Process Validation and Design of Experiments The following

Process Validation and Design of Experiments The following Power. Point presentation was presented by Robert Launsby at the MDM Conference in Anaheim, CA on February 12, 2015. For more information regarding Design of Experiments and Process Validation go to: www. launsby. com 3/18/2018 Launsby Consulting 1

Process Validation and Design of Experiments Launsby Consulting 3/18/2018 2

Robert G Launsby n n n President of Launsby Consulting in Colorado Springs MS in engineering Taught thousands about this topic n APPLICATIONS focused Author of four books Co-developer of WISDOM software 10 k gold medalist at National Senior Games 2009 www. launsby. com 3/18/2018 Launsby Consulting 3

Agenda n n n Enhancing New Product and Process success rate How to link DOE (design of experiments) with Process Validation Quick DOE example How to link DOE analysis and Monte Carlo Analysis to PV activities A brief example using Statabot 3/18/2018 Launsby Consulting 4

How To Improve New Product Success Rate n n n Customer focus (how do we make the customer successful? ) Management leads change, All Levels Implement a development process and have the discipline to use it Make data driven decisions, use tools Metrics to map progress T≠C 3/18/2018 Launsby Consulting 5

Roadmap From book “Straight Talk on Process Validation” available at Amazon. com Get your design inputs right at system/sub system/com ponent level early 3/18/2018 Launsby Consulting

Roadmap 3/18/2018 Launsby Consulting

Roadmap 3/18/2018 Launsby Consulting

Roadmap 3/18/2018 Launsby Consulting

In a Nutshell n n n IQ…. equipment setup correct? OQ…can we make a good part? Can we make good parts at worst case? This is where Design of Experiments supports PV PQ…can we make many good parts under production conditions? 3/18/2018 Launsby Consulting

What Is A Designed Experiment? n Systematic, controlled changes of the inputs (factors) to a process in order to observe corresponding changes in the outputs (responses). Why do this: 4 times the information with ½ the tests 3/18/2018 Launsby Consulting 11

What Is A P-diagram? Outputs Inputs PROCESS 3/18/2018 Launsby Consulting 12

Engineering Experimental Design n Not a substitute for knowledge of technology Incorporates current understanding n Physics first n n It is all about good scientific understanding (with some math blended in) 3/18/2018 Launsby Consulting 13

Taken from the text “Engineering Today’s Designed Experiments” available at Amazon. com Steps In Conducting DOE Keys Plan Select O. A. Define Objective, Select Factors, Levels, Responses, etc Automated by software Conduct Have a plan, be there Analyze Graphs, statistical analysis, predict responses at best set points Confirm Demonstrate with data the prediction from transfer function is useful 3/18/2018 Launsby Consulting 14

An Example Run Na. Cl EDTA Activity 1 5 1 27, 28 2 5 10 24, 24 3 10 1 33, 35 4 10 10 31, 30 Suppose we have processed an enzyme and want to store in a buffered solution. We want to maintain highest activity level while in storage. What are best conditions for NACL and EDTA to achieve this goal? 3/18/2018 Launsby Consulting 15

Pareto Chart 3/18/2018 Launsby Consulting 16

Main Effects Plot 3/18/2018 Launsby Consulting 17

Interaction Plot 3/18/2018 Launsby Consulting 18

What Is An Interaction? n n Refers to synergism between factors relative to a response. Two factors interact if the influence of one factor is impacted by the level of another factor 3/18/2018 Launsby Consulting 19

Transfer Function n The equation (algebraic) It comes from MLR Three important assumptions n n n Two levels Software packages use MLR to generate transfer function O. A Variables are on orthogonal scale 3/18/2018 Launsby Consulting 20

MLR Math includes factors (assumes 4 run previous example), and interaction effect 3/18/2018 Launsby Consulting 21

Contour Plot 3/18/2018 Launsby Consulting 22

RSM Plot 3/18/2018 Launsby Consulting 23

Basic Statistical Analysis 3/18/2018 Launsby Consulting 24

DOE and PV Steps 1. 2. 3. 4. 5. 6. Select key factors/levels responses (based upon pre-PV characterization studies) Conduct Orthogonal Array Perform analysis Predict best set-points to target response(s) Confirm above predictions Using math. model from DOE, conduct MC using worst case for inputs 3/18/2018 Launsby Consulting

DOE and PV Steps (continued) 7. 8. 9. Plot variation from Monte Carlo analysis Run process at actual worst case scenario Ensure MC analysis and actual results at worst case provide equivalent and acceptable potential process capability 3/18/2018 Launsby Consulting

DOE and Monte Carlo Using the Statabot 3/18/2018 Launsby Consulting

Graphical Analysis of Statbot DOE 3/18/2018 Launsby Consulting

Outputs From Prediction Model Set motor A at 40, motor B at 42 to target 20 seconds for response 3/18/2018 Launsby Consulting

Confirmation of DOE at 20 Seconds Great potential capability at predicted settings, but very short term Note: suppose we know batteries power can vary by +/- 5% before software in Statabot shuts down…. what is potential impact of this phenomena? 3/18/2018 Launsby Consulting

Monte Carlo Analysis n n Using parsimonious equation from DOE Vary input power by +/-5 in Monte Carlo analysis and plot the output in response This is a simulation of longer term variation 3/18/2018 Launsby Consulting

Recommendations n Software for DOE n n n Minitab or JMP if you are well versed in statistics…and need package with numerous capabilities DOE Wisdom if you have little statistics background and just need DOE support Fimmtech’s NAUTILUS software if you are injection molder 3/18/2018 Launsby Consulting