Unlock instant, AI-driven research and patent intelligence for your innovation.

Parallel probabilistic variational soft sensor modeling method for streaming big data

A modeling method and soft measurement technology, applied in design optimization/simulation, computer-aided design, etc., can solve problems such as the inability to accommodate all the memory, the inability to store data flow, and the huge amount of flow.

Active Publication Date: 2020-10-23
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the analysis of streaming big data, it is impossible to store all the data streams. Generally speaking, if memory is compared to a reservoir, batch big data is the water in the reservoir, while streaming big data is the water flowing into the reservoir, but running water The amount is too large to fit in memory

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Parallel probabilistic variational soft sensor modeling method for streaming big data
  • Parallel probabilistic variational soft sensor modeling method for streaming big data
  • Parallel probabilistic variational soft sensor modeling method for streaming big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0079] The performance of the parallel probabilistic variational model is illustrated below with a specific example of a methanation furnace unit in the synthetic ammonia production process. The main function of the methanator unit is to convert CO and CO 2 into methane, which is diverted and recycled. In this unit our aim is to minimize CO and CO in the process gas 2 content. Therefore, the first and most important procedure is to measure the remaining CO at the outlet of the cell and the CO 2 content, as a key quality variable. Here we take 10 process variables as input for soft sensor modeling, including pressure, temperature, flow and liquid level.

[0080] For this process, 95,000 samples were taken at consecutive equal time intervals. The first 5,000 samples constitute the original training dataset, and the remaining 90,000 samples are used as test samples.

[0081] In order to track the change characteristics of the state and verify the adaptive soft sensor method...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a parallel probabilistic variational soft sensor modeling method for streaming big data. The method introduces a streaming update method and a symmetric relative entropy respectively on the basis of the original variational supervised factor analysis model. According to The posterior distribution of the model parameters and the selection of the prior distribution are updated in real time due to the change of the actual streaming big data, so as to realize the self-adaptive update of the model, and combine the parallel computing strategy to further improve the model update efficiency; the present invention can aim at real-time The demanding streaming big data scenario has improved the model performance to a certain extent, combined with the parallel computing strategy to improve the model update efficiency, and achieved the purpose of adaptive soft sensor for streaming big data.

Description

technical field [0001] The invention belongs to the field of industrial process control and soft sensing, and relates to a parallel probabilistic variational soft sensing modeling method for streaming big data. Background technique [0002] In industrial processes, soft-sensing models are widely used to predict key process variables that are difficult to measure online due to factors such as harsh measurement environments, expensive measuring instruments, and large time lags. In recent years, the data-driven soft sensor modeling method is based on the data collected when the process is running, without relying on the knowledge of the process mechanism, and has been greatly favored by researchers and producers. Compared with the mechanism modeling method, the data-driven method can more truly reflect the actual operating state of the process, and the model it builds is also more reliable. However, when soft-sensing models are put into practical use, their predictive performa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/20
CPCG06F30/20
Inventor 葛志强杨泽宇
Owner ZHEJIANG UNIV