Vehicle System Comparison for Accurate Maintenance Candidate Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current algorithms, particularly artificial intelligence algorithms, require significant memory and processing resources and often fail to consider various variables affecting vehicle systems, leading to incorrect maintenance or repair scheduling, resulting in potential damage due to missed or unnecessary maintenance.
Innovation Solution
A control system that identifies common characteristics among vehicle systems to obtain and compare data, using a monitoring controller with processors to determine anomalies and schedule maintenance based on shared characteristics, such as location or environmental conditions, thereby reducing the impact of external variables on diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If algorithms including artificial intelligence algorithms are used to analyze vehicle system data, then maintenance scheduling capability is improved, but memory space and processing resources are significantly consumed
Solution Approach 1:
The patent segments the fleet into multiple groups based on common characteristics (geographic location, vehicle type, operating conditions). Each group is analyzed separately using simplified comparison algorithms rather than applying complex AI to the entire fleet, reducing overall computational resource requirements while maintaining maintenance scheduling capability.
Solution Approach 2:
The patent changes the approach from using complex AI algorithms to using simpler comparison-based methods that evaluate vehicle systems against group averages. This parameter change in the analytical method significantly reduces memory space and processing resources while preserving the ability to identify maintenance needs.
2Extent of automation
If algorithms are used to determine maintenance scheduling, then automated decision making is improved, but accuracy is reduced due to failure to consider all variables such as weather, humidity, precipitation, terrain, vehicle system age, and wear
Solution Approach 1:
The patent applies local quality by creating geographically-specific and condition-specific analysis groups. Each group shares common environmental and operational characteristics, allowing the automated system to make accurate decisions tailored to local conditions rather than applying a single generic algorithm to all vehicles.
Solution Approach 2:
The patent implements dynamic grouping where vehicle systems are continuously sorted into different groups based on changing conditions such as geographic location, weather, and operating parameters. This dynamic approach allows the automated decision-making system to adapt to varying conditions, improving accuracy while maintaining automation.
3Quantity of substance
If vehicle system data from diverse environments is analyzed together, then data volume is increased, but diagnostic accuracy is reduced due to external factors affecting comparison
Solution Approach 1:
The patent segments the diverse vehicle system data into multiple homogeneous groups based on common characteristics. By analyzing data within each segment separately rather than mixing all data together, the system maintains diagnostic accuracy while still utilizing large volumes of data across different groups.
Solution Approach 2:
The patent applies homogeneity by ensuring that each analysis group contains vehicle systems with similar characteristics (same geographic region, similar operating conditions, comparable vehicle types). This homogenization within groups allows for accurate comparative analysis while the overall system still processes large volumes of data across multiple groups.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system 200 is provided that includes a controller 201 having one or more processors 202. The one or more processors may be configured to obtain first vehicle system data from a first vehicle system of plural vehicle systems 100 based on a common characteristic shared by the plural vehicle systems, and obtain second vehicle system data from a second vehicle system of the plural vehicle systems, the second vehicle system data based on the common characteristic shared by the two or more vehicle systems. The one or more processors may also be configured to compare the first vehicle system data to the second vehicle system data 408, and identify one of the first vehicle system or the second vehicle system as a candidate vehicle system for maintenance based on comparing the first vehicle system data to the second vehicle system data 410.