Multi-Sensor Assembly Error Detection via Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting functional errors in multi-sensor arrangements of vehicle assistance systems are not sufficiently reliable and accurate, as they often rely solely on individual sensor states without considering expected measurement results, leading to incomplete error detection and potential system performance degradation.
Innovation Solution
The method incorporates data fusion from multiple sensors, such as camera and radar systems, to detect errors by comparing measurement results and calculating performance variables like differential space vectors and time ratios, allowing for more accurate identification of sensor malfunctions through standardized data representation and statistical analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data fusion from multiple sensors is implemented to improve error detection accuracy, then measurement precision and reliability improve, but device complexity increases
Solution Approach 1:
The error detection process is segmented into distinct phases: data acquisition from individual sensors, data fusion processing, performance variable calculation, and error determination. This segmentation allows each module to be optimized independently while maintaining overall system accuracy.
Solution Approach 2:
The data fusion system serves multiple functions simultaneously: it performs standardized detection of the vehicle environment, calculates performance variables for error detection, and provides continuous monitoring of sensor functionality. This multi-functionality reduces the need for separate dedicated systems.
2Reliability
If statistical analysis and performance variable calculation are performed continuously to improve error detection reliability, then detection reliability improves, but loss of time increases
Solution Approach 1:
Performance variables are calculated and compared at defined time intervals rather than continuously. This periodic approach maintains detection reliability by regularly monitoring sensor performance while reducing computational load and processing time between intervals.
Solution Approach 2:
Expected performance variables are pre-calculated and stored for comparison with actual measurements. This preliminary preparation eliminates the need for complex real-time calculations during operation, reducing processing time while maintaining detection accuracy.
Data Source
Figure 1~2
Figure 3~4
AI summary
The method involves determining actual power parameter of a multi-sensor assembly (10) based on information from data fusion of data received from sensors e.g. radar sensor (14) and camera sensor (16), of the sensor assembly. The data fusion is executed for detecting actual vehicle surrounding (20). The determined parameter is compared with expected power parameter of the sensor assembly. A determination is made to find whether function error of the sensors is present or not based on result of the comparison of the actual parameter with the expected parameter.