Deep neural network based classification of rolling element bearings and health degradation through comprehensive vibration signal analysis

Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.

Fault Pattern Diagnosis and Classification in Sensor Nodes Using Fall Curve

The rapid expansion of Internet of Things(IoT)devices deploys various sensors in different applications like homes,cities and offices.IoT applications depend upon the accuracy of sensor data.So,it is necessary to predict faults in the sensor and isolate their cause.A novel primitive technique named fall curve is presented in this paper which characterizes sensor faults.This technique identifies the faulty sensor and determines the correct working of the sensor.Different sources of sensor faults are explained in detail whereas various faults that occurred in sensor nodes available in IoT devices are also presented in tabular form.Fault prediction in digital and analog sensors along with methods of sensor fault prediction are described.There are several advantages and disadvantages of sensor fault prediction methods and the fall curve technique.So,some solutions are provided to overcome the limitations of the fall curve technique.In this paper,a bibliometric analysis is carried out to visually analyze 63 papers fetched from the Scopus database for the past five years.Its novelty is to predict a fault before its occurrence by looking at the fall curve.The sensing of current flow in devices is important to prevent a major loss.So,the fall curves of ACS712 current sensors configured on different devices are drawn for predicting faulty or non-faulty devices.The analysis result proved that if any of the current sensors gets faulty,then the fall curve will differ and the value will immediately drop to zero.Various evaluation metrics for fault prediction are also described in this paper.At last,this paper also addresses some possible open research issues which are important to deal with false IoT sensor data.

One-Variable Attack on the Industrial Fault Classification System and Its Defense

Recently developed fault classification methods for industrial processes are mainly data-driven.Notably,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data patterns.However,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault predictions.Several recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial samples.This paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial samples.Moreover,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human eye.Using the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification systems.Based on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the classifiers.In experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and datasets.For industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.

A Transmission Line Fault Classification Approach by Support Vector Machines

This paper presents an approach for shunt faults detection and classification in transmission line using Support Vector Machine （SVM）. The paper compares between using three line post-fault current samples for one-half cycle and one-fourth cycle from the inception of the fault as inputs for SVM. Two SVMs are used, first SVMabc is used for faulty phase detection and second SVMg is used for ground detection. SVMs with polynomial kernel with different degrees are used to obtain the best classification score. The classification test results show that the proposed method is accurate and reliable.

A comparative evaluation of Stacked Auto-Encoder neural network and Multi-Layer Extreme Learning Machine for detection and classification of faults in transmission lines using WAMS data

Smart grid is envisaged as a power grid that is extremely reliable and flexible.The electrical grid has wide-area measuring devices like Phasor measurement units(PMUs)deployed to provide real-time grid information and resolve issues effectively and speedily without compromising system availability.The development and application of machine learning approaches for power system protection and state estimation have been facilitated by the availability of measurement data.This research proposes a transmission line fault detection and classification(FD&C)system based on an auto-encoder neural network.A comparison between a Multi-Layer Extreme Learning Machine(ML-ELM)network model and a Stacked Auto-Encoder neural network(SAE)is made.Additionally,the performance of the models developed is compared to that of state-of-the-art classifier models employing feature datasets acquired by wavelet transform based feature extraction as well as other deep learning models.With substantially shorter testing time,the suggested auto-encoder models detect faults with 100% accuracy and classify faults with 99.92% and 99.79%accuracy.The computational efficiency of the ML-ELM model is demonstrated with high accuracy of classification with training time and testing time less than 50 ms.To emulate real system scenarios the models are developed with datasets with noise with signal-to-noise-ratio(SNR)ranging from 10 dB to 40 dB.The efficacy of the models is demonstrated with data from the IEEE 39 bus test system.

Data-Driven Approach for Condition Monitoring and Improving Power Output of Photovoltaic Systems

Increasing renewable energy targets globally has raised the requirement for the efficient and profitable operation of solar photovoltaic(PV)systems.In light of this requirement,this paper provides a path for evaluating the operating condition and improving the power output of the PV system in a grid integrated environment.To achieve this,different types of faults in grid-connected PV systems(GCPVs)and their impact on the energy loss associated with the electrical network are analyzed.A data-driven approach using neural networks(NNs)is proposed to achieve root cause analysis and localize the fault to the component level in the system.The localized fault condition is combined with a parallel operation of adaptive neurofuzzy inference units(ANFIUs)to develop a power mismatch-based control unit(PMCU)for improving the power output of the GCPV.To develop the proposed framework,a 10-kW single-phase GCPV is simulated for training the NN-based anomaly detection approach with 14 deviation signals.Further,the developed algorithm is combined with the PMCU implemented with the experimental setup of GCPV.The results identified 98.2%training accuracy and 43000 observations/sec prediction speed for the trained classifier,and improved power output with reduced voltage and current harmonics for the grid-connected PV operation.

An Efficient IIoT-Based Smart Sensor Node for Predictive Maintenance of Induction Motors

Predictive maintenance is a vital aspect of the industrial sector,and the use of Industrial Internet of Things(IIoT)sensor nodes is becoming increasingly popular for detecting motor faults and monitoring motor conditions.An integrated approach for acquiring,processing,and wirelessly transmitting a large amount of data in predictive maintenance applications remains a significant challenge.This study presents an IIoT-based sensor node for industrial motors.The sensor node is designed to acquire vibration data on the radial and axial axes of the motor and utilizes a hybrid approach for efficient data processing via edge and cloud platforms.The initial step of signal processing is performed on the node at the edge,reducing the burden on a centralized cloud for processing data from multiple sensors.The proposed architecture utilizes the lightweight Message Queue Telemetry Transport(MQTT)communication protocol for seamless data transmission from the node to the local and main brokers.The broker’s bridging allows for data backup in case of connection loss.The proposed sensor node is rigorously tested on a motor testbed in a laboratory setup and an industrial setting in a rice industry for validation,ensuring its performance and accuracy in real-world industrial environments.The data analysis and results from both testbed and industrial motors were discussed using vibration analysis for identifying faults.The proposed sensor node is a significant step towards improving the efficiency and reliability of industrial motors through realtime monitoring and early fault detection,ultimately leading to minimized unscheduled downtime and cost savings.

Multi-Fault Diagnosis for Autonomous Underwater Vehicle Based on Fuzzy Weighted Support Vector Domain Description

This paper addresses the multi-fault diagnosis problem of thrusters and sensors for autonomous underwater vehicles (AUVs). Traditional support vector domain description (SVDD) has low classification accuracy in the process of AUV multi-fault pattern classification because of the effect of sample sparse density and the uneven distribution of samples, and so on. Thus, a fuzzy weighted support vector domain description (FWSVDD) method based on positive and negative class samples is proposed. In this method, the negative class sample is introduced during classifier training, and the local density and the class weight are introduced for each sample. To improve the multi-fault pattern classifier training speed and fault diagnosis accuracy of FWSVDD, a multi-fault mode classification method based on a hierarchical strategy is proposed. This method adds fault contain detection surface for each thruster and sensor to isolate fault components during fault diagnosis. By considering the problem of pattern classification for a fuzzy sample, which may be located in the overlapping area of hyper-spheres or may not belong to any hyper-sphere in the process of multi-fault classification based on FWSVDD, a relative distance judgment method is given. The effectiveness of the proposed multi-fault diagnosis approach is demonstrated through water tank experiments with an experimental AUV prototype.

Swarm-LSTM: Condition Monitoring of Gearbox Fault Diagnosis Based on Hybrid LSTM Deep Neural Network Optimized by Swarm Intelligence Algorithms

Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling costs.Most of the renewable energy sources involve turbines and their operation and maintenance are vital and a difficult task.Condition monitoring and fault diagnosis have seen remarkable and revolutionary up-gradation in approaches,practices and technology during the last decade.Turbines mostly do use a rotating type of machinery and analysis of those signals has been challenging to localize the defect.This paper proposes a new hybrid model wherein multiple swarm intelligence models have been evaluated to optimize the conventional Long Short-Term Memory(LSTM)model in classifying the faults from the vibration signals data acquired from the gearbox.This helps to analyze the performance and behavioral patterns of the system more effectively and efficiently which helps to suggest for replacement of the unit with higher precision.The results have demonstrated that the proposed hybrid modeling approach is effective in classifying the faults of the gearbox from the time series data and achieve higher diagnostic accuracy in comparison to the conventional LSTM methods.

Remote monitoring system for real time detection and classification of transmission line faults in a power grid using PMU measurements

Remote monitoring of transmission lines of a power system is significant for improved reliability and stability during fault conditions and protection system breakdowns.This paper proposes a smart backup monitoring system for detecting and classifying the type of transmission line fault occurred in a power grid.In contradiction to conventional methods,transmission line fault occurred at any locality within power grid can be identified and classified using measurements from phasor measurement unit(PMU)at one of the generator buses.This minimal requirement makes the proposed methodology ideal for providing backup protection.Spectral analysis of equivalent power factor angle(EPFA)variation has been adopted for detecting the occurrence of fault that occurred anywhere in the grid.Classification of the type of fault occurred is achieved from the spectral coefficients with the aid of artificial intelligence.The proposed system can considerably assist system protection center(SPC)in fault localization and to restore the line at the earliest.Effectiveness of proposed system has been validated using case studies conducted on standard power system networks.

Detection and Classification of Transmission Line Transient Faults Based on Graph Convolutional Neural Network

We present a novel transient fault detection and classification approach in power transmission lines based on graph convolutional neural network.Compared with the existing techniques,the proposed approach considers explicit spatial information in sampling sequences as prior knowledge and it has stronger feature extraction ability.On this basis,a framework for transient fault detection and classification is created.Graph structure is generated to provide topology information to the task.Our approach takes the adjacency matrix of topology graph and the bus voltage signals during a sampling period after transient faults as inputs,and outputs the predicted classification results rapidly.Furthermore,the proposed approach is tested in various situations and its generalization ability is verified by experimental results.The results show that the proposed approach can detect and classify transient faults more effectively than the existing techniques,and it is practical for online transmission line protection for its rapidness,high robustness and generalization ability.

Robustness Assessment and Adaptive FDI for Car Engine

A new on-line fault detection and isolation （FDI） scheme proposed for engines using an adaptive neural network classifier is evaluated for a wide range of operational modes to check the robustness of the scheme in this paper. The neural classifier is adaptive to cope with the significant parameter uncertainty, disturbances, and environment changes. The developed scheme is capable of diagnosing faults in on-line mode and the FDI for the closed-loop system with can be directly implemented in an on-board crankshaft speed feedback is investigated by diagnosis system （hardware）. The robustness of testing it for a wide range of operational modes including robustness against fixed and sinusoidal throttle angle inputs, change in load, change in an engine parameter, and all these changes occurring at the same time. The evaluations are performed using a mean value engine model （MVEM）, which is a widely used benchmark model for engine control system and FDI system design. The simulation results confirm the robustness of the proposed method for various uncertainties and disturbances.

A Wavelet-Based Technique for Distribution Networks

This paper presents a wavelet-based technique for detection and classification of normal and abnormal conditions that occur on power distribution lines. The proposed technique depends on a sensitive fault detection parameter （denoted DET） calculated from the wavelet multi-resolution decomposition of the three phase currents only. This parameter is fast and sensitive to any small changes in the current signal since it uses the square of the first and second details of the decomposed signals. The simulation results of this study clearly show that the proposed technique can be successfully used to detect and classify not only low-current faults that could not be detected by conventional overcurrent relays but also normal transients like load switching and inrush currents.

Fault Classification for On-board Equipment of High-speed Railway Based on Attention Capsule Network

The conventional troubleshooting methods for high-speed railway on-board equipment, with over-reliance on personnel experience, is characterized by one-sidedness and low efficiency. In the process of high-speed train operation, numerous text-based onboard logs are recorded by on-board computers. Machine learning methods can help technicians make a correct judgment of fault types using the on-board log reasonably. Therefore, a fault classification model of on-board equipment based on attention capsule networks is proposed. This paper presents an empirical exploration of the application of a capsule network with dynamic routing in fault classification. A capsule network can encode the internal spatial part-whole relationship between various entities to identify the fault types. As the importance of each word in the on-board log and the dependencies between them have a significant impact on fault classification, an attention mechanism is incorporated into the capsule network to distill important information. Considering the imbalanced distribution of normal data and fault data in the on-board log, the focal loss function is introduced into the model to adjust the imbalanced data. The experiments are conducted on the on-board log of a railway bureau and compared with other baseline models. The experimental results demonstrate that our model outperforms the compared baseline methods, proving the superiority and competitiveness of our model.

k-NN based fault detection and classification methods for power transmission systems

This paper deals with two new methods,based on k-NN algorithm,for fault detection and classification in distance protection.In these methods,by finding the distance between each sample and its fifth nearest neighbor in a predefault window,the fault occurrence time and the faulty phases are determined.The maximum value of the distances in case of detection and classification procedures is compared with pre-defined threshold values.The main advantages of these methods are:simplicity,low calculation burden,acceptable accuracy,and speed.The performance of the proposed scheme is tested on a typical system in MATLAB Simulink.Various possible fault types in different fault resistances,fault inception angles,fault locations,short circuit levels,X/R ratios,source load angles are simulated.In addition,the performance of similar six well-known classification techniques is compared with the proposed classification method using plenty of simulation data.

Low Impedance Fault Identification and Classification Based on Boltzmann Machine Learning for HVDC Transmission Systems

Identification and classification of DC faults are considered as fundamentals of DC grid protection.A sudden rise of DC fault current must be identified and classified to immediately operate the corresponding interrupting mechanism.In this paper,the Boltzmann machine learning(BML)approach is proposed for identification and classification of DC faults using travelling waves generated at fault point in voltage source converter based high-voltage direct current(VSC-HVDC)transmission system.An unsupervised way of feature extraction is performed on the frequency spectrum of the travelling waves.Binomial class logistic regression(BCLR)classifies the HVDC transmission system into faulty and healthy states.The proposed technique reduces the time for fault identification and classification because of reduced tagged data with few characteristics.Therefore,the faults near or at converter stations are readily identified and classified.The performance of the proposed technique is assessed via simulations developed in MATLAB/Simulink and tested for pre-fault and post-fault data both at VSC1 and VSC2,respectively.Moreover,the proposed technique is supported by analyzing the root mean square error to show practicality and realization with reduced computations.

Ensemble enhanced active learning mixture discriminant analysis model and its application for semi-supervised fault classification

As an indispensable part of process monitoring, the performance of fault classification relies heavily on the sufficiency of process knowledge. However, data labels are always difficult to acquire because of the limited sampling condition or expensive laboratory analysis, which may lead to deterioration of classification performance.To handle this dilemma, a new semi-supervised fault classification strategy is performed in which enhanced active learning is employed to evaluate the value of each unlabeled sample with respect to a specific labeled dataset.Unlabeled samples with large values will serve as supplementary information for the training dataset. In addition,we introduce several reasonable indexes and criteria, and thus human labeling interference is greatly reduced. Finally,the fault classification effectiveness of the proposed method is evaluated using a numerical example and the Tennessee Eastman process.

Fault classification and reconfiguration of distribution ystems using equivalent capacity margin method

This paper investigates the capability of support vector machines （SVM） for prediction of fault classification and the use of the concept of equivalent capacity margin （ECM） for restoration of the power system. The SVM, as a novel type of machine learning based on statistical learning theory, achieves good generalization ability by adopting a structural risk minimization （SRM） induction principle aimed at minimizing a bound on the generalization error of a model rather than the minimization of the error on the training data only. Here, the SVM has been used as a classification. The inputs of the SVM model are power and voltage values. An equation has been developed for the prediction of the fault in the power system based on the developed SVM model. The next steps of this paper are the restoration and reconfiguration by using the ECM concept, the development of a code, and the testing of the results with various load outages, which have been executed for a 12 load system.

Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit

Most heating,ventilation,and air-conditioning(HVAC)systems operate with one or more faults that result in increased energy consumption and that could lead to system failure over time.Today,most building owners are performing reactive maintenance only and may be less concerned or less able to assess the health of the system until catastrophic failure occurs.This is mainly because the building owners do not previously have good tools to detect and diagnose these faults,determine their impact,and act on findings.Commercially available fault detection and diagnostics(FDD)tools have been developed to address this issue and have the potential to reduce equipment downtime,energy costs,maintenance costs,and improve occupant comfort and system reliability.However,many of these tools require an in-depth knowledge of system behavior and thermodynamic principles to interpret the results.In this paper,supervised and semi-supervised machine learning(ML)approaches are applied to datasets collected from an operating system in the field to develop new FDD methods and to help building owners see the value proposition of performing proactive maintenance.The study data was collected from one packaged rooftop unit(RTU)HVAC system running under normal operating conditions at an industrial facility in Connecticut.This paper compares three different approaches for fault classification for a real-time operating RTU using semi-supervised learning,achieving accuracies as high as 95.7%using few-shot learning.

Power Grid Fault Diagnosis Based on Deep Pyramid Convolutional Neural Network

Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.