# Health Status Assessment of Passenger Ropeway Bearings Based on Multi-Parameter Acoustic Emission Analysis

## TL;DR

This study uses acoustic emission analysis and a new AI model to monitor and predict bearing health in passenger ropeways, improving maintenance and safety.

## Contribution

Introduces a novel LLM-based model for automated bearing wear detection using acoustic emission data in low-speed systems.

## Key findings

- Resonant AE sensors detect bearing defects more effectively than broadband sensors.
- RMS values show periodic peaks and elevated means in defective bearings.
- The Paligemma LLM model accurately identifies wear features from AE data.

## Abstract

The health status of passenger ropeway bearings is studied using multi-parameter AE analysis.

Resonant AE sensors outperform broadband sensors in defect detection.

The laboratory research results have been successfully applied to field testing of passenger ropeway rolling bearings for two years.

A novel LLM-based approach achieves automated bearing wear detection.

What are the main findings?

Defective bearings exhibit periodic RMS peaks and elevated mean values.

Field tests confirm AE’s effectiveness in detecting early-stage bearing damage.

The pre-trained Paligemma LLM model demonstrates superior accuracy in wear feature identification.

What is the implication of the main finding?

Offers a practical solution for preventive maintenance in passenger ropeway systems.

Demonstrates the successful transition from laboratory research to practical field applications.

This study presents a comprehensive investigation of acoustic emission (AE) characteristics for condition monitoring of rolling bearings in passenger ropeway systems. Through controlled laboratory experiments and field validation across multiple operational ropeways, we establish an optimized AE-based diagnostic framework. Key findings demonstrate that resonant VS150-RIC sensors outperform broadband sensors in defect detection, showing greater energy response at characteristic frequencies for inner race defects. The RMS parameter emerges as a robust diagnostic indicator, with defective bearings exhibiting periodic peaks and higher mean RMS values. Field tests reveal progressive RMS escalation preceding visible damage, enabling predictive maintenance. Furthermore, we develop a novel Paligemma LLM model for automated wear detection using AE time-domain images. The research validates the AE technology’s superiority over conventional vibration methods for low-speed bearing monitoring, providing a scientifically grounded approach for safety-critical ropeway maintenance.