Background Articles and Features

Optimize the Electric Vehicle’s Battery Performance with Digital Twin Technology

  • Digital Twins are entering mainstream use. 75 percent of organizations implementing IoT already use Digital Twins or plan to within a year. By 2022, over two-thirds of companies that have implemented IoT will have deployed at least one digital twin in production: Gartner Survey 2019
  • Application and business intelligence leaders can use digital twins to decrease complexity in their IoT ecosystems: Gartner

The electric transportation space has begun to witness a clean energy revolution. Enormous developments in the recent past suggest that the industry will continue to generate significant revenues in economic activity. With the technological disruptions, policies in place to develop the charging infrastructure, and the reduced cost of lithium-ion batteries, electric vehicles are becoming a lot more affordable for the end-users. EVs are expected to increase from 2% of the global share in 2016 to 22% in 2030.

It is important to note that the battery today amounts to a significant 40% of the total cost of the electric vehicle. Hence, OEMs and battery pack makers are faced with the challenge to optimize battery usage, extend its life, improve performance and efficiency, at a low cost. A faster EV adoption rate, only emphasizes the urgent need for a solution.

To enable a seamless transition towards clean energy, it is crucial to derive value and specific business outcomes from the battery. Interestingly, the most recent breakthrough in battery technology - the Digital Twin, makes it possible to acquire insights and optimize deployed assets for maximum efficiency.

What is a digital twin?

A digital twin is a virtual simulation or a model of a physical product or asset. Building a virtual “twin” that mimics the physical product enables the inflow of data for monitoring and analysis. A digital twin can help visualize the performance of a deployed asset remotely, identify opportunities to improve the asset’s on-field performance, eliminate downtime, predict errors and prevent breakdowns.

Digital Twin was originally presented in 2002 by the University of Michigan as a concept for the formation of a Product Lifecycle Management (PLM) center. While the core concept stays the same, the terminology for the Digital Twin has evolved over time. The primary thought was that a physical system’s digital information would be an entity on its own, as a “twin”. This would be linked with the physical system throughout its lifecycle.

Digital Twin & the technological wave

Digital twin technology saw a resurgence in the past two years, which witnessed a boom in digital technological advancements such as - IoT, Analytics, Big Data, Machine Learning. Digital Twin is optimizing asset deployments for maximum efficiency, which helps extend the life of deployed assets, hence reducing overhead expenditures.

With digital twin technology, EV manufacturers get access to advanced algorithms for predictive and real-time feedback and offline analysis to increase battery efficiency. Data scientists, analysts, and business intelligence leaders can leverage the power of digital twin’s advanced analytics platforms and technologies to develop iterative models, generate insights and recommendations that guide decision making.

How can you build better batteries with Digital Twin technology?

Integrating the digital twin with IoT, Big Data and Machine Learning, enables real-time access, control, and analytics that is making batteries smarter, and increasing profitability. It also lets EV manufacturers and operators test and optimize new concepts without any hindrance to production.

A digital twin derives essential insight across all stages of the product life cycle for better prediction & performance of lithium-ion battery, with the use of:

  • Predictive analytics
  • Real-time visualization of battery health status
  • Over-the-air updates

How can digital twin technology be optimized for batteries?

Improved Battery Life

With the digital twin, EV makers and operators can solve serious battery life challenges. The technology uses data to provide access to instant visualization and battery analytics dashboards. It displays the current status of the deployed battery, determines the residual life and health of the battery, real-time insights highlighting the parameters which are influencing the life and health of the battery, such as - usage patterns, location, and the environment.

The battery data is transferred to the cloud for analysis by advanced Machine Learning algorithms. ML monitors the battery data, provides a projected trajectory and formulates actionable insights. With the power of data analytics, the user is able to diagnose, predict and detect anomalies like possible errors/issues/breakdowns and accurately troubleshoot them.

Residual Life expectancy

Digital Twin uses ML and AI algorithms to offers health insights that accurately predict the residual life expectancy of the battery. It thoroughly analyses the data to help fleet operators to estimate the right time to replace the battery, offering preventive maintenance, reducing any downtime. It also helps EV makers and operators to take the right measures to prevent premature aging, make configuration recommendations that extend battery life and improve the health status remotely.

Predictive Alerts

The capabilities of the digital twin technology are unparalleled battery mirroring and monitoring, and early prediction, optimizing uptime and reliability. The intelligence layer on the data produces useful predictive insights such as when to schedule maintenance and provides real-time alerts for breakdowns, errors or mishaps. It lets you schedule repairs remotely and only when necessary, eliminating the need for manual inspection and intervention. The system alerts are set as per the hierarchy, that different alert types, depending on the urgency and the magnitude of the issue. The automated root cause analysis accurately predicts product performance deviations and failures.

The digital twin is revolutionizing the battery management approach from reactive to predictive. The AI-powered battery intelligence data can help build smarter batteries. The technology is empowering OEMs and battery pack makers to maximize ROI. The digital twin models are highly scalable and can be used for optimizing multiple applications, across industries.

Radhika Oguri
Content Marketing Manager
ION Energy

The ees International Magazine is specialized on the future-oriented market of electrical energy storage systems, not only from a technological-, but also a financial and application-oriented point-of-view. In cooperation with ees Global, the ees International Magazine informs the energy industry about current progress and the latest market innovations.
Contact: Xenia Zoller - zoller(at)