Degradation prediction in Li-ion batteries is a challenging and highly nonlinear problem. Traditional physics-based approaches and tools need several designs, electrochemical, degradation parameters, and long computation times, which make it a tedious and expensive approach.
Degradation prediction in Li-ion batteries is a challenging and highly nonlinear problem. Traditional physics-based approaches and tools need several designs, electrochemical, degradation parameters, and long computation times, which make it a tedious and expensive approach.
To solve the challenge quickly and accurately, oorja has developed a Hybrid approach (Physics + ML) to predict cell and pack level degradation at various C rates, operating temperatures, and real-world drive cycles.