Processor Module Failure Prediction Using Indirect Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for assessing processor module failure rely on direct sensor measurements, which are not available in all processor modules, necessitating alternative methods for predicting and evaluating potential failures.
Innovation Solution
A method that receives component and operational histories, along with indirect sensor measurements, to generate a part survival model, determining the survival probability of processor modules based on historical data, enabling failure prediction without direct temperature monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct sensor measurements are used to assess processor module failure, then measurement precision is improved, but device complexity increases and not all modules can be monitored
Solution Approach 1:
The patent uses host vehicle environmental sensors as intermediaries to indirectly measure processor module conditions. Instead of placing sensors directly on the processor module, the system uses existing sensors that measure host vehicle temperature, humidity, and other environmental factors, then correlates this data with processor module failure risks through a part survival model.
Solution Approach 2:
The system creates a virtual model of the processor module's operational state by copying and analyzing host vehicle environmental data. The part survival model replicates the relationship between environmental conditions and component failure, allowing failure prediction without physical sensors on the processor module itself.
2Reliability
If direct temperature sensors are installed on processor modules, then reliability monitoring is improved, but manufacturing cost and device complexity increase
Solution Approach 1:
The system makes existing host vehicle sensors serve multiple functions - they continue to monitor environmental conditions for vehicle operation while simultaneously providing data for processor module failure prediction. This eliminates the need for dedicated sensors on each processor module.
Solution Approach 2:
The host vehicle's existing sensor system serves itself by providing data for both vehicle operation monitoring and component failure prediction, eliminating the need for additional dedicated monitoring infrastructure.
3Measurement precision
If comprehensive sensor data is collected for failure prediction, then measurement precision is improved, but loss of information increases due to data management complexity
Solution Approach 1:
The system extracts only the specific environmental parameters relevant to processor module failure from the host vehicle sensor data, such as temperature and humidity, rather than processing all available sensor information. This focuses computational resources on the most predictive variables.
Solution Approach 2:
The part survival model transforms raw sensor measurements into meaningful failure probability predictions by applying statistical transformations and correlations. The model converts environmental parameter variations into risk assessments that directly indicate component health status.
Data Source
AI summary
A method includes receiving a component history for a processor module, the component history including identities of host vehicles in a set of host vehicles in which the processor module was installed; receiving an operational history for the set of host vehicles for a time period the processor module was installed on the set of host vehicles; receiving indirect sensor measurements related to the set of host vehicles for the time period; receiving a part survival model that is based at least in part on a part status of a plurality of historical processor modules, the plurality of historical processor modules having a historical component history, a historical operational history, and historical indirect sensor measurements; and determining a survival probability of the processor module based at least in part on the component history, the operational history, the indirect sensor measurements, and the part survival model.