Distributed water flow predicting device

• US 5,448,476 A
• Filed: 06/17/1994
• Issued: 09/05/1995
• Est. Priority Date: 06/17/1993
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Kobayashi, Shuichiro, Murayama, Tadayoshi, Kurokawa, Fuktoshi
• Primary Examiner(s): McElheny, Jr., Donald E.
• Application Number:
  US08/262,070
• Time in Patent Office: 445 Days
• Field of Search: 364/420, 364/401, 364/510, 364/148, 364/149, 364/150, 364/151, 364/164, 364/165, 137/78.1, 137/78.5, 137/79, 137/236.1, 395/928, 395/930, 395/931, 395/914, 395/906
• US Class Current: 702/2
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: Y10S 706/914 Process plant

Abstract

The distributed water flow predicting device comprises seasonal prediction model learning means for learning weight coefficients by back propagation over a prediction model a neural network model for predicting daily distributed water flows and specific characters of an hourly distributed water flow pattern for a season, based on processed actual seasonal weather data and seasonal distributed water flows, so as to identify the prediction model. Seasonal distributed water flow predicting means pridicts daily distributed water flows and specific characters of hourly distributed water flow patterns for a required season by using the prediction model, based on inputted information about the weather, temperature, a weekday or a holiday. The seasonal distributed water flow predicting means compares the specific characters of an hourly distributed water flow pattern given by the prediction model with specific characters of past actual distributed water flow patterns so as to retrieve a most similar hourly distributed flow pattern from the past actual distributed water flow patterns, giving the retrieved pattern as a predicted hourly distributed water flow pattern, and multiplys the predicted daily distributed water flow by the predicted hourly distributed water flow pattern to predict an hourly distributed water flow.

Claims

1. A distributed water flow predicting device for predicting an hourly distributed water flow rate for a day to be distributed from a purification plant or a service reservior of a water-supply facility, the device comprising:

actual seasonal weather data processing means for processing actual seasonal weather data, based on stored past actual weather data, and information of a weekday or a holiday;

seasonal distributed water flow data processing means for processing actual seasonal distributed water flows, based on actual hourly distributed water flows for every day;

seasonal prediction model learning means for learning weight coefficients of a neural network model by back propagation over a prediction model for predicting daily distributed water flows and specific characters of an hourly distributed water flow pattern for a season, based on processed data supplied by the seasonal actual weather data processing means and the seasonal distributed water flow data processing means, so as to identify the prediction model; and

seasonal distributed water flow predicting means for predicting daily distributed water flows and specific characters of an hourly distributed water flow pattern for a required season by using the prediction model, based on inputted information about the weather, temperature, a weekday or a holiday, for comparing the specific characters of an hourly distributed water flow pattern given by the prediction model with specific characters of past actual distributed water flow patterns stored in the seasonal distributed water flow data processing means so as to retrieve a most similar hourly distributed flow pattern from the past actual distributed water flow patterns, giving the retrieved pattern as a predicted hourly distributed water flow pattern, and for multiplying the predicted daily distributed water flow by the predicted hourly distributed water flow pattern to predict an hourly distributed water flow.

2. The distributed water flow predicting device according to claim 1, wherein

the specific characters of the hourly distributed water flow pattern compared by the seasonal distributed water flow predicting means include peak values of distributed water flows in the morning and afternoon, and rise values in the morning and afternoon.

3. The distributed water flow predicting device according to claim 2, wherein

the specific characters of the hourly distributed water flow pattern further include a ratio of the peak values in the morning and afternoon.

4. The distributed water flow predicting device according to claim 3, wherein

the specific characters of the hourly distributed water flow pattern includes a time when the peak value in the morning takes place, and a time when the peak value in the afternoon takes place.

5. The distributed water flow rate predicting device according to claim 4, wherein

the specific characters of the hourly distributed water flow rate transition pattern further includes accumulated values of distributed water flows per a unit period of time from the rise points in the morning and afternoon.

6. The distributed water flow rate predicting device according to claim 1, wherein

the specific characters of the hourly distributed water flow pattern include various values indicative of information of the pattern, and the various values are weighted corresponding to their significance to be compared with the actual distributed water flow patterns.