Progressively larger volumes of data smooth the path of machine learning for adoption in production operations
Between fascination and a slight uneasiness –that’s roughly the sort of subliminal reaction even experts occasionally feel when it comes to the subject of “artificial intelligence”. Autonomous robots, self-driving vehicles or cognitive systems that image the functioning of the human brain and are even able to checkmate a chess grandmaster, may trigger concerns regarding a loss of human control. As a key technology for Industry 4.0, self-learning systems can be expected to find their way into the factories, especially if they are introduced gradually and “in small digestible pieces”, and prove that money can be earned with them.
As a sub-category in the field artificial intelligence (AI), it’s primarily machine learning (ML) that’s relevant for industrial manufacturing operations. ML enables systems to understand their surroundings, to plan actions, to respond to impediments, and to communicate with humans. Machines use production data and intelligent algorithms to learn to recognise recurrent patterns and objects autonomously. The learned knowledge can then be applied to unknown and unsorted data. This enables sources of error be identified, processes to be planned and optimised, and forecasts to be drawn up.
Machine learning needs Big Data
The hype currently associated with machine learning, although the concept in actuality dates back to the 1980s, is due to the modern-day options for data processing. It was only with the advent of Big Data applications, high–performance computers and gigantic cloud memories that the appropriate infrastructure came into being, used primarily at first by the internet giants. But the industrial sector is following suit. “From the perspective of robotics, we are following very closely what players on the global market like Google and Amazon, with their IT competences and infrastructures, are developing and researching in regard to production technology,” confirms Prof. Jörg Krüger, Head of the Automation Technology Department at the Fraunhofer Institute for Production Systems and Design Technology (IPK) in Berlin. But the examples from the IT conglomerates cannot be adopted just as they are for industrial applications as well.
It’s true than many companies, especially large ones from the automation and control segment, have been infected by the “ML virus”. But in the view of sectoral pundits the use of machine learning in the industrial segment is in many cases still in its infancy. This appraisal should not be obscured by spectacular demonstrations, e.g. when IBM impresses the public with its Watson system in the Cognitive Factory. Or when Festo, with fascinating exhibits like the very recent “elephant’s trunk”, an intelligent bionic handling assistant, answers the question of how people in the factories of tomorrow can interact with their machines simply, efficiently and above all safely. The technology exists. It’s exciting, and stimulates the imagination, but translating it into real products capable of delivering sales and profits will probably take some years yet.
SMEs and start-ups – the ball’s in their court
The fundamental question involved here is whether machine learning is only something for global players and their ideas for a comprehensive concept of a digital factory. Or whether, besides a top-down development thrust by financially potent large companies with their highly competent research and development departments, a bottom-up breakthrough spearheaded by flexible, innovative small and mid-tier enterprises would also be conceivable.
“Artificial intelligence is an important issue for the future,” says Dr. Wilfried Schäfer, Executive Director of the VDW (German Machine Tool Builders’ Association) and an organiser of the EMO Hannover 2017 (18 to 23 September), the world’s premier trade fair for the metalworking sector. “So small and mid-tier enterprises should also address the possibilities of machine learning in their production operations, enabling them to derive options in good time for their own development thrust.”
For Dr. Cord Winkelmann, Managing Director of Sensosurf in Bremen, things have already been set in motion here on many fronts. “The big companies tend to develop their own solutions, often very complex and comprehensive ones, sometimes spectacular and very effective in terms of marketing,” he comments. “These include a kind of bee swarm flying to and fro, collecting information, exchanging mutual feedback, networking, moving things forward. Digitalisation there is a boardroom issue.”
Innovative start-ups can make their own contribution to progressing development. Sensosurf has adopted the slogan “Sensor integration meets machine learning”. Founded in 2016 as a spin-off of the Institute for Microsensors, -Actuators and –Systems (IMSAS) at Bremen University, the company transfers micro-system technologies to the tough environmental conditions encountered in the mechanical engineering sector. These include flanged and pedestal bearings, linear guides and threaded rods. “We’re exploring fields from which so far there had been as yet scanty information or none at all available,” says Dr. Winkelmann. For data evaluation, machine learning is deployed in order to use information on the machines and processes.
Strategy of small steps
Large quantities of data are essential for machine learning; without them it’s simply not possible. For swift market penetration, says Dr. Winkelmann, it’s crucial that the information generated pays off from the very first moment. “It’s always the small steps we begin,” he explains. These include data evaluation at the machine, networking the machines with each other, detecting what’s characteristic about what’s happening. “Once you see what data are obtained, evaluated and visualised, you quickly get used to the new insights and the opportunities they offer,” says Dr. Winkelmann. “Measurements trigger an appetite for more.” What proves most persuasive for machinery manufacturers, he says, is that the machine learns to protect itself against operator error. The data obtained can also be used as a defence against unjustified warranty claims, for example.
“It’s important to map out migration paths for companies showing how they can introduce the technology of machine learning in small, digestible pieces,” concurs Fraunhofer expert Prof. Krüger. He sees the principal focuses of using ML at machine tool manufacturers as currently centred around the field of condition monitoring. This essentially involves interpreting measured data using pattern detection processes. The knowledge required for detecting process or machine conditions is acquired by the processes of machine learning.
Potentials in energy management
Besides the fields of predictive maintenance, condition monitoring and quality management, however, self-learning systems can also progress energy management. At the EMO Hannover 2017, the Munich-based company Gerotor will be premiering its HPS high-power storage system, which is designed to reduce the energy and connection costs involved with the aid of intelligent algorithms. The idea for the product originated with Formula 1, or to be more precise with the KERS (Kinetic Energy Recovery System) used there. The system was imposed upon racing cars at the time for reasons of environmental protection, since it returns to the drive axle energy produced during violent braking manoeuvres, by means of a rotating flywheel system.
Gerotor’s founders saw huge potential in “this efficient and at the same time wear-free technology, not only for cars driving round in circles,” as Gerotor’s director Michael Hein colloquially puts it. In the search for an application that likewise involves many and frequent braking and acceleration functions, sometimes within a matter of seconds, they found what they were looking for with machine tools and tool spindles. The advantages of digitalising and networking the power storage system were obvious: “If you’re inside the energy circuit, you’re in the information centre too.”
Coupled directly to the line, without requiring a power connection of its own, the new power storage system upgrades the efficiency of the entire line by means of energy recovery, peak smoothing and digitalisation. For this purpose, the system measures all currents and cycles, acquires data and information, improves its own algorithms, and draws conclusions. Whereas with traditional control strategies energy savings of at most 10 to 25 per cent can be achieved, says Michael Hein, users with intelligent strategies ought to achieve about double the savings effect. For Michel Hein, energy management offers a particularly simple and efficient entry route into ML. “Energy systems have to be 100-per-cent predictive,” he emphasises. “We need intelligent control strategies and an infrastructure that re-adjusts itself.”
Return on investment is crucial
He admits, however, that the concept of machine learning is practically ignored in meetings with customers The crucial consideration is rather the ROI (return on investment): “We sell our products solely by means of the argument that we save more than we cost.” This may in fact be one of the reasons why many companies tend to be rather taciturn when asked about their ML strategies. Machine learning is a means to an end, not a sales argument.
There is in any case no blueprint for introducing your own strategies. It’s advisable to call in some expert knowledge, through either one of the various Fraunhofer institutes or outside service providers. As Jörg Krüger explains, each company first has to clarify what form of intelligence is desired for a machine, a system or a robot, such as detection of the machine’s condition, autonomy, automatic adaption to changes like tool wear and tear or component characteristics. Autonomous replanning and self-organisation of production sequences, comprehending human commands and gestures for simplified programming das also rank among the capabilities that a machine could learn by itself. But Jörg Krüger also points out that this entails a further question: who checks whether something has been properly learned before the machine starts to operate automatically with the knowledge concerned?
There are also questions to be answered regarding IT security and data protection, or who assumes liability for decisions taken by an intelligent system. Could perhaps once again the “uneasiness” in dealing with cognitive systems, and possible loss of control come into play here? Cord Winkelmann doesn’t think so. A much more serious impediment for machine learning, he believes, and indeed for the digital transformation in general, is the inadequate provision of fast internet in many places, particularly for plants located in rural areas.
New Technologies Pair the Physical with the Digital
Digital twinning is one part of the technology road map for Industry 4.0 and the Industrial Internet of Things. A gamut of new technologies must be integrated to work seamlessly together to pair the physical domain with the digital information domain.
Digital twinning seeks to improve the design and maintenance of physical systems by offering datadriven ways to discretely map these physical systems into digital and computerized replicas of themselves. With the arrival of automation and data exchange, digital twinning could be useful in a myriad of industrial applications.
This new industrial context, where the physical and the digital worlds meet, is known as the fourth industrial revolution—or Industry 4.0. Brought on by the intersection of a host of high-technology electronic and computer systems, the “new way” of Industry 4.0 promises increasing gains, efficiencies, and flexibility. A gamut of new technologies must be integrated to work seamlessly together to pair the physical domain with the digital information domain. Digital twinning is only one part of the technology roadmap for Industry 4.0, as these additional technologies are helping to enable digital twinning for Industry 4.0 to manifest its potential:
• Pairing technologies
• Cyber-physical systems
• Augmented, virtual, and mixed reality
• Artificial intelligence
• Additive manufacturing
• 3D printing
• Digital thread
Pairing technologies are critical to digital twinning and the world of Industry 4.0, as these technologies empower a device or system to find, connect, and communicate with other devices and systems. For example, sensors and the Industrial Internet of Things (IIoT) products require the ability to find and connect with other devices successfully. Technologies such as Bluetooth®, among others, are employed to make these connections. To accomplish this, connected devices must be able to interrogate other potentially connectable devices successfully. When inquiring other devices, units must be able to ascertain whether they are communicating with a unit that they should be corresponding and exchanging data with. When properly enabled and successful, this accomplishment is called pairing.
Security issues are paramount. Every device should pair only after proper identification has been confirmed to avoid crosstalk or misinformation. Shortcuts may be achieved through programming algorithms that allow the devices to quickly and easily identify other units that they should pair with. Pairing gets accomplished through authentication keys employing cryptography. Pairing works to ensure that the connections stay bonded in a data exchanging relationship between devices and works to prevent an external source from prying into their data exchanges.
Being that flexibility is paramount, units must be able to make and break their pairing quickly and without external, human involvement. Successful pairing may require ongoing communication to keep the pairing active. If one of the units determines that the pairing bond is no longer relevant to its successful operational objectives, it will remove its pairing relationship and present itself available for a different pairing opportunity.
The National Science Foundation (NSF) defines cyber-physical systems (CPS) as, “The tight conjoining of and coordination between computational and physical resources.” The critical element in this definition is that it focuses on a system approach— where a set of connected things or parts form a complex whole.
A current example of a CPS is the automated airline flight-control systems. Industry 4.0 requires traffic control, not for airplanes, but for the machines, computers, robots, sensors, and processes that comprehensively work together for its realization. It represents a system of higher order than IIoT, because it sits one level higher in the complexity chain. Where IIoT is concerned with collecting, handling, and sharing of large amounts of data, CPS is focused on ensuring that this large amount of data, collected from multiple systems, gets properly utilized across multiple disciplines that are relevant to the industry involved. The unique dilemmas of any given industry will require engineering expertise to address these specific challenges.
Augmented, Virtual, and Mixed Reality
New technologies are augmenting our reality. They are providing us with the ability to overlay digital content in front of us physically, merging the real with the virtual, creating a mixed reality that should be considered augmented. This gain is allowing engineers to view things in new ways. For example, rather than viewing a DT on a computer monitor, we could view a DT using an augmented reality (AR) headset that enables the users to engage with digital content or interact with holograms.
The use of such AR empowers viewers to have an immersive experience whereby they engage their bodily senses.
Reality-enhancing headsets can create real-time experiences of actual conditions happening in the physical world, by way of experiencing them through a digitized environment. AR could lead to new insights and understandings. Additionally, a DT display could appear in the user’s field of view, making real-time feedback that much more accessible and easy to use.
Artificial Intelligence Technologies
IIoT offers the promise to provide connected data; therefore, useful data must be stored and analyzed. Artificial intelligence (AI) is a solution to how to analyze and successfully handle large amounts of digital data. It helps in allowing digital twinning to become more realized because it promotes value by enabling rapid integration, hybrid integration, investment leverage, and system management and compliance.
Through machine learning, it offers the opportunity to use digital data to model, analyze, train, apply, and infer how best to make decisions. AI is helping to change the traditional perspective of computing, moving it beyond what primarily has been an automating- and scaling-process perspective towards a knowledgebased perspective, via actionable insights. Soon, it will help engineers gather new insights and ways to create value. By using a data-science approach, rapidly powered decisions will enable the generation of further opportunities.
Additive manufacturing (AM) is a method of production in which 3D objects are built by adding layer-upon-layer of material. AM holds promise because it leads to industries that can address variable demand and produce products that are distributable and flexible. Two areas of AM – 3D printing and digital thread – are advancing to make digital twinning possible.
3D printing is perhaps the most well-known example of AM. In 3D printing, a printer is programmed to print an object using plastics, metals, or other custom materials with virtually zero lead-time. 3D printing is extremely flexible and eliminates the issues involved in producing objects with large economies of scale. What this means for the future is that you will be able to get what you want quickly—as if walking up to the fast food counter.
With complex systems, however, AM has been confined primarily to the laboratory because all the systems involved do not operate under a unified system and, thus, are hard to scale. Digital thread promises to change that.
A digital thread is a single, seamless strand of data that acts as the constant behind a data-driven digital system. It activates the potential of AM by allowing a unification of disparate applications by way of their adherence to the thread, which is their source of shared information. A digital thread creates an easier process for collecting, managing, and analyzing information from every location involved in the redesigned Industry 4.0. It enables better and more efficient design, production, and utilization throughout the entire process.
Digital twinning will be a hallmark of Industry 4.0, helping to increase gains, efficiencies, and flexibility for existing products and processes. But digital twinning is just one part of the Industry 4.0 road map. Pairing technologies, CPS, AI, and AM are key to seamlessly bringing together the physical realm and the realm of its DT information and insights. While these technologies are bringing their complexities into the digital twinning equation, ultimately, they promise to enable Industry 4.0 to manifest its potential.
by Paul Golata for Mouser Electronics
Nanusens now live on Crowdcube for Pre-Series A fund raising
Investment in high technology start up from as little as £10
Nano-technology Company, Nanusens, has taken an innovative step of crowd funding for a round of investment. Investment starts from as little as £10 on www.crowdcube.com/nanusens
Nanusens CEO, Dr Josep Montanyà i Silvestre, explained: “We have venture capital firms already investing in this round that have been supporting us for a number of years as they believe in our novel technology. I think we are one of the first high technology companies to also offer the opportunity for people to easily invest using the simple process of Crowdcube. We already have 135 investors and raised £131,500 on Crowdcube, which is a 32% of the way to our target.”
Investing via Crowdcube can be done via a credit card payment or PayPal and only becomes effective once 90% of the target figure of £400,000 has been reached at the end of the crowd funding campaign.
Until now, sensors had to come off the standard CMOS production line to have the MEMS created on them using different processes. Nanusens multi-patent pending technology enables it to create nano-sensors using a standard CMOS processes within the same production flow as the rest of the chip production. This innovative approach dramatically reduces the size and cost of the sensors along with up to 85% reduction in the time to market.
”Our first silicon nano-sensor samples from GLOBALFOUNDRIES exceeded our expectations,” explained Dr Montanyà, “with a sensitivity that is an order of magnitude above what is needed for a motion sensor in most applications. The mechanical operation of the nano-sensor design was the tricky part to get right, as that is where the innovation happens. That works perfectly and the design is fixed. Everything from now onwards just involves standard CMOS processes. Partnering with GLOBALFOUNDRIES will ensure good yields and that we will be able to rapidly ramp up production as sales take off. We have a disruptive technology solution that will revolutionise the sensor market and meet the ever-increasing demand for low cost sensors in smartphones, wearable technology and IoT devices that has already made sensors a multi-billion dollar industry.”
Nanusens has the supply chain fully defined, having partnered with trusted providers, like JCAP, member of JCET, the largest assembly group in China. The first product is planned to be ready by September. Upon finishing the electronic part and doing final qualification, sales will start. Nanusens is already in conversations with potential customers in China with whom the final specifications have been defined.
How the sensors are made using standard CMOS processes
The Inter Metal Dielectric (IMD) is etched away through the pad openings in the passivation layer using vapour HF (vHF) to create the nano-sensor structures. The holes are then sealed and the chip packaged as necessary. As only a standard CMOS process with minimal post-processing is used, and the sensors can be directly integrated with active circuitry as required, the sensors can potentially have high yields similar to CMOS devices. Further details can be seen at https://vimeo.com/258745205
more information at www.nanusens.com
VORAGO Technologies VA10820 Extends Flight Heritage
VORAGO Technologies, a leading provider of radiation-hardened and extreme temperature embedded systems technology, is delighted to have recently extended the flight heritage of the company’s microcontroller products.
The VA10820 microcontroller is currently operating on the Astranis demonstrator satellite DemoSat-2, which was launched on the PSLV-C40 polar satellite launch vehicle in January. The spacecraft was designed to demonstrate Astranis’ software-defined radio technology and is currently successfully operating in low Earth orbit.
Astranis is working towards bringing broadband to the four billion people on Earth who do not currently have internet access.
The rad-hard VA10820 was selected by Astranis on account of its impressive radiation performance specifications. Many SmallSat and CubeSat developers are taking a similar approach to the electronics radiation protection strategy in their spacecraft, by implementing the VA10820 microcontroller as the rad-hard mission critical mainstay component.
“We are delighted to support Astranis and be part of the impressive platform”, said Bernd Lienhard, Chief Executive Officer of VORAGO Technologies. “This technology is perfect for spacecraft that bring connectivity to the most remote places on Earth and we are proud to contribute to the Astranis solution.”
VORAGO Technologies is a privately held, high technology company based in Austin, TX with patented and proven solutions that enable electronics systems for extreme temperature and radiation environments. more information at www.voragotech.com
택배 절반 이상 2시간 내 배송시대 온다… 지브라 테크놀로지스
효성인포메이션시스템, 빅데이터 분석 플랫폼 무료 체험 이벤트 실시
어드밴텍, 사물인터넷 플랫폼 기반 협업 솔루션 마련
NXP 반도체, 히타치와 V2X 솔루션 공동개발로 일본 차량용 보안 시장 강화
유니버설로봇, 프로스트 앤 설리번 ‘올해의 제조업체 상’ 수상
키사이트코리아, ‘Keysight World 2018’ 9월 5일 개최한다
NXP, OmniPHY사 인수로 자율 주행차 고속네트워크 기술 확대
키사이트테크놀로지스, 엔드-투-엔드 IoT 솔루션으로 IoT 에코시스템 설계, 테스트, 보안 강화
마우저, TI 저전력 DP83TC811S-Q1 송수신기 공급
슈나이더일렉트릭, 모터 회로 차단기로 자동화 아키텍처와 통합 간소화 수행
스마트자동차3 주 ago
키사이트코리아, ‘Keysight World 2018’ 9월 5일 개최한다
스마트자동차2 주 ago
NXP, OmniPHY사 인수로 자율 주행차 고속네트워크 기술 확대
업계뉴스2 주 ago
키사이트테크놀로지스, 엔드-투-엔드 IoT 솔루션으로 IoT 에코시스템 설계, 테스트, 보안 강화
스마트자동차3 주 ago
마우저, TI 저전력 DP83TC811S-Q1 송수신기 공급
스마트공장2 주 ago
슈나이더일렉트릭, 모터 회로 차단기로 자동화 아키텍처와 통합 간소화 수행
스마트홈/컨수머2 주 ago
지브라 테크놀로지스, 헬스케어 전문화 프로그램으로 채널 파트너 지원나서
신제품뉴스3 주 ago
아티슨, 지능형 고전력 시스템 iHP 시리즈 확장
People2 년 ago
이제는 협동로봇이다.. 글로벌기업들 국내시장 공략 강화