An Intelligent Identification Method of Flood Control System Effective Engineering Based on Random Forest

Abstract

The invention discloses a random forest-based intelligent identification method for a flood control system markedly effective project, which includes: establishing a random forest feature attribute set; establishing a "mixed equivalent dispatch" model of a flood control system, generating training and verification sample sets; based on "random" thought Build a random forest base classifier; build a random forest classification model based on the idea of ​​"integration"; establish a classification accuracy evaluation index considering unequal costs, and evaluate the identification accuracy of significant projects. The method of the invention aims at the characteristics of "small samples" of historical floods in the flood control system, in order to make full use of the attribute set and training sample information, and based on the two ideas of "random" and "integration" of random forest, the classification accuracy of markedly effective projects is improved; To improve the identification efficiency of obvious engineering; for the problem of uneven cost of different types of errors in identification results, the expected overall cost is used to evaluate the classification accuracy of random forest.

Description

technical field [0001] The invention relates to a real-time scheduling method of a flood control system, in particular to a method for intelligent identification of a flood control system manifested effect engineering based on random forest. Background technique [0002] In the real-time joint dispatch of the flood control system, it is an effective way to reduce the dimension of the joint dispatch model of the flood control system, which is an effective way to reduce the dimension of the joint dispatch model of the flood control system. Accurately identify significant engineering sets. [0003] "Significant effect project" is a brand-new concept in the field of flood control and dispatching. At present, there is little research on it. The existing technology is based on inference rules to identify marked effect projects. This method is to establish an identification index system and determine the inference rules through the index thresholds, but the determination of the in...

AI Technical Summary

Problems solved by technology

[0005] In the process of effective engineering identification, different types of errors will cause different degrees of consequences

Misjudgment of non-effective projects as effective projects will only increase the complexity of flood control scheduling; misjudgment of effective projects as non-effective projects will reduce flood control effects, increase flood control risks, and even cause downstream flood disasters. Therefore, the cost of such mistakes is much greater than that of the former

Images