A dissolved oxygen concentration optimization method based on activated sludge water treatment
A technology of dissolved oxygen concentration and activated sludge, which is applied in general water supply conservation, neural learning methods, electrical digital data processing, etc., can solve problems such as difficulty in establishing mathematical models for dissolved oxygen concentration and influencing factors, and difficulty in establishing mathematical models
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2019-05-03
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The present invention adopts an integrated learning method based on xgboost to predict the parameter value of effluent water quality in real time. The difference between the effluent parameter value and the national standard value is used as feedback information, and the improved particle swarm optimization algorithm is used to globally optimize the parameter value to obtain the initial global optimal value. The BP neural network is used to establish a multi-objective optimization model with constraints to solve the problem that there is no precise mathematical description between the dissolved oxygen concentration and its influencing factors. Background technique
[0002] In recent years, with the rapid development of the economy, the level of urbanization and industrialization is getting higher and higher, and the demand for water resources in the economy and society is increasing year by year. At the same time, the continuous discharge of industria...
Examples
Embodiment
[0088] In the present invention, by analyzing the coupling between the various influencing factors in the activated sludge process and researching the treatment process, the integrated learning model based on XGBoost is used to predict the effluent parameter value, and the APSO-BP algorithm is used to optimize the dissolved oxygen concentration. Proceed as follows:
[0089] Step 1: Collect data from two sewage plants in Jinniu and Wanshan, and divide the data set into training set, verification set and test set according to the ratio of 3:1:1; the training set is used to train the model; the verification set is used to To detect whether the model is overfitting or underfitting, and judge the learning effect of the model; the test set is used to detect the generalization ability of the model. The data set here is the input data set of the xgboost effluent water quality prediction model.
[0090] Step 2: According to the characteristics of the data, make normal adjustments to s...