NeuroMem in a Factory 4.0 system in a Russian steel furnace

NeuroMem in a Factory 4.0 system in a Russian steel furnace

NeuroTechnologijos installs a NeuroMem-powered monitoring system in a steel blaster furnace in Magnitogorsk – Russia. Its solution is composed of a bank of NT Adaptive Controllers designed and manufactured by NeuroTechnologijos and mounted in an industrial enclosure. Each NT Adaptive Controller receives signals from the machinery equipment and uses a NeuroMem neural network to verify that the signals stay within normal waveforms in amplitude, frequency and envelope. If novelties are detected, a second neural network can automatically learn the new waveforms for later review by a human supervisor.

 

Accurate person identification based on face and voice

Accurate person identification based on face and voice

Dr. Manan Suri, professor at the Indian Institute of Technology, Delhi and his team from the Department of Electrical Engineering have conceptualized and qualified a system combining two NeuroMem neural networks to accurately authenticate persons based on their voice and face. The hardware platform includes a NeuroMem CM1K chip so its 1024  neurons can perform the learning and classification of patterns in real-time and near sensor.

Read his interview with Asia Tech News

Read his complete paper published at the IEEE Symposium Series on Computational Intelligence

 

Glass surface inspection with minimum investment

Glass surface inspection with minimum investment

Surface inspection systems do not have to be a big investment in term of budget, resources and time.

General Vision has developed an AI camera powered by a NeuroMem network to detect defects and which can be assembled in-line with other identical cameras to cover any width of material passing on a belt or float. The cameras can be snapped on a simple din rail and spaced regularly, or not, to monitor 24/7 the quality of glass, plastic, vinyl, wood, paper and pulp, fabrics, printing, and more.

Cameras trained for glass defect detection

Depending on the material and installation, the training can be as simple as training on only one camera and then exporting the knowledge built by its neurons, to the neurons of the other cameras. Sometimes, training may require some tuning for the 2 cameras at each end of the line and this is where the real-time learning capabilities of the neurons is very practical. Read more>>