Engineering Data Analytics

for Predictive Maintenance

23 April 2019 | 09.00 am-01.00 pm | @Maple Hotel, Bangna, Bangkok, Thailand

Limited Seats only!!

 

Ascendas Systems (Thailand) bring you solutions focus on Predictive Maintenance and how it efficiently helps in various Industries. In this seminar, our speakers will show how you can use MATLAB® and Simulink® from development to deployment.

Date: 23 April 2019 (Tuesday)

Time: 9:00am - 1:00pm

Venue: Maple Hotel, Srinakarin Road, Bangna, Bangkok, Thailand

 

Agenda

Duration

08.30-09.00 am

 

09.00-09.15 am

 

09.15-10.15 am

10.15-10.30 am

10.30-11.30 am

11.30-12.00 pm

12.00-13.00 pm

Session

Registration

 

 

Welcome Speech

By Khun Varatchaya Iamwilawan, Country Sales Manager - Ascendas Systems (Thailand)

 

Predictive Maintenance with MATLAB

By Mr. Watchara Toahngern, Application Engineer Thailand Team

Break

 

Predictive Maintenance using digital twins

By Mr. James Ang, Principle Application Engineer Thailand Team Leader

Q&A

Lunch

*The agenda may be subject to changes.

Synopsis

Topic 1 : Predictive Maintenance with MATLAB.

By Watchara Toahngern, Application Engineer

Companies that make industrial equipment are storing large amounts of machine data, with the notion that they will be able to extract value from it in the future.  However, using this data to build accurate and robust models that can be used for prediction requires a rare combination of equipment expertise and statistical know-how.

 

In this Seminar we will use machine learning techniques in MATLAB to estimate remaining useful life of equipment. Using data from a real-world example, we will explore importing, pre-processing, and labelling data, as well as selecting features, and training and comparing multiple machine learning models.  We will show how MATLAB is used to build prognostics algorithms and take them into production, enabling companies to improve the reliability of their equipment and build new predictive maintenance services.

Topic 2 : Predictive Maintenance using digital twins

By James Ang, Principle Application Engineer Team Leader (Thailand)

The industrial world is rapidly changing with the emergence of Industry 4.0 which encompasses the growing complexity of software and an ever-increasing amount of data.

The increasing code base on industrial systems is a challenge for classically trained engineers who rely on traditional methods for programming and testing. Also, sensors on modern equipment collect a significant amount of measured data which needs to be analyzed to gain knowledge about product quality, energy consumption, machine health status and other economically relevant parameters. This is where the use of machine learning algorithms e.g. for predictive maintenance is beneficial to derive actionable insights.

This second presentation shows how predictive maintenance algorithm can be developed using digital twin of hydraulic triplex pump modelled in Simscape. The predictive maintenance algorithm can detect which parts of the pump are failing simply by monitoring the pump output pressure.

The Simscape model of the pump can be configured to model degraded behaviour due to seal leakage, blocked inlets, bearing wear, and broken motor windings. The model can be used to generate training data for the machine learning algorithm and can be used to test the deployed algorithm.

Mechanical, hydraulic, and electrical parameters are all defined in MATLAB which lets you easily resize the pump. The pump housing is imported from CAD models.

Speaker Profile

James received his B.E degree in Mechanical Engineering from the University of New South Wales, Australia. He started his career at Panasonic Air Conditioning Research and Development Centre working on the development of Europe Inverter Heat Pumps. There he conducted laboratory experiments and controls design for performance optimisation. After moving to Techsource in 2010, James joined the Application Engineering team and worked across multi-engineering disciplines. James’ areas of expertise are in Control Systems, Physical Modelling, and Real-time Control. His current interests include Machine Learning, Deep Learning, and Robotics.

Watchara received his Master Engineering degree in Electrical and Information Engineering from the King Mongkut’s University of Technology Thonburi, Thailand. And He started his career at Trinergy Instrument working on the Software Developer position. There he has 5 Year experience for Automate Test & Measurement System Design. After moving to Ascendas in 2018, Watchara joined the Application Engineering team and worked across multi-engineering disciplines. Watchara’ areas of Interested are in Physical Modelling, Machine Learning and Deep Learning, Image processing & Computer vision.

Venue

Maple Hotel
9 Srinakarin Road, Bangna, Bangna, Bangkok 10250 Thailand
www.maple-thai.com 

This seminar is free, but registration is required.