[email protected]

Transforming Engineering with powerful AI and Uncertainty Quantification Software

Upcoming Webinars

Discover

What We Do

SmartUQ is a modern AI and Uncertainty Quantification tool optimized for engineering applications including simulation, digital twins, testing, and manufacturing. With industry-leading model accuracy and user-friendly GUIs and APIs, it's possible to handle the toughest challenges and easily solve everyday problems.

Featured Customers

Why SmartUQ

SmartUQ's combination of unique sampling capabilities, powerful machine learning tools, and easy to use analytics help our customers solve previously unsolvable problems:

“SmartUQ has the best prediction accuracy among all tools I have ever used.”

– Technical Fellow at a Fortune 100 Aerospace company

“Our Uncertainty Quantification discipline now uses SmartUQ as its central tool and with it we have helped save millions of dollars and thousands of hours of work.”

– Statistician at a Fortune 100 Jet Engine company

“SmartUQ's adaptive design can significantly reduce the number of required simulations [a 72% reduction] and lead to much higher model accuracy [96% reduction in reference prediction error]”

– A Fortune 500 Semiconductor Company

Upcoming Events

News

12
Jul

Discover how SmartUQ drives innovative solutions

Who are We?

SmartUQ offers Industry-Scale Uncertainty Quantification

Predictive Analytics

SmartUQ built with Predictive Analytics for Engineering

What is Uncertainty Quantification?

Manage your risk with SmartUQ

Why Uncertainty Quantification?

Gain the competitive edge with your analytics

SmartUQ 10.0 Now Available

Download Free Trial

Build vs. Buy

There are many open-source statistics and machine learning packages available but there are a few key reasons to pay for commercial off the shelf software.
Dedicated software development and research:
  • More sophisticated algorithms mean better scalability to larger data sets and more complex problems.
Customer focused development:
  • Usability is a priority.
  • Tools are built to meet customer needs.
Users aren’t the primary testers:
  • Things work out of the box.
  • Support is a call away.
Decreased lifetime cost relative to developing solutions internally:
  • Open-source tools may be free, but engineering time is expensive.
  • Account for the time to develop, integrate and use tools that are not made for the purpose before choosing to go open source.

Uncertainty Quantification & Machine Learning

One of the cornerstones of Uncertainty Quantification is building accurate predictive models with predictive analytics, but some of our customers have used SmartUQ’s machine learning predictive models outside of the Uncertainty Quantification workflow as a stand-alone tool. SmartUQ's predictive models can be built with data sets from simulation models, manufacturing, operational and sensors, and digital twins. Some applications of SmartUQ's predictive models include developing virtual sensors or performing root cause analysis.

UQ Goes Beyond Uncertainty Propagation

In addition to propagating input uncertainties, Uncertainty Quantification provides a more comprehensive framework, including several key analytics techniques:

  • Building predictive models: trained to mimic complex engineering simulations.
  • Sensitivity Analysis: ranks parameters by their ability to influence the results.
  • Statistical Calibration: handles the disagreement and uncertainty between the simulation model and physical tests.
  • Inverse Analysis: determines an underlying distribution for ill-conditioned and sparse model input.
  • Watch the Video
    Digital Twin Jet
    Flowchart describing predictive analytics

    Predictive Analytics for Modern Engineering

    Flowchart describing predictive analytics

    Predictive Analytics encompass a set of advanced analytics techniques used to develop a predictive model for real time analysis and predicting future events. Using all types of data sets such as simulation modeling, manufacturing, and operational and sensor data, a trained SmartUQ predictive model can quickly perform complex analysis like predictive maintenance or risk analysis - giving your team a competitive advantage. Below are some applications of SmartUQ’s industry-scale predictive analytics:

    To learn more, check out “Introduction to Predictive Analytics for Engineering” webinar.

    Machine Learning for Varying Geometry Systems

    Simulating domains with related but different geometries, meshes, or coordinate systems is a crucial piece of many workflows. Tasks such as geometry optimization, tolerance analysis, calibration to physical measurements, and uncertainty quantification on spatial responses all require handling varying geometries.

    SmartUQ's Varying Geometry Emulator extends the capabilities of SmartUQ's spatial emulation to capture the effects of inputs on spatial responses and the effects of inputs on the resulting geometry or mesh. This opens up fast and accurate surrogate modeling for all kinds of simulations and spatial meassurments.

  • Varying Geometry Emulator: Build ML models of spatial systems without mesh or coordinate restrictions.
  • Varying Geometry Example

    UQ for Decision Making

    Decision Making with Uncertainty Quantification.

    No matter where the data comes from - simulation, physical testing, sensors, or a digital twin - there always is an element of uncertainty. Don’t depend on a deterministic point estimate that could be considerably off the mark and have costly consequences. By using Uncertainty Quantification to consider all the possible outcomes, you can optimize your decision making process resulting in reduced risk and greater confidence in your results.

    See how SmartUQ optimizes decision-making from all data types, including:

    Decision Making with Uncertainty Quantification.
    Flowchart describing how analytics can accelerate system evaluation

    Acceleration with Analytics: Maximize Insights from Limited Data

    Flowchart describing how analytics can accelerate system evaluation

    Time and resources are always limited and sometimes important decisions must be made based on only a handful of data points. SmartUQ can help you get the most information out of the fewest points:

    • Optimize sampling of new data while making use of existing data.
    • Create balanced space filling samples while making use of existing data.
    • Direct sampling to refine data sets only where necessary.
    • Explore the entire design space through accurate emulation.
    • Save time and resources by reducing design and testing iterations.

    Take Analytics to the Next Level

    SmartUQ interface showing a functional emulator.

    We provide a wide spectrum of capabilities including:

    • Design of experiments
    • Emulation
    • Statistical calibration
    • Sensitivity analysis
    • Propagation of uncertainty
    • Statistical optimization
    • Inverse analysis

    Take advantage of analytics to gain deeper insights and create better products faster.

    Learn More
    SmartUQ interface showing a functional emulator.

    Flow chart describing statistical calibration.

    Statistical Calibration: Ground Simulations in Physical Data

    Flow chart describing statistical calibration.

    Calibration is necessary when building models in order to improve the fidelity or prediction ability of the simulation. SmartUQ features dedicated tools to facilitate model calibration including specialized hybrid design-of-experiments generators and automated statistical calibration. Improve model validation by quickly finding best-fit parameters and confidently assessing model discrepancies.

    Learn More

    Uncertainty is Everywhere

    Diagram of how uncertainty enters into a process.

    Uncertainty is part of every system. It arises from measurement accuracies, material properties, use scenarios, modeling approximations, and unknown future events. Uncertainty in model boundary conditions, initial conditions, and parameters makes it harder to answer your most important questions with confidence: Will it meet all the requirements and is it optimal?

    Learn More
    Diagram of how uncertainty enters into a process.