Few-label learning for fault diagnosis based on contrastive representations

The problem of the wind turbine gearbox fault diagnosis was investigated by employing the support vector machine (SVM), which is optimized by the improved fruit fly intelligent algorithm with decreasing steps. First of all, the fault characteristic value extracted by Hilbert transform envelope is presented. Secondly, the general SVM solution to the wind turbine gearbox fault diagnosis problem is presented, where the improved fruit fly intelligent algorithm is adopted to optimize the performance of the model of the fault detection and diagnosis. Thirdly, the effectiveness of three fault diagnosis models are compared, including the fault detection and diagnosis model by the traditional SVM, its improved model optimized by the partical swarm optimization algorithm, and improved model by the SVM optimized by the proposed approach. By using the proposed optimization algorithm, the accuracy of gearbox fault diagnosis is much better than other two models, which are validated by the extensive simulation results based on practical historical operation data.

Many assessment and detection methods are used to diagnose faults in machines. High accuracy in fault detection and diagnosis can be achieved by using numerical methods with noise-resistant properties. However, to some extent, noise always exists in measured data on real machines, which affects the identification results, especially in the diagnosis of early- stage faults. In view of this situation, a damage assessment method based on blind source separation and dynamic fuzzy neural network (DFNN) is presented to diagnose the early-stage machinery faults in this paper. In the processing of measurement signals, blind source separation is adopted to reduce noise. Then sensitive features of these faults are obtained by extracting low dimensional manifold characteristics from the signals. The model for fault diagnosis is established based on DFNN. Furthermore, on-line computation is accelerated by means of compressed sensing. Numerical vibration signals of ball screw fault modes are processed on the model for mechanical fault diagnosis and the results are in good agreement with the actual condition even at the early stage of fault development. This detection method is very useful in practice and feasible for early-stage fault diagnosis.

With the development of the smart manufacturing, data-driven fault diagnosis has receiving more and more attentions from both academic and engineering fields. As one of the most important data-driven fault diagnosis method, deep learning (DL) has achieved remarkable applications. However, the DL based fault diagnosis methods still have the following two drawbacks: 1) One of the most major branch of deep learning is to construct the deeper structures, however the deep learning models in fault diagnosis is very shadow. 2) As stated by the no-free-lunch theorem, no single model can perform best on every dataset, and the individual deep learning model still suffers from the generalization ability. In this research, a new negative correlation ensemble transfer learning method (NCTE) is proposed. Firstly, the transfer learning based ResNet-50 is proposed to construct a deep learning structure that has 50 layers. Secondly, several fully-connected layers and softmax classifiers are trained cooperatively using negative correlation learning (NCL). Thirdly, the hyper-parameters of the proposed NCTE are determined by cross validation. The proposed NCTE is conducted on the KAT Bearing Dataset, and the prediction accuracy of NCTE is as high as 98.73%. This results show that NCTE has achieved a good results compared with other machine learning and deep learning method.

The bidirectional gated recurrent unit (BiGRU) method based on dissolved gas analysis (DGA) has been studied in the field of power transformer fault diagnosis. However, there are still some shortcomings such as the fuzzy boundaries of DGA data, and the BiGRU parameters are difficult to determine. Therefore, this paper proposes a power transformer fault diagnosis method based on landmark isometric mapping (L-Isomap) and Improved Sand Cat Swarm Optimization (ISCSO) to optimize the BiGRU (ISCSO-BiGRU). Firstly, L-Isomap is used to extract features from DGA feature quantities. In addition, ISCSO is further proposed to optimize the BiGRU parameters to build an optimal diagnosis model based on BiGRU. For the ISCSO, four improvement methods are proposed. The traditional sand cat swarm algorithm is improved using logistic chaotic mapping, the water wave dynamic factor, adaptive weighting, and the golden sine strategy. Then, benchmarking functions are used to test the optimization performance of ISCSO and the four algorithms, and the results show that ISCSO has the best optimization accuracy and convergence speed. Finally, the fault diagnosis method based on L-Isomap and ISCSO-BiGRU is obtained. Using the model for fault diagnosis, the example simulation results show that using L-ISOMP to filter and downscale the model inputs can better improve model performance. The results are compared with the SCSO-BiGRU, WOA-BiGRU, GWO-BiGRU, and PSO-BiGRU fault diagnosis models. The results show that the fault diagnosis rate of ISCSO-BiGRU is 94.8%, which is 11.69%, 10.39%, 7.14%, and 5.9% higher than that of PSO-BiGRU, GWO-BiGRU, WOA-BiGRU, and SCSO-BiGRU, respectively, and validate that the proposed method can effectively improve the fault diagnosis performance of transformers.

Artificial intelligence technology is widely used in mechanical system fault diagnosis as an effective means, but there are few fault samples in practice, which seriously restricts the industrial application of Al diagnosis model to high-precision diagnosis. In order to overcome the lack of fault samples, a fault diagnosis method composed of Gaussian cloud model and domain-invariant features extraction is proposed for expanding fault training samples in this paper. The method include three steps. Firstly, the limited measured samples is obtained by calculating the time-domain feature indexes of original signals. Secondly, the Gauss cloud model is construct based on the measured samples, and perform the forward cloud computing to generate a large amounts of cloud drops as simulated samples. Finally, based on the cross-domain transfer learning framework, the convolutional neural network (CNN) is utilized to extract a large number of domain-invariant features from the measured and simulated samples as the expanded fault samples to train the intelligent fault diagnosis model. The experimental investigation is carried out based on the experimental gear data respectively, and the experimental results show that the proposed method can effectively expand the fault samples to train the fault diagnosis model.

Linear regression methods are commonly used by both researchers and data scientists due to their interpretability and their reduced likelihood of overfitting. However, these methods can still perform poorly if little labeled training data is available. Typical methods used to overcome a lack of labeled training data somehow involve exploiting an outside source of labeled data or large amounts of unlabeled data. This includes areas such as active learning, semi-supervised learning and transfer learning, but in many domains these approaches are not always applicable because they require either a mechanism to label data, large amounts of unlabeled data or additional sources of sufficiently related data. In this paper we explore an alternative, non-data centric approach. We allow the user to guide the learning system through three forms of feature-level guidance which constrain the parameters of the regression function. Such guidance is unlikely to be perfectly accurate, so we derive methods which are robust to some amounts of noise, a property we formally prove for one of our methods.

Developing ladder network for intelligent evaluation system: Case of remaining useful life prediction for centrifugal pumps

Representation learning with deep sparse auto-encoder for multi-task learning

High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.

Structural health monitoring (SHM) is a non-destructive evaluation technique that utilizes sensor data for assessing the condition of civil infrastructure. Sensors in SHM systems may experience faults, which may influence the accuracy, reliability, and performance of SHM systems. The timely detection, isolation, and accommodation of sensor faults in SHM systems has been the focus of sensor fault diagnosis (FD) approaches, which have increasingly been employing artificial intelligence (AI) algorithms due to the effectiveness of AI in sensor FD. However, current AI-based FD approaches require transmitting large amounts of raw sensor data to centralized servers for offline analysis, resulting in inefficiencies as well as computational burdens on centralized servers. This paper introduces a decentralized sensor fault diagnosis (DSFD) approach for wireless SHM systems using Artificial Intelligence of Things (AIoT). In particular, AI-based FD models are embedded into wireless sensor nodes of SHM systems to detect, isolate, and accommodate sensor faults. By embedding the FD models into the wireless sensor nodes, only high-level information, specifically the status of the sensors, is transmitted to centralized servers. As a result, data transmission inefficiencies as well as computational burdens on centralized servers are reduced. The proposed DSFD approach is validated in a controlled laboratory experiment, in which custom- built wireless senor nodes are installed on a test structure that is dynamically excited using a shake table. After training and embedding the AI-based FD models into the custom-built wireless sensor nodes, sensor faults are artificially injected into the sensor data, demonstrating the ability of the DSFD approach to diagnose sensor faults in a decentralized manner. The results of the validation test corroborate the capability of the proposed approach to efficiently ensure the accuracy, reliability, and performance of SHM systems.

Although dissolved gas analysis (DGA) is an effective method for transformer fault diagnosis, problems with the quality and accuracy of DGA characterization datasets often arise in practical industrial applications and face difficulties in adjusting the parameters of fault diagnosis models. To address the above problems, this paper proposes a fault diagnosis model (MD-IQPSO-RF) based on Mahalanobis distance (MD) data cleaning and improved quantum particle swarm (IQPSO) optimization of random forest (RF) parameters. Specifically, the abnormal samples of the DGA dataset are first processed by MD to improve the quality and accuracy of the dataset. Then, the RF parameters were optimized using the IQPSO algorithm to adjust the model parameters in order to improve the diagnostic performance of the RF. Finally, the optimal parameters of RF are output, and the training data are used to train the RF algorithm to construct the MD-IQPSO-RF transformer fault diagnosis model. The experimental results show that the model achieves an average accuracy of 93.631% for fault diagnosis, which is 6.92% higher than the unoptimized RF model. Comparison with other similar methods also achieved good results, which further validated the effectiveness of the fault diagnosis model.

This paper deals with information model for power grid fault diagnosis based on Common Information Model (CIM). Fault diagnosis gains information from topology information and device parameters of primary system grid based on IEC61970 standard and device information of secondary system grid based on IEC 61850. Device information contains information of protection movement wave record and protection configuration. However, the existent CIM can't fully represent power system fault diagnosis information. Thus, it is need to extend CIM. All kinds of information are based on different model, which causes different information standard. In this paper a preliminary study on CIM extensions which is based on power system fault diagnosis, has been proposed to perfect fault information model. On the basis of different standard model, this paper has discussed the theory of coordinating IEC 61850 and IEC61970 standard, and proposed using Web Ontology Language (OWL) based on Extensible Mark-up Language (XML) to the solution of this problem. A fault Information Model is then provided to the fault diagnosis system according to Component Interface Specification (CIS) in IEC61970. After receiving fault information, the fault diagnosis system starts for real-time, on-line fault diagnosis. Fault information model has solved the problem of the deficiency and non-standard of fault diagnosis information, attaining fault diagnosis information integrity and standardization, and making the fault diagnosis result fast and accurate.

Research on fault diagnosis of industrial robots based on generative adversarial network

In the electrical life test, the low voltage circuit breaker may have a variety of faults. At present, that lacks effective fault diagnosis method and monitoring device. To solve the above problem, the method of fault diagnosis and the design of monitoring device are proposed in this paper. The method of fault diagnosis includes the collection of test parameters and the model establishment of fault diagnosis. Based on the fault diagnosis model, the electrical life test monitoring device is designed. The device is used to collect the test data in real time, and analyzed the logic to determine whether the fault occurred during the test. When the fault occurred, the device will automatically take protective measures. In order to improve its intelligence, the intelligent monitoring device is designed based on Device net bus technology. It has been implemented in the Device net control network and has the function of Internet of things. So the real-time monitoring test process of remote network can be realized.

Rolling bearing is a critical component of machinery that has been widely applied in manufacturing, transportation, aerospace, and power and energy industries. The timely and accurate bearing fault detection thus is of vital importance. Computational data-driven deep learning has recently become a prevailing approach for bearing fault detection. Despite the progress of the deep learning approach, the deep learning performance is hinged upon the size of labeled data, the acquisition of which is expensive in actual implementation. Unlabeled data, on the other hand, are inexpensive. In this research, we develop a new semi-supervised learning method built upon the autoencoder to fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance. Compared with the state-of-the-art semi-supervised learning methods, this proposed method can be more conveniently implemented with fewer hyperparameters to be tuned. In this method, a joint loss is established to account for the effects of labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other well-established baseline methods. Specifically, nearly all emulation runs using the proposed methodology can lead to around 2%–5% accuracy increase, indicating its robustness in performance enhancement.