FEATURE INDUSTRY 4.0 SITTING ON THE EDGE OF AN AUTONOMOUS AGE


Harel Boren, CEO and executive chairman of Autonomous Machine Vision expert Inspekto, explains how the limits of existing QA technology is driving the development of more autonomous, plug and inspect machine vision systems


I


n 2015, Forbes ran an article that stated a robust systems integrator channel


would be vital for businesses to capitalise on the need for Internet of Things (IoT) and Industry 4.0 technology. This has proven to be the case, particularly regarding machine vision for quality assurance (QA). However, we now sit on the edge of an autonomous age that will entirely remove the need for systems integration for machine vision. With manufacturers across the globe


adapting to the fourth industrial revolution, investment in automation, robots and motion control systems is on the rise, as is the uptake of machine vision for QA. In 2017, German mechanical engineering industry association the VDMA, predicted that growth in German machine vision turnover would rise by 10%. Later that year it raised its forecast to 18% growth, corresponding to 2.6 billion euros. Olaf Munkelt, Chairman of the Board of VDMA Machine Vision said of the growth: “Machine vision is a major trend. The period of growth will continue. For years, the European machine vision industry has been conquering new markets and applications. Many great opportunities, such as the smart factory or the car of the future, can only be achieved with machine vision as key technology.” While this growth is attributed to the


drive to increase automation and reduce the opportunity for human error in QA, there are other contributing factors like the public spotlight being cast on high profile product recalls. For example, it was widely reported that poor QA in Samsung’s eagerness to compete with Apple was at the root of the brand’s recall of its Galaxy Note 7 smartphones in 2016. Industry simply cannot be without QA, but what makes it the necessary evil that it is? As industrial manufacturers experience


on a daily basis, there are no shortcuts to visual QA. It is always a big investment — in terms of time, money, downtime and internal resources. Each visual QA installation is a fully-fledged project in its own right: starting with a POC on samples, then development of the QA solution, including selection of the ideal components, such as cameras, lenses, lighting components and filters. Subsequently, the forming of a physical structure, and then installing the machine


18 NOVEMBER 2018 | PROCESS & CONTROL


and completing tedious software set up… it is a complex process that is reliant on the involvement of a systems integrator. Whether it’s a new QA solution, or an adjustment to a new version of the inspected product, every step in the process requires specialist knowledge. These imperative long solution-creation


and setup times inevitably lead to downtime of the production line, as well as temporary reliance on human inspection. Needless to say, integrators go to great lengths to assure that QA solutions are developed and installed such that lighting and surroundings can be carefully controlled, as any changes will impair function. Typically, machine vision solutions are


complex, cumbersome to develop and install, leading QA managers to situate them only at the end of a production line or at key junctions within. Often visual QA inspection is only on the final product, so if one component is faulty, the entire product needs to be scrapped or amended. Wouldn’t it revolutionise the


manufacturing industry if visual QA could be undertaken at all stages of production? Working this way would catch errors in components as they occur and stop their production sooner, meaning less scrappage or remanufacturing. Additionally, because the set up and


implementation of machine vision solutions is so specific, tailored and bespoke, a solution installed on one location on the production line cannot be used to assess new parts. It also cannot be moved from that location and used anywhere else in the plant, without re- tailoring a literally new project to support it. Therefore, many manufacturing processes, cannot employ machine vision tools without making continual


We will see technology advance to a point where small, agile visual-QA ‘appliances’ will simply be unpacked and placed anywhere on the production line


investment. For the line to run correctly, the plant would require systems integrators to prepare a myriad of one-off visual QA solutions, for potentially hundreds of parts, and accept the downtime that goes with this process. Luckily this era is over. The next phase


of innovation, particularly in the machine vision market, will render the systems integrator obsolete. The future is autonomous, plug and


Harel Boren says: “We’re on the cusp of a major disruption that will dramatically improve QA for manufacturers. However, it may very well signal the beginning of the end of the vision system integration golden age”


inspect machine vision. We will see technology advance to a point where small, agile visual-QA ‘appliances’ will simply be unpacked and placed anywhere on the production line. Using more progressive artificial


intelligence (AI) technologies, along with autonomous machine vision technologies, future machine vision systems will be able to quickly and easily recognise any product they’re presented with, and detect any defects upon it, in a matter of minutes. Such systems will no longer be hindered by the need to work in hard-engineered and pre-prepared locations, pampered with controlled-lighting conditions. The use of such systems by QA managers on production lines will never again call for a machine vision integrator to be tailored to place. The development of such automation


Undertaking visual QA at all stages of production would help reduce scrappage and remanufacturing


technology will not only make the systems integrator redundant, it will make machine vision a far more cost-effective option. Plug and inspect systems from one single manufacturer remove multi-vendor costs and eliminate prolonged periods of downtime for installation and implementation. Therefore, QA budgets will be able to go much further, allowing the installation of powerful visual QA at every stage of production to reduce scrap and improve quality. Next generation machine vision will also be more responsive and flexible, capable of adapting quickly to the introduction of new designs to the production line, as well as to the many changes a production line undergoes while it’s active.


Inspekto inspekto.com


/ PROCESS&CONTROL


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44