Batch Process Monitoring Research Articles

Adaptive two-dimensional subspace identification for monitoring batch processes with limited batch data

Data-driven based batch process monitoring is of critical importance in ensuring stable operating processes and consistent product quality. For long-duration batch processes, it is unrealistic to involve expensive data to train a statistical model for monitoring. To model the inherently batch-wise and variable-wise dynamics, nonlinearity, and time-varying characteristics, this paper proposes a local learning-based two-dimensional subspace identification (LL-2D-SID) scheme based on the similarity between the ongoing batch and the previous batches. The similarity is estimated by the extended extrapolative time-warping. Unlike the conventional statistical models using rich batch data, LL-2D-SID through online optimizing mechanism using limited batch data still has good prediction performance. The application of the sintering process in the polytetrafluoroethylene production has demonstrated that the LL-2D-SID based process monitoring scheme can not only accurately track temperature changes but also timely give fault alarms with a lower error alarm rate than the other SID-based process monitoring schemes.

Meta-learning-based continuous state-space models for rapid monitoring using heterogeneous grade sources with uneven sampling

In an industrial batch, it is common to produce products with different grades, so only a limited number of data are available for each grade of product. The data are also easily contaminated by external disturbances and noise. The sampling interval would be messy and irregular if contaminated samples were removed. Thus, it is difficult to build models for monitoring the corresponding process. This paper proposes a meta-learning-based functional continuous state space model for fast modeling and monitoring of multi-grade batch processes. It takes advantage of wavelet function properties to effectively handle the irregular sampling issue. In addition, the meta-learning method uses diverse historical multi-grade datasets for modeling. It rapidly establishes an efficient and reliable monitoring model for new running batches with a small number of batch data. The effectiveness of the proposed method is shown through a numerical case and an industrial case in the chemical batch process.

Real-Time Monitoring of Multistep Batch and Flow Synthesis Processes of a Key Intermediate of Lifitegrast by a Combined Spectrometer System with Both Near-Infrared and Raman Spectroscopies Coupled to Partial Least-Squares.

Process analytical technology (PAT) has been successfully applied in numerous chemical synthesis cases and is an important tool in pharmaceutical process research and development. PAT brings new methods and opportunities for the real-time monitoring of chemical processes. In multistep synthesis, real-time monitoring of the complex reaction mixtures is a significant challenge but provides an opportunity to enhance reaction understanding and control. In this study, a combined multichannel spectrometer system with both near-infrared and Raman spectroscopy was built, and calibration models were developed to quantify the desired products, intermediates, and impurities in real-time at multiple points along the synthetic pathway. The capabilities of the system have been demonstrated by operating dynamic experiments in both batch and continuous-flow processes. It represents a significant step forward in data-driven, multistep pharmaceutical ingredient synthesis.

Batch process monitoring based on sequential phase division multiway sparse weighted neighborhood preserving embedding

Batch processes are often characterized by multiphase and different batch durations, which vary from phase to phase presenting multiple local neighborhood features. In this paper, a sequential phase division-multiway sparse weighted neighborhood preserving embedding method is proposed for monitoring batch processes more sensitively. First, batches with uneven durations are synchronized, and the phases are automatically determined in chronological order. Secondly, the nearest neighbors are computed at each phase and the optimal sparse representation (SR) is obtained based on the nearest neighbors. This improves the robustness of the algorithm to noise and outliers, and solves the problem of computational difficulties associated with global SR based. Thirdly, the distance values of the neighbor elements are considered to fully extract the neighbor structure when the optimal SR is calculated. Finally, after dimension reduction, T 2 and squared prediction error statistics are established in feature space and residual space respectively for fault detection. The effectiveness of the method is verified by a multiphase numerical simulation example and the penicillin fermentation process.

A model-free-based control chart for batch process using U-statistics

Batch processes are known to generate time series of successive measurements of many process variables in each run and the main challenge is to capture and accommodate the variability in the batch domain (batch-to-batch variability) and in the time domain (data with serial correlation). Classical approaches are focused on the first goal by applying multivariate techniques in the columns of a data matrix, in which each row has the data for the entire batch run. Those approaches are grounded in the traditional Multiway Principal Component Analysis (MPCA). Recent approaches are focused on the balance between the two sources, taking into account the time series nature of the data mainly by using time series models and neural network methods to directly accommodate the variability in the time domain. This paper proposes a model-free approach based on U-statistics theory. Through this theory, we can build a group of control charts (named V charts) capable of monitoring batch processes considering both sources of variability. In general, the new batch under monitoring is evaluated according to a group of reference in-control samples, based on the distance measures from those batches. The proposed approach is really flexible since we avoid model identification, parameter estimates issues and it is able to accommodate the within and between batch variability. Additionally, our method is suitable to deal with a wide range of batch data features, since under weak conditions, the distribution of the V statistics remains well known. It makes the V-based charts able to be used in different kinds of processes. We are focused here on controlling changes caused by data drifts (including trends) and by data serial correlation (data dynamics). Through the simulated and real batch process, we show that the V charts work well, including a scenario with very few reference batches available.

Batch process quality monitoring based on temporal convolutional networks with depthwise separable coordinated attention module

AbstractQuality monitoring is an important tool for ensuring the safe operation of batch processes and the high quality of the final products. However, the inherent non‐linear, dynamic, and batch characteristics make the quality monitoring of batch process still have some difficulties. To solve these problems, this paper proposes a batch quality monitoring model based on a temporal convolutional network with a depthwise separable coordinated attention module. Firstly, a method of data unfolding incorporating sliding windows is proposed to unfold and stack the data along the direction of the variables, and a variable selection method of maximum information coefficient fused with Monte Carlo sampling is proposed to select the process variables related to the quality variables. Secondly, we take the traditional temporal convolutional network as the base network and decouple the correlation between the batch data by using depthwise separable convolution. At the same time, we utilize coordinate attention to extract data features in different spatial directions to ensure the effectiveness of quality monitoring. Finally, the feasibility and robustness of the proposed model are verified by a nonlinear numerical example and an industrial‐scale penicillin fermentation process. The experimental results show the proposed model has lower false alarm rate and false negative rate and can be used to maintain the product quality of the actual batch process.

Nonlinear multiphase batch process monitoring and quality prediction using multi-way concurrent locally weighted projection regression

The batch process has the characteristics of nonlinear and multiphase due to variation operation conditions. Nonlinear and multiphase modeling of the batch process is very important to understand the running state of a process and improve the monitoring effect. In this work, a multiphase multi-way concurrent locally weighted projection regression algorithm is proposed. Firstly, the entire process is partitioned into phases according to local quality-related characteristics and time sequence. Secondly, the nonlinear process is modeled with locally linear models in each partitioned phase, the global approximation results are obtained by weighting all the local models. Thirdly, the complete monitoring indices of quality-related and process related are built, and the quality variables are predicted while exploiting the regression structure for quality and process monitoring. Finally, a nonlinear numerical process and the penicillin fermentation process are used to verify the effectiveness of the proposed algorithm.

Phase partition and online monitoring for batch processes based on Harris hawks optimization

Most industrial batch processes exhibit significantly different characteristics at different manufacturing steps, and it is advantageous to partition batch processes reasonably and establish phase models separately for online monitoring. In the present work, a novel phase partition method is developed based on Harris hawks optimization (HHO) with hard sequentiality constraint, which seeks for the optimal phase partition results under the specific target phase number in inner loop and automatically determines the optimal phase number in outer loop by making a trade-off between modeling complexity and partition performance. First, a new definition of the sum of quadratic error (SQE) is designed as the fitness function to evaluate the within-phase compactness, which makes the time-slice matrices with similar process variable correlations stay in the same phase. Then, an optimization refinement scheme (ORS) is developed to find the potential local minimum of the SQE by inspecting and reallocating the phase-adjacent samples. Afterwards, the percentage of performance improvement indicator (PPII) is proposed to determine the optimal phase numbers by quantifying the improvement of minimum SQE. For each subphase, canonical variate analysis (CVA) is performed to build statistical models for dynamic process monitoring. The effectiveness of the proposed method is illustrated by a numerical example with some outliers and an injection molding process.

Tensor slow feature analysis and its applications for batch process monitoring

How to establish efficient monitoring models for complex batch processes is a challenging problem because of the three-dimensional (3-D) data array and serious dynamics. The unfolding operation in most methods would destroy the batch data structure and increase the dimensions of modeling data obviously. Meanwhile, it is more practical to perform within-batch detection rather than end-of-batch detection. In this work, a novel high-order tensor slow feature analysis model is proposed to handle the 3-D and dynamical issues simultaneously. The proposed model can be solved by iteratively tackling two sub-optimal problems. Within-batch detection is performed based on the properly defined monitoring statistics to timely detect the abnormal situation. The multi-phase property is further considered in this work to improve detection accuracy. A simulated case and an industrial case are taken to show the merits of the proposed method.

Industrial batch monitoring for cell culture processes during process scale-ups: data challenges and solutions

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.

Profitability related industrial-scale batch processes monitoring via deep learning based soft sensor development

Data-driven soft sensor technology has been widely developed to estimate quality-related variables, while following difficulties still limit its application in batch processes, such as different initial conditions, uneven-length of batches, and the extraction of within-batch multiphase features. To address these problems, a quality prediction and monitoring framework is proposed. Variables related to quality-related variables are first selected, and a data stacked strategy is proposed to transform three-dimensional batch data into time-lagged sequences that can be fed into soft sensor models. Aiming to extract the multiphase features, a novel differential recurrent neural networks is established by embedding differential operations into long short-term memory neural networks. Moreover, to ensure profitability, prediction residuals are employed for quality monitoring. Case study on a simulation dataset and an industrial-scale penicillin fermentation process demonstrates the effectiveness of the proposed method and its applicability to batch process monitoring and control in both academic research and industrial operation.

Phase partition and KPI‐related process monitoring for batch processes using a novel canonical correlation analysis strategy

AbstractKey performance indicators (KPI)‐related process monitoring has been of great significance to ensure product quality and economic benefits for batch processes. Considering that different phases exhibit different characteristics, one of the key issues is how to partition the whole batch process into different phases and characterize them separately by multiple phase models. In order to model and monitor batch processes more accurately and efficiently, a novel canonical correlation analysis (CCA) strategy is proposed in this paper. The phase partition algorithm is designed based on the joint canonical variable matrix (JCVM). Different from previous methods, it considers the time sequence of operation phases and can distinguish the phase switches from dynamics anomalies. Using this algorithm, phases are separated in order from a KPI‐related perspective, revealing high correlation among variables. After phase partition, a novel multi‐phase local neighbourhood standardization CAA (MPLNSCCA) method focusing on KPI is set up for online monitoring, which could further address the misclassification problems. The advantages of the proposed method are illustrated by two case studies, a penicillin simulation platform and an industrial application of Escherichia coli fermentation, respectively.

WOPCA-EGNPE algorithm based on variable division for fault monitoring of batch process

WOPCA-EGNPE algorithm based on variable division for fault monitoring of batch process

Fault monitoring of batch process based on multi-stage optimization regularized neighborhood preserving embedding algorithm

Batch process is an important type of industrial production process, and the process mechanism is complex. It is difficult to accurately describe the dynamic changes of the production process of multi-stage time-varying batch process. In addition, the data of batch process contain not only global information but also local information. The traditional neighborhood preserving embedded algorithm is used to maintain the local geometric structure of data while ignoring the global information, and the extracted latent variables cannot fully characterize batch process. Therefore, we propose a multi-stage optimization regularized neighborhood preserving embedding (ORNPE) algorithm. First, the multiple process stages are separated by affinity propagation (AP) algorithm. Second, based on maintaining local information of neighborhood preserving embedding algorithm, slow feature analysis algorithm is used to extract dynamic time-varying global information. Then, cross-entropy is used to optimize the global information, and the extraction ability of the global information is improved. Finally, a monitoring index based on support vector data description is constructed to eliminate adverse effects of non-Gaussian data for monitoring performance. The effectiveness and advantages of the proposed algorithm based on monitoring strategy are illustrated by the penicillin fermentation process and a semiconductor industry process.

Developing Tensor-Based Common and Special Feature Analysis for Comprehensive Monitoring of Complex Batch Processes

To overcome the limitation of unfolding-based methods and handle the multiple data set and limited data problems in the complex processes, such as multigrade batch processes, a novel tensor-based common and special feature extraction method and a comprehensive monitoring framework are proposed. In the proposed method, the uneven-length three-dimensional data are directly analyzed by the comprehensive tensor-based method without unfolding. To handle the multiple data set modeling problem, the tensor-based common feature extraction methods are first proposed to obtain the common features shared among different grades. The special features are sequentially determined by conducting tensor principal component analysis (PCA) on the residuals of each grade. The data are thus divided into common, special, and residual subspaces. Three monitoring statistics are established respectively in each subspace for online fault detection. The merits and effectiveness of the proposed method are demonstrated by an injection molding process with both even-length and uneven-length data in comparison with traditional methods.

Two-dimensional multiphase batch process monitoring based on sparse canonical variate analysis

Most industrial batch processes involve inherent dynamic characteristics in both within-batch time direction and batch-wise direction. In order to ensure process safety and improve process performance, the two-dimensional dynamics should be analyzed during batch process monitoring. In this work, two-dimensional region of support (2D-ROS) is first constructed to select and preserve the relevant samples for the current measured sample by calculating autoregressive orders with Akaike information criterion (AIC) in time direction and measuring the similarity with the weighted Euclidean distance in batch-wise direction. Afterwards, sparse canonical variate analysis (SCVA) algorithm is performed to yield sparse canonical vectors, which is especially advantageous for eliminating the irrelevant variables and facilitating the interpretation of underlying relationships of process variables. Meanwhile, given most measurements are subject to the non-Gaussian distribution, the upper control limits (UCLs) in 2D-SCVA can be estimated using kernel density estimation (KDE). The achieved results obtained from a numerical dynamic example and the benchmark fed-batch penicillin fermentation process clearly verify that the proposed method performs well for detecting abnormal operation for the batch processes.

Slow‐varying batch process monitoring based on canonical variate analysis

AbstractMost industrial batch processes display normal slow changes over batches because of the influence of external factors. The question of how to take this slow‐varying behaviour into account during dynamic process monitoring remains a challenge for researchers. To address the above issue, a slow‐varying batch process monitoring method is proposed for multiphase batch processes. It makes subtraction between two different batches with a certain interval for pre‐treating the original data and subsequently utilizes a canonical variate analysis (CVA) algorithm with kernel density estimation (KDE) for fault detection. For each subphase, the proposed method can extract a variable‐wise dynamic characteristic with the time evolution for every single batch and capture statistical features of slow variations along batch direction simultaneously. It is less sensitive to normal gradual changes with a low false‐positive rate. The performance of the proposed method for batch process monitoring was tested on a numerical simulation system and penicillin fermentation production process with comparison to multiphase CVA, multiphase slow feature analysis (SFA), multiphase principal component analysis (PCA), and traditional CVA without phase division. The achieved results clearly demonstrate the effectiveness of the proposed method, which is a remarkable and promising tool for modelling and monitoring batch processes with regular slow‐varying characteristics.

A novel fault detection approach based on multilinear sparse PCA: application onthe semiconductor manufacturing processes

Batch processes are extremely important to researchers since they are widely used in many fields such as biochemistry, pharmacy, and semiconductors. The powerful batch detection method is critical to increase the performance of the overall equipment and to reduce the use of check wafers. Many techniques have been used in batch process monitoring. Among them, the multivariate statistical process control (MSPC) is very useful in batch process monitoring because of the large number of records data. Therefore, batch processes have certain characteristics, such as multimodal batch nonlinearity trajectories, which were challenged by these MSPCs. In this paper, a novel process monitoring methods based on multilinear sparse PCA (MSPCA) are proposed to overcome these shortcomings. MSPCA handle batch data as a matrix (second order), although most of the other multivariate statistical analysis approaches handles batch data as a vector (first order). Vectorization of batch data tends to ignore parts of the information. Furthermore, The MSPCA can extract more useful data from the batch data with less storage requirements and computational complexity compared to current multivariate statistical analysis approaches. The efficiency of the monitoring technique is implemented in the numerical example and Lam 9600 metal etcher process. The performance of MPSCA is characterized by a fault detection rate of 100%, as well as a false alarm rate higher than 83%. Simulation results show that MSPCA outperforms the traditional techniques.

Synchronization-Free Multivariate Statistical Process Control for Online Monitoring of Batch Process Evolution

Synchronization of variable trajectories from batch process data is a delicate operation that can induce artifacts in the definition of multivariate statistical process control (MSPC) models for real-time monitoring of batch processes. The current paper introduces a new synchronization-free approach for online batch MSPC. This approach is based on the use of local MSPC models that cover a normal operating conditions (NOC) trajectory defined from principal component analysis (PCA) modeling of non-synchronized historical batches. The rationale behind is that, although non-synchronized NOC batches are used, an overall NOC trajectory with a consistent evolution pattern can be described, even if batch-to-batch natural delays and differences between process starting and end points exist. Afterwards, the local MSPC models are used to monitor the evolution of new batches and derive the related MSPC chart. During the real-time monitoring of a new batch, this strategy allows testing whether every new observation is following or not the NOC trajectory. For a NOC observation, an additional indication of the batch process progress is provided based on the identification of the local MSPC model that provides the lowest residuals. When an observation deviates from the NOC behavior, contribution plots based on the projection of the observation to the best local MSPC model identified in the last NOC observation are used to diagnose the variables related to the fault. This methodology is illustrated using two real examples of NIR-monitored batch processes: a fluidized bed drying process and a batch distillation of gasoline blends with ethanol.

Two-Dimensional, Two-Layer Quality Regression Model Based Batch Process Monitoring

In this paper, a two-dimensional, two-layer quality regression model is established to monitor multi-phase, multi-mode batch processes. Firstly, aiming at the multi-phase problem and the multi-mode problem simultaneously, the relations among modes and phases are captured through the analysis between process variables and quality variables by establishing a two-dimensional, two-layer regression partial least squares (PLS) model. The two-dimensional regression traces the intra-batch and inter-batch characteristics, while the two-layer structure establishes the relationship between the target process and historical modes and phases. Consequently, online monitoring is carried out for multi-phase, multi-mode batch processes based on quality prediction. In addition, the online quality prediction and monitoring results based on the proposed method and those based on the traditional phase mean PLS method are compared to prove the effectiveness of the proposed method.