Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

A Novel Approach Using a Neural Network Based Adaptive Filter for Performing Real-Time, On-line Qualitative System Design

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Pp. 288-296 in Automation Technology for Off-Road Equipment, Proceedings of the July 26-27, 2002 Conference (Chicago, Illinois, USA)  701P0502.(doi:10.13031/2013.10018)
Authors:   William R. Norris, Ramavarapu Sreenivas, Qin Zhang
Keywords:   Automatic Steering Control and Guidance, Controllers, Decision Making, Off Road Vehicles, Electro-Hydraulics, Neural Networks, Software Support for Vehicle Automation

The objective of this paper is to demonstrate the development of a tool used in a design framework for performing real time human-in-the-loop system design using virtual environments. The design framework, known as virtual design tools, requires a component that performs on-line adaptation of a design based on human operator performance characteristics. The on-line adaptive component was successfully applied to a four degree of freedom articulated wheel loader electrohydraulic steering design problem. A parameterized input to output map, known as a virtual modulation curve (VMC), with boundary conditions, was introduced as a novel adaptive component between the operator’s control signal and the electrohydraulic system. One possible application was explored involving the application of a neural network emulator that predicted future position and orientation errors, a parabolic minimization function, and an averaging filter, the performance of a consistent operator model was improved significantly while operating under real time constraints. The success of this technique demonstrates that it is applicable to a wide range of human-in-the-loop problems.

(Download PDF)    (Export to EndNotes)