Based on analyzing the recent research status and future developments of error compensation techniques for CMM in the world , non-rigid errors of CMM are analyzed by means of the stress distortion analysis for components of CMM bridge-type CMM, and a new idea for die error compensation of high precision CMM is provided.A new genetic neural network is to conduc the non-rigid modeling , which is first put forward , in accordance with some drawbacks of the current software compensation , which include low accuracy and trouble some expressions . And the current difficult questions , which include local minimum problem and the selection of the number of neural network hidden units , are done .Finally type ZOO CMM made in China is taken for example to conduct the non-rigid modeling , so that it has been experimentally verified that the new genetic neural network have faster convergence rate and more accuracy than the current BP neural network. |