A Brief Review of Acoustic and Vibration Signal-Based Fault Detection for Belt Conveyor Idlers Using Machine Learning Models

Alharbi, Fahad; Luo, Suhuai; Zhang, Hongyu; Shaukat, Kamran; Yang, Guang; Wheeler, Craig; Chen, Zhiyong

doi:10.3390/s23041902

Cited by 34 publications

(12 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the article [16] F. Alharbi et al presents a review of acoustic and vibration signal-based fault detection for belt conveyor idlers using ML models. It also discusses major steps in the approaches, such as data collection, signal processing, feature extraction and selection, and ML model construction.…”

Section: H Shiri Et Al In the Articlementioning

confidence: 99%

Measuring Device Detecting Impact Forces on Impact Rollers

Hrabovský,

Kurač,

Pravda

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper presents laboratory devices on which experimental measurements were carried out to prove the validity of the assumption about the reduction of vibrations transmitted to the conveyor belt structure generated by the impact forces of falling material grains in the places of transfer or on the hoppers of conveyor belts. In order to limit damage to the conveyor belts caused by the impact of the sharp edges of material grains, conveyor belts are supported by impact rollers or impact rubber rods in the places of transfers and on the hoppers of belt conveyors. The flattened ends of the impact rollers are inserted into the grooves of steel brackets installed on the supports of the fixed conveyor idlers of a conventional design. In this paper, a special modification of the fixed conveyor idler is presented, which consists of inserting plastic brackets into the structurally modified roller axle holders of the fixed conveyor idler. Measurements were carried out on the first laboratory device, which showed that the specially modified fixed conveyor idler resulted in a higher damping of up to 15% of the impact forces of the falling weight on the rubberized hoop of the impact roller shell compared to the conventional fixed conveyor idler design. Measurements carried out on the second laboratory device show that the effective vibration velocity values detected at the points where the impact roller axis fits into the fixed roller table holder, i.e. points B and D, are higher than when using plastic brackets, up to 6% for a 108 mm diameter roller, compared to steel impact roller brackets.

show abstract

Section: H Shiri Et Al In the Articlementioning

confidence: 99%

Measuring Device Detecting Impact Forces on Impact Rollers

Hrabovský,

Kurač,

Pravda

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Yao et al [7,8] utilized acoustic signals from marine diesel engines to detect abnormal conditions However, despite the advantages, acoustic signals have been reported to exhibit less efficacy as fault detection sources in comparison to vibrational signals. Although acoustic signals offer relative affordability and flexibility, they necessitate a higher level of sensor maintenance and attachment complexity than vibrational signals [9]. This discrepancy in the maintenance requirements contributes to the complexity of utilizing acoustic signals for fault detection.…”

Section: Acoustic Signal Source-based Fault Detection and Diagnosismentioning

confidence: 99%

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

Je-Gal,

Lee,

Yoon

et al. 2023

JMSE

View full text Add to dashboard Cite

Ensuring operational reliability in machinery requires accurate fault detection. While time-domain vibration pulsation signals are intuitive for pattern recognition and feature extraction, downsampling can reduce analytical complexity, but may result in low-precision data, affecting fault detection performance. To address this, we propose time–frequency feature fusion, combining information from both the time and frequency domains for fault detection. Our approach transforms vibrational pulse data into instantaneous revolutions per minute (RPM) and employs statistical analysis for the time-domain features. For the frequency-domain features, we use the combined method of empirical mode decomposition and independent component analysis (EMD-ICA), along with the Wigner bispectrum method to capture the nonlinear characteristics and phase conjugation. Using a deep neural network (DNN), we classify the anomaly states, demonstrating the effectiveness and versatility of our approach in detecting anomalies and improving diagnostic precision. Compared to using time or frequency features alone, our time–frequency feature fusion model achieves higher accuracy, with 100% accuracy at lower downsampling rates and 96.3% accuracy at a downsampling rate of 100×.

show abstract

“…Belt conveyor, referred to as conveyor belt, is a kind of cargo conveying equipment, mainly driven by friction, for continuous cargo conveying [1]. Many highly automated lines in modern factories use belt conveyors as connectors for different equipment, so they are also a very common cargo conveying equipment in industry [2]. Belt conveyor accessories are more, mainly frame, belt, transmission device and drum.…”

Section: Introductionmentioning

confidence: 99%

Structural optimization and modal analysis of belt conveyor driving drum

2024

jemm

View full text Add to dashboard Cite

In modern industrial production, belt conveyor is essential, its advantage is that it can save a lot of manpower and material resources. Belt conveyor accessories are more, the structure is complex, the complexity of the drum and the technical difficulty is higher. As we all know, the roller plays a great role in the belt conveyor, and its performance also determines the overall performance of the belt conveyor. There are many kinds of rollers on the market today. Because it carries a large number of different angles of force and friction, the loss is relatively large. In this paper, the drum structure is introduced first, and the expansion joint structure is selected as the research object. Then, the friction transmission principle between the drum and the belt is analyzed, and the variation of the envelope Angle and tension is calculated. Finally, the simulation results show that the acceleration of the improved drum is 0.1ms2 less than that before the improvement, indicating that the proposed research is helpful to the optimization of the belt conveyor drum.

show abstract

A Brief Review of Acoustic and Vibration Signal-Based Fault Detection for Belt Conveyor Idlers Using Machine Learning Models

Cited by 34 publications

References 78 publications

Measuring Device Detecting Impact Forces on Impact Rollers

Measuring Device Detecting Impact Forces on Impact Rollers

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

Structural optimization and modal analysis of belt conveyor driving drum

Contact Info

Product

Resources

About