A new intelligent fault diagnosis and prognosis method for wind turbine doubly-fed induction generator

Condition Monitoring and fault-prognosis approaches are typical methods to reduce the energy production cost and Wind Turbine downtime. In this paper, a new CM combinatory system and fault prognosis are proposed based on an adaptive threshold, feature-level fusion, and new degradation indicator and the CM operation is based on a new index Symptom of Degeneration crossing of an adaptive threshold. Also, a new adaptive threshold is proposed based on the fuzzy rules and WT operation point. Fault prognosis is conducted with the Least-Squares Support-Vector Machine method, and Particle Swarm Optimization is employed for the optimum selecting of the wavelet Kernel function and the SVM parameters. The proposed technique is compared with other methods and the simulation results illustrate the PSO-LS-SVM superiorities. The effectiveness of the proposed prognostic structure is evaluated using a WT test-rig prototype. The experimental results demonstrate that the Condition-Based Maintenance is improved by the proposed structure and the RUL is predicted before serious damage occurrences.

Research on Nonlinear Modeling Method of Support Vector Machine with Wavelet Derivation Kernel Function

The model capability of Support Vector Machine (SVM) relies on the selection of kernel function. To obtain a better application modeling of SVM, the wavelet kernel function that satisfies Merce condition is introduced to use the kernel function of SVM, achieving a good effect. In the paper, on the basis of wavelet kernel function, a wavelet derivation kernel function is proposed in the application of SVM for higher accuracy. An actual example on nonlinear function approximation shows that SVM regression model has a satisfactory approximation effect, and also support an effective nonlinear modeling method.

Anomaly Intrusion Detection Based on Support Vector Machine with Mexico Hat Wavelet Kernel Function

The selection of kernel function in Support Vector Machine (SVM) has a great influence on the model performance. In the paper, Mexico hat wavelet kernel is introduced to employ the kernel function of SVM, and theoretically it has be prove that, Mexico hat wavelet kernel satisfies the Merce condition, that is the necessary condition as the kernel function of SVM. Simulation on the anomaly detection shows that the capability of SVM based on Mexico hat wavelet kernel is better than that of SVM based on RBF kernel with a satisfactory result for anomaly intrusion detection.

Application of Wavelet Transform in Transient Signal

In this paper, analog signals will be built upon the dynamic load of transient signal with the help of MATLAB simulation method and wavelet transform concept, and analyze it with the application of wavelet denoise method, whose good effects would be proved by simulation experiment. To dispel noise from noisy signal through wavelet resolution theory approach based on collection of simulation experiment and theory. In conclusion, wavelet kernel function and decomposition have direct effect to denoise. In this paper, we’ve made an analysis to electric power transient signal characteristics by combination of wavelet basic theory and simulation experiment

A Novel Fractional-Order PID Controller for Integrated Pressurized Water Reactor Based on Wavelet Kernel Neural Network Algorithm

This paper presents a novel wavelet kernel neural network (WKNN) with wavelet kernel function. It is applicable in online learning with adaptive parameters and is applied on parameters tuning of fractional-order PID (FOPID) controller, which could handle time delay problem of the complex control system. Combining the wavelet function and the kernel function, the wavelet kernel function is adopted and validated the availability for neural network. Compared to the conservative wavelet neural network, the most innovative character of the WKNN is its rapid convergence and high precision in parameters updating process. Furthermore, the integrated pressurized water reactor (IPWR) system is established by RELAP5, and a novel control strategy combining WKNN and fuzzy logic rule is proposed for shortening controlling time and utilizing the experiential knowledge sufficiently. Finally, experiment results verify that the control strategy and controller proposed have the practicability and reliability in actual complicated system.

The Online Prediction of the Low Carbon Ferrochrome Terminal Composition in Smelting Process

The online prediction of the low carbon ferrochrome terminal composition in electro-silicothemic smelting process plays a key role in guiding the determining the tapping time, the smelting process of the power supply system, the production quality and the energy consumption and so on. By introducing the multi-scale wavelet kernel function in the support vector machine (SVM) algorithm, and according to the Bayesian classifier to certain different smelting conditions, we chose different decomposition scales. In this way, the accuracy of the terminal composition prediction during the smelting process is improved greatly. Experiments show the effectiveness of the proposed method.