|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, TADA 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.

TADA 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. TADA 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.

TADA 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.

Talk to us on how you can make sense of your data and achieve success.

More use cases

Breast Cancer Prediction for Improved Diagnosis

Breast cancer prediction is a diagnosis tool. Oncologists and medical staff face the challenge of identifying breast cancer as soon as possible. ...

Customer recommendation: key drivers identification

The world of ISPs is highly competitive. Customers trust, above all else, other customers’ recommendations. ...

Retaining Customers: Churn Prediction

Anytime a client cuts ties, you encounter the negative consequence of customer churn. While some churn is a natural component of any company, a vast churn rate can cripple any organization's growth. ...

Boosting Lead Qualification with Prediction

On average, the cost of one lead is $198 in 2020. The better the lead qualification, the higher the chances of closing with the customer and generating revenue from these $198 invested. ...

Estimating your House Listing Price

In 2019, 5.34 million existing private homes changed owners, according to data from the National Association of REALTORS®. 89% of sellers were helped by a real estate agent when trading their home....

Predicting the Selling Price of a Used Car

Sales of used light vehicles in the United States grew to about 40.8 million units in 2019. The same year, the average selling price of used cars came to nearly 21,000 U.S. dollars. ...