Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

AWS-IoT-工業智造

625 views

Published on

AWS IoT on Industrial Manufacturing

AWS IoT x 工業智造

Level: 100/200, 中文演講

講師: Young Yang, Solutions Architect, AWS & CC Lin, Vice General Manager, NEXAIOT (a Nexcom company)

聯繫銷售: https://aws.amazon.com/tw/contact-us/

與銷售線上聊天: https://pages.awscloud.com/tw-hkt-sales-chat.html

  • Be the first to comment

AWS-IoT-工業智造

  1. 1. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.S U M M I T Manufacturing on AWS IoT 智慧物聯網與製造業應用 Young Yang ML Specialist Solutions Architect beyoung@amazon.com
  2. 2. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark IoT transforms traditional industrial processes Most data collected on premises is never analyzed and thrown away Manufacturing Mining Oil and gas Agriculture
  3. 3. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark FreeRTOS: Open Source Real-time OS for devices with MCU Greengrass: Device Software Package for Gateways IoT Core: IoT Platform as a Gateway to the rest of AWS Big-data Repository: database, data- warehouse, and data lake Bi-data Analytics: Custom tools for making better business decisions Machine Learning: AI Deep Learning tools for prediction Industry 4.0 with Amazon Web Services Revenue growth IoT data drives business growth Operational Efficiency & reliability IoT data decreases OpEx
  4. 4. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Use Cases Predictive maintenance Predictive quality Asset management and monitoring Smart Industrial Applications
  5. 5. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Use Cases Predictive maintenance Predictive quality Asset management and monitoring Smart Industrial Applications
  6. 6. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Predictive Maintenance Problem Fender seeks to automate their manual process to measure the health of the dust collecting motor at the factory to improve their production efficiency and quality. Dust causes the guitar paint to have bubble and result in lengthy process to re-work the guitar. Solution Vibration sensors were installed and connected with Greengrass to AWS IoT Platform. ML baseline was created to monitor the nominal operations of critical motors in the factory. Impact Able to replace parts before catastrophic failure with ML prediction. Cost of scheduled maintenance went down with longer MTBF. Now, there is real-time alerts for unexpected downtime to improve time-to-reaction. “ All in with AWS and I got my wish, my engineers don’t think about servers, they just think about making create products. Our factories use IoT and SageMaker technologies to improve our guitar production. Ethan Kaplan Chief Product Officer, Fender Digital, Fender Musical Instruments
  7. 7. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Predictive Maintenance Problem Already running GreenGrass on the factory floors, now need ML for: 1) Factory operator location and time resource management 2) Predictive maintenance for aging and degradation of bearings with acceleration sensors Solution • Tight coupling of ML model and Lambda, plus local access to high resolution sensor resources. • Built customized model to overcome size limitation. • Created a model delivery process for continuous adjustment and improvements.
  8. 8. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Use Cases Predictive maintenance Predictive quality Asset management and monitoring Smart Industrial Applications
  9. 9. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Predictive Quality Problem Valmet produces complex equipment with multiple dependent processes running in parallel. Valmet customers need visibility into the state of these processes to control quality and avoid downtime. Solution Valmet is building a new digital twin capability to allow paper mill operators to view equipment and process data during production runs. AWS IoT Analytics is at the core of this solution training ML models for paper quality forecasting and scheduling metrics generation for digital twin view-generation. Impact AWS IoT Analytics allows Valmet to combine historical models of equipment performance with live data from current operations to glean insights that help them learn how to make their paper better and stronger.
  10. 10. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Predictive Quality Problem Pentair provides water filtration systems equipped with sensors to fish farms and large industrial brewing customers. Most of their industrial customers are located in geographies with unreliable internet connectivity. They need to send data from sensors and devices to the cloud while continuously maintaining connection which is challenging in remote areas. Solution From Pentair’s water filtration systems, data is sent to AWS IoT Core. When connectivity is limited, AWS Greengrass provides Pentair with a local connection so data is never lost Impact Pentair can make decisions in near real-time that impact the health of its devices but also the health of the fish which in turn, results in better yields, prevents the spread of disease and lowers cost of operations.
  11. 11. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Use Cases Predictive maintenance Predictive quality Asset management and monitoring Smart Industrial Applications
  12. 12. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Industrial Cloud Problem Need a worldwide industrial digital production platform to integrate more than 30,000 facilities and 1,500 suppliers and partners, empowering automation of all automobile manufacturing and logistics processes. Solution Volkswagen Croup and AWS announced a multi-year, global agreement to build the Volkswagen Industrial Cloud, leveraging the breath and depth AWS’s portfolio of services, including IoT (AWS IoT Greengrass, AWS IoT Core, AWS IoT Analytics, and AWS IoT SiteWise), machine learning, analytics, and compute services. Impact The Volkswagen Industrial Cloud will bring together real-time data from all of the Volkswagen Group’s 122 manufacturing plants to manage the overall effectiveness of manufacturing and logistics processes. “ We will continue to strengthen production as a key competitive factor for the Volkswagen Group. Our strategic collaboration with AWS will lay the foundation. Oliver Blume Chairman of the Executive Board of Porsche AG and Member of the board of Management of Volkswagen
  13. 13. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Reinvent w/Monitoring Problem 1/3 of food produced globally is lost or wasted, and of that, 39% of the loss occurs in food manufacturing. Bayer is committed to reducing crop waste across the food processing supply chain. Solution Using AWS IoT SiteWise, Bayer is exploring digital manufacturing for crop processing to identify and prevent process loss in real time. Impact Continuously monitoring food processing efficiency, quality, and resource utilization, allows Bayer to adjust processes and equipment to reduce losses even as the quality or quantity of input crop streams might change.
  14. 14. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Why IoT Lab – Our Mission? • Regional Advantage & Global Technology Hub • IoT Eco-System Enablement (Hardware/Software) • Accelerate IoT solution deployment for verticals City/Utility Commercial/IndustrialRetail/Consumer
  15. 15. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Solutions Scale IoT Business with Solutions Partner Solution Template Market Revenue Cost Savings Customer Use Case $ $ Revenue growth IoT data drives business growth Operational Efficiency & reliability IoT data decreases OpEx
  16. 16. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Target • Mixed hardware/solution partners • Smart City/Building/Community operators Problem • Lack of multi-vendor multi-protocol connectivity integration platform • Lack of end-to-end device to operation software solutions POC/Solution • Work with partners and customers to create technology prototypes and templates for: • Device integration software (multi-protocol) • Cloud data collection and AI analytics • Operational tools, provisioning tools, and management tools • 3D data visualization, VR/AR integration Smart Building Smart City/Building POC IoT Core Amazon Lambda Elastic Beanstalk EC2 S3 EMR
  17. 17. DataDecisionInsight BusinessValue Humaninputtodecision Phase of IoT Values DATA ACQUISITION Enhance Knowledge (Data Applied) GET CONNECTED • Define / Deploy Devices • Real-time data collection LIMITED DATA • Adhoc reporting • No historical data INSIGHTS How Do We Add Value (Applied Data  Insights) GAIN INSIGHTS • Customer scoring & Asset scoring • Cause & effect GAIN UNDERSTANDING • Understand customer usage • Correlation INTELLIGENCE Drive Sustainable Value to Customers (Insights  Action) DATA-DRIVEN INNOVATION • Highly differentiated revenue- generating services • Build your long term digital relationships with customers • Remote products have autonomous actions • Process becomes more agile and continuous
  18. 18. DataDecisionInsight Past Present Future Analytics Focus BusinessValue Descriptive Analytics What has happened? Humaninputtodecision Diagnostic Analytics Why did it happen? Predictive Analytics What will happen? Prescriptive Analytics What should I do? How will these decisions impact? Analytics Landscape and Maturity
  19. 19. Machine Learning Transformation Path - Manufacture Data Lake Descriptive Understand Data Predictive Use Historical Data Prescriptive Machine Learning • Security • Governance • Compliancy • Lifecycle • ETL • BI Reporting • Data statistics • Knowledge Graph • Describe, show or summarize data in a meaningful way • Demand Forecasting • Anomaly Detection • Fraud detection • Predictive Maintenance • Industry 4.0 • Raw Materials Pricing Forecasting • Demand / Production Planning • Pricing Optimization • Worker Safety • Security Immersion Day • Data Migration • 3A on Data Management: Authentication, Authorization and Audit • Big Data Immersion Day • Workshop and POC • AWS Glue • Amazon RDS • Amazon EMR • Amazon Redshift • Amazon QuickSight • ML Solutions Lab • IoT Lab • ML Discovery Workshop • Amazon SageMaker • Deep Lens • AWS IoT AWSServicesBusinessNeeds
  20. 20. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Compute EC2 Data Lake/Data AnalyticsAI/ML IoT 111011001 101011001 011011001 011011001 101011001 011011001 111011001 111011001 101011001 011011001 011011001 101011001 011011001 111011001 111011001 101011001 011011001 011011001 101011001 011011001 111011001 101011001 011011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 011011001 101011001 011011001 111011001 101011001 IoT Core Device Management End2EndSolutions Edge S3, DataStream/FireHose Device Defender SiteWise QuickSight Amazon EMR, Athena, Glue Rekognition Kinesis Data Analytics SageMaker Sensor IoT Data Services Applications Amazon Marketplace IoT GreengrassAmazon FreeRTOSIoT Device SDK2 Lambda DynamoDB, RDS, RedShift Architecture with AWS
  21. 21. Your partner in smart manufacturing CC. Lin(林崇吉) AWS IoT x工業智造 啟動工業 4.0 兩岸佈局 新漢智能系統 AWS 台北高峰會 6/12-13
  22. 22. NEXAIOT 新漢智能 工業4.0解決方案供應商  工業 4.0 諮詢與 專案執行  SCADA自動化產 品線  智能化邊緣運算 及網關閘道方案  企業私有雲及戰 情室建構  工業電腦及人機 界面 IoT Automation Solution Your Partner in Smart Manufacturing 新漢智能
  23. 23. NEXAIOT 新漢智能 致力於物聯網雲端整合與執行之策略夥伴 AWS : 工業雲展現數據分析與儲存應用 • AWS 雲端 AWS EC2 , S3 and DB • AWS 雲端AWS EMR 進行數據分析 • AWS 展現3D戰情, AR眼鏡與數據 NEXAIOT 新漢智能 : OT 設備貫通 • 整合OPC.等底層設備 • 新漢智能提供3D戰情與及時信息 • Edge server 整合 AWS GG 貫通 OT 設備 新漢智能 edge server With • NEXAIOT : OPC,Modbus… • Amazon : AWS GG
  24. 24. Solution • NEXAIOT Edge server with AWS GreenGrass. • Edge server include OPC UA Server and IOT studio. • IoT Core reports status to the 3D Dashboard Room and saves historical data in S3 for Data Analytics • 3D Dashboard Room monitor and detect alerts and can take action/control devices from remote Smart Building & Factory Facility 3D Dashboard room NEXAIOT Edge Server • AWS GG • NEXAIOT IoT Studio Building/Factory Facilities : 水電油氣 Control path Data path OPC UA AWS Cloud
  25. 25. 廠樓外觀3D圖 廠區產線3D圖 : 具備旋轉 放大縮小 產線設備放大細部資訊 異常發生並告知處理方式 : AR 遠程指導 3D視覺化廠房與產線
  26. 26. 具備AI智慧化產線機台設計 6軸手臂 MiniBOT 7軸手臂 MiniBOT 7R AI Vision  超完美軟硬體整合方案 :  AWS  Intel  NEXAIOT  視覺AI化方案 :  Intel OpenVINO 技術  雲端化展現 :  AWS Dashboard for remote monitoring and robomaker  開放性工業機器手臂 :  新漢創博公司 6軸/7軸工業機器手臂
  27. 27. 具備AI智慧化產線機台設計影片
  28. 28. 完美的工業雲端整合方案 : Predictive Maintenance Architecture
  29. 29. 完美的工業雲端整合方案 : Predictive Maintenance Architecture 新漢智能針對轉動設備之預知技術 從感測安裝 頻譜數據 並上傳至AWS分析
  30. 30. 完美的工業雲端整合方案 : Predictive Quality Architecture
  31. 31. 完美的工業雲端整合方案 : Predictive Quality Architecture 進行將產線系統之設備數據傳送至AWS 進行分析預測生產品質與M2M 分析能力
  32. 32. 完美的工業雲端整合方案 : Asset Condition Monitoring Architecture
  33. 33. 完美的工業雲端整合方案 : Asset Condition Monitoring Architecture 讀取產線戰情之所有設備運作 , 稼動,維護等資訊進行最佳化設備資產管理
  34. 34. 新漢華亞智慧工廠暨企業戰情中心 • 廠區 : • 位於桃園龜山華亞三路: 8000 cm2 • 年產 : 新台幣 50億 • 主要產品 : 工業應用系統產品 • 產線 : SMT , DIP , 智慧倉儲 , M2M 戰情室 • 企業戰情中心 (Enterprise War Wall) • 顯示器 : • 4x2 ,55”(7M寬)多矩陣顯示屏 • 展現11大功能 • 主要應用 : 3C產品產線
  35. 35. 工業4.0 - 新漢華亞智慧工廠暨企業戰情室(EWR)
  36. 36. 智慧工廠 – 石化業 FormosaPetrol Company – Cloud/BigSCADA System Industry Flow Subsystem (PLC) DCS System PMS Station Industry Ethernet Prediction Maintenance System AMI SystemFactory/Process Automation System Safety Control Rockwell Automation Vibration Monitoring Safety System (SIL3) Gateway MMI Station CCTV Data Server Cloud Gateway Gateway DCS Controller Zigbee EtherNet/IP DeviceNet PFOFINET PROFIBUS
  37. 37. 智慧機械 – 智能產線與精實管理
  38. 38. 智慧工廠 - 產線機台聯網平台 OPC-UA共通協定 點膠 微調焊封濺鍍 電檢電測 製程 設備 資料 匝道器 OPC-UA頻率元件機聯網共通協定 端點 伺服器 MES ERP CRM 智慧 生產 應用 智 慧 設 備 智慧 分析 應用 製程不良分析與參數動態調整模組 濺鍍參數 分析模組 點賿參數 分析模組 封焊 參數最佳化 生產履歷/稼動追蹤模組 生產戰情室與資料可視化模組 異值資料 整合模組 生產履歷 整合資料 調頻參數 分析模組 設備預診斷分析模組 工研院電光所 鼎新 資通 資策會服創所 新漢 OPC-UA Client OPC-UA Server / Pub 工廠廠務與環控 頻率元件智慧製造聯盟架構 加高電子 加高電子
  39. 39. Thank you! S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved. Speaker Name Contact information
  40. 40. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark AIoT Value for Smart Manufacturing DATA ACQUISITION INSIGHTS INTELLIGENCE BUILDING A STRATEGY TO DRIVE DIFFERENTIATION AND INNOVATION TIME
  41. 41. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark AIoT Value for Smart Manufacturing GET CONNECTED • Define / Deploy Device • Real-time data collection • Condition monitoring • Alert & alarm on thresholds • Address data silos LIMITED DATA • Adhoc reporting • Disparate data (e.g. LOB) • No historical data BUILDING A STRATEGY TO DRIVE DIFFERENTIATION AND INNOVATION DATA ACQUISITION Enhance Knowledge (Data Applied) TIME
  42. 42. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark AIoT Value for Smart Manufacturing GAIN INSIGHTS • Data correlation • Cause & effect • Anomaly detection • Customer scoring • Asset scoring GAIN UNDERSTANDING • Understand customer usage • Feature usage • Growing data sets • Threshold analysis • Correlation • Machine Learning GET CONNECTED • Define / Deploy Device • Real-time data collection • Condition monitoring • Alert & alarm on thresholds • Address data silos LIMITED DATA • Adhoc reporting • Disparate data (e.g. LOB) • No historical data DATA ACQUISITION INSIGHTS Enhance Knowledge (Data Applied) How Do We Add Value (Applied Data 🡪 Insights) BUILDING A STRATEGY TO DRIVE DIFFERENTIATION AND INNOVATION TIME
  43. 43. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark AIoT Value for Smart Manufacturing GAIN INSIGHTS • Data correlation • Cause & effect • Anomaly detection • Customer scoring • Asset scoring GAIN UNDERSTANDING • Understand customer usage • Feature usage • Growing data sets • Threshold analysis • Correlation • Machine Learning GET CONNECTED • Define / Deploy Device • Real-time data collection • Condition monitoring • Alert & alarm on thresholds • Address data silos LIMITED DATA • Adhoc reporting • Disparate data (e.g. LOB) • No historical data DATA-DRIVEN INNOVATION • Intelligent event response (AI/ML) • Predictive & Prescriptive Maintenance • Highly differentiated revenue- generating services • Cloud-delivered customer applications • Replenishment and supply management • Remote product control • Integration with 3rd party data • Asset optimization • Data as a Product DATA ACQUISITION INSIGHTS INTELLIGENCE Enhance Knowledge (Data Applied) How Do We Add Value (Applied Data 🡪 Insights) Drive Sustainable Value to Customers (Insights 🡪 Action) BUILDING A STRATEGY TO DRIVE DIFFERENTIATION AND INNOVATION TIME
  44. 44. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark ENTERPRISE APPS DEVELOPMENT & OPERATIONSMOBILE SERVICESAPP SERVICESANALYTICS Data Warehousing Hadoop / Spark Streaming Data Collection Machine Learning Elastic Search Virtual Desktops Sharing & Collaboration Corporate Email Backup Queuing & Notifications Workflow Search Email Transcoding One-click App Deployment Identity Sync Single Integrated Console Push Notifications DevOps Resource Management Application Lifecycle Management Containers Triggers Resource Templates TECHNICAL & BUSINESS SUPPORT Account Management Support Professional Services Training & Certification Security & Pricing Reports Partner Ecosystem Solutions Architects MARKETPLACE Business Apps Business Intelligence Databases DevOps Tools NetworkingSecurity Storage Regions Availability Zones Points of Presence INFRASTRUCTURE CORE SERVICES Compute VMs, Auto-scaling, & Load Balancing Storage Object, Blocks, Archival, Import/Export Databases Relational, NoSQL, Caching, Migration Networking VPC, DX, DNS CDN Access Control Identity Management Key Management & Storage Monitoring & Logs Assessment and reporting Resource & Usage Auditing SECURITY & COMPLIANCE Configuration Compliance Web application firewall HYBRID ARCHITECTURE Data Backups Integrated App Deployments Direct Connect Identity Federation Integrated Resource Management Integrated Networking API Gateway IoT Rules Engine Device Shadows Device SDKs Registry Device Gateway Streaming Data Analysis Business Intelligence Mobile Analytics

×