Complex Nonlinear Signals Research Articles

Self-supervised learning for denoising of multidimensional MRI data.

To develop a fast denoising framework for high-dimensional MRI data based on a self-supervised learning scheme, which does not require ground truth clean image. Quantitative MRI faces limitations in SNR, because the variation of signal amplitude in a large set of images is the key mechanism for quantification. In addition, the complex non-linear signal models make the fitting process vulnerable to noise. To address these issues, we propose a fast deep-learning framework for denoising, which efficiently exploits the redundancy in multidimensional MRI data. A self-supervised model was designed to use only noisy images for training, bypassing the challenge of clean data paucity in clinical practice. For validation, we used two different datasets of simulated magnetization transfer contrast MR fingerprinting (MTC-MRF) dataset and in vivo DWI image dataset to show the generalizability. The proposed method drastically improved denoising performance in the presence of mild-to-severe noise regardless of noise distributions compared to previous methods of the BM3D, tMPPCA, and Patch2self. The improvements were even pronounced in the following quantification results from the denoised images. The proposed MD-S2S (Multidimensional-Self2Self) denoising technique could be further applied to various multi-dimensional MRI data and improve the quantification accuracy of tissue parameter maps.

Amplitude-based multiscale reverse dispersion entropy: a novel approach to bearing fault diagnosis

The multiscale fluctuation dispersion entropy algorithm (MFDE) is widely used to extract the characteristics from a variety of complex nonlinear signals, including bearing signals, due to its excellent performance to quantify the uncertainties of complex nonlinear systems. However, limited by the classification number and coarse-graining process, the periodic impulses generated by the defect point cannot be effectively detected by MFDE, restraining the characterization abilities of entropy features and resulting in undesirable diagnosis results for bearing faults. To overcome the disadvantages of MFDE, an amplitude-based multiscale dispersion entropy (AMDE) is proposed in this paper. The AMDE utilizes the phase scale factor to calculate multiple groups of amplitude difference series that contain different amplitude information. As such, the amplitude compression caused by the large-scale factor in traditional coarse-graining process is avoided, and the calculated entropy features not only characterize the irregularity of the whole signal but also reflect the changes of the impulse components. Afterwards, the perception range and the sensibility of AMDE are expanded and enhanced for amplitude variation, and the coarse-graining process and Gaussian reference are used to obtain multi-dimensional reversed entropy features. Combining those steps, the amplitude-based multiscale reverse dispersion entropy (AMRDE) algorithm is proposed. Finally, the capability of the proposed algorithm to track the amplitude variation and fluctuation is successfully demonstrated by analyzing noisy signals and amplitude-modulated signal. Meanwhile, the features extracted from bearing signals demonstrated that it is effective to use AMRDE to represent the health conditions of rolling bearing. Therefore, the entropy metric calculated by AMRDE can be the useful indicator in the fields of mechanical equipment fault diagnosis, structural health monitoring, and so on.

Signal estimation and filtering from quantized observations via adaptive stochastic resonance.

Using a gradient-based algorithm, we investigate signal estimation and filtering in a large-scale summing network of single-bit quantizers. Besides adjusting weights, the proposed learning algorithm also adaptively updates the level of added noise components that are intentionally injected into quantizers. Experimental results show that minimization of the mean-squared error requires a nonzero optimal level of the added noise. The process adaptively achieves in this way a form of stochastic resonance or noise-aided signal processing. This adaptive optimization method of the level of added noise extends the application of adaptive stochastic resonance to some complex nonlinear signal processing tasks.

Research Progress on Intelligent System’s Learning, Optimization, and Control—Part II: Online Sparse Kernel Adaptive Algorithm

When dealing with complex nonlinear signals in intelligent system, by defining the inner product of two data vectors in the feature space, the kernel function can reflect the nonlinear mapping relationship between reproducing kernel Hilbert space (RKHS) and original data space. Therefore, by implementing classical linear adaptive filtering in RKHS space, the filtering operation can be expressed as a special relation of inner product with kernel function, which is referred to as “kernel trick.” As long as these algorithms can be expressed in the form of inner product, not only the convex least squares problem can be solved iteratively, but also the nonlinear adaptive filtering algorithms can be obtained, which have both general approximation characteristics and convexity. Therefore, the combination of kernel method and adaptive filtering algorithm is realized. On the other hand, since the Gram matrix is used, the dimension of kernel adaptive algorithm is determined by the number of data samples. When the number of observation sample point is increasing, the size of the state space increases exponentially with the growth of the dimension. Thereby, the kernel adaptive algorithm should solve the problem of online sparsification to avoid “curse of dimensionality.” As part II, based on online sparse kernel learning and the classical adaptive filtering algorithm, the kernel adaptive algorithms and online sparse algorithms are investigated in this paper. The main works of this paper have two aspects. First, combined with classical adaptive algorithm and kernel feature mapping, this paper investigates the basic concept of kernel adaptive algorithm and the realization mechanism of four kernel adaptive algorithm intensively: 1) kernel least mean squares; 2) kernel recursive least squares; 3) kernel affine projection algorithm; and 4) kernel principal component analysis. Second, in order to reduce the computational complexity, this paper studies some online sparse algorithms which include novel criterion, approximate linear dependency, sliding window, coherence criterion, surprise criterion, and so on. Finally, this paper summarizes the essence of existing conclusions of above algorithms and perspectives the future research direction.

Attention-Based LSTM Network for Rotatory Machine Remaining Useful Life Prediction

As one of the key components in mechanical systems, rotatory machine plays a significant role in safe and stable operation. Accurate prediction of the Remaining Useful Life (RUL) of rotatory machine contributes to realization of intelligent operation and maintenance for mechanical manufacturing. In order to overcome the limitations of traditional machine learning algorithms in dealing with complex nonlinear signals, a novel prediction framework for RUL of rotatory machine based on deep learning is proposed in this paper. One-dimensional convolutional neural network is utilized to extract local features from the original signal sequence. In addition, the proposed framework analyzes sensor signals and predicts RUL by combining Long Short-Term Memory (LSTM) network with attention mechanism. Multi-layer LSTM is set up to extract useful temporal features layer by layer and improve the robustness of the model, while attention mechanism is able to effectively solve the problem of information loss in the long-distance signal transmission of LSTM. Through the feature extraction of multi-layer LSTM and the strong supervision ability of attention mechanism, the RUL of rotatory machine can be accurately predicted. The experimental results show that the proposed method for RUL estimation is efficient and has higher prediction accuracy than the traditional machine learning algorithms.

Fault Detection and Isolation in Industrial Processes Using Deep Learning Approaches

Automated fault detection is an important part of a quality control system. It has the potential to increase the overall quality of monitored products and processes. The fault detection of automotive instrument cluster systems in computer-based manufacturing assembly lines is currently limited to simple boundary checking. The analysis of more complex nonlinear signals is performed manually by trained operators, whose knowledge is used to supervise quality checking and manual detection of faults. We present a novel approach for automated Fault Detection and Isolation (FDI) based on deep learning. The approach was tested on data generated by computer-based manufacturing systems equipped with local and remote sensing devices. The results show that the approach models the different spatial/temporal patterns found in the data. The approach can successfully diagnose and locate multiple classes of faults under real-time working conditions. The proposed method is shown to outperform other established FDI methods.

Fault Diagnosis of Reciprocating Compressor Based on Convolutional Neural Networks with Multisource Raw Vibration Signals

Reciprocating compressors are widely used in petroleum industry. Due to containing complex nonlinear signal, it is difficult to extract the fault features from its vibration signals. This paper proposes a new method named Convolutional Neural Network based on Multisource Raw vibration signals (MSRCNN). The proposed method uses multisource raw vibration signals collected by several sensors as input and uses the designed CNN to operate both the feature extraction and classification. The gas valve signals of reciprocating compressor in different states are used as the experimental data. In order to test the effectiveness of the proposed method, it is compared with the traditional BP (Back‐Propagation) neural network fault diagnosis method based on power spectrum energy and wavelet packet energy. In order to further test the antinoise performance of the proposed method, some noisy signals with different signal‐to‐noise ratios were constructed by adding white noise into sampled signals for testing. The results show that the MSRCNN model has higher fault recognition rate than the traditional methods. This indicates that the MSRCNN method not only has good fault recognition effect, but also has certain antinoise performance.

Correction of complex nonlinear signal response from a pixel array detector.

The pulsed free-electron laser light sources represent a new challenge to photon area detectors due to the intrinsic spontaneous X-ray photon generation process that makes single-pulse detection necessary. Intensity fluctuations up to 100% between individual pulses lead to high linearity requirements in order to distinguish small signal changes. In real detectors, signal distortions as a function of the intensity distribution on the entire detector can occur. Here a robust method to correct this nonlinear response in an area detector is presented for the case of exposures to similar signals. The method is tested for the case of diffuse scattering from liquids where relevant sub-1% signal changes appear on the same order as artifacts induced by the detector electronics.

Classification of surface EMG signal with fractal dimension

Surface EMG (electromyography) signal is a complex nonlinear signal with low signal to noise ratio (SNR). This paper is aimed at identifying different patterns of surface EMG signals according to fractal dimension. Two patterns of surface EMG signals are respectively acquired from the right forearm flexor of 30 healthy volunteers during right forearm supination (FS) or forearm pronation (FP). After the high frequency noise is filtered from surface EMG signal by a low-pass filter, fractal dimension is calculated from the filtered surface EMG signal. The results showed that the fractal dimensions of filtered FS surface EMG signals and those of filtered FP surface EMG signals distribute in two different regions, so the fractal dimensions can represent different patterns of surface EMG signals.