Battery Energy Storage Systems

Battery energy storage systems (ESS) ranging from grid-scale BESS to commercial and industrial installations, deliver huge value, but they are also complex electrochemical assets that degrade in different ways over time. Small shifts in operation, environment, and usage patterns can quietly accelerate aging, reduce capacity, increase resistance, and raise safety risk.

The-Precursor Diagnostics focuses on making these degradation pathways measurable, explainable, and actionable through diagnostics and prognostics.

Diagnostics turns raw BESS data into a clear, current picture of health and risk. ForeSee1 is designed to diagnose degradation modes early and monitor their evolution which enable operators move from conventional alarms and symptoms to mechanisms and root causes.

ForeSee1 quantifies degradation modes and indicators such as loss of lithium inventory (LLI), loss of active material (LAM), resistance change, capacity fade, and State of Health (SoH) and connects them to underlying mechanisms across the life of the energy storage cell. It also quantifies risk and safety metrics so teams can flag emerging issues earlier in the operational lifecycle.

Prognostics extends that understanding forward in time. ForeSee1 forecasts Remaining Useful Life (RUL) and health trajectories to support planning, maintenance strategy, and lifecycle cost control, especially when assets continue operating under changing conditions.

To do this, ForeSee1 uses a hybrid approach that combines signal processing, physics-based modeling, statistical computations, and machine learning to forecasts remaining useful life. Forecasts are grounded in degradation science. ForeSee1 enables data-driven learning at scale.

ForeSee1 is a scalable, modular digital twin software platform for building and running diagnostics and prognostics pipelines for energy storage systems. It allows you to declaratively model a pipeline, validate it, compute results, and collect outputs. This enables you to standardize workflows across sites, fleets, chemistries, and duty cycles.

Because the architecture is asset-agnostic, the same framework can be adapted across ESS contexts while keeping the pipeline building blocks consistent and extensible.