Proving the Business Case for the Internet of Things

Progress, Amazon IoT self service anomaly detection

William Payne
June 14, 2018

Software development tech specialist Progress has launched an anomaly detection and prediction service in collaboration with Amazon Web Services (AWS) for Industrial IoT applications. The technology is designed to provide a simple route to detecting industrial equipment failures, predicting likely failures in advance, and validating against failures, both known and unknown. 

The new service employs "cognitive machine learning". Cognitive computing is a branch of AI that aims to make results of machine learning or deep learning easily understandable to humans. Cognitive based applications aim to make outcomes more relevant and immediately actionable for organisations.

Progress says that industrial organisations globally are struggling to make sense of industrial IoT data and to detect anomalies and prevent equipment failures.

AWS and Progress are providing the service under an R&D-specific license currently. AWS is also offering free trials of Progress DataRPM cloud instances for qualified manufacturers with connected sensors and the ensuing time series data. The trial will allow companies to load their data securely on AWS, detect equipment anomalies, predict failures before they occur, and validate against failures.

The new service is designed to provide end-to-end automation of the steps from data ingestion and analysis to insights visualisation. Users can upload sensor data, map the attributes and click “run”. The entire cognitive flow works in an automated fashion to show near-immediate results.

Results are shown in ”stories,” in a human-readable format that highlights patterns and anti-patterns in the sensor data. This is part of the concept of cognitive computing.

Using drill-down and filters, users can gain a better understanding of the behaviour of assets and most important sensors for predicting the most likely failures states.

For those with successful POCs and pilots, the framework enables a transition from R&D to full production environments with no code rewrites.

“With billions of interconnected devices pumping out untold volumes of data, there is a huge demand for ways to gather valuable insights from the data. But with limited budgets and lengthy deployment cycles for many machine learning applications, the true value of data is often left untapped or underutilised,” said Dmitri Tcherevik, Chief Technology Officer, Progress. “That is why Progress now offers an R&D self-service option for those organisations looking to start on their IIoT journey more quickly and easily than previously possible. R&D teams can use our self-service cognitive cloud-based application to immediately start detecting and predicting anomalies across their industrial data for fast time-to-insights and more accurate ROA calculations.”

The Progress DataRPM application uses cognitive techniques and machine learning and meta learning-based algorithms to identify and predict anomalies, often before they occur in the production environment. Meta-learning, a subset of machine learning, is a set of algorithms that teach computers how to self-learn in difficult Industrial IoT big data environments.