Actuator and Sensor Fault Classification for Wind Turbine Systems Based on Fast Fourier Transform and Uncorrelated Multi-Linear Principal Component Analysis Techniques

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Emotion recognition, or the ability of computers to interpret people's emotional states, is a very active research area with vast applications to improve people's lives. However, most image-based emotion recognition techniques are flawed, as humans can intentionally hide their emotions by changing facial expressions. Consequently, brain signals are being used to detect human emotions with improved accuracy, but most proposed systems demonstrate poor performance as EEG signals are difficult to classify using standard machine learning and deep learning techniques. This paper proposes two convolutional neural network (CNN) models (M1: heavily parameterized CNN model and M2: lightly parameterized CNN model) coupled with elegant feature extraction methods for effective recognition. In this study, the most popular EEG benchmark dataset, the DEAP, is utilized with two of its labels, valence, and arousal, for binary classification. We use Fast Fourier Transformation to extract the frequency domain features, convolutional layers for deep features, and complementary features to represent the dataset. The M1 and M2 CNN models achieve nearly perfect accuracy of 99.89% and 99.22%, respectively, which outperform every previous state-of-the-art model. We empirically demonstrate that the M2 model requires only 2 seconds of EEG signal for 99.22% accuracy, and it can achieve over 96% accuracy with only 125 milliseconds of EEG data for valence classification. Moreover, the proposed M2 model achieves 96.8% accuracy on valence using only 10% of the training dataset, demonstrating our proposed system's effectiveness. Documented implementation codes for every experiment are published for reproducibility.

Study of Torsional Vibration Bifurcation Characteristics of Direct-Drive Wind Turbine Shaft System

This paper set out to establish the dynamics model of shaft torsional vibration for direct-drive wind turbine with the phenomenon of unstable shaft system torsional vibration. The stability of the equilibrium point of the dynamical model is investigated, and the Routh–Hurwitz stability criterion is used to obtain a range of values for the bifurcation control parameters. For the stable equilibrium point, the stability domain of the system is calculated by constructing the Lyapunov function. The sensitivity analysis of system parameters is carried out to obtain the law of the effect of system parameters on system stability of the torsional vibration system. The results are substituted for example calculations, and the results verify the correctness of the theoretical analysis conclusions. It is proved that it is feasible to analyze the torsional vibration characteristics of the direct-drive wind turbine shaft system by using the principle of Routh–Hurwitz stability, etc., which provides a reference for the structural design of direct-drive wind turbine.

Tracking Control of a Hyperchaotic Complex System and Its Fractional-Order Generalization

Hyperchaotic complex behaviors often occur in nature. Some chaotic behaviors are harmful, while others are beneficial. As for harmful behaviors, we hope to transform them into expected behaviors. For beneficial behaviors, we want to enhance their chaotic characteristics. Aiming at the harmful hyperchaotic complex system, a tracking controller was designed to produce the hyperchaotic complex system track common expectation system. We selected sine function, constant, and complex Lorenz chaotic system as target systems and verified the effectiveness by mathematical proof and simulation experiments. Aiming at the beneficial hyperchaotic complex phenomenon, this paper extended the hyperchaotic complex system to the fractional order because the fractional order has more complex dynamic characteristics. The influences order change and parameter change on the evolution process of the system were analyzed and observed by MATLAB simulation.

Nonlinear Dynamic Process Monitoring Based on Two-Step Dynamic Local Kernel Principal Component Analysis

Nonlinearity may cause a model deviation problem, and hence, it is a challenging problem for process monitoring. To handle this issue, local kernel principal component analysis was proposed, and it achieved a satisfactory performance in static process monitoring. For a dynamic process, the expectation value of each variable changes over time, and hence, it cannot be replaced with a constant value. As such, the local data structure in the local kernel principal component analysis is wrong, which causes the model deviation problem. In this paper, we propose a new two-step dynamic local kernel principal component analysis, which extracts the static components in the process data and then analyzes them by local kernel principal component analysis. As such, the two-step dynamic local kernel principal component analysis can handle the nonlinearity and the dynamic features simultaneously.

Solutions of Feature and Hyperparameter Model Selection in the Intelligent Manufacturing

In the era of Industry 4.0, numerous AI technologies have been widely applied. However, implementation of the AI technology requires observation, analysis, and pre-processing of the obtained data, which takes up 60–90% of total time after data collection. Next, sensors and features are selected. Finally, the AI algorithms are used for clustering or classification. Despite the completion of data pre-processing, the subsequent feature selection and hyperparameter tuning in the AI model affect the sensitivity, accuracy, and robustness of the system. In this study, two novel approaches of sensor and feature selecting system, and hyperparameter tuning mechanisms are proposed. In the sensor and feature selecting system, the Shapley Additive ExPlanations model is used to calculate the contribution of individual features or sensors and to make the black-box AI model transparent, whereas, in the hyperparameter tuning mechanism, Hyperopt is used for tuning to improve model performance. Implementation of these two new systems is expected to reduce the problems in the processes of selection of the most sensitive features in the pre-processing stage, and tuning of hyperparameters, which are the most frequently occurring problems. Meanwhile, these methods are also applicable to the field of tool wear monitoring systems in intelligent manufacturing.

Transient Stability Analysis of Direct Drive Wind Turbine in DC-Link Voltage Control Timescale during Grid Fault

Transient stability during grid fault is experienced differently in modern power systems, especially in wind-turbine-dominated power systems. In this paper, transient behavior and stability issues of a direct drive wind turbine during fault recovery in DC-link voltage control timescale are studied. First, the motion equation model that depicts the phase and amplitude dynamics of internal voltage driven by unbalanced active and reactive power is developed to physically depict transient characteristics of the direct drive wind turbine itself. Considering transient switch control induced by active power climbing, the two-stage model is employed. Based on the motion equation model, transient behavior during fault recovery in a single machine infinite bus system is studied, and the analysis is also divided into two stages: during and after active power climbing. During active power climbing, a novel approximate analytical expression is proposed to clearly reveal the frequency dynamics of the direct drive wind turbine, which is identified as approximate monotonicity at excitation of active power climbing. After active power climbing, large-signal oscillation behavior is concerned. A novel analysis idea combining time-frequency analysis based on Hilbert transform and high order modes is employed to investigate and reveal the nonlinear oscillation, which is characterized by time-varying oscillation frequency and amplitude attenuation ratio. It is found that the nonlinear oscillation and even stability are related closely to the final point during active power climbing. With a large active power climbing rate, the nonlinear oscillation may lose stability. Simulated results based on MATLAB® are also presented to verify the theoretical analysis.

Stability Enhancement of Wind Energy Conversion Systems Based on Optimal Superconducting Magnetic Energy Storage Systems Using the Archimedes Optimization Algorithm

Throughout the past several years, the renewable energy contribution and particularly the contribution of wind energy to electrical grid systems increased significantly, along with the problem of keeping the systems stable. This article presents a new optimization technique entitled the Archimedes optimization algorithm (AOA) that enhances the wind energy conversion system’s stability, integrated with a superconducting magnetic energy storage (SMES) system that uses a proportional integral (PI) controller. The AOA is a modern population technique based on Archimedes’ law of physics. The SMES system has a big impact in integrating wind generators with the electrical grid by regulating the output of wind generators and strengthening the power system’s performance. In this study, the AOA was employed to determine the optimum conditions of the PI controller that regulates the charging and discharging of the SMES system. The simulation outcomes of the AOA, the genetic algorithm (GA), and particle swarm optimization (PSO) were compared to ensure the efficacy of the introduced optimization algorithm. The simulation results showed the effectiveness of the optimally controlled SMES system, using the AOA in smoothing the output power variations and increasing the stability of the system under various operating conditions.

Multidimensional Data Interpretation of Vibration Signals Registered in Different Locations for System Condition Monitoring of a Three-Stage Gear Transmission Operating under Difficult Conditions

This article provides a discussion of the results of studies on the original system condition monitoring of a three-stage transmission with a bevel–cylindrical–planetary configuration installed in an experimental scraper conveyor. Due to the high vibroactivity of gear transmissions operating under the impact of a scraper conveyor’s chain drive, these unwanted effects of machine operating vibrations were assumed to be applied. For purposes of the study, vibrations were measured on the driving transmission housing in an idling scraper conveyor. The main purpose of the study was to establish the frequencies characteristic of the gear transmission, and to determine whether it was possible to run vibroacoustic diagnostics of the same transmission under conditions with a considerable impact of the conveyor chain. An additional cognitively significant research goal was the analysis of the dependence of the diagnostic utility of the signal depending on the sensor mounting point. Five different locations of three-axis sensors oriented to the next stages and various types of gears were determined, as well as places characterized by high spatial accessibility, which are often selected as places for measuring the vibration of gears. Using MATLAB software, a program was written that was calibrated and adapted to the specifics of the measuring equipment based on the collected test results. As a result, it was possible to obtain a multidimensional data interpretation of vibration signals of system condition monitoring of a three-stage gear transmission operating under difficult conditions. The results were based on signals registered on the real three-stage gear transmission operating under the impact of a scraper conveyor’s chain drive.

Rotating Machinery Diagnosing in Non-Stationary Conditions with Empirical Mode Decomposition-Based Wavelet Leaders Multifractal Spectra

Diagnosing the condition of rotating machines by non-invasive methods is based on the analysis of dynamic signals from sensors mounted on the machine—such as vibration, velocity, or acceleration sensors; torque meters; force sensors; pressure sensors; etc. The article presents a new method combining the empirical mode decomposition algorithm with wavelet leader multifractal formalism applied to diagnosing damages of rotating machines in non-stationary conditions. The development of damage causes an increase in the level of multifractality of the signal. The multifractal spectrum obtained as a result of the algorithm changes its shape. Diagnosis is based on the classification of the features of this spectrum. The method is effective in relation to faults causing impulse responses in the dynamic signal registered by the sensors. The method has been illustrated with examples of vibration signals of rotating machines recorded on a laboratory stand, as well as on real objects.

A combined model for short-term wind speed forecasting based on empirical mode decomposition, feature selection, support vector regression and cross-validated lasso

BACKGROUND

The planning and control of wind power production rely heavily on short-term wind speed forecasting. Due to the non-linearity and non-stationarity of wind, it is difficult to carry out accurate modeling and prediction through traditional wind speed forecasting models.

METHODS

In the paper, we combine empirical mode decomposition (EMD), feature selection (FS), support vector regression (SVR) and cross-validated lasso (LassoCV) to develop a new wind speed forecasting model, aiming to improve the prediction performance of wind speed. EMD is used to extract the intrinsic mode functions (IMFs) from the original wind speed time series to eliminate the non-stationarity in the time series. FS and SVR are combined to predict the high-frequency IMF obtained by EMD. LassoCV is used to complete the prediction of low-frequency IMF and trend.

RESULTS

Data collected from two wind stations in Michigan, USA are adopted to test the proposed combined model. Experimental results show that in multi-step wind speed forecasting, compared with the classic individual and traditional EMD-based combined models, the proposed model has better prediction performance.

CONCLUSIONS

Through the proposed combined model, the wind speed forecast can be effectively improved.

Semi-supervised associative classification using ant colony optimization algorithm

Labeled data is the main ingredient for classification tasks. Labeled data is not always available and free. Semi-supervised learning solves the problem of labeling the unlabeled instances through heuristics. Self-training is one of the most widely-used comprehensible approaches for labeling data. Traditional self-training approaches tend to show low classification accuracy when the majority of the data is unlabeled. A novel approach named Self-Training using Associative Classification using Ant Colony Optimization (ST-AC-ACO) has been proposed in this article to label and classify the unlabeled data instances to improve self-training classification accuracy by exploiting the association among attribute values (terms) and between a set of terms and class labels of the labeled instances. Ant Colony Optimization (ACO) has been employed to construct associative classification rules based on labeled and pseudo-labeled instances. Experiments demonstrate the superiority of the proposed associative self-training approach to its competing traditional self-training approaches.

Special Issue on “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes”

Complex industrial automation systems and processes, such as chemical processes, manufacturing systems, wireless network systems, power and energy systems, smart grids and so forth, have greatly contributed to our daily life [...]

An Overview on Fault Diagnosis, Prognosis and Resilient Control for Wind Turbine Systems

Wind energy is contributing to more and more portions in the world energy market. However, one deterrent to even greater investment in wind energy is the considerable failure rate of turbines. In particular, large wind turbines are expensive, with less tolerance for system performance degradations, unscheduled system shut downs, and even system damages caused by various malfunctions or faults occurring in system components such as rotor blades, hydraulic systems, generator, electronic control units, electric systems, sensors, and so forth. As a result, there is a high demand to improve the operation reliability, availability, and productivity of wind turbine systems. It is thus paramount to detect and identify any kinds of abnormalities as early as possible, predict potential faults and the remaining useful life of the components, and implement resilient control and management for minimizing performance degradation and economic cost, and avoiding dangerous situations. During the last 20 years, interesting and intensive research results were reported on fault diagnosis, prognosis, and resilient control techniques for wind turbine systems. This paper aims to provide a state-of-the-art overview on the existing fault diagnosis, prognosis, and resilient control methods and techniques for wind turbine systems, with particular attention on the results reported during the last decade. Finally, an overlook on the future development of the fault diagnosis, prognosis, and resilient control techniques for wind turbine systems is presented.

Active Fault Localization of Actuators on Torpedo-Shaped Autonomous Underwater Vehicles

To ensure the mission implementation of Autonomous Underwater Vehicles (AUVs), faults occurring on actuators should be detected and located promptly; therefore, reliable control strategies and inputs can be effectively provided. In this paper, faults occurring on the propulsion and attitude control systems of a torpedo-shaped AUV are analyzed and located while fault features may induce confusions for conventional fault localization (FL). Selective features of defined fault parameters are assorted as necessary conditions against different faulty actuators and synthesized in a fault tree subsequently to state the sufficiency towards possible abnormal parts. By matching fault features with those of estimated fault parameters, suspected faulty sections are located. Thereafter, active FL strategies that analyze the related fault parameters after executing purposive actuator control are proposed to provide precise fault location. Moreover, the generality of the proposed methods is analyzed to support extensive implementations. Simulations based on finite element analysis against a torpedo-shaped AUV with actuator faults are carried out to illustrate the effectiveness of the proposed methods.

Fault Classification of Nonlinear Small Sample Data through Feature Sub-Space Neighbor Vote

The fault classification of a small sample of high dimension is challenging, especially for a nonlinear and non-Gaussian manufacturing process. In this paper, a similarity-based feature selection and sub-space neighbor vote method is proposed to solve this problem. To capture the dynamics, nonlinearity, and non-Gaussianity in the irregular time series data, high order spectral features, and fractal dimension features are extracted, selected, and stacked in a regular matrix. To address the problem of a small sample, all labeled fault data are used for similarity decisions for a specific fault type. The distances between the new data and all fault types are calculated in their feature subspaces. The new data are classified to the nearest fault type by majority probability voting of the distances. Meanwhile, the selected features, from respective measured variables, indicate the cause of the fault. The proposed method is evaluated on a publicly available benchmark of a real semiconductor etching dataset. It is demonstrated that by using the high order spectral features and fractal dimensionality features, the proposed method can achieve more than 84% fault recognition accuracy. The resulting feature subspace can be used to match any new fault data to the fingerprint feature subspace of each fault type, and hence can pinpoint the root cause of a fault in a manufacturing process.

Inverter Efficiency Analysis Model Based on Solar Power Estimation Using Solar Radiation

The photovoltaic (PV) industry is an important part of the renewable energy industry. With the growing use of PV systems, interest in their operation and maintenance (O&M) is increasing. In this regard, analyses of power generation efficiency and inverter efficiency are very important. The first step in efficiency analysis is solar power estimation based on environment sensor data. In this study, solar power was estimated using a univariate linear regression model. The estimated solar power data were cross-validated with the actual solar power data obtained from the inverter. The results provide information on the power generation efficiency of the inverter. The linear estimation model developed in this study was validated using a single PV system. It is possible to apply the coefficients presented in this study to other PV systems, even though the nature and error rates of the collected data may vary depending on the inverter manufacturer. To apply the proposed model to PV systems with different power generation capacities, reconstructing the model according to the power generation capacity is necessary.