Natural gas purification process modeling optimization method based on unscented kalman neural network

Abstract

The invention aims to overcome the disadvantages in the prior art, and provides a natural gas purification process modeling optimization method based on an unscented kalman neural network. The natural gas purification process modeling optimization method comprises the following steps: determining input variables; collecting process production data; carrying out preprocessing on the data; carrying out data normalization processing; adopting the unscented kalman neural network to carry out modeling on the data to obtain a model; designing a preference function by using two output variables of the model of the unscented kalman neural network, and applying a multi-target genetic algorithm to optimize the input variables; disaggregating the input variables after being optimized and bringing in the model of the unscented kalman neural network in sequence, calculating the two output values of the model at the time, comparing with a sample value average value, and observing the optimization effect. The method can establish an accurate and reliable high sulfur natural gas purification desulfurization industrial process model, the yield of the finished product can be improved based on the model, the energy consumption in the desulfurization process can be reduced, and the method has important practical significance for guiding practical industrial production.

Description

technical field [0001] The invention belongs to the intelligent energy-saving and production-increasing technology in the desulfurization production process of high-sulfur natural gas, and relates to a natural gas purification process modeling optimization method based on an unscented Kalman neural network. Background technique [0002] The industrial process of high-sulfur natural gas is complex, with many process parameters, affected by uncertain factors such as temperature, pressure, flow rate, equipment aging and raw gas processing capacity, and is a typical complex nonlinear dynamic characteristic chemical system. The purification and desulfurization process of high-sulfur natural gas mainly includes the following parts: the main absorption tower MDEA solution absorbs acidic components H2S and CO2, the hydrolysis reactor removes (COS), the regeneration tower MDEA solution circulation regeneration and heat exchange process, and the specific process flow process Such as ...

AI Technical Summary

Problems solved by technology

However, there is a mutual constraint relationship between output and energy consumption. The optimization of one of the objectives must be at the expense of the other, and the units of each objective are often inconsistent, so it is difficult to objectively evaluate the pros and cons of the solutions to the two objectives.

Images