Bigger wins!

Strengthen the business impact

delivered by predictive analytics

Click here for upcoming PAW events

Full Agenda – Manufacturing June 20-23, 2016

  Day 1: Tuesday, June 21, 2016

All Sessions are in Room: Salon A4. All Breaks are in Room: Salon A Pre-function

8:00-8:45am • Room: Salon A Pre-function

Registration & Networking Breakfast


8:45-8:50am

Conference Co-Chairs Welcome

Bala Deshpande
Founder
SimaFore

Jon Riley
Vice President, Digital Manufacturing
National Center for Manufacturing Sciences

[ Top of this page ] [ Agenda overview ]


8:50-9:10am

Diamond Sponsor Presentation
Connected Data Platforms for Smart Manufacturing

The next frontier for step change manufacturing process improvement requires a single holistic view of all aspects of the process in order to proactively monitor and detect variability and initiate corrective action before yield and quality are compromised. This session will focus on connected data platforms for data at rest and data in motion, to establish a complimentary single view of data across all aspects of the the process, for Predictive Analytics and step change process improvement.

Grant Bodley
GM Global Manufacturing & Automotive Solutions
Hortonworks

9:10-10:00am

Keynote
Fault Prediction and Failure Detection using Big Data and Predictive Analytics

A 1% reduction in maintenance costs can result in tens of billions in savings for manufacturing industry. Today we have the capability to collect and store all the data the machines and products can throw at us. But we will need to think differently if we want to successfully translate the wins from predictive modeling to machine data. This talk will provide a broad overview of the challenges coming from variety, structure and quality of data that data scientists need to manage to produce actionable analytics.

Bala Deshpande
Founder
SimaFore

[ Top of this page ] [ Agenda overview ]


10:00-10:30am • Room: Salon A Pre-function

Exhibits & Morning Coffee Break


10:30-11:15am

Failure Detection, Fault Prediction, Predictive Maintenance
Case Study: Ford Motor Company
Decision Support for Uncertain Manufacturing Process Data Using Interval Regression Analysis

Data generated from manufacturing processes often contain uncertainties. Resistance spot welding (RSW) is a joining method widely used in automotive industries. RSW data has a significant uncertainty on the welding quality measure. Nugget width is often used to measure the quality of welding given a set of materials and welding conditions. The nugget width values (i.e., range) for a given input (i.e., non-range) are highly-variable. This study tackles this using interval regression analysis and model highly-variable resistance spot welding data. This study also discusses the results of interval regression analysis and ability to support making decisions with uncertain data.

Junheung Park
Data Scientist, Global Data Insight and Analytics
Ford Motor Company

11:20am-12:05pm

Failure Detection, Fault Prediction, Predictive Maintenance
Case Study: Applied Research Labs
Using Vehicle Digital Bus Data for Predicting Failure of Line Haul Trucks

This presentation will discuss the development of prediction analytics for the failure of line haul trucks using available vehicle digital data bus data. The approach essentially mapped multiple channels of low bandwidth (< 10 Hz) sensor data into a subspace that produced more distinct characteristics to the changing behavior of the vehicle. The subspace data was compared across multiple vehicles. When several vehicles had a series of consecutive similar subspace mappings, the vehicles were considered to be experiencing similar system health degradation. The results represent anecdotal evidence that estimating the next potential maintenance action of a vehicle is feasible.

Jeffrey Banks
Department Head, Complex Systems Engineering & Monitoring
The Pennsylvania State University

12:05-1:30pm • Room: Salon A Pre-function

Lunch in the Exhibit Hall


1:30-2:15pm

KEYNOTE
Predictive Analytics and Smart Manufacturing

This talk will describe the objective of the "smart" manufacturing design and analysis program at NIST. The research focus is to develop and deploy advances in cyber-physical infrastructure (multi-stack reference architecture), modeling methodology for system integration, standards, methods, and protocols for real-time data analytics, and, metrics and assessment methods that will assure the performance (agility, asset utilization, and sustainability) of dynamic production systems. To address the industry needs, our research focus was on developing measurement science-based methodology to enable prediction of the energy and material footprints at the factory level for gate-to-gate life cycle impacts with uncertainty quantification.

Sudarsan Rachuri
Federal Program Officer, Advanced Manufacturing Office
Office of Energy Efficiency and Renewable Energy, Department of Energy

[ Top of this page ] [ Agenda overview ]


2:15-2:35pm

Sponsor Presentation
Monetizing the Trillion Dollar Opportunity in Industrial IoT

As organizations compete with each other for driving amazing experiences for the 21st century digital customer, they are inundated with data explosion. With the much predicted shortage of data scientists and complexities of diverse tools, the call of the hour is cognitive data science. In this session, Ruban Phukan will outline how cognitive data science empowers companies to build data products to monetize the trillion dollar opportunity in Industrial IoT by discussing diverse use cases to demonstrate how machines and data can generate insights for strategic advantage.

Ruban Phukan
CoFounder & Chief Products and Analytics Officer
DataRPM


2:40-3:25pm

Smart Manufacturing
Case Study: Elmet Technologies
Improved Statistical Process Control of Mature Manufacturing Processes Using Multiple Available Data Streams

Mature manufacturing processes present complex problems in data collection, integration and analysis to create process controls algorithms and models. Process measurements such as pressure, temperature and stress are generally collected by a multitude of sensors and dumped into separate data silos without any horizontal integration. Manufacturing processes in this control regime are basically out-of-control and have a high potential to result in expensive scrap product events. Multiple production process runs were modeled using available parameters data sets. The results are used to optimize refractory metal reduction processes and near net sample metallurgical applications.

Peter Frankwicz
Senior Process Engineer
Elmet Technologies

[ Top of this page ] [ Agenda overview ]


3:25-3:55pm • Room: Salon A Pre-function

Exhibits & Afternoon Break


3:55-4:40pm

Data Science for Manufacturing
Case Study: The Data Incubator
Data-Driven Hiring of Data Scientists for Manufacturing

Hiring, even for data scientists, is often not very data driven. At The Data Incubator, we run a fellowship to train and place data scientists in industries like manufacturing. We regularly receive over 2000 applications per session. To cope, we have to rely on robust analytics and machine-learning for our admissions process to ensure we are finding the best talent for our hiring partners. We’ll explain why most traditional keyword-driven screening processes do not work for finding data science talent and how to both streamline and build an automated data-driven screening process that filters for skills and talent.

Michael Li
CEO
The Data Incubator

[ Top of this page ] [ Agenda overview ]


4:45-5:30pm

Data Science in Manufacturing
Case Study: Seagate Technology
Building a Predictive Analytics Organization

The Data Science division at Seagate is just over a year-old now and we have learned a lot in that time. We will present the approach this new team is taking in building the organization, project management, partnering with IT, convincing engineers they really do need our help and the surprising pull from the business side of the company.

This will involve discussions on our overall structure utilizing CRISP-DM, the organizational approach that supports this, the efforts to communicate outward with Kansan dashboards, the approach to launch through internal marketing, engagement with key internal partners, top level non-specific views of our key projects and the achieved and expected impact our team will have on the bottom line for Seagate.

Chris Labbe
Managing Technologist
Seagate Technology

5:30-7:00pm • Room: Salon A Pre-function

Networking Reception

[ Top of this page ] [ Agenda overview ]




  Day 2: Wednesday, June 22, 2016


All Sessions are in Room: Salon A4. All Breaks are in Room: Salon A Pre-function

8:00-9:05am

Registration & Networking Breakfast


9:05-9:10am

Conference Welcome

Bala Deshpande
Founder
SimaFore

Jon Riley
Vice President, Digital Manufacturing
National Center for Manufacturing Sciences

9:10-10:00am

Keynote
Changing the Way we Make Things: The Brilliant Factory

The presentation will provide a general overview of some of the main programs on-going in various GE businesses aimed at improving Design for Manufacturing as well as Manufacturing operations. The overall effort, known in GE as "Brilliant Factory" and closely reflects what is called in the general industry as "Smart Manufacturing" will change the way we make products.

Matteo Bellucci
Manager, Process System Lab
General Electric

[ Top of this page ] [ Agenda overview ]


10:00-10:45am

Big Data in Manufacturing and Supply Chains
My Supply Chain and Customer Service Is A Mess: Using Predictive Analytics, Big Data and Machine Learning To Fix It

Come and Learn how integrating predictive analytics, big data and machine learning into your operations can help optimize and manage supply chain, plan operations and organize logistics. See case studies about how the largest food manufacturer in the world and a global telecommunications company used a blended combination of customer service analytics, inventory planning and optimization, new product forecasting, and demand signal analytics to increase customer satisfaction to over 95% and also save over $100M.

Joseph Brandenburg
CEO and Chief Data Scientist
Analytics4Retail

10:45-11:15am

Exhibits & Morning Coffee Break


11:15am-12:00pm

IoT and Analytics
Manufacturing and the State of Cybersecurity

Today's industrial manufacturing is increasingly connected with supply chains, industrial controls systems, energy grids and customers. While productivity opportunities are tremendous, cybersecurity should be a concern for every company. Anything that can be connected can be hacked, compromising productivity and growth. With connected, smart manufacturing cyber-security for industrial control systems is no long an option it is a business imperative. Manufacturers must protect the integrity of their systems, supply chains and products in order to safeguard customers and brand. This session will explore the current manufacturing landscape as well as threats, opportunities and resources

Rebecca Taylor
Senior Vice President
The National Center for Manufacturing Sciences

[ Top of this page ] [ Agenda overview ]


12:00-1:00pm

Lunch in the Exhibit Hall



1:15-2:00pm

Keynote
Internet of Things and the Cybersecurity Challenge

The Internet of Things allows data collection, monitoring, decision making, and process optimization using networks of low cost sensors and actuators. For manufacturing, better decision making and automation help optimize asset utilization and supply chain functions. The potential value of leveraging predictive analytics in IoT for manufacturing is very significant. However, there are barriers to achieving this potential, notably cybersecurity as data confidentiality, integrity, and availability are critical. We will look at ways to apply lessons learned from large-scale analytics in secure environments to this new frontier.

Thomas Bui
Enterprise Technology Leader, Cybersecurity Domain
The Boeing Company

2:00-2:10pm

Lightning Round

Dell   IBM

2:15-3:00pm

Analytics in Manufacturing Supply Chains
Predicting Behavior In Chemical Industry Supply Chains

Manufactured chemicals are found in nearly every product around us - they are core to our economy. Large chemical companies can have tens of thousands of customers and vendors. As integrate their supply chain with their customers and suppliers to gain supply chain efficiencies, a related benefit is better data visibility and analytics. Analyzing this detailed supply chain data across companies and across supply chain echelons provides detailed descriptive and predictive insights.

Gary Neights
Senior Director
Elemica

[ Top of this page ] [ Agenda overview ]


3:00-3:30pm

Exhibits & Afternoon Break


3:30-4:15pm

IoT and Industrial Internet
Case study: The Photizo Group
Predictive Analytics - What is 2% Worth

How can even small improvements in operational efficiency, as small as 2% drive massive gains in profitability. Lessons learned from one of the most highly connected, IoT enabled industries.

Edward Crowley
CEO
Photizo Group, Inc.

4:20-5:05pm

Predictive Maintenance
Manufacturing Analytics at Scale: Data Mining and Machine Learning Inside Bosch

Bosch is a global leader in manufacturing. Our products span a wide range of industries, including sensors, automotive parts, home appliances, power tools, security systems, Internet of Things, and more. Bosch has established a centralized data science team tasked with increasing revenue and decreasing costs for Bosch. I will present some successful use-cases from the manufacturing domain including: test-time reduction, inline defect identification, and root-cause analyses that leverage big-data tools and advanced analytics.

Carlos Cunha
Senior Data Scientist
Robert Bosch, LLC

[ Top of this page ] [ Agenda overview ]

Share |

Co-located with
PAW Chicago
Text Analytics World
The eMetric Summit

Thank you to our 2016 Sponsors

Hortonworks

Dell Statistica
IBM

ADVZOR
DataRPM
ESI
Information Builders
Minitab

PAtimes

Blog Partners
© 2019 Predictive Analytics World | Privacy
Produced by Prediction Impact, Inc. and Rising Media, Inc.

Predictive Analytics Company           Predictive Analytics Event Producer