Fault detection in multimodal processes based on the local entropy double subspace

Decentralized adaptively weighted stacked autoencoder-based incipient fault detection for nonlinear industrial processes

The self-attention mechanism has advantages in analyzing the internal characteristics of data and capturing local information. Therefore, it is applied to fault detection. Since complex industrial processes usually contain a mixture of properties, such as nonlinearity, dynamics, and non-Gaussianity, this places higher demands on fault detection methods. To further improve the performance of the self-attention mechanism for fault detection in complex industrial processes, an innovative self-attention mechanism integrating the adaptive double subspace (ISA-ADS) method is proposed for fault detection. First, the query matrix, the key matrix, and the value matrix of the self-attention mechanism are designed so that they can better focus on local information through the adaptive sample weight allocation strategy. At the same time, this design reduces the interference of nonlinear and noisy information and amplifies the impact of important fault information in the sample. Second, considering the problem of Gaussian and non-Gaussian distributions of the data and the different degrees of influence of different subspaces on the final process monitoring results, an adaptive Gaussian and non-Gaussian double subspace fault detection model based on the self-attention output matrix is established, which adaptively assigns different weights to different subspaces by determining their importance. The statistics of different subspaces are fused using the Bayesian inference and a new adaptive monitoring statistic is constructed to obtain a more accurate monitoring of the process state. Finally, the ISA-ADS is validated using the Tennessee Eastman (TE) process and the actual polyethylene production process. The results show that ISA-ADS has a low false alarm rate and a high fault detection rate, verifying the effectiveness of its fault detection performance.

This paper describes the application of principal component analysis (PCA) and independent component analysis (ICA) to identify the reference spectra of a pharmaceutical tablet's constituent compounds from Raman spectroscopic data. The analysis shows, first with a simulated data set and then with data collected from a pharmaceutical tablet, that both PCA and ICA are able to identify most of the features present in the reference spectra of the constituent compounds. However, the results suggest that the ICA method may be more appropriate when attempting to identify unknown reference spectra from a sample. The resulting PCA and ICA models are subsequently used to estimate the relative concentrations of the constituent compounds and to produce spatial distribution images of the analyzed tablet. These images provide a visual representation of the spatial distribution of the constituent compounds throughout the tablet. Images associated with the ICA scores are found to be more informative and not as affected by measurement noise as the PCA based score images. The paper concludes with a discussion of the future work that needs to be undertaken for ICA to gain wider acceptance in the applied spectroscopy community.

Manifold regularized stacked autoencoders-based feature learning for fault detection in industrial processes

Recently, blind source separation (BSS) methods have gained significant attention in the area of signal processing. Independent component analysis (ICA) and second-order blind identification (SOBI) are two popular BSS methods that have been applied to modal identification of mechanical and structural systems. Published results by several researchers have shown that ICA performs satisfactorily for systems with very low levels of structural damping, for example, for damping ratios of the order of 1% critical. For practical structural applications with higher levels of damping, methods based on SOBI have shown significant improvement over ICA methods. However, traditional SOBI methods suffer when nonstationary sources are present, such as those that occur during earthquakes and other transient excitations. In this paper, a new technique based on SOBI, called the modified cross-correlation method, is proposed to address these shortcomings. The conditions in which the problem of structural system identification can be posed as a BSS problem is also discussed. The results of simulation described in terms of identified natural frequencies, mode shapes, and damping ratios are presented for the cases of synthetic wind and recorded earthquake excitations. The results of identification show that the proposed method achieves better performance over traditional ICA and SOBI methods. Both experimental and large-scale structural simulation results are included to demonstrate the applicability of the newly proposed method to structural identification problems.

This paper proposes a robust independent component analysis (ICA) approach for noise reduction. Noise reduction is a difficult problem in ICA model. In general signal processing applications, there is more than one interference signal which may have unknown characteristics. In these situations, traditional linear ICA may lead to poor results. Hence, noise reduction is preferred to be performed with nonlinear adaptive filtering. In this paper, a radial basis function network (RBFN) is employed to transform the observed signals into output space in a nonlinear manner. The weights of RBFN are updated by utilizing a modified fixed‐point algorithm. The proposed method has not only the capacity of recovering the mixed signals, but also reducing noise with unknown characteristics from observed signals. The simulation results and analysis show that the proposed algorithm is suitable for practical unsupervised noise reduction problem. © 2008 Wiley Periodicals, Inc. Electron Comm Jpn, 91(3): 45–52, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10073

In this study, a system for faults detection using a combination of Support Vector Data Description (SVDD) with metaheuristic algorithms is presented. The presented approach is applied to a real industrial process where the set of measured faults is scarce. The original contribution in this work is the industrial context of application and the comparison of swarm intelligence algorithms to optimize the SVDD hyper-parameters. Four recent metaheuristics are compared hereby to solve the corresponding optimization problem in an efficient manner. These optimization techniques are then implemented for fault detection in a multivariate industrial process with non-balanced data. The obtained numerical results seem to be promising when the considered optimization techniques are combined with SVDD. In particular, the Spotted Hyena algorithm outperforms other metaheuristics reaching values of F1 score near 100% in fault detection.

Automatic facial feature extraction is one of the most important and attempted problems in computer vision. It is a necessary step in face recognition, facial image compression. There are many methods have been proposed in the literature for the facial feature extraction task. However, all of them have still disadvantage such as not complete reflection about face structure, face texture. Therefore, a combination of different feature extraction methods which can integrate the complementary information should lead to improve the efficiency of feature extraction stage. In this paper we describe a methodology for improving the efficiency of feature extraction stage based on the association of two methods: geometric feature based method and Independent Component Analysis (ICA) method. Comparison of two methods of facial feature extraction: geometric feature based method combined with PCA method (called GPCA) versus geometric feature based method combined with ICA method (called GICA) on CalTech dataset has demonstrated the efficiency of GICA method. Our results show that GICA achieved good performance 96.57% compared to 94.70% of GPCA method. Furthermore, we compare two methods mentioned above on our dataset, with performance of GICA being 98.94% better 96.78% of GPCA method. The experiment results have confirmed the benefits of the association geometric feature based method and ICA method in facial feature extraction.KeywordsFace recognitionindependent component analysis (ICA)principal component analysis (PCA)geometric features

<span>The purpose of this research is to observe the effectiveness of independent component analysis (ICA) method for denoising raw EEG signals based on word imagination, which will be used for word classification on unspoken speech. The electroencephalogram (EEG) signals are signals that represent the electrical activities of the human brain when someone is doing activities, such as sleeping, thinking or other physical activities. EEG data based on the word imagination used for the research is accompanied by artifacts, that come from muscle movements, heartbeat, eye blink, voltage and so on. In previous studies, the ICA method has been widely used and effective for relieving physiological artifacts. Artifact to signal ratio (ASR) is used to measure the effectiveness of ICA in this study. If the ratio is getting larger, the ICA method is considered effective for clearing noise and artifacts from the EEG data. Based on the experiment, the obtained ASR values from 11 subjects on 14 electrodes amounted are within the range of 0,910 to 1,080. Thus, it can be concluded that ICA is effective for removing artifacts from EEG signals based on word imagination.</span>

The quantity of mRNA transcripts in a cell is determined by a complex interplay of cooperative and counteracting biological processes. Independent Component Analysis (ICA) is one of a few number of unsupervised algorithms that have been applied to microarray gene expression data in an attempt to understand phenotype differences in terms of changes in the activation/inhibition patterns of biological pathways. While the ICA model has been shown to outperform other linear representations of the data such as Principal Components Analysis (PCA), a validation using explicit pathway and regulatory element information has not yet been performed. We apply a range of popular ICA algorithms to six of the largest microarray cancer datasets and use pathway-knowledge and regulatory-element databases for validation. We show that ICA outperforms PCA and clustering-based methods in that ICA components map closer to known cancer-related pathways, regulatory modules, and cancer phenotypes. Furthermore, we identify cancer signalling and oncogenic pathways and regulatory modules that play a prominent role in breast cancer and relate the differential activation patterns of these to breast cancer phenotypes. Importantly, we find novel associations linking immune response and epithelial–mesenchymal transition pathways with estrogen receptor status and histological grade, respectively. In addition, we find associations linking the activity levels of biological pathways and transcription factors (NF1 and NFAT) with clinical outcome in breast cancer. ICA provides a framework for a more biologically relevant interpretation of genomewide transcriptomic data. Adopting ICA as the analysis tool of choice will help understand the phenotype–pathway relationship and thus help elucidate the molecular taxonomy of heterogeneous cancers and of other complex genetic diseases.

This paper concentrates on investigating an enhanced independent component analysis (ICA) method for blind separation of signals corrupted by noise in wireless communications. Because of the traditional classical ICA methods that always have an inadequate capacity of anti-noise or insufficient separable ability in noise circumstance without satisfying practical application requirements. For this reason, two mechanisms are conducted to establish the modified cost function and fulfill the optimization assignment in the process of constituting an enhanced ICA algorithm. This proposed algorithm can benefit tremendously from the derived minimum bit error rate (BER) criterion and the novel adaptive moment estimation (Adam) optimization approach. In this work, firstly, the novel cost function is obtained according to minimum BER fused into maximum likelihood (ML) principle-based ICA cost function. Furthermore, by utilizing Adam processing, the task of blind separation of mixed signals is implemented via optimizing this modified cost function. Lastly, theoretical analysis and experiment results corroborate the better effectiveness and robustness of the proposed enhanced ICA algorithm compared with a series of popular representative ICA methods.

The electroencephalogram (EEG) is a set of data measured by electrodes placed on the scalp and is often under the influences of artifacts. Mental EEG is recorded when a person performs different mental tasks. In this article, we separated the mental EEG signals into independent components with individual meanings based on Independent Component Analysis (ICA) method, and the EEG was reconstructed by excluding those components related to ocular and line artifacts for further feature extraction. In the end, we made a simulation to compare denoising of mental EEG using ICA with the result using wavelet packet analysis. The ICA method was found to be more efficient than the classical methods.

Fault detection in continuous industrial processes is crucial to ensure production, quality, safety, environmental and economic aspects. Reliable fault detection systems have become even more necessary due to increasingly stringent regulations. The complexity of processes, on the one hand, and the availability of data, on the other, have spread the adoption of the data-driven approach for industrial fault detection. Deep Reinforcement Learning (RL) has recently been applied for this purpose, mainly in rotating machinery and rolling bearings. In chemical processes, most RL applications are in process control. The main contribution of this work lies in proposing a reinforcement learning (RL)-based framework for fault detection in continuous chemical processes. The challenges are related to the large number of variables, nonlinear relationships and changing operational dynamics, to name a few. The classic Tennessee Eastman Process (TEP) benchmark was used as a case study. The results were compared with Principal Component Analysis (PCA), commonly used for chemical process monitoring, dynamic PCA (DPCA), and neural networks. Compared to PCA, the RL approach showed considerably lower missed detection rate (MDR) and time to detection (TTD) while maintaining reasonable false alarm rate (FAR) for all hard-to-detect faults, contributing to early fault detectability. Similar results were obtained with regard to DPCA. Compared to the supervised approach, RL proved to be more flexible regarding model parameterization, which can be very useful for practical aspects of industrial fault detection. The results show that RL-based approaches can be very useful for fault detection in continuous, non-linear, and time-varying systems, such as chemical processes. For example, with regard to adaptive alarm thresholds and the detection of known and unknown faults. The latter represents a major challenge in industrial practice.

Traditional independent component analysis (ICA) method based on FastICA algorithm faced two main disadvantages.One is that the order of the independent components (ICs) is difficult to be determined and the other is that the FastICA algorithm often leads to local minimum solution, and the suitable source signals are not isolated.To alleviate these problems, an improved ICA algorithm based on artificial immune system (AIS) (called AIS-ICA) is presented. AIS is an attractive heuristic technique and has many advantages over other heuristic techniques such as it can be easily implemented and has great capability of escaping local optimal solutionsThe basic idea of the proposed AIS-ICA algorithm is to use AIS to determine the separating matrix of ICA.Simulation results from the artificial signal data illustrate the efficiency of the proposed AIS-ICA approach.

Not alike to principal component analysis (PCA) based monitoring statistics (T2 and SPE), the control limits for independent component analysis (ICA) monitoring statistics (I2 , Ie 2 and SPE) cannot be determined directly from a particular approximation distribution due to latent variables do not follow Gaussian distribution. Lee et al. (2004) proposed to use kernel density estimation (KDE) to obtain the control limits. However, the KDE method is very sensitive to the choice of smoothing parameter. Therefore, this study utilizes the support vector machine (SVM) for process fault detection by taking information of ICA extracted statistics as inputs of SVM. The proposed method (named, ICA-SVM) will be implemented in the Tennessee Eastman Process. In which, several multivariate monitoring schemes such as PCA, ICA, modified ICA and ICA- PCA will be also compared to demonstrate the efficiency of proposed method.