»ùÓÚÈ˹¤Éñ¾­ÍøÂçµÄË«¼¶²âÁ¿ÏµÍ³¶¨Î»Îó²î²¹³¥

ÎÌ´¨

£¨¹ã¶«¹¤Òµ´óѧ ¾«Ãܵç×ÓÖÆÔì¼¼ÊõÓë×°±¸¹ú¼ÒÖصãʵÑéÊÒ£¬¹ã¶« ¹ãÖÝ 510006£©

ÕªÒª£ºÎª½â¾ö·Ç½Ó´¥Ê½¸ß¾«¶È´«¸ÐÆ÷Á¿³ÌºÍ¾«¶ÈÄÑÒÔ¼æÈݵÄÎÊÌ⣬ʵÏÖ´óÁ¿³Ì×ÔÓÉÇúÃæµÄ¸ß¾«¶ÈɨÃè²âÁ¿£¬ÔÚ¶Ô¹úÄÚÍâ²âÁ¿ÒÇÆ÷½øÐÐÑо¿·ÖÎöºó£¬Ìá³öÒ»ÖÖͨ¹ýÈáÐÔ½ÂÁ´´ø¶¯¸ß¾«¶È´«¸ÐÆ÷¸úËæÇúÃæʵÏÖ´«¸ÐÆ÷Á¿³ÌÀ©Õ¹µÄË«¼¶²âÁ¿ÏµÍ³¡£Îª½øÒ»²½Ìá¸ß¸ÃϵͳµÄ²âÁ¿¾«¶È£¬²ÉÓü¤¹â¸ÉÉæÒǶԲâÁ¿ÏµÍ³µÄ¶¨Î»Îó²î½øÐб궨£¬ÀûÓÃÈ˹¤Éñ¾­ÍøÂ罨Á¢Ë«¼¶²âÁ¿ÏµÍ³µÄ¶¨Î»Îó²îÄ£ÐÍ£¬È»ºóÀûÓøÃÄ£ÐͽøÐж¨Î»Îó²î²¹³¥£¬ÒÔÇ󾡿ÉÄܵØÏû³ý²âÁ¿ÏµÍ³µÄϵͳÎó²î£¬ËæºóʹÓü¤¹â¸ÉÉæÒÇÔٴζԶ¨Î»Îó²î½øÐвâÁ¿£¬²âÁ¿½á¹ûºÍ×÷Ϊ´«Í³¶¨Î»Îó²î²¹³¥·½·¨µÄ²¹³¥±í²¹³¥·¨½øÐжԱȣ¬×îÖÕ·¢ÏÖ¶¨Î»¾«¶È´ó´óÌá¸ß£¬Ö¤Ã÷ÁË»ùÓÚÈ˹¤Éñ¾­ÍøÂçµÄ¶¨Î»Îó²îµÄÓÅÔ½ÐÔ¡£

¹Ø¼ü´Ê£ºÈ˹¤Éñ¾­ÍøÂ磻ɨÃè²âÁ¿£»¶¨Î»¾«¶È

ÖÐͼ·ÖÀàºÅ£ºTP212 ÎÄÏ×±êÖ¾Â룺A doi£º10.3969/j.issn.1006-0316.2022.07.012

ÎÄÕ±àºÅ£º1006-0316 (2022) 07-0075-06

Positioning Accuracy Compensation of a Secondary Measurement System Based on Artificial Neural Network

WENG Chuan

( State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangdong University of Technology, Guangzhou 510006, China )

Abstract£ºIn order to solve the problem that the range and precision of the non-contact high-precision sensor are difficult to be compatible and realize the high-precision scanning measurement of the large range free-form surface, after the research and analysis of measuring instruments at home and abroad, a dual-level measurement system is proposed to expand the sensor range by driving the high-precision sensor to follow the surface through the flexible hinge. In order to further improve the measurement accuracy of the system, the laser interferometer is used to calibrate the positioning error of the measurement system. And the artificial neural network is used to establish the positioning error model of the secondary measurement system, and then the model is used to compensate the positioning error so as to eliminate the system error of the measurement system as much as possible. And then the laser interferometer is used to measure the positioning error again. At the same time, it is compared with the compensation table compensation method which is considered as the traditional compensation method of positioning error. As the result, it is found that the positioning accuracy is greatly improved, which proves the superiority of the positioning error compensation based on artificial neural network.

Key words£ºartificial neural network£»scanning measurement£»positioning accuracy

———————————————

ÊÕ¸åÈÕÆÚ£º2021-12-06

×÷Õß¼ò½é£ºÎÌ´¨£¨1996£­£©£¬ÄУ¬¹ã¶«ÉÇÍ·ÈË£¬Ë¶Ê¿£¬Ö÷ÒªÑо¿·½ÏòΪ¸ß¾«ÃܲâÁ¿£¬E-mail£º644827901@qq.com¡£