Overview
What this module delivers
CoreMagna AI Loss helps engineering teams estimate core loss under actual operating conditions, including waveform shape, duty behavior, and temperature variation, instead of relying only on limited datasheet points or fixed empirical exponents.
Capability focus
Inputs
Excitation waveforms, switching profiles, temperature sweeps, duty cycles, and imported mission-profile data.
Outputs
Waveform-conditioned loss estimates, scenario comparisons, and exportable loss envelopes for thermal and derating workflows.
Guardrails
Traceable assumptions, calibration hooks, and batch-aware material alignment tied to CenturaCores validation pathways.
Deep dive
Functionality
CoreMagna AI Loss uses hybrid physics-informed modeling that combines Steinmetz-class baselines with waveform-aware learned corrections, improving prediction quality for non-ideal excitation where simple exponent fitting often breaks down.
Temperature-aware and process-aware modeling captures how annealing state, operating point movement, and hysteresis versus eddy-current balance can shift loss behavior, with calibration hooks for lot-level adjustment when needed.
The module supports imported waveform data from measured captures, SPICE-derived volt-second profiles, and mission-profile scenarios so loss prediction follows real operating trajectories instead of idealized test conditions.
Evaluation dimensions
- Waveform fidelity and excitation class
- Temperature and operating-point coverage
- Calibration and batch alignment
- Thermal handoff readiness
- Traceability of assumptions
Example workflow
A charger design team imports a non-sinusoidal excitation profile from a PFC or LLC stage, applies temperature sweep assumptions, compares waveform-conditioned loss across operating points, then exports worst-case envelopes to support hotspot review and thermal derating decisions.
Use the links below for the CoreMagna AI hub, adjacent modules, and CenturaCores tools and product context that fit your program.
- CoreMagna AI hub
- CoreMagna AI Simulation module for field and thermal correlation
- CoreMagna AI Material module for batch and grade alignment
- CoreMagna AI Manufacturing module for process-aware calibration planning
- CoreMagna AI Cost module for derating and scenario tradeoff analysis
- EV charger core selection technical guidance
Advantages
Better screening than one-size-fits-all empirical exponents
Faster scenario sweeps before detailed FEA or hardware iteration
Clearer linkage between loss prediction and thermal design reviews
Traceable assumptions for compliance, validation, and customer discussions
Target users
- Power magnetics engineers evaluating loss budgets
- Thermal teams assessing hotspot and derating risk
- Quality and validation teams investigating field-return behavior
Industry use cases
- High-frequency PFC and LLC power stages in EV charging
- Solar inverter magnetics across wide MPPT operating ranges
- Industrial drives and switched power stages with hard-edged excitation
Ready to explore CoreMagna AI?
Join the beta or speak with a nanocrystalline specialist about your program requirements and validation path.
Frequently asked questions
What waveforms can CoreMagna AI Loss evaluate?
It evaluates sinusoidal and non-sinusoidal waveforms, including measured captures, switching-derived profiles, and mission-profile datasets used in practical converter operation.
How does the Loss module differ from classical Steinmetz-only estimation?
Steinmetz-class baselines are retained, then corrected using waveform-conditioned and operating-point-aware modeling so predictions remain useful for realistic excitation patterns.
How are temperature effects represented?
Temperature-aware modeling tracks loss behavior across sweep ranges and supports calibration hooks to reflect process and material variation in validation workflows.
Can results feed downstream thermal simulation or derating studies?
Yes. Exportable loss envelopes and scenario comparisons are designed for thermal handoff, hotspot review, and derating decisions.
How should teams align Loss outputs with Material and Manufacturing assumptions?
Use grade and batch context from the Material module and process calibration themes from Manufacturing so loss assumptions reflect the same material and line reality your program relies on for validation.