Dissolved oxygen concentration soft-measuring method based on group decision case reasoning

Abstract

The invention provides a dissolved oxygen concentration soft-measuring method based on group decision case reasoning, realizes the precise estimate of dissolved oxygen concentration, and aims to solve the problems that an analytical instrument for dissolved oxygen concentration in the sewage disposal process lags in measurement and difficult to built a precise mathematic model for estimate the dissolved oxygen concentration. According to the method, a case reasoning soft-measuring model can be built through the steps of determining characteristic variable, building soft-measuring case library, distributing weight, obtaining target cases, normalizing numerical value, retrieving cases, reusing group decision cases, storing cases, and the like, and an algorithm can be implemented, so that the measurement error can be reduced; the problem of measuring lag of the analytical instrument can be solved, and the complex process for building a precise mathematic model can be avoided; the experimental result shows that the method can be used for quickly and precisely estimating the dissolved oxygen concentration, has the self-learning ability, reduces the purchasing and maintenance cost of the analytical instrument, and facilitates the real-time monitoring of the dissolved oxygen concentration.

Description

technical field [0001] The invention utilizes the case reasoning technology in the field of artificial intelligence to realize the soft measurement of the dissolved oxygen concentration in the sewage treatment process. The real-time and rapid detection of the dissolved oxygen concentration is the prerequisite for the stable control of the concentration, which will affect the sewage treatment effect. As an important part of sewage treatment, the detection of dissolved oxygen concentration in the process of sewage treatment is an important branch of advanced manufacturing technology, which belongs to both the field of artificial intelligence and the field of water treatment. Background technique [0002] With the growth of the national economy and the enhancement of public awareness of environmental protection, sewage treatment technology has ushered in unprecedented opportunities for development. The national medium and long-term scientific and technological development plan ...

AI Technical Summary

Problems solved by technology

However, when using neural network modeling, there are usually the following problems: lack of effective methods to determine the number of hidden layers and nodes; the model has problems of overfitting and poor generalization ability; it is easy to fall into local minimum points, and cannot guarantee the global optimum

In addition, the support vector machine modeling method also has some problems. For example, for large data sets, the training speed is slow, and the selection of parameters mainly depends on experience and has uncertainty.

As a relatively new machine learning method, case reasoning is widely used in classification, predictive regression and other fields. The weight distribution results of its characteristic variables have an important impact on the quality of reasoning solutions. Genetic algorithm is a typical objective distribution method. The weight distribution of feature variables is obtained through multiple random iterative evolutions, but the iterative optimization ability of the genetic algorithm has not been fully utilized when assigning weights, and the weight distribution information contained in the case base has not been fully excavated, resulting in subsequent similarities. Degree calculations and problem solving are adversely affected

The existence of the above factors has brought adverse effects on the application effect of the soft sensor model, and new treatment methods must be found to meet the needs of real-time and accurate measurement of dissolved oxygen concentration in the sewage treatment process

Images