SMT007 Magazine

SMT007-Jan2021

Issue link: http://iconnect007.uberflip.com/i/1323994

Contents of this Issue

Navigation

Page 17 of 89

18 SMT007 MAGAZINE I JANUARY 2021 layers of complexity, from both a design and process standpoint. Data Infrastructure "The data-driven world will be always on, always tracking, always monitoring, always listening and always watching—because it will be always learning." [1] A data infrastructure refers to the hardware, firmware and software required to collect, interpret, and analyze the immense amount of data generated by an organization. Big data is defined as a collection of data from traditional and digital sources inside and outside an orga- nization that provides a source for ongoing dis- covery and analysis. In today's business envi- ronment, data is collected everywhere, from systems and sensors to mobile devices. The challenge is that the industry is still developing methods to best collect, interpret, and analyze the data. With the vast amount of data being acquired, having a robust data infrastructure to manage these tasks is mission-critical to Industry 4.0 and smart processes. Fun Facts on Big Data [1] • By 2025, the world's data will grow to 175 zettabytes – One zettabyte is equivalent to a trillion gigabytes – It would take 1.8 billion years to download 175ZB at the average current internet connection speed • On average, office workers each receive 110 to 120 emails per day, equaling approximately 124 billion emails on any given day • Amazon records $283,000 in sales per minute • 49% of the world's stored data will reside in public cloud environments by 2025 • Manufacturing and financial services are the leading industries in terms of Data Readiness Condition (DATCON) maturity • More than 150 billion devices will be connected globally by 2025 management, speed, and scalability as your IIoT initiative grows and matures. 2. Cyber Physical Systems Cyber physical systems are the integration of computers, networking and physical pro- cesses. Computers and networks monitor and control physical processes with feedback loops; the physical system reacts; the system uses software to interpret actions and tracks results. This system is based on embedded computers and software in devices, not for tra- ditional data computation, but rather as a loop of action and machine learning. The smart factory is a flexible system enhanced by aug- mented intelligence that can self-optimize per- formance across a broader network. A cyber physical system can self-adapt to and learn from new conditions in real or near-real time, and autonomously run entire production pro- cesses. The traditional manual methodology for pro- cess optimization consisted of four tasks: a) Gain process understanding. b) Create process model. c) Recognize constraints and optimization parameters. d) Optimize the process model. Enabled by the previous connectivity char- acteristic and "machine learning," the smart process adapts and makes process tweaks on-the-fly based on what is working and what isn't. How does this work? The pro- cess "learns" from the data through connec- tivity and data exchange between the equip- ment, software and process KPIs. Based on this information, the process model can then decide which system configuration delivers the best performance, and which does not. The integration of cyber and physical com- ponents provides both new opportunities and challenges. The benefits include new func- tionality in traditional physical systems, such as brakes and engines in vehicles, intelligent control systems for biochemical processes, and wearable devices. On the other hand, the integration of cyber components adds new

Articles in this issue

Archives of this issue

view archives of SMT007 Magazine - SMT007-Jan2021