Data-based latent variable methods for process analysis, monitoring and control

An Optimization Approach Coupling Preprocessing with Model Regression for Enhanced Chemometrics

Chemometric methods are broadly used in the chemical and biochemical sectors. Typically, derivation of a regression model follows data preprocessing in a sequential manner. Yet, preprocessing can significantly influence the regression model and eventually its predictive ability. In this work, we investigate the coupling of preprocessing and model parameter estimation by incorporating them simultaneously in an optimization step. Common model selection techniques rely almost exclusively on the performance of some accuracy metric, yet having a quantitative metric for model robustness can prolong model up-time. Our approach is applied to optimize for model accuracy and robustness. This requires the introduction of a novel mathematical definition for robustness. We test our method in a simulated set up and with industrial case studies from multivariate calibration. The results highlight the importance of both accuracy and robustness properties and illustrate the potential of the proposed optimization approach toward automating the generation of efficient chemometric models.

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.

Multimode Operating Performance Visualization and Nonoptimal Cause Identification

In the traditional performance assessment method, different modes of data are classified mainly by expert knowledge. Thus, human interference is highly probable. The traditional method is also incapable of distinguishing transition data from steady-state data, which reduces the accuracy of the monitor model. To solve these problems, this paper proposes a method of multimode operating performance visualization and nonoptimal cause identification. First, multimode data identification is realized by subtractive clustering algorithm (SCA), which can reduce human influence and eliminate transition data. Then, the multi-space principal component analysis (MsPCA) is used to characterize the independent characteristics of different datasets, which enhances the robustness of the model with respect to the performance of independent variables. Furthermore, a self-organizing map (SOM) is used to train these characteristics and map them into a two-dimensional plane, by which the visualization of the process monitor is realized. For the online assessment, the operating performance of the current process is evaluated according to the projection position of the data on the visual model. Then, the cause of the nonoptimal performance is identified. Finally, the Tennessee Eastman (TE) process is used to verify the effectiveness of the proposed method.

Steady-State Data Reconciliation Framework for a Direct Continuous Tableting Line

Purpose

Reliable process monitoring in real-time remains a challenge for the pharmaceutical industry. Dealing with random and gross errors in the process measurements in a systematic way is a potential solution. In this paper, we present a process model-based framework, which for given sensor network and measurement uncertainties will predict the most likely state of the process. Thus, real-time process decisions, whether for process control or exceptional events management, can be based on the most reliable estimate of the process state.

Methods

Reliable process monitoring is achieved by using data reconciliation (DR) and gross error detection (GED) to mitigate the effects of random measurement errors and non-random sensor malfunctions. Steady-state data reconciliation (SSDR) is the simplest forms of DR but offers the benefits of short computational times. We also compare and contrast the model-based DR approach (SSDR-M) to the purely data-driven approach (SSDR-D) based on the use of principal component constructions.

Results

We report the results of studies on a pilot plant-scale continuous direct compression-based tableting line at steady-state in two subsystems. If the process is linear or mildly nonlinear, SSDR-M and SSDR-D give comparable results for the variables estimation and GED. SSDR-M also complies with mass balances and estimate unmeasured variables.

Conclusions

SSDR successfully estimates the true state of the process in presence of gross errors, as long as steady state is maintained and the redundancy requirement is met. Gross errors are also detected while using SSDR-M or SSDR-D. Process monitoring is more reliable while using the SSDR framework.

A Multivariate Statistical Analyses of Membrane Performance in the Clarification of Citrus Press Liquor

The orange press liquor is a by-product of the orange juice production containing bioactive compounds recognized for their beneficial implications in human health. The recovery of these compounds offers new opportunities for the formulation of products of interest in food, pharmaceutical and cosmetic industry. The clarification of orange press liquor by microfiltration (MF) and/or ultrafiltration (UF) processes is a valid approach to remove macromolecules, colloidal particles, and suspended solids from sugars and bioactive compounds. In this work the clarification of orange press liquor was studied by using three flat-sheet polymeric membranes: a MF membrane with a pore size of 0.2 μm and two UF membranes with nominal molecular weight cut-off (MWCO) of 150 and 200 kDa, respectively. The membrane performance, in terms of permeate flux and membrane rejection towards hesperidin and sugars, was studied according to a multivariate analyses approach. In particular, characteristics influencing the performance of the investigated membranes, such as molecular weight cut-off (MWCO), contact angle, membrane thickness, pore size distribution, as well as operating conditions, including temperature, and operating time, were analysed through the partial least square regression (PLSR). The multivariate method revealed crucial information on variables which are relevant to maximize the permeate flux and to minimize the rejection of hesperidin and sugars in the clarification of orange press liquor.

Compositional analysis of lignocellulosic biomass: conventional methodologies and future outlook

The composition and structural properties of lignocellulosic biomass have significant effects on its downstream conversion to fuels, biomaterials, and building-block chemicals. Specifically, the recalcitrance to modification and compositional variability of lignocellulose make it challenging to optimize and control the conditions under which the conversion takes place. Various characterization protocols have been developed over the past 150 years to elucidate the structural properties and compositional patterns that affect the processing of lignocellulose. Early characterization techniques were developed to estimate the relative digestibility and nutritional value of plant material after ingestion by ruminants and humans alike (e.g. dietary fiber). Over the years, these empirical techniques have evolved into statistical approaches that give a broader and more informative analysis of lignocellulose for conversion processes, to the point where an entire compositional and structural analysis of lignocellulosic biomass can be completed in minutes, rather than weeks. The use of modern spectroscopy and chemometric techniques has shown promise as a rapid and cost effective alternative to traditional empirical techniques. This review serves as an overview of the compositional analysis techniques that have been developed for lignocellulosic biomass in an effort to highlight the motivation and migration towards rapid, accurate, and cost-effective data-driven chemometric methods. These rapid analysis techniques can potentially be used to optimize future biorefinery unit operations, where large quantities of lignocellulose are continually processed into products of high value.

Multivariate Analysis and Statistics in Pharmaceutical Process Research and Development

The application of statistics in pharmaceutical process research and development has evolved significantly over the past decades, motivated in part by the introduction of the Quality by Design paradigm, a landmark change in regulatory expectations for the level of scientific understanding associated with the manufacturing process. Today, statistical methods are increasingly applied to accelerate the characterization and optimization of new drugs created via numerous unit operations well known to the chemical engineering discipline. We offer here a review of the maturity in the implementation of design of experiment techniques, the increased incorporation of latent variable methods in process and material characterization, and the adoption of Bayesian methodology for process risk assessment.

Aluminium Process Fault Detection and Diagnosis

The challenges in developing a fault detection and diagnosis system for industrial applications are not inconsiderable, particularly complex materials processing operations such as aluminium smelting. However, the organizing into groups of the various fault detection and diagnostic systems of the aluminium smelting process can assist in the identification of the key elements of an effective monitoring system. This paper reviews aluminium process fault detection and diagnosis systems and proposes a taxonomy that includes four key elements: knowledge, techniques, usage frequency, and results presentation. Each element is explained together with examples of existing systems. A fault detection and diagnosis system developed based on the proposed taxonomy is demonstrated using aluminium smelting data. A potential new strategy for improving fault diagnosis is discussed based on the ability of the new technology, augmented reality, to augment operators’ view of an industrial plant, so that it permits a situation-oriented action in real working environments.

Supervisory control system for monitoring a pharmaceutical hot melt extrusion process

Continuous pharmaceutical manufacturing processes are of increased industrial interest and require uni- and multivariate Process Analytical Technology (PAT) data from different unit operations to be aligned and explored within the Quality by Design (QbD) context. Real-time pharmaceutical process verification is accomplished by monitoring univariate (temperature, pressure, etc.) and multivariate (spectra, images, etc.) process parameters and quality attributes, to provide an accurate state estimation of the process, required for advanced control strategies. This paper describes the development and use of such tools for a continuous hot melt extrusion (HME) process, monitored with generic sensors and a near-infrared (NIR) spectrometer in real-time, using SIPAT (Siemens platform to collect, display, and extract process information) and additional components developed as needed. The IT architecture of such a monitoring procedure based on uni- and multivariate sensor systems and their integration in SIPAT is shown. SIPAT aligned spectra from the extrudate (in the die section) with univariate measurements (screw speed, barrel temperatures, material pressure, etc.). A multivariate supervisory quality control strategy was developed for the process to monitor the hot melt extrusion process on the basis of principal component analysis (PCA) of the NIR spectra. Monitoring the first principal component and the time-aligned reference feed rate enables the determination of the residence time in real-time.

Principal component analysis for the early detection of mastitis and lameness in dairy cows

This investigation analysed the applicability of principal component analysis (PCA), a latent variable method, for the early detection of mastitis and lameness. Data used were recorded on the Karkendamm dairy research farm between August 2008 and December 2010. For mastitis and lameness detection, data of 338 and 315 cows in their first 200 d in milk were analysed, respectively. Mastitis as well as lameness were specified according to veterinary treatments. Diseases were defined as disease blocks. The different definitions used (two for mastitis, three for lameness) varied solely in the sequence length of the blocks. Only the days before the treatment were included in the blocks. Milk electrical conductivity, milk yield and feeding patterns (feed intake, number of feeding visits and time at the trough) were used for recognition of mastitis. Pedometer activity and feeding patterns were utilised for lameness detection. To develop and verify the PCA model, the mastitis and the lameness datasets were divided into training and test datasets. PCA extracted uncorrelated principle components (PC) by linear transformations of the raw data so that the first few PCs captured most of the variations in the original dataset. For process monitoring and disease detection, these resulting PCs were applied to the Hotelling's T2 chart and to the residual control chart. The results show that block sensitivity of mastitis detection ranged from 77·4 to 83·3%, whilst specificity was around 76·7%. The error rates were around 98·9%. For lameness detection, the block sensitivity ranged from 73·8 to 87·8% while the obtained specificities were between 54·8 and 61·9%. The error rates varied from 87·8 to 89·2%. In conclusion, PCA seems to be not yet transferable into practical usage. Results could probably be improved if different traits and more informative sensor data are included in the analysis.