Manufacturing IT, MES

For years, researchers from MIT and Brown University have been developing an interactive system that lets users drag-and-drop and manipulate data on any touchscreen, including smartphones and interactive whiteboards. Now, they’ve included a tool that instantly and automatically generates machine-learning models to run prediction tasks on that data. Courtesy: Melanie Gonick, MIT
Manufacturing IT, MES June 28, 2019

Drag-and-drop data analytics using machine learning

MIT researchers have developed a system that lets nonspecialists use machine-learning (ML) models to make predictions for medical research, sales, and more.

By Rob Matheson
Courtesy: CFE Media
Manufacturing IT, MES June 26, 2019

Deep embedded vision benefits for manufacturers

Deep embedded vision systems can work without operating systems and feature advanced algorithms for processing raw image streams from integrated image sensors.

Manufacturing IT, MES June 25, 2019

12 benefits of using standards in design, implementation for iMOM projects

Integrated manufacturing operations management (iMOM) is designed to increase and sustain business benefits for users such as improved accuracy and thorough implementation.

By Stan DeVries
Courtesy: CFE Media
Manufacturing IT, MES June 21, 2019

Using AI to help robots remember

Researchers at the University of Maryland have developed a method to combine perception and motor commands using the hyperdimensional computing theory, which could fundamentally alter and improve how robots translate what they sense into what they do through artificial intelligence (AI).

By Gregory Hale
Image courtesy: Bob Vavra, CFE Media
Manufacturing IT, MES June 18, 2019

Algorithm developed to predict and inform robots where humans are headed

MIT researchers have developed an algorithm that accurately aligns partial trajectories in real-time, allowing motion predictors to accurately anticipate the timing of a person’s motion to make human-robot interaction safer.

By Jennifer Chu
Figure: Comparison of transactional data extraction to the more sophisticated requirements of industrial data extraction across a number of factors. Courtesy: HighByte
Manufacturing IT, MES June 12, 2019

Improve industrial data integration with ETL software

Extract, transform, load (ETL) software can help improve data gathering for operations technology (OT) applications, but there are major challenges with data integration that companies need to overcome.

By John Harrington
Dr. Alexander Broos, VDW, German Machine Tool Builders Association, spoke at OPC Day, Sept. 13, 2018, at IMTS in Chicago, explaining that non-standard connections are among machine builders’ challenges. With OPC UA from OPC Foundation, there already is connectivity, he said. Courtesy: Mark T. Hoske, CFE Media
Manufacturing IT, MES June 10, 2019

Top 5 Control Engineering articles June 3-9

Articles about the Career and Salary Survey, CNC digitalization, alarm management and process safety, process instrumentation education, and asset performance in refineries were Control Engineering’s five most clicked articles from June 3-9. Miss something? You can catch up here.

By Chris Vavra
Harting to be a collaborative partner in a development project to retrofit legacy protocol plastic injection molding machines with an integrated Industrie 4.0 digital control system that is also linked with its factory-wide MES/ERP system. Courtesy: Harting/Control Engineering Europe
Manufacturing IT, MES June 8, 2019

Retrofitting Industrie 4.0 for digital control systems

Ypsomed, a medical technology company, was able to retrofit Industrie 4.0 digital control systems onto its legacy plastic injection molding machines.

By Suzanne Gill
Machine learning and other advanced technologies are embedded in advanced analytics software to empower engineers and other experts. Courtesy: Seeq
Manufacturing IT, MES May 30, 2019

Refineries need machine learning to improve operations

Machine learning and other advanced technologies are embedded in advanced analytics software to empower engineers and other experts.

By Michael Risse
Courtesy: Chris Vavra, CFE Media
Manufacturing IT, MES May 29, 2019

Framework developed to help deep neural network performance

North Carolina State University researchers have developed AOGNets, a framework for building deep neural networks that uses a compositional grammar approach to extract useful information from raw data.

By Matt Shipman