Chemically, physically and visually identical to their mined counterparts, synthetic diamonds and tungsten carbide super materials promise the same benefits to industry… plus that bit more.
The planet’s hardest material, the diamond’s extreme and diverse properties give it the high tensile strength, chemical inertness, broad optical transmission and outstanding thermal conductivity.
Throughout a range of industry applications, synthetic super materials are preferred, thanks to their unrivalled purity and hardness. Lab-grown diamonds, for example, are 10 times more durable than natural ones.
In recent years, the technology behind lab-grown diamonds has made significant advances – allowing for high-quality diamonds to be grown more efficiently.
THE CHALLENGE
Element Six (E6) is a global leader in the design, development and production of synthetic diamond and tungsten carbide super materials.
Since 1959, the company has worked to deliver extreme performance through the development of innovative, cutting-edge synthetic diamond and tungsten carbide solutions.
E6 are always looking for ways to accurately predict synthetic diamond material properties to improve discovery and R & D.
Recognising the importance of facilitating the development of machine learning models, the team approached T-DAB for a solution enabling the automatic collection, integration, and storage of data from experiments carried out by a collaborative robot (CoBot).
THE SOLUTION
Guided by the expertise and insights from the team at E6, T-DAB developed an easy-to-use tool engineered to automatically collect data from the CoBot; store and integrate it and allow for data analysis from individual and aggregated experiments.
The platform utilises AWS and Azure for maximum reliability and it automatically harvests data collected from IoT sensors on the CoBot – saving material scientists time, while eliminating the risk of errors.
Its ETL process, which ran as a Windows service during development, also allows for the loading of historic, manually collected data.
Previously, experimental data was printed out as a PDF, to be manually followed by material scientists. By integrating the ETL process with E6’s legacy Lotus Notes database, this manual process could be presented as a webform – eliminating the need to re-enter, or duplicate, data.
A powerful tool for analysis, the solution features an intuitive Power BI dashboard which allows E6 to leverage data from experiments. Quick and easy to use, it has reduced the time necessary for analysis aggregation time from as much as 4 hours to as little as a few seconds.
Collaboration is key to a project’s success. T-DAB required the client to develop its in-house data science team to support this, backed by legacy services.
As well as fully integrating E6’s junior data scientists and engineers into the project team to work alongside T-DAB, a programme of weekly technical help clinics was delivered.
While the client junior engineer was introduced to data engineering principles including SQL servers and ETL, the client junior data scientist now has a deeper knowledge of machine learning methods, including Bayesian Statistics and Convolutional Neural Networks.
THE RESULT
T-DAB acted as domain experts throughout the project, with E6 providing the guidance and steering necessary for the project’s success.
This collaboration increased data collection efficiency by more than 700%. In operations involving the CoBot, that rises to as much as 1500%, while increasing data quality by 300%.
Analysis is quicker and sharper, ensuring the R&D team can receive the vital information they need faster, with far greater accuracy and traceability.
T-DAB’s effective knowledge-sharing ensured E6’s team could achieve the best results and use of the tool.
As well as enhancing the R&D team’s data input, quality and storage, the project provides a foundation for further digital growth, while serving as a strong reminder of the benefits data can deliver when properly harnessed.
