systems. Architecture definition is a key part of the Systems Engineering process. This research focuses on the functional architectures used to describe the decomposition, definition, and allocation of system functions and behavior. Existing state-based modeling of system behavior readily captures subsystem inputs and outputs, making Discrete Time Markov Chain analysis straightforward. However, this is not yet the case for functional modeling and analysis which describes a top-down decomposition of system functional and performance requirements, the logical sequencing of functions, the relative timing and duration of functions, and the inputs and outputs that trigger the execution of ***, a new method is needed to further leverage the information captured during functional architecting that relates to functional flow, timing, and data & message exchanges. Using a simplified avionics example, this new method is demonstrated and results in the creation of experiment data tables summarizing the execution of the functional chain under various input conditions. Markov chain analysis is then used to analyze the resulting sequence of functional states and transition probabilities. This aids system architects in analyzing system behavior to influence system design, testing, and operation even with increasing system complexity.
Wireless Sensor Networks (WSNs) are gaining popularity in industries such as environmental monitoring, processcontrol, and healthcare. WSNs, on the other hand, have constraints such as restricted energy sources and c...
详细信息
A DW is needed to efficiently and continuously prepare data for practical real-time dataanalysis and forecasting with machine learning (ML) algorithms. This paper discusses extraction, transformation, and loading pro...
详细信息
ISBN:
(数字)9798331508180
ISBN:
(纸本)9798331508197
A DW is needed to efficiently and continuously prepare data for practical real-time dataanalysis and forecasting with machine learning (ML) algorithms. This paper discusses extraction, transformation, and loading process (ETL) automation and the critical subsystems integration for algorithmic trading ML modelling and stock market forecasting. Additionally, we discuss a new API designed for direct access to the DW. It opens vast opportunities for performance and dataprocessing time to become critical nonfunctional requirements.
In the process of hunting down and confronting a swarm of drones, due to the large number of targets and their high mobility, it is often difficult to completely prevent the escape of sub-targets in the swarm. For the...
详细信息
In the process of hunting down and confronting a swarm of drones, due to the large number of targets and their high mobility, it is often difficult to completely prevent the escape of sub-targets in the swarm. For the engineering background of multiple armed drones hunting swarm targets, there is an optimization design problem of the deployment quantity of defensive drones and the interception probability of the encirclement. The process of penetrating the encirclement by the swarm is modeled as an M-X/M/1 queuing model with an impatient customer. Based on the constructed model, a numerical solution method based on binary search is proposed for the queuing model. This method adjusts the numerical solution of the system to approximate the analytical solution through the sum of state probabilities in the model. In this way, the problem of nested infinite summation when using analytical methods can be avoided, and the accuracy requirements are met at the same time. Finally, simulation tests verify the effectiveness of the proposed algorithm.
The proceedings contain 31 papers. The topics discussed include: research on communication security strategy for intelligent connected vehicles based on HSM;a pose reconstruction model of soft robot arms based on Coss...
ISBN:
(纸本)9798350385694
The proceedings contain 31 papers. The topics discussed include: research on communication security strategy for intelligent connected vehicles based on HSM;a pose reconstruction model of soft robot arms based on Cosserat Theory;a SIM-to-real pipeline for stroke-based robotic painting;interpretable ml model for quality control of locks using counterfactual explanations;leveraging computer vision in AI for efficient image analysis in case investigations;MSRDN: a super-resolution network for human body;neural-network-based inverse dynamic solutions of an asymmetric parallel robot;the application of autoencoder In IMU dataprocess;research on fabrication and flight performance of Minitype robotic butterfly with visual recognition;research on part feature rule description and matching algorithm based on topological relation;and research on the surface topography inspection of sandpaper based on machine vision.
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstra...
详细信息
ISBN:
(纸本)9781665409155
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models pretrained on datasets dissimilar to their target data, such as chest X-ray models trained on ImageNet, under-perform models trained from scratch. Users that lack the resources to pretrain must use existing models with lower performance. This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pretraining process with an existing pretrained model. Through experimentation on 16 diverse vision datasets, we show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pre-training data. Taken together, HPT provides a simple framework for obtaining better pretrained representations with less computational resources.
暂无评论