Predicting system and predicting method configured to predict inflow volume of rainwater

• US 6,474,153 B1
• Filed: 02/22/2000
• Issued: 11/05/2002
• Est. Priority Date: 03/09/1999
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yamanaka, Osamu, Nagaiwa, Akihiro, Nakada, Masajiro, Tsutsumi, Masahiko
• Primary Examiner(s): Fuller, Benjamin R.
• Assistant Examiner(s): Allen, Andre J.
• Application Number:
  US09/510,670
• Time in Patent Office: 987 Days
• Field of Search: 731/701.7, 731/701.8, 731/702.1, 702/3, 706/931
• US Class Current: 73/170.17
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G01W 1/14 Rainfall or precipitation gauges measuring volume in general G01F

Abstract

A predicting system configured to predict an inflow volume of rainwater includes a rainfall volume measuring unit for measuring a rainfall volume that has fallen by a present time, a rainfall volume predicting unit for predicting a rainfall volume in a future, and an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flown into an objective facility by the present time. The system also includes a model identification unit, which has a non-linear model having a Neural-Network model for calculating an inflow volume of rainwater from a rainfall volume, and which has a parameter determining part for determining a degree and coefficient parameters of the non-linear model, based on the rainfall volume that has fallen by the present time measured by the rainfall volume measuring unit and the inflow volume of rainwater that has flown into the objective facility by the present time measured by the inflow-volume measuring unit. An inflow-volume predicting unit is adapted to predict an inflow volume of rainwater flowing into the objective facility in the future, based on the rainfall volume in the future predicted by the rainfall volume predicting unit, according to the non-linear model determined by the model identification unit. Thus, the inflow volume of rainwater flowing into the objective facility can be predicted more accurately even if there is a non-linear relationship between the rainfall volume and the inflow volume of rainwater.

Claims

1. A system configured to predict an inflow volume of rainwater, comprising:

a rainfall volume measuring unit for measuring a rainfall volume that has fallen by a present time;

a rainfall volume predicting unit for predicting a rainfall volume in a future time period;

an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

a model identification unit comprising

a nonlinear model that includes a Neural-Network model for calculating an inflow volume of rainwater from a rainfall volume, and

a parameter determining part for determining degree and coefficient parameters of the nonlinear model, based on the rainfall volume that has fallen by the present time measured by the rainfall volume measuring unit and the inflow volume of rainwater that has flowed into the objective facility by the present time measured by the inflow-volume measuring unit;

an inflow-volume predicting unit for predicting an inflow volume of rainwater that will flow into the objective facility in a future time period, based on the future rainfall volume predicted by the rainfall volume predicting unit, according to the nonlinear model and parameters determined by the model identification unit; and

wherein (1) the rainfall volume predicting unit is associated with the inflow-volume predicting unit and the rainfall volume measuring unit, and (2) the parameter determining part is associated with the rainfall volume measuring unit, the inflow-volume measuring unit, and the inflow-volume predicting unit.

2. A system configured to predict an inflow volume of rainwater according to claim 1, wherein:

the rainfall volume measuring unit is adapted to measure amounts of rainfall that have fallen in unit time periods up to the present time;

the inflow-volume measuring unit is adapted to measure inflow volumes of rainwater that have flowed into the objective facility in unit time periods up to the present time; and

the parameter determining part is adapted to determine the degree and the coefficient parameters of the nonlinear model, based on a plurality of data that includes the amounts of rainfall that have fallen in the respective unit time periods up to the present time measured by the rainfall volume measuring unit and a plurality of data that includes the inflow volumes of rainwater that have flowed into the objective facility in the respective unit time periods up to the present time measured by the inflow-volume measuring unit.

3. A system configured to predict an inflow volume of rainwater according to claim 2, wherein:

the rainfall volume measuring unit is connected to a rainfall volume data picking-up unit which is adapted to pick up only necessary rainfall data from the plurality of data that includes the amounts of rainfall that have fallen in the respective unit time periods up to the present time measured by the rainfall volume measuring unit;

the inflow-volume measuring unit is connected to an inflow-volume data picking up unit which is adapted to pick up only data of the inflow volumes of rainwater corresponding to the picked up data of the amounts of rainfall, from the plurality of data on the inflow volumes of rainwater that have flowed into the objective facility in the respective unit time periods up to the present time measured by the inflow-volume measuring unit; and

wherein the parameter determining part is associated with the rainfall volume data picking-up unit and the inflow-volume data picking unit.

4. A system configured to predict an inflow volume of rainwater according to claim 1, wherein:

the model identification unit includes an efficient rainfall-volume calculating part for calculating a contributing rainfall-volume to an inflow volume of rainwater flowing into the objective facility, based on preceding rainfall data;

the parameter determining part is adapted to determine the degree and the coefficient parameters of the nonlinear model, based on the contributing rainfall-volume calculated by the efficient-rainfall-volume calculating part and the inflow volume of rainwater that has flowed into the objective facility up to the present time measured by the inflow-volume measuring unit; and

wherein the efficient rainfall-volume calculating part is associated with the rainfall volume measuring unit and the parameter determining part.

5. A system configured to predict an inflow volume of rainwater according to claim 1, wherein:

at least one of the rainfall volume measuring unit and the inflow-volume measuring unit has a noise-reducing part.

6. A system configured to predict an inflow volume of rainwater according to claim 1, wherein:

a plurality of rainfall volume measuring units are arranged in an area covered by the objective facility, for measuring a plurality of data of amounts of rainfall;

the rainfall volume predicting unit is adapted to predict a plurality of data that includes amounts of rainfall in a future time period corresponding to the plurality of rainfall volume measuring units;

the nonlinear model is a model into which a plurality of data are inputted;

the parameter determining part is adapted to determine the degree and the coefficient parameters of the nonlinear model based on the plurality of rainfall data measured by the plurality of rainfall volume measuring units and the inflow volume of rainwater that has flowed into the objective facility. by the present time measured by the inflow-volume measuring unit; and

the inflow-volume predicting unit is adapted to predict the inflow volume of rainwater that will flow into the objective facility in the future, based on the plurality of data on the rainfall in a future time period predicted by the rainfall volume predicting unit, according to the nonlinear model determined by the model identification unit.

8. A system configured to predict an inflow volume of rainwater according to claim 1, wherein:

the parameter determining part has a program constructed by an algorithm using a least-squares method.

18. A system configured to predict an inflow-volume of rainwater according to claim 1, wherein the model is a linear model.

19. A system configured to predict an inflow-volume of rainwater according to claim 1, wherein the model is a nonlinear model.

7. A system configured to predict an inflow volume of rainwater, comprising:

a rainfall volume measuring unit for measuring a rainfall volume that has fallen by a present time;

a rainfall volume predicting unit for predicting a rainfall volume in a future time period;

an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

a model identification unit comprising

an efficient-rainfall-volume calculating part for calculating a contributing rainfall-volume to an inflow volume of rainwater flowing into the objective facility, based on preceding rainfall and a non-linear model,

a linear model for calculating an inflow volume of rainwater from a rainfall volume, and

a parameter determining part for determining degree and coefficient parameters of the linear model, based on the contributing rainfall-volume calculated by the efficient-rainfall-volume calculating part and the inflow volume of rainwater that has flowed into the objective facility by the present time measured by the inflow-volume measuring unit;

an inflow-volume predicting unit for predicting an inflow volume of rainwater that will flow into the objective facility in a future time period, based on the future rainfall volume predicted by the rainfall volume predicting unit, according to the linear model and parameter determined by the model identification unit; and

wherein (1) the rainfall volume predicting unit is associated with the rainfall volume measuring unit and the inflow-volume predicting unit, (2) the parameter determining part is associated with the inflow-volume measuring unit, the inflow-volume predicting unit, and the efficient-rainfall-volume calculating part, and (3) the rainfall volume measuring unit is associated with the efficient-rainfall-volume calculating part.

9. A system configured to predict an inflow volume of rainwater according to claim 7, wherein:

the parameter determining part has a program constructed by an algorithm using a least-squares method.

10. A system configured to predict an inflow volume of rainwater, comprising:

a rainfall volume measuring unit for measuring a rainfall volume that has fallen by a present time;

an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

a model identification unit having

a nonlinear model for calculating an inflow volume of rainwater from a rainfall volume, and

a parameter determining part for determining degree and coefficient parameters of the nonlinear model, based on the rainfall volume that has fallen by the present time measured by the rainfall volume measuring unit and the inflow volume of rainwater that has flowed into the objective facility by the present time measured by the inflow-volume measuring unit;

an inflow-volume predicting unit for predicting an inflow volume of rainwater that will flow into the objective facility in a future time period, based on the rainfall volume that has fallen by the present time measured by the rainfall volume measuring unit, according to the nonlinear model and parameters determined by the model identification unit; and

wherein (1) the parameter determining part is associated with the inflow-volume predicting unit, the inflow-volume measuring unit, and the rainfall volume measuring unit, and (2) the inflow-volume predicting unit is associated with the rainfall volume measuring unit.

11. A system configured to predict an inflow volume of rainwater according to claim 10, wherein:

a plurality of rainfall volume measuring units are arranged in an area covered by the objective facility, for measuring a plurality of data of amounts of rainfall,

the nonlinear model is a model into which a plurality of data are inputted,

the parameter determining part is adapted to determine the degree and the coefficient parameters of the nonlinear model based on the plurality of rainfall data measured by the plurality of rainfall volume measuring units and the inflow volume of rainwater that has flowed into the objective facility by the present time measured by the inflow-volume measuring unit; and

the inflow-volume predicting unit is adapted to predict the inflow volume of rainwater that will flow into the objective facility in the future, based on the plurality of data on the amounts of rainfall that has fallen by the present time measured by the plurality of rainfall volume measuring units, according to the nonlinear model determined by the model identification unit.

12. A system configured to predict an inflow volume of rainwater, comprising:

a rainfall volume measuring unit for measuring a rainfall volume that has fallen by a present time;

an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

a model identification unit having

an efficient-rainfall-volume calculating part for calculating a contributing rainfall-volume to an inflow volume of rainwater flowing into the objective facility, based on a preceding rainfall and a nonlinear model,

a linear model for calculating an inflow volume of rainwater from a rainfall volume, and

a parameter determining part for determining degree and coefficient parameters of the linear model, based on the contributing rainfall-volume calculated by the efficient-rainfall-volume calculating part and the inflow volume of rainwater that has flowed into the objective facility by the present time measured by the inflow-volume measuring unit;

an inflow-volume predicting unit for predicting an inflow volume of rainwater that will flow into the objective facility in a future time period, based on the rainfall volume that has fallen by the present time measured by the rainfall volume measuring unit, according to the linear model determined by the model identification unit; and

wherein (1) the parameter determining part is associated with the inflow-volume predicting unit, the inflow-volume measuring unit, and the efficient-rainfall-volume calculating part, and (2) the rainfall volume measuring unit is associated with the inflow-volume predicting unit and the efficient-rainfall-volume calculating part.

13. A method for predicting an inflow volume of rainwater flowing into an objective facility comprising:

measuring a rainfall volume that has fallen by a present time;

predicting a rainfall volume in a future time period using the measured rainfall volume;

measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

determining degree and coefficient parameters of a nonlinear model based on a rainfall volume that has fallen by the present time and an inflow volume of rainwater that has flowed into the objective facility by the present time; and

predicting the inflow volume of rainwater that will flow into the objective facility in the future, based on a predicted future rainfall volume, according to the nonlinear model that includes a neural network model.

14. A method for predicting an inflow volume of rainwater flowing into an objective facility comprising:

measuring a rainfall volume that has fallen by a present time;

predicting a rainfall volume in a future time period using the measured rainfall volume;

measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

calculating a contributing rainfall-volume to the inflow volume of rainwater flowing into the objective facility based on the preceding rainfall and a nonlinear model;

determining degree and coefficient parameters of a linear model, based on the contributing rainfall-volume and an inflow volume of rainwater that has flowed into the objective facility by the present time; and

predicting the inflow volume of rainwater that will flow into the objective facility in the future, based on a predicted future rainfall volume, according to the linear model.

15. A method for predicting an inflow volume of rainwater flowing into an objective facility comprising:

measuring a rainfall volume that has fallen by a present time;

measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

determining degree and coefficient parameters of a nonlinear model, based on a rainfall volume that has fallen by the present time and an inflow volume of rainwater that has flowed into the objective facility by the present time; and

predicting the inflow volume of rainwater that will flow into the objective facility in the future, based on the rainfall volume that has fallen by the present time, according to the nonlinear model.

16. A method for predicting an inflow volume of rainwater flowing into an objective facility comprising:

measuring a rainfall volume that has fallen by a present time;

measuring an inflow volume of rainwater that has flowed into an objective facility by the present time;

calculating a contributing rainfall-volume to the inflow volume of rainwater flowing into the objective facility based on a preceding rainfall and a nonlinear model;

determining degree and coefficient parameters of a linear model, based on the contributing rainfall-volume and an inflow volume of rainwater that has flowed into the objective facility by the present time; and

predicting the inflow volume of rainwater that will flow into the objective facility in the future, based on a rainfall volume that has fallen by the present time, according to the linear model.

17. A system configured to predict an inflow-volume of rainwater, comprising:

a rainfall volume measuring unit for measuring rainfall volume that has fallen by a present time, referred to as rainfall volume data;

an inflow-volume measuring unit for measuring an inflow volume of rainwater that has flowed into an objective facility by the present time, referred to as inflow-volume data;

a model identification unit having

a model for calculating an inflow-volume of rainfall from rainfall volume data, and

a parameter determining part for determining parameters in the model, based on at least one of the rainfall volume data and the inflow-volume data;

an inflow-volume predicting unit for predicting an inflow-volume of rainwater that will flow into the objective facility in a future time period, based on the rainfall volume data according to the model and parameters determined by the model identification unit; and

wherein (1) the parameter determining part is associated with the rainfall-volume measuring unit, the inflow-volume predicting unit, and the inflow-volume measuring unit, and (2) the inflow-volume predicting unit is associated with the rainfall-volume measuring unit.