Industrial Internet, predictive analytics, new machine-human collaboration

Industrial Internet, predictive analytics and new machine-human collaboration in the workplace can significantly boost productivity, create new jobs and skills, and minimize unplanned downtime in major industries, GE said, with the potential to save on more than 300 million hours in servicing complex machines. GE released 14 predictive software technologies to help with that and reduce emissions as well. See comments from industry leaders, photos, and info graphic.

10/10/2013



Panel of industry leaders listens as GE chairman and CEO, Jeff Immelt (far right), reviews how GE leadership has received additional education in analytics at the second annual Minds + Machines conference, Oct. 9, in Chicago. Courtesy: CFE MediaBusiness and technology leaders can implement solutions to improve efficiency and ultimately create smarter, faster, and more predictive solutions to improve productivity, efficiency, and reliability, according to Jeff Immelt, GE chairman and CEO, at the GE Minds + Machines 2013 conference in Chicago. At last year’s conference GE (NYSE: GE) announced the launch of its portfolio of industrial Internet solutions. Launched in January, GE’s Grid IQ Insight—a predictivity solution for the electric utility industry—was among the first solutions rolled out as a part of GE’s expanding portfolio of industrial Internet solutions. The advanced analytic solution helps utilities turn mounds of data into actionable information, Immelt said. Comments follow below from leaders presenting at the conference.

Jeff Immelt, GE chairman and CEO, describes how GE is focused on outcomes for customers, at the Minds + Machines conference, Oct. 9, in Chicago. Courtesy: CFE Media, Steve RourkeToday’s electrical distribution systems continue to evolve as new smart devices are added to the network. With each installation comes the capability to better monitor and report important data related to energy usage, outages, and changes in demand. This mass influx of raw data has led to a major void that must be addressed—data is currently being generated exponentially faster than it can be analyzed. To fill this void, utility companies often search for software that can help break down data from sensors and smart devices to find value hidden in a sea of raw data, GE said.

Grid IQ Insight provides utilities with advanced analytic capabilities to meet business needs and create a stronger connection to the machines that power the grid, the company said. It applies proven analytics to make sense of big data collected from intelligent machines to better predict, manage, model, and forecast potential problems that a utility’s electrical grid may face, GE said. The software strategically monitors influential data—such as electrical usage, grid performance, and weather history—creating an interconnected “ecosystem” of people and machines to better equip utilities with the information and tools needed to optimize use of electrical distribution systems. Utilities can then apply the information and knowledge gained through Grid IQ Insight’s advanced analytics and visualization to ensure a more efficient and reliable energy supply to customers.

“Making sense of grid data can be both a challenge and an opportunity,” said Michael Carlson, general manager—software solutions, GE’s Digital Energy business. “Applications like Grid IQ Insight are contributing immensely toward the emergence of the industrial Internet. These innovations will enable the integration of people, machines, and big data with analytics, creating a living network of information capable of developing more reliable and efficient energy solutions in the future.”

Social data integration

One way GE’s Grid IQ Insight connects minds and machines is through its capability to monitor social media for outage information. Daily, approximately 500 million registered Twitter users generate more than 340 million tweets, according to GE-cited sources. That immense amount of content translates to about 320,000 daily tweets from a typical utility’s customer base. Grid IQ Insight software can analyze social content to identify postings that can help locate a trouble spot or outage in a utility’s electrical distribution system, GE said. In many cases, the outage location can be detected before the first customer calls the utility to report a problem.

GE’s industrial Internet solution, Grid IQ Insight, helps mesh intelligent machines, people, data, and advanced analytics, transforms large amounts of raw data to easily digestible and useful information, and has social media monitoring capabilities.“GE’s Grid IQ Insight software can play an invaluable role during and after a storm or natural disaster has occurred,” Carlson continued. “For example, weather-related shocks to the grid can be greatly improved and expedited through Grid IQ Insight’s ability to monitor social media content through the peak of the storm—and in its aftermath. The software rapidly sorts through content to find out what areas are hit the hardest and are in need of immediate power or help. The ability to harness and disseminate this information to utility command centers can help restore critical power in a way that would have been unimaginable just years ago. The information and intelligence brought to light by the Grid IQ Insight software make it a truly brilliant solution.”

In addition to analyzing outage data in the wake of a storm, Grid IQ Insight is designed to provide crucial information regarding renewable energy generation. While renewable energy provides clean energy to the grid, it can be hard to supply guaranteed power due to the variability of the weather. Grid IQ Insight combines past, present, and future weather patterns and forecasts to help maximize the amount of renewable energy a facility can integrate into the grid. GE’s grid analytics software allows utilities to optimize which source of power is most efficient at a given time. Combining this energy with the readily available power from traditional power generation facilities helps to establish an efficient reliable electrical grid.

GE’s Digital Energy business provides protection and control, communications, power sensing, and power quality solutions. Its products and services are said to increase the reliability of electrical power networks and critical equipment for utility, industrial, and large commercial customers. From protecting and optimizing assets such as generators, transmission lines and motors, to ensuring secure wireless data transmission and providing uninterruptible power, GE’s Digital Energy business delivers industry-leading technologies to solve the unique challenges of each customer.

GE’s industrial Internet solution, Grid IQ Insight, helps mesh intelligent machines, people, data, and advanced analytics, transforms large amounts of raw data to easily digestible and useful information, and has social media monitoring capabilities.Presentations: Get analytics

At the meeting, Immelt noted that in the future the “Physical and analytical worlds must come together.” GE industrial Internet goals focus on customers’ outcomes. Repeatability and speed are critical, and world-class partners will be included to support customers’ solutions with offerings that drive growth, increase customer value, and transform the GE services businesses. Brilliant machines, advanced analytics, and higher productivity for people with mobility solutions will help, Immelt said.

The GE Predix industrial strength platform connects machines, sensors, and analytics to extract more value from big data. Partners include Intel, Accenture, Amazon web services group, Pivotal (analytics), Cisco, Kaggle, and AT&T. He expects lots of investments in manufacturing and industrial Internet. He noted that 10,000 technology engineers are working on new innovations, including what will soon be 1,000 in Silicon Valley.

Within industry, uptime and asset optimization are increasingly important, Immelt said, and there’s an increasing need for people and processes to accurately analyze and optimize huge amounts of data. For example, in the oil industry, a double ram blowout preventer (which weighs in at 50,000 lb, used at 12,500 ft underwater) has 30 sensors producing 200,000 data points daily.

Florian Zettelmeyer, MIT Graduate, professor, and director of the Center for Data Analytics, Kellogg School of Management at Northwestern, also emphasized that businesses need to adjust their processes and understand analytics. They need to empower people to better understand what’s going on in real time by measuring the right things. Data scientists, experts in analysis, are in great demand and can help with what questions to ask, meaning of data, and how to link causes and effects.

Zettelmeyer offer four ways to make the industrial Internet work more effectively: 1) share information; 2) use data in new ways; 3) start in byte sizes; and 4) scale to opportunities.

Bill Ruh, vice president of GE Software, noted that GE has 24 GE software solutions that can help, including 14 new ones introduced Oct. 9. Andy Geisse, CEO of AT&T Business Solutions, said more than 1 billion devices now are connected via networks. Guido Jouret, vice president and general manager of Internet of things (IoT) for Cisco, said more machines will be interconnected than people and will include self-regulation capabilities due to the sheer number of machines. Hank Skorny, vice president and general manager of Intel Services Division, said Intel opened a software division a little over two years ago given the understanding of how important of role software will play in the future. Challenges for large-scale adoption and cross-device communication include a lack of common language for communications. He said Intel recently introduced low-power, small-sized Quark chips, for use in very small, or mobile systems (including on a person or in a moving machine.)

Smarter grid

In discussions about GE Grid Insights software, Mike Bahorich, executive vice president and chief technology officer, Apache Corp., an oil and gas exploration company, said just 1% savings in processes could results in $35 billion saved. Because of the operating environment, it’s critical for Apache to “let software and sensors do some of the worrying or thinking for us.”

Sonja Indrebo, chief information officer and senior vice president IT for Statoil, said it’s important to bring technology and IT together in smarter ways. Information security is key, she said, as more system openness increases encounters with security issues. Monitoring offshore fields from on-shore locations can bring the offshore problems to people rather than requiring people to go to the problems, which can be safer and more cost effective. In big data, Statoil is looking at current and historical data to help improve processes and analyze oil and gas discovery, using technologies to help identify new drilling locations more effectively.

Dr. Peg Van Bree, CEO of St. Luke’s Medical Center, said communications technologies help improve processes, with ideas coming from workers of all levels and roles. Technologies can help hospitals be more efficient, tracking patients and equipment to shorten stays when it makes sense and improve outcomes. Big data analytics can have a dramatic improvement in determining what and how to change to optimize the hospital of the future.

Terry Donnelly, executive vice president and chief operating officer of Commonwealth Edison, said the digital environment will help ComEd’s 4 million customers. Thousands of electrical substations will be digitized; field and line personnel will use visualization tools to work more closely with operations; downtime will decrease; and GE smart meters are already helping with outage detection and increasingly will provide valuable usage information. Control rooms are using big data tools for real-time electronic communications, and have migrated away from older technologies including paper maps.

Jim Compton, vice chairman and chief revenue officer for United Airlines, said the airline business is all about optimization, since seats are perishable product, downtime is critical, and the largest operating cost is fuel. He noted that the digital nature of the Boeing 787 airplane represents a revolutionary, not evolutionary, move that required many new processes. In comparison, the Boeing 787 has 300 software loaded parts and the Boeing 777 has 100 software loaded parts. For United, big data will help e-commerce, in connecting with customers and driving revenue.

In Immelt’s closing remarks, he emphasized the need for companies to provide additional training for leadership teams on the importance of analytics and how to effectively use analytics to evaluate everything from people to their systems.   

Survey: More help is needed

Kate Johnson, GE vice president and chief commercial officer for enterprise solutions, reviewed answers to questions asked of the audience (perhaps 300 managers).

• Is your company using predictive analytics to drive operational efficiency?

28% No, but we want to

60% Yes, but in limited scope

13% Yes, we use extensively

• Does your company partner with vendors based on service outcomes?

51% No, we’re not ready

24% Yes, but our partners are not ready

24% Yes, we have outcome sharing partnerships in place today

Key concepts, in review

Industrial Internet solutions like GE’s Grid IQ Insight:

• Help mesh intelligent machines, people, data, and advanced analytics software

• Transform large amounts of raw data to easily digestible and useful information

• Identify outage locations more quickly with social media monitoring capabilities.

- Edited by Mark T. Hoske, content manager, CFE Media, Control Engineering, Plant Engineering, and Consulting-Specifying Engineer, mhoske(at)cfemedia.com, with info from GE and CFE Media’s Steve Rourke.

ONLINE

www.gedigitalenergy.com 

www.ge.com 



Jonas , , 11/10/13 08:36 AM:

From my perspective of process control, I personally agree technologies are the basis for the solutions that boost productivity, minimize unplanned downtime through greater reliability by detecting deteriorating performance by predicting the onset of failure before actual breakdown, and reduce emissions through improved energy efficiency etc.

I also agree raw data has to be turned into actionable information

Getting the raw data from which actionable information can be distilled to support decision making requires more sensors and smarter devices, so I also agree sensors and devices have to be added to a network. Modern cars and airplanes are massively multi-networked; integrating 2X or 3X as many sensors as only a few years ago, why should modern plants be any different? FOUNDATION fieldbus and WirelessHART are technologies ideal for building smarter plants. Digital networks also make it easier to add more sensors later as plants discover additional measurements are required. WirelessHART is the simplest way of modernizing an existing plant.

A complementary way to cope with lots of data is what I would like to call “real-time analytics”; for instance in the world of process automation there is now asset management systems with expert software having algorithms that monitor the readings from multiple sensors on a piece of process equipment like a heat exchanger, pump, blower, air cooled exchanger, cooling tower, even critical steam traps etc. determining its health in real-time. This helps maintenance to improve reliability and increase energy efficiency, as well as improving HS&E. See the blog post from this user conference:
http://community.emerson.com/process/emerson-exchange/b/weblog/archive/2013/10/03/why-are-there-missing-measurements.aspx

Think of it as real-time decision-making based on real-time information, rather than the typical reliance on historical data. “Big Data” is about analyzing historical data to find patterns. Real-time data processing is a different, complementary field. I personally think the processing of real-time RAW DATA into INFORMATION shall be close to the source, in the intelligent devices themselves where possible. Further processing is done in software as the information percolates up. Reducing the entropy of information till we get KNOWLEDGE:
http://www.isa.org/Template.cfm?Section=Technical_Paper_Collections&template=/Ecommerce/ProductDisplay.cfm&ProductID=5225
If you analyze the raw data in real-time you don’t have to store mounds of the individual pieces of raw data, only the distilled information, but of course you can still store the raw data, perhaps in the “cloud”, if you later like to analyze the “big data” to reveal or correlate hidden long-term patterns.

A pump becomes a “smart pump” when it is fitted with all the sensors enabling software to tell operations if it has vibration or overheating problems and other issues

Digital communications and wireless data transmission is key to efficiently bringing in data from more sensors and smarter devices also in the process industries

Equipment in the process industries will also have more sensors on them, generating more data points, and digital networks at the sensor level is the most efficient way to bring the data in so it can be analyzed in software

By measuring the right things and having software analyze that data, thus bringing the data and information to the people, rather than people going to the field to collect the data, tasks that used to take a long time can now be done in real time

In the process control world, smarter plants start with digital cross-device communications from the very “first meter”; at the sensor level. Unlike the higher levels of the automation hierarchy where there are many protocols, at the sensor level there are just a few real-time digital communication protocols that are taking the place of 4-20 mA and on/off sensor signals in the process industries, a common language; FOUNDATION fieldbus for wired networks and WirelessHART for wireless networks.

I agree we should let software and sensors do the heavy lifting

Communication technologies like fieldbus and wireless sensor networks help workers in process industry plants become more efficient; those in operations, maintenance, and other roles

Process plants will also be digitized. Major energy producers like BP, Chevron, Shell, Saudi Aramco and Reliance etc. are already creating digital environments in their new plants. Fieldbus technology has, much thanks to them, been refined over the years now becoming more mature and easier to use to the point where smaller plants can also adopt digital communication networks at the sensor level instead of hardwired analog 4-20 mA and discrete on/off signals, That people are increasingly familiar with computers, software, and networks from daily life or course also helps.

WirelessHART technology
http://www.hcf-files.com/webasyst/published/DD/2.0/file_link.php?sl=2ddbeee7c953e420bdcc7da6ee5f2b8d&DB_KEY=V0VCRklMRVM%3D

FOUNDATION fieldbus technology
http://www.fieldbus.org/images/stories/technology/aboutthetechology/overview/fieldbus_brochure.pdf

The digital nature of networked process control instrumentation like flowmeters and control valves enables centralized diagnostics from intelligent device management (IDM) software. This enables maintenance personnel to determine if a flowmeter needs to be removed for calibration or if it can be left on the pipe for a while longer, or if a control valve needs to be pulled for service or if it can remain on the pipe until the next turnaround. This results in longer “time on pipe” for the instrumentation, and thus less downtime in the plant. New processes are required to take advantage of the new intelligence, but some work is already available:
http://www.eddl.org/DeviceManagement/Pages/DeviceDiagnostics.aspx#Institutionalizing

There is also standardization work ongoing for these work processes:
http://www.isa.org/isa108/

That is; more sensors to generate the data, digital networks to transmit the data, and software to distill the raw data into actionable information.
The Top Plant program honors outstanding manufacturing facilities in North America. View the 2013 Top Plant.
The Product of the Year program recognizes products newly released in the manufacturing industries.
The Leaders Under 40 program features outstanding young people who are making a difference in manufacturing. View the 2013 Leaders here.
The new control room: It's got all the bells and whistles - and alarms, too; Remote maintenance; Specifying VFDs
2014 forecast issue: To serve and to manufacture - Veterans will bring skill and discipline to the plant floor if we can find a way to get them there.
2013 Top Plant: Lincoln Electric Company, Cleveland, Ohio
Case Study Database

Case Study Database

Get more exposure for your case study by uploading it to the Plant Engineering case study database, where end-users can identify relevant solutions and explore what the experts are doing to effectively implement a variety of technology and productivity related projects.

These case studies provide examples of how knowledgeable solution providers have used technology, processes and people to create effective and successful implementations in real-world situations. Case studies can be completed by filling out a simple online form where you can outline the project title, abstract, and full story in 1500 words or less; upload photos, videos and a logo.

Click here to visit the Case Study Database and upload your case study.

Why manufacturers need to see energy in a different light: Current approaches to energy management yield quick savings, but leave plant managers searching for ways of improving on those early gains.
Electric motor power measurement and analysis: Understand the basics to drive greater efficiency; Selecting the right control chart; Linear position sensors gain acceptance
Protecting standby generators for mission critical facilities; Selecting energy-efficient transformers; Integrating power monitoring systems; Mitigating harmonics in electrical systems

Annual Salary Survey

Participate in the 2013 Salary Survey

In a year when manufacturing continued to lead the economic rebound, it makes sense that plant manager bonuses rebounded. Plant Engineering’s annual Salary Survey shows both wages and bonuses rose in 2012 after a retreat the year before.

Average salary across all job titles for plant floor management rose 3.5% to $95,446, and bonus compensation jumped to $15,162, a 4.2% increase from the 2010 level and double the 2011 total, which showed a sharp drop in bonus.

2012 Salary Survey Analysis

2012 Salary Survey Results

Maintenance and reliability tips and best practices from the maintenance and reliability coaches at Allied Reliability Group.
The One Voice for Manufacturing blog reports on federal public policy issues impacting the manufacturing sector. One Voice is a joint effort by the National Tooling and Machining...
The Society for Maintenance and Reliability Professionals an organization devoted...
Join this ongoing discussion of machine guarding topics, including solutions assessments, regulatory compliance, gap analysis...
IMS Research, recently acquired by IHS Inc., is a leading independent supplier of market research and consultancy to the global electronics industry.
Maintenance is not optional in manufacturing. It’s a profit center, driving productivity and uptime while reducing overall repair costs.
The Lachance on CMMS blog is about current maintenance topics. Blogger Paul Lachance is president and chief technology officer for Smartware Group.