Design variables selection

Lee, W. Christensen J. H. and Rudd, D. F. (1966) AIChEJl 12, 1104. Design variable selection to simplify process calculations. 

The number of published accounts of variable selection methods in the general literature is enormous. To provide a focus, this section will concentrate just on applications to computer-aided drug design. Variable selection was identified as an important requirement at about the same time as the need for variable elimination techniques. The simplest method of variable selection is to choose those variables that have a large correlation with the response and, for simple datasets, that method is probably not a bad choice. As we have shown in this chapter, variable selection may be an integral part of a modeling technique, but not all modeling methods lend themselves to variable selection, and in these cases, other techniques need to be applied. 

Platform Variables. Platform variables of an equation are new variables of an equation in which there are more than one new variable. Platform variables contain desirable design variable selections. If multiple root variables appear as platform variables, it is useful to select them as a design variable if possible. 

Motard, R. L., Shacham, M., and Rosen, E. M., Design Variable Selection to Simplifying Process Calculations, AIChE Journal 21, No. 3,... 

The process design variable selected for the modelled process in the multi-objective optimisation search engine is the portion of HCl recycled to the oxy-chlorinator unit while the produced HCl is dealt with as a by-product that have a specific value. It would be a straightforward extension to the framework to include multiple design variables - however, in this paper, only a single variable was considered for ease of demonstration. Also, as the environmental potentials in this case all trend in the same direction, the impact potential most sensitive to this design variable, i.e. GWP, was chosen to represent the environmental performance of the process. 

If distillation is the choice of separator, then some preliminary selection of the major design variables must be made to allow the design to proceed. The first decision is operating pressure. As pressure is raised,... 

Cruciani G, S dementi and M Baroni 1993. Variable Selection in PLS Analysis. In Kubinyi H (Editor) 31 QSAR in Drug Design. Leiden, ESCOM, pp. 551-564. 

Understanding the chemistry of the process also provides the greatest opportunity in applying the principles of inherent safety at the chemical synthesis stage. Process chemistry greatly determines the potential impact of the processing facility on people and the environment. It also determines such important safety variables as inventory, ancillary unit operations, by-product disposal, etc. Creative design and selection of process chemistry can result in the use of inherently safer chemicals, a reduction in the inventories of hazardous chemicals and/or a minimization of waste treatment requirements. 

Signal-flow graphs are particularly useful in two respects. First, they make the process designer examine in considerable detail the dynamic structure and fimctioning of the process. Second, the nature of the interface between person and machine can be seen more clearly. The variables that are displayed in a system are, of course, available for study, but workers frequently respond to derivative functions of variables or "hidden" variables that must be deduced. Given that the process variables to be displayed will influence the worker s control strategy and that the number of deductions to be made will affect the mental workload involved, a process designer can select the type and amoimt of process information which will enhance performance of the task. 

For nonlinear systems, however, the evaluation of the flow rates is not straightforward. Morbidelli and co-workers developed a complete design of the binary separation by SMB chromatography in the frame of Equilibrium Theory for various adsorption equilibrium isotherms the constant selectivity stoichiometric model [21, 22], the constant selectivity Langmuir adsorption isotherm [23], the variable selectivity modified Langmuir isotherm [24], and the bi-Langmuir isotherm [25]. The region for complete separation was defined in terms of the flow rate ratios in the four sections of the equivalent TMB unit ... 

Though the total degrees of freedom is seen to be (C + 4) some of the variables will normally be fixed by general process considerations, and will not be free for the designer to select as design variables . The flash distillation unit will normally be one unit in a process system and the feed composition and feed conditions will be fixed by the upstream processes the feed will arise as an outlet stream from some other unit. Defining the feed fixes (C + 2) variables, so the designer is left with ... 

The variables selected as design variables (fixed by the designer) cannot therefore be assigned as output variables from an f node. They are inputs to the system and their edges must be oriented into the system of equations. 

If, for instance, variables r3 and u4 are selected as design variables, then Figure 1.11 shows one possible order of solution of the set of equations. Different types of arrows are used to distinguish between input and output variables, and the variables selected as design variables are enclosed in a double circle. 

With this order, the equations can be solved sequentially, with no need for the simultaneous solution of any of the equations. The fortuitous selection of v3 and v4 as design variables has given an efficient order of solution of the equations. 

For many design calculations it will not be possible to select the design variables so as to eliminate the recycle of information and obviate the need for iterative solution of the design relationships. 

The biparte graph for this example, with 3 and 5 selected as the design variables (inputs), is shown in Figure 1.13. 

When a design problem cannot be reduced to an acyclic form by judicious selection of the design variables, the design variables should be chosen so as to reduce the recycle of... 

K Degrees of freedom (variables free to be selected as design variables) —... 

In manual calculations the designer can use intuition in selecting the design variables and, as he proceeds with the calculation, can define other variables if it becomes clear that... 

Quantitative Structure-Activity Relationship models are used increasingly in chemical data mining and combinatorial library design [5, 6]. For example, three-dimensional (3-D) stereoelectronic pharmacophore based on QSAR modeling was used recently to search the National Cancer Institute Repository of Small Molecules [7] to find new leads for inhibiting HIV type 1 reverse transcriptase at the nonnucleoside binding site [8]. A descriptor pharmacophore concept was introduced by us recently [9] on the basis of variable selection QSAR the descriptor pharmacophore is defined as a subset of... 

At this point an attempt has been made to identify all of the important v ari-ables. It has also been decided which variables will be fixed and which will be varied. For the nonfixed variables, the range and number of levels (complexity) have been determined. Classical experimental design tools will be used to specify the design for the controllable variables. The design is selected via a software package or statistical reference materials and it specifies (1) the number of runs, (2) the levels of the variable(s), and (3) tlie order of the runs. 

Vector projection operators act by cancelhng out all components of a vector except the one it is designed to select. The decomposition of a function in an analogous way requires expression of the function as a sum of components each of a proper symmetry species. For example, it is possible to write any function of three variables as a sum of components that are symmetric or antisymmetric with respect to inversion ... 

It is clear from this formula that the variance of the response is independent of x, the settings of the design variables. Consequently, there is no opportunity for achieving a more robust response in the presence of the environmental variation, z, by selecting particular settings for the design variables. 

---