A universal multi-source domain adaptation method with unsupervised clustering for mechanical fault diagnosis under incomplete data.

Recently, due to the difficulty of collecting condition data covering all mechanical fault types in industrial scenarios, the fault diagnosis problem under incomplete data is receiving increasing attention where no target prior information can be available. The existing open-set or universal domain adaptation (DA) diagnosis methods typically treat private fault samples in the target as a generalized "unknown" fault class, neglecting their inherent structure. This oversight can lead to confusion in latent feature space representations and difficulties in separating unknown samples. Therefore, a universal DA method with unsupervised clustering is developed to explore the intrinsic structure of the target samples for mechanical fault diagnosis, where multi-source information on different working conditions is considered to transfer complementary knowledge. First, a composite clustering metric combining single-domain and cross-domain evaluation is constructed to recognize shared and unknown health classes on source-target domains. Second, to alleviate the intra-class shift while enlarging the inter-class gap, a class-wise DA algorithm is suggested which operates on the basis of maximum mean discrepancy. Finally, an entropy regularization criterion is utilized to facilitate clustering of different health classes. The efficacy of the presented approach in the fault diagnosis issues when monitoring data is inadequate has been verified through extensive experiments on three rotating machinery datasets.

Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis.

Intelligent fault diagnosis aims to build robust mechanical condition recognition models with limited dataset. At this stage, fault diagnosis faces two practical challenges: (1) the variability of mechanical working conditions makes the collected data distribution inconsistent, which brings about the domain shift; (2) some unpredictable unknown fault modes that do not observe in the training dataset may occur in the testing scenario, leading to a category gap. In order to cope with these two entangled challenges, an open set multi-source domain adaptation approach is developed in this study. Specifically, a complementary transferability metric defined on multiple classifiers is introduced to quantify the similarity of each target sample to known classes to weight the adversarial mechanism. By applying an unknown mode detector, unknown faults can be automatically identified. Moreover, a multi-source mutual-supervised strategy is further adopted to mine relevant information between different sources to enhance the model performance. Extensive experiments are conducted on three rotating machinery datasets, and the results show that the proposed method is superior to traditional domain adaptation approaches in the mechanical diagnosis issues that new fault modes occur.

A Novel Piecewise Tri-Stable Stochastic Resonance System Driven by Dichotomous Noise.

Stochastic resonance (SR) has been widely studied as a means of signal processing since its conception. Since SR is different from other denoising methods in nature, it can be used for not only feature extraction but also signal enhancement. Additive white Gaussian noise (AWGN) is often used as a driving source in SR research due to its convenience in numerical simulation and uniform distribution, but as a special noise, it is of great significance to study the SR principle of dichotomous noise as a driving source for nonlinear dynamics. In this paper, the method of piecewise tri-stable SR (PTSR) driven by dichotomous noise is studied, and it is verified that signal enhancement can still be achieved in the PTSR system. At the same time, the influence of the parameters of the PTSR system, periodic signal, and dichotomous noise on the mean of signal-to-noise ratio gain (SNR-GM) is analyzed. Finally, dichotomous noise and AWGN are used as the driving sources of the PTSR system, and the signal enhancement ability and noise resistance ability of the two drivers are compared.

Rolling mill health states diagnosing method based on multi-sensor information fusion and improved DBNs under limited datasets.

Due to the harsh working conditions and high cost of data acquisition in the actual environment of modern rolling mills, the resulting limited datasets issue leading in performance collapse of traditional deep learning (DL) methods has been plaguing researchers and needs to be urgently addressed. Hence, an improved single-sensor Deep Belief Network (IDBN) is first proposed to repetitively extract valuable information from hidden features and visible features of the previous improved Restricted Boltzmann Machine (IRBM) to alleviate this issue. Next, the multi-sensor IDBNs (MSIDBNs) are applied to obtain complementary and enriched health state features from different multi-sensor data to cope with limited datasets more effectively. Then, the Fast Fourier Transform (FFT) technique is adopted for the multi-sensor information to further enhance the effectiveness of feature extraction. Most importantly, the redefined pretraining and finetuning stages are designed for the MSIDBNs. Meanwhile, the optimal placement of multiple sensors is fully discussed to obtain the most efficient information about health content. Finally, two limited datasets are conducted to validate the superiority of the proposed MSIDBNs. Results show that the proposed MSIDBNs are capable of extracting valuable features from multi-sensor information and achieving more remarkable performance compared with the state-of-the-art (SOTA) methods under limited datasets.

Single-trial motor imagery electroencephalogram intention recognition by optimal discriminant hyperplane and interpretable discriminative rectangle mixture model.

Spatial filtering is widely used in brain-computer interface (BCI) systems to augmented signal characteristics of electroencephalogram (EEG) signals. In this study, a spatial domain filtering based EEG feature extraction method, optimal discriminant hyperplane-common spatial subspace decomposition (ODH-CSSD) is proposed. Specifically, the multi-dimensional EEG features were extracted from the original EEG signals by common space subspace decomposition (CSSD) algorithm, and the optimal feature criterion was established to find the multi-dimensional optimal projection space. A classic method of data dimension optimizing is using the eigenvectors of a lumped covariance matrix corresponding to the maximum eigenvalues. Then, the cost function is defined as the extreme value of the discriminant criterion, and the orthogonal N discriminant vectors corresponding to the N extreme value of the criterion are solved and constructed into the N-dimensional optimal feature space. Finally, the multi-dimensional EEG features are projected into the N-dimensional optimal projection space to obtain the optimal N-dimensional EEG features. Moreover, this study involves the extraction of two-dimensional and three-dimensional optimal EEG features from motor imagery EEG datasets, and the optimal EEG features are identified using the interpretable discriminative rectangular mixture model (DRMM). Experimental results show that the accuracy of DRMM to identify two-dimensional optimal features is more than 0.91, and the highest accuracy even reaches 0.975. Meanwhile, DRMM has the most stable recognition accuracy for two-dimensional optimal features, and its average clustering accuracy reaches 0.942, the gap between the accuracy of the DRMM with the accuracy of the FCM and K-means can reach 0.26. And the optimal three-dimensional features, for most subjects, the clustering accuracy of DRMM is higher than that of FCM and K-means. In general, the decision rectangle obtained by DRMM can clearly explain the difference of each cluster, notably, the optimization of multidimensional EEG features by optimal projection is superior to Fisher's ratio, and this method provides an alternative for the application of BCI. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-021-09768-w.

Bearing Fault Diagnosis of Hot-Rolling Mill Utilizing Intelligent Optimized Self-Adaptive Deep Belief Network with Limited Samples.

Given the complexity of the operating conditions of rolling bearings in the actual rolling process of a hot mill and the difficulty in collecting data pertinent to fault bearings comprehensively, this paper proposes an approach that diagnoses the faults of a rolling mill bearing by employing the improved sparrow search algorithm deep belief network (ISAA-DBN) with limited data samples. First, the fast spectral kurtosis approach is adopted to convert the non-stationary original vibration signals collected by the acceleration sensors installed at the axial and radial ends of the rolling mill bearings into two-dimensional (2D) spectral kurtosis time-frequency images with higher feature recognition, and the principal component analysis (PCA) technique is used to decrease the dimension of the data in order to achieve a high diagnosis rate with a limited number of samples. Subsequently, the sparrow search algorithm (SSA) is used to realize the intelligent optimized self-adaptive function of a deep belief network (DBN). Furthermore, the firefly disturbance algorithm is employed to improve the spatial search capability and robustness of SSA-DBN in order to achieve better performance of the ISSA-DBN method. Finally, the proposed approach is experimentally compared to other approaches used for diagnosis. The results show that the proposed approach not only retains the useful features of the data through dimension reduction but also improves the efficiency of the diagnosis and achieves the highest diagnosis accuracy with limited data samples. In addition, the optimal position of the sensor for diagnosing rolling mill roll faults is identified.

Multi-Representation Domain Adaptation Network with Duplex Adversarial Learning for Hot-Rolling Mill Fault Diagnosis.

The multi-process manufacturing of steel rolling products requires the cooperation of complicated and variable rolling conditions. Such conditions pose challenges to the fault diagnosis of the key equipment of the rolling mill. The development of transfer learning has alleviated the problem of fault diagnosis under variable working conditions to a certain extent. However, existing diagnosis methods based on transfer learning only consider the distribution alignment from a single representation, which may only transfer part of the state knowledge and generate fuzzy decision boundaries. Therefore, this paper proposes a multi-representation domain adaptation network with duplex adversarial learning for hot rolling mill fault diagnosis. First, a multi-representation network structure is designed to extract rolling mill equipment status information from multiple perspectives. Then, the domain adversarial strategy is adopted to match the source and target domains of each pair of representations for learning domain-invariant features from multiple representation networks. In addition, the maximum classifier discrepancy adversarial algorithm is adopted to generate target features that are close to the source support, thereby forming a robust decision boundary. Finally, the average value of the predicted probabilities of the two classifiers is used as the final diagnostic result. Extensive experiments are conducted on an experimental platform of a four-high hot rolling mill to collect the fault state data of the reduction gearbox and roll bearing. The experimental results reveal that the method can effectively realize the fault diagnosis of rolling mill equipment under variable working conditions and can achieve average diagnostic rates of up to 99.15% and 99.40% on the data sets of the rolling mill gearbox and bearing, which are respectively 2.19% and 1.93% higher than the rates achieved by the most competitive method.

Discrimination Improvement Through Undesirable Feedback in Coupling Object Manipulation Tasks.

Subjective effort can significantly affect the ability of humans to act optimally in dynamic manipulation tasks. In a previous study, we designed a complex object coupling manipulation task that required tight performance and induced high cognitive workload. We hypothesize that strong-effort-related physiological reactivity during the dynamic manipulation task improves the user performance in an undesired task feedback situation. To test this hypothesis, using the motor intentions' discrimination from electroencephalogram (EEG) measurements, we evaluate the effort expended by 20 participants in a controlling task with constraints involving complex coupling objects. Specifically, the finer motor decisions are obtained from the controlling information in EEG by using two fingers from the same hand rather than two hands. The motor intention is decoded from a task-dependent EEG through a regularized discriminant analysis, and the area under the curve is [Formula: see text]. Furthermore, we compare the undesired and desired task feedback conditions along with the individual's effort dynamic adjustment, and investigate whether the undesired task feedback improved the discrimination of the motor activities. A stronger effort to attain the desired feedback state corresponds to improved motor activity discrimination from the EEG in the undesired task feedback scenario. The differences in the brain activities under the undesired and desired task feedback conditions are analyzed using brain-network-based topographical scalp maps. Our experiment provides preliminary evidence that inducing strong effort can improve discrimination performance during highly demanding tasks. This finding can advance our understanding of human attention, potentially improve the accuracy of intention recognition, and may inspire better EEG acquisition contexts.

Improvement motor imagery EEG classification based on sparse common spatial pattern and regularized discriminant analysis.

BACKGROUND: The classification of psychological tasks such as motor imagery based on electroencephalography (EEG) signals is an essential issue in the brain computer interface (BCI) system. The feature extraction is an important issue for improving classification accuracy of BCI system. NEW METHOD: For extracting discriminative features, common spatial pattern (CSP) is an effective feature extraction method. However, features extracted by CSP are dense, and even feature patterns are repeatedly selected in the feature space. A sparse CSP algorithm is proposed, which embeds the sparse techniques and iterative search into the CSP. To improve the classification performance, two regularization parameters are added to the traditional linear discriminant analysis (LDA). RESULTS: The sparse CSP algorithm can select several channels of EEG signals with the most obvious features. The improved regularized discriminant analysis is used to solve the singularity problem and improve the feature classification accuracy. Comparison with Existing Method(s): The proposed algorithm was evaluated by the data set I of the IVth BCI competition and our dataset. The experimental results of the BCI competition dataset show that accuracy of the improved algorithm is 10.75 % higher than that of the traditional algorithm. Comparing with the currently existing methods for the same data, it also shows excellent classification performance. The effectiveness of the improved algorithm is also shown in experiments on our dataset. CONCLUSIONS: It sufficiently proves that the improved algorithm proposed in this paper improves the classification performance of motor intent recognition.

Intentions Recognition of EEG Signals with High Arousal Degree for Complex Task.

This paper presents a novel electroencephalography (EEG) evoked paradigm based on neurological rehabilitation. By implementing a conceptual model "cup-and-ball" system, EEG signals in manipulating the dynamic constrained objects are generated. Based on the operational EEG signals, a method is proposed to recognize different mental intentions. Under the manipulating task with a high arousal level, common spatial patterns (CSP) is used to extract and optimize features of the EEG signals from ten participants. Quadratic discriminant analysis (QDA) is implemented on EEG signals in different dimensions to identify different EEG patterns. The cross-validation is used to make classifier adaptive to a given data set. The receiver operating characteristic (ROC) curves are presented to illustrate recognition performance. The classification effect of QDA is verified by paired t-test (P < 0.001). Based on the proposed method, the average accuracy of mental intentions is 0.9857 ± 0.0191 and the area under the ROC curve (AUC) is 0.9665 ± 0.0291. The performance of QDA is also compared with the other three classifiers such as the support vector machine (SVM), the decision tree (DT) and the k-nearest neighborhood (k-NN) rule. The results suggest that the proposed method is very competitive with other methods.

Automatic Detection of Epileptic Seizures in EEG Using Sparse CSP and Fisher Linear Discrimination Analysis Algorithm.

In order to realize the automatic epileptic seizure detection, feature extraction and classification of electroencephalogram (EEG) signals are performed on the interictal, the pre-ictal, and the ictal status of epilepsy patients. There is no effective strategy for selecting the number of channels and spatial filters in feature extraction of multichannel EEG data. Therefore, this paper combined sparse idea and greedy search algorithm to improve the feature extraction of common space pattern. The feature extraction can effectively overcome the repeating selection problem of feature pattern in the eigenvector space by the traditional method. Then we used the Fisher linear discriminant analysis to realize the classification. The results show that the proposed method can get high classification accuracy using fewer data. For 10 subjects, the averaged accuracy of epilepsy detection is more than 99%. So, the detection of an epileptic seizure based on sparse features using Fisher linear discriminant analysis classifiers is more suitable for a reliable, automatic epileptic seizure detection system to enhance the patient's care and the quality of life.

Improvement Motor Imagery EEG Classification Based on Regularized Linear Discriminant Analysis.

Mental tasks classification such as motor imagery, based on EEG signals is an important problem in brain computer interface systems (BCI). One of the major concerns in BCI is to have a high classification accuracy. The other concerning one is with the favorable result is guaranteed how to improve the computational efficiency. In this paper, Mu/Beta rhythm was obtained by bandpass filter from EEG signal. And the classical linear discriminant analysis (LDA) was used for deciding which rhythm can give the better classification performance. During this, the common spatial pattern (CSP) was used to project data subject to the ratio of projected energy of one class to that of the other class was maximized. The optimal projection dimension was determined corresponding to the maximum of area under the curve (AUC) for each participant. Eventually, regularized linear discriminant analysis (RLDA) is possible to decode the imagined motor sensed using electroencephalogram (EEG). Results show that higher classification accuracy can be provided by RLDA. And optimal projection dimensions determined by LDA and RLDA are of consistent solution, this improves computational efficiency of CSP-RLDA method without computation of projection dimension.

Analytical investigation of modulation instability in a fiber Bragg grating.

Modulation instability (MI) in a fiber Bragg grating (FBG) is investigated and reviewed analytically. The dispersion relation equation of MI obtained from the coupled-mode equation is solved exactly. The closed-form expressions of the gain of MI and the threshold condition in the normal dispersion regime are derived. The results from the closed-form expressions are well consistent with those from numerical simulations and previous literature. Based on the analytical investigation, the characteristics of MI in an FBG are analyzed.