GraphSAGE-LSTM-based deep canonical correlation analysis for batch process monitoring

On-line batch process monitoring using a consecutively updated multiway principal component analysis model

Complex industrial process data often exhibit nonlinear static and dynamic characteristics. Traditional deep learning methods such as stacked autoencoder (SAE) have excellent nonlinear static feature learning capabilities, but they ignore the dynamic correlation existing in process data. Feature learning based on manifold learning using neighborhood structure preserving has been widely used in industrial dynamic process monitoring. However, most of the manifold learning methods extract linear features, and complex nonlinearities in process data are ignored. Therefore, a novel spatiotemporal neighborhood preserving stack autoencoder (STNP-SAE) is proposed to simultaneously learn deep nonlinear static and dynamic features of process data in this article. By constructing the spatial and temporal adjacent graphs, STNP-SAE can capture the spatiotemporal neighborhood structure information of process data during the feature learning process. Then, STNP-SAE is used to construct a soft sensor framework for quality prediction. The prediction performance of the proposed method is validated on a practical industrial process.

Batch process data contain between‐run and within‐run sources of variation, which complicates data analysis and process monitoring. Multilevel methods, such as multilevel simultaneous component analysis, greatly enhance the interpretation of large sets of batch process data by separating the between‐run and within‐run variation. Using a multilevel approach in batch process monitoring greatly reduces the occurrence of false alarms that are caused by trivial variations and process changes that were made on purpose. This also reduces the need for model updating, which often is a large effort and causes downtime of the monitoring system. Furthermore, relevant phenomena that are masked by larger but uninteresting sources of variation when standard batch process monitoring methods are applied can often be detected if the multilevel approach is used. Chemical batch process data are used to illustrate the methods. Copyright © 2012 John Wiley & Sons, Ltd.

Improved monitoring of batch processes by incorporating external information

Real time phase detection based online monitoring of batch fermentation processes

Batch processes are very important to the chemical and manufacturing industries. Techniques for monitoring these batch processes to ensure their safe operation and that they produce consistent high quality products are needed. Nomikos and MacGregor (1994) present a multi-way principal component analysis (MPCA) approach for monitoring batch processes, and test results show that the method is simple, powerful, and effective. However MPCA is a linear method, and most batch processes are nonlinear. In this paper a nonlinear principal component analysis (NLPCA) method (Dong-McAvoy, 1993) is used for batch process monitoring. The main focus of this paper is on multi-stage batch process monitoring. The proposed approach and special problems for multi-stage batch processes are illustrated through a detailed simulation study.

Batch process monitoring in the original measurement's space

For cross-modal subspace clustering, the key point is how to exploit the correlation information between cross-modal data. However, most hierarchical and structural correlation information among cross-modal data cannot be well exploited due to its high-dimensional non-linear property. To tackle this problem, in this paper, we propose an unsupervised framework named Cross-Modal Subspace Clustering via Deep Canonical Correlation Analysis (CMSC-DCCA), which incorporates the correlation constraint with a self-expressive layer to make full use of information among the inter-modal data and the intra-modal data. More specifically, the proposed model consists of three components: 1) deep canonical correlation analysis (Deep CCA) model; 2) self-expressive layer; 3) Deep CCA decoders. The Deep CCA model consists of convolutional encoders and correlation constraint. Convolutional encoders are used to obtain the latent representations of cross-modal data, while adding the correlation constraint for the latent representations can make full use of the information of the inter-modal data. Furthermore, self-expressive layer works on latent representations and constrain it perform self-expression properties, which makes the shared coefficient matrix could capture the hierarchical intra-modal correlations of each modality. Then Deep CCA decoders reconstruct data to ensure that the encoded features can preserve the structure of the original data. Experimental results on several real-world datasets demonstrate the proposed method outperforms the state-of-the-art methods.

Adsorption thermal energy storage for cogeneration in industrial batch processes: Experiment, dynamic modeling and system analysis

A Step-wise sequential phase partition algorithm with limited batches for statistical modeling and online monitoring of multiphase batch processes

There has been a lot of research activity in the area of batch process analysis and monitoring for abnormal situation detection since the pioneer work of Nomikos and MacGregor []. However, some of the key ideas and the thought process that led to those first papers have been forgotten. Batch process data are dynamic data. The whole philosophy of looking at batch process data with latent variables was developed because batch process variables are both autocorrelated and cross‐correlated. Statistical process control by definition checks deviations from a nominal behavior (a target). Therefore for statistical process control of batch processes we should look at deviations of process variable trajectories from their nominal trajectories and from their nominal auto/cross‐correlations. An added advantage to modeling the deviations from the target trajectory is that a non‐linear problem is converted to a linear one that it is easy to tackle with linear latent variable methods such as principal component analysis (PCA) and partial least squares (PLS). This paper first takes a critical look at the true nature of batch process data. The general case where variables are not present during the entire duration of the batch is addressed. It is then illustrated how proper centering (by taking the deviations from the target trajectory) can retain valuable information on auto‐ and cross‐correlation of the process variables. This auto‐ and cross‐correlation is only modeled with a certain types of models. Topics such as scaling and trajectory alignment are revisited and issues arising when using the indicator variable approach are addressed. The development of control charts for multiblock, multiway PCA/PLS is discussed. Practical issues related to applications in industry are addressed. Then some of the methods that have appeared in the literature are examined as to their assumptions, their advantages and disadvantages and their range of applicability. Finally the nature of transition data (start‐ups, grade transitions) is discussed and issues related to aligning, centering and scaling such types of data are presented. Copyright © 2003 John Wiley & Sons, Ltd.

In complex underwater environments, the single mode of a single sensor cannot meet the precision requirement of object identification, and multisource fusion is currently the mainstream research approach. Deep canonical correlation analysis is an efficient feature fusion method but suffers from problems such as not strong scalability and low efficiency. Therefore, an improved deep canonical correlation analysis fusion method is proposed for underwater multisource sensor data containing noise. First, a denoising autoencoder is used for denoising and to reduce the data dimension to extract new feature expressions of raw data. Second, given that underwater acoustic data can be characterized as 1-dimensional time series, a 1-dimensional convolutional neural network is used to improve the deep canonical correlation analysis model, and multilayer convolution and pooling are implemented to decrease the number of parameters and increase the efficiency. To improve the scalability and robustness of the model, a stochastic decorrelation loss function is used to optimize the objective function, which reduces the algorithm complexity from O(n³) to O(n²). The comparison experiment of the proposed algorithm and other typical algorithms on MNIST containing noise and underwater multisource data in different scenes shows that the proposed algorithm is superior to others regardless of the efficiency or precision of target classification.

Cell culture process scale-ups are common in biologics manufacturing as the process moves from the early stages of process development to commercial manufacturing. Statistical batch process monitoring (BPM) is frequently deployed for efficient real-time monitoring and control of cell culture processes. A BPM platform relies on historical process data to train in-control model for real-time monitoring of future batches. Deploying a BPM platform during or immediately after process scale-up is nontrivial due to limited batch campaigns at the commercial scale. In the absence of available at-scale commercial data during scale-ups, we propose an approach to reuse data sets generated at bench or pilot-scale for training BPM models at the commercial scale. The proposed method uses a scaling model to learn complex data scaling relations between bench/pilot-commercial scales. The model is then used to synthesise data sets at a commercial scale using existing in-control bench/pilot data. Using synthesised at-scale commercial scale data, a BPM model can be trained and deployed soon after the scale-up, which would not have been possible otherwise. The efficacy of the proposed approach is illustrated in an industrial cell culture process.

Scene change detection is the process of identifying the differences between the multi-temporal image scenes at the semantic level, which has significant potential in the application of urban development and land management. In this paper, we propose a novel deep convolution canonical correlation analysis neural network (DCCANet) architecture, which could consider the spectral-spatial-temporal correlation feature for scene change detection in remote sensing images. For this purpose, we put together the convolutional neural networks (CNNs) and the deep canonical correlation analysis (DCCA) into the end-to-end network. The CNN could get the spectral-spatial feature information for scene representation, while the later could enhance the temporal correlation by nonlinear high- dimensional transformations between the multi-temporal image scenes for scene change detection. Experiments with high-resolution remote sensing image scene datasets demonstrated that our proposed approach can get a better performance in scene classification and change detection.

This paper describes the concepts of statistical batch process monitoring and the associated problems. It starts with an introduction to process monitoring in general which is then extended to batch process monitoring. The performance of control charts for batch process monitoring is discussed by means of two performance indices: the overall type I error and the action signal time. Problems associated with the existing approach are discussed and highlighted. Improvements are suggested and checked with the performance indices. To evaluate the effect of the proposed improvements as well as to assess the performance of the existing approach, an industrial batch production process is used.