ニューラルネットワークを用いた工作機械の簡易知能型熱変形制御(機械要素,潤滑,工作,生産管理など)

概要

論文の詳細を見る
As higher precision machining in required, reducing thermal deformation of a machine tool becomes more important. In the previous report, a new method for estimating optimum temperature of cooling oil on a spindle was established. Inverse analysis using neural network was used for calculating optimum oil temperature, because neural network is suitable for controlling non-linear phenomenon. In this paper, a lathe with a simple and intelligence control of thermal deformation using neural network was developed and evaluated for high precision. At first, in the experiment, thermal behavior of a lathe was measured for a few basic study data of the neural network. Next, the neural network was used to lean the relationship between the measured temperatures and the thermal deformation on the lathe. Then the neural network was rewrote for some algebraic equations, and the algebraic equations were carried in the lathe with a PC. At last, thermal deformation was controlled in the NC program by using both the algebraic equations and temperature distribution of the lathe. It is concluded from the results that (1) The proposed method was effective in order to reduce thermal deformation. (2) Necessary device for the proposed method was only measuring device of temperature, and a forced cooling device or a linear scale were not necessary.
2004-10-25