The style of the underwater images varies according to the region of the sea. However, Tidal Stream Turbine (TST) rotor images captured in the laboratory environment cannot reflect the real underwater environment in image style, resulting in poor generalization of image signal-based fault detection algorithms. Due to the fixed capture position of the camera, the TST rotor image dataset has a high semantic similarity between images, resulting in content loss in conventional image-to-image translation networks. Meanwhile, the one-to-one translation feature in other works cannot meet our requirements. In this work, a Domain Variable Prior-based Multi-style Transfer Network (DVP-MSTN) is proposed to achieve TST rotor image style augmentation. First, the backbone network is trained using a public paired dataset to acquire prior knowledge of domain variable (Knowledge Acquiring, KA). Next, a Multi-domain Transfer Unit (MDT unit) is introduced to enable the conversion of style representations in low-dimensional space. Finally, the prior knowledge is shared to train the MDT unit by fixing the parameters of the backbone network optimized from the KA process (Knowledge Sharing, KS). In addition, an algorithm based on the dark channel of the image is proposed to improve the transfer of low-contrast features. Specifically, a discriminator is used to discriminate the image dark channel to guide the MDT unit to generate low-contrast style representation conditionally. Meanwhile, color loss is employed to preserve the color feature of the image. By controlling the weights of the style code, this method enables control over the image style transfer process, thereby expanding the variety of image styles in the dataset for the purpose of data augmentation.

Functional dependencies (FDs) have been extensively employed in discovering inferential relationships in databases, which provide feasible approaches for many data mining tasks, such as data obfuscation, query optimization, and schema normalization. Since the explosive growth of data leads to a rapid increase of FDs on large datasets, existing algorithms that pay more attention to the exact FD discovery cannot extract FDs efficiently. To bridge this gap, we propose an Efficient double-cycle approximation of Functional Dependency (EulerFD) discovery algorithm, which ensures both efficiency and accuracy of FD discovery. EulerFD induces FDs from invalid ones as invalidating an FD only requires comparing and verifying some pairs of tuples (that violate the dependency) while validating an FD requires examining and verifying all tuples. Considering the abundant tuple pairs in large datasets, a novel sampling strategy is employed in EulerFD to quickly extract invalid FDs by revising the sampling range according to previous sampling results. Furthermore, EulerFD evaluates the stopping criteria in a double-cycle structure as feedback for further sampling. The sampling strategy and the double-cycle structure complement each other to achieve a more efficient sampling effect. Experimental results on real-world and synthetic datasets, especially the massive datasets from DMS of Alibaba Cloud, justify the design and verify the efficiency and effectiveness of the proposed EulerFD.

Marine current turbine (MCT) blades are continuously exposed to seawater, making them susceptible to marine biofouling and causing MCT blade imbalance faults. The diagnosis method based on a single sensor often fails when the data quality is poor. To realize the complementarity of multi-sensor information, a blades biofouling diagnosis method of MCT based on Gray-weighted Dempster-Shafer (GD-S) evidence fusion is proposed, which uses the fusion of the current sensor and image sensor. Firstly, the collected images and stator current are preprocessed to enhance the features of blade biofouling. Secondly, the MCT images and current signal features are used to construct 1DCNN and 2DCNN models respectively, and the probability of the two models are output. Finally, the probabilities of the two models are fused based on the proposed GD-S evidence fusion method. To verify the effectiveness of the proposed method, experiments are carried out on a 230W MCT platform. The results show that the proposed method has satisfactory performance for symmetrical biofouling and poor illumination.

To solve the problem of insufficient fault samples for inverter fault diagnosis in weakly supervised small sample scenario, this paper proposed a fault diagnosis method for inverter based on data augmentation (DA) with improved genetic algorithm-specific coefficient wavelet reconstruction (IGA-SCWR). First, IGA is used to find the optimal fine-tuning coefficient (FTC) k, which is the key to ensure the quality of DA. Second, through wavelet packet decomposition, the wavelet coefficients are changed under the guidance of the optimal FTC k, and sufficient samples of new synthesized data were obtained. Then the “end-to-end” feature extraction and fault classification are realized based on convolutional neural networks (CNNs). Finally, the effectiveness of the proposed method is verified by a series of experiments.

This paper proposed a hybrid fault-tolerant control (HFTC) strategy for three-phase cascaded multilevel inverters based on half-bridge recombination method. A new fault-tolerant topology is designed for the common single and double faults in three-phase cascaded H-bridge multilevel inverters (CHB-MLIs), and the fault-tolerant method is based on the combination of hardware and control. The above faults are classified into three categories, for which an HFTC strategy is developed so that the fault-tolerant process can be completed efficiently. The proposed HFTC strategy can realize the fault-tolerant control of single and double faults at any position; output balanced line voltages under all single and double faults, thus improving the utilization rate of DC voltage. And in most fault cases, it can keep the phase voltage level unchanged, thus restoring the performance of the inverter to the normal working state. Finally, the applicability and superiority of the proposed novel topology and HFTC strategy are verified by the simulation with a cascaded seven-level inverter.

Marine current turbine (MCT) is an efficient device for the utilization of marine current energy. As MCTs operate underwater for a long time, marine growth will attach to the machinery. Therefore, it is essential to recognize attachment on MCTs, since an increase in attachment will potentially deteriorate the power generation quality. Semantic segmentation is a suitable technique to perform this task, which however requires a large amount of labeled data. To acquire sufficient data, a specialized image generation method without high manual cost is proposed. For precise attachment recognition on blurry underwater images, we propose an improved semantic segmentation network (C-SegNet); this network adopts multi-scale feature concatenation and transfer learning to enhance the quality of recognition results. Besides, we use weighted cross-entropy loss to make the network pay more attention to some difficult segmentation objects. In the inference phase, dropout is utilized to estimate the recognition uncertainty, and a precise attachment area ratio is computed. Experimental results confirm the effectiveness of the proposed method under a submerged scene. In addition, C-SegNet has better performance than other state-of-the-art segmentation networks.

Marine current turbine (MCT) has been vigorously developed by many countries in the world because of its own advantages. However, the blade imbalance fault is the result of the marine biological attachments that will easily affect the efficiency of MCT. In this paper, a novel VMD denoising method is employed to detect the MCT blade imbalance fault. Firstly, the Hilbert transform (HT) is used to get the instantaneous frequency of the stator current. Then, the instantaneous frequency is broken up into several intrinsic mode functions (IMF) components by variational mode decomposition (VMD). And the objective IMF is selected by the maximal information coefficient (MIC). Finally, the PSD analysis is used to detect the imbalance fault. The effectiveness of the proposed method for fault detection is validated by experimental results.

Wireless body area networks (WBANs) are applied to monitor patients remotely. The sensors in WBANs have the characteristics of limited computing and less memory, while requiring real-time and security communications between sensors. In order to deal with the above problems, this article proposes a new asymmetric cryptographic algorithm (Diffie-Hellman-Hash-compression, abbreviated as DHS-C), which is based on the matrix decomposition. The asymmetric cryptographic algorithm can effectively solve the robustness problem in WBANs. The implementation of semitensor-compressed sensing can encrypt multiple signals with different dimensions and reduce the amount of transmission. In addition, the hash function, Arnold scrambling, and chaotic scrambling are applied to improve the security of our algorithm. A series of simulation and security analysis, including key space, pixel distribution of the encrypted image, adjacent pixel correlation, required storage space, compression ratio, peak-signal-to-noise ratio, and so on, are given to show the better performance of our proposed scheme.

Most of signals in the electrical machines and drives are non-Gaussian and highly nonlinear in nature. A useful set of techniques for examining these kinds of signals relies on the spectral representations of higher-order statistics (HOS), well-known as polyspectra. They describe statistical dependences of frequency components that are neglected by traditional spectral measures. The bispectrum is the most used HOS, and studying higher-order correlations provides more information about the electromechanical system's behavior. It helps in building more accurate diagnostic models. Based on this proper relationship the overall aim of the current work is the interpretation of the stator current tidal turbine bispectrum under imbalanced rotor blades condition. Based on this proper relationship, the overall aim of the current work is the interpretation of the permanent magnet synchronous generator (PMSG)-based tidal current turbine (TCT) stator current bispectrum for the diagnosis of biofouling. The proposed bispectrum-based diagnosis method has been tested using experimental data issued from a TCT experiencing biofouling emulated by an attachment on the turbine rotor. The achieved results clearly indicate the feasibility and efficacy of the proposed method.

The cascaded H-bridge multilevel inverter for grid-connected photovoltaic(PV) system has the advantages of high power quality and easy modularization, but as the levels of the inverter increase, the failure probability of the power switching devices will also increase. In the open-circuit faults of the power switching devices, there are two groups of similar faults that are difficult to distinguish. To solve this problem, a secondary classification fault diagnosis strategy based on PCA-SVM is proposed. The first classification is used to make a preliminary fault diagnosis between all types of faults, the second classification is to make a further diagnosis of the two groups of similar faults. Finally, compared with other fault diagnosis strategies, the proposed strategy improves the accuracy of fault diagnosis.

Marine current energy conversion systems are progressively attracting more attention due to its efficaciousness in providing a predictable source of energy with high energy density. This paper considers the critical issues such as the rejection of lumped disturbances, system uncertainties in the internal dynamics, and unknown external forces in the marine current energy conversion system (MCECS). An active disturbance rejection control (ADRC) strategy is applied to realize the maximum power extraction for a direct-driven permanent magnet synchronous generator (PMSG) based marine current turbine (MCT). The ADRC is used to realize the real-time estimation of system interference and interference compensation in order to improve the system ability to suppress errors and disturbances. Finally, this strategy is successfully tested through simulation, the results for which show that the control strategy is effective compared with conventional control.

Reducing greenhouse gas emissions becomes a top priority in the world with the emergence of global warming and environmental problems. Thus, a variety of renewable energy appears during the last decades. The Ocean, which covers two-thirds of the world, captures and stores huge amounts of energy which could satisfy 5 times of world energy demand. During the last 10 years, various Marine Current Energy Conversion Systems (MCECSs) have been developed around the world. In this paper, the marine current energy and its extraction forms are briefly presented. Then, various projects are classified into two categories, geared drive train system and direct drive train system, according to the different generators. The mainly characteristics of the different generators are also discussed. The relative converters are future presented. According to this paper, the researchers will easily find that the Permanent Magnet Synchrous Generator (PMSG) and Induction Generator (IG) are preferred in MCECS.

Different with the onshore power generation equipment, marine current turbine always operates in a poor natural environment that the arrangement of measured points is restricted. With a small amount of signal, single domain usually cannot detect the fault comprehensively. A multi-domain reference method is proposed in this paper for imbalance fault detection of variable-speed direct-drive marine current turbine. The proposed method acquires the reference information from multiple domains of stator current signal for spectral analysis. First, the priority of multiple domains including time domain, time-frequency domain and angle domain are considered. Then, the feature required for fault detection is selected and reconstructed. Finally, imbalance fault detection is performed by spectral analysis. Experimental results verify the effectiveness of the proposed method in marine current turbine under complex conditions.

This paper deals with a fault detection method based on an empirically data-driven approach combined to a statistical tool. This approach is an enhanced version of the empirical mode decomposition. The proposed fault detector application to bearing defects in wind turbine based on induction generator clearly shows that it is well suited for stationary and non-stationary behavior regardless the rank of the intrinsic mode function introduced by the fault.

This paper presents a novel approach for induction machine condition monitoring using stator current measurements. The proposed method, based on hypothesis testing, specifically investigates a binary detection problem: the machine is healthy or faulty. The Generalized Likelihood Ratio Test (GLRT) is used to address this statistical detection problem with unknown signal and noise parameters. It is indeed a Constant False Alarm Rate (CFAR) detector. Decision is obtained according to a threshold, which is set to reach a desired false alarm probability. The proposed detector implementation needs estimations that are based on the Maximum Likelihood Estimator (MLE). In particular, Total Least Squares-Estimation of Signal Parameters via Rotational Invariance Techniques (TLS-ESPRIT) estimates frequencies. The proposed CFAR detector is tested on experimental data of bearings faults and broken rotor bars that clearly show it effectiveness.

Marine current turbine (MCT) have been widely used nowadays, it is important to monitor their health state. Unnecessary marine biological growth or marine pollutants attached to the moving parts will affect the operation of the system by introducing imbalance. The imbalance, regarded as faults, would change the performance of turbine and lead to progressively increasing damages. In this paper, a marine current turbine prototype with permanent magnet synchronous generator (PMSG) has been studied. An innovative imbalance fault detection method is proposed for marine current turbines under the condition of wave and turbulence. In the proposed method, the average frequency of current is calculated through synchronous sampling. Meanwhile, current fluctuation influence is reduced during one revolution. The empirical mode decomposition (EMD) and spectrum analysis are used to achieve fault characteristics. Theoretical analysis, simulation and experimental results under different conditions validate the proposed method. Moreover the proposed method could be used for long-term marine current turbine monitoring in respect to its simplicity and low time cost.

This paper presents a hybrid approach for online fault detection in nonlinear processes. To solve the possible monitoring difficulties caused by nonlinear characteristics of industrial process data, two applications of the Kernel Method: Hypersphere Support Vector Machine (HSSVM) and Kernel Principal Component Analysis (KPCA) are used as fault detection methods. On top of that, to obtain the adaptive models for online monitoring and fault detection in unsteady-stage conditions, instead of the static ones established by traditional HSSVM and KPCA, multiple methods are adopted, including Recursive KPCA, Adaptive Control Limit (ACL) and Online Sequential Extreme Learning Machine (OS-ELM), all of which update the detection model in real time with dynamically adjusting. The T2 control limit of Recursive KPCA, the classification hyperspheres of HSSVM and the single hidden layer feedforward network (SLFN) trained with OS-ELM work collaboratively in monitoring the real time process data to detect the possible faults. The proposed approach was tested and validated via a set of experimental data collected from a bearing test rig. Experimental results show that this approach is adequate for fault detection while meets the needs of real time performance.

The main advantages of multilevel inverters are the improved power quality and higher efficiency. Cascaded H-Bridge (CHB) multilevel inverters are widely used in photovoltaic grid-connected generators, electric vehicles and motor drive systems. However, the CHB multilevel inverters require a large number of isolated dc power supplies, which make these inverters complicated to implement in industrial applications. This paper presents a model predictive control method to improve the mentioned drawbacks of CHB inverters by using a flying capacitor to replace a dc power supply. Simulation and experimental results of a seven-level asymmetrical CHB grid-connected inverter show that one can simultaneously maintain the inverters output voltage level and can also keep the flying capacitors voltage balance.

The failure rate of non-steady conditions is much higher than the failure rate of steady conditions. So, it is important to monitor non-steady conditions of system. The systems' monitoring results indicate that there are large false alarms or missing alarms based on traditional process control methods. The primary problems are higher data dimension, more complex correlation among variables, non-Gaussian distribution, the signal mutations and so on. Hence, this paper proposed a novel Longitudinal-standardization multi-period PCA fault detection strategy based on adaptive confidence limit (LMPCA-ACL) for periodic non-steady conditions. This LMPCA-ACL strategy comprises three helpful parts as follows. First one is to transform the non-Gaussian normal data into Gaussian data through a novel longitudinal-standardization (LS). The second part is to utilize the proposed multi-period PCA algorithm to reduce dimensions, remove correlation and improve the monitoring accuracy. The third part is to build the adaptive confidence limit to resolve the problems of signal mutations and real-time monitoring by the dynamic data window method. In this paper, the LMPCA-ACL strategy is applied to real-time monitor the motor cyclical process of loading and unloading. The examination results indicate that the LMPCA-ACL strategy is superior to other methods in fault detection if the system is under periodic non-steady conditions.

The multi-level inverter system is becoming a very promising candidate to replace the conventional two-level inverter, but system reliability remains an open issue. The most common reliability problem is that power switch transistors have open-circuit or short-circuit faults during operation. In order to improve the accuracy of the fault diagnosis and accelerate the operation speed in a cascaded H-bridge multilevel inverter system, a novel fault diagnosis strategy based on principle component analysis and multiclass relevance vector machine (PCA-mRVM) is presented in this paper. In this strategy, the output voltage of CHMLIS, which is preprocessed through the fast Fourier transform, is used to identify the type and location of occurring fault through the mRVM model. Then PCA is utilized to reduce input sample's dimension, which decrease the training time of diagnostic model. The PCA-mRVM strategy could not only achieve higher model sparsity and shorter diagnosis time, but also provide probabilistic outputs for every class membership. Hardware experimental results of simple-fault have shown that the PCA-mRVM could achieve the best diagnosis performance than traditional fault diagnosis methods. In addition, simulation results of complicated-fault have further validated that the PCA-mRVM strategy is useful in multi-fault diagnosis, which is better than other methods.

Smart grids have initiated a radical reappraisal of distribution networks function where the integration of renewable energy sources, load demand control, and effective use of the network are indexed as the most important keys for smart grid expansion and deployment regardless each country policies. One of the most efficient ways of effective use of these grids would be to continuously monitor their conditions. This allows for early detection of power quality degeneration facilitating therefore a proactive response, prevent a fault ride-through the renewable power sources, minimizing downtime, and maximizing productivity. In this smart grid context, this paper proposes the evaluation and comparison of advanced signal processing tools, namely the Hilbert transform and the ensemble empirical mode decomposition method for the detection of voltage sags as they are the most commonly encountered power quality disturbances.

The multivariate statistical methods are commonly used to fault detection through a straight limit line given by the HotellingT2. However, the traditional straight limit line is difficult to detect the fault effectively under the non-steady conditions, which the false alarm rate and missing alarm rate are high. For these problems above, a fault detection method based on dynamic peak-valley limit is proposed in this paper. The proposed method introduces relative principal component analysis to carry out the dimension reduction, and extracts principal components, then adopts moving least squares to preprocess PCs to obtain the fitting curve which is called peak-valley curve, finally uses peak and valley points to construct a control limit combined the traditional straight limit line. At the end, the proposed method is applied to wind power generation system, and the simulation results verify the effectiveness of the proposed method.

This paper focuses on the microgrid control method in different operating modes. The conventional droop control scheme is typically used to achieve autonomous voltage and frequency regulation, which considers only local information, and the global optimal performance can't be guaranteed. In island mode, when the load or generation inside the MG changes, circulations will be generated between the inverters in case the line impedances are mismatch. Furthermore, the MG active power output does not follow the reference in grid connected mode. Dealing with the above problems, a central controller is designed to maintain the stable operation of the microgrid in different modes in this paper. Some simulations are carried out and the results validate the efficiency of the proposed method.

This paper presents a new multi-dimension predictive model based on the diagonal recurrent neural networks (PDRNN) with a parallel learning algorithm. This method can be used to predict not only values, but also some points in the multi-dimension space. And also its applications in data mining are discussed in the paper. Some analysis results show the significant improvement to ship route prediction using the PDRNN algorithm in database of geographic information system (CIS).