How AI in BrightBlue Works

While AI has been all over the headlines recently, the history of artificial intelligence goes back decades. One type of artificial intelligence that has been the foundation for automated work is known as an expert system. It’s the type of AI that’s behind our BrightBlue® smart analytics platform.

What Is an Expert System?

An expert system is a computer system emulating and automating the decision-making ability of a human engineer through a series of “if this, then that” logic algorithms. These expert system AI solutions, like BrightBlue®, can summon the industry knowledge of an expert at a scale and speed that cannot be accomplished by a human.

How Do Expert Systems Work in Building Analytics?

Expert system, logic-based, artificial intelligence is the foundation of building analytics software like BrightBlue®.  BrightBlue® has been fine-tuned to recognize faults, opportunities for optimization, and potential early signs of mechanical failure. How is this accomplished?

First, the information model is created with experts’ knowledge. Then it is combined with data recorded at timed intervals to populate each individual expert system. Each expert system is a series of calculations, verifications and checks running in a sequence. Let’s walk through an example of how the economizer analysis, an expert system in BrightBlue®, is applied to an air handling unit (AHU), as described in this article by an expert software developer.

1. Determine CO² Mode

The first step is to determine how the air handling unit adjusts ventilation rates based on measured CO² levels in the building. This is an important check to understand if the economizer sequence can be overridden by the CO2 mode to prevent false positives from triggering.

2. Determine Fresh Air Fraction

The next step is to calculate the percentage of fresh air being supplied to the areas served by the AHU. A simple check on the outside air damper position isn’t always enough. A 20 percent open position may not equate to 20 percent airflow because of variables such as damper curves, a variety of duct sizes, bypass loops, etc.
Through expert system checks, BrightBlue® uses measured airflows and temperatures to accurately calculate the fresh air fraction while checking for errors in sensor data that could produce additional false positives.

3. Determine Minimum Fresh Air Requirements

Once the fresh air fraction is known, it’s compared to the minimum fresh air requirements to maintain the correct ventilation rates. The system needs to determine how the AHU maintains minimum airflow and what those requirements are based on.

4. Determine Ideal Economizer Operation

The last step is to definitively answer the question: “Is my economizer operating correctly?” The software combines the outputs from Steps 1 through 3 and completes final checks to ensure the AHU economizer sequence is operating in an ideal state.

How Can the Artificial Intelligence of BrightBlue® Help You?

Embedding expert engineering analyses into a fault detection and diagnostics (FDD) application allows facilities management personnel and service providers to efficiently scale their team and focus on what matters most – fixing the issues identified by the expert system analysis.

By quickly fixing the identified issues, BrightBlue® can reduce utility usage and operating costs, improve equipment life span and save money. If you’re interested in scaling your building’s FDD through expert systems, BrightBlue® may be the solution for you. Get in touch with us, and we’ll answer any questions you have about how to implement BrightBlue® for your building.