Vijayalayan R from MathWorks India discusses the significance of an efficient Battery Management System (BMS) for electric vehicles and how emerging technologies such as Artificial Intelligence can be leveraged in the design and development of sustainable BMS.
Significance of efficient BMS in the EV ecosystem
We are seeing several tailwinds that are helping the Electric Vehicle (EV) industry grow in India. We are also seeing some teething troubles. There have been concerns over the safety of electric vehicles, especially two-wheelers, in our country. Vehicles catching fire and a few manufacturers recalling some batches of their EVs have been reported. Battery manufacturers are looking at various ways to enhance the safety of the cell.
Some of these include technology to turn off parts during an adverse event and finding a non-inflammable electrolyte for the battery. This is where a properly designed battery management system (BMS) plays a vital role.
Battery Swapping Policy
As we are investing efforts to boost EV charging infrastructure in the country, battery swapping is an attractive alternative that involves exchanging discharged batteries for charged ones and provides flexibility to charge them separately. NITI Aayog under Govt of India has been working with a wide spectrum of stakeholders — battery swapping operators, battery manufacturers, vehicle OEMs, financial institutions, CSOs, think tanks, and other experts — to draft a policy that will introduce a battery swapping policy and interoperability standards to improve efficiency in the EV ecosystem.
A few key aspects mentioned in the draft policy are:
- Batteries must be BMS-enabled – to enable monitoring, data analysis and safety
- The battery’s BMS must be self-certified and open for testing to check its compatibility with various systems, and capability to meet safety requirements
- Batteries must be IoT-enabled to allow for safety and security monitoring
Having understood the significance of an efficient BMS, let us look at some of the technologies that are driving advancements in the technology.
Battery Modeling and Digital Twins
Battery models have become an indispensable tool for the design of battery-powered systems. Their uses include –
- battery characterization
- state-of-charge (SOC) and state-of-health (SOH) estimation
- algorithm development
- system-level optimization
- real-time simulation for battery management system design.
Battery models based on equivalent circuits are preferred for system-level development and control applications due to their relative simplicity.
A digital twin of a battery, which is an up-to-date representation of the actual battery, provides access to verified simulation models across cloud platforms, hence supporting collaboration and rapid innovation across multiple engineering teams. Researchers, engineers, and other stakeholders use digital twin models to accelerate development time and reduce batteries’ development costs. These battery models can also help in developing a BMS that accounts for degradation.
Artificial Intelligence, IoT and Data Science
Battery state of charge (SOC) is a critical signal for a BMS. Yet, it cannot be directly measured. Virtual sensor modeling can help in situations where the signal of interest cannot be measured or when a physical sensor adds too much cost and complexity to the design. Deep learning and machine learning techniques can be used as alternatives or supplements to Kalman filters and other well-known virtual sensing techniques. These AI-based virtual sensor models must integrate with other parts of the embedded system.
With the need for remote monitoring of the performance of a battery, as suggested by the draft of NITI Ayog’s Battery Swapping policy, we will likely see IoT leveraged more broadly to support the initiative.
Automate Model Verification and Code to Safety Standards
With the increase in software content in today’s electric vehicles, companies need to focus on migrating their existing embedded software development process to be compliant with objectives of functional safety standards such as ISO 26262. Model-Based design with production code generation has been extensively utilized throughout the automotive software engineering community because of its ability to address complexity, productivity, and quality challenges. It can also help in automating model and code verification, thereby enabling engineers to streamline verification and deployment efforts when adhering to the ISO 26262 functional safety standard.
Technologies that enable data analytics, artificial intelligence (AI), modeling and simulation, embedded software development, and verification have become relevant for building a sustainable and stronger EV ecosystem. The regulatory framework currently being developed by the government will help accelerate the adoption of these technologies and ensure compliance of various OEMs and other value chain players. All these will make consumers the ultimate beneficiary. When they start purchasing and using more EVs, the ecosystem will develop further in aspects of technology, operations, and regulation.
About the Author
R Vijayalayan manages the automotive industry and control design vertical application engineering teams at MathWorks India. He specializes in the field of Industrial Automation, Robotics and Model-Based Design. He can be reached at [email protected]
Subscribe today for free and stay on top of latest developments in EV domain.