Time-domain Feature Parameters Research Articles

Research on internal leakage detection of the ball valves based on stacking ensemble learning

Abstract Natural gas is an important clean energy source that is mainly transported through pipelines. The ball valve is a crucial piece of control equipment for the pipeline transportation system for natural gas, and the failure of internal leakage of the ball valve will seriously affect the natural gas transmission and increase the risk of sudden safety accidents. In response to the problems of the limitations of a single machine learning model in the traditional ball valve internal leakage rate prediction methods and failure to qualitatively analyze unilateral and bilateral internal leakage recognition of ball valve, a study of ball valve internal leakage detection based on Stacking ensemble learning is proposed. A total of 15 time and frequency domain feature parameters were obtained by feature extraction of 125 and 96 sets of raw acoustic emission signals from the ball valve; the parameters of a single machine learning model were adjusted by Bayesian optimization grid search. An internal leakage rate prediction model and an internal leakage recognition model are constructed, and the proposed model is compared and analyzed with a single model through a field ball valve internal leakage test. The results indicate that the Stacking ensemble learning model outperforms each single machine learning model in terms of SMAPE (17.2583), RMSE (1.1009), and MAE (0.9375) for internal leakage rate prediction. The Stacking ensemble learning model outperformed the single machine learning model in terms of accuracy (1), recall (1), precision (1), FAR(0), and F1-score (1) for internal leakage recognition. Stacking ensemble learning significantly enhances the model's ability to detect internal ball valve leaks.

Welding Penetration Monitoring for Ship Robotic GMAW Using Arc Sound Sensing Based on Improved Wavelet Denoising

The arc sound signal is one of the most important aspects of information related to pattern identification regarding the penetration state of ship robotic GMAW; however, arc sound is inevitably affected by noise interference during the signal acquisition process. In this paper, an improved wavelet threshold denoising method is proposed to eliminate interference and purify the arc sound signal. The non-stationary random distribution characteristics of GMAW noise interference are also estimated by using the high-frequency detail coefficients in different domains after wavelet transformation, and a mode of measuring scale that is logarithmically negatively correlated with the wavelet decomposition scale is created to update the threshold. The gradient convergent threshold function is established using the natural logarithmic function structure and concave–convex gradient to enable the nonlinear adjustment of the asymptotic rate. Further, some property theorems related to the optimized threshold function are proposed and theoretically proven, and the effectiveness and adaptability of the improved method are verified via the denoising simulation of speech synthesis signals. The four traditional denoising methods and our improved version are applied in the pretreatment of the GMAW arc sound signal, respectively. Statistical analysis and short-time Fourier transform are used to extract eight-dimensional time and frequency domain feature parameters from the denoised signals with randomly time-varying characteristics, and the extracted joint feature parameters are used to establish a nonlinear mapping model of penetration state identification for ship robotic GMAW using the pattern classifiers of RBFNN, PNN and PSO-SVM. The simulation results yielded by visual penetration classification and the multi-dimensional evaluation index of the confusion matrix indicate that the improved denoising method proposed in this paper achieves a higher accuracy in the extraction of penetration state features and greater precision in the identification of pattern classification.

A simple proposition for heart sound signal de-noising for effective components identification in normal and abnormal cases

Mass scale, simple, efficient, minimum infrastructure-based engineering approach with an inbuilt detection capability of Heart Sound Signal (HSS) can save many lives due to cardiovascular diseases in a rural area of any developing country lacking super medical facilities and expert medical practitioners. De-noising of HSS is a crucial step for reliable and accurate identification sound components such as S1, S2, and others as HSS gets easily corrupted with random internal and external noise sources. In recent years, Wavelet-based filtering methods are the most common for de-noising of HSS for which selection of correct wavelet, level of decomposition, the best threshold selection are crucial for which excellent domain expertise is inevitable. Though these methods provide excellent returns in high-frequency noise/murmurs elimination, low-frequency noise/murmurs in abnormal HSS cannot be detected adequately as the noise/murmur spectrum overlaps with HSS component. This paper introduces a simple but very effective Power Law Algorithm (PLA) that performs de-noising in the time domain for efficient Heart Sound component identification both in normal and abnormal cases. A comparative study with qualitative (based on the visual parameter) and quantitative analysis (based on SNR and FIT coefficient) on de-noised HSSs has been performed that clearly shows PLA based method improves quality components identification than using wavelet thresholding. Further, time-domain feature parameters and power spectral density representation of the PLA-based de-noised signal exhibits a definite indication of the algorithm's efficacy towards heart sound classification both for Normal or Abnormal classes.

Effect of wheel polygonalization on the Degree of Non-linearity of dynamic response of high-speed vehicle system

Polygonalization of the wheel describes the growth of out-of-round profiles of the wheels of railway vehicle. This problem was identified in the 1980s but its mechanism is still not well understood. The wheel-rail disturbance formed by wheel polygonalization will accelerate the fatigue fracture of the key parts of rail vehicles and seriously threaten the safety of rail vehicle. This fact has led to significant efforts in detecting and diagnosing wheel polygonalization, in particular in setting the criteria for health monitoring. Currently, the time-domain feature parameters extraction method based on data statistics and frequency-domain feature parameters extraction method based on spectrum estimation are widely applied to detect wheel polygonalization. However, the basis of spectral estimation is the Fourier transform, which is not good at dealing with non-linear vibration systems (such as vehicle-track coupled system). Aiming at the wheel polygonalization problem existing in high-speed train, the non-linear extent of vibration response of vehicle system caused by wheel polygonalization is analyzed based on vehicle-track coupled dynamics and adaptive data analysis method. A typical high-speed train model is established according to the vehicle-track coupled dynamics theory. The wheel polygonalization model is introduced and vehicle system vibration response is calculated by numerical integration. The vibration response signal is decomposed by empirical mode decomposition (EMD) to produce the intrinsic mode functions (IMFs). By calculating the intra-wave frequency modulation of IMFs, that is, the difference between instantaneous and mean frequencies and amplitudes, the non-linearity of the dynamic response is quantified. Influences of wheel polygonalization on the non-linearity of steady-state and unsteady vibration responses of vehicle system are analyzed in detail. An objective criterion for wheel polygonalization health monitoring based on Degree of Non-linearity is proposed, which provides an effective tool for prognostics and health management of trains.

Gearbox fault diagnosis through quantum particle swarm optimization algorithm and kernel extreme learning machine

Gearbox is the key component of mechanical transmission system. Accurate fault diagnosis of gearbox is of great significance to ensure the operation of rotating machinery. Based on the comprehensive simulation test-bed in the laboratory, a gearbox fault diagnosis method based on QPSO-KELM is proposed. Firstly, the fault pre planting experiments of gear fault, bearing fault and gear bearing mixed fault are carried out on the comprehensive simulation test-bed. Then, the vibration signals collected are preprocessed by TSA to eliminate noise. The time domain, frequency domain and NASA feature parameters of the preprocessed signals are taken as training samples and test samples of QPSO-KELM. The experimental results show that the proposed method can effectively solve the problem of gearbox fault pattern recognition, and the fault diagnosis accuracy is higher than traditional methods, so the research has certain reference significance and engineering application value.

A Diagnosis Method for the Compound Fault of Gearboxes Based on Multi-Feature and BP-AdaBoost

Gearbox is an important structure of rotating machinery, and the accurate fault diagnosis of gearboxes is of great significance for ensuring efficient and safe operation of rotating machinery. Aiming at the problem that there is little common compound fault data of gearboxes, and there is a lack of an effective diagnosis method, a gearbox fault simulation experiment platform is set up, and a diagnosis method for the compound fault of gearboxes based on multi-feature and BP-AdaBoost is proposed. Firstly, the vibration signals of six typical states of gearbox are obtained, and the original signals are decomposed by empirical mode decomposition and reconstruct the new signal to achieve the purpose of noise reduction. Then, perform the time domain analysis and wavelet packet analysis on the reconstructed signal, extract three time domain feature parameters with higher sensitivity, and combine them with eight frequency band energy feature parameters obtained by wavelet packet decomposition to form the gearbox state feature vector. Finally, AdaBoost algorithm and BP neural network are used to build the BP-AdaBoost strong classifier model, and feature vectors are input into the model for training and verification. The results show that the proposed method can effectively identify the gearbox failure modes, and has higher accuracy than the traditional fault diagnosis methods, and has certain reference significance and engineering application value.

Fault Identification Method of Diesel Engine in Light of Pearson Correlation Coefficient Diagram and Orthogonal Vibration Signals

In order to select fault feature parameters simply and quickly and improve the identification rate of diesel engine faults by using the vibration signals, this paper proposes a diesel engine fault identification method on the basis of the Pearson correlation coefficient diagram (PCC Diagram) and the orthogonal vibration signals. At first, the orthogonal vibration acceleration signals are synchronously acquired in the direction of the top and side of the cylinder head. And the time-domain feature parameters are extracted from the orthogonal vibration acceleration signals to obtain the Pearson correlation coefficient (PCC). Then, the correlation coefficient diagram used to do feature parameter screening is constructed by selecting the feature parameters with the correlation coefficient of more than 0.9. Finally, generalized regression neural network (GRNN) is adopted to classify and identify fuel supply fault in diesel engine. The results show that using the PCC Diagram can simplify the selection process of the feature parameters of the orthogonal vibration signals quickly and effectively. It can also improve the fault identification rate of diesel engine significantly with the help of adding the newly proposed cross-correlation coefficient of the orthogonal vibration signals into the GRNN input feature vector set.

EMD and GNN-AdaBoost fault diagnosis for urban rail train rolling bearings

Rolling bearings are the most prone components to failure in urban rail trains, presenting potential danger to cities and their residents. This paper puts forward a rolling bearing fault diagnosis method by integrating empirical mode decomposition (EMD) and genetic neural network adaptive boosting (GNN-AdaBoost). EMD is an excellent tool for feature extraction and during which some intrinsic mode functions (IMFs) are obtained. GNN-AdaBoost fault identification algorithm, which uses genetic neural network (GNN) as sub-classifier of the boosting algorithm, is proposed in order to address the shortcomings in classification when only using a GNN. To demonstrate the excellent performance of the approach, experiments are performed to simulate different operating conditions of the rolling bearing, including high speed, low speed, heavy load and light load. For de-nosing signal, by EMD decomposition is applied to obtain IMFs, which is used for extracting the IMF energy feature parameters. The combination of IMF energy feature parameters and some time-domain feature parameters are selected as the input vectors of the classifiers. Finally, GNN-AdaBoost and GNN are applied to experimental examples and the identification results are compared. The results show that GNN-AdaBoost offers significant improvement in rolling bearing fault diagnosis for urban rail trains when compared to GNN alone.

Comparison of AC and pulsed magnetization-based elasto-magnetic methods for tensile force measurement in steel strand

AC and pulsed magnetization-based elasto-magnetic measurement methods of tensile force in steel strand are compared in the study. Completely opposite conclusions on the dependency of maximum magnetic induction on the tensile force are drawn from the two modes. The opposite conclusions are consistent with the predicted results before and after the Villari reversal point. Harmonic and spectral analysis techniques are introduced to investigate new feature parameters for tensile force characterization. In AC mode, the distortion factor of the induced voltage signals demonstrates the better stability and force prediction accuracy than the conventional time-domain feature parameters of maximum magnetic induction and coercive force. In the pulsed mode, the linear correlation between the spectral amplitudes of the induced pulsed signals and the tensile force is analyzed. A new parameter, the summation of the spectrum amplitudes in a particular band, is introduced to characterize tensile force. The calibration curve for tensile force measurement with the new parameter shows a lower prediction error and hysteresis error compared to the time-domain analysis results. Conclusions obtained from the comparative study on the performance of the two magnetization modes and two types of parameters may provide new insights into the improvements in the tensile force detection accuracy of the elasto-magnetic methods.

Running State Evaluation Method of Turbine Bearing Based on Feature Vector

Due to the high modal coupling of the cooling turbine bearing in environment control system, it is very difficult to extract the vibration signal feature and construct the recognition model on different feature.Arunning state evaluation method of the turbine bearing is proposed based on the feature vector with limited testing data in this paper. Firstly, aiming at some failure modes in several typical faults of turbine bearing, three time domain feature parameters and seven frequency domain feature parameters are chosen to construct feature vector for discrimination. Then, the feature vectors of different fault testing data are dimensional reduced based on the principal component analysis method. Based on above, the support vector machine (SVM) model of the turbine bearing running state is proposed for monitoring and predicting the occurrence and development of typical turbine bearing failure modes. Experimental results suggest that the bearing running state evaluation method proposed in this paper can improve the prediction accuracy effectively.

A Novel Personalized Diagnosis Methodology Using Numerical Simulation and an Intelligent Method to Detect Faults in a Shaft

Personalized medicine is a hot topic to develop a medical procedure for healthcare. Motivated by molecular dynamics simulation-based personalized medicine, we propose a novel numerical simulation-based personalized diagnosis methodology and explain the fundamental procedures. As an example, a personalized fault diagnosis method is developed using the finite element method (FEM), wavelet packet transform (WPT) and support vector machine (SVM) to detect faults in a shaft. The shaft unbalance, misalignment, rub-impact and the combination of rub-impact and unbalance are investigated using the present method. The method includes three steps. In the first step, Theil’s inequality coefficient (TIC)-based FE model updating technique is employed to determine the boundary conditions, and the fault-induced FE model of the faulty shaft is constructed. Further, the vibration signals of the faulty shaft are obtained using numerical simulation. In the second step, WPT is employed to decompose the vibration signal into several signal components. Specific time-domain feature parameters of all of the signal components are calculated to generate the training samples to train the SVM. Finally, the measured vibration signal and its components decomposed by WPT serve as a test sample to the trained SVM. The fault types are finally determined. In the simulation of a simple shaft, the classification accuracy rates of unbalance, misalignment, rub-impact and the combination of rub-impact and unbalance are 93%, 95%, 89% and 91%, respectively, whereas in the experimental investigations, these decreased to 82%, 87%, 73% and 79%. In order to increase the fault diagnosis precision and general applicability, further works are continuously improving the personalized diagnosis methodology and the corresponding specific methods.

Research On The Classification For Faults Of Rolling Bearing Based On Multi-Weights Neural Network

abstract A methodology based on multi-weights neural network (MWNN) is presented to identify faults of rolling bearing. With considerations of difficulties in analyzing rolling bearing vibration data, we analyzed how to extract time domain feature parameters of faults. Further, the time domain feature parameters extracted from fault signals are utilized to train multi-weights neural network for achieving an optimal coverage of fault feature space. Thus, faults of rolling bearing can be identified. Finally, simulations results based on real sampling data indicate the effectiveness of the methodology proposed in this paper. In addition, simulation results also indicate that MWNN utilized in this paper is more excellent than probabilistic neural network (PNN) and suitable for the classification of small samples.

Wind Generator State Recognition Based on Information Fusion Technology

This paper mainly researches on information fusion technology in the application of wind generator state recognition. Set up the model of information fusion based on bayesian theory, and develop status identification system by the platform of Labview. Conduct the test on Drivetrain Diagnosis Simulator (DDS), Simulate the normal and fault condition of wind generator main drive system by using normal and fault gear. Collect the vibration data, extract time domain feature parameters of the vibration signal, and train the identification system with these features. Verify the accuracy of the recognition system through the experiment.

Fault Diagnosis of Hoist Gearbox Based on Time-Domain Analysis of EMD and Fuzzy Clustering

In this paper, the method of combining the time-domain analysis of empirical mode decomposition (EMD) and fuzzy clustering is explored for the hoist gearbox fault diagnosis. Firstly, it adopts the EMD technique to decompose the signal of vibration. With it, any complicated dataset can be decomposed into a finite and often small number of intrinsic mode functions (IMFs). Then a number of IMFs containing main fault information were selected, from which time domain feature parameters-- variance and kurtosis coefficient were extracted. At last, fuzzy clustering is used to diagnose and identify the kind of fault. The numerical simulation and the analysis of the response signal data from the hoist gearbox show that the method is effective at discriminating the three condition of the gear, i.e. the normal, surface fatigue pitting and cracked tooth.

Fault diagnosis of direct-drive wind turbine based on support vector machine

A fault diagnosis method of direct-drive wind turbine based on support vector machine (SVM) and feature selection is presented. The time-domain feature parameters of main shaft vibration signal in the horizontal and vertical directions are considered in the method. Firstly, in laboratory scale five experiments of direct-drive wind turbine with normal condition, wind wheel mass imbalance fault, wind wheel aerodynamic imbalance fault, yaw fault and blade airfoil change fault are carried out. The features of five experiments are analyzed. Secondly, the sensitive time-domain feature parameters in the horizontal and vertical directions of vibration signal in the five conditions are selected and used as feature samples. By training, the mapping relation between feature parameters and fault types are established in SVM model. Finally, the performance of the proposed method is verified through experimental data. The results show that the proposed method is effective in identifying the fault of wind turbine. It has good classification ability and robustness to diagnose the fault of direct-drive wind turbine.

A model for automatic identification of human pulse signals

This paper presents a quantitative method for automatic identification of human pulse signals. The idea is to start with the extraction of characteristic parameters and then to construct the recognition model based on Bayesian networks. To identify depth, frequency and rhythm, several parameters are proposed. To distinguish the strength and shape, which cannot be represented by one or several parameters and are hard to recognize, the main time-domain feature parameters are computed based on the feature points of the pulse signal. Then the extracted parameters are taken as the input and five models for automatic pulse signal identification are constructed based on Bayesian networks. Experimental results demonstrate that the method is feasible and effective in recognizing depth, frequency, rhythm, strength and shape of pulse signals, which can be expected to facilitate the modernization of pulse diagnosis.