Journal of Chemometrics最新文献

To address the issue of underreporting faults in the detection of tiny faults by dynamic factor analysis (DFA), a novel fault detection and diagnosis method based on DFA-sliding window combined with mean square error (DFA-SWMSE) is proposed. Firstly, the data matrix is augmented by introducing time lag shifts. Secondly, factor analysis (FA) is applied to the augmented data matrix, achieving dimensionality reduction and feature extraction while retaining most of the original data's information. Then, the sliding window technique is applied to calculate the mean square error of the dimensionally reduced data, allowing for the monitoring of the system's current state and the detection of tiny faults. Finally, effective fault diagnosis is achieved through the analysis of fault factors and variable contributions. The proposed method is validated using a complex dynamic numerical example and a three-tank system process named Sim3Tanks. This system has gained widespread application in the field of process fault detection due to its ability to simulate and generate various types of faults. The proposed method is compared with principal component analysis (PCA), dynamic principal component analysis (DPCA), PCA similarity factor (SPCA), FA, and DFA. The experimental results thoroughly validate the effectiveness of the proposed method in detecting and diagnosing tiny faults in dynamic processes.

Forensic chemists frequently employ statistical profiling approaches to assess the degree of similarity between samples of illicit drugs. Such profiling information can help reveal connections between nodes in distribution networks and manufacturing laboratories. For amphetamine, the routine method of comparing a pair of samples includes the use of a dissimilarity measure based on the Pearson correlation coefficient calculated between their chemical profiles obtained through gas chromatography–mass spectrometry. This simple measure of (dis)similarity has been shown distinguish pairs sharing a common origin (e.g., same production batch) to a reasonable level of accuracy. However, Pearson correlation fails to capture all the relevant notions of similarity between chemical profiles of amphetamine. We present a new statistical method for forensic drug comparison that uses a more sophisticated statistical modelling approach to determine similarity between samples. We show that this leads to improved performance over the correlation-based approach. The proposed method is easily extendable and has an intuitive interpretation both from chemistry and forensic perspectives, which supports wide applicability to illicit drug profiling in practice.

Water structures take an important role in chemical and biological systems, because the structure and function of a molecule may depend on the structure of water with which the molecule interacts. Near-infrared (NIR) spectroscopy has been proven to be powerful in analyzing the structure of water due to its sensitive response to OH. However, chemometrics is vitally important in the analysis of NIR spectrum of water due to the low resolution of the spectrum and the complexity of the water structures. In this review, chemometric methods for structural analysis of water in aqueous systems, particularly in chemical and biological processes, by NIR spectroscopy were summarized, from the improvement of spectral resolution to the effective extraction of the spectral information of different water structures. Through the changes of the spectral features of the water structures, the structural transformation of proteins, thermo-responsive polymers, antifreeze agents, as well as the structural variation of water in the transformation were elucidated. Water was proved to be a good probe for analyzing the structure and interactions in aqueous solutions and chemical/biological processes by NIR spectroscopy.

In practical industrial applications, equipment usually operates normally and failures are relatively rare, resulting in serious imbalances in the collected data. This imbalance leads to issues such as overfitting, instability, and poor robustness, significantly reducing the accuracy and stability of fault diagnosis system. To address these challenges, this research proposes a method for imbalanced data augmentation and industrial process fault diagnosis based on improved Generative Adversarial Network (GAN). The method adopts Wasserstein distance with gradient penalty and integrates residual connections into the architecture of the generator. This innovation not only helps improve gradient transfer in the generator, but also significantly enhances the data generation capabilities of the generative model through improving the stability of training. Limited industrial process data is used by a generative model to produce synthetic samples with high similarity and diversity. These high-quality samples improve fault diagnosis by enriching the imbalanced dataset. Experimental results on two industrial datasets confirm the method's effectiveness in enhancing fault diagnosis performance with limited data.

Dendrobium officinale is a medicinal and food plant with high commercial and medicinal value. Yunnan is known as China's “plant kingdom,” and although the climatic conditions are favorable, the large vertical climatic differences have led to a large difference in the quality of dendrobium from different origins. The analysis of quality differences between several origins with large ecological advantages has not been reported yet. Therefore, the aim of this study is to compare these regions in terms of both morphology and chemical composition and to analyze the variation of their chemical composition in spectral information. The PLS-DA, SVM, and PLSR models were developed to qualitatively and quantitatively evaluate Dendrobium from different production areas. The results show that the Menghai production area was superior to other production areas in terms of phenotypic morphology, quality, and yield. Within the appropriate range, the higher the specific absorbance, the higher the quercetin content.

Aiming at the difficulty of detecting time-lag faults in dynamic processes, a fault detection strategy based on time neighborhood difference (TND) is proposed, and it is introduced into the partial least squares (PLS) method to suggest the PLS-TND fault detection method. The TND method takes the mean to the multibatch training set to obtain a baseline training set, and it constructs the mean squared Euclidean distance (MSED) statistic by calculating the average distance between the sample's first k-moments neighborhood samples and samples at the same moment in the baseline training set. The TND method can help the PLS method to effectively detect time-lag faults and significantly improve the fault detection capability of PLS by measuring the overall positional difference between the temporal neighborhood sample set of the sample and its temporal neighborhood sample set in the baseline training set. The PLS-TND method is compared with some classical fault detection methods through a numerical simulation process and a Continuous Stirred Tank Reactor (CSTR) system design fault detection experiment. The PLS-TND method gives the best performance of fault detection.

In this article, we propose a novel classification approach for functional data based on a shrinkage estimate of functional Mahalanobis distance. We first introduce a new shrinkage functional Mahalanobis distance (SFMD), by using this new distance, we transform the functional observations into a set of vector-valued pseudo-samples. Furthermore, we adopt some good classification algorithms designed for multivariate data to this pseudo-samples instead of the original functional data. The new approach has advantage of highly flexible and scalable, that is, it can easily combine with any classification algorithm, such as support vector machine, tree-based methods, and neural networks. We demonstrate the performance of the proposed functional classifier through both extensive simulation studies and two real data applications.