UK company is using AI to detect lithium plating, and predict failures with up to 90% accuracy, making EV battery fires a thing of the past.
The automotive industry is undergoing a transformation, with electric vehicles (EVs) leading the charge towards a greener, more sustainable future. However, recent headlines about fires related to suspected EVs catching fire have raised concerns, casting a shadow on the impending EV landscape. This is where UK-based Eatron Technologies steps in, offering a glimmer of hope in the form of Artificial Intelligence (AI)-powered advanced battery management software to mitigate the risk of EV battery fires.
Vehicle fires have been a concern in the automotive world, regardless of the powertrain, but the spotlight has recently been on electrified vehicles. In the wake of these incidents, the industry faces the daunting challenge of rebuilding consumer trust in EVs. Dr. Umut Genc, CEO at Eatron Technologies, emphasises the need to address these concerns: “The reality is that EV battery fires are incredibly rare, but even one is one too many. As an industry, we need to ensure the number of catastrophic battery failures reaches zero, and then stays there. Our intelligent, connected, and safe automotive-grade battery management software has demonstrated that AI holds the key to achieving this.”
Battery failures are often complex, arising from various factors. Lithium plating, a common cause, occurs when metallic lithium deposits form around the anode, typically during fast charging at low temperatures. Over time, these deposits erode battery performance. Unchecked, this can lead to the growth of dendrites, needle-like structures that pierce the separator between the anode and cathode, causing a short circuit within the cell. This, in turn, initiates thermal runaway, a self-sustaining chain reaction that’s challenging to extinguish.
Detecting lithium plating without physically inspecting the battery cell (nearly impossible once it’s in a vehicle) has long been a formidable challenge. Various techniques have been developed, but they all have limitations, particularly when distinguishing lithium plating from other degradation mechanisms.
Enter Eatron Technologies, armed with Artificial Intelligence. They’ve not only improved lithium plating detection but can predict when it might occur. “Using feature extraction, we transform the battery’s raw health data into a format that highlights anomalies. Coupled with our proprietary AI pipeline that accurately tracks battery behaviour, our AI diagnostics can predict cell failures with up to 90% accuracy and zero false positives,” explains Dr. Umut Genc.
Predicting failures before they happen is a game-changer. It allows for proactive measures, potentially altering the way the battery is managed to minimize further damage, and ultimately, scheduling a convenient service visit for rectification. The critical outcome is that failures are avoided, and the spectre of recent fire-related incidents becomes a thing of the past.
In a world where EVs are heralded as the future of transportation, Eatron Technologies’ pioneering use of AI offers a glimmer of hope. By minimising the risk of battery-related incidents, they’re paving the way for a safer, more reliable future for electric mobility.