Distributed optical fibre sensor for condition monitoring of mining conveyor using wavelet transform and artificial neural network

Abstract

Condition monitoring of mining conveyors is highly essential, not only to reduce economic loss due to sudden component breakdown but also to prevent safety risks to maintenance personnel. The vibration measurement by means of Distributed Optical Fibre Sensors (DOFS) is a potential solution to provide cost-effective real-time monitoring of mining conveyors. However, an effective application of detecting early damage and damage progression mainly depends on collection quality of optical signal and robust signal processing methods. Therefore, this study focuses on the identification of an effective signal processing method for real-time monitoring of mining conveyor systems. A prototype conveyor system with various levels of idler damages was built to run experimental tests and to collect optical signals for further analysis. A wavelet-based damage detection method is proposed, and its efficiency is evaluated. Additionally, Artificial Neural Network (ANN) is integrated to develop a smart fault detection technology for fast detection and damage classification. The proposed method has 99% accuracy in classify damage condition under varying coveyor operating speed.

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

“…For example, Wijaya et al [ 12 ] developed an anomaly detection method using DOFS signals and statistical features. Another study by the same author [ 60 ] captured the vibration signals using DOFS technology and then processed them using ANN based on frequency analysis of the faulty idlers. As a result of the DOFS technology, there is no need to use multiple sensors for long and distributed infrastructures since the optical fiber cable itself acts as a continuous sensor.…”

“…In other words, it is the process of focusing on the most discriminating signal characteristics, representing a useful tool in FD systems. The next step is to select a subset of sensitive features related to belt conveyor idlers’ health states based on a number of factors, such as correlation, principal component analysis (PCA), stacked autoencoder [ 40 ], and Pearson correlation [ 60 ]. The performance of the ML models is determined by these steps [ 63 ].…”

“…However, it is difficult to determine the accuracy of fault detection and classification algorithms by using only one feature. Therefore, in this study [ 60 ], several commonly used statistical time domain features (e.g., RMS, peak to peak, standard deviation, skewness, crest factor, and kurtosis) have been considered. Other articles [ 45 , 46 , 48 , 58 ] used statistical features as a part of the analysis, including mean, median, mode, standard error, standard deviation, kurtosis, skewness, minimum value, maximum value, sample variance, and range with different ML models.…”

“…Another study [ 60 ] used four decomposition levels to obtain 24 features, analyzed according to their correlation with the output, and filtered by Pearson correlation to eliminate features with low correlations. Db9 is selected as the optimal wavelet function in the analysis, which illustrates that the key issue is selecting the appropriate number of vanishing moments.…”

Perimeter Security System Based on Ultra-Weak Fiber Bragg Grating Array

“…Fiber sensing technology is corrosion-resistant, electromagnetic interferenceresistant and sensitive compared to traditional security technologies such as infrared detectors, video surveillance, laser beam detectors, and electronic guardrail. The perimeter security system has many advantages, such as long-distance monitoring, and has been used in many important places such as high-speed rail lines and subway tunnels [1] [2] [3] [4] [5]. Fiber perimeter security technologies include distributed sensing technologies (e.g., phase-sensitive optical timedomain reflectometer (ϕ-OTDR), Mach-Zehnder interferometer (M-ZI)), and fiber Bragg grating (FBG) semi-distributed sensing technologies [6] [7] [8] [9].…”