Study on novel signal processing and simultaneous-fault diagnostic method for wind turbine

2019 ◽  
Vol 41 (14) ◽  
pp. 4100-4113
Author(s):  
Xian-Bo Wang ◽  
Pu Miao ◽  
Kun Zhang ◽  
Xiaoyuan Zhang ◽  
Jun Wang
Keyword(s):  
Signal Processing ◽  
Wind Turbine ◽  
Extreme Learning Machine ◽  
Feature Learning ◽  
Mode Decomposition ◽  
Vibrational Signals ◽  
Fault Diagnostic ◽  
Diagnostic Framework ◽  
Learning Machine ◽  
Signal Processing Methods

High-precision fault diagnosis is important for the widely installed complex industrial product, the wind turbine. However, intelligent monitoring is difficult due to the fuzzy boundaries and individual different variations of the unseen single or simultaneous-fault of such intricate equipment. To solve this problem, this study proposes an ensemble fault diagnostic framework for simultaneous and coupling failure. First, this paper develops novel signal processing methods for effective feature learning and mapping from the non-stationary and nonlinear raw vibrational signals. The adapted variational mode decomposition is introduced based on the particle swarm optimization that applies the minimum mean envelope entropy to optimize the parameters settings. Second, the novel ensemble extreme learning machine-based network is proposed to isolate the faults that applies one extreme learning machine network to count the number of fault scenarios, and the other one to identify the specific single or simultaneous-fault labels. With this scheme, the self-adaptive ensemble extreme learning machine-based fault diagnostic framework is more accurate and faster than the prevailing probabilistic classifier-based methods, as the proposed method does not rely on empirically specified decision-making threshold and generates all the candidate fault labels at the same time. Finally, this study builds the test platform and compares the overall results with the existing feature analysis methods and classifiers. The experimental results verify that the proposed framework detects both single and simultaneous-fault accurately and quickly.

scholarly journals Iterative variational mode decomposition and extreme learning machine for gearbox diagnosis based on vibration signals

2019 ◽  
Vol 13 (1) ◽  
pp. 4477-4492
Author(s):  
M. Firdaus Isham ◽  
M. Salman Leong ◽  
L. M. Hee ◽  
Z. A. B. Ahmad
Keyword(s):  
Signal Processing ◽  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Processing Method ◽  
Mode Number ◽  
Variational Mode Decomposition ◽  
Vibration Signals ◽  
Signal Processing Method ◽  
Mode Decomposition ◽  
Learning Machine

Vibration-based monitoring and diagnosis provide an excellent and reliable monitoring strategies for maintaining and sustaining a million dollars of industrial assets. The signal processing method is one of the key elements in gearbox fault diagnosis for extracting most useful information from raw vibration signals. Variational mode decomposition (VMD) is one of the recent signal processing methods that helps to solve many limitations in traditional signal processing method. However, pre-determine the input parameters especially the mode number become a challenging task for using this method. Then, this study aims to propose an iterative approach for selecting the mode number for the VMD method by using the normalized mean value (NMV) plot. The NMV value is calculates based on the ratio of a summation of VMD modes and the input signals. The result shows that the proposed iterative VMD approach can select an accurate mode number for the VMD method. Then, the vibration signals decomposed into different VMD modes and used for gearbox fault diagnosis. Statistical features have been extracted from the selected VMD modes and pass into extreme learning machine (ELM) for fault classification. Iterative VMD-ELM provide significance improvement of about 20% higher accuracy in classification result as compared with EMD-ELM. Hence, this research study offers a new mean for gearbox diagnosis strategy.  

scholarly journals A Hydraulic Pump Fault Diagnosis Method Based on the Modified Ensemble Empirical Mode Decomposition and Wavelet Kernel Extreme Learning Machine Methods

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2599
Author(s):  
Zhenbao Li ◽  
Wanlu Jiang ◽  
Sheng Zhang ◽  
Yu Sun ◽  
Shuqing Zhang
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Recognition Accuracy ◽  
Ensemble Empirical Mode Decomposition ◽  
Hydraulic Pump ◽  
Vibration Signals ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

To address the problem that the faults in axial piston pumps are complex and difficult to effectively diagnose, an integrated hydraulic pump fault diagnosis method based on the modified ensemble empirical mode decomposition (MEEMD), autoregressive (AR) spectrum energy, and wavelet kernel extreme learning machine (WKELM) methods is presented in this paper. First, the non-linear and non-stationary hydraulic pump vibration signals are decomposed into several intrinsic mode function (IMF) components by the MEEMD method. Next, AR spectrum analysis is performed for each IMF component, in order to extract the AR spectrum energy of each component as fault characteristics. Then, a hydraulic pump fault diagnosis model based on WKELM is built, in order to extract the features and diagnose faults of hydraulic pump vibration signals, for which the recognition accuracy reached 100%. Finally, the fault diagnosis effect of the hydraulic pump fault diagnosis method proposed in this paper is compared with BP neural network, support vector machine (SVM), and extreme learning machine (ELM) methods. The hydraulic pump fault diagnosis method presented in this paper can diagnose faults of single slipper wear, single slipper loosing and center spring wear type with 100% accuracy, and the fault diagnosis time is only 0.002 s. The results demonstrate that the integrated hydraulic pump fault diagnosis method based on MEEMD, AR spectrum, and WKELM methods has higher fault recognition accuracy and faster speed than existing alternatives.

scholarly journals Short-Term Electricity Price Forecasting by Employing Ensemble Empirical Mode Decomposition and Extreme Learning Machine

Forecasting ◽  
2021 ◽  
Vol 3 (3) ◽  
pp. 460-477
Author(s):  
Sajjad Khan ◽  
Shahzad Aslam ◽  
Iqra Mustafa ◽  
Sheraz Aslam
Keyword(s):  
Extreme Learning Machine ◽  
Empirical Mode Decomposition ◽  
Electricity Market ◽  
Ensemble Empirical Mode Decomposition ◽  
Electricity Price ◽  
Price Forecasting ◽  
Short Term ◽  
Mode Decomposition ◽  
Electricity Price Forecasting ◽  
Learning Machine

Day-ahead electricity price forecasting plays a critical role in balancing energy consumption and generation, optimizing the decisions of electricity market participants, formulating energy trading strategies, and dispatching independent system operators. Despite the fact that much research on price forecasting has been published in recent years, it remains a difficult task because of the challenging nature of electricity prices that includes seasonality, sharp fluctuations in price, and high volatility. This study presents a three-stage short-term electricity price forecasting model by employing ensemble empirical mode decomposition (EEMD) and extreme learning machine (ELM). In the proposed model, the EEMD is employed to decompose the actual price signals to overcome the non-linear and non-stationary components in the electricity price data. Then, a day-ahead forecasting is performed using the ELM model. We conduct several experiments on real-time data obtained from three different states of the electricity market in Australia, i.e., Queensland, New South Wales, and Victoria. We also implement various deep learning approaches as benchmark methods, i.e., recurrent neural network, multi-layer perception, support vector machine, and ELM. In order to affirm the performance of our proposed and benchmark approaches, this study performs several performance evaluation metric, including the Diebold–Mariano (DM) test. The results from the experiments show the productiveness of our developed model (in terms of higher accuracy) over its counterparts.

scholarly journals A Carbon Price Prediction Model Based on the Secondary Decomposition Algorithm and Influencing Factors

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1328
Author(s):  
Jianguo Zhou ◽  
Shiguo Wang
Keyword(s):  
Prediction Model ◽  
Extreme Learning Machine ◽  
Influencing Factors ◽  
Search Algorithm ◽  
Carbon Price ◽  
Carbon Trading ◽  
Price Prediction ◽  
Model Based ◽  
Mode Decomposition ◽  
Learning Machine

Carbon emission reduction is now a global issue, and the prediction of carbon trading market prices is an important means of reducing emissions. This paper innovatively proposes a second decomposition carbon price prediction model based on the nuclear extreme learning machine optimized by the Sparrow search algorithm and considers the structural and nonstructural influencing factors in the model. Firstly, empirical mode decomposition (EMD) is used to decompose the carbon price data and variational mode decomposition (VMD) is used to decompose Intrinsic Mode Function 1 (IMF1), and the decomposition of carbon prices is used as part of the input of the prediction model. Then, a maximum correlation minimum redundancy algorithm (mRMR) is used to preprocess the structural and nonstructural factors as another part of the input of the prediction model. After the Sparrow search algorithm (SSA) optimizes the relevant parameters of Extreme Learning Machine with Kernel (KELM), the model is used for prediction. Finally, in the empirical study, this paper selects two typical carbon trading markets in China for analysis. In the Guangdong and Hubei markets, the EMD-VMD-SSA-KELM model is superior to other models. It shows that this model has good robustness and validity.

scholarly journals Sparse Feature Learning of Hyperspectral Imagery via Multiobjective-Based Extreme Learning Machine

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1262 ◽  
Author(s):  
Xiaoping Fang ◽  
Yaoming Cai ◽  
Zhihua Cai ◽  
Xinwei Jiang ◽  
Zhikun Chen
Keyword(s):  
Multiobjective Optimization ◽  
Extreme Learning Machine ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Spectral Band ◽  
Feature Learning ◽  
Pareto Solution ◽  
Conflicting Objectives ◽  
Learning Machine ◽  
Hidden Layer

Hyperspectral image (HSI) consists of hundreds of narrow spectral band components with rich spectral and spatial information. Extreme Learning Machine (ELM) has been widely used for HSI analysis. However, the classical ELM is difficult to use for sparse feature leaning due to its randomly generated hidden layer. In this paper, we propose a novel unsupervised sparse feature learning approach, called Evolutionary Multiobjective-based ELM (EMO-ELM), and apply it to HSI feature extraction. Specifically, we represent the task of constructing the ELM Autoencoder (ELM-AE) as a multiobjective optimization problem that takes the sparsity of hidden layer outputs and the reconstruction error as two conflicting objectives. Then, we adopt an Evolutionary Multiobjective Optimization (EMO) method to solve the two objectives, simultaneously. To find the best solution from the Pareto solution set and construct the best trade-off feature extractor, a curvature-based method is proposed to focus on the knee area of the Pareto solutions. Benefited from the EMO, the proposed EMO-ELM is less prone to fall into a local minimum and has fewer trainable parameters than gradient-based AEs. Experiments on two real HSIs demonstrate that the features learned by EMO-ELM not only preserve better sparsity but also achieve superior separability than many existing feature learning methods.

Sign in / Sign up

Export Citation Format

Share Document