|Solutions|Product Formulation Optimization : Fire-Resistant Paint

Product Formulation Optimization : Fire-Resistant Paint

Fire-resistant material is a must for helicopters. A helicopter manufacturer wants to design fire-resistant material for its passenger compartment. Their essential objective is for the material to take at least 15 minutes to combust to give the pilot the time (and a chance) to eject. Based on a set of historical laboratory tests data performed by the helicopter manufacturer, Quaartz identified an excellent mix of components and their proportion to create a fire-resistant material.

Industry

Helicopter – Aviation – Materials

Project Duration and Effort

Six days

tYPE OF PREDICTION

Binary Classification

Customer Benefits

6 days only to extract essential information about the materials tested from 40 years of accumulated data
Find out which components and their combinations are fire-resistant with excellent accuracy
Get right away the optimal mix of the various elements to use in the resulting material

Problem to solve

A helicopter manufacturer has been testing various compositions of cabin components materials for the past 40 years. The goal is to protect the pilots from a fast-spreading fire and give them enough time to eject (i.e., 15 minutes). It has gathered these 40 years of laboratory tests on the diverse materials. The resulting database contains approximately 500 records. The manufacturer’s design team wants to know which components are critical for obtaining fire-resistance. They also want to determine each component’s proportion to use in the end material to achieve this goal. Hence, the helicopter manufacturer intends to accomplish both data mining objectives by digging out crucial information from 40 years of past lab results and accurate prediction. They also want to know the accuracy of these predictions. There are different purposes to achieve in this material design study: to use the lab data collected, reduce the time required and cost of the analysis and get a competitive edge in fire-resistant material design, all the while protecting lives.

Objectives

Find the right combination and proportions of components to get an optimal fire-resistant material.
Make the best use of the 40 years of laboratory data (500 records) to identify critical factors.

Our customer wants to answer the following question:
Can we predict which components to use with precision, in which proportions to create a new fire-resistant material, in a few days?

Solution

We started with a database of 500 records. The records contain lab tests results on the fire-resistance of different materials under diverse circumstances. For each record, the database includes both pieces of information on the material and the test setup. As far as the material is concerned, it indicates the type of resin used, its density, its polymer class, its fabric, the weaving style, the weave weight, the solvent, the paint. Regarding the test setup, the fire agent experiments are logged, and the laboratory in charge of the testing.

Quaartz has found several combinations of components which designed excellent fire-resistant materials in a short amount of time. Where it typically takes several months to develop fire-resistant material between the formulation by the material design team and the lab testing, it takes here the same material design team six days to achieve the same result. Quaartz empowers the material design team to mine 40 years of lab testing data and extracts the essential information, where the team saved months. The most impacting factors were the prepreg (i.e., pre-impregnated) resin used, the material’s thickness (by far the most important criteria), and the resin density.

Quaartz made such predictions with 86% accuracy.
Once identified, we can visualize, through valuable ‘Live Predict’ visualization (what-if analysis), what will happen if we vary the material’s thickness.

Products

For Enterprises

Offers and services