Courtesy WIRED Brand Lab
The Internet of Things is getting smarter. Companies are incorporating artificial intelligence—in particular, machine learning—into their IoT applications. The key: finding insights in data.
With a wave of investment, a raft of new products, and a rising tide of enterprise deployments, artificial intelligence is making a splash in the Internet of Things (IoT). Companies crafting an IoT strategy, evaluating a potential new IoT project, or seeking to get more value from an existing IoT deployment may want to explore a role for AI. Large organizations across industries are already leveraging or exploring the power of AI with IoT to deliver new offerings and operate more efficiently.
Gartner predicts that by 2022, more than 80 percent of enterprise IoT projects will include an AI component, up from only 10 percent today.
Artificial intelligence plays a growing role in IoT applications and deployments. Both investments and acquisitions in startups that merge AI and IoT have climbed over the past two years. Major vendors of IoT platform software now offer integrated AI capabilities such as machine learning-based analytics.
The value of AI in this context is its ability to quickly wring insights from data. Machine learning, an AI technology, brings the ability to automatically identify patterns and detect anomalies in the data that smart sensors and devices generate—information such as temperature, pressure, humidity, air quality, vibration, and sound. Compared to traditional business intelligence tools—which usually monitor for numeric thresholds to be crossed—machine learning approaches can make operational predictions up to 20 times earlier and with greater accuracy.
Other AI technologies such as speech recognition and computer vision can help extract insight from data that used to require human review.
AI applications for IoT enable companies to avoid unplanned downtime, increase operating efficiency, spawn new products and services, and enhance risk management.
In a number of sectors—industrial manufacturing or offshore oil and gas, to name two—unplanned downtime resulting from equipment breakdown can cost big money.
Predictive maintenance—using analytics to predict equipment failure ahead of time in order to schedule orderly maintenance procedures—can mitigate the damaging economics of unplanned downtime. Machine learning makes it possible to identify patterns in the constant streams of data from today’s machinery to predict equipment failure. In manufacturing, Deloitte finds predictive maintenance can reduce the time required to plan maintenance by 20–50 percent, increase equipment uptime and availability by 10–20 percent, and reduce overall maintenance costs by 5–10 percent.
AI-powered IoT can also help improve operational efficiency. Just as machine learning can predict equipment failure, it can predict operating conditions and identify parameters to be adjusted on the fly to maintain ideal outcomes, by crunching constant streams of data to detect patterns invisible to the human eye and not apparent on simple gauges.
Machine learning often finds counterintuitive insights: A shipping fleet operator’s machine learning tools determined that cleaning their ships’ hulls more often—an expensive, downtime-causing process—actually increased the fleet’s overall profitability. The math went against shipping industry instincts: Hulls kept smooth through frequent cleaning improve fuel efficiency enough to vastly outweigh the increased cleaning costs.
Enhancing IoT with AI can also directly create new products and services. AI-controlled drones and robots—which can go where humans can’t—bring all-new opportunities for monitoring and inspection that simply didn’t exist before. Fleet management for commercial vehicles is being reinvented through AI, which can monitor every measurable data point in a fleet of planes, trains, trucks or automobiles to find more efficient routing and scheduling, and reduce unplanned downtime.