Automatic Fault Diagnosis Research Articles

A new transform discrete wavelet technique based on artificial neural network for induction motor broken rotor bar faults diagnosis

The main objective of this article is to contribute the automatic fault diagnosis of broken rotor bars in three-phase squirrel-cage induction motor using vibration analysis. In fact, two approaches are combined to do so, based on signal processing technique and artificial intelligence technique. The first technique is based on discrete wavelet transform (DWT) to detect the harmonics that characterize this fault, using the Daubechies wavelet vibration analysis according to three axes (X, Y, Z). This application permits having the approximation mode function and the details (recd). To exact choice of reconstruction details which contains the information of the broken rotor bars faults, two statistical studies based on the root mean square values (RMS) and Kurtosis shock factor calculation are carried out for each (recd). The choice of (recd) is conditioned by (RMS) and Kurtosis values as: RMSrecd1 < RMSrecd2 and Kurtosisrecd1 > Kurtosisrecd2. Experimental results showed that (recd1 and recd2) satisfied the condition set for (RMS) and Kurtosis values. At the end of first technique, a spectral envelop of recd1 is adopted to detect the broken rotor bars fault and the second technique based on artificial neural network (ANN) is used to identify the number of broken rotor bars. The characteristics of features used as input variables of ANN are the RMS of recd1 and recd2, and the Kurtosis shock factor of recd1 and recd2. The experimental results demonstrated the high efficiency of the proposed method with rotor broken bars fault classification rate of 98.66%.

System integration for predictive process adjustment and cloud computing-based real-time condition monitoring of vibration sensor signals in automated storage and retrieval systems

As automation and digitalization are being increasingly implemented in industrial applications, manufacturing systems comprising several functions are becoming more complex. Consequently, fault analysis (e.g., fault detection, diagnosis, and prediction) has attracted increased research attention. Investigations involving fault analysis are usually performed using real-time, online, or automated techniques for fault detection or alarming. Conversely, recovery of faulty states to their healthy forms is usually performed manually under offline conditions. However, the development of intelligent systems requires that appropriate feedback be provided automatically, to facilitate faulty-state recovery without the need for manual operator intervention and/or decision-making. To this end, this paper proposes a system integration technique for predictive process adjustment that determines appropriate recovery actions and performs them automatically by analyzing relevant sensor signals pertaining to the current situation of a manufacturing unit via cloud computing and machine learning. The proposed system corresponds to an automated predictive process adjustment module of an automated storage and retrieval system (ASRS). The said integrated module collects and analyzes the temperature and vibration signals of a product transporter using an internet-of-things-based programmable logic controller and cloud computing to identify the current states of the ASRS system. Upon detection of faulty states, the control program identifies corresponding process control variables and controls them to recover the system to its previous no-fault state. The proposed system will facilitate automatic prognostics and health management in complex manufacturing systems by providing automatic fault diagnosis and predictive recovery feedback.

Deep Learning Fault Diagnosis for Spacecraft Attitude Determination and Control

The growing numbers, complexity, and data return of space missions are driving a need for automated fault detection and diagnosis. Traditional fault monitoring techniques possess limited ability to diagnose anomalies, requiring operators to investigate extensive amounts of telemetry to isolate root causes. An important hurdle to automating fault diagnosis for complex subsystems such as attitude determination and control is that interpreting anomalies to determine a root cause is highly contextual and inherently uncertain. This paper presents a method of using one-class support vector machines to train a long short-term memory neural network to diagnose time-varying faults in a simulated CubeSat attitude determination and control subsystem. Using elements of transfer learning, the one-class support vector machines are retrained on nominal flight telemetry, allowing the neural network to diagnose faults on the flight unit. The diagnoses are robust to missing data, false positives, modeling errors, contradicting information, and multiple faults. An application is demonstrated for the LightSail 2 solar sail satellite, where the system succeeds in diagnosing both known and previously unknown attitude determination and control faults.

Intelligent Fault Diagnosis of Aeroengine Sensors Using Improved Pattern Gradient Spectrum Entropy

Timely and effective fault diagnosis of sensors is crucial to enhance the working efficiency and reliability of the aeroengine. A new intelligent fault diagnosis scheme combining improved pattern gradient spectrum entropy (IPGSE) and convolutional neural network (CNN) is proposed in this paper, aiming at the problem of poor fault diagnosis effect and real-time performance when CNN directly processes one-dimensional time series signals of aeroengine. Firstly, raw fault signals are converted into spectral entropy images by introducing pattern gradient spectral entropy (PGSE), which is used as the input of CNN, because of the great advantage of CNN in processing images and the simple and rapid calculation of the modal gradient spectral entropy. The simulation results prove that IPGSE has more stable distinguishing characteristics. Then, we improved PGSE to use particle swarm optimization algorithm to adaptively optimize the influencing parameters (scale factor λ ), so that the obtained spectral entropy graph can better match the CNN. Finally, CNN mode is proposed to classify the spectral entropy diagram. The method is validated with datasets containing different fault types. The experimental results show that this method can be easily applied to the online automatic fault diagnosis of aeroengine control system sensors.

A local knit pattern-based automated fault classification method for the cooling system of the data center

Many automated sound-based fault diagnosis or classification methods have been presented in the literature. A novel automatic fault diagnosis method is presented by using sounds for the cooling system of the data center. A novel feature generator and an iterative feature selector are used together to present an automated data center cooling system (DCCS) fault diagnosing method. A new feature generator is proposed inspired by knitting hence, it is called a local knit pattern (LKP). A multiple pooling based decomposition method is presented as a preprocessor. The LKP generates features from each signal. Iterative neighborhood component analysis (INCA) feature selector selects the most discriminative. Twelve classifiers are calculated in the classification phase. The selected classifiers were achieved greater than 90.0% classification accuracies, and the best-resulted classifier is Quadratic SVM. It reached 96.40% classification accuracy. Results show that new generation automated sound fault diagnosis applications can also be developed as novel sound-based fault detection applications.

Research and Application of Automatic Fault Diagnosis and Isolation Device for Distribution Line

This paper takes the equipment of a specific project as an example to develop an automatic fault diagnosis and isolation device for 10kV overhead line or cable line when a user has grounding and shortcircuit faults, so as to realize fast fault location, isolation and recovery, reduce the power outage time of users, and thus improve the reliability of distribution network. The project takes the 10kV South and North Trunk Lines ‘hand in hand’ power supply network as the research object, and studies the solutions of the automatic fault isolation function and the restoration of power supply, hoping to further improve the level of rapid power recovery, reduce power loss, and improve the reliability, automation and information level of power supply for reference.

Multipoint Optimal Minimum Entropy Deconvolution Adjusted for Automatic Fault Diagnosis of Hoist Bearing

Multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) is a powerful method that can extract the periodic characteristics of signal effectively, but this method needs to evaluate the fault cycle a priori, and moreover, the results obtained in a complex environment are easily affected by noise. These drawbacks reduce the application of MOMEDA in engineering practice greatly. In order to avoid such problems, in this paper, we propose an adaptive fault diagnosis method composed of two parts: fault information integration and extracted feature evaluation. In the first part, a Teager energy spectrum amplitude factor (T‐SAF) is proposed to select the intrinsic mode function (IMF) components decomposed by ensemble empirical mode decomposition (EEMD), and a combined mode function (CMF) is proposed to further reduce the mode mixing. In the second part, the particle swarm optimization (PSO) taking fractal dimension as the objective function is employed to choose the filter length of MOMEDA, and then the feature frequency is extracted by MOMEDA from the reconstructed signal. A cyclic recognition method is proposed to appraise the extracted feature frequency, and the evaluation system based on threshold and weight coefficient removes the wrong feature frequency. Finally, the feasibility of the method is verified by simulation data, experimental signals, and on‐site signals. The results show that the proposed method can effectively identify the bearing state.

A New Interpretable Learning Method for Fault Diagnosis of Rolling Bearings

In modern manufacturing processes, requirements for automatic fault diagnosis have been growing increasingly as it plays a vitally important role in the reliability and safety of industrial facilities. Rolling bearing systems represent a critical part in most of the industrial applications. In view of the strong environmental noise in the working environment of rolling bearing, its vibration signals have nonstationary and nonlinear characteristics, and those features are difficult to be extracted. In this article, we proposed a new intelligent fault diagnosis method for rolling bearing with unlabeled data by using the convolutional neural network (CNN) and fuzzy $C$ -means (FCM) clustering algorithm. CNN is first utilized to automatically extract features from rolling bearing vibration signals. Then, the principal component analysis (PCA) technique is used to reduce the dimension of the extracted features, and the first two principal components are selected as the fault feature vectors. Finally, the FCM algorithm is introduced to cluster those rolling bearing data in the derived feature space and identify the different fault types of rolling bearing. The results indicate that the newly proposed fault diagnosis method can achieve higher accuracy than other existing results in the literature.

Chiller Fault Diagnosis Based on VAE-Enabled Generative Adversarial Networks

Artificial intelligence (AI)-enhanced automated fault diagnosis (AFD) has become increasingly popular for chiller fault diagnosis with promising classification performance. In practice, a sufficient number of fault samples are required by the AI methods in the training phase. However, faulty training samples are generally much more difficult to be collected than normal training samples. Data augmentation is introduced in these scenarios to enhance the training data set with synthetic data. In this study, a variational autoencoder-based conditional Wasserstein GAN with gradient penalty (CWGAN-GP-VAE) is proposed to diagnose various faults for chillers. A detailed comparative study has been conducted with real-world fault data samples to verify the effectiveness and robustness of the proposed methodology. <i>Note to Practitioners</i>&#x2014;This work attacks the fact that faulty training samples are usually much harder to be collected than the normal training samples in the practice of chiller automated fault diagnosis (AFD). Modern supervised learning chiller AFD relies on a sufficient number of faulty training samples to train the classifier. When the number of faulty training samples is insufficient, the conventional AFD methods fail to work. This study proposed a variational autoencoder-based conditional Wasserstein GAN with gradient penalty (CWGAN-GP-VAE) framework for generating synthetic faulty training samples to enrich the training data set for machine learning-based AFD methods. The proposed algorithm has been carefully designed, implemented, and practically proved to be more effective than the existing methods in the literature.

Analysis and Classification of Faults in Switched Reluctance Motors Using Deep Learning Neural Networks

The simple and robust construction, less weight, wide operating speed range, and higher fault tolerance capability of switched reluctance (SR) motor make it a viable contender for the conventional dc and ac machines. The faults at the rotor, winding, stator converters, and sensors lead to overcurrent, increase torque ripples, and sudden breakdown of the system. Thus, it is an urgent requirement to recognize and classify the faults that exist in switched reluctance motors, thereby the reliability, robustness, and widespread utilization of SR motors can be increased. The phases of the SR Motor are excited by using an asymmetric bridgeless resonance converter. This paper proposes an automatic diagnosis and classification of faults using radial basis function neural network (RBFNN). A mathematical model of the SR motor is established to determine the state of the art of fault condition of SR motors. The speed data of SR motor are utilized by RBFNN to generate fault information. Gabor filter is used for preprocessing the input data, and segmentation is achieved using high accurate DCT-DOST transformation. A gray-level co-occurrence matrix optimized with a genetic algorithm is used to extract the features in the speed signal of the motor. A test setup was developed in MATLAB to measure the performances of the RBFNN classifier in real-time. The effectiveness of the simulated fault classification model is verified by comparing the results of the conventional PI controller with several optimized algorithm-based tuned PI controllers.

Intelligent Fault Diagnosis Model for Rotating Machinery Based on Fusion of Sound Signals

The failure of rotating machine elements causes unnecessary downtime of the machine. Fault in the rotating machinery can be identified from noises, vibration signals obtained from sensors. Bearing and shaft are the most important basic rotating machine elements. Detection of fault from vibration signals is widely used method in condition monitoring techniques for diagnosis of machine elements. Fault diagnosis from sound signals is cost effective than vibration signals. Sound signal analysis is not well explored in the field of automated fault diagnosis. Under various simulated fault conditions, the sound signals are obtained by placing microphone near the bearing for different speeds. The features are extracted by using statistical and histogram methods. The best features of sound signals are obtained by decision tree algorithm. The extracted features are used as inputs to the classifier-Artificial Neural Network. The classification accuracy results from statistical and histogram features are obtained and compared.

A deep network solution for intelligent fault detection in analog circuit

Automatic fault diagnosis in analog electronic circuits is one of the interesting and important cases for researchers of this field that has gained substantial improvements in recent decades. Fault detection issue could be transferred into a classification problem. In this paper, a new fault detection method is proposed based on deep Convolution Neural Network (CNN). We used the real part of Power Spectrum Density (PSD) of faulty signals as the input images of CNN. The main reason for this is extracting microstructure features among signals by using PSD which result in a better discrimination amongst wide range of faults. Our method is evaluated by two benchmark circuits. The superior performance of our method is proved by simulation results and compared with other state of arts.

Accurate Bearing Fault Diagnosis under Variable Shaft Speed using Convolutional Neural Networks and Vibration Spectrogram

Predicting bearing faults is an essential task in machine health monitoring because bearings are vital components of rotary machines, especially heavy motor machines. Moreover, indicating the degradation level of bearings will help factories plan maintenance schedules. With advancements in the extraction of useful information from vibration signals, diagnosis of motor failures by maintenance engineers can be gradually replaced by an automatic detection process. Especially, state-of-the-art methods using deep learning have contributed significantly to automatic fault diagnosis. This paper proposes a novel method for diagnosing bearing faults and their degradation level under variable shaft speed. In the proposed method, vibration signals are represented by spectrograms to apply deep learning methods through preprocessing using Short-Time Fourier Transform (STFT). Then, feature extraction and health status classification are performed by a convolutional neural network (CNN), VGG16. According to our various experiments, our proposed method can achieve very high accuracy and robustness for bearing fault diagnosis even under noisy environments.

Novel Fast and Automatic Condition Monitoring Strategy Based on Small Amount of Labeled Data

Signal-based automatic condition monitoring techniques are one of the effective ways to ensure the operational safety of modern industrial systems. Currently, the main challenge is to increase their effectiveness under noisy environment and with limited labeled data. In this article, a novel fast and automatic signal-based fault diagnosis procedure that does not require any kinds of machine learning algorithms is proposed. This procedure is based on the measurement of the similarity in the frequency domain between the collected data and a small amount of labeled reference signals (LRSs). The LRSs are obtained under various known operation conditions using fast Fourier transform (FFT) algorithm. The proposed approach is suitable for a real-time implementation and capable of successfully overcoming the challenge of condition monitoring of rotating machines under noisy environment and with limited labeled data. The merits, fastness, and also robustness against noise of the proposed technique are demonstrated experimentally through different practical applications, as well as compared to state-of-the-art procedures on a database of vibration signals measured under a variety of machine health and working conditions.

Workflow-Aware Automatic Fault Diagnosis for Microservice-Based Applications With Statistics

Microservice architectures bring many benefits, e.g., faster delivery, improved scalability, and greater autonomy, so they are widely adopted to develop and operate Internet-based applications. How to effectively diagnose the faults of applications with lots of dynamic microservices has become a key to guarantee applications' performance and reliability. As a microservice performs various behaviors in different workflows of processing requests, existing approaches often cannot accurately locate the root cause of an application with interactive microservices in a dynamic deployment environment. We propose a workflow-aware automatic fault diagnosis approach for microservice-based applications with statistics. We characterize traces across microservices with calling trees, and then learn trace patterns as baselines. For the faults affecting the workflows of processing requests, we estimate the workflows' anomaly degrees, and then locate the microservices causing anomalies by comparing the difference between current traces and learned baselines with tree edit distance. For performance anomalies causing significantly increased response time, we employ principal component analysis to extract suspicious microservices with large fluctuation in response time. Finally, we evaluate our approach on three typical microservice-based applications with a series of experiments. The results show that our approach can accurately locate the microservices causing anomalies.

Maintenance of recovery boilers from VLCC shipboard

The integrated maintenance and diagnosis system is intended for the measurement, monitoring, diagnosis, prediction and analysis of the main technical and functional parameters of a mechanical plant for its safe operation. Various software versions are implemented on modern ships that can ensure constant and efficient surveillance of all systems. These integrated systems of maintenance can focus on a category of aggregates and can prevent a great part of the defects that result from the incorrect exploitation of the respective aggregate or the lack of ensuring an efficient maintenance process. Integrated automatic diagnostics systems for onboard installations are the most efficient means of operation used for a wide range of applications. Also, integrated systems for automatic fault diagnosis - ISAFD is intended for measuring, monitoring and analyzing the technical parameters of machines used in the energy, chemical, metallurgical, food, construction or naval.

Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions

Automatic and reliable fault diagnosis of rotating machinery cross working conditions is of practical importance. For this purpose, ensemble transfer convolutional neural networks (CNNs) driven by multi-channel signals are proposed in this paper. Firstly, a series of source CNNs modified with stochastic pooling and Leaky rectified linear unit (LReLU) are pre-trained using multi-channel signals. Secondly, the learned parameter knowledge of each individual source CNN is transferred to initialize the corresponding target CNN which is then fine-tuned by a few target training samples. Finally, a new decision fusion strategy is designed to flexibly fuse each individual target CNN to obtain the comprehensive result. The proposed method is used to analyze multi-channel signals measured from rotating machinery. The comparison result shows the superiorities of the proposed method over the existing deep transfer learning methods.

Hybrid model for fault detection and diagnosis in an industrial distillation column

Abstract The present work describes a method of automatic fault detection and identification based on a hybrid model (HM): First Principles – Neural Network. The FPM can simulate a wide range of situations while the NN corrects the model output using information from the historical data of the process. Operating conditions corresponding to different types of faults were simulated with the HM and saved with their description in a process state library. To detect a fault, the online measured data was compared with that corresponding to the operation under normal conditions. If a significant deviation was detected, the current state was compared with all the states stored in the process state library and it was identified as the one at the shortest distance. The method was tested with real data from a methanol-water industrial distillation column. During the studied period of operation of the plant, two faults were identified and reported. The proposed method was able to identify such failures more effectively than an equivalent model of first principles. The results obtained show that the proposed method has a great potential to be used in the automatic diagnosis of faults in refining and petrochemical processes.

Automatic Fault Diagnosis of Infrared Insulator Images Based on Image Instance Segmentation and Temperature Analysis

As an onsite condition monitoring method, an infrared inspection can help to discover and analyze abnormal temperature increases in power equipment. For improving the efficiency of the onsite diagnosis of insulators in substations, this article proposes an automatic diagnosis method using instance segmentation and temperature analysis of infrared insulator images. For developing this method, thousands of infrared images from field inspection databases were collected to establish an annotated data set of insulator images. With the aid of the Mask R-convolutional neural network (CNN), it was possible to extract multiple insulators automatically in the infrared images. Transfer learning, as well as the dynamic learning rate algorithm, were then employed to realize the training process of Mask R-CNN with the annotated image data set. The result of the testing experiment showed that the mean Average Precision (mAP) of the model is 0.77, and the frame per second (FPS) is 5.07, which indicated great identification accuracy and computing speed of the proposed model. Next, function fitting was realized to extract the temperature distribution of each insulator. Finally, to evaluate the condition of each insulator, rules, which are based on the related standards, were established using machine language. This is the first time that the machine could independently realize fault analysis of multiple insulators in the infrared images, which is a great attempt to adapt the development of the Internet of Things and the tendency of predictive maintenance. Moreover, because of the universality of the model algorithm used, automatic infrared fault diagnosis for other power equipment could also be performed in a similar manner, which has significant potential applicability in the area of power equipment diagnosis.

Design and implementation of automatic fault diagnosis system for wind turbine

Operation of wind turbines under fault state will directly affect the power output efficiency of wind farms. This paper proposes a new automatic fault diagnosis method for wind turbines. A fault diagnosis system framework is constructed and data of vibration status of wind turbines collected is processed and used for fault diagnosis. Firstly, wavelet coefficients are obtained using a discrete wavelet transform (DWT) for vibration acceleration signals collected from wind turbines. Then, the wavelet coefficients are sequentially subjected to phase space reconstruction (PSR) and singular value decomposition (SVD) to extract the fault features. Finally, an extreme learning machine (ELM) is used to classify the faults. Experimental results show that the proposed method is more effective and accurate than other fault diagnosis methods for wind turbines, such as support vector machine (SVM) and multiscale convolutional neural network (MSCNN).