Machine Vision & AI Realizes Automated Inspection in Manufacturing Moderator: Ethan Huang, IIoT Advnatech Panelist 1: Yuki Tominaga, Phoxter (Japan) Panelist 2: Neil Chen, IIoT Advantech Panelist 3: Jesse Chen, CEO SmaSoft (Taiwan) Dec, 2019 IIoT Advantech
Edge SRP & Go to Market Milestones AI Vision Inspection Solution CCJV Co-Creation 共创 2019 3Q 2020 2019 4Q Machine Vision Solution Co-Creation 共创 2018 2H 2019 2Q 2019 4Q
Machine Vision Markets & Products US$440mn Non US$120mn US$400mn Manufaturing 11% US$160mn Automotive Other 19% US$800mn Manufactuing 10% Wood US$680mn 4% Metal Packaging 5% 17% US$2bn US$600mn Glass US$1.6bn 5% Pharmaceutical US$320mn 6% Semicon Electronics CAGR: 7.8% 8% 15% 2016-2020
Machine Vision applications in manufacture 1. 2. Processing Assembly Alignment; inspection Guidance; Gauge, Verification Future Manufacturing Applications: 1) Structured data extraction, Gauge, Coordinated Pattern Recognition => Machine Vision Solution 2) Randomized image Recognition => AI Inspection Solution 4. 3. 5. Packaging Logistics Inspection & Testing Identification; Guidance Identification; Defect Inspection Identification; Guidance
Advantech VisionNavi Agenda 1. Market demands for the Software 2. The Solution 3. Application 4. Co-Creation Dec, 2019 Yuki.Tominaga, Phoxter
Growing needs of Machine Vision Increase of wage Labor shortage, Education cost Report from Tsukubabank Health, Labour and Welfare Ministry Japan https://www.tsukubabank.co.jp/corporate/info/monthlyreport https://www.mhlw.go.jp/english/wp/wp-hw3/dl/j1_05.pdf /pdf/2016/03/201603_11.pdf
What the users really want to do with Machine Vision? Make more money/Save money – speed up the production – reduce the number of inspectors in the production line – improve quality; by categorizing defects and feedback the result to production Protect their own brand – prevent outflow of defective products to the market – execute reliable inspection
VisionNavi
Industries Semiconductor Electric parts PWB assembly Logistics Machine parts Food Beverages Medical
Applications More features for various situation - Preprocessing - Filter - Color extraction - Color convertion - Image rotate - etc. Measurement OCR - Judgement - Positioning - Count - Compare with good sample - Blob analysis - Matching - etc. Find defects/flaw/spot/etc. Code reading, 1D/2D
People with inspection problems Phoxter has solutions for AOI, but no sales link to the people who need them AOI solutions!
Co-Creating the Future Co-Creating the Future of the IoT World of the IoT World
Go To Market Strategy Dec, 2019 Neil.Chen, IIoT Machine Vision, Advantech
Vision-Based Track and Trace Solutions $3.93 billion, CAGR 18.9% by 2023 Source: AIA Online Marketing, 2019 Electronics Quality Manufacturing PCB/SMT/DIP Assembly Packaging Logistics Assurance Process Guidance Identification Major MV Inspection (High Inspection Application Growth) (High Growth) Vision System, Device Device Vision Sensor, Platform Product Platform ID Reader Vision Sensor Reference: Bernstein analysis, 2017
Solutions in Identification RFID Vision Laser Retail/Industry Retail Industry Handheld Stationary Handheld Reuse Reliable Stable Expensive tag High Price Low price Dimension Multi-code, OCR
Go To Market Cloud Service Material/Finish • Value Claim/ Marketplace Whole Process Good/Assert Ecosystem • OEE Monitoring • Visualization 2D Code 1D Code Optics Partner • Application Driven • Domain Focus • DFSI O.C.R O.C.V VisionNavi Field Device Edge Computing • Sensor, I/O, Data • Control, Comm. HMI, SCADA Automation PCs Intelligent HMI Wireless Sensor Module I/O & DAQ Devices Compact IPC Vision sensor Gateways
Service Network Optics, Use Case Virtual Machine Trial Test Online Evaluation DFSI Evaluation Kit Integrate optics(Lens, Upload images, On site demo, Lighting), duplicate feasibility study verify result use case
Machine Vision Algorithm Mix Rule Base Identification: 1D/2D code Segmentation O.C.R/Defect Detection Gauge/Alignment Classification Present/Counting Deep Learning Verification Advantech Confidential & Internal Use Only
Co-Creating the Future Co-Creating the Future of the IoT World of the IoT World
Advantech AINavi Agenda 1.Overview, Architecture 2.Selling point 3. Features 4. Applications Dec, 2019 Jesse.Chen, SmaSoft
Company Introduction 偲倢科技
OUR COMPANY SMASOFT With the emergence of industrial 4.0 brings a tidal wave of smart manufacturing and with this, in contrast to past production line focusing on hardware performances, the current age of smart manufacturing focuses more on hardware software system integration. It is no coincidence that Smasoft’s expertise and focus has been the system integration, both hardware and software, of an automation solution. This is done with the software LabVIEW from National Instruments (NI), and Smasoft’s proprietary SmaSEQ, that allows users to easily integrate robotic arm controls, automated optical inspection (AOI) algorithms using industrial cameras, and even AI model inferencing all without any prior programming experience.
OUR WORK Solve your automation problems We are the Automation solution supplier Developing an automated manufacturing system requires highly- trained professional software engineers who, often need a significant amount of time and effort to train; Hence, with a software integration platform like SmaSEQ, one would be able to automate any production line applications without any programming experience, which would surely increase the working productivity and efficiency, and significantly shorten the training/educating time-span required for an automation software engineer.
OUR SOFTWARE SmaSEQ Unlike the traditional production lines in which different hardware have distinct software and programming languages, our product offers complete design and compilation for the entire industrial automation process as a total solution, which offers many advantages such as ease-of- use when compared with solutions made up of other independent equipment; This greatly speeds up hardware integration and software development process, and also greatly enhances production performance.
OUR SOFTWARE “SmaSEQ” Automation Place notes Modules on scheduler Multi- Schedule Threads Functions Easy-To-Use Scheduling setting
SmaAITrainer Standalone AI Model Trainer
SmaAI AI Defect Inspection High-speed AI inference A high-speed and high-accuracy AI solution Distr trib ibuted AI AI stru ructu ture re Simultaneously run multiple AI models cost-effectively
SmaAI Trainer Training Flow Training IPC SmaAI Trainer Data Model ＋ Collection Deployment NVIDIA T4 Advantech MIC-770+ MIC-75G20
Distributed SmaAI Inference System MIC-730AI … Model DeepStream Vision 1 GPU IPC w TensorRT Model … 1 DIO GPU IPC w TensorRT … Motion Model … 1 GPU IPC w TensorRT Robot … …
rd part 3 rd party Pass assive Com omponents Defect Ins nspectio ion wi with WISE SE-PaaS/AFS Detectable defect: Dark crack Edge AI System Missing angle MIC-730AI Poor soldering Missing material OK image dislocation Daily OK Check NG Result Camera / Operate/QA Labeled Ruled-base AOI Model Model 2 MIC-770 data 5 Update Deploy 1 Smasoft Upload Data & SRP 4 Subscribe Re-training Task Marketplace Public Cloud
OUR PARTNER Smasoft software platforms have been approved by various partners; and with partners’ support, we can supply more innovative and diverse solutions to our customers.
Edge SRP S T E P 0 3 A I T r a i n i n g S m a A I T r a i n e r • Image Augmentation and processing • Image Data Verification S T E P 0 1 • Preview of the results I m a g e A c q u i s i t i o n S m a A I S T E P 0 2 C l a s s D e f i n i t i o n
Training Services T r a i n i n g C o u r s e S m a A I T r a i n e r Knowledge Base Classroom Training WISE-PaaS/AFS SmaAITrainer S m a A I Online Training Example Project SmaAcQ SmaAI
Go to Markets M a r k e t i n g S u m m a r y M a t e r i a l s L i v e D e m o s T r a i n i n g W e b i n a r
Edge SRP & Go to Market Milestones Welcome to join us 2020 CCJV Co-Creation Co-Creation 共创 共创 2018 2H 2019 2Q 2019 4Q 2019 3Q
Co-Creating the Future Co-Creating the Future of the IoT World of the IoT World
Recommend
More recommend
