東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Neural network control of a parallel...

Harmon, Frederick G.

FindBook

Google Book

Amazon

博客來

Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle./
作者:	Harmon, Frederick G.
面頁冊數:	262 p.
附註:	Source: Dissertation Abstracts International, Volume: 66-07, Section: B, page: 3908.
Contained By:	Dissertation Abstracts International66-07B.
標題:	Engineering, Mechanical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3182492
ISBN:	9780542237263

Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle.
Harmon, Frederick G.

Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle. - 262 p.

Source: Dissertation Abstracts International, Volume: 66-07, Section: B, page: 3908.

Thesis (Ph.D.)--University of California, Davis, 2005.

Parallel hybrid-electric propulsion systems would be beneficial for small unmanned aerial vehicles (UAVs) used for military, homeland security, and disaster-monitoring missions. The benefits, due to the hybrid and electric-only modes, include increased time-on-station and greater range as compared to electric-powered UAVs and stealth modes not available with gasoline-powered UAVs. This dissertation contributes to the research fields of small unmanned aerial vehicles, hybrid-electric propulsion system control, and intelligent control. A conceptual design of a small UAV with a parallel hybrid-electric propulsion system is provided. The UAV is intended for intelligence, surveillance, and reconnaissance (ISR) missions. A conceptual design reveals the trade-offs that must be considered to take advantage of the hybrid-electric propulsion system. The resulting hybrid-electric propulsion system is a two-point design that includes an engine primarily sized for cruise speed and an electric motor and battery pack that are primarily sized for a slower endurance speed. The electric motor provides additional power for take-off, climbing, and acceleration and also serves as a generator during charge-sustaining operation or regeneration. The intelligent control of the hybrid-electric propulsion system is based on an instantaneous optimization algorithm that generates a hyper-plane from the nonlinear efficiency maps for the internal combustion engine, electric motor, and lithium-ion battery pack. The hyper-plane incorporates charge-depletion and charge-sustaining strategies. The optimization algorithm is flexible and allows the operator/user to assign relative importance between the use of gasoline, electricity, and recharging depending on the intended mission. A MATLAB/Simulink model was developed to test the control algorithms. The Cerebellar Model Arithmetic Computer (CMAC) associative memory neural network is applied to the control of the UAVs parallel hybrid-electric propulsion system. The CMAC neural network approximates the hyper-plane generated from the instantaneous optimization algorithm and produces torque commands for the internal combustion engine and electric motor. The CMAC neural network controller saves on the required memory as compared to a large look-up table by two orders of magnitude. The CMAC controller also prevents the need to compute a hyper-plane or complex logic every time step.

ISBN: 9780542237263Subjects--Topical Terms:

783786
Engineering, Mechanical.

Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle.
LDR:03381nmm 2200289 4500 001 1824550
005 20061201083827.5
008 130610s2005 eng d
020 $a 9780542237263
035 $a (UnM)AAI3182492
035 $a AAI3182492
040 $a UnM $c UnM
100 1 $a Harmon, Frederick G. $3 870118
245 1 0 $a Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle.
300 $a 262 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-07, Section: B, page: 3908.
500 $a Adviser: Andrew A. Frank.
502 $a Thesis (Ph.D.)--University of California, Davis, 2005.
520 $a Parallel hybrid-electric propulsion systems would be beneficial for small unmanned aerial vehicles (UAVs) used for military, homeland security, and disaster-monitoring missions. The benefits, due to the hybrid and electric-only modes, include increased time-on-station and greater range as compared to electric-powered UAVs and stealth modes not available with gasoline-powered UAVs. This dissertation contributes to the research fields of small unmanned aerial vehicles, hybrid-electric propulsion system control, and intelligent control. A conceptual design of a small UAV with a parallel hybrid-electric propulsion system is provided. The UAV is intended for intelligence, surveillance, and reconnaissance (ISR) missions. A conceptual design reveals the trade-offs that must be considered to take advantage of the hybrid-electric propulsion system. The resulting hybrid-electric propulsion system is a two-point design that includes an engine primarily sized for cruise speed and an electric motor and battery pack that are primarily sized for a slower endurance speed. The electric motor provides additional power for take-off, climbing, and acceleration and also serves as a generator during charge-sustaining operation or regeneration. The intelligent control of the hybrid-electric propulsion system is based on an instantaneous optimization algorithm that generates a hyper-plane from the nonlinear efficiency maps for the internal combustion engine, electric motor, and lithium-ion battery pack. The hyper-plane incorporates charge-depletion and charge-sustaining strategies. The optimization algorithm is flexible and allows the operator/user to assign relative importance between the use of gasoline, electricity, and recharging depending on the intended mission. A MATLAB/Simulink model was developed to test the control algorithms. The Cerebellar Model Arithmetic Computer (CMAC) associative memory neural network is applied to the control of the UAVs parallel hybrid-electric propulsion system. The CMAC neural network approximates the hyper-plane generated from the instantaneous optimization algorithm and produces torque commands for the internal combustion engine and electric motor. The CMAC neural network controller saves on the required memory as compared to a large look-up table by two orders of magnitude. The CMAC controller also prevents the need to compute a hyper-plane or complex logic every time step.
590 $a School code: 0029.
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, Aerospace. $3 1018395
650 4 $a Artificial Intelligence. $3 769149
690 $a 0548
690 $a 0538
690 $a 0800
710 2 0 $a University of California, Davis. $3 1018682
773 0 $t Dissertation Abstracts International $g 66-07B.
790 1 0 $a Frank, Andrew A., $e advisor
790 $a 0029
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3182492