Existing self-supervised multivariate time series anomaly detection methods struggle with interference among variables during reconstruction. They also tend to miss capturing critical anomaly information, resulting in unsatisfactory performance, especially in scenarios with strong mechanistic contexts. To this end, we propose a targeted anomaly detection algorithm called inference stacked recurrent autoencoder (ISRAE). Its key contribution lies in the design of a specific inference kernel, derived from specialist knowledge, which captures the strong mechanistic relationships among variables. This kernel is then fused with the multidimensional anomalies predicted by the SRAE, which mitigates interference among variables through the stacking technique. Furthermore, a novel differential constraint is introduced into the loss function, which not only highlights anomaly reconstruction errors, but also smooths the reconstructions, enhancing overall detection performance. Comprehensive comparison experiments and ablation studies show that ISRAE achieves superior anomaly detection performance under strong mechanistic contexts and highlight the importance of each key module in ISRAE.

Rapid developments of offshore wind industry offer a strong demand opportunity for offshore wind turbine remote diagnosis. As offshore wind turbines are often located in harsh and communication-constrained environments, the collection and transmission of data is severely restricted, which poses a serious challenge to the conventional centralized diagnostic paradigm that relies on data aggregation. To address this challenge, we propose a novel event-triggered federated learning framework for decentralized fault diagnosis of offshore wind turbines. Specifically, federated learning is first employed to learn decentralized local knowledge from geographically distributed offshore wind turbines, so that the communication objects are transformed from massive raw data into learned parameters, thereby relieving the communication burden. Then, we design an event-triggered communication mechanism and incorporate it into federated learning, the core of which is to modify the communication requirement from uploading all trained parameters periodically to communicating only when necessary. The proposed framework is verified by a real-world offshore wind turbine dataset from six large wind farms in China. An ablation study shows that the proposed framework can maintain high diagnostic performance while reducing communication costs. A comprehensive comparison based on three benchmark models demonstrates that the proposed framework can reduce the communication burden by up to 63% while obtaining better diagnostic performance.Note to Practitioners—This study was motivated by the problem of collaborative diagnosis of distributed offshore wind turbines under the constraints of data privacy and communication overhead. The method employs a federated learning-based fault diagnosis framework, which permits to obtain global fault diagnosis knowledge without aggregating raw data scattered in each end device, thus avoids the risk of data leakage. Moreover, a strategy integrating parameter variation and accuracy gain is designed to avoid communication redundancy for collaborative training. The practicability and superiority of our proposed framework is demonstrated using extensive experiments against actual industrial data collected from six offshore wind farms.

Despite the widespread use of Fourier transform (FT) networks and generative adversarial networks (GANs) in audio signal processing, their practical effectiveness in unsupervised offline systems has not yet reached a fully satisfying level. Accumulating substantial experience in recent years, this article showcases how to construct an optimized, efficient music generation system. In the proposed system, the short-time Fourier transform is employed to divide a long music signal into equally sized short melodic segments. Each short melodic segment undergoes FT, and a nonautoregressive parallel WaveGAN system is trained by jointly optimizing multiresolution spectrograms and adversarial loss functions. This approach effectively captures the time–frequency distribution of real music waveforms. In essence, the proposed music generation system is a self-feedback unsupervised model relying on specific melody and note model pruning techniques. To further refine the music evaluation mechanism, in addition to conducting data analysis on the output melodies, subjective evaluation mechanisms are also incorporated.

Non-rechargeable batteries remain as the main source of energy for small systems, owing to their unique advantages in energy density, safety, reliability and sustainability. Accurate prediction of the remaining useful life of the battery is not only beneficial to maintenance and production safety, but also can be regarded as a starting point for possible secondary life applications. In this study, an interactive attention sequence-to-sequence network is proposed for the remaining useful life prediction of the non-rechargeable batteries. The proposed approach can effectively extract the degenerate information of each variable-length sequence and dynamically weight the sequence features of different dimensions. For illustration, a case of primary battery dataset collected from the power supply system of 139 vibration sensors is utilized. The extensive experiments verify the effectiveness of the proposed approach.

Privacy protection as a major concern of the industrial big data enabling entities makes the massive safety-critical operation data of a wind turbine unable to exert its great value because of the threat of privacy leakage. How to improve the diagnostic accuracy of decentralized machines without data transfer remains an open issue; especially these machines are almost accompanied by skewed class distribution in the real industries. In this study, a class-imbalanced privacy-preserving federated learning framework for the fault diagnosis of a decentralized wind turbine is proposed. Specifically, a biometric authentication technique is first employed to ensure that only legitimate entities can access private data and defend against malicious attacks. Then, the federated learning with two privacy-enhancing techniques enables high potential privacy and security in low-trust systems. Then, a solely gradient-based self-monitor scheme is integrated to acknowledge the global imbalance information for class-imbalanced fault diagnosis. We leverage a real-world industrial wind turbine dataset to verify the effectiveness of the proposed framework. By comparison with five state-of-the-art approaches and two nonparametric tests, the superiority of the proposed framework in imbalanced classification is ascertained. An ablation study indicates that the proposed framework can maintain high diagnostic performance while enhancing privacy protection.

Data-driven fault diagnosis and classification for wind turbine systems have received much attention due to a large amount of data available recorded by supervisory control and data acquisition (SCADA) systems and smart meters. It is of interest but challenging to diagnose and classify multiple faults occurring simultaneously in a system monitored. In this study, a data-driven and supervised machine learning-based fault diagnosis and classification algorithm is addressed by the combination and consolidation among Hilbert-Huang Transformation (HHT), Multi-Linear Principal Component Analysis (MPCA), and Support Vector Machine (SVM) to enhance the feasibility and capability of fault diagnosis and classification for systems subjected to multiple faults. The algorithm proposed is applied to the 4.8 MW wind turbine benchmark model, where multiple actuator faults are taken into considerations. The effectiveness of the methodology is demonstrated by using intensive simulations and comparison studies.

In order to improve the classification accuracy of analog circuit failure modes, this paper proposes an ultra-lightweight subspace attention module (ULSAM) classification method, which combines lightweight (reducing parameters) with attention mechanism to improve convolutional neural networks (CNN) feature extraction and classification performance. This article uses depthwise separable (DWS) convolution, by decomposing the standard convolution into depthwise convolution (feature extraction) and pointwise convolution (feature aggregation). Meanwhile, the attention mechanism is applied, only one 1×1 filter is used after depthwise convolution, which can compute efficient interaction of cross-channel information, and uses the linear relationship between feature maps to avoid the use of multi-layer perceptron (MLP). The application of the failure modes of analog circuits shows that the proposed ULSAM method can realize the pattern classification of analog circuit faults more quickly and accurately.

In order to solve the problems of low prediction accuracy and long training time that are common in the existing analog circuit fault diagnosis models, this paper proposes a new combination of wavelet packet feature extraction, singular value decomposition(SVD) and dimensionality reduction and support vector machine(SVM) classification method. This method selects wavelet packet analysis with higher accuracy than traditional wavelet analysis, extracts features of analog circuit fault data, and normalizes the extracted feature data; then uses singular value decomposition method to perform fault data matrix decompose to achieve the purpose of dimensionality reduction. The size of the singular value obtained by decomposition reflects the characteristics of the fault information. Selecting the matrix with the largest singular value as a sample can express the fault characteristics more accurately and efficiently; finally, use the support vector machine to decompose the fault after the singular value. The matrix is trained and classified, so as to realize the fault diagnosis of the analog circuit. The simulation experiment results show that, compared with the current diagnosis models such as BAGRNN, the SVD model proposed in this paper improves the fault diagnosis rate of analog circuits, effectively reduces the amount of matrix calculation, and speeds up the diagnosis.

Clustering is able to find out implicit data distribution and is especially useful in data driven machine learning. Density based clustering has an attractive property of detecting clusters of arbitrary structures. The density peak algorithm makes use of two assumptions to detect cluster centers and then groups the other data. This approach is simple to implement and shown to be promising in many experiments. However, we find its clustering results are dependent on density kernel types and kernel parameters, and density difference across clusters also influences the results significantly. In this paper, we make a detailed study of the density peak algorithm and attribute the problems to the local density criterion in detecting cluster centers. We then use density normalization to relieve the influence of the problems, and present a density kernel to further improve clustering results. We conduct experiments with different types of datasets to demonstrate the performance of our approach.

Data-driven fault diagnosis and classification for wind turbine systems have received much attention due to a large amount of data available recorded by supervisory control and data acquisition (SCADA) system and smart meters. It is challenging to diagnose and classify multiple faults occurring simultaneously in a system monitored. In this study, a data-driven fault diagnosis and classification algorithm is addressed by integrating fast Fourier transform (FFT) and multi-linear principal component analysis (MPCA) in order to enhance the capability of fault diagnosis and classification for systems subjected to multiple faults. The algorithm proposed is applied to a 4.8-MW wind turbine benchmark system, where multiple actuator faults are taken into accounts. The effectiveness of the algorithm is demonstrated by intensive simulations and comparison studies.

In this paper, a deep learning fault detection approach is proposed based on the convolutional neural network in order to cope with one class of faults in wind turbine systems. Fault detection is very vital in nowadays industries due to the fact that instantly detection can prevent waste of cost and time. Deep learning as one of the powerful approaches in machine learning is a promising method to identify and classify the intrigued problems, which are hard to solve by classical methods. In this case, less than 5% performance reduction in generator torque along with sensor noise, which is challenging to identify by an operator or classical diagnosis methods is studied. The proposed algorithm, which is evolved from convolutional neural network idea, is evaluated in simulation based on a 4.8 MW wind turbine benchmark and the accuracy of the results confirms the persuasive performance of the suggested approach.

In this paper, a robust fault estimation approach is proposed for multi-input and multioutput nonlinear dynamic systems on the basis of back propagation neural networks. The augmented system approach, input-to-state stability theory, linear matrix inequality optimization, and neural network training/learning are integrated so that a robust simultaneous estimate of system states and actuator faults are achieved. The proposed approaches are finally applied to a 4.8 MW wind turbine benchmark system, and the effectiveness is well demonstrated.

The density peak based clustering algorithm is a recently proposed density based clustering approach. This algorithm treats the data corresponding to local density peaks as cluster centers and groups non-center data based on the density relationship among neighboring data. While being simple, this algorithm is shown to be effective and computationally efficient. In the density peak based algorithm, the data with the largest local density are selected as cluster centers. On one hand, the real cluster centers may not have the largest local density in clusters. On the other hand, this practice may discriminate against the clusters of small density. In this paper we propose to measure the centerness of data and treat the centerness peaks as cluster centers. The centerness of one data is evaluated by the distribution of nearest neighbors in the neighborhood, and it measures to which degree one data is surrounded by its nearest neighbors. We present a histogram based method to calculate the centerness, and show that the centerness measure solves the problem resulted from density difference among clusters in the density peak based algorithm. In addition, the cluster centers identified by centerness peaks are more consistent with human observation. Experiments on various datasets and comparisons with other algorithms illustrate the effectiveness of our algorithm.

To achieve reliable operation of wind energy conversion technology, this ρ aper develops a robust observer-based fault tolerant control technique for wind turbine drive train systems in presence of simultaneous unknown inputs, faults and Brownian perturbations. Integration of several advanced techniques, namely, augmented approach, unknown input observer method, and linear matrix inequaity, is employed to estimate the means of the system states and the considered faults robustly. Based on the estimates, robust fault tolerant control strategy is implemented to drive the system trajectory convergent and eliminate the effects of faults from both actuators and sensors successfully. The control gains are selected to guarantee the convergence of the means of system states and com pens ate for the de grad ation caused by concerned faults. The ob server gain is determined via a linear matrix inequality optimization such that the closed-loop system is stochastically input-to-state stable satisfying required robust performance. The desi gned observer-based fault tolerant control c an make the over all system work in a steady condition and the system outputs c an be compensated to successfully track the healthy outputs in fault-free c ases. Finally, the proposed fault estimation-based fault tolerant control method is applied to a drive train system of the 4.8 MW benchmark wind wind turbine to validate the effectiveness.

Although electronic system has entered the digital age, analog circuit is still an essential part. Therefore the performance monitoring or evaluation of analog circuit is extremely important. However some problems about analog circuit performance monitoring is being, such as data acquisition online of the industry field with uncertainty, performance monitoring timeliness. Here an online performance monitoring method for analog circuit (OPM) subject to the data uncertainty is proposed. The main idea of OPM is to employ a learning machine same as least square support vector regression (LSSVR) to train and learn the data set. Considering the data from industrial field usually hold nonlinear feature, time varying feature and contain faults value, a novel robust LSSVR (RLSSVR) is presented to detection the performance of Electronic System. Moreover, the multi-kernel function is employed which has more flexibility than the single-kernel function, and can get more support vector numbers accuracy. At the same time, the novel robust learning algorithm is employed to process the data set which is with fault values. For the robust idea, the fault value is solved via the LSSVR model iteratively weights, and then the trained RLSSVR model is updated depend on the interaction between incremental learning and decrement learning. During the interaction, the interests of the history data and the control storage data are all be considered. Numerical experiment supported by the college analog electronic experiments, adopted eight indexes of one order low power amplifier to evaluate performance. The training data set were gotten via precision instrument evaluation in two years. Simulation results reveal that proposed RLSSVR can handle the regressive deviation caused by the nonlinear feature, time varying feature and contain faults value exist in the industry processing, and has speeder than the traditional LSSVR, and WLSSVR.