Drives and Control Solutions

Motors, Control Solutions, Power Transmission and Advanced Motion Technology                                                                 

Beckhoff twincat 400April 17, 2019

Beckhoff Automation has announced a new machine learning (ML) solution that is seamlessly integrated into TwinCAT 3 software. Building on established standards, TwinCAT 3 Machine Learning offers ML applications the same advantages of system openness familiar from PC-based control technology. In addition, this TwinCAT solution supports real-time ML, allowing it to simultaneously handle demanding tasks like motion control. These capabilities provide machine builders and manufacturers with an optimum foundation to enhance machine performance, for example, through predictive maintenance, process self-optimization and autonomous detection of process anomalies.

With machine learning, controls engineers no longer have to follow the traditional engineering route of designing solutions for specific tasks and turning those solutions into algorithms. Instead, the automation controller can learn the desired algorithms from exemplary process data. With this alternative approach, powerful ML models can be trained and then used to deliver superior, higher-performing solutions. In automation technology, this opens up new possibilities in many areas, including predictive maintenance and process control, anomaly detection, collaborative robotics (cobots), automated quality control and machine optimization.

The models to be learned are trained in an ML framework, such as MATLAB® or TensorFlow, and then imported into the TwinCAT runtime via the Open Neural Network Exchange Format (ONNX), a standardized data exchange format used to describe trained models. The TwinCAT runtime incorporates the following new functions for this purpose:

  • TwinCAT 3 Machine Learning Inference Engine for classic ML algorithms, such as support vector machine (SVM) and principal component analysis (PCA)
  • TwinCAT 3 Neural Network Inference Engine for deep learning and neural networks, such as multilayer perceptrons (MLPs) and convolutional neural networks (CNNs)

Directly execute model results in real-time

Inference, i.e. the execution of a trained ML model, can be performed directly in real-time with a TwinCAT TcCOM object. With smaller networks, system response times of less than 100 µs corresponding to a TwinCAT cycle time of 50 µs are supported. Models can be called via PLC, C/C++ TcCOM interfaces or a cyclical task.

Through seamless integration with the control technology, the multi-core support provided by TwinCAT 3 is also available for ML applications. This means, for instance, that different task contexts can access a particular TwinCAT 3 Inference Engine without restricting each other. All fieldbus interfaces and data available in TwinCAT remain fully accessible as well. This allows ML solutions to use immense amounts of data, for example, for complex sensor data fusion (data merging), and it also means that real-time interfaces to actuators are available to enable, among other things, optimal controller performance.

Go HERE for more information

Latest Articles

  • Prev
PC-based control and TwinCAT provide a foundation for advanced Industrie 4.0 and Internet of Things ...
Join ABB for an in-depth look at how variable frequency drives assist in aeration applications for ...
Leading Canadian forest product company, Chantiers Chibougamau, has selected ABB to help overhaul ...
ABB Motion Canada alongside our HVAC Partners nationwide has introduced a special program for our ...
Energy overload situations can cause braking resistor failure, but is easily prevented with the ...
Brock Solutions is pleased to announce the recent award by the Region of Peel of the Clarkson and ...
If the main power is lost to a VFD while the motor is under load, the DC bus of the VFD drops at an ...
This webinar (Friday April 17, 2020 at 11:00am - 12:00pm EDT) will review simple and easily ...
With the spring tradeshow season coming upon us, and discussions beginning to come up about the new ...

           Partnering For The Next Step                

Siemens CanadaWelcome to the Digital Enterprise Virtual Summit brought to you by Siemens

How quickly can you react to changing conditions and demands in your market? How can you ensure your production will run securely at any time in the future?

Industry’s digital and technological transformation is the answer for meeting today’s and tomorrow’s challenges and market needs.

With the right digitalization and automation solutions, expertise won from practical experience, and a partnership approach that benefits all involved parties.

To explore these possibilities, we’re bringing together top-level speakers, specialists and decision-makers from various industries and experts from Siemens

to the Digital Enterprise Virtual Summit under the motto “Partnering for the next step.”   

READ MORE

 

Product News

  • Prev
Along developing exciting new products, POSITAL continuously updates its established product ...
Endress+Hauser’s new extremely compact Liquiline Mobile CML18 multi-parameter device provides ...
Maplesoft™ announced the release of MapleSim™ Insight, a new software product from Maplesoft that ...
To ensure the safety of lone workers at all times, companies depend on solutions that speed up ...
One of Yaskawa America’s top technical experts shows off the benefits of the company’s new Compass ...
The DURApulse GS20 Series of next generation high-performance vfd drives provides many standard and ...
More fully digital soft starters have been added to the AutomationDirect drives and motor controls ...
Yokogawa Test & Measurement Corporation announces that it has developed the AQ2200-212 sensor ...
The Mach 3 is designed for digitally sensitive applications and comes with added ...
nVent Electric plc, a global provider of electrical connection and protection solutions, recently ...

New Product


Maplesoft™ announced the release of MapleSim™ Insight, a new software product from Maplesoft that gives machine builders powerful, simulation-based debugging and 3-D visualization capabilities that directly connect to their automation tools. As a result, engineers can perform simulation-based testing of their controller easily and efficiently.

Simulation-based testing of machine control strategies is a key element of virtual prototyping and using digital twins for virtual commissioning. However, this step can be cumbersome, as many automation tools provide limited options for machine-level, simulation-based controller testing, and these options often require moving development to an entirely new platform.

Read More


 

Rittal & EPLAN Pump out a Powerful Solution for Metro Vancouver

Kerrwil Publications Great Place to Work. Certified December 2019 - December 2020

538 Elizabeth Street, Midland,Ontario, Canada L4R2A3 +1 705 527 7666
©2020 All rights reserved

Use of this Site constitutes acceptance of our Privacy Policy (effective 1.1.2016)
The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Kerrwil