Introduction of industrial big data is the core of intelligent manufacturing, based on "big data + industrial Internet", cloud computing, big data, Internet of Things, artificial intelligence and other technologies to lead the transformation of industrial production methods, pulling the innovation and development of the industrial economy, so what are the characteristics of industrial big data? The following big data engineers to tell you about it.
1, accuracy (accuracy):
Mainly refers to the authenticity, completeness and reliability of the data, and is more concerned about the quality of the data, as well as the reliability of the processing, analysis techniques and methods. Higher confidence requirements for data analysis, relying only on statistical correlation analysis is not enough to support fault diagnosis, prediction and early warning and other industrial applications, the need to combine the physical model with the data model to mine the cause and effect relationship.
2, closed-loop (closed-loop):
Including the product lifecycle horizontal process of data chain closure and correlation as well as intelligent manufacturing vertical data acquisition and processing, need to support the state of the closed-loop scenarios such as perception, analysis, feedback, control and other closed-loop dynamic continuous adjustment and optimization.
3, diverse (variety):
Refers to the diversity of data types and a wide range of sources. Industrial data is widely distributed, distributed in machine equipment, industrial products, management systems, the Internet and other links, and the structure is complex, both structured and semi-structured sensing data, but also unstructured data.
4, data volume (volume):
The size of the data determines the value of the data under consideration and the potential information. Industrial data volume is relatively large, a large number of machines and equipment of high-frequency data and Internet data continue to influx, large industrial enterprises will reach the petabyte or even EB level of data sets.
5, fast (velocity):
Refers to the speed of obtaining and processing data. Industrial data processing speed needs are diverse, production site-level requirements for analysis time frame to the millisecond level, management and decision-making applications need to support interactive or batch data analysis.
6, strong relevance (strong-relevance):
On the one hand, the same stage of the product life cycle of the data has a strong relevance, such as the composition of the product components, working conditions, equipment status, maintenance, parts and components of the supplemental purchasing, etc.; on the other hand, the product life cycle of the R & D design, production, service and other different links between the data. On the other hand, there is a need to correlate data from different parts of the product lifecycle, such as R&D, design, production, service, and so on.
7, low value density (value):
Industrial big data more emphasis on the user value-driven and data availability itself, including: to enhance the innovation capacity and production and operation efficiency and to promote personalized customization, service-oriented transformation and other new modes of intelligent manufacturing change.
8, temporal sequence (sequence):
Industrial big data has a strong temporal sequence, such as orders, equipment status data.
About industrial big data characteristics, we share with you here, the development of Chinese society so far, the application of big data is gradually popularized, so the future prospects are immeasurable, I hope that people who want to engage in this industry can be reasonable choice.