Industrial process data parsing platform based on cloud computing

Abstract

The invention discloses an industrial process data parsing platform based on cloud computing. The industrial process data parsing platform comprises a cloud server, an industrial field end, a client and a monitor; the cloud server is formed by two parts including a system host and n sub-clusters, wherein each sub-cluster comprises a sub-cluster host and multiple slaves connected with the host, thesystem host controls the multiple sub-cluster hosts, and each sub-cluster host controls the slaves connected with the sub-cluster host; the industrial field end reads data of industrial objects in real time and sends the data to the cloud server for analysis processing; the client is used for being remotely connected with the cloud server, reads and displays computing results of the cloud serverin real time and can remotely sends instruction to the cloud server; and the monitor is used for monitoring the cloud server, managing user information and industrial object information and sending control instructions to the industrial field end through the cloud server in real time. The platform can achieve remote monitoring on the industrial process, is high in operation efficiency and can bearsimultaneous usage of mass users.

Description

technical field [0001] The invention belongs to the field of industrial process control, and in particular relates to an industrial process data analysis platform based on cloud computing. Background technique [0002] In industrial process control, the industrial process data analysis software platform often plays a very important role. The platform can mainly collect and store process data in real time, and use corresponding modeling algorithms to realize data-driven industrial process monitoring and process analysis. Soft measurement of variables and quality variables to maintain smooth operation and improve product quality. [0003] Among them, data-driven industrial process monitoring is to establish a mathematical model through measured process data, thereby estimating and obtaining the operating status of the process, and finally identifying the abnormal behavior of the process, realizing timely diagnosis of faults, and ensuring the safe operation of the system; and p...

AI Technical Summary

Problems solved by technology

[0005] However, driven by the Internet and ultra-large-scale data, the traditional industrial process data analysis platform can no longer meet the needs of modern industry. First of all, the traditional system can no longer store ultra-large-scale data. If less data is still used for calculation, large deviations will occur ;Secondly, due to the large amount of data, the traditional stand-alone algorithm operation mode can no longer meet the real-time and stability of calculation; at the same time, the client form of the system is single, and both the client and the algorithm program cannot realize remote monitoring and control on site; finally Algorithms in traditional systems are not shared and reusable, and a set of process monitoring and soft-sensing algorithms must be written separately for each industrial object. The algorithm utilization rate is low, and it is not easy to manage the algorithm

Images