Rapid state estimation method for polyphenyl ether production process

Abstract

The invention discloses a rapid state estimation method for a polyphenyl ether production process, which comprises the following steps of: establishing a linear high-dimensional system dynamic model of a process of generating polyphenyl ether by alkylation of phenol and methanol, and dividing a high-dimensional system state vector into low-dimensional state blocks according to system characteristics, and performing state estimation on the state block by using a variational Bayesian theory and a Kalman filtering principle. According to the method, the calculation cost can be effectively reduced while the relatively high state estimation precision is maintained, and the balance between the estimation precision and the calculation cost of a high-dimensional system is realized.

Description

technical field [0001] The invention relates to the technical field of complex process state estimation and monitoring, in particular to a rapid state estimation method for polyphenylene ether production process. Background technique [0002] The process of producing polyphenylene ether from the alkylation of phenol and methanol involves many state variables and belongs to the field of complex industrial processes, so the process can be described as a high-dimensional system, and the state estimation of the polyphenylene ether production process is can be transformed into a state estimate for this high-dimensional system. In the prior art, the Kalman filter is used to estimate the state of the high-dimensional system. The Kalman filter can provide the optimal estimate in the sense of the minimum mean square error, but the Kalman filter needs to be paid when it is actually applied to the high-dimensional system. Computationally expensive. In order to reduce the computationa...

AI Technical Summary

Problems solved by technology

In the prior art, the Kalman filter is used to estimate the state of the high-dimensional system. The Kalman filter can provide the optimal estimate in the sense of the minimum mean square error, but when the Kalman filter is actually applied to the high-dimensional system, it needs to pay Computationally expensive

In order to reduce the calculation cost, the method of ensemble Kalman filtering has also been proposed. Although the calculation cost can be reduced to a certain extent, the reduction effect is limited.

At the same time, the estimation accuracy depends on the size of the sample set. When the sample set is large enough, the accuracy of state estimation can achieve satisfactory results, but the cost of calculation is relatively high when the sample set is large; and when the sample set Although the calculation cost can be reduced to a certain extent when it is small, it is difficult to achieve satisfactory results in the accuracy of state estimation at this time.

At present, there is no good state estimation method that can achieve the trade-off between estimation accuracy and computational cost for high-dimensional systems

Images