The beautiful intersection of simulation and AI

Check out all the on-demand sessions from the Intelligent Security Summit here.


Simulation has emerged as a critical technology to help companies shorten time-to-market and lower design costs. Engineers and scientists use simulation for a variety of applications, including:

  • Using a virtual model (also known as a digital twin) to simulate and test their complex systems early and often in the design process.
  • Maintain a digital thread of traceability through requirements, system architecture, component design, code and tests.
  • Extend their systems to perform predictive maintenance (PdM) and failure analysis.

Many organizations are improving their simulation capabilities by incorporating artificial intelligence (AI) into their model-based designs. Historically, these two fields have been separate, but create significant value for engineers and researchers when used together effectively. The strengths and weaknesses of these technologies are perfectly aligned to help businesses solve three main challenges.

Challenge 1: Better training data for more accurate AI models with simulation

Simulation models can synthesize real-world data that is difficult or expensive to collect into good, clean and cataloged data. While most AI models run with fixed parameter values, they are constantly exposed to new data that may not be captured in the training set. If left unattended, these models will generate inaccurate insights or fail outright, causing engineers to spend hours trying to figure out why the model isn’t working.

Simulation can help engineers overcome these challenges. Rather than tweaking the AI ​​model’s architecture and parameters, it has been shown that time spent improving the training data can often yield more substantial improvements in accuracy.

Event

Intelligent Security Summit On-Demand

Learn the critical role of AI and ML in cybersecurity and industry-specific case studies. Watch sessions on demand today.

Look here

With a model’s performance so dependent on the quality of the data it’s trained on, engineers can improve results with an iterative process of simulating data, updating an AI model, observing which conditions it can’t predict well, and collecting more simulated data for those relationship.

Challenge 2: AI for new functions in the product

Simulation has become an important part of the design process for engineers using embedded systems for applications such as control systems and signal processing. In many cases, these engineers develop virtual sensors, devices that calculate a value that is not measured directly from the available sensors. But the ability of these methods to capture the nonlinear behavior found in many real-world systems is limited, so engineers turn to AI-based approaches that have the flexibility to model the complexity. They use data (either measured or simulated) to train an AI model that can predict the unobserved state from the observed states and then integrate that AI model with the system.

In this case, the AI ​​model is part of the control algorithm that ends up on the physical hardware and usually needs to be programmed in a lower-level language, such as C/C++. These requirements may impose limitations on the types of machine learning models suitable for such applications, so technical professionals may need to try multiple models and compare trade-offs in accuracy and device performance.

At the forefront of research in this area, reinforcement learning takes this approach further. Instead of just learning the estimator, reinforcement learning includes the entire control strategy. This technique has proven effective in some challenging applications, such as robotics and autonomous systems, but building these types of models requires an accurate model of the environment – ​​never a guarantee – as well as massive computing power to run large numbers of simulations.

Challenge 3: Balance “right” against “right now”

Companies have always struggled with time-to-market. Organizations that ship a buggy or defective solution to customers risk irreparable damage to their brand, especially startups. The opposite is the case when “also-ran” in an established market has problems gaining traction. Simulations were an important design innovation when they were first introduced, but their steady improvement and ability to create realistic scenarios can slow down perfectionist engineers. Too often, organizations try to build “perfect” simulation models that take significant time to build, introducing the risk that the market will have moved on.

To strike the right balance between speed and quality, engineering professionals must recognize that there will always be environmental nuances that cannot be simulated. AI models should never be blindly trusted, even when they serve as approximations for complex, high-quality systems.

The future of AI for simulation

AI and simulation technologies have individually built and sustained the momentum for nearly a decade. Now, engineers are starting to see a lot of value in their intersection, given the symbiotic nature of their strengths and weaknesses.

As models continue to serve increasingly complex applications, AI and simulation will become even more important tools in the engineer’s toolbox. With the ability to develop, test and validate models accurately and affordably, these methodologies will only continue to grow in use.

Seth DeLand is Product Marketing Manager for Data Analytics at MathWorks.

Data Decision Makers

Welcome to the VentureBeat community!

DataDecisionMakers is where experts, including the technical people involved in data work, can share data-related insights and innovation.

If you want to read about cutting-edge ideas and up-to-date information, best practices and the future of data and data technology, join us at DataDecisionMakers.

You may even consider contributing an article of your own!

Read more from DataDecisionMakers

Leave a Reply

Your email address will not be published. Required fields are marked *