Abstract: In order to solve the key technical problems of straightness perception of scraper conveyor in coal intelligent mining process, based on the research of curvature sensing principle of fiber grating, a three-dimensional curvature sensor of fiber grating is designed and developed. Then, based on the discrete point curvature information obtained by the three-dimensional curvature sensor of fiber grating, the 3D algorithm is derived by using the method of fitting recursion, and the 3D bending shape fitting perception and reconstruction of the scraper conveyor are realized. By setting up a test platform for three-dimensional bending of the scraper conveyor, the measuring effect of perceived and actual shape in the three-dimensional straight state and three-dimensional bending state of the scraper conveyor is verified. The test results show that the measured curve is basically the same as the perceptual curve in the three-dimensional bending configuration of the scraper conveyor, and the error of the direction of each coordinate axis is not more than ±15 mm, which can meet the requirements of the accuracy of detecting the straightness of the intelligent work.