Elevator Installation Quality Detection Using Simulated ML Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional elevator installation methods are prone to human error during testing and lack sophistication, leading to potential safety vulnerabilities.
Innovation Solution
A method and apparatus utilizing a machine learning model trained with simulation data to evaluate elevator installation quality, incorporating sensors and a digital twin simulation model to assess the operation of elevator entities and generate reports or signals indicating acceptable or unacceptable quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manual testing procedures are used by technicians, then the installation process is simple and easy to operate, but the reliability and accuracy of quality assessment deteriorate due to human error and simple testing methods
Solution Approach 1:
The patent replaces manual mechanical testing procedures with an automated machine learning-based assessment system. Sensors collect operational data from elevator components, and a machine learning model automatically analyzes this data to evaluate installation quality, eliminating human error and simple testing limitations while maintaining operational simplicity through automated processing.
Solution Approach 2:
The system enables self-assessment of installation quality through automated data collection and analysis. The machine learning model independently evaluates the elevator installation by processing sensor data without requiring external expert intervention, thereby improving reliability while keeping the system relatively simple to implement.
2Measurement precision
If sophisticated testing procedures are implemented to improve quality assessment, then the measurement precision improves, but the ease of operation deteriorates due to complex testing procedures
Solution Approach 1:
Complex sophisticated testing procedures are replaced with an automated machine learning system that performs precise measurements and evaluations. The system automatically collects data from sensors, processes it through trained models, and generates quality assessments without requiring operators to perform complex manual testing steps, thereby maintaining high measurement precision while improving ease of operation.
Solution Approach 2:
The machine learning model acts as an intermediary between raw sensor data and quality assessment results. It automatically processes complex data relationships and transformations, providing precise measurements without requiring operators to directly perform complex testing procedures, thus maintaining precision while simplifying operation.
3Measurement precision
If multiple sensors and machine learning models are deployed to improve detection accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The system segments the quality assessment function into distinct components: multiple sensors for data collection, a machine learning model for analysis, and an output interface for results. This segmentation allows each component to be optimized independently while working together to achieve high detection precision, managing overall system complexity through modular architecture.
Solution Approach 2:
The machine learning model serves multiple functions: it processes data from various sensor types, evaluates different aspects of installation quality, and generates comprehensive assessments. This multi-functionality reduces the need for separate specialized systems for each testing aspect, thereby improving measurement precision across multiple parameters while controlling overall device complexity.
Data Source
AI summary
A method for generating data descriptive of a quality of an elevator installation is provided, the method is performed by an apparatus (170) configured to execute a machine learning-model trained with a simulation data, the method comprises: receiving (210) data descriptive of an operation of at least one entity of the installed elevator; inputting (220) the received data to the machine-learning model executed by the apparatus (170); setting (230), in accordance with an output from the machine-learning model, a detection result to express one of the following: (i) the quality of the elevator installation is acceptable (230A), (ii) the quality of the elevator installation is unacceptable (230B). An apparatus (170) and a computer program are also provided.