Industry: Manufacturing Area: HDD/SSD Solution: Machine Learning
Our client for this project is an American data storage company. It is one of the largest providers of both Hard and Solid State Drives globally and has been operating for over 40 years.
One of the key components of these devices is a silicone wafer, which acts as a semi conductor within the drives. These wafers are highly sensitive to their environment, factors such as improper temperature, air quality and air moisture, can all lead to the material being compromised and unfit for use. The manufacturing process is extremely complex and involves hundreds of separate actions, it takes approximately 60 days to turn the raw materials into the finished product. Each silicone wafer costs between £20-£50, and in some cases failure rates can reach 10%.
For these reasons our client closely monitors the manufacturing environment using a range of sensors, to ensure it stays within the required parameters for safe production. The challenge our client faced, was processing the large volume of data these sensors collect. Their old systems often struggled to analyse the information efficiently, which meant by the time an environmental abnormality was detected, it was too late and the silicon wafers had become damaged.
Brainpool proposed the implementation of a predictive ML system which is capable of analysing the incoming environmental data in real time, whilst forecasting any potential changes in the manufacturing environment.
In order to achieve this, Brainpool utilised a significant amount of training (historical) data from our client’s sensors, which would allow the system to form an understanding of what precursors may indicate an unexpected change on the production line. This forecasting would continually improve over time, as the the system gathered more environmental data.
By utilising the data provided Brainpool were able to create a predictive ML system which could process the incoming data in a timely manner. The system can also accurately forecast potential changes in the manufacturing environment. The implementation of this technology enabled the client to drastically reduce their overall waste, whilst simultaneously improving efficiency.