Motivated by the increasing requirements in positioning precision for lithography applications, this paper analyzes how the position error in a high-precision motion system is affected by the response of the controlle...
详细信息
The advancement of IoT technology has transformed various aspects of automation, including motor control. This paper delves into the development of an IoT-based system for controlling the speed of a DC motor, specific...
详细信息
This paper proposes a dual output series resonant converter suitable for LED lighting applications, accommodating wide input voltage variations. It utilizes a five-switch converter configuration integrated with boost ...
详细信息
Deep Reinforcement Learning (RL) applied to data-driven control exhibits promising outcomes for control tasks with continuous action spaces. A notable drawback of Deep RL lies in its computational demands, which pose ...
详细信息
ISBN:
(纸本)9798350349467;9798350349450
Deep Reinforcement Learning (RL) applied to data-driven control exhibits promising outcomes for control tasks with continuous action spaces. A notable drawback of Deep RL lies in its computational demands, which pose a concern when considering deploying Deep RL applications on resource-constrained unmanned platforms. Research in mixed numerical precision methods is actively contributing to enhancing the computational efficiency of Deep Learning approaches. While mixed-precision strategies are established for supervised learning tasks, exploration of this realm is limited for Deep RL. Our objective is to bridge this gap in research by enhancing the computational efficiency of the Deep Deterministic Policy Gradient (DDPG) algorithm through the utilization of mixed-precision and loss scaling. We will present numerical cases to quantify the performance and computational advancements of DDPG agents trained with mixed precision in the context of control for a complex dynamic system model.
This article provides a comprehensive overview of improved inventory management models in technology companies and how AI methodologies such as machine learning, predictive analytics, and optimization algorithms are r...
详细信息
High-Efficiency Video Coding (HEVC), standardized as H.265, is at the forefront of video compression technology since its introduction, with its applications ranging from live broadcasting of events with minimum delay...
详细信息
Sensor fault detection and reconstruction are essential for efficient performances of systems and for increased reliability in safety-critical processes. A novel fault estimation scheme is proposed for uncertain syste...
详细信息
ISBN:
(数字)9781665473385
ISBN:
(纸本)9781665473385
Sensor fault detection and reconstruction are essential for efficient performances of systems and for increased reliability in safety-critical processes. A novel fault estimation scheme is proposed for uncertain systems in conjunction with sliding mode observer used for its state estimation. A system is defined using the observer outputs and known inputs to formulate the sensor fault as its unmeasured state. For this system, three observers are designed to estimate the sensor fault;a reduced-order linear observer, a robust sliding mode observer, and a novel norm estimator. The norm observer is an algorithm to estimate the norm bound of the fault. These three observers are validated through simulation exercises.
The proliferation of electric vehicles for both passenger and cargo transportation in all aspects of life has resulted in the extensive utilization and investigation of various types of electrical power converters, wi...
详细信息
ISBN:
(纸本)9798350348774;9798350348781
The proliferation of electric vehicles for both passenger and cargo transportation in all aspects of life has resulted in the extensive utilization and investigation of various types of electrical power converters, with the aim of identifying the most optimal ones for specific applications based on parameters such as cost, complexity of control algorithms, power losses, reliability and many others. This paper evaluates the performance of three battery pack multilevel inverter topologies for aircraft applications using simulation results. The topologies under consideration are the Cross-Switched, Cascaded Half-Bridges, and Battery Modular Multilevel Management Converter. All three topologies enable the integration of the DC-AC converter, Battery Management System, and onboard charger functions on a single platform.
The Cold Chain refers to the process of transporting and storing temperature-sensitive products within a specified temperature range, ensuring that these products maintain their efficacy and safety from manufacturing ...
详细信息
We propose an algorithm for regulation of vertical penetration rate in rotary drilling systems for the case where parameters of the environment are unknown, and only nominal (approximate) values of the drillstring par...
详细信息
暂无评论