The surge in renewable energy and e-mobility is redefining our world, pushing industries to a pivotal moment where efficient energy storage systems are essential. The success of electrification, from electric vehicles to large-scale battery storage, relies on the capabilities of advanced batteries. Despite improvements in battery chemistry, managing safety and efficiency at both the cell and pack levels remains a challenge. Sophisticated Battery Management Systems (BMS) are crucial in addressing these issues by monitoring key metrics—State of Health (SOH), State of Charge (SOC), and Remaining Useful Life (RUL).

Electra’s EVE-Ai Fleet Analytics platform leverages these metrics to optimize performance, enhance operational visibility, and extend the life of electric assets. Our approach combines physical modeling with data-driven insights, enabling precise battery management that meets the rigorous demands of modern electric and hybrid vehicles. This ensures safety and efficiency and maximizes asset value and supports sustainability efforts, securing the reliability of our electric-powered future.

Managing electric assets

Industry Challenges 

As the push towards electrification grows, operators face significant challenges related to residual value, sustainability, and the high costs of electric vehicle investments. Half of the operators are concerned about the declining residual value of their electric fleets, while many plan to go fully electric by 2030. High battery costs, representing a third of total expenses, and maintenance issues are top concerns, with 55% of operators worried about faults and unplanned downtime. The lack of asset visibility can lead to a 20% increase in operational costs, highlighting the urgent need for better management solutions.

Key Metrics

Efficient battery management is essential in the rapidly evolving landscape of electric mobility and energy storage. Understanding key metrics helps enhance performance, extend battery life, and minimize risks. Here are the critical metrics:

• State of:
  • Charge (SoC): Calculates the battery’s current capacity as a proportion of its maximum capacity
  • Health (SOH): Measures the battery’s condition relative to its original state, indicating capacity loss and overall degradation.
• Remaining Useful Life (RUL): Predicts how much operational life remains, guiding maintenance schedules and cost planning.
• Risk Analysis: Identifies potential battery failures, allowing proactive measures to enhance safety and reliability.

How to measure key metrics  – Electra Approach: Physics Informed 

While many methods exist to calculate key battery indicators like SOH, SOC, and RUL, Electra’s approach stands out with its Physics-Informed Model. By blending physics-based principles, such as changes in cell open circuit voltage and capacity retention, with data-driven insights from machine learning, Electra’s model delivers highly accurate monitoring and predictions of battery performance. This hybrid approach enhances monitoring, optimizes battery usage, extends lifespan, and ensures safety across electric assets.

Our Solution EVE-Ai Fleet Analytics

Advanced technology is essential to track key metrics like SOH and RUL, and that’s where Electra’s EVE-Ai Fleet Analytics comes in. This can also be useful to fleet asset managers transitioning to battery power for the first time, as they need tools that provide confidence in their investment, such as data on improved asset ROI driven by longer system life and reduced maintenance costs. Our platform combines state-of-the-art software with real-time data from fleet sensors, using machine learning and physics-informed models to provide precise insights into battery performance. This technology monitors battery health and predicts maintenance needs, enabling proactive management of electric assets. By delivering early warnings of potential failures, EVE-Ai helps fleet operators enhance safety, reduce unplanned downtime, extend battery life, and optimize operational efficiency. This comprehensive approach empowers businesses to make data-driven decisions that maximize asset reliability, reduce costs, and support sustainable fleet management.

Focus 1 – Battery State of Health

SoH – State of Health (SOH) is a key metric that assesses how much capacity a battery system has lost since it was new, providing valuable insight into its general health. SOH changes slowly over time, with most battery assets experiencing less than a 1% decline per year over a lifespan of 20+ years. It compares the battery’s current capacity to its original capacity at purchase, offering useful information about its life expectancy and potential replacement dates. Batteries with low SOH store less charge at a given voltage, reducing their availability and overall efficiency.

Abstraction of capacity loss as a result of resistance growth and loss of active material

Electra’s EVE-Ai Fleet Analytics product tackles SoC and SoH visibility in three key areas:

1. The current state of health across a fleet of electric assets
2. Historical SOH analysis and identifying key factors contributing to SOH loss 
3. Future SOH forecasting based on historical usage patterns and similar systems.

Assessing the current state of health across a set of assets can provide key information to make decisions on resource utilization and scheduling of preventative maintenance. The historical trends connect observed SOH loss to usage factors. Adding visibility here can give operators insights into changing their usage patterns to prolong system life. 

Forecasting health through end-of-life based on usage trends can support users and operators to understand the long-term consequences of their operating patterns. This helps encourage better battery usage before the system reaches the end of its useful life or performance problems impact daily decisions.

With the added visibility and insights, EVE-Ai Fleet Analytics can ensure fleet operators have the data they need to maximize their fleet of battery assets now and in the future.

Monitoring both the State of Health (SOH) and State of Charge (SOC) is essential for effective electric asset management. It enables accurate estimation of remaining useful life, supports risk analysis, facilitates fault detection, and helps optimize preventive maintenance scheduling.

Here the main advantages:

1. Asset Visibility and Monitoring: Comprehensive monitoring of both SOH and SOC gives operators full visibility into their fleet, enabling better decision-making and overall asset management.
2. Predictive Health Forecasting: By analyzing historical SOH trends, operators can forecast battery end-of-life and understand how usage impacts long-term performance.
3. Optimizing Maintenance Scheduling: Regular SOH assessments provide essential data for then estimating faults and implementing preventative maintenance, minimizing downtime and preventing unexpected failures.
4. Maximizing Battery Lifespan: Regularly tracking SOH helps identify early signs of battery wear, allowing managers to implement maintenance strategies that extend the asset’s operational life.
5. Ensuring Safe Operation: Monitoring SOH ensures electric assets remain in good condition, reducing the likelihood of unexpected failures or safety hazards.

Focus 2 – Remaining Useful Life

The Remaining Useful Life (RUL) of batteries is critical for various applications such as EV fleets, Battery Energy Storage Systems (BESS), electric robots, and drones. Unlike lab testing, real-world usage conditions—such as operating temperatures, usage patterns, and charging behaviors—affect battery longevity unpredictably. 

EVE-Ai Fleet Analytics addresses this challenge by leveraging machine learning and physics-based models to adaptively forecast RUL based on usage patterns and SOH trends for each fleet asset. This data point can inform maintenance strategies or optimize asset utilization to extend the fleet’s lifetime. 

The RUL forecast identifies underlying factors to battery aging – both caused by user-imposed operating conditions and those attributed to typical calendar aging of the battery. The different aging modes of a battery impact end-users in notably different ways and accumulate at different rates in different operating conditions. Knowing what has changed and how it impacts end users is critical to managing a fleet of battery systems.

Battery charging and discharging is a highly reversible process for lithium-ion systems, but not perfectly reversible. Identifying the root causes of the loss in performance is critical to understanding the impact on future use. Hundreds of factors influence this process, but most can be bucketed into two main groups: 

• a loss of active material for charging and discharging the battery, or
• an increase in resistivity within the battery which increases losses during charging or discharging

These root causes are normal and unavoidable, but they can be accelerated by different usage patterns, with key differences in short-term and long-term impacts on the end user. 

Under a variety of conditions, particularly in the early stages of usage, these factors might not significantly impact the user experience, yet they can be identified through data analysis to glean valuable insights for optimizing future usage. An additional consideration is the non-linear nature of battery aging, which tends to accelerate as the system approaches the end of its life. We have incorporated this non-linear progression into the analytical models of EVE-Ai Analytics. This enhancement enables our product to accurately forecast the Remaining Useful Life (RUL) at an early stage and steadily increase the reliability and confidence in this metric over time.

Focus 3 – Risk Analysis and Fault Detection 

Risk analysis is a key tool in battery fleet operations and asset management. It builds and maintains confidence in the high-cost battery assets’ ability to perform adequately throughout their useful life without safety concerns. In EVE-Ai Fleet Analytics, Electra aims to provide the data and tools to quell those fears, build customer confidence, and catch potential issues early when maintenance is more manageable.

As mentioned with the SOH & RUL analyses, the core of EVE-Ai Analytics is a thorough understanding of how a battery system has changed over time as a result of its operating conditions. That same core powers our risk analysis and fault detection capabilities. EVE-Ai Analytics is focused on delivering enhanced visibility into risks associated with battery systems and their usage. This allows operators to manage potential issues and optimize system performance more confidently and proactively.

Depending on how a battery has aged, different operating conditions may pose a greater probability of a user-facing performance issue or, in extreme cases, may pose a safety risk. This context works in multiple ways, allowing EVE-Ai Analytics’ Risk Analysis to assess a higher risk for systems with more safety-critical battery degradation modes, and a higher risk to systems whose operating conditions are more likely to exhibit performance or safety issues. 

This risk analysis can enable fleet asset managers to more actively distribute demand to the various systems or identify candidates for preventative maintenance. These insights may also decrease over time to accommodate changes in user behavior that reduce risk—minimizing fast charging, reducing time held at high voltage during storage or charging, or reducing power spikes during consumption all help improve system lifetime and safety. 

Sometimes the underlying degradation in the battery changes at such a rate or surpasses a threshold, indicating a possible system fault. Detecting these faults early helps mitigate safety risks for operators and can unlock proactive measures for battery system servicing or replacement.

Collectively, EVE-Ai Analytics’ Risk Analysis and Fault Detection capabilities help battery fleet operators gain better visibility into their systems’ safety. This helps nurture confidence in battery systems while also providing early warnings for systems that exhibit abnormal behavior.

Use Cases

Our Eve-Ai Fleet Analytics can be utilized for managing fleets of electric assets, including cars, batteries, robots, trucks, and buses. The platform provides comprehensive insights and advanced analytics to optimize the performance, efficiency, and lifecycle management of all-electric assets in your fleet.

Impact of EVE-Ai Fleet Analytics Solution

To conclude, monitoring SOC, SOH, SOC, and RUL through EVE-Ai Fleet Analytics is essential for optimizing the performance and longevity of electric assets, including EVs, BESS, and other battery-powered equipment. Accurate insights into these metrics provide several key benefits:

• Enhancing Operational Visibility and Safety: Real-time data analytics offer immediate insights into battery conditions, enabling safe operations and early detection of potential issues.
• Preventing Failures and Downtime: Predictive maintenance based on these metrics helps prevent unexpected failures, reducing operational disruptions and costly downtimes.
• Maximizing Asset Value and ROI: Accurate assessments of SOH, RUL, and Risk Analysis enable better financial planning, enhance the residual value of electric assets and equipment, and support extended warranties, increasing ROI and asset value. 
• Optimizing Operations: Detailed performance analysis of battery systems allows for tailored operational adjustments, improving overall efficiency and extending battery life.
• Sustainability Benefits: Effective battery monitoring and management reduce the need for early replacements, minimizing waste and environmental impact while promoting sustainable practices.
• Scalability: All analyses are integrated into Electra’s platform, simplifying scalability and leveraging advanced cell and system modeling capabilities to identify key cell aging factors across various operating conditions and applications.

Interested in discovering how this solution can add value to your operations?
Reach out to us today! And stay tuned, more blog posts will come!