Elevator Abnormal Noise Detection Using Dual Microphones
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormal noise detection devices for industrial equipment and infrastructure facilities, such as elevators, often erroneously detect abnormalities due to ambient noise, leading to unnecessary suspension times as they struggle to differentiate between actual and ambient disturbances.
Innovation Solution
The implementation of a system that includes both a moving body microphone to collect operating noise and a fixed microphone to collect ambient noise, with machine learning models to determine the abnormality degree of both, integrating detection results with position information to differentiate between true abnormalities and ambient noise-induced errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a microphone is used to detect operating noise for abnormality detection, then abnormality detection capability is improved, but erroneous detection due to ambient noise increases
Solution Approach 1:
The detection system is segmented into two independent components: a moving body microphone for capturing operating noise and a fixed microphone for capturing ambient noise. Each microphone focuses on a specific noise source, allowing the system to separately analyze and compare operating noise characteristics against ambient noise levels, thereby improving detection accuracy while reducing false positives
Solution Approach 2:
The fixed microphone acts as an intermediary that captures ambient noise characteristics. By introducing this intermediate measurement point, the system can differentiate between actual abnormal operating noises and ambient disturbances, using the ambient noise data as a reference to filter out false detections
2Reliability
If abnormal noise detection is performed continuously, then safety monitoring is improved, but unnecessary suspension time increases due to erroneous detection
Solution Approach 1:
The system implements feedback by continuously comparing operating noise characteristics against ambient noise levels and historical data. The abnormality determination unit uses this feedback mechanism to validate detected anomalies, only triggering suspension when the abnormal noise pattern is confirmed to be distinct from ambient disturbances, thereby reducing unnecessary suspensions while maintaining safety
Solution Approach 2:
Instead of immediately suspending upon detecting any abnormal noise, the system applies partial action by first validating the detection through comparison with ambient noise data and historical patterns. This staged approach allows the system to investigate potential abnormalities without immediately halting operations, reducing unnecessary suspension time while maintaining safety through continued monitoring
3Device complexity
If only a moving body microphone is used for noise collection, then device complexity is reduced, but ability to differentiate ambient noise from abnormal noise deteriorates
Solution Approach 1:
The noise collection system is segmented into two specialized microphones: a moving body microphone that travels with the equipment to capture operating noise, and a fixed microphone that remains stationary to capture ambient noise. This segmentation allows each microphone to optimize for its specific function, improving noise source differentiation accuracy without requiring a single complex microphone system
Solution Approach 2:
The system adds a spatial dimension to noise detection by placing microphones in different locations - one attached to the moving body and another fixed in the environment. This dimensional separation creates distinct measurement perspectives, enabling the system to differentiate between noise originating from the moving body versus ambient environmental noise
Data Source
AI summary
According to one embodiment, an abnormal noise detection device includes a first processing circuit. The first processing circuit is configured to collect an operating noise of a moving body by a first microphone installed in the moving body; detect an abnormal noise in the operating noise; input position information of the moving body; and store history information in which a detection result of detecting the abnormal noise and the position information are associated with each other in a first memory. The first processing circuit is configured to determine presence or absence of abnormality of the moving body by integrating the detection result for each piece of the position information on a basis of the history information.