10 Ways Machine Learning Is Revolutionizing Manufacturing
Louis Columbus for Forbes: Every manufacturer has the potential to integrate machine learning into their operations and become more competitive by gaining predictive insights into production.
Machine learning’s core technologies align well with the complex problems manufacturers face daily. From striving to keep supply chains operating efficiently to producing customized, built- to-order products on time, machine learning algorithms have the potential to bring greater predictive accuracy to every phase of production. Many of the algorithms being developed are iterative, designed to learn continually and seek optimized outcomes. These algorithms iterate in milliseconds, enabling manufacturers to seek optimized outcomes in minutes versus months.
The ten ways machine learning is revolutionizing manufacturing include the following:
Industry 4.0 breathes new life into cybersecurity
Dave Sutton for IT Pro Portal: A technical evolution has taken place, which has made cyberthreats more potent than at any other time in our history. According to PricewaterhouseCoopers, over half of British businesses will suffer cyberattacks by 2018. As businesses seek to embrace Industry 4.0, cybersecurity protection must be a top priority for Industrial Control Systems (ICS). These attacks are financially crippling, reduce production and business innovation, and cost lives.
In years gone by, legacy ICS were developed with proprietary technology and were isolated from the outside world, so physical perimeter security was deemed adequate and cybersecurity was not relevant. However, today the rise of digital manufacturing means many control systems use open or standardised technologies to both reduce costs and improve performance, employing direct communications between control and business systems. Companies must now be proactive to secure their systems online as well as offline. Cont'd...
Printed Perforated Lampshades for Continuous Projective Images
From Haisen Zhao, Lin Lu, Yuan Wei, Dani Lischinski, Andrei Sharf, Daniel Cohen-Or, Baoquan Chen:
We present a technique for designing 3D-printed perforated lampshades, which project continuous grayscale images onto the surrounding walls. Given the geometry of the lampshade and a target grayscale image, our method computes a distribution of tiny holes over the shell, such that the combined footprints of the light emanating through the holes form the target image on a nearby diffuse surface. Our objective is to approximate the continuous tones and the spatial detail of the target image, to the extent possible within the constraints of the fabrication process.
To ensure structural integrity, there are lower bounds on the thickness of the shell, the radii of the holes, and the minimal distances between adjacent holes. Thus, the holes are realized as thin tubes distributed over the lampshade surface. The amount of light passing through a single tube may be controlled by the tube's radius and by its direction (tilt angle). The core of our technique thus consists of determining a suitable configuration of the tubes: their distribution across the relevant portion of the lampshade, as well as the parameters (radius, tilt angle) of each tube. This is achieved by computing a capacity-constrained Voronoi tessellation over a suitably defined density function, and embedding a tube inside the maximal inscribed circle of each tessellation cell. The density function for a particular target image is derived from a series of simulated images, each corresponding to a different uniform density tube pattern on the lampshade... (full paper)
Companies, employees not quite ready for cognitive technology wave of robotics, AI, machine learning
Larry Dignan for Between the Lines: Robots, artificial intelligence, machine learning and other cognitive technologies will replace about 7 percent of U.S. jobs by 2025 with office and administrative staff taking the biggest hit, according to a Forrester Research forecast.
The bad news is jobs will be lost. The good news is that new gigs will be created as cognitive technology takes hold. One reason the disruption won't be larger or happen sooner is that companies aren't ready for the change related to the new automated workforce, said Forrester.
Among the key items:
16 percent of U.S. jobs will be replaced, but 9 percent of jobs will be created. That's how Forrester gets to the 7 percent job loss by 2025 figure.
Emerging jobs will be robot monitoring pros, data scientists, automation specialists and content curators.
93 percent of automation technologists feel unprepared to take on smart machine technologies.
83 percent saw cognitive computing as critical to their companies' future.
32 percent of respondents said they are prepared for the cognitive technology changes ahead, but only 12 percent are prepared to deal with the human and organizational fallout.
46 percent say the number of jobs will remain about the same and 43 percent of respondents thought jobs would decline.
Full Article:
'UK manufacturers fail to understand Industry 4.0'
Ian Vallely for Works Management: There isn't enough understanding of Industry 4.0 by UK manufacturers, according to a report by BDO in partnership with the Institution of Mechanical Engineers. It said just 8% of UK manufacturers have a significant understanding of Industry 4.0 processes despite 59% recognising that the fourth industrial revolution will have a big impact on the sector, according to the report .
As the increasing use of automation, data exchange, technology and wider supply chain communications driven by Industry 4.0 provides both huge opportunities and threats to UK manufacturing, there remains a ‘gaping hole’ in the education and understanding of Industry 4.0.
According to the BDO Industry 4 0 Report, increased productivity, better data analysis, increased competitiveness and lower manufacturing costs are the top ways in which Industry 4.0 will affect UK manufacturing. Cont'd...
FIRST 3D TOOLS PRINTED ABOARD SPACE STATION
Evan Gough for UniverseToday: Astronauts aboard the International Space Station have manufactured their first tool using the 3D printer on board the station. This is another step in the ongoing process of testing and using additive manufacturing in space. The ability to build tools and replacement parts at the station is something NASA has been pursuing keenly.
The first tool printed was a simple wrench. This may not sound like ground-breaking stuff, unless you’ve ever been in the middle of a project only to find you’re missing a simple tool. A missing tool can stop any project in its tracks, and change everybody’s plans.
The benefits of manufacturing needed items in space are obvious. Up until now, every single item needed on the ISS had to be sent up via re-supply ship. That’s not a quick turnaround. Now, if a tool is lost or destroyed during normal use, a replacement can be quickly manufactured on-site. Cont'd...
Midea makes bid for robotics maker Kuka official
DW.com: Chinese appliance firm Midea has announced it has launched a cash offer for a stake of 30 percent in German industrial robotics supplier Kuka. The takeover bid has stoked controversy in Germany and Europe.
Midea said on Thursday it would offer 115 euros ($130) per share to Kuka owners under efforts to become the biggest single shareholder in one of the world's leading manufacturers of industrial robots.
The Chinese appliance maker, which is so far only known to be producing washing machines and air conditioners, also said its offer would end July 15, with no ceiling on the percentage of shares it was aiming to buy. Kuka shares closed at just above 106 euros in trading at the Frankfurt Stock Exchange on Wednesday. The stock gained about 26 percent since the deal was first proposed in May. Cont'd...
MIT Food Computers
From MIT: The Food Computer is a controlled-environment agriculture technology platform that uses robotic systems to control and monitor climate, energy, and plant growth inside of a specialized growing chamber. Climate variables such as carbon dioxide, air temperature, humidity, dissolved oxygen, potential hydrogen, electrical conductivity, and root-zone temperature are among the many conditions that can be controlled and monitored within the growing chamber. Operational energy, water, and mineral consumption are monitored (and adjusted) through electrical meters, flow sensors, and controllable chemical dosers throughout the growth period.
Each specific set of conditions can be thought of as a climate recipe, and each recipe produces unique results in the phenotypes of the plants. Plants grown under different conditions may vary in color, size, texture growth rate, yield, flavor, and nutrient density. Food Computers can even program biotic and abiotic stresses, such as an induced drought, to create desired plant-based expressions... (project homepage)
How Big Area Additive Manufacturing is Enabling Automotive Microfactories
Ian Wright for Engineering.com: Make no mistake, 3D printing is changing manufacturing.
Although it may take years before we see the full impact of bringing this technology from rapid prototyping to full-scale production, there are already hints of big things to come.
Take Local Motors’ recent purchase of two Big Area Additive Manufacturing (BAAM) systems from Cincinnati Incorporated (CI) as an example. The former company designs, builds and sells custom vehicles out of its US-based microfactories. The latter is a century-old manufacturer of metal fabrication tools and, more recently, BAAM. Cont'd...
Computational Hydrographic Printing
From Yizhong Zhang, Chunji Yin, Changxi Zheng, Kun Zhou's paper: Hydrographic printing is a well-known technique in industry for transferring color inks on a thin film to the surface of a manufactured 3D object. It enables high-quality coloring of object surfaces and works with a wide range of materials, but suffers from the inability to accurately register color texture to complex surface geometries. Thus, it is hardly usable by ordinary users with customized shapes and textures.
We present computational hydrographic printing, a new method that inherits the versatility of traditional hydrographic printing, while also enabling precise alignment of surface textures to possibly complex 3D surfaces. In particular, we propose the first computational model for simulating hydrographic printing process. This simulation enables us to compute a color image to feed into our hydrographic system for precise texture registration. We then build a physical hydrographic system upon off-the-shelf hardware, integrating virtual simulation, object calibration and controlled immersion. To overcome the difficulty of handling complex surfaces, we further extend our method to enable multiple immersions, each with a different object orientation, so the combined colors of individual immersions form a desired texture on the object surface. We validate the accuracy of our computational model through physical experiments, and demonstrate the efficacy and robustness of our system using a variety of objects with complex surface textures... (full paper)
Carnegie Mellon Taps Private Gift for Engineering Simulation Center
Dian Schaffhauser for Campus Technology: Carnegie Mellon University has launched a new collaboration with Ansys, a global company that produces software for engineering simulation. Under the terms of the agreement, the company will endow a new "Ansys Career Development Chair" in the College of Engineering and help fund a new building dedicated to the study of Industry 4.0. That facility will bring together faculty, students, researchers and corporate participants.
Industry 4.0 is the name given to a movement that uses sensor, robotic, simulation and other innovative technologies to shrink development cycles and transform product design, development and manufacturing.
The new 30,000 square foot facility, which will be known as the Ansys Building, is intended to expand the "making" capabilities of the college by adding a simulation and collaboration lab and a large open bay facility for undergraduate students to build full-scale projects. That open bay facility will be next door to the fabrication and machining facilities of the Hamerschlag Hall MakerWing, announced in December, where students will be able to make their components and then assemble them into larger systems. Cont'd...
How Small Manufacturers Can Leverage Smart Manufacturing
Andrew Waycott for Industry Week: I see three ways in which smaller manufacturers can leverage Smart Manufacturing. The first is the way applicable to all manufacturers—using today’s affordable sensors to get better data, then using that data to fine-tune the process, decrease variability and remove bottlenecks. All of these bring costs down and drive quality up.
Now let’s talk about the other two ways—ways that are specific to the smaller manufacturer.
Smaller manufacturers have the edge in building volumes of one—in other words, customized orders. For many smaller manufacturers, the look is less assembly line and more set of work stations. This means that the operator in a smaller plant typically makes more decisions. It’s a more people-oriented process. Cont'd...
3D printing of patterned membranes opens door to rapid advances in membrane technology
Penn State Materials Research Institute via Science Daily: A new type of 3D printing developed by researchers at Penn State will make it possible for the first time to rapidly prototype and test polymer membranes that are patterned for improved performance.
Ion exchange membranes are used in many types of energy applications, such as fuel cells and certain batteries, as well as in water purification, desalination, removal of heavy metals and food processing. Most ion exchange membranes are thin, flat sheets similar to the plastic wrap in your kitchen drawer. However, recent work has shown that by creating 3D patterns on top of the 2D membrane surface, interesting hydrodynamic properties emerge that can improve ion transport or mitigate fouling, a serious problem in many membrane applications.
Currently, making these patterned membranes, also called profiled membranes, involves a laborious process of etching a silicon mold with the desired pattern, pouring in the polymer and waiting until it hardens. The process is both time-consuming and expensive, and results in a single pattern type.
“We thought if we could use 3D printing to fabricate our custom-synthesized ion exchange membranes, we could make any sort of pattern and we could make it quickly,” says Michael Hickner, associate professor of materials science and engineering at Penn State. Cont'd...
Bosch Rexroth launches Industry 4.0 training rigs
The Engineer: Bosch Rexroth has launched a new range of training rigs designed to help students get up to speed with the internet of things (IoT) and Industry 4.0.
The rigs will form part of the company’s Drive & Control Academy programme and are built with industry-grade components. Aimed specifically at educational and industrial institutions, the rigs are tailored towards students and teachers as well as customers and employees, designed to assist with the adoption of Industry 4.0 practices.
According to Bosch Rexroth, the modular hydraulic, pneumatic and mechatronic systems simulate a complete production process, combining several elements that can be operated individually or together. The physical rigs are accompanied by corresponding exercises, eLearning, project manuals and other supporting material.
“The launch of our new training rigs offering is market leading and aims to provide the younger generation with a better understanding in the future of manufacturing,” said Richard Chamberlain, product manager service at Bosch Rexroth.
“We firmly believe our industry grade training rigs will equip students with the ability to stay ahead of the curve. Our course material helps guide trainees through consecutive steps that build on one another, which means motivation remains high.” Cont'd...
New dual-step method provides 3D printing of conductive metals.
Shalini Saxena for ArsTechnica: Customizable, wearable electronics open the door to things like heart-monitoring t-shirts and health-tracking bracelets. But placing the needed wiring in a complex 3D architecture has been hard to do cheaply. Existing approaches are limited by material requirements and, in the case of 3D writing, slow printing speeds. Recently, a research team at Harvard University developed a new method to rapidly 3D print free-standing, highly conductive, ductile metallic wires.
The new method combines 3D printing with focused infrared lasers that quickly anneal the printed nanoparticles into the desired architecture. The result is a wire with an electrical conductivity that approaches that of bulk silver. Cont'd...
Records 991 to 1005 of 1150
First | Previous | Next | Last
Featured Product
RCO Series x86 Super-Rugged Industrial Computers
Premio's RCO Series redefines rugged edge computing by offering comprehensive solutions optimized to meet the demands requirements of Industry 4.0 edge AI applications. With super-rugged durability, real-time performance capabilities with x86 Intel processors, extensive IoT connectivity, and scalable EDGEBoost technologies, this series of industrial computers are engineered to excel in diverse high-specification deployment challenges. From AGV/AMR deployments to smart manufacturing, the RCO Series is fully optimized to deliver 24/7 operational reliability and real-time AI performance.
