Predictive Maintenance Algorithm for Commercial Vehicle Fleets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicular maintenance methods lack a dynamic and manageable system to predict and prevent vehicle component failures across a fleet of vehicles, relying on manufacturer schedules and operator-reported issues, with a need for a more proactive approach using telematics data.
Innovation Solution
A computer-based method and system that aggregates maintenance data from driver vehicle inspection reports, telematics data, and manufacturer-recommended service schedules, applying this data to a predictive maintenance algorithm to forecast component failures and schedule preventative maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manufacturer schedules and operator-reported maintenance methods are used, then the maintenance system is simple to implement, but the ability to predict and prevent vehicle component failures is insufficient
Solution Approach 1:
The patent combines multiple data sources including manufacturer service schedules, operator inspection reports, and telematics sensor data into a unified predictive maintenance system. This integration allows the system to leverage diverse information streams to improve failure prediction accuracy while managing complexity through centralized data aggregation and processing algorithms.
Solution Approach 2:
The patent introduces a computer-based predictive maintenance system that acts as an intermediary between traditional maintenance methods and actual vehicle maintenance decisions. This system processes and analyzes data from multiple sources, providing synthesized failure predictions and maintenance recommendations that bridge the gap between simple scheduling and complex real-time monitoring.
2Measurement precision
If telematics data is collected and analyzed from all vehicles, then the precision of failure prediction improves, but the quantity of data to be processed increases significantly
Solution Approach 1:
The patent extracts and prioritizes critical failure prediction indicators from the comprehensive telematics data stream. By identifying and focusing on the most relevant sensors and data points that directly correlate with component failures, the system achieves high prediction precision without requiring processing of all available data, thus managing data volume effectively.
Solution Approach 2:
The patent segments the large volume of telematics data into component-specific data sets, allowing for targeted analysis of each vehicle component's health indicators. This segmentation enables the system to process data more efficiently by focusing computational resources on relevant component monitoring rather than analyzing all data from all vehicles uniformly.
3Loss of time
If maintenance is performed based on operator signals or manufacturer schedules, then the ease of operation is maintained, but the loss of time for preventive action increases
Solution Approach 1:
The patent implements preliminary action by predicting component failures before they occur, allowing maintenance to be scheduled in advance. The system analyzes current vehicle data and projected failure timelines to recommend optimal maintenance timing, enabling fleet managers to perform preventive maintenance proactively rather than reactively, thus reducing downtime while maintaining operational simplicity through automated recommendations.
Data Source
AI summary
A computer-based method for predicting vehicle component failures from a fleet of vehicles and taking corrective action. The method includes receiving maintenance data regarding a vehicle component, receiving from a vehicle's telemetry device, sensor data for the vehicle component. obtaining manufacturer's recommended service data for the vehicle component, the maintenance data, the sensor data, and the manufacturer's recommended service data collectively forming vehicle component data, comparing the stored vehicle component data to a statistical behavioral model for the vehicle component to produce vehicle component comparative data, and applying the vehicle component comparative data to a predictive maintenance algorithm for the vehicle component to predict a date of failure of the vehicle component.