In Part 1 of our Trailblazers interview, Burcu Akinci, professor of civil and environmental engineering and associate dean for research, College of Engineering at Carnegie Mellon, discusses her views on the state of innovation in the industry, as well as its challenges, and her battle against accepting the status quo.
In Part II, Akinci explores how to foster a culture of innovation, including the importance of having a visionary leader who wants to change things and is a risktaker. She also discusses how emerging technologies like machine learning and AI will impact the industry. “AI and machine learning work well when you have a lot of data - and combine that data with domain models,” she says.
Dr. Burcin Kaplanoglu, vice president, Oracle Industries Innovation Lab, led the conversation.
There are a lot of components associated with innovation. Much of the culture of innovation starts from the top. You must have a visionary leader who wants to change things and is willing to take risks. Someone who is willing to fail fast, learn from it, and go forward rather than scrutinizing every decision.
I'm not saying to invest blindly, but with some of the innovative technologies, occasionally the ROIs are not there to quantify at the beginning. You must invest a little bit to get the ROI.
That brings up the question you were asking in terms of education. You must have folks who not only are experts in engineering or their discipline, but who also understand enough about technology to evaluate what is coming up in the pipeline without waiting for 10 years to see how the ROI will shake out.
Somebody should have enough knowledge to say, "Oh, here are the critical issues and here are the opportunities that this technology can provide."
That combination is getting more and more critical—domain expertise together with some technological expertise or understanding. They might not be the expert in machine learning language programming, but they understand the principles and can evaluate the emerging technologies.
We have been living in an age where, with a click of a button, we have access to information and can develop good situational awareness on a topic.
When it comes to construction, infrastructure, and facilities, we still don't always have that. Any technology that's going to enable us to have good situational awareness for a comprehensive assessment, and eventually predict issues before they occur, is going to be critical.
For example, the sensors that are embedded in your HVAC system provide a great opportunity to build up situation awareness, assessment, and prediction capabilities. How do you fuse them together with other facility related data and information?
How do you derive actionable information? How do you bring the situational awareness and assessment that is needed by the engineers so they can make the best decisions instead of making decisions in the dark? Finally, how do you predict issues before they occur so that you can fix them before they become problematic?
Those are transformational changes. That's where this digital revolution will occur. It will empower our engineers with the right information so that they have a complete understanding of what's happening in the field and can make proactive decisions.
AI and machine learning work well when you have a lot of data and developments. In terms of short-term impact, we are seeing significant AI/ML development that take advantage of images and scans collected in the field for vision-based assessment.
There has been a whole community of researchers, both in computer science and engineering, who have been doing vision-based algorithms and data sharing. Faster developments of AI to analyze images for progress monitoring, quality controls, and safety management are expected. We're seeing those use cases being developed with the startups.
Computer vision-based approaches can also apply for the infrastructure management side of things and for condition assessment. Instead of inspecting averages every two years, it would be possible to send a drone out every month for a good understanding of what's happening in the field.
When it comes to facility operation, we're also in a data-rich area. In a typical 60,000 square foot facility, you can have 21,000 data points coming out of your building automation system alone.
But as a user, it would be overwhelming to trend all those time-series data points and understand what they are saying – you want actionable information instead. At the same time, you're also dealing with these HVAC systems consuming and wasting energy because there are undetected faults that impact occupancy comfort and operations.
That's another area where you can use AI to get into a more prescriptive mode on how you operate or maintain your facilities, and eventually get into the predictive mode, instead of just saying there's something wrong with the HVAC system because the room temperatures are above or below the set points.
It is important for a system to be able to state reliably, "Here's what is wrong (or even better - here is what is expected to be wrong), here's the root cause, and here is how you can fix it.” And if you can fix this, this is how much money you're going to save. AI works beautifully in that setting, too.
See innovation in action at the Oracle Industries Innovation Lab.
Oracle Construction and Engineering, the global leader in construction management software and project portfolio management solutions, helps you connect your teams, processes, and data across the project and asset lifecycle. Drive efficiency and control in project delivery with proven solutions for project controls, construction scheduling, portfolio management, BIM/CDE, construction payment management, and more.
Read more Trailblazers articles here.
Corie Cheeseman is a senior content marketing manager for Oracle Construction and Engineering.
Previous Post
Next Post