Abstract

To supply electric power uninteruptedly during the maintenance task of live power electric line, it is necessary to realize an autonomous control of 6-link electro-hydraulic manipulator for the safe maintenance task. However electro-hydraulic manipulator using hydraulic actuators has many nonlinear elements and its parameter fluctuations are greater than those of an electrically driven manipulator. Therefore it is relatively difficult to realize autonomous assembly tasks particularly in the case of manipulating flexible objects. In this report, a discrete event control system is introduced for the assembly task of electric lines into sleeves as a typical task of live power electric lines. In the implemetation of a discrete event control system, a novel learning vector quantization neural network is proposed and applied to the insertion task. To apply the proposed discrete event control system to the electric lines and sleeves which are not used in the neural network learning, lerning data have been generated by using the fuzzy inference. By the experimental results of 2 types of electric lines and sleeves, the proposed discrete event control algorithm and neural network learning using the generation of learning data by the fuzzy inference are comfirmed very effective to the complex task such as the insertion of electric lines to sleeves.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call