Stator bar sectional dimension detection system based on machine vision

Abstract

The invention discloses a stator bar sectional dimension detection system based on machine vision. The system is used for detecting the length and width of the cross section of a line segment of a stator bar. The system comprises an image collecting transmission module, an image preprocessing module, a calibration module and a measurement module, wherein the image collecting transmission module is used for collecting, converting and transmitting a wide face image and a narrow face image of the stator bar; the image preprocessing module is used for processing a digital image and generating a target sectional dimension model and a standard sectional dimension model; the calibration module is used for performing camera calibration; and the measurement module is used for performing image matching on the target sectional dimension model and the standard sectional dimension model and obtaining an actually measured sectional dimension of a stator bar measured piece through a pixel difference method and error correction. The system can automatically and simultaneously detect the cross section length and the cross section width of each stator bar measured piece and can perform production line type detection on the sectional dimension of stator bar measured pieces of the same model produced in batches, and on-line real-time detection of the sectional dimension of the stator bar is achieved.

Description

technical field [0001] The invention belongs to the field of detecting the geometric dimensions of stator wire rods, and relates to a detection system for the cross-sectional size of stator wire rods, in particular to a detection system for the cross-sectional size of stator wire rods based on machine vision. Background technique [0002] With the continuous improvement of the design and manufacturing technology of large generator stator bars, the detection technical requirements for large generator stator bars are also increasing. Most of the traditional stator bar cross-sectional size inspections are done manually. The inspectors use low-efficiency tools such as digital calipers to detect the cross-sectional size of the stator bar, read visually, and manually record and process the test results. The manual detection method is slow in detection speed and low in efficiency. It is difficult to keep up with the production speed of stator wire rods, which affects the production...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the disadvantages of low efficiency, high labor cost and poor accuracy of the above-mentioned manual detection method of the cross-sectional size of the traditional stator wire rod, the present invention provides a detection system for the cross-sectional size of the stator wire rod based on machine vision

Images