Control device, method for calculating change amount, and program

Abstract

This device provides an effective way to maintain the controllability of water treatment plants using machine learning over a wide range of applications. [Solution] The control device 100 is a device for controlling a water treatment plant 1 and includes: an accumulation unit 112 that accumulates a plurality of performance records each containing the state of the water treatment plant 1 and the amount of operation performed on the water treatment plant 1; a model generation unit 113 that generates a model representing the relationship between one or more explanatory variables related to the state of the water treatment plant 1 and a target variable indicating the amount of change to the operation, using machine learning based on the plurality of performance records; and a calculation unit 115 that calculates the amount of change to the operation based on the current state of the water treatment plant 1 and the model.

Claims

1. A device for controlling a water treatment plant, A storage unit that stores multiple performance records, each containing the state of the water treatment plant and the amount of operations performed on the water treatment plant, A model generation unit generates a model representing the relationship between one or more explanatory variables related to the state of the water treatment plant and a target variable indicating the amount of change to the manipulated variable, using machine learning based on the multiple performance records. A calculation unit that calculates the amount of change to the manipulated variable based on the current state of the water treatment plant and the model, A control device equipped with the following features.

2. The model generation unit generates a model that represents the relationship between the state of the water treatment plant, a plurality of explanatory variables representing the history of the change amount, and the objective variable representing the change amount of the manipulated variable. The control device according to claim 1.

3. The model generation unit generates a model that represents the relationship between a plurality of explanatory variables, including the previous change amount of the manipulated variable, as explanatory variables representing the history of the change amount, and the target variable representing the change amount. The control device according to claim 2.

4. The model generation unit generates a model that represents the relationship between a plurality of explanatory variables, which include a plurality of manipulated variables arranged in a time series, and the target variable, which represents the amount of change, as explanatory variables representing the history of the amount of change. The control device according to claim 2.

5. The model generation unit generates the model such that the values ​​of the target variable are different in the case where the history of the change amount indicates an increase in the manipulated amount and in the case where the history of the change amount indicates a decrease in the manipulated amount, even if the state of the water treatment plant is the same. A control device according to any one of claims 2 to 4.

6. The aforementioned water treatment plant is a water treatment plant that treats sewage using microorganisms, The aforementioned operating amount includes the amount of air blown into the sewage. A control device according to any one of claims 1 to 4.

7. One or more explanatory variables related to the state of the water treatment plant are: The volume of the wastewater to be treated, The amount of microorganisms in the aforementioned sewage, The amount of oxygen in the aforementioned sewage, The aforementioned manipulated amount and, The quantity representing the water quality of the aforementioned sewage, Including at least one of the following: The control device according to claim 6.

8. When the aforementioned multiple performance records are updated, the model generation unit regenerates the model based on the updated multiple performance records. A control device according to any one of claims 1 to 4.

9. The model generation unit generates the model using the random forest method. A control device according to any one of claims 1 to 4.

10. The system further includes a display unit that displays the amount of change calculated by the calculation unit. A control device according to any one of claims 1 to 4.

11. The calculation unit further calculates the next operation amount based on the change amount and the operation amount. A control device according to any one of claims 1 to 4.

12. The system further includes a display unit that displays the next operation amount calculated by the calculation unit. The control device according to claim 11.

13. Accumulating multiple performance records, each containing the status of the water treatment plant and the amount of operations performed on the water treatment plant, A model representing the relationship between one or more explanatory variables related to the state of the water treatment plant and a target variable indicating the amount of change to the manipulated variable is generated by machine learning based on the multiple performance records. Based on the current state of the water treatment plant and the model, the amount of change to the manipulated variable is calculated. A method for calculating the amount of change, including the change amount.

14. Accumulating multiple performance records, each containing the status of the water treatment plant and the amount of operations performed on the water treatment plant, A model representing the relationship between one or more explanatory variables related to the state of the water treatment plant and a target variable indicating the amount of change to the manipulated variable is generated by machine learning based on the multiple performance records. Based on the current state of the water treatment plant and the model, the amount of change to the manipulated variable is calculated. A program that causes a device to execute a command.

Images