Predictive technology reduces costs, supporting sustainability objectives, according to a study on AI technology applied in the construction industry conducted by JLL.

AI Makes a Difference

For Brett Ellis, regional facilities and asset manager at the multinational construction and mining company Komatsu, AI is the difference between days and weeks.

Komatsu has been using drones to map construction sites for several years. The information is used to determine slope angles, digging depth, and cut-and-fill reports. This data helps the operator perform the work more efficiently.

Now, artificial intelligence can identify defects in drone data and classify them in the order of priority for repairs – high, medium, and low.

It can provide repair cost estimates, how soon they can be done, and the costs for the entire building, said Ellis at a recent JLL webinar on developments for facility managers in the APAC region.

"I can do something in three days that used to take three weeks," Ellis said. "If I do this every year, I have a benchmark, and I can review it. And I can get that data to talk to other systems."

JLL's research shows that technology is the common thread in how unit managers will face a future of more work with fewer personnel, changing asset usage, greater cost control, and the need to focus on sustainability.

The Dramatic Rise of Added Value

The rapidly evolving category of generative AI is becoming more and more an integral part of how all the pieces of the puzzle fit together. McKinsey research estimates that generative AI could add an annual value of up to $4.4 trillion.

Technology can provide unit managers with prescriptive data and perspectives by combining data integration, advanced analytics, and AI-based recommendations. Comprehensive data collection from various sources in the unit portfolio would include IoT sensors, building management systems, maintenance records, occupancy data, energy consumption data, and more, says Ellis.

While preventive maintenance continues to dominate as a cost-cutting strategy in asset management, "predictive" technology is the new buzzword, capturing information about assets that will help reduce costs.

The use of sensors and IoT devices to monitor vibrations, temperature, pressure, and flow has been on the stage for a while, but the introduction of AI means "we can gather even more actionable data," Ellis said.

"Machine learning algorithms analyze data from sensors and historical maintenance records to predict when maintenance is needed. AI can identify equipment behavior patterns that precede failures," he said. "Those algorithms chew on the data in the background and will tell you: 'Hey, you need to do something now; we've noticed some trends through the sensors; we think now is the right time.'"

And in the future, technological developments will empower facility managers with a more integrated approach. Savings from one area could be reallocated to another with the slide of a screen. Data from various sources will be able to communicate with other sets of data.

"I'm certainly looking for data to work harder and technology to work harder than before," says Ellis.

Data Democratization

Kevin Janus, director of the JLL Technologies program, says the "maintenance journey" is rapidly transitioning from preventive maintenance, which was cutting-edge five years ago, itself an evolution from corrective maintenance ("it's broken; we need to fix it").

"Many companies are starting to look at this in a more holistic way," Janus said in a webinar discussing JLL's survey results on facility managers. "Predictive maintenance is really the next step."

Janus says that the "democratization of information gathering is upon us," and as technology becomes commonplace in facility management, the cost of acquiring systems will decrease. The cost of sensors is already decreasing, he said.

But there are also ways to adapt existing systems. "Look at what you have – people were sold building management systems in the 1980s and 1990s. There are ways to take the old and the new and create a dataset from it."

A November 2022 research paper by analysts at the Research and Innovation Institute for Sustainability in Civil Engineering in Lisbon, Portugal, found that throughout the exploitation and maintenance phase, unit management teams collect and process data from various sources, often having to be properly considered when making future decisions.

This data could feed AI-based statistical models, improving the decision-making process, they said.

With the advent of smart buildings, which incorporate most spaces with smart objects, Building Information Modeling or BIM, offers new opportunities for builders to modernize these buildings at lower costs and a shorter project duration, allowing the exchange of information between various stakeholders involved.

Conventional FM practices must incorporate integrated intelligent management advice, which is embedded in information and functional integration, according to the authors.

It is now much easier to introduce datasets to get results, and AI now provides much more information than before, says Janus. AI is, in fact, machine learning, and there are systems, such as IBM's Watson supercomputer, that can take trends data that are too much for the ordinary person to look at and provide an analysis of trends based on parameters that the unit manager might be interested in, such as seasonal factors.

But, Janus warns, artificial intelligence "is only as good as the programming and thinking in it. So, it takes human intelligence to generate artificial intelligence. That's my warning story for that day."