The hottest analysis big data in industrial manufa

  • Detail

Analyze the big data in industrial manufacturing

how to realize intelligent manufacturing is a problem that everyone is concerned about. From Michael Porter of Harvard Business School to Wharton School of the University of Pennsylvania, there is a general consensus that digital transformation is the way to realize intelligent manufacturing. Importantly, this consensus also comes from many world-class manufacturing enterprises and entrepreneurs

this consensus is based on the integration of numerous technology trends, such as IOT, cyber systems (CPS), industrial IOT, mobile technology, artificial intelligence, cloud computing, virtual/virtual augmented reality (VR/AR), and big data analysis. We must remain sober and do not simply think that with these technologies, the next five years will be a golden age for manufacturing. The reason is very simple. The transformation process of this new manufacturing culture is quite complex and difficult. Without the integration of industries, enterprises and users, this transformation cannot be realized. Digital transformation means not only simple digitalization of enterprises, but also taking digital as the core driving force of intelligent manufacturing and using data to integrate the industrial chain and value chain

since the industrial revolution, manufacturers have been deliberately collecting and storing data in order to improve operations. With the passage of time, the demand for data analysis in the manufacturing industry will grow. However, in the past many years, the fundamental motivation for using data has not changed, the complexity of data has increased, and the ability to convert data into intelligence has become greater and greater

in 2012, Gartner gave the definition of big data, which particularly emphasized that big data is a diversified information asset, focusing not only on actual data, but also on big data processing methods. The amount of data itself is not the core indicator to judge the value of big data, but the real-time and multivariate data can be used for tensile test, stress test and bending test, which have a more direct impact on the definition and value of big data

when discussing the analysis of industrial big data, I noticed two different views:

the first view is that the manufacturing industry has always had big data. For decades, our enterprise has been collecting data through various application systems such as historical records, MES, ERP, EAM, etc. In some industrial chains, especially in marketing, big data is a new hot word

the second view is that from the perspective of industrial big data, manufacturing industry is a market that has not been opened or just opened. There are a large number of different types of data, but they have not yet been applied to analysis

considering these views, we should always maintain an appropriate skepticism in the face of any new market formulation, including term interpretation, definition or analytical framework. Here I am more inclined to the second point. Our manufacturing industry does have a lot of data, but this is not the meaning of big data that most of us understand from the market. How should we define big data in manufacturing before we understand the analysis of industrial big data? Here you can further understand the characteristics of big data through the three characteristics of big data

data sources

there are two main sources of industrial big data. The first is intelligent devices. Pervasive computing has a lot of space. Modern workers can bring a pervasive sensor and other equipment to participate in production and management. Therefore, the industrial data source is the association between a large number of devices of about 28billion, which is one of the data sources we need to collect in the future

the second data comes from the data generated by human trajectory, including the internal processes of procurement, production, logistics and sales and external interconnection information in the modern industrial manufacturing chain. Through the combination of behavior track data and device data, big data can help us analyze and mine customers. Its application scenarios include real-time core transactions, services, background services, etc

data relationship

data must be analyzed in the corresponding environment to understand the relationship between data. For example, every new model will undergo a series of brutal flight tests before being delivered to the airlines. The extreme weather test is one of the tests. The purpose of this test is to ensure that the engine, materials and control system of the aircraft can operate normally under extreme weather conditions

the key to the problem is to find the root cause of the problem, eliminate the known errors, and ensure the reliability and effectiveness of the solution. Once the root cause is found and identified, and acceptable emergency measures are in place, the problem can be treated as a known error. The process of problem investigation must collect all available event related information to identify and eliminate the root causes of events and problems. Data collection and analysis must be combined with the environmental data of the event/problem

data value

for digital transformation, big data should not only pay attention to the actual amount of data, but also the most important thing is to pay attention to the application of big data processing methods in specific occasions, so that the data can have great innovative value. Without consideration of income or design of return on investment (ROI), big data analysis can neither be implemented nor create value for the enterprise

definition of industrial big data analysis

engine is the heart of aircraft and the top priority related to aviation safety and life safety. In order to monitor the condition of the engine in real time, most modern civil aviation companies have installed the aircraft engine health management system in the first two non-destructive testing. The data collected through sensors, transmitting systems, signal receiving systems, signal analysis systems, etc. will be transmitted through VHF or satellite communication through the aircraft communication addressing and reporting system, which is why GE's engine monitoring system obtains more than 1PB of data every day and has obtained the approval of the Korean Ministry of food and drug safety (MFDs)

the production execution system (MES) is the same as the aircraft engine health management system. We can collect a large amount of process variables, measurement results and other data in real time from the production of the factory. Reports generated based on a large number of data sets or analysis of basic statistics are not enough to be called big data analysis of manufacturing industry

the diversity of data types is an important attribute of industrial big data analysis

big data is not just the accumulation of a large number of data. One of the important attributes of big data is that people try to collect and understand the changing data types. If only a large number of data of the same type are collected, no amount of data can be called big data

for example, the time series collected in the production environment simulates process variables. The type of data is single, and it is easy to build an index. Even if there are tens of thousands, it is not enough to become big data

data must include high variability and species diversity. There are numerous big data applications in manufacturing plants, but they do not include simply classifying and displaying a series of process measurement results. For these tasks, the basic statistical presentation can be completed. The components of some big data databases or data lakes are also text information, image data, geographic or geological information and non structural information, for example, data types obtained through social media or other collaboration platforms

the information structure of manufacturing industry can be summarized into two layers, one is the management layer, and the other is the automation layer. Decision support, management, production execution, process control and equipment connection and sensing are realized from the three dimensions of operation management, production execution and control. Big data analysis in the manufacturing industry refers to the use of general data models to combine the structural system data and non structural data of the management and automation layers, and then discover new insights through advanced analysis tools

significance of big data analysis to enterprise production intelligence

the core of manufacturing innovation is to rely on a large number of cutting-edge technologies. Advanced technology is the means of innovation. With the support of new technologies, enterprise management application systems, such as ERP and EAM, can be integrated with relevant systems of industrial automation through the integrated manufacturing operation management system mom. On the basis of integrated manufacturing operation management, we can realize an integrated manufacturing enterprise information system solution integrating it+mom+mes+bi

from the perspective of the integration of industrialization and industrialization, information system suppliers should do a good job in the unity of planning, standards, function design and implementation strategies from the perspective of the enterprise's main information systems vendor (MIV). Assist enterprises in risk control, reduce investment, reduce operation and maintenance costs, and achieve full integration of enterprise information systems

it should be noted that the enterprise management information platform is generally regarded as an integration and dashboard tool for manufacturing enterprise management. Many vendors have invested heavily in their proprietary integration with ERP and automation systems, as well as open integration, as well as dashboard and mobile technology, hoping to provide metrics for decision makers who need the right information anytime, anywhere

three approaches to big data analysis in manufacturing industry

approach 1 uses open technologies and platforms to move data from any system to any other place

the manufacturing operation management system construction project is a system engineering, not only a set of traditional software system we understand, but also a platform for project implementation and service. This needs to reflect the comprehensive management ability and soft power of manufacturing enterprises in terms of project management and strategic customer service of manufacturing enterprises

the whole platform should be structured from three major stages: early stage, project implementation and after-sales service. In the early planning, attention should be paid to standards, design and implementation, especially to form a unified connection with the management integrated information system. With the formulation of the unified plan in the early stage, the project implementation link can integrate the industry experience, integration ability, implementation ability, software development ability, etc. It is particularly necessary to establish and form a super team system in the organization. Continuous service, long-term operation, integration of IOT applications into the interconnection + strategy with software + cloud services are the focus of follow-up services

in the big data analysis of the manufacturing industry, it is necessary to strengthen the support for the follow-up continuous service through the application of IOT technology. Through the industrial IOT, we can strengthen and lock the long-term cooperation with the enterprise's supply chain enterprises through timely response to customers, regular inspection of IOT software and hardware systems, provision of emergency spare parts, provision of consumables, and improvement of applications. Through the management platform and IOT data, we can continue to provide valuable services to customers

approach 2: invest in data models that can handle structural and non structural data in the system architecture stack inside and outside the factory

new technology is the core of innovation revolution. One of the most important features is integration, that is, the integration of manufacturing operation management system mom with ERP, EAM, OA and business analysis, including one click login, interface integration, message push, workflow integration, master data, application integration bus and platform

as the master data between these systems are all unified, the data interaction between all systems depends on the application system bus for data interaction. After integrating the cross system business processes, workflow, service processes, etc., seamless integration and analysis can be achieved. For enterprise managers, after one click login, they can personalize and display

Copyright © 2011 JIN SHI