Data-driven Fault Diagnosis Method Research Articles

A novel adversarial transfer learning in deep convolutional neural network for intelligent diagnosis of gas‐insulated switchgear insulation defect

Recently, numerous data-driven fault diagnosis methods have been developed, and the tasks involving the same distribution of training and test data have been well solved. However, considering the particularity of gas-insulated switchgear (GIS), collecting massive data, especially with the same distribution, is difficult. Therefore, existing fault diagnosis methods hardly achieve satisfactory insulation defect diagnosis with small datasets. Aiming at solving this problem, a novel domain adversarial transfer convolutional neural network (DATCNN) is proposed, realising the diagnosis of GIS insulation defects on small samples. First, a residual CNN is built to learn feature representations from the source and target domains. Second, the domain adversarial training strategy is used for feature transfer, where a conditional adversarial mechanism is introduced, and the joint distribution of features and labels is improved to a random linear combination, which realises the simultaneous adaptation of features and labels. Finally, the Nesterov accelerated gradient descent optimisation algorithm is used to speed up the gradient convergence. DATCNN has 99.15% and ≥89.5% diagnosis accuracy for GIS insulation defects in the laboratory and on-site, respectively. Comprehensive experiment results show the effectiveness and superiority of the proposed method in diagnosing GIS insulation defects with small samples.

Data-driven fault diagnosis for wind turbines using modified multiscale fluctuation dispersion entropy and cosine pairwise-constrained supervised manifold mapping

Condition monitoring and fault diagnosis of wind turbines is an attractive yet challenging task. This paper presents a novel data-driven fault diagnosis scheme for wind turbines, using refined time-shift multiscale fluctuation-based dispersion entropy (RTSMFDE) and cosine pairwise-constrained supervised manifold mapping (CPCSMM). The developed RTSMFDE can improve multiscale dispersion entropy in complexity measurement of time series, by employing the refined time-shift analysis approach. Moreover, the proposed CPCSMM combines cosine distance metric, supervised theory and sparse global manifold structure, to obtain the most important features, resulting in a low dimensional representation. In this fault diagnosis scheme, a high-dimensional fault feature set is first constructed using RTSMFDE. Then, sensitive features are extracted using CPCSMM. Finally, the low-dimensional feature set is fed to a beetle antennae search-based support vector machine for fault identification. Simulation experiments and wind turbine fault diagnosis experiments were used, to show that the proposed RTSMFDE can comprehensively mine the wind turbine features and outperforms the existing state-of-the-art entropy methods. The visualization results and classification effects of the proposed CPCSMM approach are better than existing unsupervised and supervised dimensionality reduction methods. The proposed data-driven fault diagnosis method can effectively and accurately identify multi-faults and outperforms existing fault diagnosis techniques.

An Online Data-Driven Fault Diagnosis Method for Air Handling Units by Rule and Convolutional Neural Networks.

The stable operation of air handling units (AHU) is critical to ensure high efficiency and to extend the lifetime of the heating, ventilation, and air conditioning (HVAC) systems of buildings. In this paper, an online data-driven diagnosis method for AHU in an HVAC system is proposed and elaborated. The rule-based method can roughly detect the sensor condition by setting threshold values according to prior experience. Then, an efficient feature selection method using 1D convolutional neural networks (CNNs) is proposed for fault diagnosis of AHU in HVAC systems according to the system’s historical data obtained from the building management system. The new framework combines the rule-based method and CNNs-based method (RACNN) for sensor fault and complicated fault. The fault type of AHU can be accurately identified via the offline test results with an accuracy of 99.15% and fast online detection within 2 min. In the lab, the proposed RACNN method was validated on a real AHU system. The experimental results show that the proposed RACNN improves the performance of fault diagnosis.

A multi-rate sampling data fusion method for fault diagnosis and its industrial applications

The multi-sensor data fusion based data-driven fault diagnosis method is a promising approach to detect faults of complex systems. However, in the actual industrial environment, the sampling rate of different sensors is often inconsistent. In order to apply this kind of data to fault diagnosis, the traditional methods are to preprocess it and convert it into single sampling rate data. However, these methods are all machine learning methods, which rely on manual feature extraction. To the best of our knowledge, few works have used deep learning (DL) methods to solve this problem. To fill this gap, a novel multi-rate sampling data fusion method for fault diagnosis is proposed in this paper. In the proposed method, signals with different sampling rates are fused. First, a convolutional neural network (CNN) is adopted to learn features from raw data automatically. Then, a long short-term memory (LSTM) network is utilized to mine the time correlation in extracted features and encode the temporal information. The methodology is validated on a public experimental dataset and data from a real industrial scenario. The proposed method is compared with some state-of-the-art machine learning (ML) and DL methods, the results show that the proposed method can distinguish different conditions satisfactorily and has the best diagnostic accuracy among all comparison methods.

A deep transfer learning method based on stacked autoencoder for cross-domain fault diagnosis

In the actual industrial process, the distribution of historical training data and online testing data is always different due to the switching of operating modes and changes in climate conditions. At this time, the performance of traditional data-driven fault diagnosis methods based on the assumption that historical training data and online testing data follow the same distribution will degrade. Therefore, how to ensure the reliability of the fault diagnosis method for the distribution distortion is necessary yet challenge. In this paper, a cross-domain fault diagnosis method based on transferred stacked autoencoder is proposed. In detail, a stacked autoencoder is firstly used to extract features of a large amount of source domain data, and the features are classified to establish the source domain model. Then, a small amount of target domain data is introduced to fine-tune the source domain model to achieve domain adaptation. The effectiveness and superiority of the proposed deep transfer method was demonstrated through wind turbine system experiment and pump truck experiment. In addition, this paper also discusses the number of layers of the stacked autoencoder and model transfer strategies in detail to help practitioners understand the proposed method in practice.

A knowledge-guided and data-driven method for building HVAC systems fault diagnosis

Fault diagnosis is crucial for energy conversation of building HVAC systems. Generally, knowledge-driven fault diagnosis methods have good interpretability, whereas data-driven fault diagnosis methods have high diagnosis accuracy. With the aim of integrating the advantages of both types of methods, this paper proposes a knowledge-guided and data-driven fault diagnosis method. The proposed method develops a diagnostic Bayesian network (DBN) based on both expert knowledge and operational data. A probabilistic framework is developed for determining the prior DBN structures based on expert knowledge. An improved genetic algorithm-based approach is raised for further optimizing the DBN structures based on the operational data. Local casual graphs are generated from the DBN for visually interpreting the fault action mechanisms. Experts can evaluate the reliability of the diagnosis results using the local casual graphs, and then make reliable decisions. The proposed method is evaluated using the experimental data from the ASHARE Project 1312-RP. The results show that the performance of the proposed method is promising. Six typical faults are interpreted by the local casual graphs. It is demonstrated that the local casual graphs can effectively reveal the action mechanisms behind the six faults.

Data-driven fault diagnosis method based on the conversion of erosion operation signals into images and convolutional neural network

In the industrial process, the safety and reliability of the mechanical system determine the quality of the product, and whether small faults can be diagnosed in time is the key to ensuring the safe operation of the system and restraining the deterioration of faults. In recent years, the data-driven fault diagnosis has attracted widespread attention in academia. However, the traditional data-driven fault diagnosis methods rely on the features extracted from expert systems, so that the effect of fault diagnosis is entirely reliant on how well the expert system can extract the features. This paper proposes a new fault diagnosis method based on AlexNet Convolutional neural network (CNN) from a data-driven perspective. Firstly, a new method for converting time-domain vibration signal into RGB image based on erosion operation (EOSTI) is proposed. Initially converted three-dimensional (3-D) images have relatively close structural elements and are difficult to identify. For such defects, the target separated RGB image is generated. Secondly, explore the classification accuracy of AlexNet to make it more suitable for fault classification of different bearing datasets. Finally, the proposed method which is tested on two datasets, including coal washing machine dataset, maintenance fault dataset, has achieved prediction accuracy of 99.43 % and 99.67 %, respectively. The results have been compared with other methods. The comparisons show the effectiveness and accuracy of the proposed approach. The result shows that this method is feasible in engineering practice.

Data-Driven Fault Diagnosis Using Deep Canonical Variate Analysis and Fisher Discriminant Analysis

In this article, a novel data-driven fault diagnosis method by combining deep canonical variate analysis and Fisher discriminant analysis (DCVA-FDA) is proposed for complex industrial processes. Inspired by the recently developed deep canonical correlation analysis, a new nonlinear canonical variate analysis (CVA) called DCVA is first developed by incorporating deep neural networks into CVA. Based on DCVA, a residual generator is designed for the fault diagnosis process. FDA is applied in the feature space spanned by residual vectors. Then, a Bayesian inference classifier is performed in the reduced dimensional space of FDA to label the class of process data. A continuous stirred-tank reactor and an industrial benchmark of the Tennessee Eastman process are carried out to test the performance of DCVA-FDA fault diagnosis. The experimental results demonstrate that the proposed DCVA-FDA fault diagnosis is able to significantly improve the fault diagnosis performance when compared to other methods also examined in this article.

A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network

Fault diagnosis is important to ensure the safety and efficience of mechanical equipment. In recent years, data-driven fault diagnosis methods have received extensive attention and research from many scholars. Different from the traditional fault feature extraction methods that rely on expert experience, this paper proposes a feature extraction method based on deep learning (DL). In order to meet the needs of neural networks for the amount of data, data augmentation is emploied to increase the amount of original data. Then, a novel signal-to-image mapping (STIM) is proposed to convert the one-dimensional vibration signals into two-dimensional grey images, which greatly reduce the human involvement. Finally, a convolutional neural network (CNN) model is established to extract fault features from grey images and realize fault classification. The learning process of the CNN model is analyzed and two different bearing experiment datasets are used to verify the effectiveness of the proposed method.

Data-driven fault diagnosis method for the safe and stable operation of solid oxide fuel cells system

Solid oxide fuel cell system is complex with multiple variables strongly coupled. Once a fault occurs, if it cannot be found in time, the initial minor fault may slowly evolve and spread to subsequent components. Therefore, fault diagnosis is a promising approach to guarantee the stability of the system. In this paper, the impact of air leakage and fuel starvation is investigated. To diagnose the two types of faults, a novel data-driven online fault diagnosis method based on principal component analysis and support vector machine is developed. Data comes from the entire stage of the solid oxide fuel cell system experiment. The results show that the proposed method can effectively identify the air leakage and fuel starvation fault in real time. Through comparison with traditional machine learning methods, this method shows higher accuracy and better generalization performance. Moreover, it combines prior knowledge and statistical characteristics to extract effective features, thereby reducing the calculation burden. Furthermore, with proper modifications, the proposed method can be extended to other types of solid oxide fuel cell system faults, which is significant in enhancing the reliability of the system.

A novel semi-supervised data-driven method for chiller fault diagnosis with unlabeled data

In practical chiller systems, applying efficient fault diagnosis techniques can significantly reduce energy consumption and improve energy efficiency of buildings. The success of the existing methods for fault diagnosis of chillers relies on the condition that sufficient labeled data are available for training. However, label acquisition is laborious and costly in practice. Usually, the number of labeled data is limited and most data available are unlabeled. Most of the existing methods cannot exploit the information contained in unlabeled data, which significantly limits the improvement of fault diagnosis performance in chiller systems. To make effective use of unlabeled data to further improve fault diagnosis performance and reduce the dependency on labeled data, we proposed a novel semi-supervised data-driven fault diagnosis method for chiller systems based on the semi-generative adversarial network, which incorporates both unlabeled and labeled data into learning process. The semi-generative adversarial network can learn the information of data distribution from unlabeled data and this information can help to significantly improve the diagnostic performance. Experimental results demonstrate the effectiveness of the proposed method. Under the scenario that there are only 80 labeled samples and 16,000 unlabeled samples, the proposed method can improve the diagnostic accuracy to 84%, while the supervised baseline methods only reach the accuracy of 65% at most. Besides, compared with the supervised learning method based on the neural network, the proposed semi-supervised method can reduce the minimal required number of labeled samples by about 60% when there are enough unlabeled samples.

Discriminative Dictionary Learning-Based Sparse Classification Framework for Data-Driven Machinery Fault Diagnosis

Data-driven machinery fault diagnosis is important for smart industrial systems to guarantee safety and reliability. However, the conventional data-driven fault diagnosis methods rely on the expert-designed features, which greatly affect the diagnosis performances. Inspired by the sparse representation-based classification (SRC) methods which can learn discriminative sparse features adaptively, we propose a novel discriminative dictionary learning based sparse classification (DDL-SC) framework for data-driven machinery fault diagnosis. The DDL-SC framework can jointly learn a discriminative dictionary for sparse representation and an optimal linear classifier for pattern recognition, which bridges the gaps between two separate processes, dictionary learning and classifier training in traditional SRC methods. In the learning stage, to enhance the discriminability of dictionary learning, we introduce the discriminative sparse code error along with the reconstruction error and classification error into the optimization objective. In the recognition stage, we employ sparse codes of testing signals with respect to the learned discriminative dictionary as inputs of the learned classifier, and promote the recognition performance by connecting a binary hard thresholding operator with the classifier predictions. The effectiveness of DDL-SC is evaluated on the planetary bearing fault dataset and gearbox fault dataset, indicating that DDL-SC yields the recognition accuracies of 99.73% and 99.41%, respectively. Besides, the comparative studies prove the superiority of DDL-SC over several state-of-the-art methods for data-driven machinery fault diagnosis.

Data‐driven design of fault diagnosis for three‐phase PWM rectifier using random forests technique with transient synthetic features

A three-phase pulse-width modulation (PWM) rectifier can usually maintain operation when open-circuit faults occur in insulated-gate bipolar transistors (IGBTs), which will lead the system to be unstable and unsafe. Aiming at this problem, based on random forests with transient synthetic features, a data-driven online fault diagnosis method is proposed to locate the open-circuit faults of IGBTs timely and effectively in this study. Firstly, by analysing the open-circuit fault features of IGBTs in the three-phase PWM rectifier, it is found that the occurrence of the fault features is related to the fault location and time, and the fault features do not always appear immediately with the occurrence of the fault. Secondly, different data-driven fault diagnosis methods are compared and evaluated, the performance of random forests algorithm is better than that of support vector machine or artificial neural networks. Meanwhile, the accuracy of fault diagnosis classifier trained by transient synthetic features is higher than that trained by original features. Also, the random forests fault diagnosis classifier trained by multiplicative features is the best with fault diagnosis accuracy can reach 98.32%. Finally, the online fault diagnosis experiments are carried out and the results demonstrate the effectiveness of the proposed method, which can accurately locate the open-circuit faults in IGBTs while ensuring system safety.

Probabilistic Information-Theoretic Discriminant Analysis for Industrial Label-Noise Fault Diagnosis

Fault diagnosis, which aims to identify the root cause of the observed abnormality, is essential for the control and optimization of industrial processes. Many existing data-driven fault diagnosis methods require all the training samples to be correctly labeled. However, label noise is ubiquitous in practical industrial data, and the performance of these methods may be severely affected. In this article, we address the fault diagnosis issue in the presence of label noise. A probabilistic information-theoretic discriminant analysis (PITDA) algorithm is proposed, which consists of two iterative steps. First, a probabilistic feature extractor based on information theory is presented to extract discriminative features from industrial data. Second, a robust mixture discriminant analysis method is applied to build label noise-tolerant classifier in the feature space and produce the probability used in the first step. Iteration of these two steps gives the PITDA algorithm, which is able to perform fault diagnosis for complex and high-dimensional industrial data in the presence of label noise. Experimental results on synthetic data, Tennessee Eastman benchmark process, and a real-world air compressor working process demonstrate the effectiveness and advantages of the proposed algorithm.

A comparison study of basic data-driven fault diagnosis methods for variable refrigerant flow system

HVAC systems occupy a large part of the building’s energy consumption. The development of fault detection and diagnosis (FDD) techniques for HVAC system is becoming increasingly essential for building energy saving. The present paper proposes a comparison study on the basic data-driven methods for variable refrigerant flow (VRF) system fault diagnosis. And five widely used data-driven methods were analyzed, which were decision tree (DT), support vector machines (SVM), clustering (CL), shallow neural networks (SNN), and deep neural networks (DNN). The six common types of fault data in VRF system and three evaluation indexes were used to compare the performance of the proposed five FDD methods in single fault and multiple faults. Results indicate that the single fault diagnosis performance of all methods is better than multiple fault diagnosis. The performances of DNN, SNN, and SVM are better than CART and CL no matter single fault or multiple fault diagnosis. Among them, we believe that the SVM method is preferred for single fault diagnosis and the DNN method is preferred for multiple fault diagnosis. And the performance of method CL is the worst, especially in the case of multiple fault classification, the accuracy is only about 48%. The study results are dedicated to providing a reference for subsequent research in FDD of VRF system. Some important remarks are finally concluded in this paper.

Intelligent ball screw fault diagnosis using a deep domain adaptation methodology

Intelligent data-driven fault diagnosis methods have been successfully developed in the recent years. However, as one of the most important machines in the industries, the ball screw health monitoring problem has received less attention, due to the complex operating patterns and sophisticated mechanical structures. In practice, the working conditions of the ball screws usually change, that further makes the fault diagnosis problem more challenging since the data distributions are not the same. In order to address this issue, a deep learning-based domain adaptation method is proposed for the cross-domain ball screw fault diagnosis problem. The deep convolutional neural network is adopted for feature extraction and health condition classification. The maximum mean discrepancy metric is proposed to measure and optimize the data distributions of different operating conditions. A data segmentation method which is specially designed for the ball screw is further integrated. The experiments on the real ball screw condition monitoring data are carried out for validation. The results indicate the proposed approach is promising for the cross-domain diagnostic tasks of the ball screw in the real industries.

Modeling of Coal Mill System Used for Fault Simulation

Monitoring and diagnosis of coal mill systems are critical to the security operation of power plants. The traditional data-driven fault diagnosis methods often result in low fault recognition rate or even misjudgment due to the imbalance between fault data samples and normal data samples. In order to obtain massive fault sample data effectively, based on the analysis of primary air system, grinding mechanism and energy conversion process, a dynamic model of the coal mill system which can be used for fault simulation is established. Then, according to the mechanism of various faults, three types of faults (i.e., coal interruption, coal blockage and coal self-ignition) are simulated through the modification of model parameters. The simulation shows that the dynamic characteristic of the model is consistent with the actual object, the relative error of each output variable is less than 2.53%, and the total average relative error of all outputs is about 1.2%. The model has enough accuracy and adaptability for fault simulation, and the problem of massive fault samples acquisition can be effectively solved by the proposed method.

Data-Driven Fault Diagnosis Method Based on Second-Order Time-Reassigned Multisynchrosqueezing Transform and Evenly Mini-Batch Training

To promote the progress of fault diagnosis system, this study proposes an intelligent and effective fault diagnosis algorithm based on data-driven. Firstly, we propose a new time-frequency analysis method named second-order time-reassigned multisynchrosqueezing transform (STMSST) based on Gaussian-modulated linear group delay (GLGD) model to deal with the vibration signals of fault object for obtaining time-frequency images with high resolution. Then, an improved training method named evenly mini-batch training method is combined with convolutional neural network (CNN) to train and learn fault features from those obtained time-frequency images. Further, the proposed fault diagnosis algorithm is tested on the Case Western Reserve University (CWRU) bearing dataset and the Machinery Failure Prevention Technology (MFPT) Society dataset, respectively, and the experimental results indicate that the feature representation and training effect in our method is superior to state-of-the-art fault diagnosis methods. Finally, the proposed method is applied on the loudspeaker pure-tone detection dataset, which achieves the loudspeaker anomaly diagnosis, and the diagnosis result has verified that the method can meet the needs of practical engineering.

An Empirical Analysis about the Generalization Performance of Data-driven Fault Diagnosis Methods

An Empirical Analysis about the Generalization Performance of Data-driven Fault Diagnosis Methods

Enhancing Intelligent Cross-Domain Fault Diagnosis Performance on Rotating Machines with Noisy Health Labels

In the recent years, the intelligent data-driven fault diagnosis methods on the rotating machines have been popularly developed. Especially, deep learning algorithms have been adopted in several studies and promising results have been obtained. However, the cross-domain fault diagnostic problem still remains a challenging issue, where the training and testing data are collected from different operating conditions of the machine. To bridge the domain gap in the training and testing data and increase the model generalization ability, a domain adaptation approach is proposed in this paper within the deep learning framework. Multiple convolutional operations are employed for automatic feature extraction. The maximum mean discrepancy is used to optimize the distributions of the learned features for accurate diagnosis. To further enhance the model generalization ability, the health condition labels of the data are injected with additional noise during model training. Experiments on a bearing fault diagnosis dataset are carried out for validation. The results show that, compared with the popular transfer learning algorithms, the proposed method with noisy health labels can successfully improve the cross-domain diagnosis performance on rotating machines.