Flash Data Center 4.0

Flash Data Center, the proprietary remote-control software of Flash Battery was among the 41 finalists to the international Bauma Innovation Award 2022 for the best industrial projects in the area of research and innovation and will be presented at the Bauma 2022 show.

Marco Righi, CEO and founder of Flash Battery, explained: “Flash Data Center is a remote control software designed to monitor, on a daily basis, how each lithium battery we’ve ever sold is being used, regardless of where it is in the world. Its most important feature is the fact that it automatically controls the data in real time.” He added that the software controls and analyses the battery operation data received 24/7 and sends results to both the customer and the Flash Battery technical assistance department.

Flash Data Center 4.0 is the remote control by Flash Battery with enhanced capabilities driven by Machine Learning features.

Flash Data Center 4.0 release is also integrated into a virtual environment with Containerized Architecture, harnessing the power of latest-generation artificial intelligence and machine learning technologies to ensure the interconnection of the over 15 000 Flash Battery systems currently operating in 54 countries across the world.

The system learns from the analysed data and improves battery performance. And customers have the possibility to perform advanced analyses of the big data coming from their battery systems in real time. In addition, the new graphic interface is designed to offer a simpler and even more intuitive and interactive navigation experience.

“Flash Data Center analyses every parameter having to do with the battery’s operation, the most important of which is the battery’s State of Health (SOH), to get an accurate picture of the condition of every single battery out there in the market,” said Righi. “Other parameters taken into account include voltage, current, temperature, and analysis of charge/discharge times, standing watch over the peaks and lows reached during these activities.”

Righi added that this solution offers some advantages, considering that a lithium battery can be used in a wide variety of contexts and in many ways, which all affect its longevity. Knowing ahead of time where and how to act to extend its life cycle or improve its performance is a great advantage.

“Ever since 2012, we have produced batteries for many very different contexts and which have been subject to an ample mix of stresses,” he said. “Take, for example, the automated logistics sector, where AGVs and LGVs operate non-stop 24 hours a day in industrial plants with a temperature range of -30 to +45°C. Thanks to predictive analysis, it is possible to know how users are using the batteries and how long these will last and behave in the future.”

Flash Battery manufactures lithium iron phosphate batteries for off-highway and industrial vehicles.

Other advantages of predictive analysis include ensuring the application stays reliable over time, and helping sizing the vehicle more accurately when the remote control function is implemented already at the prototype stage. Data from the prototype helps understand if the battery should deliver more or less energy or build in specific performance-enhancing characteristics.

“Let’s also consider the fact that our customers are usually not the end-users of the electrified vehicles. Our batteries are installed on machines and vehicles that our customers sell all over the world. So it becomes clear that having real time data on their operation is the fast-track way to assess if the end-user is using the application correctly, For example, if it is exposing the vehicle to repeated full discharges or out-of-range temperatures.”

One last advantage with Flash Data Center is that its machine learning-driven automatic data control, allows for advanced planning of extraordinary maintenance work. This avoids unnecessary and expensive machine downtime and lets customers manage the end-of-life of the systems independently.

Righi explained that Machine Learning is a subset of artificial intelligence that creates systems with the ability to learn and improve performance through the data analysed. In this case, the concept starts from the complex nature of the battery.

“We are working with devices that have an especially complex chemistry, so Machine Learning enables us to extract from the battery a clear and accurate description of how it is behaving. Our added value lies in the fact that we have collected a huge amount of data on the operation of our batteries. The first Flash Data Center was already in place in 2013 and today we work with an astounding 180 million logs or nearly 500 000 logs a day.”

With the large amount of data at hand, the battery behaviour information extracted is incredibly precise. Flash Battery can practically recreate a “digital twin” for each battery and use it for simulations, especially at the design stage, and for formulating and testing behaviour hypotheses for next-generation batteries still in the making.

“Flash Data Center 4.0 can output a very accurate SOH analysis that helps us in our research into increasingly higher-performance and smarter new-generation batteries with ad hoc features for the needs and use of every kind of industrial application,” added Righi. 

The amount of data Flash Battery is collecting is increasing at a faster and faster rate compared to the past; today, the company analyses up to 4 000 sensors per battery, and the trend is growing. “We are therefore well on our way to building a very sound infrastructure that can continuously process huge amounts of data, interpret trends, variations and anomalies, and reproduce realistic usage scenarios we can use to develop smarter and smarter lithium batteries,” said Righi.