AI Research For Tomorrow’s Production

While at the Hannover Messe Preview last week in Germany, I talked with the representatives of a German consortium with the interesting name of “it’s OWL”. Following are some thoughts from the various organizations that compose the consortium.

Intelligent production and new business models

Artificial Intelligence is of crucial importance for the competitiveness of industry. In the Leading-Edge Cluster it’s OWL six research institutes cooperate with more than 100 companies to develop practical solutions for small and medium-sized businesses. At the OWL joint stand (Hall 7, A12) over 40 exhibitors will demonstrate applications in the areas of machine diagnostics, predictive maintenance, process optimization, and robotics.

Prof. Dr. Roman Dumitrescu (Managing Director it’s OWL Clustermanagement GmbH and Director Fraunhofer IEM) explains: “Our research institutes are international leaders in the fields of machine learning, cognitive assistance systems and systems engineering. At our four universities and two Fraunhofer Institutes, 350 researchers are working on over 100 projects to make Artificial Intelligence usable for applications in industrial value creation. With it’s OWL, we bring this expert knowledge into practice. In 2020, we will launch three new strategic initiatives worth 50 million € to unlock the potential for AI in production, product development and the working world for small and medium-sized enterprises.”

In the initiative ‘AI Marketplace’ 20, research institutes and companies are developing a digital platform for Artificial Intelligence in product development. Providers, users, and experts can network and develop solutions on this platform. In the competence centre ‘AI in the working world of industrial SMEs’, 25 partners from industry and science make their knowledge of work structuring in the context of AI available to companies.

Learning machine diagnostics and ‘SmartBox’ for process optimization

The Institute for Industrial Information Technology at the OWL University of Applied Sciences and Arts will present new results for intelligent machine diagnostics at the trade fair. Using a three-phase motor, it will be illustrated how learning algorithms and information fusion can be used to reliably identify, predict, and visualize states of technical systems. Patterns and information hidden in time series signals are learned and presented to the user in an understandable way. Inaccuracies and uncertainties in individual sensors are solved by conflict-reducing information fusion. For example, motors can be used as sensors. Within a network of sensors and other data sources in production plants, motors can measure the “state of health” and analyze the causes of malfunctions via AI. This reduces scrap and saves up to 20 percent in materials.

The ‘SmartBox’ of the Fraunhofer Institute IOSB-INA is a universally applicable solution that identifies anomalies in processes in various production environments on the basis of PROFI-NET data. The solution requires no configuration and learns the process behavior.

With retrofitting solutions of the Fraunhofer Institute, companies can prepare machines and systems in their inventory for Industrie 4.0 applications without major investment expenditure. The spectrum ranges from mobile production data acquisition systems in suitcase format for studies of potential to permanently installable retrofit solutions. Intelligent sensor systems, cloud connections and machine learning methods build the basis for data analysis. This way, processes can be optimised and more transparency, control, planning, safety, and flexibility in production can be achieved.

Cognitive robotics and self-healing in autonomous systems

The Institute of Cognition and Robotics (CoR-Lab) presents a cognitive robotics system for highly flexible industrial production. The potential of model-driven software and system development for cognitive robotics is demonstrated by using the example of automated terminal assembly in switch cabinet construction. For this purpose, machine learning methods for environ- mental perception and object recognition, automated planning algorithms and model-based motion control are integrated into a robotic system. The cell operator is thereby enabled to perform different assembly tasks using reusable and combinable task blocks.

The research project “AI for Autonomous Systems” of the Software Innovation Campus Paderborn aims at achieving self-healing properties of autonomous technical systems based on the principles of natural immune systems. For this purpose, anomalies must be detected at runtime and the underlying causes must be independently diagnosed. Based on the localization it is necessary to plan and implement behavioral adjustments to restore the function. In addition, the security of the systems must be guaranteed at all times and system reliability must be increased. This requires a combination of methods of artificial intelligence, machine learning and biologically inspired algorithms.

Predictive maintenance and digital twin

Within the framework of the ‘BOOST 4.0’ project, the largest European initiative for Big Data in industry, it’s OWL is working with 50 partners from 16 countries on various application scenarios for Big Data in production. it’s OWL focuses on predictive maintenance: thanks to the systematic collection and evaluation of machine data from a hydraulic press and a material conveyor system, it is possible to identify patterns in the production process in a pilot company. The Fraunhofer IEM has provided the technological and methodological basis. And successfully so: over the past two years the prediction of machine failures has been significantly improved in this specific application by means of machine learning methods. The Mean Time To Repair (MTTR) has already been reduced by more than 30 percent. The Mean Time Between Failures (MTBF) is now six times longer than before. A model of the predictive production line can be seen at the stand.

The digital twin is an important prerequisite for increasing the potential for efficiency and productivity in all phases of the machine life cycle. Companies and research institutes are working on the technical infrastructure for digital twins in an it’s OWL project. Digital descriptions and sub-models of machines, products and equipment as well as their interaction over the entire life cycle are now accessible thanks to interoperability. Requirements from the fields of energy and production technology as well as existing Industrie 4.0 standards and IT systems are taken into account. This is expected to result in potential savings of over 50 percent. At the joint stand, Lenze and Phoenix Contact will use typical machine modules to demonstrate how digital twins can be used to exchange information between components, machines, visualisations and digital services across manufacturers. Interoperability proves for the first time how the combination of data can be used to create useful information with added value for different user groups. For example, machine operators and maintenance staff can detect anomalies and receive instructions for troubleshooting.

Connect and get started – production optimization made easy

The cooperation in the Leading-Edge Cluster gives rise to new business ideas that are developed into successful start-ups. For example, Prodaso—a spin-off from Bielefeld University of Applied Sciences—has developed a simple and quickly implementable solution for the acquisition and visualization of machine and production data. The hardware can be connected to a machine in a few minutes via plug-and-play. The machine data is displayed directly in the cloud.

Prodaso has succeeded in solving a central challenge: Until now, networking machines from different manufacturers have been complex and costly. The Prodaso system can be retrofitted to all existing systems, independent of manufacturer and interface. In addition, the start- up also provides automated analysis and optimization tools. This enables companies to detect irregularities and deviations in the process flow at an early stage and to initiate appropriate measures. The company, founded in 2019, has already connected approximately 100 machines at companies in the manufacturing industry.

​​​​Motor Drives Increasingly An Enabler of IoT Says Market Intelligence Firm

​​​​Motor Drives Increasingly An Enabler of IoT Says Market Intelligence Firm

Just before Thanksgiving, I had the opportunity to talk with Adrian Lloyd, CEO of Interact Analysis. Interact is a new market research and intelligence company composed of industry veterans of other firms. The company researchers perform many more interviews than the industry norm combining with deep regional manufacturing data in order to achieve better and more granular results.

Company CEOs provided insight to me years ago about the accuracy (or lack) of many market analyses. I’m always in search of better information. We’ll try this one.

Interact has just released two reports—low voltage AC drives and motion control.

2019 low voltage AC motor drives report from Interact Analysis

  • Decentralized and motor mounted drives to show the strongest growth
  • Danfoss overtook Siemens in 2018 to be number 1 drives supplier to the EMEA region
  • Cabinet mounted general purpose drives have largest percentage of sales by product type

The research shows that growth in the intralogistics and materials handling sector has led to increased demand for decentralised and motor mounted drives, leading them to show the strongest growth over the five-year forecast period out of all seven product types covered. Cabinet mounted general purpose drives account for nearly half of drive sales globally, but also represent the slowest growing product type.

Meanwhile, from a regional perspective, although ABB is the number 1 drives supplier on a global basis, Danfoss has overtaken Siemens to be number 1 in EMEA. The Americas is predicted to be the fastest growing drives market for 2019, while the market in EMEA is shrinking, and China continues to occupy the largest share of the market (43% by unit shipments in 2019).

Interact Analysis has pioneered a new forecasting approach that gives an unprecedented level of detail. For example, users could choose to view anticipated demand for drives under 2.2 kW in the Indian packaging market. This is possible because the report is underpinned by 12 years of data on industrial production (the value of goods produced) and machinery production (the value of the machines used to produce goods). This information comes from Interact Analysis’s Manufacturing Industry Output Tracker – a big data tool that aggregates national manufacturing surveys from all major manufacturing economies in a set of over 1.2 million datapoints.

Lloyd says of this report: “In 2018 average drive prices fell by 2.7% compared with 2017, and we expect this trend to continue. To compound this, 2019 is experiencing a slowdown in the market. Yet the drives industry has reason for positivity. And not just because we expect the market to rebound in 2020.

“The world is becoming increasingly automated – in fact it is becoming rare to open a national daily newspaper and not read something about how automation is impacting the economy. Automation growth sectors, such as eCommerce warehouses, are creating vast new opportunities for drives. In the longer run, it is very positive for drives manufacturers that our research shows drives buyers increasingly see drives as the front line of predictive maintenance and industrial IoT.

“Most drives reports model industry dynamics by simply comparing the growth of the drives market with the growth of the entire manufacturing sector. Ours is different. Interact Analysis’s Manufacturing Industry Output tracker compares the value of goods produced with the value of machines used to produce goods to give a whole range of fresh new insights unavailable in any other drives report.”

Motion Control Market to Exceed $15bn by 2023

New 2019 motion control market report from Interact Analysis reveals

  • Despite a short-term dip in 2019, longer term forecasts predict solid growth
  • Increased reliance on industrial robotics a significant contributor
  • Growth rate to exceed that of global manufacturing production by 2020

Interact Analysis has released a new market report – Motion Controls – 2019 – pointing to strong growth over the next four years for motion control products.

Despite a small decline in 2019 (-3.8%) the report outlines how the market for motion control products will grow strongly, ultimately exceeding $15bn in 2023. Also noteworthy is the firm’s belief that the motion control market will outpace growth of global manufacturing production from 2020 onwards. The positive outlook holds true despite the torrid time currently facing machine tool vendors which, as the single largest consumer of motion control products, generated over a third of motion control revenues in 2018.

Interact Analysis points to several sectors which are helping to drive a more positive outlook for motion controls. These include food & beverage machinery, packaging machinery, robotics and material handling equipment, especially equipment for warehouse automation and intralogistics. Together these sectors generated just under a quarter of total motion control revenues in 2018 and are forecast to account for closer to 30% in 2023.

The report outlines further factors strengthening the outlook for motion control demand, including the trend for decentralization. Here higher-protection ratings are helping to advance the market for particular motion products. Although even combined the opportunity is small compared to the total (representing only 2.4% of the global market in 2018), the findings show that revenues for both products are projected to experience higher growth than the rest of the market, driving their combined value to exceed $500m in 2023.

Geographically, six regions – China, USA, Japan, Germany, Italy and South Korea – will continue to dominate market revenues. China, in particular, is expected to add significant revenues over the next four years, making it almost twice as big as the United States. In industry terms, sectors utilising metal cutting tools remain the largest in revenue terms, however the strongest overall growth during the forecast period came from mobile robots and industrial robots, which are the only ones forecast to experience growth in 2019 versus 2018.

Tim Dawson, research director for Interact Analysis and principal analyst of the motion controls report, said: “Although the motion control market may be considered fairly mature there are important trends impacting its future growth helping drive revenues at an above average rate for the long-term. Couple that with product releases from new vendors, plus expanding portfolios from existing ones; and the fundamentals for this industry appear very strong, even despite headwinds in certain key sectors.”

Taking a Digital Journey

Taking a Digital Journey

Keynoters have a tough time with originality these Digital Days with everyone emphasizing Digital Transformation. Steve Lomholt-Thomson, chief revenue officer of AVEVA, took us on a Digital Journey this morning. Setting the tone of the three days of AVEVA World Congress (North America edition).

Three technology trends to watch: an IoT boom; cloud/empowered edge; and, AI / ML. The theme is digital. The Digital Organization discovers its Digital DNA, figures out how to build that Digital DNA through people who challenge the status quo; and then figures out how to track talent flow.

Which all starts us on our Digital Journey. On this journey, we unify end-to-end data, connect data silos taking an wholistic view of the business, and then visualize our assets and supply chain. I believe implied in all this is the company’s product AVEVA System Platform. The company touted six customer stories with at least five of them (and probably the sixth) all leveraging System Platform.

Oh, and the only time the “W” word was used referred to past tense.

Other areas of the company were highlighted:

Focus on assets–asset performance management including how to use machine learning (ML) and artificial intelligence (AI) for predictive analytics (predictive maintenance.

How to combine it all into a Digital Twin–bringing the design lifecycle and physical lifecycle into congruence.

Recently hired head of North America business, Christine Harding, interviewed customers from Campbell’s (soup/snacks), Quantum Solutions (integration project at St. Louis/Lambert airport), and Suncor (Canadian oil sands).

I have the rest of today and then tomorrow to take deeper dives into many of these topics. If there is anything you want me to ask, send a note.

​​​​Motor Drives Increasingly An Enabler of IoT Says Market Intelligence Firm

Predictive Software for Sustainable Hydro Power Generation

Moving to sustainable sources of energy to generate electrical power, as Europe has, requires a balancing act. Solar and wind generation provide an imbalance of power since they only operate when proper atmospheric conditions exist—i.e. sunlight or wind. Hydro generation provides a necessary balance, explained Pier-Vittorio Rebba, technology manager power generation for ABB.

But many hydro plants are aging. Management realizes the need to digitalize operations to obtain the best use of Asset Performance Management applications as well as best optimization of plant assets. ABB and its customer Enel Green Power partnered to digitalize operations delivering predictive maintenance solutions that will lower maintenance costs and transform the performance, reliability, and energy efficiency of its hydropower plants throughout Italy.

The three-year contract will enable 33 of Enel Green Power’s hydroelectric plants, comprised of about 100 units, to move from hours-based maintenance to predictive and condition-based maintenance, leveraging the ABB Ability Asset Performance Management solution. With operations in five continents, the Enel Group’s renewable business line, Enel Green Power, is a global leader in the green energy sector, with a managed capacity of more than 43 GW.

“We are privileged to be partnering with Enel Green Power, a digital pioneer, in their move from hours-based to predictive maintenance utilizing ABB Ability technologies for big data, machine learning and advanced analytics,” said Kevin Kosisko, Managing Director, Energy Industries, ABB. “Predictive maintenance and asset performance management must become a key component of plant operators’ strategies to optimize maintenance operations, minimize risk, improve resilience and reduce costs. The results are more competitive electricity rates, in a more sustainable way.”

Collaborating closely since early 2018, the two companies have jointly developed and tested predictive maintenance and advanced solutions (PresAGHO) via a pilot on five Enel plants in Italy and Spain, including Presenzano, a 1,000-megawatt plant near Naples.

The new contract includes digital software solutions and services that will provide analysis of over 190,000 signals and the deployment of about 800 digital asset models, aimed at improving plant operational performance, reducing unplanned failures and enabling more efficient planned maintenance practices through predictive maintenance. The integration is expected to yield savings in fleet maintenance costs and increase plant productivity.

The ABB Ability Collaborative Operations Center for power generation and water will help bring wider benefits of digitalization and engagement, supporting informed decision-making, real-time solutions and cost savings. The center already provides similar digital solutions and advanced applications for more than 700 power plants, water facilities and electric vehicle charging stations globally.

“With personnel retirements resulting in knowledge gaps and more competitive electricity marketplaces, we believe that many power generation customers globally can benefit from this kind of digital transformation around maintenance and operations,” said Mr Kosisko.

Gaining Business Benefits Through IoT and Edge Computing in Industry

Gaining Business Benefits Through IoT and Edge Computing in Industry

Fourth in the series of posts as I digest all of the information I gathered at Hewlett Packard Enterprise (HPE) Discover 2018 in Las Vegas. This post focuses on use cases. Yes, people, there are people some in manufacturing and some not who are using HPE IoT and Edge computing for fun and profit.

First off, a panel assembled by Tom Bradicich, VP and GM IoT and Edge and Ph.D. entitled Intelligence at the Edge.

Nathalie Elad of Comcast- We are an aggregator of data from homes sending this data from local server to cloud. He is working with HPE on virtualization. No, it doesn’t collect individual family usage to sell to others (yes, it came up). But the company does need data to know how to channel bandwidth. The challenge-“we double bits every 18 months and need to flex up and down during the day.” Interesting stat—there used to be 3.3 devices per house, now may be 20 or even 30.

Tim Thai, Tesla- OT—IT is still a challenge. “The Edge is dynamic, wherever business sets up shop.” Regarding IoT, there are “Things” in manufacturing-control and sensors. They incorporate sensors in testing of technology in cars. Not to mention “there are a ton of sensors in a car.”

Philip Rostle, Alfa Romeo Sauber F1 racing, discussed F1 race car as the edge. There are lots of channels coming off the car during a race. They measure performance versus predicted. You think you have connection problems, he described connection in race as “variable”. Every car has a GPS. They track all cars in the race trying to predict status of the other cars. They run scenarios, analytics, quickly at the edge during a race to help determine strategy. Took “moonshot” server power to the edge so that they get maximum performance within the rules of F1.

In a special breakfast session, we talked with the CTO of the Ryder Cup and European PGA Tour. Think you know golf? Ever wonder about some of the stats that the TV announcers can quote during an event? Well, the tour requires a lot of data. And to get that data, they need connectivity. Golf is also an entertainment event. There are 50,000 spectators at the Ryder Cup. They all expect WiFi to access real-time information about the tournament.

First the data. Every shot has a dozen parameters to capture for every golfer. These are logged on the course. To connect, they use Aruba wireless networking devices. There are 30 switches and 700 access points. They collect 20K data points for scoring; 140K data points for other shot information. “Data drives insights that leads to performance for golfers.” They can track each golfer and also track spectator traffic patterns. An untold story, they lay 18km of fiber cable each tournament; ready to go for Wednesday morning and tear down beginning Sunday evening.

Mike Orr, director of digital transformation at Murphy Oil, uses Edgeline on oil platforms. He noted that his biggest hurdle was working with IT mostly due to its legacy software systems. He made this technology economics point—when oil went from $140 to $20, company laid off many workers. The only way he could get his work done was with technology.

I’ve already discussed the Texmark Chemicals “Refinery of the Future” use case, but I learned a few additional points at this conference.

Intel supplied streaming video analytics—used for physical security/monitoring, open gate for railway access allowed humans and critters into the site, monitored for exception to alert operators.

Deloitte is developing an IoT practice. It assembled an ecosystem including NI, Allied, ThingWorx, OSIsoft, SparkCognition AI for pumps. It also developed the operator dashboards for the project.

All together there were 12 partners in the ecosystem that completed the project that included predictive maintenance for two critical pumps and the video surveillance system.

HPE coordinated the entire project.

The insurance company was impetus to do something to upgrade the technology. Texmark kicked off the project by renting a party bus and taking 15 employees to the HPE IoT lab in Houston. They saw a demo of a pump with FlowServe monitoring and analytics. Employees discussed and picked the initial project targets—two critical pumps in the process plus the “video as a sensor” for the railway access. Getting early employee involvement was the key factor for successful implementation.

Follow this blog

Get a weekly email of all new posts.