Power plant control device which uses a model, a learning signal, a correction signal, and a manipulation signal

• US 8,554,706 B2
• Filed: 03/09/2012
• Issued: 10/08/2013
• Est. Priority Date: 11/20/2007
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Hayashi, Yoshiharu, Yamada, Akihiro, Sekiai, Takaaki, Shimizu, Satoru, Fukai, Masayuki
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US13/415,876
• Publication Number:
  US 20120166375A1
• Time in Patent Office: 578 Days
• Field of Search: 706/12, 706 45- 48, 73/10.1, 73/10.2, 73/10.6, 73/190.1, 73/232, 73/233.1, 73/233.2, 73/233.3, 703/1, 702/1, 702/85, 702/98, 702/99, 702/104, 702/24
• US Class Current: 706/16
• CPC Class Codes: G05B 13/027 using neural networks only

Abstract

A gas concentration estimation device of a coal-burning boiler adapted to estimate the concentration of the gas component included in an exhaust gas emitted from a coal-burning boiler using a neural network, including: a process database section adapted to store process data of a coal-burning boiler; a filtering processing section adapted to perform filtering processing for extracting data suitable for learning of a neural network from the process data stored in the process database section; a neural-network learning processing section adapted to perform learning processing of the neural network based on the data extracted by the filtering processing section and suitable for learning of the neural network; and a neural-network estimation processing section adapted to perform estimation processing of the CO concentration or the NOx concentration in the exhaust gas emitted from the coal-burning boiler based on the learning processing of the neural-network learning processing section.

Claims

1. A gas concentration estimation method for a coal-burning boiler, adapted to estimate a concentration of a gas component emitted from a coal-burning boiler using a neural network comprising:

(a) storing process data of the coal-burning boiler;

(b) performing filtering processing for extracting data suitable for learning of a neural network, from the process data stored;

(c) performing learning processing of the neural network based on the data which is extracted in (b) and suitable for learning of the neural network; and

(d) performing estimation processing of one of the CO concentration and the NOx concentration in an exhaust gas emitted from the coal-burning boiler, based on the learning processing of the neural-network;

wherein (b) includes;

(b1) specifying error data within the data, which includes a substantial error with respect to the data used for learning of the neural network, based on a trend of a variation to signals used as input signals of the neural network, and

(b2) filtering the specified error data to eliminate the error data from the data used in the learning processing of the neural network;

(b3) extracting the process data having input signals including one reference input signal and the other input signals, where each of the other input signals having a value within a predetermined threshold value range and each of the values are close to each other, to make a group, with respect to the process data used for learning of the neural network and having signals used as input signals of the neural network,

(b4) obtaining a function of fitting the relationship between the reference input signal and a gas concentration signal value as the estimation object, both included in the process data belonging to the same group, and

(b5) specifying the data to be eliminated based on the difference between the value of the function thus fitted and the signal value of one of the CO concentration and the NOx concentration as the estimation object.

2. The gas concentration estimation method according to claim 1, further comprising:

(e) displaying, on a display device, the data belonging to the same group, the function obtained in step (b4), and the data eliminated.

3. A gas concentration estimation method for a coal-burning boiler, adapted to estimate a concentration of a gas component emitted from a coal-burning boiler using a neural network, comprising:

(a) storing process data of the coal-burning boiler;

(b) performing filtering processing for extracting data suitable for learning of a neural network, from the process data stored;

(c) performing learning processing of the neural network based on the data which is extracted in (b) and suitable for learning of the neural network; and

(d) performing estimation processing of one of the CO concentration and the NOx concentration in an exhaust gas emitted from the coal-burning boiler, based on the learning processing of the neural-network;

wherein (b) includes performing filtering processing prior to a neural-network learning process, for extracting data suitable for learning of a neural network, from the process data stored in the process database section, where the filtering processing eliminating error data from the data, which exceeds a predetermined threshold variation from a trend shown by the data.