Elevator Pit Sensor Learning Phase for Detection Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for a cost-effective and reliable detection system in elevator systems to identify service technicians or mechanics in the elevator pit and on the pit ladder, which must have high detection performance with minimal false positives and negatives, and require minimal maintenance, while also ensuring proper installation and verification.
Innovation Solution
A safety net system utilizing sensors, such as 2D LiDAR or RADAR, coupled with a processor that performs a learning phase to generate a background signal, compares it with known physical characteristics, and verifies successful installation, using a machine-learning algorithm to distinguish between hit points, additional points, and false points, thereby ensuring accurate detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a sensor is installed in the elevator pit to detect service technicians, then detection capability is improved, but false positive and false negative determinations increase
Solution Approach 1:
The system performs a learning phase before normal operation to establish a background model of the elevator pit environment. This preliminary action captures the static physical characteristics (walls, ladder, equipment) and separates them from dynamic elements (service technicians), enabling more accurate detection during operational phase and reducing false positives and false negatives
Solution Approach 2:
The system continuously compares current sensor readings against the established background model and provides feedback to the detection algorithm. This feedback mechanism allows the system to distinguish between expected environmental variations and actual service technician presence, improving detection reliability while maintaining precision
2Measurement precision
If a learning phase is implemented to verify sensor installation, then detection accuracy is improved, but installation time and complexity increase
Solution Approach 1:
The sensor system automatically performs the learning phase and background model establishment without requiring manual calibration or configuration by installers. The system self-configures by capturing environmental data and processing it through the detection algorithm, thereby improving detection accuracy while minimizing the time and skill required for installation
3Area of stationary object
If multiple sensors are deployed to cover the entire elevator pit, then detection coverage is improved, but system cost and complexity increase
Solution Approach 1:
The system uses a single sensor that performs multiple functions: capturing the complete elevator pit environment, establishing the background model, and detecting service technicians. The sensor is positioned and configured to maximize its field of view coverage, making one sensor serve the role of multiple sensors would otherwise be needed, thereby maintaining detection coverage while reducing system complexity
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively reduces false negative and false positive determinations, providing confidence in the detection system's operation and ensuring safety by accurately identifying individuals in hazardous locations within the elevator pit and on the pit ladder.
Implementation Method 1
A safety net system utilizing sensors, such as 2D LiDAR or RADAR
Implementation Method 2
A safety net system utilizing sensors, such as 2D LiDAR or RADAR
Data Source
Figure 1
Figure 2
Figure 3~5
AI summary
A method of operating a safety net system of an elevator system is provided. The method includes installing a sensor in an elevator pit of the elevator system and executing a learning phase of the sensor to verify successful installation of the sensor. The executing of the learning phase includes causing the sensor to sense physical characteristics of a portion of the elevator pit when the elevator pit is known to have certain physical characteristics to generate a background reading, comparing the background reading against a reading associated with known physical characteristics of the portion of the elevator pit and verifying the successful installation of the sensor based on results of the comparing.