Tire Wear Prognostics via Histogram Data Compression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for tire wear prognostics are costly due to the need for elaborate models and sensors, and streaming data to a cloud server requires excessive data transfer, which is inefficient.
Innovation Solution
A system that uses a cloud-based approach to predict tire wear by compiling physical tire wear data into histograms, which are then analyzed using machine learning to identify coefficients that translate histogram data into measures of tire wear, minimizing data requirements and on-board processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If elaborate models and sensors are used for tire wear prognostics, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts only the essential wear-related features from raw sensor data by compiling them into histograms. Instead of using all raw sensor data or complex models, the system identifies and extracts key wear indicators (such as vibration characteristics, temperature patterns, and load distribution) and represents them in a compressed histogram format. This extraction process maintains measurement precision while dramatically reducing data complexity and processing requirements.
2Measurement precision
If all wear data is streamed to cloud server, then measurement precision is improved, but data transfer volume increases
Solution Approach 1:
The system extracts only the essential wear information from raw sensor data by compiling it into histograms with fixed bins representing different wear characteristics. This extraction transforms potentially terabytes of raw sensor data into compact histogram representations containing only the essential wear indicators, reducing data transfer volume by orders of magnitude while preserving prediction accuracy.
Solution Approach 2:
Instead of transmitting raw sensor data, the system creates a simplified copy in the form of histograms that capture the essential wear characteristics. These histogram copies contain aggregated statistical information (counts of events in different wear-related bins) that preserve the necessary predictive information while occupying minimal space for transmission and storage.
3Quantity of substance
If histogram data is compiled and processed, then data transfer is reduced, but processing time may increase
Solution Approach 1:
The system performs preliminary processing by compiling raw sensor data into histograms locally on the vehicle or at edge devices before transmission. This preliminary action of aggregating data into histogram bins occurs in real-time as data is collected, so that when data is sent to the cloud, it is already in the processed histogram format. This eliminates the need for time-consuming data aggregation at the cloud server and reduces overall processing time.
Solution Approach 2:
The system changes the parameter representation from continuous raw sensor values to discrete histogram bin counts. This parameter transformation converts complex continuous data into simplified discrete categories, making the data much faster to process and analyze. The histogram bins group similar wear conditions together, allowing for rapid comparison and prediction without processing individual data points.
Data Source
AI summary
A storage maintains coefficients that map histogram data elements to tire wear, the coefficients being trained based on a correlation of histogram data to measured tire wear. A processor is programmed to receive a wear data histogram from a vehicle, utilize the coefficients to translate the wear data histogram into a measure of physical tire wear; and send an alert message indicating the estimated tire wear.