Perovskite cell laser scribing trajectory tracking method and system

By collecting and optimizing the laser speckle images of perovskite batteries, using the improved YOLOv8 model to detect and generate trajectories, the problem of laser marking deviation path is solved, high-precision trajectory tracking is achieved, and battery performance and yield rate are improved.

CN120472283APending Publication Date: 2025-08-12LECHENG INTELLIGENT TECH (SUZHOU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510352147.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-25
Publication Date
2025-08-12

AI Technical Summary

Technical Problem

During the manufacturing process of perovskite batteries, the laser scribing equipment deviates from the planned path, resulting in deviations in the size and shape of the battery cell, affecting performance and yield, and it is difficult to obtain the actual path of the laser scribing to determine whether modification is needed.

Method used

By collecting laser speckle images, using the improved YOLOv8 model for training and detection, the laser speckle position information is obtained, and the trajectory is generated and optimized to achieve high-precision tracking of laser scribe trajectory.

Benefits of technology

Ensure that the laser marks the precise path, reduces deviations, improves product yield, reduces production costs, and provides a basis for subsequent path planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120472283A_ABST
    Figure CN120472283A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a perovskite cell laser scribing trajectory tracking method and system, and the method comprises the steps: S1, collecting a laser speckle image of a perovskite cell during laser scribing, and making a data set; s2, training an improved YOLOv8 model by using the data set to obtain a detection model; s3, the detection model is used for detecting the laser speckles, and position information of the laser speckles is obtained; s4, generating a first track according to the position information; and S5, the first track is optimized, a second track is generated, and the second track is the laser scribing track of the perovskite cell. According to the method, the laser scribing track can be tracked, the actual track of laser scribing is obtained and compared with the planned path, and a basis is provided for further research of subsequent laser scribing path planning.
Need to check novelty before this filing date? Find Prior Art