Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


BaumannBerndMichael1997 ljc.pdf (747.5 KB)

ETD Abstract Container

Abstract Header

Intelligent Control Strategies For Hybrid Vehicles Using Neural Networks and Fuzzy Logic

Baumann, Bernd Michael
http://rave.ohiolink.edu/etdc/view?acc_num=osu1377172999

Abstract Details

1997, Master of Science, Ohio State University, Mechanical Engineering.
The goal of hybrid vehicle development and operation is to achieve a considerable increase in the automobile's overall fuel economy. This can be achieved by combining a internal combustion engine and an electric machine with an automated manual transmission or a continuously variable transmission. The availability of these highly efficient yet complex components has resulted in various hybrid electric vehicle prototypes like the 1997 Ohio State University FutureCar. However, the control of a hybrid vehicle powertrain remains as the key to actually make use of the potential given by the components. Two intelligent control techniques, neural networks and fuzzy logic, have been explored for their ability to implement hybrid vehicle operation strategies. Software libraries written in the C programming language have been developed which allow the implementation of controllers using both approaches. Based on this, a combination of both neural networks and fuzzy logic systems was developed. This Neuro Fuzzy control scheme allows the use of expert knowledge for the intuitive design of the controller. It also provides the system with the ability to adapt to aging components, changing drivers, and varying driving cycles. Online adaptation is possible. The controller is tolerant to faults and uncertainties, and can be executed in real time. The application of the presented control scheme in the development of a supervisory controller for a parallel hybrid electric vehicle featuring load leveling strategy is shown. This vehicle control unit implements the operation strategy of the vehicle by coordinating the powertrain components. It uses driver inputs and powertrain and vehicle feedback signals to determine optimized operating points of the components. Its outputs are sent to the controllers of the internal combustion engine, the electric machine, and the automated manual transmission and clutch. The system also includes three estimators based on neural networks. They determine the optimum operating point of the internal combustion engine, the road load of the vehicle as seen by the powertrain, and the state of charge of the battery pack. Results from developing these estimators are presented. Simulation results are employed to test the ability of neural networks to handle the inputs and outputs of a vehicle control unit.
Giorgio Rizzoni, Dr. (Advisor)
118 p.
Automotive Engineering; Mechanical Engineering

Recommended Citations

Citations

  • Baumann, B. M. (1997). Intelligent Control Strategies For Hybrid Vehicles Using Neural Networks and Fuzzy Logic [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1377172999

    APA Style (7th edition)

  • Baumann, Bernd. Intelligent Control Strategies For Hybrid Vehicles Using Neural Networks and Fuzzy Logic. 1997. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1377172999.

    MLA Style (8th edition)

  • Baumann, Bernd. "Intelligent Control Strategies For Hybrid Vehicles Using Neural Networks and Fuzzy Logic." Master's thesis, Ohio State University, 1997. http://rave.ohiolink.edu/etdc/view?acc_num=osu1377172999

    Chicago Manual of Style (17th edition)

osu1377172999
407
© 1997, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.