Modeling and optimizing method for biogas high-pressure washing

Abstract

The invention discloses a modeling and optimizing method for biogas high-pressure washing. The modeling and optimizing method comprises the following steps: step 1, collecting initial sample data of a biogas high-pressure washing process; step 2, establishing a product gas quality and equipment energy consumption multi-target initial model of sample data about the biogas high-pressure washing process based on a self-adaptive online learning machine, collecting a new sample of the biogas high-pressure washing process, and optimizing the product gas quality and the equipment energy consumption by utilizing a self-adaptive iterative optimization model for balancing the old model and the new sample characteristics; forming a product gas quality and equipment energy consumption multi-objective optimization model; 3, solving a product gas quality and equipment energy consumption multi-objective optimization model of the biogas high-pressure washing process based on a novel multi-objective differential evolution algorithm; and 4, selecting an optimal operation variable with high product gas quality and relatively low equipment energy consumption by a decision maker according to the Pareto optimal solution set. The efficient modeling method is provided for the biogas high-pressure washing process, the calculation cost of retraining the model is reduced, and the precision of the model is improved.

Description

technical field [0001] The invention relates to the technical field of biogas high-pressure water washing, in particular to a modeling and optimization method for biogas high-pressure water washing. Background technique [0002] The biogas high-pressure water washing process is widely used in the purification process of biogas projects at home and abroad because of its advantages such as simple control, low cost, high absorption efficiency, and large processing capacity. At present, scholars have established detailed mechanism models for the physical dissolution process, gas-liquid mass transfer process, and material transfer process between equipment involved in the biogas high-pressure water washing process. However, the parameters involved in the mechanism model are difficult to obtain. Solving is cumbersome. Moreover, there are many theoretical assumptions in the mechanism model, but in practice, the model is difficult to apply. For biogas high-pressure water washing o...

AI Technical Summary

Problems solved by technology

However, some old data will only bring errors to the model, making the overall prediction effect of ELM lower

Secondly, the quality of the new sample will affect the prediction accuracy. For example, the data characteristics of the new sample are quite different from the old sample, which will cause a transient situation in the prediction curve. If the network is trained according to the data trend of this new sample, the training deviation will be relatively large. Large, degraded generalization performance of online extreme learning machines

Most scholars only consider the role of old data and add forgetting factors, but ignore the impact of changes in the characteristics of new samples, which affects the accuracy of the biogas high-pressure water washing model

Images