Table 2 - available via license: CC BY
Content may be subject to copyright.
Source publication
Increasing demand for higher safety of motors can be noticed in recent years. Developing of new fault detection techniques is related with higher safety of motors. This paper presents fault detection technique of an electric impact drill (EID), coffee grinder A (CG-A), and coffee grinder B (CG-B) using acoustic signals. The EID, CG-A, and CG-B use...
Context in source publication
Context 1
... signals are analysed: healthy (Figure 1 and 2), with 15 broken rotor blades (faulty fan) (Figure 3), with a bent spring (Figure 4), with a shifted brush ( Figure 5), with a rear ball bearing fault ( Figure 6). x FOR PEER REVIEW 2 of 24 measure signals immediately. Vibration and acoustic analysis can also detect mechanical and electrical faults of rotating machinery. ...
Citations
... The acoustic-based approach utilizes acoustic signals collected by acoustic sensors installed near the pipe. Detection technology based on sound waves has attracted much attention due to its low cost and fast detection [5]. ...
Pipeline leakage detection is an integral part of pipeline integrity management. Combining AE (Acoustic Emission) with deep learning is currently the most commonly used method for pipeline leakage detection. However, this approach is usually applicable only to specific situations and requires powerful signal analysis and computational capabilities. To address these issues, this paper proposes an improved Transformer network model for diagnosing faults associated with abnormal working conditions in acoustic emission pipelines. First, the method utilizes the temporal properties of the GRU and the positional coding of the Transformer to capture and feature extract the data point sequence position information to suppress redundant information, and introduces the largest pooling layer into the Transformer model to alleviate the overfitting phenomenon. Second, while retaining the original attention learning mechanism and identity path in the original DRSN, a new soft threshold function is introduced to replace the ReLU activation function with a new threshold function, and a new soft threshold module and adaptive slope module are designed to construct the improved residual shrinkage unit (ASB-STRSBU), which is used to adaptively set the optimal threshold. Finally, pipeline leakage is classified. The experimental results show that the NDRSN model is able to make full use of global and local information when considering leakage signals and can automatically learn and acquire the important parameters of the input features in the spatial and channel domains. By optimizing the GRU improved Transformer network recognition model, the method significantly reduces the model training time and computational resource consumption while maintaining high leakage recognition accuracy. The average accuracy reached 93.97%. This indicates that the method has good robustness in acoustic emission pipeline leakage detection.
... The signal analysis research domain includes Fourier transform [7], wavelet packet transform [8], dual-tree complex wavelet transform [9], Parsimonious Network based on fuzzy Inference System (PANFIS) [10] and the acoustic signal-based approach [11]. Variation mode decomposition was proposed by [3] Yonggang Xu et al. [12], and the adaptive kurtogram (AK) method detects fault signals in damaged machines. ...
... We selected CWT to enhance the raw data's features because the wavelet domain expands the dimensionality of the functional signal, which can significantly extrude the data features. Compared with Fourier transform, wavelet domain representation influences both the time and scale (or frequency) axes, Processes 2023, 11,1527 3 of 17 which means the wavelet transform offers substantial advantages in analyzing nonlinear data. This can provide better results as it correlates the mother wavelet with Raman spectra patterns for various scales and wave number positions. ...
Rolling element bearings (REBs) are the most frequent cause of machine breakdowns. Traditional methods for fault diagnosis in rolling bearings rely on feature extraction and signal processing techniques. However, these methods can be affected by the complexity of the underlying patterns and the need for expert knowledge during signal analysis. This paper proposes a novel signal-to-image method in which the raw signal data are transformed into 2D images using continuous wavelet transform (CWT). This transformation enhances the features extracted from the raw data, allowing for further analysis and interpretation. Transformed images of both normal and faulty rolling bearings from the Case Western Reserve University (CWRU) dataset were used with deep-learning models from the ResNet family. They can automatically learn and identify patterns in raw vibration signals after continuous wavelet transform is used, eliminating the need for manual feature extraction. To further improve the training results, squeeze-and-excitation networks (SENets) were added to improve the process. By comparing results obtained from several models, we found that SE-ResNet152 has the best performance for REB fault diagnosis.
... It is difficult but important to extract fault characteristics and determine fault types. In this regard, methods, such as acoustic emission detection [3] and analysis of vibration [4] have been used. Vibration analysis is frequently employed for fault diagnosis because vibration data can be easily obtained using an attached acceleration sensor. ...
Rolling element bearings play a critical role in rotating machines with variable speed conditions, and their fault detection has attracted considerable interest from researchers in recent decades. In this paper, a high-order-degradation bistable system is proposed, and the corresponding sto-chastic resonance (SR) based on a new measurement index is investigated for fault detection with variable speed conditions. It successfully achieves fault detection without prior knowledge. Firstly, the output signal-to-noise ratio (SNR) of the high-order-degradation bistable stochastic resonance (HBSR) is theoretically analyzed using the approximate adiabatic theory. Secondly, a novel measurement index for determining the occurrence of stochastic resonance is proposed. Thirdly, the experimental data are used to validate the efficiency of the proposed nonlinear system and measurement index when the fault types and the actual fault order are unknown. Finally, the ground test data from a civil aircraft engine is also used to further validate the performance of the HBSR based on the novel measurement index.
... Both methods require the selected parameters, and the number of groups is determined before testing. MSAF-17-MULTIEXPANDED-FILTER-14 [78], SMOFS-22-MULTIEXPANDED [79], MSAF-RATIO-24-MULTIEXPANDED-FILTER-8 [80], and MSAF-RATIO-27-MULTIEXPANDED-4-GROUPS [72] are some variations of the MSAF and SMOFS methods, which have different parameters and algorithms, depending on the type of the fault and the target system. For example, MSAF-17-MULTIEXPANDED-FILTER-14 specifies that the method looks for one to 17 common frequency components, and 14 refers to the 14 Hz bandwidth used to determine a feature vector [78]. ...
... MSAF-17-MULTIEXPANDED-FILTER-14 [78], SMOFS-22-MULTIEXPANDED [79], MSAF-RATIO-24-MULTIEXPANDED-FILTER-8 [80], and MSAF-RATIO-27-MULTIEXPANDED-4-GROUPS [72] are some variations of the MSAF and SMOFS methods, which have different parameters and algorithms, depending on the type of the fault and the target system. For example, MSAF-17-MULTIEXPANDED-FILTER-14 specifies that the method looks for one to 17 common frequency components, and 14 refers to the 14 Hz bandwidth used to determine a feature vector [78]. An additional example of a different parameter is SMOFS-22-MULTIEXPANDED, in which 22 refers to the number of frequency components used in feature extraction [81]. ...
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.
... • MSAF-Multiexpanded stands for the method of selection of amplitudes of frequency multi-expanded filter. These features are mostly used in fault diagnosis in electrical drilling motors [65] and commutator motors [66]. These acoustic features are handcrafted and generated by computing the difference between Fast Fourier Transform (FFT) spectra of different classes. ...
... • SMOFS-Multicrafted is shortened method of frequency selection which is the same as MSAF-multi expanded and is being applied in the industrial sector. This is also used to classify faults in motors [65]. The only difference between SMOFS-multi crafted and MSAFmulti expanded FE method is the selection of frequency components after FFTs computation. ...
The concept of Acoustic Source Identification (ASI), which refers to the process of identifying noise sources has attracted increasing attention in recent years. The ASI technology can be used for surveillance, monitoring, and maintenance applications in a wide range of sectors, such as defence, manufacturing, healthcare, and agriculture. Acoustic signature analysis and pattern recognition remain the core technologies for noise source identification. Manual identification of acoustic signatures, however, has become increasingly challenging as dataset sizes grow. As a result, the use of Artificial Intelligence (AI) techniques for identifying noise sources has become increasingly relevant and useful. In this paper, we provide a comprehensive review of AI-based acoustic source identification techniques. We analyze the strengths and weaknesses of AI-based ASI processes and associated methods proposed by researchers in the literature. Additionally, we did a detailed survey of ASI applications in machinery, underwater applications, environment/event source recognition, healthcare, and other fields. We also highlight relevant research directions.
... Vununu et al. proposed a drill-bit fault diagnosis method based on power spectrum density (PSD) images and a deep convolutional autoencoder (DCAE) [11]. Glowacz designed a fault detection method for electric impact drills and coffee grinders using the root mean square (RMS), MSAF-17-MULTIEXPANDED-FILTER-14, and nearest neighbor (NN) classifier [12]. Wang et al. proposed a method for identifying unknown faults in the iron-making process using variable selection and a moving-window hidden Markov model (VS-MWHMM) [13]. ...
The air-door is an important device for adjusting the air flow in a mine. It opens and closes within a short time owing to transportation and other factors. Although the switching sensor alone can identify the air-door opening and closing, it cannot relate it to abnormal fluctuations in the wind speed. Large fluctuations in the wind-velocity sensor data during this time can lead to false alarms. To overcome this problem, we propose a method for identifying air-door opening and closing using a single wind-velocity sensor. A multi-scale sliding window (MSSW) is employed to divide the samples. Then, the data global features and fluctuation features are extracted using statistics and the discrete wavelet transform (DWT). In addition, a machine learning model is adopted to classify each sample. Further, the identification results are selected by merging the classification results using the non-maximum suppression method. Finally, considering the safety accidents caused by the air-door opening and closing in an actual production mine, a large number of experiments were carried out to verify the effect of the algorithm using a simulated tunnel model. The results show that the proposed algorithm exhibits superior performance when the gradient boosting decision tree (GBDT) is selected for classification. In the data set composed of air-door opening and closing experimental data, the accuracy, precision, and recall rates of the air-door opening and closing identification are 91.89%, 93.07%, and 91.07%, respectively. In the data set composed of air-door opening and closing and other mine production activity experimental data, the accuracy, precision, and recall rates of the air-door opening and closing identification are 89.61%, 90.31%, and 88.39%, respectively.
... The handcrafted features refer to specific properties or characteristics that can be extracted from the signal using various algorithms that utilize the information present in the signal itself. These features are the spectrum power, the peak frequency, Time-Frequency Representation (TFR) [43], the Mean Instantaneous Frequency (MIF) [44], the Mean Instantaneous Bandwidth (MIB) [44], Envelope Modulation Spectrum (EMS) [45], Long-Term Average Spectrum (LTAS) [45], Linear Spectral Frequency (LSF) [46], Octave-based Modulation Spectral Contrast (OMSC) [47], chroma features [48], features extracted through Linear Predictive Coding (LPC) [46], [49], [50] and features extracted through the method of selection of amplitudes of frequency multi-expanded filter [51], [52]. Finally, the second feature type is calculated based on the maximum pixel intensity values in ROI and WOI. ...
In the recycling industry, the use of deep spectral convolutional networks for the purpose of material classification and composition estimation is still limited, despite the great opportunities of these techniques. In this study, the use of Laser-Induced Breakdown Spectroscopy (LIBS), Machine Learning (ML), and Deep Learning (DL) for the three-way sorting of Aluminum (Al) is proposed. Two sample sets of Al scrap are used: one containing 733 pieces for pre-training and validation with a ground truth of X-Ray Fluorescence (XRF), and the second containing 210 pieces for testing for unknown compositions. The proposed method comprises a denoising system combined with a method that extracts 145 features from the raw LIBS spectra. Further, three ML algorithms are assessed to identify the best-performing one to classify unknown pieces of aluminum post-consumer scrap into three commercially interesting output classes. The classified pieces are weighed, melted, and analyzed using spark analysis. Finally, to optimize the best-performing ML system, three state-of-the-art denoising and three feature extraction networks are pre-trained for learning the baseline correction and the proposed feature extraction. Transfer Learning from the six pre-trained networks is applied to create and evaluate 24 end-to-end DL models to classify Al in real-time from >200 spectra simultaneously. The end-to-end DL scheme shows the advantages of learning and denoising the spectra, allowing the transfer of traditional spectral analysis knowledge and the proposed feature extraction into DL, where the network learns from the entire spectrum. The best results for ML and DL were obtained with Random Forest processing one spectrum in 150 ms and BPNN+GHOSTNET(Fine-tuning) processing 200 spectra in 9 ms, which achieved 0.80 Precision, 0.81 Recall, 0.80 F1-score, and 0.80 Precision, 0.79 Recall, 0.79 F1-score, respectively.
... Even though there are many challenges with audio for fault diagnosis [13], some studies have proven that audio signal has the potential to diagnose faults in mechanical components. In [14][15][16][17], faults in moving mechanical components like drill and coffee grinder, three-phase induction motor, railway point machines, and spindle were diagnosed using audio signal processing with the help of machine learning techniques, which gave reasonable accurate results. In [18], it was found that sound signal has the potential to differentiate types of faults in DC motor using statistical quantitative measures of time and frequency domain signal. ...
Bearings are a common component and crucial to most rotating machinery. Their failures are the causes for more than half of the total machine failures, each with the potential to cause extreme damage, injury, and downtime. Therefore, fault detection through condition monitoring has a significant importance. Since the initial cost of standard condition monitoring techniques such as vibration signature analysis is high and has a long payback period, the condition monitoring via audio signal processing is proposed for both localized faults and distributed/ generalized roughness faults in the rolling bearing. It is not appropriate to analyze bearing faults using Fast Fourier Transform (FFT) of the noise signal of bearing since localized faults are Amplitude Modulated (AM) and mixed up with background noises. Localized faults are processed using Kurstogram technique for finding the appropriate filtering band because localized faulty bearings produce impulsive signals
... Moreover, this method uses computer and thermal imaging cameras, and the cost of the experimental setup is low. Moreover, in [42] other methods are developed and implemented with classification algorithms for feature extraction such as: Root Mean Square, Method of Selection of Amplitudes of Frequency Multiexpanded Filter (MSAF-17-MULTIEXPANDED-FIL-TER-14). The results are good and the total efficiency of recognition of all classes are in the range 96%-100%. ...
In this paper, a workbench for remote control of DC motors is proposed. We intend to monitor and control rotating machines. Artificial failures are simulated by injecting different signals into the rotating motor's shaft. A comprehensive, original, and novel approach combining mathematical models, physical phenomena, and smart measurement methods is proposed to eliminate fluctuation faults caused by IoT sensor systems. These consist of a whole set of sensors (Accelerometer in Micro Electro Mechanical Systems [MEMS] technology, etc.) linked to a wireless node which constitutes a monitoring and control generic system of a DC motor running locally or via a remote control through an Internet platform. A reliability test of the IoT sensor system and an exploration of a proposed experimental bench in two measurement environments are successfully achieved. The results prove the reliability of devices for possible detection of acceleration signals corresponding to different speeds and injected vibrations with different forms and frequencies. A universal new approach, based on the Allan VARiance method, that has been proven robust when various disturbing signals are combined, has been successfully implemented to identify artificial vibration signatures. A reconstruction of MEMS sensor outputs using genetic algorithms is successfully fulfilled to get a compromise between the time of data acquisition and the time of processing via a learning phase of our system by means of a pseudo calibration of each motor applying our pseudo real‐time control system. After the calibration phase, our control system aims to space out the measurements without degrading the effectiveness of the monitoring process.
... The spectral descriptors extracted as features are spectral flux, spectral centroid, spectral crest, spectral flatness, spectral kurtosis, spectral entropy, spectral bandwidth, and spectral skewness [11,12]. The other handcrafted features are the peak frequency, the power of the spectrum, the Mean Instantaneous Frequency (MIF) [13], the Mean Instantaneous Bandwidth (MIB) [13], Long-Term Average Spectrum (LTAS) [14], Envelope Modulation Spectrum (EMS) [14], Octave-based Modulation Spectral Contrast (OMSC) [15], Linear Spectral Frequency (LSF) [16], Time-Frequency Representation (TFR) [17], chroma features [18], features extracted through Linear Predictive Coding (LPC) [16,19,20] and features extracted through the Method of Selection of Amplitudes of Frequency Multi-expanded Filter developed by Glowacz et al. [21,22]. The second type of extracted features is a set of 11 "peak features" that hold information on the (relative) intensities of the most prominent peaks in the recorded spectra. ...
The aluminium Twitch fraction of a Belgian recycling facility could be further sorted by implementing Laser-Induced Breakdown Spectroscopy (LIBS). To achieve this goal, the presented research identifies commercially interesting output fractions and investigates machine learning methods to classify the post-consumer aluminium scrap samples based on the spectral data collected by the LIBS sensor for 834 aluminium scrap pieces. The classification performance is assessed with X-Ray Fluorescence (XRF) reference measurements of the investigated aluminium samples, and expressed in terms of accuracy, precision, recall, and f1 score. Finally, the influence of misclassifications on the composition of the desired output fractions is evaluated.
