Road Condition Prediction Using Vehicle Driving Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional road maintenance methods are labor-intensive and time-consuming, with low accuracy in detecting and determining road damage, leading to potential overlooks and delayed repairs.
Innovation Solution
A method and apparatus using big data analysis to predict road conditions by collecting driving data from vehicles, comparing it to normal samples, and determining abnormal sections based on occurrence thresholds and weighted evaluation values, with an analysis module to identify the cause of abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual inspection by staff is used to detect road conditions, then detection can be performed, but it is labor and time consuming with low efficiency
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated electronic system that collects driving data from vehicles, processes it through algorithms, and automatically identifies road abnormalities. This substitution eliminates human labor from the detection process while significantly improving efficiency and reducing time consumption.
Solution Approach 2:
The system enables road condition detection to serve itself by using driving data naturally generated during normal vehicle operation. The detection process leverages existing vehicle sensor data without requiring dedicated inspection resources, allowing the system to autonomously identify road problems.
2Measurement precision
If image collection and analysis is used to inspect road sections, then pavement damages can be identified, but it involves significant time consumption and complicated image processing
Solution Approach 1:
The patent extracts only the essential features needed for road condition assessment from driving data, avoiding the need for complete image collection and processing. By focusing on specific abnormality indicators derived from vehicle sensor data, the system achieves accurate damage detection while eliminating complex image processing operations.
Solution Approach 2:
The system replaces complex image processing mechanical operations with computational algorithms that analyze driving data. This substitution simplifies the detection process by using mathematical models and statistical methods instead of labor-intensive image segmentation and analysis.
3Measurement precision
If conventional image recognition methods are used for pavement damage analysis, then damage types can be classified, but determination accuracy is low
Solution Approach 1:
The patent changes the parameters used for damage determination from image-based features to driving data-based parameters such as vibration patterns, speed variations, and vehicle response characteristics. This parameter transformation enables more accurate and faster identification of pavement damage types by leveraging dynamic vehicle-road interaction data.
Data Source
AI summary
The present disclosure provides methods and apparatuses for predicting road conditions based on big data. One exemplary method comprises: collecting driving data associated with a road section; comparing the collected driving data with a normal observation sample to determine whether the driving data is abnormal data, putting the abnormal data and the road section into an abnormality database in response to the driving data being abnormal data, and continuously recording driving data of this road section; determining whether the road section is an abnormal road section according to the number of occurrences of abnormal data associated with the road section; and predicting a reason for the abnormality of the road section determined as the abnormal road section, according to a preset model. The technical solutions provided by the present disclosure can help accurately predict road conditions by analyzing big data, thereby saving manpower and material resources.