Engine Sensor Useful Life Prediction From Event Measurement Deviation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in predicting the remaining useful life of sensors in internal combustion engine aftertreatment systems, leading to inaccurate measurements and potential component malfunctions due to sensor degradation or failure, which can result in costly maintenance and emissions compliance issues.
Innovation Solution
A server-based system that receives and analyzes data from sensors during specific engine events, using data analytics and machine learning models to determine measurement deviations and predict the remaining useful life of sensors without relying on population data, thereby enabling early maintenance and reducing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is monitored continuously to predict remaining useful life, then measurement precision and reliability are improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent segments the sensor monitoring process into distinct phases: data collection during specific engine events, offline data processing to calculate measurement deviations, and predictive analytics to determine remaining useful life. This segmentation allows complex analysis to be performed in manageable stages without requiring continuous real-time processing, thereby maintaining measurement precision while reducing instantaneous system complexity.
Solution Approach 2:
The system performs preliminary actions by collecting and storing sensor data during specific engine events before actual failure occurs. Measurement deviations are calculated in advance by comparing successive measurements, and predictive models are prepared offline. This preliminary action enables early warning of sensor degradation without requiring complex real-time analysis during critical operations.
2Reliability
If sensor degradation is detected early through measurement deviation analysis, then maintenance timing is optimized, but loss of time for data processing and analysis increases
Solution Approach 1:
The patent implements periodic action by analyzing sensor measurements at specific intervals during defined engine events. Instead of continuous analysis, the system periodically compares measurements taken during recurring engine operations, calculating measurement deviations only when new data becomes available. This periodic approach maintains reliable detection of sensor degradation while minimizing the time spent on data processing by focusing analysis only on relevant periodic data points.
3Productivity
If population data is used to predict sensor life, then productivity is improved through faster predictions, but measurement precision decreases due to lack of individual sensor context
Solution Approach 1:
The patent implements feedback by continuously monitoring individual sensor measurements and comparing them against expected performance patterns. The system calculates measurement deviations specific to each sensor and uses this feedback to update predictions of remaining useful life. This feedback mechanism maintains high prediction accuracy for individual sensors while enabling rapid assessment by leveraging real-time sensor-specific data rather than relying solely on generic population statistics.
Data Source
AI summary
At least one server comprising at least one processor coupled to at least one memory storing instructions. The server can receive a first signal from a first monitored system comprising an internal combustion engine and a first sensor, the first signal associated with a first occurrence of an internal combustion engine event, a second occurrence of the internal combustion engine event, and first measurement data of the first sensor. The server can determine a first measurement from the first measurement data. The server can determine a second measurement from the first measurement data. The server can determine a measurement deviation between the first measurement and the second measurement. The server can compare the measurement deviation to a stored measurement threshold. The server can determine a first exhibited useful life of the first sensor based on the measurement deviation and at least one of the first measurement or the second measurement.