Fault detection and classification for a two‐stage batch process

A batch process is finite in duration and can be separated into two stages: startup and production. We develop a methodology to monitor a batch process during the startup stage to reduce the length of the startup stage. We focus on processes that are characterized by multiple process parameters and product characteristics. Because of the complex interdependencies characterizing the process parameters and product characteristics, it is more effective to evaluate them simultaneously. To address the multivariate nature of the process we use a multivariate statistical model: PLS (Projection to Latent Structures). PLS has been applied to several applications in statistical process monitoring. We present a new application of PLS to the startup stage of a batch process. Iterative adjustments made during startup in search of an acceptable production zone consume considerable amounts of material, labor and equipment time. We develop a monitoring procedure to reduce the time as well as the number of iterations and adjustments needed for startup. A PLS model is constructed, using baseline data, to characterize the relationship among process parameters during good production. The startup stage is monitored using the PLS characterization to determine if the process is consistent with good production. We illustrate the improved startup operations with an example from a batch process in filament extrusion, the application that motivates this work. Copyright © 2001 John Wiley & Sons, Ltd.

Batch process monitoring in the original measurement's space

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 this work, Iterative Learning Control on a fed-batch fermentation process using linearised models has been studied. The repetitive nature of batch processes enables ILC to obtain information from a previous batch in order to improve the performance of the current batch such that the product quality converges asymptotically to the desired trajectory The basic batch to batch ILC law presents the control action of a current batch as a summation of the control action from the previous batch and the deviation of the output trajectory from the desired reference trajectory incorporation with a learning rate. In a bid to address the issue of the process non-linearity, the control policy and the output trajectory were linearised around their respective nominal trajectories. The linearised models were then identified using Multi Linear Regression (MLR), Principal Component Analysis (PCR) and Partial Least Squares (PLS). In order to curb the effects of plant-model mismatches and process variations, the linearised models were reidentified after each batch operation. This was done by selecting the immediate previous batch as the nominal batch and then adding the recently obtained process data into the historical data batch on completion of the current batch run. The weighting matrices in the objective function were carefully selected taking into consideration that they have a major influence on the robust performance of the process. In using PLS and PCR models the issue of process collinearity was effectively addressed. The proposed batch to batch ILC strategy was applied to a simulated fed-batch fermentation process for the production of secreted protein. The results of the optimal control policy were comparable to that obtained in using full mechanistic model. ILC, a simple but yet an effective optimal control strategy has demonstrated to be a viable option in complex processes such as batch processes where mechanistic models are difficult to develop. Keywords: Iterative Learning Control, batch process, fed-batch fermentation, batch to batch ILC, control policy. DOI: 10.7176/CMR/14-3-02 Publication date: August 31 st 2022

There are usually no on-line product quality measurements in batch and semi-batch processes, which make the process control task very difficult. In this paper, a model for predicting the end-product quality from the available on-line process variables at the early stage of a batch is developed using partial least squares (PLS) method. Furthermore, some available mid-course quality measurements are used to rectify the final prediction results. To deal with the problem that the process may change with time, recursive PLS (RPLS) algorithm is used to update the model based on the new batch data and the old model parameters after each batch. An application to a simulated batch MMA polymerization process demonstrates the effectiveness of the proposed method.

This paper proposes a framework for quality-based fault detection and diagnosis for nonlinear batch processes with multimode operating environment. The framework seeks to address 1) the mode partition problem using a kernel fuzzy C-clustering method, and the optimal cluster number will be guaranteed by a between-within proportion index; 2) the diagnosis problem using a contribution rate method based on an improved kernel partial least squares (PLS) model, by which better detection and diagnosis performances are provided; and 3) the classification of online measurements using a hybrid kernel PLS regression and the Bayes inference theory, where the new coming measurement can be correctly assigned to its constituent mode. The whole framework is developed for batch processes, and applied to the hot strip mill rolling process. It is shown using the real industrial data that for faults affecting the thickness and flatness of the strip steel in this process, the detection and diagnosis abilities of the present methods are better compared with the existing methods.

Multivariate statistical analysis methods such as principal component analysis (PCA) and partial least squares (PLS) are powerful tools for chemical process modeling and monitoring. This paper applies PCA/PLS techniques and their variants, multiway PCA/PLS and orthogonal PCA, to an industrial batch process. The study utilizes an existing large historical process data set and combines multivariate statistical methods with batch time optimization calculations to identify possibilities for process improvement. The objective is to increase throughput by shortening the batch reaction time. The batch time optimization calculations provide feasible setpoint operational suggestions while maintaining the underlying data correlation structure. A pseudo-setpoint approach is also proposed to investigate the reaction period during which the setpoint profiles remain constant. Results for an industrial reactor indicate that the batch time can be shortened by approximately 4.3%.

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.

Multiscale PLS-based GLRT for fault detection of chemical processes

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.

In this paper the benefits from introducing FDC- methods for the monitoring of wet-chemistry batch- processors will be outlined. As an example, a typical spray-process equipment shall be used to demonstrate the benefits of using fault detection and classification. These include monitoring of process parameters and frequency of equipment alarms and as result indicating the current state of the equipment. Batch processors usually have a high throughput and in the case of wet-chemistry equipment the process result may be monitored only indirectly. This makes the knowledge about the state of the equipment obligatory for minimizing scrap. Aim of FDC-methods is detecting tool degrading through recording and interpreting the process-parameters during every run and, if necessary, triggering preventive maintenance. Process engineers, maintenance engineers and the equipment operator need to have all the information they need for their decisions delivered in a way they can easily access. To achieve this, Infineon Technologies has implemented various software-tools which all share the same date-base.

Nonlinear fault detection for batch processes via improved chordal kernel tensor locality preserving projections

High-dimensional large sample data sets, between feature variables and between samples, may cause some correlative or repetitive factors, occupy lots of storage space, and consume much computing time. Using the Elman neural network to deal with them, too many inputs will influence the operating efficiency and recognition accuracy; too many simultaneous training samples, as well as being not able to get precise neural network model, also restrict the recognition accuracy. Aiming at these series of problems, we introduce the partial least squares (PLS) and cluster analysis (CA) into Elman neural network algorithm, by the PLS for dimension reduction which can eliminate the correlative and repetitive factors of the features. Using CA eliminates the correlative and repetitive factors of the sample. If some subclass becomes small sample, with high-dimensional feature and fewer numbers, PLS shows a unique advantage. Each subclass is regarded as one training sample to train the different precise neural network models. Then simulation samples are discriminated and classified into different subclasses, using the corresponding neural network to recognize it. An optimized Elman neural network classification algorithm based on PLS and CA (PLS-CA-Elman algorithm) is established. The new algorithm aims at improving the operating efficiency and recognition accuracy. By the case analysis, the new algorithm has unique superiority, worthy of further promotion.

Batch processes have significantly different properties across different phases. It is essential to divide batch processes reasonably and model corresponding phases correctly for fault detection. Order information is critical for phase partition. Different from traditional phase partition methods, which customarily adopt the results of PCA for advanced research, a novel method called Markov-chain-based spectral partition (MCSP) is proposed in this paper, which takes the sequence (order) information into consideration for phase partition. Due to the combination of neighborhood information and order information, MCSP can separate each batch into major phases automatically. The time-varying characteristics remain relatively stable in each phase, which is suitable for following a Gaussian-mixture-model-based fault detection model to reflect the phase properties. Due to its simple and intuitive format, our proposed method has superior performance in fault detection. The effectiveness of MCSP is illustrated in ...

Efficient cross-validatory algorithm for identifying dynamic nonlinear process models