Solving Intractable Physics Using AI

Many engineering companies have already adopted #artificialintelliegence to increase efficiency in their R&D effort when validating or optimising designs. While effectively adopting AI promises to deliver immense value, as these teams have learned, it requires much more than simply building and deploying machine learning models.

To take full advantage of an AI solution to scale, it needs to fit into, and enhance, your engineering workflow. We have worked on over 300 AI projects to solve intractable physics problems with the world’s most innovative engineering teams including Honeywell, Siemens, BMW, Kautex-Textron and more, and we have learned what it takes to be successful.?

Through this newsletter, I want to share our learnings with engineering leaders and provide:

• Helpful?insights?from our learnings working at the forefront of product development
• Expected benefits from adopting a more data-driven workflow
• Guidelines?to evaluate a suitable use case for AI
• How to upgrade your workflow management strategy

Follow me for more insights on AI in Engineering Product Development.

The Intersection of AI and Engineering: A Look into the Future

Engineering leaders feel pressure to speed time to market and yet highly complex products that are hard to model require time-intensive, repetitive testing to validate.

Today’s methods, such as simulation, fall short in solving these intractable physics problems.?

To stay competitive, the majority of engineering leaders in automotive, aerospace and industrial markets in the US and EU are looking to AI as a means to accelerate time to market and increase engineering efficiency.

Findings in the?State of AI in Engineering, our commissioned study conducted by Forrester Consulting, highlight the urgent need for engineering leaders to evaluate how AI solutions can help them cut validation costs and speed time to market.

How Does AI Fit Into Your Engineering Workflow?

To take full advantage of an AI solution at scale, it will need to fit into your overall engineering workflow. Below, I listed a few signals on how to evaluate a suitable 'AI fit', and how to update your workflow management strategy accordingly.

Engineering workflow management: Before the adoption of AI

There are several reasons contributing to traditional, inefficient engineering workflow management strategies:

• Knowledge isn’t being retained.?The results of simulation or tests carried out during development aren’t being captured, meaning very little knowledge is being retained for future generations of designs, developed by future generations of engineers.
• It can often feel like an iterative guessing game.?How should you change your design to improve its performance? What is the relative importance of design parameters? How to find an optimum when considering multiple goals and strict constraints? These are the questions that engineers are failing to quantify.
• You often need to start from scratch.?Your team has worked on refining a design for the last month around a narrow set of goals and constraints from other departments. What if these requirements suddenly change? It can mean going back to square one. You will still encounter this issue with the use of traditional design space exploration tools since the design requirements for optimisation campaigns need to be defined upfront.
• It involves a lot of manual effort.?Because of the iterative nature of traditional engineering workflows, a lot of an engineer’s time is spent setting up repetitive simulations or empirical testing, analysing and preparing reports for one result at a time, and trying to align with other departments despite the uncertainty of how changes in the design will affect its quality or performance.

What to aim for in engineering workflow management: Data-driven R&D

Companies that have fully incorporated the benefits of AI into their engineering workflows can derive insight from data, which accelerates their product development processes.

Here are a few characteristics of this end goal:

• AI is not replacing how each test or simulation is carried out,?but instead reduces the total amount needed as part of a design cycle. Engineering organisations have spent decades refining ways to assess the quality and performance of their designs. It is the quality of this data, describing complex, intractable physical phenomena, which enables machine learning models to be built.
• AI allows you to instantly predict and optimise the performance of your designs.?Using historical data, an AI model can learn the relationships between design variables and test results. This enables you to quickly build a global understanding of your physical engineering system. For a new design, you’ll be able to predict the test outcomes. For a new set of goals and constraints, you’ll instantly find optimal designs. No more iterative guessing game, and no more starting from scratch.
• Effective communication?of design requirements, test results, and performance trade-offs are key element of an efficient product development process. By building AI solutions collaboratively and deploying them to colleagues or customers, knowledge and insight can be shared instead of being retained in the minds of a handful of experts.

No engineering company can adopt AI at scale overnight and reap benefits the next day.

Improving engineering workflow management with AI adoption and ML solutions requires some adjustments to your existing engineering processes and workflow, including setting up repeatable processes to generate and capture data from your simulations or tests. My team is more than happy to talk to you about your AI use case!

Feel free to contact the experts at Monolith to discuss your AI Use Case and run a feasibility analysis.

If you’d like to see more tips and more hands-on examples on AI in Engineering Product Development, consider subscribing to my blog - and leave a comment down below.

Test Less. Learn More.

Richard