Troubleshooting of an Industrial Batch Process Using Multivariate Methods

Industrial data science – a review of machine learning applications for chemical and process industries

Understand and optimize industrial processes via machine learning and chemical engineering principles.

Challenges in the Development of Soft Sensors for Bioprocesses: A Critical Review

Among the greatest challenges in soft sensor development for bioprocesses are variable process lengths, multiple process phases, and erroneous model inputs due to sensor faults. This review article describes these three challenges and critically discusses the corresponding solution approaches from a data scientist’s perspective. This main part of the article is preceded by an overview of the status quo in the development and application of soft sensors. The scope of this article is mainly the upstream part of bioprocesses, although the solution approaches are in most cases also applicable to the downstream part. Variable process lengths are accounted for by data synchronization techniques such as indicator variables, curve registration, and dynamic time warping. Multiple process phases are partitioned by trajectory or correlation-based phase detection, enabling phase-adaptive modeling. Sensor faults are detected by symptom signals, pattern recognition, or by changing contributions of the corresponding sensor to a process model. According to the current state of the literature, tolerance to sensor faults remains the greatest challenge in soft sensor development, especially in the presence of variable process lengths and multiple process phases.

Backstepping Methodology to Troubleshoot Plant-Wide Batch Processes in Data-Rich Industrial Environments

Troubleshooting batch processes at a plant-wide level requires first finding the unit causing the fault, and then understanding why the fault occurs in that unit. Whereas in the literature case studies discussing the latter issue abound, little attention has been given so far to the former, which is complex for several reasons: the processing units are often operated in a non-sequential way, with unusual series-parallel arrangements; holding vessels may be required to compensate for lack of production capacity, and reacting phenomena can occur in these vessels; and the evidence of batch abnormality may be available only from the end unit and at the end of the production cycle. We propose a structured methodology to assist the troubleshooting of plant-wide batch processes in data-rich environments where multivariate statistical techniques can be exploited. Namely, we first analyze the last unit wherein the fault manifests itself, and we then step back across the units through the process flow diagram (according to the manufacturing recipe) until the fault cannot be detected by the available field sensors any more. That enables us to isolate the unit wherefrom the fault originates. Interrogation of multivariate statistical models for that unit coupled to engineering judgement allow identifying the most likely root cause of the fault. We apply the proposed methodology to troubleshoot a complex industrial batch process that manufactures a specialty chemical, where productivity was originally limited by unexplained variability of the final product quality. Correction of the fault allowed for a significant increase in productivity.

Strategies for synchronizing chocolate conching batch process data using dynamic time warping

In batch processing, process control is typically carried out comparing trajectories of process variables with those in an in-control set of batches that yielded products within specifications. However, one strong assumption of these schemes is that all batches have equal duration and are synchronized, which is often not satisfied in practice. To overcome that, dynamic time warping (DTW) methods may be used to synchronize stages and align the duration of batches. In this paper, three DTW methods are compared using supervised classification through the k-nearest neighbor technique to determine the in-control set in a milk chocolate conching process. Four variables were monitored over time and a set of 62 batches with durations between 495 and 1170 min was considered; 53% of the batches were known to be conforming based on lab test results and experts' evaluations. All three DTW methods were able to promote the alignment and synchronization of batches; however, the KMT method (Kassidas et al. in AIChE J 44(4):864-875, 1998) outperformed the others, presenting 93.7% accuracy, 97.2% sensitivity, and 90.3% specificity in batch classification as conforming and non-conforming. The drive current of the main motor was the most consistent variable from batch to batch, being deemed the most important to promote alignment and synchronization of the chocolate conching dataset.

Monitoring microsphere coating processes using PAT tools in a bench scale fluid bed

Among the factors that influence adherence to medication within the pediatric population, taste/irritation has been identified as a critical barrier to patient compliance. With the goal of improving compliance, microspheres (matrix systems within which the drug is dispersed) can be coated with a reverse enteric polymer that will prevent the release of the drug in the oral cavity while maintaining an immediate release once the drug product reaches the stomach, thereby achieving a taste neutral profile. In this work, the in-line performance of three process analytical technology (PAT) tools is evaluated in order to monitor the microsphere coating process. These tools are Raman spectroscopy, near-infrared spectroscopy and focused beam reflectance measurements, together with process data and raw material attributes. The ability of these different sources of information to predict the coating's barrier performance is evaluated by using a combined-data-approach: multiblock partial least squares (MBPLS). Results show that Raman spectroscopy has a superior predictive performance and that it has the potential to monitor the coating process of the microspheres as well as to detect process discrepancies (such as spray rate changes), demonstrating its usefulness for the monitoring of fluid bed coating processes. It was also demonstrated that Raman can be used to clearly differentiate batches with significantly difference in-vitro dissolution performance. This monitoring is considered critical to ensure consistent coating performance for this thin film barrier membrane that is essential to patient compliance.

Enhanced process understanding and multivariate prediction of the relationship between cell culture process and monoclonal antibody quality

This work investigates the insights and understanding which can be deduced from predictive process models for the product quality of a monoclonal antibody based on designed high-throughput cell culture experiments performed at milliliter (ambr-15^® ) scale. The investigated process conditions include various media supplements as well as pH and temperature shifts applied during the process. First, principal component analysis (PCA) is used to show the strong correlation characteristics among the product quality attributes including aggregates, fragments, charge variants, and glycans. Then, partial least square regression (PLS1 and PLS2) is applied to predict the product quality variables based on process information (one by one or simultaneously). The comparison of those two modeling techniques shows that a single (PLS2) model is capable of revealing the interrelationship of the process characteristics to the large set product quality variables. In order to show the dynamic evolution of the process predictability separate models are defined at different time points showing that several product quality attributes are mainly driven by the media composition and, hence, can be decently predicted from early on in the process, while others are strongly affected by process parameter changes during the process. Finally, by coupling the PLS2 models with a genetic algorithm first the model performance can be further improved and, most importantly, the interpretation of the large-dimensioned process-product-interrelationship can be significantly simplified. The generally applicable toolset presented in this case study provides a solid basis for decision making and process optimization throughout process development. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 33:1368-1380, 2017.

Towards better process understanding: chemometrics and multivariate measurements in manufacturing of solid dosage forms

The manufacturing of tablets involves many unit operations that possess multivariate and complex characteristics. The interactions between the material characteristics and process related variation are presently not comprehensively analyzed due to univariate detection methods. As a consequence, current best practice to control a typical process is to not allow process-related factors to vary i.e. lock the production parameters. The problem related to the lack of sufficient process understanding is still there: the variation within process and material properties is an intrinsic feature and cannot be compensated for with constant process parameters. Instead, a more comprehensive approach based on the use of multivariate tools for investigating processes should be applied. In the pharmaceutical field these methods are referred to as Process Analytical Technology (PAT) tools that aim to achieve a thorough understanding and control over the production process. PAT includes the frames for measurement as well as data analyzes and controlling for in-depth understanding, leading to more consistent and safer drug products with less batch rejections. In the optimal situation, by applying these techniques, destructive end-product testing could be avoided. In this paper the most prominent multivariate data analysis measuring tools within tablet manufacturing and basic research on operations are reviewed.

General procedure to aid the development of continuous pharmaceutical processes using multivariate statistical modeling - an industrial case study

Streamlining the manufacturing process has been recognized as a key issue to reduce production costs and improve safety in pharmaceutical manufacturing. Although data available from earlier developmental stages are often sparse and unstructured, they can be very useful to improve the understanding about the process under development. In this paper, a general procedure is proposed for the application of latent variable statistical methods to support the development of new continuous processes in the presence of limited experimental data. The proposed procedure is tested on an industrial case study concerning the development of a continuous line for the manufacturing of paracetamol tablets. The main driving forces acting on the process are identified and ranked according to their importance in explaining the variability in the available data. This improves the understanding about the process by elucidating how different active pharmaceutical ingredient pretreatments, different formulation modes and different settings on the processing units affect the overall operation as well as the properties of the intermediate and final products. The results can be used as a starting point to perform a comprehensive and science-based quality risk assessment that help to define a robust control strategy, possibly enhanced with the integration of a design space for the continuous process at a later stage.

Study of the application of multiway multivariate techniques to model data from an industrial fermentation process

Several multivariate statistical techniques have been extensively proposed for monitoring industrial processes. In this paper, multiway extensions of two such techniques: multiway principal component analysis (MPCA) and multiway partial least squares regression (MPLS) were applied to a large data set from an industrial pilot-scale fermentation process to improve process knowledge. The MPCA model is able to diagnose faults occurring in the process whether they affect or not process productivity while the MPLS model enables the prediction of final product concentration and the detection of faults that will influence the fermentation productivity.

The Process Analytical Technology initiative and multivariate process analysis, monitoring and control

Process analytical technology is an essential step forward in pharmaceutical industry. Real-time analyzers will provide timely data on quality properties. This information combined with process data (temperatures, flow rates, pressure readings) collected in real time can become a powerful tool for this industry, for process understanding, process and quality monitoring, abnormal situation detection and for improving product quality and process reliability. A very important tool for this achievement is the multivariate analysis.