Smart Lighting Sensor Fault Detection via Spatial Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Smart lighting systems with multiple luminaires and sensors face challenges in detecting sensor failures and errors, which often go unreported or are detected manually with delayed feedback, due to limited data collection over short periods and unsophisticated fault detection methods.
Innovation Solution
A method using three or more sensor units to generate spatial correlation parameters from sensor data, identifying faulty sensors by determining common sensors with correlation parameters below a defined threshold, and reconfiguring the lighting system by associating luminaires with functional sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data is collected over short time periods with limited memory storage, then data collection is simple and cost-effective, but fault detection capability is insufficient
Solution Approach 1:
The system dynamically adjusts the data collection strategy by collecting high-frequency sensor data only when needed for fault detection analysis, while using lower-frequency collection during normal operation. This allows the system to maintain high reliability for fault detection without continuously consuming excessive memory resources.
Solution Approach 2:
The patent transitions from analyzing sensor data in the time domain only to analyzing data in both time and spatial dimensions. By incorporating spatial correlation analysis across multiple sensors and comparing sensor responses across different spatial locations, the system achieves superior fault detection capability without requiring proportionally longer data collection periods.
2Productivity
If manual fault detection methods are used, then system complexity is low, but fault detection is delayed and inefficient
Solution Approach 1:
The system implements continuous automated feedback loops where sensor data is constantly monitored, spatial correlation parameters are calculated in real-time, and fault conditions are automatically detected and reported. This automated feedback mechanism dramatically improves fault detection speed compared to manual methods while managing system complexity through modular architecture.
Solution Approach 2:
The lighting system performs self-diagnosis by automatically analyzing its own sensor data for faults. The system autonomously calculates spatial correlation parameters, compares them against thresholds, and identifies faulty sensors without requiring external manual intervention, thereby improving detection productivity while keeping the system relatively simple.
3Measurement precision
If spatial correlation analysis with three or more sensors is implemented, then fault detection accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent segments the fault detection process into distinct modular steps: data collection from multiple sensors, spatial correlation parameter calculation, threshold comparison, and fault determination. This segmentation allows each module to be optimized independently and simplifies the overall complex data processing task by breaking it into manageable components.
Solution Approach 2:
The system transforms raw sensor data into spatial correlation parameters that capture the relationships between multiple sensors. By changing the parameter representation from individual sensor readings to correlation-based features, the system achieves higher fault detection accuracy while the processing complexity is managed through efficient parameter transformation algorithms.
Data Source
Figure 1
Figure 2A~2C
Figure 3
AI summary
A method for identifying sensor units (3) at fault in a lighting system (1) performed using three or more sensor units (3), each respective one of the sensor units (3) comprising a respective sensor (116) configured to generate sensor data, the method comprising at an external processing apparatus (20) external to the sensor units (3): receiving from each of the sensor units (3) the sensor data; generating correlation parameters from the sensor data for selected pairs of neighbouring sensor units (3); and monitoring the correlation parameters to determine a sensor unit (3) at fault.