Estimation of wear and strain of contact wire using contact force of pantograph

Abstract

The contact force of pantograph is one of the most important indexes in evaluating current-collection performance. Quality of contact wires maintenance will be more improved by use of observed contact force. However, specific methods for applying the contact force have yet to be proposed. This paper discusses possibility of estimation of wear and strain of contact wire using the contact force data. For this purpose, the learning capability of an artificial neural network is used. A complex number version of a back-propagation algorithm is used for a learning weight. As the result of this study, the author verified that estimation of the wear and the strain of contact wire using the contact force is valid.