Search

Belt conveyors are critical in coal transportation systems; however, they are supported by rollers, which incur high energy costs. Magnetic levitation support is adopted. The measurement of a magnetic levitation air gap is important, and a displacement sensor is usually used in real-time. To address the problems of poor linearity and low measurement stability of single displacement sensors in magnetic levitation systems, a magnetic levitation support system based on multi-sensor data fusion is proposed. First, an industrial camera sensor is used to collect images, and the suspended air gap is obtained through image processing. Second, using an extended Kalman filter, the photoelectric position sensor and industrial camera sensor are fused to the suspension air gap value in the process of suspension. The electromagnet current is controlled by the PID (proportion integration differentiation) control algorithm, and experiments are carried out. Experimental results showed that, compared with an estimation of the suspension state of two sensors before and after EKF fusion, the root mean square error is reduced by 0.0597 and 0.0081, respectively, compared with the measurement value of a single sensor. Moreover, the fusion data were more robust, thereby meeting the requirements of magnetic levitation control.

The capability of deep learning (DL) techniques for dealing with non-linear, dynamic and correlated data has paved the way for DL-based fault detection and diagnosis (FDD). Among them, autoencoders (AEs) have shown their potential to serve as the fault detection network. However, misclassifying faulty samples that share similar patterns to normal samples is a common drawback of AEs. In this work, a source-aware autoencoder (SAAE) is proposed as an extension of AEs to incorporate faulty samples in the training stage. In SAAE, flexibility in tuning recall and precision trade-off, ability to detect unseen faults and applicability in imbalanced data sets are achieved. Bidirectional long short-term memory (BiLSTM) with skip connections SAAE is designed as the structure of the fault detection network. Further, a deep network with BiLSTM and residual neural network (ResNet) is proposed for the subsequent fault diagnosis step to avoid randomness imposed by the order of the input features. A framework for combining fault detection and fault diagnosis networks is also presented without the assumption of having a perfect fault detection network. A comprehensive comparison among relevant existing techniques in the literature and SAAE-ResNet is also conducted on the Tennessee-Eastman process, which shows the superiority of the proposed FDD method.

The perception of sewage sludge has increasingly changed from being a waste, which is a burden to the environment and society, to a useful resource of materials and renewable energy. There are several available technologies at different stages of maturity that aim to convert sludge to energy in the form of electricity and/or fuels. In this paper, a decision-making support tool is proposed to help in choosing the optimal pathway for the sludge-to-energy conversion from a techno-economic perspective. The conversion technologies under study are: (1) anaerobic digestion, (2) pyrolysis, (3) gasification, (4) incineration, (5) supercritical water oxidation, (6) supercritical water gasification, as well as the corresponding dewatering and drying methods for each technology. Different synergies between the available technologies are compared by the formulation of a superstructure optimization problem expressed in a mixed-integer non-linear program (MINLP) model. The applicability of the proposed model is explored via a case study for a hypothetical sludge treatment plant with a capacity of 100 tons of dry solids (tDS) per day. The model is solved via the BARON solver using GAMS software within a reasonable processing time. According to the obtained results, the fast pyrolysis technology, coupled with filter press dewatering and thermal drying as pre-treatment steps, show the most promising outcomes with the minimum treatment cost of USD 180/tDS. Fast pyrolysis converts the sludge to bio-oil, which can be used as an alternative fuel after further refining, and biochar, which can be used for soil amendment or adsorption purposes. The model parameters are subject to uncertainty that is addressed in the sensitivity analysis section of this paper. Moreover, the pyrolysis pathway shows a high degree of robustness in most of the sensitivity analysis scenarios. Meanwhile, anaerobic digestion coupled with fast pyrolysis demonstrates the best energy recovery performance upon increasing electricity prices.

With Industry 4.0, temporal relations between process and quality variables become increasingly complex. Some dynamic supervised learning algorithms are designed to extract their dynamic cross-relations, but auto-correlations among quality variables are rarely considered, which, however, can provide additional valuable information. This article proposes a novel dynamic auto-regressive latent variable model (DALVM) to capture both auto and cross correlations from high-dimensional time series data. DALVM is designed to maximize the covariance between current quality score and the weighted sum of past quality and process scores, and an auto-regressive exogenous inner model is developed for consistency purpose. Further, a concurrent anomaly detection system is developed based on DALVM, referred to as ConDALVM, which conducts subsequent decompositions in the extracted latent spaces. ConDALVM realizes a comprehensive monitoring for both static and dynamic anomalies in process and quality spaces. The superiority of the methods is demonstrated through a numerical simulation and two industrial processes.

Accurate modeling of industrial processes is an important topic in process systems engineering for further anomaly detection and fault diagnosis. Dynamics is inevitable in these processes, and several dynamic variants were proposed in the literature to extract both cross-correlations and auto-correlations between process variables and quality variables. However, all of them focus on the auto-correlations in process variables only, while the valuable auto-regressive information between collected quality variables is ignored. In this paper, a new dynamic auto-regressive partial least squares (DAPLS) method is proposed to capture the auto-correlations of both process and quality variables as well as the cross-correlations between them. In DAPLS, quality-relevant dynamics are exploited by maximizing the covariance between current quality sample and the weighted combinations of both past process and quality samples. Its inner modeling objective is also explicit and consistent with its outer model. The case studies with the numerical simulations and the Tennessee Eastman process have demonstrated the effectiveness of the proposed model.

Process monitoring and fault diagnosis (PM-FD) of coal mills are essential to the security and reliability of the coal-fired power plant. However, traditional methods have difficulties in addressing the strong nonlinearity and multi-modality of coal mills. In this paper, a novel multi-mode Bayesian PM-FD method is proposed. Gaussian mixture model (GMM) is first applied to identify the operating modes of the coal mill. Subsequently, combined with multi-output relevance vector regression (MRVR), Bayesian inference is introduced to reconstruct and monitor the newly observed samples from different running modes. Additionally, the squared prediction error and the contribution plot method are employed for fault detection and isolation. The performance of the proposed PM-FD method is verified through its application in a self-defined nonlinear system and two actual fault cases of a medium-speed coal mill. Compared with the traditional methods, the experimental results demonstrate the effectiveness of the proposed method.

Partial least squares (PLS) is a multivariate statistical analytical method which can be used to extract valuable information from high-dimensional and correlated data effectively. To model the ine...

Multivariate statistical analytical methods, such as principal component analysis (PCA) and canonical correlation analysis (CCA), are widely used to extract useful information from data collected in modern industrial processes. Their dynamic extensions are also designed intensively in the literature to exploit dynamic variations in the processes. However, none of these algorithms consider the inevitably strong dependence in adjacent samples caused by high sampling frequencies or relatively slow continuous process changes, and the dependence may lead to unnecessarily large time lags and sub-optimal prediction performance. In this paper, a dynamic weighted CCA (DWCCA) algorithm is proposed to address this issue with the aid of basis functions. DWCCA constructs its latent space by maximizing the correlation between current data and a weighted representation of past data. To remove the negative effect caused by strongly collinear successive samples, it is assumed that the weights of past data rely only on a limited number of basis functions, and in this work, polynomial basis, Fourier basis, and Gaussian basis functions are considered and compared. Comprehensive modeling scheme is also designed for DWCCA with subsequent PCA decomposition to exploit static and dynamic variations concurrently. Case studies on the Tennessee Eastman process and the boiler process are presented to illustrate the effectiveness of the proposed dynamic models over other existing dynamic methods.

Multi-block multivariate statistical methods have been developed to extract useful information from process and quality data in the era of big data, where process variables are partitioned into several meaningful blocks. However, most of these methods did not consider cross-correlations among divided blocks, which leads to inferior monitoring performance. In this article, a block-aware factorization machine (BAFM) algorithm is proposed to exploit information from process and quality data. In BAFM, quality data are first classified into normal and abnormal labels with principal component analysis based quality monitoring framework. Afterwards, a block number is attached to each process variable, and the interactions among different variables (both within and cross blocks) are learned through latent variables, which is supervised by the classified quality labels. Apart from the variable relation within the same block, BAFM also incorporates the block information; thus, both inner and cross correlations are constructed. The monitoring framework based on BAFM is developed, and its effectiveness and superiority are demonstrated through the Tennessee Eastman process.

This paper is concerned with data science and analytics as applied to data from dynamic systems for the purpose of monitoring, prediction, and inference. Collinearity is inevitable in industrial operation data. Therefore, we focus on latent variable methods that achieve dimension reduction and collinearity removal. We present a new dimension reduction expression of state space framework to unify dynamic latent variable analytics for process data, dynamic factor models for econometrics, subspace identification of multivariate dynamic systems, and machine learning algorithms for dynamic feature analysis. We unify or differentiate them in terms of model structure, objectives with constraints, and parsimony of parameterization. The Kalman filter theory in the latent space is used to give a system theory foundation to some empirical treatments in data analytics. We provide a unifying review of the connections among the dynamic latent variable methods, dynamic factor models, subspace identification methods, dynamic feature extractions, and their uses for prediction and process monitoring. Both unsupervised dynamic latent variable analytics and the supervised counterparts are reviewed. Illustrative examples are presented to show the similarities and differences among the analytics in extracting features for prediction and monitoring.

Canonical correlation analysis (CCA) is widely used as a supervised learning method to extract correlations between process and quality datasets. When used to extract relations between current data and historical data, CCA can also be regarded as an auto-regressive modeling method to capture dynamics. Various dynamic CCA algorithms were developed in the literature. However, these algorithms do not consider strong dependence existing in adjacent samples, which may lead to unnecessarily large time lags and inaccurate estimation of current values from historical data. In this paper, a dynamic weighted CCA (DWCCA) algorithm is proposed to address this issue with a series of polynomial basis functions. DWCCA extracts dynamic relations by maximizing correlations between current data and a weighted representation of past data, and the weights rely only on a limited number of polynomial functions, which removes the negative effect caused by strongly collinear neighboring samples. After all the dynamics are exploited, static principal component analysis is then employed to further explore the cross-correlations in the dataset. The Tennessee Eastman process is utilized to demonstrate the effectiveness of the proposed DWCCA method in terms of prediction efficiency and collinearity handling.

Recently, a concurrent monitoring scheme based on slow feature analysis (SFA) has been developed to differentiate operating point changes with process dynamics. The original SFA algorithm requires the data to be fed in as a whole in the training stage and is unsuitable for an increasingly tremendous data volume in modern industries. Other variations have also been developed such as recursive slow feature analysis (RSFA) to process data sequentially, which, however, requires storing, updating, and decomposing two covariance matrices, and increases computational and memory costs. In this work, a new process monitoring scheme is proposed based on a covariance free incremental slow feature analysis (IncSFA) method, which handles massive data efficiently and has a linear feature updating complexity with respect to data dimensionality. The effectiveness of IncSFA-based monitoring method is demonstrated with the Tennessee Eastman Process.

The global trend toward a green sustainable future encouraged the penetration of renewable energies into the electricity sector to satisfy various demands of the market. Successful and steady integrations of renewables into the microgrids necessitate building reliable, accurate wind and solar power forecasters adopting these renewables' stochastic behaviors. In a few reported literature studies, machine learning- (ML-) based forecasters have been widely utilized for wind power and solar power forecasting with promising and accurate results. The objective of this article is to provide a critical systematic review of existing wind power and solar power ML forecasters, namely artificial neural networks (ANNs), recurrent neural networks (RNNs), support vector machines (SVMs), and extreme learning machines (ELMs). In addition, special attention is paid to metaheuristics accompanied by these ML models. Detailed comparisons of the different ML methodologies and the metaheuristic techniques are performed. The significant drawn-out findings from the reviewed papers are also summarized based on the forecasting targets and horizons in tables. Finally, challenges and future directions for research on the ML solar and wind prediction methods are presented. This review can guide scientists and engineers in analyzing and selecting the appropriate prediction approaches based on the different circumstances and applications.

Concurrent monitoring schemes that achieve simultaneous process and quality-relevant monitoring have recently attracted much attention. In this Article, we formulate a supervised fault diagnosis fr...

Aim. This study aimed to predict the key targets and endocrine mechanisms of Guizhi Fuling Wan (GZFLW) in treating adenomyosis (AM) through network pharmacology, molecular docking, and animal experiment verification. Methods. The related ingredients and targets of GZFLW in treating AM were screened out using TCMSP, BATMAN-TCM, SwissTargetPrediction, and PubChem Database. Then, the protein-protein interaction (PPI) analysis and the network of compound-hub targets were constructed. At the same time, the key targets were uploaded to the Metascape Database for KEGG pathway enrichment analysis. After that, the molecular docking technology of the main active components and hub targets was performed. Furthermore, animal experiments were used to verify the results of network pharmacology analysis. Results. A total of 55 active ingredients of GZFLW and 44 overlapping targets of GZFLW in treating AM were obtained. After screening, 25 hub targets were collected, including ESR1, EGF, and EGFR. Then, the KEGG pathway enrichment analysis results indicated that the endocrine therapeutic mechanism of GZFLW against AM is mainly associated with the estrogen signaling pathway, endocrine resistance, and an EGFR tyrosine kinase signaling pathway. Then, molecular docking showed that the significant compounds of GZFLW had a strong binding ability with ERα and EGFR. More importantly, the animal experiments confirmed that the GZFLW could downregulate the abnormal infiltration of the endometrial epithelium into the myometrium and had no interference with the normal sexual cycle. This effect may be directly related to intervening the local estrogen signaling pathway of the endometrial myometrial interface (EMI). It may also be associated with the myometrium cells’ estrogen resistance via GPER/EGFR signaling pathway. Conclusion. The endocrine mechanism of GZFLW in treating AM was explored based on network pharmacology, molecular docking, and animal experiments, which provided a theoretical basis for the clinical application of GZFLW.

The practitioners are concerned with strip-thickness relevant faults of steel-making cold-rolling continuous annealing process (CAP) which is a typical dynamic nonlinear process. In this paper, a novel data-driven dynamic concurrent kernel canonical correlation analysis (DCKCCA) approach is proposed for the diagnosis of the CAP strip thickness relevant faults. First, a DCKCCA algorithm is proposed to capture dynamic nonlinear correlations between strip thickness and process variables. Strip thickness specific variations, process-specific variations, and thickness-process covariations are monitored respectively. Secondly, a multi-block extension of DCKCCA is designed to compute the contributions according to block partition of lagged variables, in order to help localize faults relevant to abnormal strip thickness. Finally, the proposed methods are illustrated by the application to a real continuous annealing process.

Canonical correlation analysis (CCA) is a well-known data analysis technique that extracts multidimensional correlation structure between two sets of variables. CCA focuses on maximizing the correlation between quality and process data, which leads to the efficient use of latent dimensions. However, CCA does not focus on exploiting the variance or the magnitude of variations in the data, making it rarely used for quality and process monitoring. In addition, it suffers from collinearity problems that often exist in the process data. To overcome this shortcoming of CCA, a modified CCA method with regularization is developed to extract correlation between process variables and quality variables. Next, to handle the issue that CCA focuses only on correlation but ignores variance information, a new concurrent CCA (CCCA) modeling method with regularization is proposed to exploit the variance and covariance in the process-specific and quality-specific spaces. The CCCA method retains the CCA's efficiency in predicting the quality while exploiting the variance structure for quality and process monitoring using subsequent principal component decompositions. The corresponding monitoring statistics and control limits are then developed in the decomposed subspaces. Numerical simulation examples and the Tennessee Eastman process are used to demonstrate the effectiveness of the CCCA-based monitoring method.