Fast Independent Component Analysis Method Research Articles

Rolling bearing compound fault diagnosis based on spatiotemporal intrinsic mode decomposition

Aiming at the vibration signal characteristics of multi-channel rolling bearing complex faults containing various shock components, a rolling bearing complex fault diagnosis model based on spatiotemporal intrinsic mode decomposition (STIMD) method and fast spectral kurtosis method was proposed. The spatiotemporal intrinsic mode decomposition method combines the signal atomic decomposition method with the idea of signal blind source separation. Through the fast independent component analysis and the nonlinear matching pursuit method of the established overcomplete dictionary base, various fault mode components are separated. The initial phase function selected based on the high kurtosis fault frequency band obtained by the fast spectral kurtosis method can better fit the bearing fault frequency domain characteristics, so that the spatiotemporal intrinsic mode decomposition method can more accurately separate various impact components in the vibration signal. The simulation model of bearing compound fault was established and the data collected from fault diagnosis experiment platform were used to verify that the STIMD method was effective in solving the problem of rolling bearing compound fault diagnosis. By analyzing the kurtosis changes under different signal noise ratio (SNR) conditions and comparing the simulation results with the fast independent component analysis method, it shows that the kurtosis index decomposed by the proposed method is more able to prove the existence of faults under the condition of low SNR, that is, the impact is completely covered by noise. Therefore, a spatiotemporal intrinsic mode decomposition method with fast spectral kurtosis optimization can solve the problem of blind source separation in the field of composite faults of multi-channel rolling bearings and realize composite fault diagnosis.

The parameter identification of metro rail corrugation based on effective signal extraction and inertial reference method

Rail corrugation is a severe track damage and failure problem in metro lines. So, the accurate assessment of rail corrugation is significant for the safety and comfort of vehicles. It is an efficient means to detect rail corrugation through the acceleration signal. However, the acceleration signal contains the mixed signal caused by vehicle component noise and wheel polygonal wear, resulting in poor rail corrugation detection accuracy. Therefore, a new method is presented to extract the effective signal components and accurately identify the rail corrugation. Firstly, the Cubic mapping, modified sine algorithm, and Lévy flight are introduced into the dung beetle optimizer algorithm. A new improved dung beetle optimizer (IDBO) algorithm is presented to optimize the hyperparameters of the VMD algorithm, which can increase the signal decomposition performance of the VMD. Secondly, the fast independent component analysis method separates the independent components (ICs) from the VMD modes and original acceleration signal. Based on the selection criteria of ICs, the dominant signal components related to rail corrugation are determined. The rail corrugation amplitude can be obtained through the inertial reference method. The experimental results demonstrate that the presented method has better rail corrugation recognition accuracy, the root mean square error is smaller than the comparison method, and the corrugation wavelength of the straight track is larger than the curve track.

Fetal electrocardiogram signal extraction and analysis method combining fast independent component analysis algorithm and convolutional neural network

Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.

Adaptive Fast Independent Component Analysis Methods for Mitigating Multipath Effects in GNSS Deformation Monitoring

Carrier-phase multipath is the main problem of GNSS deformation monitoring. Traditional methods usually adopt sidereal day filtering to mitigate the multipath. However, the necessity of presetting the session duration of the static baseline solution reduces the timeliness of the methods in real engineering. Moreover, these methods are not suitable for the systems that contain different types of GNSS satellites (e.g., BDS). To address the problems, this paper proposes an Adaptive Fast Independent Component Analysis (AF-ICA) method for mitigating multipath effects in GNSS deformation monitoring, which can effectively process the multi-GNSS data and separate several multipath signals. In the experimental study, compared with Sidereal Filtering in Observation Domain (SF-OD) method, AF-ICA method can improve both the positioning accuracy and peak-to-peak value. In GNSS deformation monitoring positioning accuracy, AF-ICA method can achieve the root-mean-square (RMS) of 1 mm horizon-tally and 2 mm vertically. Compared with the MSF method, the positioning accuracy of the AF-ICA method in the direction of ENU is improved by 44%, 14%, and 31%, respectively, and the corresponding peak-to-peak values increased by 36%, 17%, and 29%, respectively. Our proposed method can automatically get the monitoring information without estimating the orbit period in advance to realize automatic deformation monitoring. Through the automatic monitoring solution, the AF-ICA method in this paper can be applied to the natural disaster monitoring in the Internet of Things and provides real-time data monitoring information for disaster early warning.

Dimensional Reduction With Fast ICA for IoT Botnet Detection

The Internet of Things (IoT) has unique characteristics with a minimalist design and has network access with great scalability, which makes it difficult to control access. Setting up an intrusion detection system (IDS) on an IoT system while taking into account its unique characteristics is a big challenge. In this paper, we propose a dimensional reduction approach utilizing the fast independent component analysis (ICA) method to address scalability issues of IDS for IoT systems. Experimental results show that the reduction of dimensions by the fast ICA method overall improves the IDS execution time and does not significantly affect accuracy.

Fault diagnosis of rolling element bearing based on spatiotemporal intrinsic mode decomposition

In view of the problem that source signals cannot be effectively separated in the process of blind source separation of similar nonstationary nonlinear signals, a spatiotemporal intrinsic mode decomposition method was proposed for bearing fault diagnosis. Spatiotemporal intrinsic mode decomposition can separate source signals and construct Fourier basis dictionaries and nonlinear signal models. The fault components can be separated by using this method in fault diagnosis. The proper initial phase function is selected for blind source separation of signals and signal decomposition components are obtained. By simulation analysis, spatiotemporal intrinsic mode decomposition than the fast independent component analysis method can more intuitive clearly separate the signals of admixed with large modulation components of correlation coefficient, and through the impact of component kurtosis index to judge fault, inherent modal decomposition method better prove time restore original bearing vibration signals and fault impact. Through the analysis and comparison of experimental data, the spatiotemporal intrinsic mode decomposition method has a significant effect on the fault diagnosis and analysis of rolling bearing outer ring, inner ring, and can intuitively express the fault characteristic frequency and frequency doubling through the analysis of envelope spectrum. In processing the industrial data, the spatiotemporal intrinsic mode decomposition method can also find the frequency characteristics of inner ring fault more clearly and accurately. Therefore, the spatiotemporal intrinsic mode decomposition method can solve the problem of blind source separation and realize fault diagnosis in rolling bearing fault field.

High-Precision Identification of Power Quality Disturbances Under Strong Noise Environment Based on FastICA and Random Forest

The continuous integration of fluctuating distributed generators and nonlinear power electronic equipment have produced severe signal contamination and induced various power quality (PQ) problems to modern power systems. PQ disturbances (PQD) greatly ruin user experience and also bring significant power losses. Therefore, a high-precision machine learning-based PQD identification model is proposed in this article, which combines the advantages of the modified fast independent component analysis method and the improved random forest classifier. First, ten types of PQD models are established, and fast independent component analysis is adopted to denoise the PQD sample signals mixed with Gaussian noises. Second, the discrete wavelet transform is utilized to extract the statistical and wavelet-related features from the denoised PQD samples, so as to form the desired feature set. Finally, a random forest-based PQD identification model is proposed. Compared with several existing models, the proposed model has higher identification accuracy and stronger feasibility under strong noise environment, which could provide valuable information for future PQ management.

Brain Function Diagnosis Enhanced Using Denoised fNIRS Raw Signals

Nowadays, brain function evaluation using Functional Near Infrared Spectroscopy (fNIRS) is one of the most potential non-invasive monitoring techniques. This paper concerns usefulness of the NIRS signals denoising using the Hemodynamic Evoked Response (HomER) as graphical user interface displays the NIRS data, fast independent component analysis (FASTICA) method to reduce data dimension and the combined Wavelet & PCA method for enhancing NIRS signals. NIRS signals include many types of noise, spread across a broad spectrum of frequencies, such as: low frequency noise from respiratory interference, 0.1 - 0.3 Hz, Mayer wave, about 0.1 Hz, cardiac interference, 0.8 - 2.0 Hz, and other artifacts from head and facial motions. Meanwhile, electronic components generate high frequency noise. Multi-resolution wavelet and PCA was applied successfully to enhance the NIRS signals. It consists of adaptively modifying the wavelet coefficients based on the degree of noise contamination of the processed NIRS signal. This is done subsequently to the signal pre-processing by reducing data dimension using the FASTICA method. We demonstrate, using signal-to-noise ratio and correlation indicators, that the technique used is superior to the wavelet and moving average filter and outperforms the proposed denoising NIRS signal.

Study on Leakage Rate in Water Distribution Network Using Fast Independent Component Analysis

Abstract Analyzing the causes of urban water distribution network and taking the measures of leakage control are one of most serious issues which China water industry has been facing for a long time. This paper proposes a theory of blind source separation, which is applied to calculate the leakage of water distribution networks, special leakage experimental platform of water distribution networks is established. Fast independent component analysis method (FastICA) was successfully used to separate the physical leakage from total node flow, which provides a powerful support for reducing physical leakage.