Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 12 of 12

Full-Text Articles in Computer Engineering

Towards Qos-Based Embedded Machine Learning, Tom Springer, Erik Linstead, Peiyi Zhao, Chelsea Parlett-Pelleriti Oct 2022

Towards Qos-Based Embedded Machine Learning, Tom Springer, Erik Linstead, Peiyi Zhao, Chelsea Parlett-Pelleriti

Engineering Faculty Articles and Research

Due to various breakthroughs and advancements in machine learning and computer architectures, machine learning models are beginning to proliferate through embedded platforms. Some of these machine learning models cover a range of applications including computer vision, speech recognition, healthcare efficiency, industrial IoT, robotics and many more. However, there is a critical limitation in implementing ML algorithms efficiently on embedded platforms: the computational and memory expense of many machine learning models can make them unsuitable in resource-constrained environments. Therefore, to efficiently implement these memory-intensive and computationally expensive algorithms in an embedded computing environment, innovative resource management techniques are required at the …


Modeling And Simulation Of Sofc System With Heat Transfer Among Bop Components, Ling Hong, Rongmin Wu, Jianwu Zhou, Tian Xia, Xiaojie Li, Pengjie Tian, Hao Peng, Chunhui Shou Jul 2022

Modeling And Simulation Of Sofc System With Heat Transfer Among Bop Components, Ling Hong, Rongmin Wu, Jianwu Zhou, Tian Xia, Xiaojie Li, Pengjie Tian, Hao Peng, Chunhui Shou

Journal of System Simulation

Abstract: High temperature solid oxide fuel cell (SOFC) is a high temperature and efficient hydrogen-electric conversion device. Its high temperature operating environment puts forward higher requirements for thermal insulation of stack and balance of plants(BoP) in the system. In this paper, a lumped SOFC system model is established based on the thermal efficiency-heat transfer unit number method (ε-NTU method), in combination with limited measurable parameters for high-temperature system.Quantitative analysis of components temperature and heat transfer among components can be achieved by heat exchange simulation between components and BoP hot-box environment. A simple feedback controlleris designed for system self-starting and operation. …


On-Device Deep Learning Inference For System-On-Chip (Soc) Architectures, Tom Springer, Elia Eiroa-Lledo, Elizabeth Stevens, Erik Linstead Mar 2021

On-Device Deep Learning Inference For System-On-Chip (Soc) Architectures, Tom Springer, Elia Eiroa-Lledo, Elizabeth Stevens, Erik Linstead

Engineering Faculty Articles and Research

As machine learning becomes ubiquitous, the need to deploy models on real-time, embedded systems will become increasingly critical. This is especially true for deep learning solutions, whose large models pose interesting challenges for target architectures at the “edge” that are resource-constrained. The realization of machine learning, and deep learning, is being driven by the availability of specialized hardware, such as system-on-chip solutions, which provide some alleviation of constraints. Equally important, however, are the operating systems that run on this hardware, and specifically the ability to leverage commercial real-time operating systems which, unlike general purpose operating systems such as Linux, can …


Dynamic Simulation For Tethered Trailer Vehicle, Chen Ning, Hongchao Ma Jun 2020

Dynamic Simulation For Tethered Trailer Vehicle, Chen Ning, Hongchao Ma

Journal of System Simulation

Abstract: Tethered trailer vehicle is a non professional tractor that drags an unpowered vehicle with hemp rope. This conduct has many problems: poor operating stability, and high incidence of traffic accident. A nonlinear dynamic model for longitudinal, lateral, and yaw motions was developed. The model considers nonlinearity through a modified Dugoff's tire friction model, and is seven-degree-of-freedom. A new nonlinear tethered tractor-trailer combination model was created to simulate critical parameters which would cause unstable state. Then, a trailer front-wheel steering feedback control strategy was derived with the goal of improving stability and trajectory tracking feature of the tractor-trailer system. The …


Moea/D Algorithm Based On The Hybrid Framework For Multi-Objective Evolutionary Algorithm, Hongjun Tian, Wang Lei, Qidi Wu Feb 2020

Moea/D Algorithm Based On The Hybrid Framework For Multi-Objective Evolutionary Algorithm, Hongjun Tian, Wang Lei, Qidi Wu

Journal of System Simulation

Abstract: Aimto the difficulties of designing the bonding mechanism of global optimization algorithm and local search strategy for hybrid multi-objective evolutionary algorithm, and of improving the performance of multi-objective evolutionary algorithms, based on the feedback control idea, a systematic and modular hybrid MOEA/D algorithm combining the global optimization and local search is proposed. In the algorithm, a diversity measure method based on crowded entropy is designed; a local search strategy based on simplified quadratic approximation and population diversity enhancement strategy for MOEA/D is proposed. The numerical experiments show that the proposed HMOEA/D can achieve a balance between diversity …


Harmonic Reduction Of Svc With System Integrated Apf, Yan Xuhui, Wang Feng, Mahmood Ul Hassan, Muhammad Humayun Jan 2020

Harmonic Reduction Of Svc With System Integrated Apf, Yan Xuhui, Wang Feng, Mahmood Ul Hassan, Muhammad Humayun

Turkish Journal of Electrical Engineering and Computer Sciences

Static var compensators (svcs) are widely used to compensate for reactive power in a system. The hybrid active power filter (hapf) in combination with svc has extensively been studied in the literature to reduce harmonics generated by the svc. This study proposes a new topology of svc for three-phase systems based on a three-phase thyristor-control reactor (tcr). The harmonics generated by the tcr are minimized by an active power filter (apf), which can be realized by a reduced resonant capacitor size. A control strategy comprising feedback and feedforward control is employed to achieve good harmonic reduction and fast transient response. …


Global Stabilization Of A Class Of Fractional-Order Delayed Bidirectional Associativememory Neural Networks, Zhanying Yang, Xiaoyun Tang, Jie Zhang Jan 2019

Global Stabilization Of A Class Of Fractional-Order Delayed Bidirectional Associativememory Neural Networks, Zhanying Yang, Xiaoyun Tang, Jie Zhang

Turkish Journal of Electrical Engineering and Computer Sciences

This paper focuses on the stabilization problem of a class of fractional-order bidirectional associative memory neural networks with time delays. Based on feedback control, a sufficient condition is derived to achieve the global stabilization of systems by using the fractional inequality, the Lyapunov stability theory, and the comparison principle. In particular, this kind of control scheme is proved to be robust in the presence of external disturbances when the feedback gains are sufficiently large. In addition, a condition is obtained to achieve the global quasi-stabilization of systems with some external disturbances, and the corresponding error bound is estimated. Finally, some …


Analysis Of Feedback Control Applied With Command Shaping To Minimize Residual Vibration, Nicholas L. Jacobs Aug 2016

Analysis Of Feedback Control Applied With Command Shaping To Minimize Residual Vibration, Nicholas L. Jacobs

Open Access Theses

Joint flexibility is a physical trait that affects all robotic systems to some degree. This characteristic has been shown to be very detrimental to the performance of these robotic systems when implementing fast point-to-point motion. During such motion, the robot will induce vibrations in its structure that will extend past the completion of the move. Many techniques have been applied over the years in order to minimize these residual vibrations. One such method is known as command shaping, which will construct the input profile so as to avoid exciting the natural frequencies of the system. This work seeks to extend …


A Centralized Self-Adaptive Fault Tolerance Approach Based On Feedback Control For Multiagent Systems, Şebnem Bora, Oğuz Di̇kenelli̇ Jan 2016

A Centralized Self-Adaptive Fault Tolerance Approach Based On Feedback Control For Multiagent Systems, Şebnem Bora, Oğuz Di̇kenelli̇

Turkish Journal of Electrical Engineering and Computer Sciences

Our research introduces a self-adaptive fault tolerance approach for multiagent systems that enables the system to avoid crash failures. It is a replication-based approach that exploits a feedback control loop and a proportional (P) controller within a replication infrastructure. Thus, we are able to both observe the agents' behaviors to estimate criticalities and determine the number of replicas in replica groups with respect to the agents' criticalities and the number of available resources. Thus, agents that are to be replicated and the numbers of replicas in replica groups are automatically and adaptively identified in dynamic environments. We implement this approach …


Optimal In Vitro Realization Of Pulsatile Coronary Artery Flow Waveforms Using Closed-Loop Feedback Algorithms With Multiple Flow Control Devices, Serdar Yilmaz, Onur Toker, Nurullah Arslan, Herman Sedef Jan 2012

Optimal In Vitro Realization Of Pulsatile Coronary Artery Flow Waveforms Using Closed-Loop Feedback Algorithms With Multiple Flow Control Devices, Serdar Yilmaz, Onur Toker, Nurullah Arslan, Herman Sedef

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we study optimal in vitro realization of pulsatile coronary artery flows using newly proposed closed-loop feedback algorithms with a clearly defined mathematical performance objective, and we compare several flow control device technologies in terms of their ability to generate pulsatile flow signals as accurately as possible. In the literature, there are several published results for in vitro pulsatile flow realization systems. However, most of the proposed systems operate in an open-loop setting and use a single flow control device, and their performance is assessed mostly by graphical means without a clearly defined mathematical performance objective. Furthermore, some …


Study And Control Of 5-Level Pwm Rectifier-5-Level Npc Active Power Filter Cascade Using Feedback Control And Redundant Vectors, Thameur Abdelkrim, El Madjid Berkouk, Karima Benamrane, Tarak Benslimane Jan 2012

Study And Control Of 5-Level Pwm Rectifier-5-Level Npc Active Power Filter Cascade Using Feedback Control And Redundant Vectors, Thameur Abdelkrim, El Madjid Berkouk, Karima Benamrane, Tarak Benslimane

Turkish Journal of Electrical Engineering and Computer Sciences

The purpose of this paper is to develop a control and regulation method for the input DC voltages of a 5-level neutral point clamping (NPC) active power filter (APF). This APF is applied for the enhancement of medium-voltage network power quality by compensation of harmonic currents produced by an induction motor speed variator. In the first part, the authors present a topology of a 5-level NPC voltage source inverter and its simplified space vector pulse width modulation (SVPWM) control strategy. In the second part, the control strategy of the 5-level pulse width modulation current rectifier is presented. In the third …


Adaptive Performance And Power Management In Distributed Computing Systems, Ming Chen Aug 2010

Adaptive Performance And Power Management In Distributed Computing Systems, Ming Chen

Doctoral Dissertations

The complexity of distributed computing systems has raised two unprecedented challenges for system management. First, various customers need to be assured by meeting their required service-level agreements such as response time and throughput. Second, system power consumption must be controlled in order to avoid system failures caused by power capacity overload or system overheating due to increasingly high server density. However, most existing work, unfortunately, either relies on open-loop estimations based on off-line profiled system models, or evolves in a more ad hoc fashion, which requires exhaustive iterations of tuning and testing, or oversimplifies the problem by ignoring the coupling …