As engineering professionals, we continually seek innovative ways to improve our industry, enhance efficiency, and ensure the safety of the public.
Today, I would like to highlight some of the themes discussed in Episode 033 of the AEC Engineering and Technology Podcast, where Rob Otani, CTO at Thornton-Tomasetti, and I discussed how AI (artificial intelligence) and ML (machine learning) are revolutionizing engineering design and construction.
If you find this summary interesting, check out the full-length episode!
1. Understanding the Core Essence of AI Applications in Engineering
- The foundation of impactful AI applications lies in an in-depth understanding of the field’s intricacies.
- One of the most valuable things we can do is to utilize AI tools to address tangible, persistent engineering issues.
- Those entrenched in the day-to-day operations, grappling with repetitive tasks, possess the acumen to pinpoint areas requiring innovative solutions.
2. The Vision That Sparked Innovation: Leveraging Machine Learning for Practical Solutions
- Robert’s journey into the realm of machine learning started in 2015, spurred by a team member’s discourse on its significance in the tech sphere.
- Recognizing its potential in predicting solutions akin to engineers’ methodologies of fitting curves to smart data, Rob envisioned creating an app.
- This application, tailored for the entire team, promised rapid and precise solutions, effectively streamlining their daily workflows.
3. Accelerating Engineering Processes: Teaching Computers Human Intelligence
- The fundamental objective is to train computers to replicate human intelligence, a process typically spanning 5 to 10 years.
- Leveraging data and expertise, this endeavor aims to expedite engineering processes by furnishing fast solutions, validated through traditional methods.
4. Practical Implementations: AI Transforming Inspections and Preventive Approaches
- The AI landscape witnessed the emergence of T2D2.ai, a startup spawned from an R&D project in 2017 or 2018.
- In just six months, a model employing computer vision to detect concrete cracks was successfully trained.
- Over time, this technology evolved to assess various exterior damages, significantly reducing building inspection timelines compared to manual efforts.
- This development serves as a glimpse into the early stages of AI’s integration, promising future innovations in problem-solving methodologies.
5. Digitizing Inspections: The Value of Proactive and Cost-effective Strategies
- The concept behind T2D2.ai advocates for frequent, cost-effective inspections as a proactive strategy to prevent significant issues.
- Emphasizing tracking changes and the evolution of existing damage over time, this digitized approach introduces possibilities that are not readily available while employing traditional methods.
- It offers a proactive and cost-effective aid to traditional industry practices, which tend to be analog and manual.
6. AI and Project Management: Unlocking Data and Overcoming Resistance to Change
- Project management in the engineering sector, encompassing technical, financial, and staffing aspects, often grapples with fragmented and critical information scattered across diverse platforms.
- The challenge lies in streamlining and harnessing this data, especially within the accounting and finance sectors.
- As application programming interfaces (APIs) gradually emerge, the industry is steadily embracing data analytics, paving the way for the gradual integration of AI’s predictive capabilities.
7. Transformative Workflow: Overcoming Challenges and Innovating Design Processes
- Resistance to change poses a significant challenge in engineering with regard to AI and ML integration.
- Presentations strive to enlighten teams, portraying AI as a potent tool, almost akin to “Excel on steroids.”
- Demonstrating 95% accuracy of AI-based methods using engineers’ spreadsheets underscores AI’s potential in simplifying tasks and reshaping workflows.
8. The Future Vision: AI-Aided Design Focusing on Efficiency and Cost Savings
- The paradigm shift in engineering methodologies moves from the constraints of optimizing 2D designs toward striking a balance between excessive reliance on 3D software and manual engineering efforts.
- The envisioned goal is to use AI and ML to automate early design stages, empowering engineers to focus on specific building components.
- This envisages delivering efficient, visually appealing designs while leveraging AI for enhanced efficiency.
9. Empowering Engineers: Training for the Future of AI and ML in Engineering
- Acknowledging the effectiveness of existing software and designers’ reliance, emphasis lies in understanding clients’ early project requirements, focusing on broader structural characteristics over intricate details.
- The target for the next five years is to significantly reduce the 30% to 40% fee typically allocated for early design stages, directing efforts toward delivering superior final designs and ensuring cost-effectiveness across projects.
10. Guidance for Aspiring Engineers: Mastering Tools and Principles in AI and ML
- For aspiring engineers venturing into AI and ML, a strong emphasis is placed on comprehensive training through weekend and online classes.
Mastery in both tools and fundamental engineering principles constitutes the path to success, seamlessly combining tool proficiency with a robust understanding of engineering principles.
About the Author Nick Heim, P.E.
Nick Heim, P.E., is a civil engineer with six years of experience in the repair and restoration of existing structures. Nick is also the host of the AEC Engineering and Technology Podcast (“AECTECH”) and brings valuable insights and expertise to listeners worldwide.
Nick’s interests lie at the intersection between the built world and technology, and he can be found looking for the ever-changing answer to the question, “How can we do this better?” He can be found on LinkedIn, producing content about use of technologies in his civil engineering career and small business.
We would love to hear any questions you might have or stories you might share about how AI and ML are revolutionizing engineering design and construction.
Please leave your comments, feedback or questions in the section below.