SEATTLE—A new artificial intelligence (AI) and machine-learning analytics tool set for manufacturing and process control is reported to put the power of machine learning in the hands of non-data scientists. The PAICe product suite was recently introduced by Tignis, a developer of software that uses AI and machine learning to improve process reliability and control. It is reported to help manufacturers “achieve process improvements not previously possible with advanced process control (APC).”
Among the process improvements enabled by the software is the ability to use surrogate machine learning models that are reported to be more accurate and “up to one million times faster than physics-based simulations.” The result is faster production, better quality control, and faster time to market, Tignis said in a release.
At the PAICe Product Suite’s core is a new, low-code programming language built by Tignis called DTQL (Digital Twin Query Language). It is reported to be the first language designed specifically to build machine analytics on digital twins.
Through DTQL, the PAICe product suite is said to significantly remove obstacles that have prevented engineers from leveraging historical data to make better decisions. It enables process and reliability engineers to convert their deep subject matter knowledge into hundreds of machine learning-based predictive models that are easily managed across thousands of diverse physical assets—without having to become a data-scientist, according to the release.
The PAICe product suite is said to accelerate the ability to build, validate, and deploy machine learning-enabled solutions in the manufacturing and process industries. Its initial focus is on semiconductor manufacturing, oil and gas processing, and energy. It is the latest venture by Jon Herlocker, a serial entrepreneur former vice president and chief technical officer at VMware.
“The PAICe product suite puts machine learning in the hands of people that have never been able to use it before,” said Herlocker, in the release. “This is important because machine learning-based control algorithms not only outperform classic feedback or feedforward advanced process control, they continuously learn from new process data, reducing the need to retune controls and improve over time. With the PAICe product suite, many more manufacturers will now be able to take advantage of the benefits of machine learning in modern manufacturing and process control by increasing process quality, throughput, and yield.”
The PAICe product suite enables machine learning for more than just predictive maintenance. It also enables it for process optimization and directly in process control loops. Its reported ability to run machine learning-based simulations one million times faster than legacy physics-based simulations allows manufacturers to have real time feedback control in places that were not possible in the past, such as real-time optimization, according to Tignis.
Key features of the suite include PAICe Builder, PAICe Monitor, and PAICe Maker. PAICe Builder is a machine learning analytics tool that is said to be easy enough for anyone to use. It provides simple connectivity to OSIsoft PI data historian and other data sources, and is available in downloadable or cloud versions, allowing users to do analytics anywhere.
PAICe Monitor allows users to easily deploy their analytics to private or public cloud infrastructure and thousands of assets with one click (including Web APIs to ingest and send data to and from data historians). It offers a scalable cloud infrastructure so that users can build the analytics they need. The Tignis managed infrastructure means that users only pay for the resources they need.
PAICe Maker deploys and manages machine learning based control algorithms that improve over time with more data. Hybrid on-premises and cloud architecture is said to ensure low latency for control, “but the best possible model training and learning in the cloud,” according to the release.
Through Tignis’s beta test program, prior to launch, the PAICe product suite is in use by a number industrial clients spanning the oil and gas, semiconductor and energy industries. Notable users of the product suite are reported to include Tokyo Electron (TEL), Synopsys, Etairon, and Optimum Energy.