5. Process Improvement
5.5. Advanced topics
5.5.3. How do you optimize a process?
5.5.3.2. Multiple response case

5.5.3.2.3.

Multiple responses: The mathematical programming approach

The mathematical programming approach maximizes or minimizes a primary response, subject to appropriate constraints on all other responses

The analysis of multiple response systems usually involves some type of optimization problem. When one response can be chosen as the "primary", or most important response, and bounds or targets can be defined on all other responses, a mathematical programming approach can be taken. If this is not possible, the desirability approach should be used instead.

In the mathematical programming approach, the primary response is maximized or minimized, as desired, subject to appropriate constraints on all other responses. The case of two responses ("dual" responses) has been studied in detail by some authors and is presented first. Then, the case of more than 2 responses is illustrated.

• Dual response systems
• More than 2 responses

Dual response systems

Optimization of dual response systems

The optimization of dual response systems (DRS) consists of finding operating conditions x that

with T denoting the target value for the secondary response, p the number of primary responses (i.e., responses to be optimized), s the number of secondary responses (i.e., responses to be constrained), and is the radius of a spherical constraint that limits the region in the controllable factor space where the search should be undertaken. The value of should be chosen with the purpose of avoiding solutions that extrapolate too far outside the region where the experimental data were obtained. For example, if the experimental design is a central composite design, choosing (axial distance) is a logical choice. Bounds of the form L x_i U can be used instead if a cubical experimental region were used (e.g., when using a factorial experiment). Note that a Ridge Analysis problem is related to a DRS problem when the secondary constraint is absent. Thus, any algorithm or solver for DRS's will also work for the Ridge Analysis of single response systems.

Nonlinear programming software required for DRS

In a DRS, the response models and can be linear, quadratic or even cubic polynomials. A nonlinear programming algorithm has to be used for the optimization of a DRS. For the particular case of quadratic responses, an equality constraint for the secondary response, and a spherical region of experimentation, specialized optimization algorithms exist that guarantee global optimal solutions. In such a case, the algorithm DRSALG can be used (download from http://www.nist.gov/cgi-bin/exit_nist.cgi?url=http://www.stat.cmu.edu/jqt/29-3), but a Fortran compiler is necessary.

More general case

In the more general case of inequality constraints or a cubical region of experimentation, a general purpose nonlinear solver must be used and several starting points should be tried to avoid local optima. This is illustrated in the next section.

Example for more than 2 responses

Example: problem setup

The values of three components (x₁, x₂, x₃) of a propellant need to be selected to maximize a primary response, burning rate (Y₁), subject to satisfactory levels of two secondary reponses; namely, the variance of the burning rate (Y₂) and the cost (Y₃). The three components must add to 100% of the mixture. The fitted models are:

The optimization problem

The optimization problem is therefore:

maximize	1(x)
subject to:	2(x) -4.5
	3(x) 20
	x1 + x2 + x3 = 1.0
	0 x1 1
	0 x2 1
	0 x3 1

Solve using Excel solver function

We can use Microsoft Excel's "solver" to solve this problem. The table below shows an Excel spreadsheet that has been set up with the problem above. Cells B2:B4 contain the decision variables (cells to be changed), cell E2 is to be maximized, and all the constraints need to be entered appropriately. The figure shows the spreadsheet after the solver completes the optimization. The solution is (x^*)' = (0.212, 0.343, 0.443) which provides ₁ = 106.62, ₂ = 4.17, and ₃ = 18.23. Therefore, both secondary responses are below the specified upper bounds. The solver should be run from a variety of starting points (i.e., try different initial values in cells B1:B3 prior to starting the solver) to avoid local optima. Once again, confirmatory experiments should be conducted at the estimated optimal operating conditions.

Excel spreadsheet

	A	B	C	D	E
1	Factors			Responses
2	x1	0.21233		Y1(x)	106.6217
3	x2	0.343725		Y2(x)	4.176743
4	x3	0.443946		Y3(x)	18.23221
5	Additional	constraint
6	x1 + x2 + x3	1.000001