Page 27 - Climate Control News July 2019

Building Automation
Engineering real results from Artificial Intelligence
SENIOR PRODUCT MARKETING manager for the Simulink platform at MathWorks, Mi- chael Carone, explains how to use Artificial In- telligence (AI) to improve the performance of HVAC systems.
According to a recent report from the McKin- sey Global Institute, Artificial Intelligence (AI) could potentially deliver $13 trillion of global ac- tivity by 2030.
This amounts to an additional 1.2% of GDP annual growth, which would be significantly more than the 0.3% growth we saw from the steam engine that sparked the dawn of the in- dustrial revolution.
Yet with all this potential, AI is still in its in- fancy. Companies are struggling with AI and that's because too many people are focused on just the intelligent AI algorithms.
“APPLYING INSIGHTS IS ABOUT WHAT WE AS ENGINEERS AND SCIENTISTS BRING TO THE AI,NOT WHAT THE AI BRINGS TO US.”
There are three other requirements (or three other I’s, if you will), to being successful with ar- tificial intelligence:
1. The discovery and use of insights from do-
main experts in applications where the AI will
be used;
2. Tools to handle the implementation details
across the entire design workflow, not just the
AI piece;
3. Ensuring that there is an effective interac-
tion between the AI and the surrounding envi- ronment, especially with people.
To illustrate these three requirements for
building a successful AI, I’d like to use Buildin- gIQ as an example.
BuildingIQ is using MATLAB to build a cloud- hosted system that optimises the energy con- sumption of a building’s HVAC system. Data is used from external sources, such as a tempera- ture forecast and an electricity price forecast, to minimise the building’s energy consumption re- peatedly with a 12-hour predictive horizon. This approach has reduced energy used by HVAC sys- tems by 10 to 25 per cent.
Let’s go back to the first I, insights.
Applying insights is about what we as
engineers and scientists bring to the
AI, not what the AI brings to us. We
use our insights when selecting data,
making tradeoffs, and evaluating re-
sults. When working with AI, it’s im-
portant that you can use tools so that
your insights are an integral part of
the work. BuildingIQ does this by fil-
tering out data, looking at poles and ze- roes, and running nonlinear optimisations so that the data coming in and out of the AI al- gorithm is sound.
Designing an implementation is about design- ing the entire solution, not just the AI. If you’re a researcher, that means testing, data analysis, and reporting. If you’re building a car, it’s about requirements gathering, modeling and simula- tion, and verification and validation. And if you’re creating a climate control system as is the case with BuildingIQ, it’s about designing an HVAC control system and projecting weather and energy prices that work with the AI.
Michael Carone of MathWorks.
The third requirement is ensuring that the AI interacts effectively with the surrounding environment and within complex human work- flows. This can mean different things based on the industry and ap- plication. For example, in a car, the AI can avoid accidents, but needs
to do it in a smooth way to ensure that rid- ers still have a pleasant experience. In a HVAC example, BuildingIQ offers a mobile app that provides information and flexibility so that peo- ple can adjust operating parameters to optimise their comfort levels.
Success with AI requires more than just de- veloping intelligent algorithms. We must also apply insights from domain experts, design the AI within a complete implementation, and en- sure the AI can interact well in its surrounding environment. Consider your own projects and how you can use AI combining data science with engineering.
CLIMATE CONTROL NEWS
JULY 2019
27