Physics-AI · Metal AM Simulation

SolidNeticsSimulate. Build. Certify.

Laser Powder Bed Fusion Physics-AI Surrogates

The cloud-native Physics-AI platform for metal additive manufacturing. Surrogate models — trained on thousands of high-fidelity simulations — carry a part from scan path through melt-pool, microstructure and residual stress to a certification-ready report, then optimize the process to print it faster. No installs, no meshing bottlenecks, no trial builds.

Physics-AI surrogates  |  scan path · melt-pool · microstructure · residual stress · certification · optimization

solidnetics.com — CAD → qualified build
01

Physics AI — learn once, predict at part scale

Full-physics AM simulation is accurate but far too slow to run over a whole part. SolidNetics trains physics-informed surrogate models on thousands of high-fidelity simulations, so part-scale residual stress, distortion and microstructure that once took days run in minutes — fast enough to optimize the process in a closed loop.

01 · Simulate

High-fidelity physics

FusionCore resolves the melt-pool thermal history and GrainPath resolves solidification microstructure — the ground truth the AI learns from.

FusionCoreGrainPath
02 · Learn

Surrogate engines

FusionMap and GrainMap run thousands of those thermal and microstructure simulations and train physics-informed surrogate models from the results.

FusionMapGrainMap
03 · Predict

Part-scale, in minutes

StressForge applies the trained surrogates to predict residual stress and distortion across the entire part — at full scale, with no meso-scale solve.

StressForge
04 · Optimize

Closed-loop tuning

Because prediction is now fast, ProcessPilot searches the process window to cut residual stress and distortion while keeping the build fast.

ProcessPilot
02

Your metal AM build, simulated end to end

SolidNetics replaces a desktop of disconnected tools with a single browser tab built for additive manufacturing. Import a CAD part, define the process strategy visually, and run the whole LPBF chain on scalable cloud infrastructure — from a first feasibility check to a full build qualification.

// 100% cloud

Run from any browser

No installation, no licence servers, no hardware. CPUs and GPUs scale on demand, and every update ships automatically.

// CAD-native

From part to build setup

Import STL, STEP, IGES or OBJ. Define the LPBF process strategy with surface-based selection and automatic normal detection.

// End-to-end

Scan path to certification

One connected pipeline carries a build from laser trajectory through to a qualification verdict — no manual handoff between stages.

03

The LPBF pipeline

Six solvers and two internal Physics-AI engines carry a part from geometry to a certification verdict — then ProcessPilot closes the loop by tuning the process to reach it faster. Each stage consumes the previous stage's contract — no manual handoff, no re-exporting between tools.

S1PathWeaver
S2FusionCore
IntFusionMap
S3GrainPath
IntGrainMap
S4StressForge
S5CertifyAM
S6ProcessPilot

// geometry · process strategy → trajectory → melt-pool → microstructure → residual stress → qualification → process optimization

PathWeaver
Ent
S1 · Scan-Path Generator

Turns a part and a process strategy into a time-stamped laser trajectory — the single contract every downstream AM solver reads.

Slicing & region decomposition Stripe / island / chessboard Multi-laser zoning Hatch & timing
FusionCore
Ent
S2 · Melt-Pool Thermal

High-fidelity meso-scale thermal simulation of LPBF — resolving melt-pool geometry, solidification gradients and phase evolution.

Melt-pool geometry Thermal gradient G Solidification rate R Phase evolution
FusionMap
Internal
Surrogate Data Engine

High-throughput simulation engine that trains the surrogate models powering StressForge and GrainPath. Not exposed as a standalone tool.

High-throughput Training-data generation Surrogate fitting
GrainPath
Ent
S3 · Microstructure

Predicts solidification microstructure, grain morphology and columnar-to-equiaxed transitions from thermal-gradient and solidification-velocity fields.

Grain morphology Columnar ↔ equiaxed Texture from G & R
GrainMap
Internal
Microstructure Surrogate Engine

Runs thousands of GrainPath microstructure simulations to train the surrogate models that bring grain prediction to part scale — the microstructure counterpart of FusionMap. Not exposed as a standalone tool.

High-throughput Microstructure training-data Surrogate fitting
StressForge
Ent
S4 · Residual Stress

Part-scale residual stress, warping and distortion in LPBF builds, using physics-informed surrogates trained on high-fidelity thermal data.

Residual stress Warping & distortion Inherent-strain method
CertifyAM
New
S5 · Qualification

Consolidates thermal, microstructure and mechanical predictions into defect-probability maps, property estimates and certification-ready quality reports.

Defect maps Property estimates Pass / fail gates Quality reports
ProcessPilot
New
S6 · Process Optimization

Closes the loop: drives the trained Physics-AI surrogates across the LPBF process window to minimize residual stress and distortion while maximizing build-rate — returning optimized, region-aware process parameters.

Multi-objective Residual stress & distortion ↓ Build-rate ↑ Region-aware parameters
04

From CAD to a qualified build

Three steps, entirely in the browser.

1
Upload & set the process

Import a CAD model and define the LPBF process strategy — orientation, laser parameters and scan strategy — through surface-based selection.

2
Generate on the cloud

Scan path and simulation domain are built on scalable cloud infrastructure — no local hardware or meshing bottlenecks.

3
Run & qualify

Solve melt-pool, microstructure and residual stress across CPUs and GPUs, then explore defect maps and qualification results online.

05

Why SolidNetics

Built to remove the trial-and-error between a CAD part and a validated, qualified build.

End-to-end AM

The only path from LPBF scan path through melt-pool, microstructure and residual stress to certification — fully connected, one workflow.

Predict before you print

See melt-pool behaviour, distortion and defect risk before committing powder and machine time — instead of qualifying by repeated builds.

Physics-AI, not guesswork

Surrogates trained by FusionMap and GrainMap on thousands of high-fidelity runs return part-scale microstructure and residual-stress predictions in minutes, not days — and ProcessPilot optimizes the process on top of them.

CAD-to-cloud automation

STL, STEP, IGES and OBJ in; visual process setup; everything runs in the cloud with no installation and no workstation.

Certification-ready

Defect maps, property estimates and pass/fail gates are consolidated into quality reports built for part qualification.

Always up to date

New solvers, machine profiles and validation checks roll out automatically — you always run the latest version.

06

Built for demanding AM industries

Where metal additive manufacturing has to be right the first time — the problem each sector faces, and how SolidNetics solves it.

Aerospace

The issue

Flight-critical parts — brackets, fuel nozzles, turbine components — must be fully traceable. Residual stress and hidden defects cause distortion and rejected builds, and qualification by repeated trial prints is slow and costly.

How SolidNetics solves it

Predicts melt-pool, microstructure, residual stress and defect probability before printing, and produces certification-ready reports that de-risk and shorten qualification.

Medical & Implants

The issue

Every patient-specific titanium implant is a unique geometry that can't be trial-printed, yet it must meet exact porosity, fatigue and dimensional targets.

How SolidNetics solves it

Simulates microstructure and residual stress for each patient geometry, guaranteeing mechanical performance and dimensional accuracy without iterative builds.

Tooling & Moulds

The issue

Conformal-cooling tools warp and crack under residual stress. A failed insert means lost powder, machine hours and lead time on an expensive build.

How SolidNetics solves it

Predicts distortion and residual stress up front so geometry can be pre-compensated — delivering right-first-time tools and fewer rebuilds.

Automotive

The issue

Lightweight performance and EV parts need fast iteration, but porosity and build failures stall the move from prototype to series production.

How SolidNetics solves it

Surrogate-accelerated simulation screens process parameters in minutes, cutting scrap and speeding qualification for production-rate AM.

Energy

The issue

Heat exchangers, turbine and nuclear components run in extreme thermal and pressure conditions where defects or residual stress threaten integrity.

How SolidNetics solves it

Generates defect-probability maps and residual-stress fields so engineers can confirm structural integrity and long-term reliability before the build.

Research & Academia

The issue

Process–structure–property studies need high-fidelity thermal and microstructure data that is slow and expensive to produce experimentally.

How SolidNetics solves it

Cloud, physics-based and surrogate solvers generate G/R, microstructure and residual-stress datasets at scale — no lab time or workstation required.

The new standard in metal AM simulation

Stop qualifying parts by trial and error. Predict melt-pool, microstructure, residual stress and defects before the build — and ship certification-ready reports from a single cloud platform.