ROSI: A Robotic System for Harsh Outdoor Industrial Inspection - System Design and Applications

Rocha, Filipe Augusto Santos; García, Gabriel J.; Pereira, Raphael F.S.; Faria, Henrique D.; Silva, Thales H.; Andrade, Rafael; Barbosa, Evelyn S.; Almeida, A. G. B.; Cruz, E. Urbano; Andrade, Wagner Ferreira; Serrantola, Wenderson Gustavo; Moura, Luiz Gustavo Lourenço; Azpúrua, Héctor; Franca, André Stanzani; Pessin, Gustavo; Freitas, Gustavo; Costa, Ramon R.; Lizarralde, Fernando

doi:10.1007/s10846-021-01459-2

Cited by 23 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to a decision tree, a random forest reduces the risk of overfitting using multiple decision trees instead of one [ 68 ]. For example, Rocha et al [ 59 ] developed RF to effectively identify damaged bearings noise in belt conveyor idlers with an accuracy of 95%. Another study [ 50 ] used RF with a trial-and-error approach in extracting features and tuning the hyperparameter of the number of trees.…”

Section: Review Of Fd Methods Based On Shallow Machine Learning and D...mentioning

confidence: 99%

“… Input Types Vibration Methods Acoustic Methods Raw input domain [ 44 ] Statistical features from the time domain or frequency domain [ 45 , 46 , 47 , 48 , 58 ] [ 8 , 50 , 59 ] Statistical features from the time-frequency domain [ 4 , 12 , 23 , 60 ] [ 24 , 41 ] Combination of statistical features from all domains [ 40 ] …”

Section: Data Acquisition Of Belt Conveyor Idlersmentioning

confidence: 99%

“…For analysis, the segmented signal is then divided into training and testing samples to train ML models. Several signal processing and analysis-based methods are successfully used in belt conveyor idlers, which aim to obtain the original features by the signal transformation, such as the wavelet transform (WT) [ 24 , 41 , 61 ], fast Fourier transforms (FFT) [ 8 , 12 , 50 , 59 ], local mean decomposition (LMD) [ 42 ], and envelope analysis [ 12 ], etc.…”

Section: Signal Processing and Feature Extractionmentioning

confidence: 99%

“…The FFT algorithm converts the time domain signal into a frequency spectrum with frequency resolution [ 59 ]. For example, Liu et al [ 1 ] used Fourier transform to analyze the experimental data collected from idlers and obtained the sound frequency band (FB), which can effectively detect the final failures of idlers.…”

Section: Signal Processing and Feature Extractionmentioning

confidence: 99%

See 3 more Smart Citations

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

Alharbi

Luo

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Due to increasing demands for ensuring the safety and reliability of a system, fault detection (FD) has received considerable attention in modern industries to monitor their machines. Bulk materials are transported worldwide using belt conveyors as an essential transport system. The majority of conveyor components are monitored continuously to ensure their reliability, but idlers remain a challenge to monitor due to the large number of idlers (rollers) distributed throughout the working environment. These idlers are prone to external noises or disturbances that cause a failure in the underlying system operations. The research community has begun using machine learning (ML) to detect idler’s defects to assist industries in responding to failures on time. Vibration and acoustic measurements are commonly employed to monitor the condition of idlers. However, there has been no comprehensive review of FD for belt conveyor idlers. This paper presents a recent 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. Additionally, the paper provides an overview of the main components of belt conveyor systems, sources of defects in idlers, and a brief introduction to ML models. Finally, it highlights critical open challenges and provides future research directions.

show abstract

Section: Review Of Fd Methods Based On Shallow Machine Learning and D...mentioning

confidence: 99%

Section: Data Acquisition Of Belt Conveyor Idlersmentioning

confidence: 99%

Section: Signal Processing and Feature Extractionmentioning

confidence: 99%

Section: Signal Processing and Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

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

Alharbi

Luo

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This is the reason why many inspection methods use either static inspection devices, the localization of which can be performed by applying advanced methods based for example on the deep neural networks [25] or using the inertial measurement units creating a basis for the automatic measurement of level differences in belt conveyors [26]. However, there are also many types of mobile robotbased inspection systems for the automatic inspection of the belt conveyors [27] capable of operation even in harsh outdoor environments [28]. The inspection methods often use optical methods involving vision-based [29] and thermal infrared [30][31][32][33][34] principles with the integrated warning systems [35].…”

Section: Introductionmentioning

confidence: 99%

Non-Destructive Testing of Pipe Conveyor Belts Using Glass-Coated Magnetic Microwires

Semrád

Draganová

2022

Sustainability

View full text Add to dashboard Cite

Belt conveyors have been used in a wide range of applications because in comparison to the alternative solutions represented by the rail or road transportation, their operation is typically more cost effective, with lower energy demands and the possibility of utilizing renewable energy sources, and during their operation, less noise and air pollution is produced. The presented article is focused on pipe belt conveyors that are even more sustainable and in harmony with the environment, especially considering transportation of fine and dusty materials. More specifically, pipe belt conveyors have the possibility of utilizing microwires as a sensing element for microwire-based sensors for the pipe belt conveyor diagnostics from a mechanical loading point of view. This is because during the enclosing of the pipe conveyor belt, periodical cyclical mechanical loading is applied due to the bending. From the results of the performed set of FEM (Finite Element Method) analyses of the glass-coated magnetic microwires, it can be concluded that during the selection process of the microwires, emphasis should be directed the thickness of the glass coating, which can affect the lifetime of the microwire significantly. The microwire length has negligible influence on the estimated number of bending cycles until the damage or crack occurs.

show abstract

Sound-Based Anomalies Detection in Agricultural Robotics Application

Baltazar,

dos Santos,

Soares

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

ROSI: A Robotic System for Harsh Outdoor Industrial Inspection - System Design and Applications

Cited by 23 publications

References 24 publications

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

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

Non-Destructive Testing of Pipe Conveyor Belts Using Glass-Coated Magnetic Microwires

Sound-Based Anomalies Detection in Agricultural Robotics Application

Contact Info

Product

Resources

About