Waterfall Data Segmentation for Valid Vibration Monitoring Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vibration sensor systems like DAS do not account for sensing points that are not placed along the monitored object, leading to inaccurate data measurement.
Innovation Solution
A classifying apparatus that performs semantic segmentation on waterfall data to distinguish between monitoring and non-monitoring points in a vibration sensor, using a machine learning-based model to classify sensing points into normal and abnormal classes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If semantic segmentation is performed on waterfall data to classify sensing points, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the waterfall data into distinct regions corresponding to monitoring points and non-monitoring points. The semantic segmentation process segments the time-frequency-space data to identify and separate valid sensing point locations from invalid ones, enabling precise classification while processing the data in a structured manner.
Solution Approach 2:
The patent introduces an intermediary classification layer that acts as a mediator between the raw waterfall data and the final vibration analysis. The semantic segmentation model serves as an intermediary that processes and filters the data, identifying monitoring points before the main analysis, thus improving measurement precision without requiring the entire system to be overly complex.
2Productivity
If all sensing points are used for vibration monitoring, then productivity is improved, but measurement precision deteriorates due to inclusion of non-monitoring points
Solution Approach 1:
The patent applies local quality by recognizing that different sensing points have different qualities or validity. Instead of treating all sensing points uniformly, the semantic segmentation identifies which specific locations along the vibration sensor correspond to actual monitoring points on the target object. This allows the system to apply different processing or weighting to different local regions, ensuring high measurement precision from valid points while excluding invalid ones.
Data Source
AI summary
A classifying apparatus performs: acquiring a waterfall data that indicates amplitude of vibration for each point in time and for each sensing point in a vibration sensor that is placed along a target object; performing semantic segmentation on the waterfall data to generate a class data that indicates a normal class or an abnormal class for each element of the waterfall data; and classifying the sensing points into a monitoring point and a non-monitoring point. The normal class is assigned to the element whose sensing point is predicted to be the monitoring point. The abnormal class is assigned to the element whose sensing point is predicted to be the non-monitoring point. The monitoring point is the sensing point that is placed along the target object. The non-monitoring point is the sensing point that is not placed along the target object.