BusinessProcessConnection_webheaderFINAL.jpg

Download Full Day Schedule. (PDF)BP-PredictiveEngineering_PDF.jpg

REGISTER NOW!
Regular Rate $1,395
Late/Walk-in Rate $1,595

Volunteer_AdSample.jpg

Join us for this FULL DAY Predictive Engineering Analytics Series! | Thursday, May 11

“Predictive Engineering Analytics (PEA) is the application of multi-discipline simulation and test, combined with intelligent reporting and data analytics to develop digital twins that can predict the behavior of products across all performance attributes, throughout the product lifecycle.”
- Siemens PLM

Product development used to be straight forward - you created a design, built it, broke it, and redesigned it until you got it right. Today’s demand for quickly bringing complex, reliable products to market at lower cost is making a more integrated approach to design, testing, and simulation necessary. However, this approach is still working to catch up to the digital revolution. Today’s mindset is to design and then verify the design in isolation through simulation and test. This process is problematic because everyone is designing, building, and analyzing product modules in their own groups. When the various modules come together to create a complex system, problems are encountered. Earlier integration of product modules with the supporting simulation and test is required for more streamlined product development. Leveraging the product’s digital twin, a digital representation that can predict product performance, as a whole system, throughout each step of the development process, is one way to achieve this goal.

This Themed Connection will explore the tools and processes available for creating the digital twin through simulation, test, and data analytics. It will look into how the digital twin can be used to support the entire product lifecycle from conceptual design to product warranty. We will also discuss the real world challenges surrounding the use of those tools for improving product development. Finally, we will begin to explore future applications of predictive engineering analytics for design, manufacturing, and product maintenance.

TIME & TITLE SESSION DESCRIPTION

9:30-10:00 am
Predictive Engineering Analytics Series - Part 1

Siemens Simcenter strategy for Predictive Engineering Analytics

David Gillespie
Portfolio Development Executive
Siemens PLM Software

Ian McGann
Portfolio Manager
Siemens PLM Software

This session focuses on Siemens Simcenter strategy for Predictive Engineering Analytics. This strategy is based on the following key concepts: 1) predictive, meaning to be able to transition systematically from simulation that verifies designs to model based approaches that predict behavior, optimize designs and address integration and cross discipline issues early in the program cycle when changes to designs are least costly, 2) engineering, meaning that we focus on holistic engineering objectives that address a product’s functional requirements, and 3) analytics – using multi-physics, multi-attribute, and multi-discipline approaches, and incorporating big data analytics and field knowledge into the engineering process. We will address these topics, provide a Simcenter Portfolio overview, and review a process demonstrator showing systematic connectivity of simulation and data through a program life cycle.

MichaelCheung.jpg
DipenParikh.jpg

10:00-10:30 am
Predictive Engineering Analytics Series - Part 2

Leveraging Product Development Analytics

Michael Cheung
Deloitte Consulting LLP

Dipen Parikh Principal
Deloitte Consulting LLP

Many companies collect a wealth of data across functions and the value chain, but do not effectively transform it into actionable insights for their Product Development activities that drive significant value for on-going and future products. By leveraging advanced technologies, implementing a smart data model, and adhering to agile innovation principles, engineering organizations can shift to making insight-driven design decisions. These capabilities will generate design insights from traditionally disparate activities across the life cycle such as testing, simulation, maintenance, and actual customer usage. These design insights can be used to improve design objectives, predict failure modes, and better deliver the customer experience.

10:30-10:45 am BREAK
SudarshanDR.jpg

10:45-11:15 am
Predictive Engineering Analytics Series - Part 3

Leveraging PLM Analytics for Product Performance

SUDARSHAN D.R.
Senior Consultant
TATA CONSULTANCY SERVICES

Product quality and reliability being one of the most critical considerations towards establishing product brand, it's no wonder companies invest significantly toward ensuring the new product development imbibes a rigorous quality assurance program. Product performance needs to be closely monitored not just during the First Article Inspection or the initial batch, but quite a few ongoing production runs to infer failure modes from the early symptoms of product performance. Quality executives struggle with control charts, FMEA, six sigma analyses, while the design function strives to strike a fine balance on product cost with product specifications following tight tolerances on form, fit or function. It becomes imperative to analyze the data more closely – during manufacturing, service & support to strike this optimal balance.

How does one improve the predictability of product failures so timely corrective actions can arrest the catastrophic failure of the product, warranting total replacement? How can the periodic servicing operations be accurately tuned, to become timely and effective so as to avoid costly routines uncalled for in a seemingly healthy operating environment? What critical parameters need to be monitored closely to provide the early indications of an impending failure amongst several contributing factors?

How may one leverage PLM to manage the data along the complete lifecycle to provide the hints and pin point trouble candidates for early resolution and corrective action? This presentation takes into account a few industry examples of early product failures encountered and delineates an approach linking several enterprise systems including PLM with effective product analytics devised as part of an effective NPD process.

11:15-11:30 am BREAK
11:30-1:00 pm LUNCH

1:00-2:00 pm
Predictive Engineering Analytics Series - Part 4

Digital Design and Manufacturing Showcase Walk-through

2:00-2:30 pm BREAK

2:30-3:30 pm
Predictive Engineering Analytics Series - Part 5

Roundtable: Brainstorming Solutions for Better Use of Simulation, Optimization, and Test (Predictive Engineering Analytics) for Improved Product Design

Open discussion about the challenges facing companies in the area of predictive engineering analytics. The discussion will be split into four major topics, 25 min. each - 1) simulation, 2) testing in the digital world, 3) how digital representations are being used, and 4) the interactions between simulation, test, and digital models. The discussion will probe areas like are there fundamental issues with your current tools that are causing problems? What is preventing your company from streamlining its current processes? Are there data hand-off hurdles that are hurting your efficiency?

3:30-3:45 pm BREAK

3:45-4:15 pm
Predictive Engineering Analytics Series - Part 6

Roundtable: Brainstorming Solutions for Better Use of Simulation, Optimization, and Test (Predictive Engineering Analytics) for Improved Product Design (cont.)

Continue the open discussion about the challenges facing companies in the area of predictive engineering analytics. The discussion will be split into four major topics, 25 min. each - 1) simulation, 2) testing in the digital world, 3) how digital representations are being used, and 4) the interactions between simulation, test, and digital models. The discussion will probe areas like are there fundamental issues with your current tools that are causing problems? What is preventing your company from streamlining its current processes? Are there data hand-off hurdles that are hurting your efficiency?

Revised 3/23/17 | Schedule subject to change.