Passenger Conveyor Module Health Assessment Using Cross-Module Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Technicians face difficulties in determining the health condition of modules in passenger conveyor systems, such as elevators, escalators, and moving walkways, during on-site visits, as it is challenging to assess whether other system components are functioning properly.
Innovation Solution
A diagnostic controller receives signals from modules containing operational data, applies machine learning models trained on legacy data to analyze the operational influence of modules on each other, and issues alerts for malfunctions, with sensor data indicating fluctuations outside predetermined thresholds, and allows for retraining based on inspected conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If technicians visit the site to address reported issues, then they can directly inspect the system, but it is difficult to determine whether other aspects of the system are working properly
Solution Approach 1:
A diagnostic controller is introduced as an intermediary device that receives signals from multiple modules, processes operational data, and generates health condition assessments. This mediator consolidates information from various system components, enabling comprehensive monitoring without requiring technicians to manually inspect each aspect of the complex system.
Solution Approach 2:
The system performs self-diagnosis by automatically collecting operational data from modules, analyzing health conditions, and generating alerts for potential malfunctions. This self-service capability allows the system to monitor its own status continuously, providing comprehensive detection without requiring constant technician intervention.
2Reliability
If the system continuously monitors all modules, then malfunction detection is improved, but data processing complexity and energy consumption increase
Solution Approach 1:
The diagnostic controller monitors all modules continuously but only processes and analyzes data when anomalies are detected or at scheduled intervals. This partial processing approach maintains high reliability for malfunction detection while reducing unnecessary energy consumption from continuous full-system data analysis.
Solution Approach 2:
The system implements periodic health condition assessments where the diagnostic controller evaluates module status at regular intervals rather than continuously processing all data streams. This periodic action maintains reliable detection capability while significantly reducing energy consumption compared to continuous monitoring and analysis.
3Productivity
If machine learning models are used to analyze operational data, then predictive maintenance is enhanced, but computational requirements and system complexity increase
Solution Approach 1:
The machine learning analysis is segmented into modular components where the diagnostic controller executes specific algorithms for different types of operational data. This segmentation allows the system to implement predictive maintenance capabilities while managing computational complexity through divided, specialized processing tasks rather than monolithic complex analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A passenger conveyor system having: a passenger conveyor disposed in a building; one or more modules, including a first module, operationally coupled to the passenger conveyor; a diagnostic controller configured to receive a first signal from the first module containing first data indicative of an operational condition of the first module, wherein the diagnostic controller is configured to: determine a health condition of each of the one or more modules from the first signal; and issue an alert when the health condition of the one or more modules is indicative of a malfunction.