Augury: Leveraging IoT and AI for Real-Time Machine Health Insights

Augury has grown steadily since its startup days, now employing more than 100 people in New York and Israel who work to provide customers superior insights into the health and performance of their machines. Specifically, the company helps high-speed manufacturing and continuous production for Fortune 500 companies in industries such as pharmaceuticals, food and beverage, and consumer packaged goods, among others. In these “always-on” manufacturing environments, maintaining production health is key. Augury’s technology helps customers perform vital monitoring of their manufacturing and production lines using IoT devices and manufacturing analytics. The platform includes sensors, networking connectivity, dashboards, and diagnostics.

Augury, a company dedicated to providing insights into the health and performance of manufacturing machines, was facing a challenge. The founders of Augury, graduates of the Technion—Israel Institute of Technology, realized that while they could often tell when a machine was malfunctioning based on changes in sound or performance, the machines themselves lacked the ability to signal exactly what was going wrong. This led to inefficient troubleshooting methods such as manually cleaning fan airways to solve software problems. Furthermore, as Augury grew and began to handle a significant increase in enterprise customers, it needed to rebuild its IoT platform to be able to scale sufficiently. It required a stable cloud solution for IoT that could offer superior scalability, as well as a broad range of technologies and functionality.

Augury decided to launch a startup dedicated to making machines smarter and more reliable, using machine learning and IoT technology. Augury was launched in 2011 as a cloud-based solution deploying IoT devices that are connected to manufacturing machines around the world. These devices continuously send data to the cloud where it is analyzed by Augury’s machine learning algorithms, resulting in insights that are immediately provided to its customers. To handle the increase in enterprise customers, Augury decided to complete a full migration to Google Cloud, moving all of the company’s microservices to Google Kubernetes Engine (GKE). Augury uses Google Cloud big data technology including Cloud Dataflow and BigQuery to push data from basic Cloud Storage buckets into BigQuery tables, which enables tens of millions of machine learning features. This allows Augury to run faster research cycles and enhance the algorithms that predict machine failures.

• Augury is able to keep its promise of delivering continuous insights to customers by relying on the direct capabilities of Google Cloud IoT technologies. This constant flow of incoming data allows for ongoing improvement of capabilities to monitor and fix problems with IoT devices, thanks to early detection of connectivity issues. This ensures that sensor data arrives in an uninterrupted manner without data loss and that customers receive early warning of developing machine failures. The autoscaling features included in GKE solved the challenge of managing the sheer volume of data coming in through its IoT devices by ensuring the solid and balanced algorithm processing latency that meets the Service Level Agreement (SLA) that Augury has with its customers. This emphasis on continuous data flows and analysis means that Augury customers get the benefit of real-time insights into machine health. Some manufacturing customers look at this data as often as hourly, and rely on Augury to consume, analyze, and deliver insights as quickly as possible.

• Reduces machine failure by 75% through AI and IoT

• Saves millions of dollars for manufacturing plants through superior insights into the health and performance of their machines

• Enables F500 companies to transform their supply chain and culture to agile just-in-time manufacturing