Motor Fault Diagnosis Based on Convolutional Block Attention Module-Xception Lightweight Neural Network.

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model's order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram's corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks.

A smart look at monitoring while drilling (MWD) and optimizing using acoustic emission technique (AET).

Monitoring while drilling (MWD) is a crucial task in mining operations. Accurately measuring drill and rock-related operating parameters can significantly reduce the cost of drilling operations. This study explores the potential of monitoring drilling specific energy (SE) and optimizing drilling operations by processing vibroacoustic signals generated while drilling. For this purpose, 30 samples of different rocks, are used for drilling tests. During the drilling process, the acoustic and vibration signals are recorded and analyzed in the time, frequency, and time-frequency domains., and parameters related to the resulting spectra are extracted. After obtaining the vibroacoustic parameters for drilling, the relationship between them and the drilling SE was investigated. There is evidence that the progression of SE contributes to the magnitude of rock drilling vibroacoustic features, which could be employed to indicate energy conditions during drilling. Results obtained in this study have the potential to be used as the basis for an industrial monitoring system that can detect excessive energy consumption and advise the user of the end of the bit's useful life. This method can be an intelligent technique for measuring the behavior of real-time drilling operations based on the SE simply by installing vibroacoustic sensors on the drilling machines.

Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge.

Gear fault detection and remaining useful life estimation are important tasks for monitoring the health of rotating machinery. In this study, a new benchmark for endurance gear vibration signals is presented and made publicly available. The new dataset was used in the HUMS 2023 conference data challenge to test anomaly detection algorithms. A survey of the suggested techniques is provided, demonstrating that traditional signal processing techniques interestingly outperform deep learning algorithms in this case. Of the 11 participating groups, only those that used traditional approaches achieved good results on most of the channels. Additionally, we introduce a signal processing anomaly detection algorithm and meticulously compare it to a standard deep learning anomaly detection algorithm using data from the HUMS 2023 challenge and simulated signals. The signal processing algorithm surpasses the deep learning algorithm on all tested channels and also on simulated data where there is an abundance of training data. Finally, we present a new digital twin that enables the estimation of the remaining useful life of the tested gear from the HUMS 2023 challenge.

Early-Stage Fault Diagnosis of Motor Bearing Based on Kurtosis Weighting and Fusion of Current-Vibration Signals.

To solve the problem of a low signal-to-noise ratio of fault signals and the difficulty in effectively and accurately identifying the fault state in the early stage of motor bearing fault occurrence, this paper proposes an early fault diagnosis method for bearings based on the Differential Local Mean Decomposition (DLMD) and fusion of current-vibration signals. This method uses DLMD to decompose the current signal and vibration signal, respectively, and weights the decomposed product function (PF) according to the kurtosis value to reconstruct the signal, and then fuses the reconstructed signals to obtain the current-vibration fusion signal after normalization, and then analyzes the fusion signal spectrally through the Hilbert envelope spectrum. Finally, the fusion signal is analyzed by the Hilbert envelope spectrum, and a clear fault characteristic frequency is obtained. The experimental results demonstrate that compared to traditional bearing fault diagnosis methods, the proposed method significantly improves the signal-to-noise ratio of fault signals, effectively enhances the sensitivity of early-stage fault detection in motor bearings, and improves the accuracy of fault identification.

A Time-Frequency Domain Mixed Attention-Based Approach for Classifying Wood-Boring Insect Feeding Vibration Signals Using a Deep Learning Model.

Wood borers, such as the emerald ash borer and holcocerus insularis staudinger, pose a significant threat to forest ecosystems, causing damage to trees and impacting biodiversity. This paper proposes a neural network for detecting and classifying wood borers based on their feeding vibration signals. We utilize piezoelectric ceramic sensors to collect drilling vibration signals and introduce a novel convolutional neural network (CNN) architecture named Residual Mixed Domain Attention Module Network (RMAMNet).The RMAMNet employs both channel-domain attention and time-domain attention mechanisms to enhance the network's capability to learn meaningful features. The proposed system outperforms established networks, such as ResNet and VGG, achieving a recognition accuracy of 95.34% and an F1 score of 0.95. Our findings demonstrate that RMAMNet significantly improves the accuracy of wood borer classification, indicating its potential for effective pest monitoring and classification tasks. This study provides a new perspective and technical support for the automatic detection, classification, and early warning of wood-boring pests in forestry.

Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis.

This study introduces an innovative approach for fault diagnosis of a multistage centrifugal pump (MCP) using explanatory ratio (ER) linear discriminant analysis (LDA). Initially, the method addresses the challenge of background noise and interference in vibration signals by identifying a fault-sensitive frequency band (FSFB). From the FSFB, raw hybrid statistical features are extracted in time, frequency, and time-frequency domains, forming a comprehensive feature pool. Recognizing that not all features adequately represent MCP conditions and can reduce classification accuracy, we propose a novel ER-LDA method. ER-LDA evaluates feature importance by calculating the explanatory ratio between interclass distance and intraclass scatteredness, facilitating the selection of discriminative features through LDA. This fusion of ER-based feature assessment and LDA yields the novel ER-LDA technique. The resulting selective feature set is then passed into a k-nearest neighbor (K-NN) algorithm for condition classification, distinguishing between normal, mechanical seal hole, mechanical seal scratch, and impeller defect states of the MCP. The proposed technique surpasses current cutting-edge techniques in fault classification.

Condition Monitoring of Pneumatic Drive Systems Based on the AI Method Feed-Forward Backpropagation Neural Network.

Machine condition monitoring is used in a variety of industries as a very efficient strategy for equipment maintenance. This paper presents a study on monitoring a pneumatic system using a feed-forward backpropagation neural network as a classifier and compares the results obtained with different sensor signals and associated extracted features as input for classification. The vibrations of the body of a pneumatic cylinder are acquired using both common industrial sensors and low-cost sensors integrated into an Arduino board. Pressure sensors for both chambers and a position sensor are also used. Power spectral density (PSD) is used to extract features from the acceleration signals, as well as statistical indices. Statistical indices are considered for pressure and position sensors. The results, which are based on experimental data obtained on a test bench, show that a feed-forward neural network makes it possible to identify the operating states with a good degree of reliability. Even with low-cost instrumentation, it is possible to realize reliable condition monitoring based on vibrations. This last result is particularly important as it can help to further increase the uptake of this maintenance approach in the industrial environment.

Remaining Useful Life Estimation of Hollow Worn Railway Vehicle Wheels via On-Board Random Vibration-Based Wheel Tread Depth Estimation.

The problem of remaining useful life estimation (RULE) of hollow worn railway vehicle wheels in terms of remaining mileage via wheel tread depth estimation using on-board vibration signals from a single accelerometer on the bogie frame is presently investigated. This is achieved based on the introduction of a statistical time series method that employs: (i) advanced data-driven stochastic Functionally Pooled models for the modeling of the vehicle dynamics under different wheel tread depths in a range of interest until a critical limit, as well as tread depth estimation through a proper optimization procedure, and (ii) a wheel tread depth evolution function with respect to the vehicle running mileage that interconnects the estimated hollow wear with the remaining useful mileage. The method's RULE performance is investigated via hundreds of Simpack-based Monte Carlo simulations with an Attiko Metro S.A. vehicle and many hollow worn wheels scenarios which are not used for the method's training. The obtained results indicate the accurate estimation of the wheels tread depth with a mean absolute error of ∼0.07 mm that leads to a corresponding small error of ∼3% with respect to the wheels remaining useful mileage. In addition, the comparison with a recently introduced Multiple Model (MM)-based multi-health state classification method for RULE, demonstrates the better performance of the postulated method that achieves 81.17% True Positive Rate (TPR) which is significantly higher than the 45.44% of the MM method.

Scale-Fractal Detrended Fluctuation Analysis for Fault Diagnosis of a Centrifugal Pump and a Reciprocating Compressor.

Reciprocating compressors and centrifugal pumps are rotating machines used in industry, where fault detection is crucial for avoiding unnecessary and costly downtime. A novel method for fault classification in reciprocating compressors and multi-stage centrifugal pumps is proposed. In the feature extraction stage, raw vibration signals are processed using multi-fractal detrended fluctuation analysis (MFDFA) to extract features indicative of different types of faults. Such MFDFA features enable the training of machine learning models for classifying faults. Several classical machine learning models and a deep learning model corresponding to the convolutional neural network (CNN) are compared with respect to their classification accuracy. The cross-validation results show that all models are highly accurate for classifying the 13 types of faults in the centrifugal pump, the 17 valve faults, and the 13 multi-faults in the reciprocating compressor. The random forest subspace discriminant (RFSD) and the CNN model achieved the best results using MFDFA features calculated with quadratic approximations. The proposed method is a promising approach for fault classification in reciprocating compressors and multi-stage centrifugal pumps.

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann-Whitney Test.

This work presents a technique for fault detection and identification in centrifugal pumps (CPs) using a novel fault-specific Mann-Whitney test (FSU Test) and K-nearest neighbor (KNN) classification algorithm. Traditional fault indicators, such as the mean, peak, root mean square, and impulse factor, lack sensitivity in detecting incipient faults. Furthermore, for defect identification, supervised models rely on pre-existing knowledge about pump defects for training purposes. To address these concerns, a new centrifugal pump fault indicator (CPFI) that does not rely on previous knowledge is developed based on a novel fault-specific Mann-Whitney test. The new fault indicator is obtained by decomposing the vibration signature (VS) of the centrifugal pump hierarchically into its respective time-frequency representation using the wavelet packet transform (WPT) in the first step. The node containing the fault-specific frequency band is selected, and the Mann-Whitney test statistic is calculated from it. The combination of hierarchical decomposition of the vibration signal for fault-specific frequency band selection and the Mann-Whitney test form the new fault-specific Mann-Whitney test. The test output statistic yields the centrifugal pump fault indicator, which shows sensitivity toward the health condition of the centrifugal pump. This indicator changes according to the working conditions of the centrifugal pump. To further enhance fault detection, a new effect ratio (ER) is introduced. The KNN algorithm is employed to classify the fault type, resulting in promising improvements in fault classification accuracy, particularly under variable operating conditions.

Digital Twin-Driven Tool Condition Monitoring for the Milling Process.

Exact observing and forecasting tool conditions fundamentally affect cutting execution, bringing further developed workpiece machining accuracy and lower machining costs. Because of the unpredictability and time-differing nature of the cutting system, existing methodologies cannot achieve ideal oversight progressively. A technique dependent on Digital Twins (DT) is proposed to accomplish extraordinary accuracy in checking and anticipating tool conditions. This technique builds up a balanced virtual instrument framework that matches entirely with the physical system. Collecting data from the physical system (Milling Machine) is initialized, and sensory data collection is carried out. The National Instruments data acquisition system captures vibration data through a uni-axial accelerometer, and a USB-based microphone sensor acquires the sound signals. The data are trained with different Machine Learning (ML) classification-based algorithms. The prediction accuracy is calculated with the help of a confusion matrix with the highest accuracy of 91% through a Probabilistic Neural Network (PNN). This result has been mapped by extracting the statistical features of the vibrational data. Testing has been performed with the trained model to validate the model's accuracy. Later, the modeling of the DT is initiated using MATLAB-Simulink. This model has been created under the data-driven approach. The physical-virtual balance of the DT model is acknowledged utilizing the advances, taking into consideration the detailed planning of the constant state of the tool's condition. The tool condition monitoring system through the DT model is deployed through the machine learning technique. The DT model can predict the different tool conditions based on sensory data.

Identification of milling status based on vibration signals using artificial intelligence in robot-assisted cervical laminectomy.

BACKGROUND: With advances in science and technology, the application of artificial intelligence in medicine has significantly progressed. The purpose of this study is to explore whether the k-nearest neighbors (KNN) machine learning method can identify three milling states based on vibration signals: cancellous bone (CCB), ventral cortical bone (VCB), and penetration (PT) in robot-assisted cervical laminectomy. METHODS: Cervical laminectomies were performed on the cervical segments of eight pigs using a robot. First, the bilateral dorsal cortical bone and part of the CCB were milled with a 5 mm blade and then the bilateral laminae were milled to penetration with a 2 mm blade. During the milling process using the 2 mm blade, the vibration signals were collected by the acceleration sensor, and the harmonic components were extracted using fast Fourier transform. The feature vectors were constructed with vibration signal amplitudes of 0.5, 1.0, and 1.5 kHz and the KNN was then trained by the features vector to predict the milling states. RESULTS: The amplitudes of the vibration signals between VCB and PT were statistically different at 0.5, 1.0, and 1.5 kHz (P < 0.05), and the amplitudes of the vibration signals between CCB and VCB were significantly different at 0.5 and 1.5 kHz (P < 0.05). The KNN recognition success rates for the CCB, VCB, and PT were 92%, 98%, and 100%, respectively. A total of 6% and 2% of the CCB cases were identified as VCB and PT, respectively; 2% of VCB cases were identified as PT. CONCLUSIONS: The KNN can distinguish different milling states of a high-speed bur in robot-assisted cervical laminectomy based on vibration signals. This method is feasible for improving the safety of posterior cervical decompression surgery.

Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection.

With the rapid development of sensor technology, structural health monitoring data have tended to become more massive. Deep learning has advantages when handling big data, and has therefore been widely researched for diagnosing structural anomalies. However, for the diagnosis of different structural abnormalities, the model hyperparameters need to be adjusted according to different application scenarios, which is a complicated process. In this paper, a new strategy for building and optimizing 1D-CNN models is proposed that is suitable for diagnosing damage to different types of structure. This strategy involves optimizing hyperparameters with the Bayesian algorithm and improving model recognition accuracy using data fusion technology. Under the condition of sparse sensor measurement points, the entire structure is monitored, and the high-precision diagnosis of structural damage is performed. This method improves the applicability of the model to different structure detection scenarios, and avoids the shortcomings of traditional hyperparameter adjustment methods based on experience and subjectivity. In preliminary research on the simply supported beam test case, the efficient and accurate identification of parameter changes in small local elements was achieved. Furthermore, publicly available structural datasets were utilized to verify the robustness of the method, and a high identification accuracy rate of 99.85% was achieved. Compared with other methods described in the literature, this strategy shows significant advantages in terms of sensor occupancy rate, computational cost, and identification accuracy.

The Performance Analysis of PSO-ResNet for the Fault Diagnosis of Vibration Signals Based on the Pipeline Robot.

In the context of pipeline robots, the timely detection of faults is crucial in preventing safety incidents. In order to ensure the reliability and safety of the entire application process, robots' fault diagnosis techniques play a vital role. However, traditional diagnostic methods for motor drive end-bearing faults in pipeline robots are often ineffective when the operating conditions are variable. An efficient solution for fault diagnosis is the application of deep learning algorithms. This paper proposes a rolling bearing fault diagnosis method (PSO-ResNet) that combines a Particle Swarm Optimization algorithm (PSO) with a residual network. A number of vibration signal sensors are placed at different locations in the pipeline robot to obtain vibration signals from different parts. The input to the PSO-ResNet algorithm is a two-bit image obtained by continuous wavelet transform of the vibration signal. The accuracy of this fault diagnosis method is compared with different types of fault diagnosis algorithms, and the experimental analysis shows that PSO-ResNet has higher accuracy. The algorithm was also deployed on an Nvidia Jetson Nano and a Raspberry Pi 4B. Through comparative experimental analysis, the proposed fault diagnosis algorithm was chosen to be deployed on the Nvidia Jetson Nano and used as the core fault diagnosis control unit of the pipeline robot for practical scenarios. However, the PSO-ResNet model needs further improvement in terms of accuracy, which is the focus of future research work.

Selective weighted multi-scale morphological filter for fault feature extraction of rolling bearings.

Morphological filtering shows effectiveness in vibration signal analysis because of its simplicity and efficiency. Considering that different structural elements have different effects on filtering results, a new multi-scale morphological filtering (MMF) method called selective weighted multi-scale morphological filter (SWMMF) is developed for integrating results of different scales based on adaptive weighting strategy. Firstly, four morphological operators (dilation-closing, closing-dilation, erosion-opening and opening-erosion) are integrated into a new combination difference morphological filter to strengthen effect of faulty component extraction. Secondly, this new morphological filter is further extended to multiple scales in order to overcome limitation of single scale filter. Finally, the filtered results of different scales are adaptively combined by using the whale optimization algorithm (WOA)-based selective weighting method. The effectiveness of multi-scale filter and selective weights is proved by comparing with single-scale and average weighting filter on simulation and real-world cases (bearing vibration signals with different defects). The testing results on vibration signals indicate that SWMMF is able to extract effectively defect frequency and the corresponding multiplication frequencies from bearing vibration signals with heavy noise. The testing results illustrate that SWMMF outperforms other representative MMFs (e.g., weighted multi-scale morphological gradient operator (WMMG), weighted multi-scale difference operator (WMDIF), weighted multi-scale average operator (WMAVG)) on impulsive feature extraction of bearing vibrations signals with various defects. Moreover, it is demonstrated that SWMMF has good applicability in bearing fault diagnosis due to setup of adaptive weights and selection of structure element.

Automatic Implementation Algorithm of Pressure Relief Drilling Depth Based on an Innovative Monitoring-While-Drilling Method.

An innovative monitoring-while-drilling method of pressure relief drilling was proposed in a previous study, and the periodic appearance of amplitude concentrated enlargement zone in vibration signals can represent the drilling depth. However, there is a lack of a high accuracy model to automatically identify the amplitude concentrated enlargement zone. So, in this study, a neural network model is put forward based on single-sensor and multi-sensor prediction results. The neural network model consists of one Deep Neural Network (DNN) and four Long Short-Term Memory (LSTM) networks. The accuracy is only 92.72% when only using single-sensor data for identification, while the proposed multiple neural network model could improve the accuracy to being greater than 97.00%. In addition, an optimization method was supplemented to eliminate some misjudgment due to data anomalies, which improved the final accuracy to the level of manual recognition. Finally, the research results solved the difficult problem of identifying the amplitude concentrated enlargement zone and provided the foundation for automatically identifying the drilling depth.

Analyses of Vibration Signals Generated in W. Nr. 1.0038 Steel during Abrasive Water Jet Cutting Aimed to Process Control.

The presented research was aimed at finding a suitable tool and procedure for monitoring undercuts or other problems such as cutting without abrasive or inappropriate parameters of the jet during the abrasive water jet (AWJ) cutting of hard-machined materials. Plates of structural steel RSt 37-2 of different thickness were cut through by AWJ with such traverse speeds that cuts of various qualities were obtained. Vibrations of the workpiece were monitored by three accelerometers mounted on the workpiece by a special block that was designed for this purpose. After detecting and recording vibration signals through the National Instruments (NI) program Signal Express, we processed this data by means of the LabVIEW Sound and Vibration Toolkit. Statistical evaluation of data was performed, and RMS was identified as the parameter most suitable for online vibration monitoring. We focus on the analysis of the relationship between the RMS and traverse speed.

Fault Diagnosis of Rolling Bearings Based on WPE by Wavelet Decomposition and ELM.

The fault diagnosis classification method based on wavelet decomposition and weighted permutation entropy (WPE) by the extreme learning machine (ELM) is proposed to address the complexity and non-smoothness of rolling bearing vibration signals. The wavelet decomposition based on 'db3' is used to decompose the signal into four layers and extract the approximate and detailed components, respectively. Then, the WPE values of the approximate (CA) and detailed (CD) components of each layer are calculated and composed to be the feature vectors, which are finally fed into the extreme learning machine with optimal parameters for classification. The comparative study of the simulations based on WPE and permutation entropy (PE) shows that the classification method of seven kinds of signals of normal bearing signals and six types of fault states (7 mils and 14 mils) based on WPE (CA, CD) with the number of nodes in the hidden layers of ELM determined by the five-fold cross-validation has the best performances, the training accuracy can reach 100%, and the testing accuracy can reach 98.57% with 37 nodes of the hidden layer by ELM. The proposed method using WPE (CA, CD) by ELM provides guidance for the multi-classification of normal bearing signals.

Analysis of Cardiac Vibration Signals Acquired From a Novel Implant Placed on the Gastric Fundus.

The analysis of cardiac vibration signals has been shown as an interesting tool for the follow-up of chronic pathologies involving the cardiovascular system, such as heart failure (HF). However, methods to obtain high-quality, real-world and longitudinal data, that do not require the involvement of the patient to correctly and regularly acquire these signals, remain to be developed. Implantable systems may be a solution to this observability challenge. In this paper, we evaluate the feasibility of acquiring useful electrocardiographic (ECG) and accelerometry (ACC) data from an innovative implant located in the gastric fundus. In a first phase, we compare data acquired from the gastric fundus with gold standard data acquired from surface sensors on 2 pigs. A second phase investigates the feasibility of deriving useful hemodynamic markers from these gastric signals using data from 4 healthy pigs and 3 pigs with induced HF with longitudinal recordings. The following data processing chain was applied to the recordings: (1) ECG and ACC data denoising, (2) noise-robust real-time QRS detection from ECG signals and cardiac cycle segmentation, (3) Correlation analysis of the cardiac cycles and computation of coherent mean from aligned ECG and ACC, (4) cardiac vibration components segmentation (S1 and S2) from the coherent mean ACC data, and (5) estimation of signal context and a signal-to-noise ratio (SNR) on both signals. Results show a high correlation between the markers acquired from the gastric and thoracic sites, as well as pre-clinical evidence on the feasibility of chronic cardiovascular monitoring from an implantable cardiac device located at the gastric fundus, the main challenge remains on the optimization of the signal-to-noise ratio, in particular for the handling of some sources of noise that are specific to the gastric acquisition site.