In a rapidly changing and competitive global marketplace, companies need to carefully consider where and how data is transformed into business value to enhance operations and improve customer experience. Sometimes data and analysis need to be processed centrally, such as data stored in the cloud; sometimes operational decisions need to be made immediately, so centralized solutions can't provide analysis, and you need to import edge analysis.
It has been reported that edge analysis occurs at or near the edge of the operational network and is often referred to as decentralized analysis or edge computing. However, due to a combination of cost, complexity, security and technical barriers, it has not been possible to analyze at the edge of the industry until recently.
But the situation is changing and digitalization is happening in all industrial environments. The brownfield infrastructure is adding intelligence by adding devices such as sensors and gateways, and the new infrastructure can be digitized through embedded software and smart devices.
Michael Guilfoyle, research director at ARC Advisory Group, a US consultancy, said that with this change, the market focus has shifted from centralized big data and analytics to edge data management and analysis. This is reasonable because the Internet of Things (IoT) edge devices and their associated data have increased dramatically and will continue.
But the excessive analysis of the edge analysis of equipment and related data ignores some of the most valuable data and insights that industrial companies can obtain, namely operational data (operaTIonal data) and process knowledge.
Traditionally, hierarchical structures have been used to capture, access, and deliver data across the enterprise, but there are many limitations in using data. This data structure already existed before the Internet. As the Internet becomes a ubiquitous part of the business and operational environment, this traditional data structure is being replaced.
Companies are now beginning to see the value of more comprehensive data and analysis. This improved perspective includes centralized processing, such as in the cloud, and seamlessly extends to the operational edge. As enterprise leaders struggle to deal with explosive growth data, cloud computing is seen as a solution to the quantitative, speed, and complexity issues.
The cloud solution combines complex and large data sets with advanced analytics to deliver the computing power to solve problems. For example, applying machine learning to acoustic data to predict asset failures; integrating text analysis to optimize processes, or using image analysis for product assurance.
In response to the growing use of cloud applications, the concept of enterprise edge is defined as the furthest extension of the business environment, whether it is physical infrastructure, distributed operations or customer interaction. Edge analysis extends data processing and operations to or near the data source. In industrial operations, edge-performing analysis typically supports tactical use cases that increase efficiency, reliability, unplanned downtime, security, and customer experience.
A common misconception when considering edge analysis data is that they only contain streaming data, ie time stamps based on the input source. The underlying vision is a combination of online, automated, edge analysis, and workflow automation that is key to capturing value from the data.
Although this is correct, only some of the IIoT strategies are described. What is missing is an understanding of the value of the operational process and its associated data. These data are usually generated and captured by Subject Matter Experts (SMEs) and therefore often contain high-value information.
Operating data, especially at the edge, is often underutilized. Unless there is a formal process, this data is rarely systematically sourced as part of the operational database. In addition to operational data, SME understands operational processes and best practices. These high-value employees have specific knowledge of how to operate the equipment, perform maintenance, and ensure safety procedures.
For example, crude oil engineers are well aware of the impact of crude oil types on equipment failure during refining. Of course, this kind of intellectual property is very valuable, and companies are worried that they will leave the company when workers retire or quit.
The good news is that there are technologies that can mathematically model data and get this expertise after analysis. This process knowledge can be enhanced through operations and IIoT data, and the fusion of knowledge and data can be used to drive the optimization decision process and device performance required for the IIoT strategy.
9 in 1 usb c adapter,10 In 1 Usb C Hub,usb-c multifunction adapter,type-c all-in-1 adapter macbook,USB C HUB,best USB-C Hubs
Shenzhen Konchang Electronic Technology Co.,Ltd , https://www.konchangs.com