FTCO

Fab Technology Co-Optimization (FTCO™)

An intelligence solution platform that transforms your multiphysics simulation and manufacturing data into engineering intelligence at scale.
Talk to an FTCO expert

What is FTCO?

Engineering intelligence, not just engineering data

Traditional simulation workflows produce answers for the specific conditions that were simulated. FTCO enables to go further by transforming simulation and manufacturing data into engineering intelligence that captures the relationships between those results. Instead of being limited to the discrete points of a DOE, engineers gain insight into the broader engineering space and can evaluate conditions, trade-offs, and scenarios that were never explicitly simulated.

Engineering intelligence tailored to your problem

Every semiconductor organization faces different engineering challenges. FTCO provides a flexible intelligence solution platform that can be tailored to specific technologies, workflows, objectives, and data sources. By combining multiphysics simulation, manufacturing data, analytics, and machine learning, FTCO trains surrogate models that capture the relationships most relevant to your engineering decisions. The resulting intelligence can be applied to calibration, optimization, sensitivity analysis, process capability studies, and other high-value workflows.

Explore, optimize, and decide in real time

Instead of launching new simulation campaigns for every question, engineers can interact with surrogate models to evaluate scenarios, quantify sensitivities, explore trade-offs, and optimize outcomes in real time. This enables engineering expertise to scale beyond simulation specialists while maintaining a foundation in physics-based simulation.

FTCO Solutions, from your simulations to
engineering intelligence at scale

Accelerate simulation workflows and create engineering-ready surrogate models

01

Define the engineering space

Use Victory DoE to identify the process, design, and operating parameters relevant to the engineering challenge. Smart design-of-experiments methods define the simulation campaign and explore the parameter space with a manageable number of simulations.

02

Generate engineering data

Have Victory DoE automatically execute the simulation campaign and collect the resulting data. Existing measurement data can also be incorporated where available. Physics-based simulation provides the foundation for the engineering intelligence that follows.

03

Build engineering intelligence

Victory Analytics applies analytics and machine learning to the collected data, revealing relationships, sensitivities, dependencies, and trade-offs within the engineering problem. The resulting engineering intelligence is tailored to the technology, objectives, and workflow being addressed.

04

Accelerate engineering workflows

Apply engineering intelligence to traditional workflows such as calibration, analysis, sensitivity studies, process capability evaluation, optimization, and multi-response trade-off exploration.

05

Create surrogate models

Use the engineering intelligence to build machine-learned surrogate models that make simulation-derived knowledge accessible in real time. Depending on the application, surrogate models can represent structures, complete response curves, or engineering metrics, enabling rapid exploration of design and process scenarios.

Scaling Calibration Expertise

Calibration remains essential for predictive simulation. FTCO accelerates calibration
workflows, helping organizations apply expert knowledge more efficiently and address growing
engineering complexity with limited specialist resources.

Accelerating calibration workflows

The challenge of traditional calibration workflows is that this process is time-consuming, iterative, and dependent on a small number of highly specialized experts.

FTCO accelerates calibration workflows through automation, analytics, and machine learning. By helping engineers identify the most influential parameters, quantify sensitivities, and focus effort where it matters most, FTCO can significantly reduce the time required to achieve calibrated simulation models while scaling expertise across engineering teams.

From calibrated simulation to engineering intelligence

Once simulations have been calibrated against measured data, FTCO can use the resulting simulation and manufacturing data to generate engineering intelligence tailored to the application. Depending on the engineering objective, this intelligence can support analysis, optimization, sensitivity studies, process capability evaluation, or the creation of machine-learned surrogate models.

What you need to bring

The required inputs depend on the application, but typically include measured manufacturing data, the associated process conditions, and the simulation workflows to be calibrated. The amount of data required depends on the engineering objective, the number of variables involved, and the complexity of the underlying relationships. FTCO workflows can then be tailored to the specific problem being addressed.

From Simulated Points to Real-Time
Engineering Intelligence

Traditional simulations provide answers only for the conditions that were run. FTCO surrogate
models learn the relationships between those results, enabling engineers to predict outcomes,
explore trade-offs, and evaluate scenarios that were never explicitly simulated. 

Three different types of surrogates are available – structural, curve, parametric – which support
different engineering tasks, from interactive structure exploration to process and IV optimization
and capability analysis.”

Understand Process Sensitivities

Parametric Surrogate

Identify which process, design, or operating parameters have the greatest impact on the metrics you care about. Parametric surrogates enable rapid sensitivity studies without launching new simulation campaigns.

The surrogate ranks parameter influence and highlights the most sensitive variables.

Evaluate Process Capability

Parametric Surrogate

Assess the impact of manufacturing variation on device and process performance. Parametric surrogates support capability analysis and statistical studies across large parameter populations.

The surrogate predicts the resulting spread in device and process metrics.

Optimize Multiple Objectives

Parametric Surrogate

Explore trade-offs between competing engineering targets and identify parameter combinations that satisfy multiple constraints simultaneously. Parametric surrogates enable rapid multi-response optimization studies.

The surrogate identifies process settings that best satisfy both objectives.

Explore Structure Changes

Structure Surrogate

Interactively visualize how process variations affect geometry and physical structures. Engineers can explore structural changes in real time rather than rerunning full simulation flows.

The surrogate instantly predicts the resulting structure geometry.

Predict Complete Device Behavior

Curve Surrogate

Evaluate entire response curves across operating conditions. Curve surrogates predict full device or process responses instead of individual metrics.

The surrogate predicts the complete IV response without running a new simulation.

The tools behind FTCO

Add intelligence to multiphysics

Victory Analytics

Provides the machine learning capabilities.

View Victory Analytics

Victory DoE

Designs the experiments and keeps every simulation project's results in one place, ready for Victory Analytics.

View Victory DoE

Multiphysics Tools

Build the multiphyiscs flow that suits your needs

View Multiphysics Tools

Built with Micron Technology for memory devices

FTCO took shape through a collaboration with Micron Technology, Inc., around the process questions memory development raises.

Memory | Digital twin

April 2024

Micron Technology

Micron’s engineers use an FTCO digital twin to speed design and pathfinding on memory products. The twin learns from Micron’s production data and from physics-based simulation of etching, deposition and mechanical stress. Engineers outside the TCAD team get process, design and yield optimization in their own hands.

“Silvaco’s AI and digital twin solution is enabling us to accelerate our groundbreaking advancements in memory and storage.”

Dr. Gurtej Sandhu, Principal Fellow of Technology Pathfinding, Micron Technology, Inc.

Read the announcement

FTCO resources

Conference talks and webinars on fab technology co-optimization, plus a SEMI interview on where it came from.

See all webinars
Browse the SURGE 2025 archive

Webinar

Manufacturing-Aware PIC Simulation Webinar FTCO & Digital Twins

Modern semiconductor development requires rapid exploration of large design spaces while maintaining the predictive accuracy of physics-based simulation.

Webinar

TCAD-Aware SPICE Model Extraction with Utmost IV: From Manufacturing to Surrogate Circuit Modeling

Accurate compact models are essential for translating device behavior into trustworthy circuit simulation,

Webinar

Accelerating Manufacturing-Aware Simulations for Photonic Integrated Circuits with FTCO™ and Digital Twins

Photonic integrated circuit (PIC) designers face a persistent challenge: devices that perform well in simulation often underperform after fabrication.

Conference talk

SURGE 2025

How to Utilize Victory Analytics and Machine Learning to Calibrate TCAD Data

Dr. Stefania Carapezzi, Field Applications Engineer at Silvaco, on calibrating TCAD data with machine learning in Victory Analytics.

Conference talk

SURGE 2025

AI Takes EDA to the Next Level

Dr. Walden (Wally) Rhines, now Silvaco's CEO, on where AI is taking electronic design automation.

Webinar · SEMI

Developing Silicon Carbide DMOSFETs: A Digital Twin Design Reference Flow

A SEMI-hosted webinar on silicon carbide DMOSFET development.

Webinar

Applying Artificial Intelligence in Fab Technology Co-Optimization (FTCO™)

Silvaco's webinar on putting AI to work in fab technology co-optimization.

Interview · SEMI

Applying AI in fab technology co-optimization

SEMI talks to former Silvaco CEO Dr. Babak Taheri about FTCO.

Presentation · PDF

SURGE 2025

FTCO overview

The whole FTCO workflow in one document.

Talk to an FTCO expert

Tell us which process you want a digital twin of and what data you already have on it.
Measurements from split conditions and the parameters you’re trading off are a good place to start.
An FTCO expert will get back to you on what it takes for your process.

Contact an FTCO expert

Questions about FTCO

What is FTCO?

FTCO stands for Fab Technology Co-Optimization. It is an intelligence solution platform that combines multiphysics simulation, automation, analytics, and machine learning to create engineering intelligence. Depending on the application, that intelligence can support calibration, optimization, sensitivity analysis, process capability studies, and surrogate model development.

A surrogate model is a machine-learned representation of engineering behavior built from simulation and, where available, manufacturing data. Unlike a collection of simulation results, a surrogate model learns the relationships between those results, enabling engineers to predict outcomes, explore trade-offs, and evaluate conditions that were not explicitly simulated in the original DOE campaign. It can represent structures, response curves, or engineering metrics depending on the application.

By employing an FTCO surrogate workflow. Victory DoE uses a user-defined multiphysics simulation flow to generate simulation data across a defined engineering space. Victory Analytics then applies machine learning to learn the relationships between those simulation results and create a surrogate model. Unlike a DOE result table, the surrogate model can evaluate additional conditions and parameter combinations beyond the original simulation set. Accuracy depends on the quality of the simulations, coverage of the engineering space, and, where applicable, calibration against measured data.

Calibration occurs at the simulation level. Engineers compare multiphysics simulation results with measured manufacturing data and refine the simulation until it accurately represents process behavior. An FTCO calibration workflow can be used to significantly accelerate the calibration step through automation, analytics, and machine learning. The calibrated simulations then become the foundation for engineering intelligence and surrogate models.