Using factorial design and multivariate analysis when experimenting in a continuous process

Abstract

This article discusses the design and analysis of an experiment performed in a continuous process (CP). Three types of iron ore pellets are tested on two levels of a process variable in an experimental blast furnace process, using a full factorial design with replicates. A multivariate approach to the analysis of the experiment in the form of principal component analysis combined with analysis of variance is proposed. The analysis method also considers the split-plot-like structure of the experiment. The article exemplifies how a factorial design combined with multivariate analysis can be used to perform product development experiments in a CP. CPs also demand special considerations when planning, performing and analyzing experiments. The article highlights and discusses such issues and considerations, for example, the dynamic characteristic of CPs, a strategy to handle disturbances during experimentation and the need for process control during experimentation.

Towards Improved Analysis Methods for Two‐Level Factorial Experiments with Time Series Responses

“…To relate our simulations to an actual industrial setting, the choice of process model, including the dynamics of active factors, is inspired by the authors' work with an experimental blast furnace (see Vanhatalo and Bergquist and Vanhatalo and Vännman). The simulated response we use throughout this article is carbon monoxide (CO) efficiency (hereafter η CO ), an important response for the blast furnace where higher values generally are preferred as they indicate a more energy‐efficient process.…”

Integration of Response Surface Methodology (RSM) and Principal Component Analysis (PCA) as an Optimization Tool for Polymer Inclusion Membrane Based-Optodes Designed for Hg(II), Cd(II), and Pb(II)

“…By coupling both chemometric areas, DoE and MVA, a valuable way to study complex chemical systems is created. In this context, such connection has been used, either in a complementary or integral form, in diverse areas, such as product development in a continuous process [ 4 ], the development of a drug product [ 5 ], size exclusion chromatography for development of silica-based stationary phases [ 6 ], for undertaking metabolomic studies [ 7 ], for enhancing the performance of cathodes [ 8 ], for studying the cadmium biosorption process [ 9 ], for studying the effects of physical properties of dosage forms [ 10 ], to determine the moisture content in mAb lyophilisates [ 11 ], and to create solvent maps to identify safer alternatives to toxic/hazardous solvents, and also in the optimization of an SNAr reaction [ 12 ], among others. Despite such a wide range of applications, in the area of optodes for metal ions, although DoE strategies have been employed [ 13 , 14 ], little advantage has been taken from the simultaneous coupling between DoE and MVA concerning the manufacturing and optimization of sensor composition.…”

Analysis of an unreplicated 22factorial experiment performed in a continuous process

“…From an experimental perspective, it is often difficult to choose response variables since the process variables usually are interconnected and correlated, and many variables will react to the same event (Kourti & MacGregor, 1995). Multivariate techniques have therefore been considered important for experimental analysis of such experiments (see Vanhatalo & Vännman 2008). Another difficulty is that process variables usually are measured with high frequency in relation to the process dynamics.…”