Use Case

Battery Manufacturing
AI-POWERED PROCESS CONTROL

Achieving Coating Uniformity in Battery Electrode Manufacturing

Every lithium-ion battery has a cathode and an anode, made from sheets of active materials, additives, and binders formed into a slurry. This slurry is applied to metal foils and dried into sheets. Controlling the thickness and uniformity of these sheets is crucial for battery performance. However, the complexity and numerous variables in the process lead to quality issues and higher scrap rates.

Customer

Our customer can be any company that produces electrodes for batteries, with production lines connected to any type of historian that allows data access.

Problem

Every lithium-ion battery contains a cathode and an anode, which are critical components in its structure. These electrodes are initially produced as individual sheets and later formed into their final shapes, which vary depending on the type of battery.

The manufacturing process begins with a precise mixture of active materials, conductive additives and binders, which is transformed into a slurry. The slurry is then uniformly applied to metal foils and dried to form the electrode sheets.

Tight control over the thickness and uniformity of these sheets is critical to ensuring optimal battery performance and reliability. However, the sheer number of controllable parameters combined with the high complexity of the process makes this a challenging task, resulting in increased quality issues and scrap rates.

Solution

A comprehensive target KPI for the uniformity must be defined. This KPI can combine key parameters such as moisture, thickness and grammage. To ensure that all key parameters remain within their intended ranges, limits must be set on the target KPI.

Next, the raw historical process data of the targeted electrode manufacturing line is fed into the AI engine that powers Process Booster, aivis®. The AI performs a root cause analysis to identify the key factors and characteristic behavior influencing the uniformity. Such insights already enable process engineers to further develop their comprehensive understanding of the underlying issues.

The AI also creates a process control model live-predicting the uniformity and recommending adjustments of controllable parameters as soon as it deviates from its intended range.

Outcome

A process control model running live in Process Booster, predicting the uniformity and facilitating corrective actions if necessary. In addition, a better understanding of the underlying issues enables experts to further improve the process.

A process control model running live in Process Booster, predicting the uniformity and facilitating corrective actions if necessary. In addition, a better understanding of the underlying issues enables experts to further improve the process.

Impact

Expecting significant cost savings and increased yield and OEE due to a lower scrap rate per line.

Unlock the full potential of your production line

Get in touch with us now and take the first step towards a more streamlined production process. Or do you need an immediate solution to an acute problem? See if you qualify for our Instant Solution Program!