Predict process outcomes, or invert to recommend settings.
ML-PREDICT learns the forward map from process parameters to outcomes. ML-REVERSE inverts it. Given a target, it returns the settings most likely to hit it. Both are physics-informed surrogates of the CO-SIMU library, trained on synthetic data the CO-SIMU models generate and calibrated against your own measurements.
Surrogates of the physics. Not fits to your last dataset.
ML-PREDICT and ML-REVERSE are narrow, high-accuracy machine-learning models that approximate the CO-SIMU mesoscopic simulators. They take seconds to evaluate where the underlying physics takes hours. They are trained on the physics, not on raw industrial data alone, which keeps them honest in regions where measurements are sparse.
The same architecture supports both directions. Trained one way, the model predicts outcomes from process parameters. Trained the other way, it inverts the problem and recommends settings to hit a target. Hybrid physics-plus-ML is the rule, not a black-box regression. The perimeter of validity is explicit, and the model knows when it should not be trusted.
Four capabilities, one consistent architecture.
Forward prediction (ML-PREDICT)
From process parameters (slurry composition, drying profile, calendering pressure, infiltration conditions) predicts outcomes such as porosity, conductivity, tortuosity, saturation, yield and capacity loss. Inference runs in seconds rather than hours.
Inverse recommendation (ML-REVERSE)
Given a target performance envelope, returns the process settings most likely to hit it. The inverse map is trained directly, not derived by random search over the forward model. Fast, repeatable, auditable.
Hybrid physics + ML
Trained on synthetic data generated by the CO-SIMU mesoscopic simulators, then calibrated against your real measurements. The physics keeps the model honest outside the dense data regions. Your measurements pin it down inside them.
Confidence & safe rails
Every prediction carries an explicit confidence score. A self-diagnostic module flags inputs that fall outside the trained perimeter. You see what the model knows and what it does not before acting on a recommendation.
From rheology to saturation. Concrete forward maps.
On mixing and coating, the forward model learns slurry parameters → viscosity and rheology. On drying, it maps slurry composition and furnace parameters → porosity, conductivity and tortuosity, with classification heads for defects such as cracks. On calendering, pressure and roll speed → porosity, conductivity and tortuosity. On infiltration, viscosity, density, contact angle, separator microstructure, pressure and temperature → saturation percentage.
Each of these maps can be inverted. Need a target porosity, saturation or capacity? ML-REVERSE returns the parameter window along with a confidence score, so engineers move from outcome objectives to actionable setpoints in a single step. Bayesian optimization layered on top picks the most informative experiments when you do need to extend the perimeter.
What buyers ask about ML-PREDICT & ML-REVERSE.
Move from hours of simulation to seconds of inference.
Tell us the process parameters and outcomes you want a surrogate for. We scope the CO-SIMU training runs, the calibration data we need from you, and the ML-PREDICT or ML-REVERSE deployment.