Optical Fiber Rotation Alignment Using Brightness Profile Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fusion splicing systems require extensive time for determining the rotation angle of optical fibers, as they need to image data multiple times while adjusting the rotation angle, leading to inefficiencies in the rotation alignment process.
Innovation Solution
A fusion splicing system that includes a brightness profile extracting unit, features extracting unit, prediction model creation unit, and determination unit, which uses machine learning to determine the rotation angle of optical fibers based on brightness profile data, allowing for accurate alignment and splicing with reduced imaging and processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional imaging methods are used to determine rotation angle by repeatedly imaging while adjusting rotation angle, then measurement precision of rotation angle is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary action by extracting brightness profile data and creating a prediction model in advance. The determination unit uses this pre-established model to directly determine the rotation angle from a single image without requiring repeated imaging and adjustment, thereby significantly reducing the time required for rotation angle determination while maintaining high measurement precision
Solution Approach 2:
The invention replaces the mechanical trial-and-error adjustment method with an information processing approach. Instead of physically adjusting the rotation angle and taking multiple images, the system uses brightness profile extraction and machine learning-based prediction to calculate the rotation angle directly from image data, substituting mechanical operations with computational methods
2Measurement precision
If repeated imaging is performed to determine rotation angle, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The system creates a prediction model in advance that can directly determine rotation angle from brightness profile data. This preliminary preparation enables single-image determination without repeated imaging, thereby improving measurement precision while simultaneously increasing fusion splicing productivity by eliminating time-consuming iterative imaging processes
Solution Approach 2:
The invention replaces the low-productivity mechanical process of repeated imaging and manual adjustment with an automated information processing system. The determination unit uses brightness profile extraction and machine learning algorithms to calculate rotation angle directly, substituting iterative mechanical operations with efficient computational methods that enhance both precision and productivity
Data Source
AI summary
Brightness profile data having a number of dimensions is extracted based on image data in a radial direction of an optical fiber, the brightness profile data representing features for each rotation angle of the optical fiber. Machine learning uses training data to create a prediction model that based on the brightness profile data determines a rotation angle of each pair of optical fibers is. The pair of optical fibers are rotated to the determined rotation angle and then fusion spliced. The training data indicates a correspondence relationship between the rotation angle of the optical fiber and brightness profile in the radial direction for each rotation angle of the optical fiber. The prediction model can determine a rotation angle of an arbitrary optical fiber based on brightness profile data of the arbitrary optical fiber.