EMS@C-LEVEL · 25 Feb 2025 · 49m
Oshri Cohen, CEO of Cybord, and Joel Scutchfield, General Manager of SMT and Semicon Business Operations for Koh Young America, discuss how AI is transforming inspection in electronics manufacturing. They explain that while traditional golden-unit comparisons fail due to component variety, AI enables 100% inspection of components and processes, moving the industry from reactive defect detection to proactive prevention. The guests highlight the critical importance of validating data inputs, adhering to IPC standards, and sharing data across platforms via initiatives like CFX to maximize AI efficacy and traceability. Customers are increasingly demanding immediate automated actions, such as rejecting counterfeit components, rather than just alerts, driving a shift toward autonomous, 'lights-out' manufacturing environments.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Quality & testCybord RTI
The AI inspects components from the bottom side at line speed and instructs the machine to immediately reject defective parts to a dump station.
“The first one is actually taking actual actions , immediate actions , like our RTI , the one that just you know . Look at a component from the bottom side . If there is any defect in a component , just instruct the machine , throw it away to the dump…”
Oshri Cohen · Hear it at 32:21
Engineering & simulationKoyang Auto-Programming (KPL)less than one hour
AI engines identify package types and outlines to automatically generate inspection programs for new boards, reducing setup time from days to under an hour with minimal human intervention.
“instead of placing 10 people for two , three days to program the machine , they can run the auto adjustment or the AI program , the auto-adjustment or the AI program , and then within I don't know one hour , less than one hour , they get the perfect program for the AOR…”
Oshri Cohen · Hear it at 23:37
Quality & testKoyang AI Engines
The system uses measurement-based 3D data to train algorithms that optimize printer and mounter settings (speed, pressure, clean cycles) to prevent bad products from being built.
“So now I'm using the results that I'm finding at post-print SPI and post-mount AOI to potentially make adjustments to those systems to ensure that bad product is not being built , based on the data that we're collecting and the information that we're gathering…”
Joel Scutchfield · Hear it at 4:37
Quality & testCybord AI
The AI validates component authenticity by analyzing images from pick-and-place and AOI positions to distinguish original materials from counterfeits, ensuring supply chain integrity.
“If you would like to build a model in AI that validates authenticity right , then you must make sure that the data set you build your model based on must be validated as original and franchise material right . Otherwise , you mistakenly can teach the model to look for counterfeit materials instead of original materials…”
Oshri Cohen · Hear it at 12:08
Engineering & simulationKoyang Smart Review
AI engines analyze post-reflow solder joints and part markings to classify judgments and adjust inspection tolerances in real-time, reducing false calls and human intervention.
“so forth . So when we're trying to help them classify judgments and use this information to determine , ideally , at the end of the day , adjust tolerances on the inspection tool itself so we're not creating calls that shouldn't be called it gets a little more complicated , right…”
Joel Scutchfield · Hear it at 17:16
large enterprises
Other shows on the same ground, closest first.
Phil Marcoux, Advisor to the Printed Circuit Engineering Association (PCEA), discusses the transformative role of AI in the electronics industry, emphasizing that successful AI integration relies on high-quality, human-generated data and closed-loop feedback between manufacturing and design. He warns against the current 'AI bubble' where startups receive funding without defined products, drawing parallels to the dot-com era and the early adoption of Surface Mount Technology (SMT). Marcoux highlights specific applications such as component availability checks via tools like Wenovo and Circuit Mind, and the critical need for standardized communication protocols like IPC CFX to bridge the gap between design and production.
Scott Everett, Co-Founder and CEO of Eigen Innovations, explains how his company uses industrial vision systems and AI to transform manufacturing quality control from reactive, destructive testing to proactive, insight-driven decision-making. He argues that while IoT infrastructure for data capture is mature, the industry struggles with 'insight architecture,' requiring contextualized data to provide explainable stories that empower non-technical operators to make real-time adjustments. Everett highlights specific applications in the automotive sector, such as ensuring the hermetic seal of vehicle headlights, where 100% inline inspection replaces random sampling to achieve zero-defect manufacturing.
Matt Puchalski, founder and CEO of Bucket Robotics, explains how his Y Combinator-backed startup uses synthetic data generated from STEP files to automate visual inspection in manufacturing, bypassing the need for physical 'golden samples.' He contrasts this approach with legacy systems from Keyence and Cognex, highlighting how starting from CAD models allows for rapid simulation of good and bad parts. Puchalski also shares his background in autonomous vehicles at Argo AI and Latitude AI, discussing the unique reliability challenges of deploying Level 4 AVs and how those lessons inform his current work in flexible manufacturing.
Anna-Katrina Shedletsky, CEO and co-founder of Instrumental, explains how her platform uses AI and aggregated product data to optimize manufacturing and reduce waste. Drawing from her experience leading product design teams at Apple, including the high-risk Apple Watch program, she details how Instrumental helps companies close feedback loops in development and production. She highlights specific use cases, such as using unsupervised learning to correlate visual inspection data with functional test failures, to improve yield and accelerate time-to-market. Additionally, Shedletsky discusses her Women in STEM Mentorship Program and Instrumental's recent recognition on the Inc. 5000 list.
Jarred Knecht, founder of AI quality inspection software KonnectAi and president of ProEV and ECI, explains how his family’s wire harness business evolved from industrial sectors to EV and defense markets. He details the development of KonnectAi, an AI-powered visual inspection tool designed to replace the irreplaceable institutional knowledge of veteran inspectors like 'Joe' without adding cost or complexity. Knecht discusses the challenges of implementing technology in traditional manufacturing, emphasizing a 'baby steps' approach to workforce adoption and the strategic value of AI in business development and talent retention.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by EMS@C-LEVEL. The episode itself belongs to its publisher.