SMT007 Magazine

SMT-Sept2018

Issue link: https://iconnect007.uberflip.com/i/1022231

Contents of this Issue

Navigation

Page 57 of 91

58 SMT007 MAGAZINE I SEPTEMBER 2018 methods, such as those derived from neural networks, the assignment of components on a PCB should gradually become largely autono- mous. Las Marias: How will AI change the electron- ics manufacturing/electronics assembly land- scape? Krippner: In the future—because of the rising difficulty in finding qualified SMT line person- nel as well as general cost pressures—there will be either fewer special- ists or more personnel with less e xperience in the AOI area. Nonetheless, first pass yield (FPY) will have to be over 90% right from the start and the number of escaped defects, zero. Preventing defect escape and false calls by person - nel during verification then becomes a logical tactic. This is where Viscom steps in with new AI soft - ware developments, which should be ready for market over the course of next year. Las Marias: What key challenges are you seeing in adopting AI in manufacturing? Krippner: An immense amount of data—actu- ally, big data—is needed to implement AI. The basic technologies and workflow related to AI-assisted verification have already been completely integrated in the Viscom software. Now data—as much actual data from the field as possible—is needed to train the AI algo- rithms. This training phase is currently in prog- ress. All this is proceeding step by step, since each classifier trained in this fashion must be validated before use. This requires additional data that are not used for the training. Over the long term, both the AI verifica- tion as well as the AOI programming will be automatic, achieving better results than before from the start. At Viscom, we follow the strat- egy of growing profits through innovation and technological leadership. One very influenc- ing factor is our customers, who we want to continue to enthuse with progressive solutions. Las Marias: What manufacturing trends will be greatly addressed by AI? Krippner: Especially at high resolutions due to miniaturization, fast imaging systems and evaluation methods are necessary. Miniatur- ization will certainly go hand in hand with more computational power, which then will be available for even better inspection solutions. AI implies that machines can learn continu- ously and then succeed in solving new prob- lems. A key issue is complete automatization. We will see more so-called lights-out factories in the future where human employees are no longer part of the process and machines can therefore produce. Las Marias: Are you seeing wide implementa- tion of AI in electronics manufacturing right now? Krippner: Today's modern electronics manu- facturing is Industry-4.0 driven. This explicitly includes Viscom's intelligently linked inspec- tion solutions. Information is automatically processed and exchanged with other systems on the production line, which then can provide necessary corrections. Machines react auton- omously to process fluctuations, exchange information with one another and then adapt their processes. This shows that even though AI is a relatively new trend here, electronics manufacturing is the right industry to success- fully advance it. Las Marias: 3D AOI is the latest in inspection technology right now. What can you say about the adoption of 3D in the industry today? How are you encouraging users/customers to shift from 2D to 3D? Krippner: In the case of AOI, 3D is already the standard for high-end systems, resulting in less programming work and lower error rates. Our image results are excellent, includ - ing complete surround viewing of inspected Peter Krippner

Articles in this issue

Archives of this issue

view archives of SMT007 Magazine - SMT-Sept2018