Extrapolated Usage Data Prediction for Electronic Device Health
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic devices face challenges in predicting hardware component failures due to limited usage data, leading to unpredictable and costly remedial processes, especially in environments with multiple devices, where data collection may not cover the necessary historical period for accurate predictions.
Innovation Solution
A system that collects usage data over a short period and extrapolates it to a longer period using a data collector and model generator, which analyzes this data, including historical data from similar devices, to predict the electronic device's state and provide recommendations for preventative actions, such as updating or replacing components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If usage data is collected only over a short period, then data collection time is reduced, but prediction accuracy deteriorates due to insufficient historical data
Solution Approach 1:
The patent creates virtual copies of usage data by extrapolating short-term observed data to generate long-term predicted usage patterns. The model generator produces synthetic historical data that mimics actual device usage behavior, enabling accurate predictions without requiring extensive real-world data collection periods.
Solution Approach 2:
The system performs preliminary data preparation by collecting and analyzing usage patterns during the initial deployment phase. This early data collection and model training establishes a foundation that enables accurate predictions to be made immediately, rather than waiting for long-term data accumulation.
2Measurement precision
If usage data is collected over a long period, then prediction accuracy is improved, but data collection time increases
Solution Approach 1:
Instead of waiting for long-term data to accumulate naturally, the system creates synthetic long-term usage data by extrapolating from short-term observations. This copying approach generates sufficient historical context for accurate predictions without the time penalty of actual long-term data collection.
Solution Approach 2:
The model generator transforms the time parameter by projecting short-term usage patterns into long-term predictions. By changing the temporal scope through mathematical extrapolation rather than physical waiting, the system achieves long-term prediction accuracy without incurring long-term data collection delays.
3Reliability
If hardware component failures are predicted accurately, then device reliability is improved, but system complexity increases due to data collection and analysis infrastructure
Solution Approach 1:
The electronic device performs its own self-diagnosis and health monitoring using the data collection and prediction system. This self-service capability enables the device to autonomously identify potential failures and generate maintenance alerts without requiring complex external monitoring infrastructure, thus improving reliability while managing system complexity.
Solution Approach 2:
The data collection and analysis system serves multiple functions: it collects usage data for performance optimization, generates failure predictions for reliability improvement, and provides maintenance scheduling capabilities. This multi-functionality justifies the added system complexity by delivering multiple benefits from a single integrated infrastructure.
Data Source
AI summary
In an example in accordance with the present disclosure, a system is described. The system includes a data collector to collect usage data for the electronic device over a first period of time. The system also includes a model generator. The model generator extrapolates usage data for the electronic device over a second period of time that is longer than the first period of time and predicts a state of the electronic device based on extrapolated usage data for the electronic device over the second period of time.