POWER PLANT CONTROL DEVICE WHICH USES A MODEL, A LEARNING SIGNAL, A CORRECTION SIGNAL, AND A MANIPULATION SIGNAL

• US 20120166375A1
• Filed: 03/09/2012
• Published: 06/28/2012
• Est. Priority Date: 11/20/2007
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: HAYASHI, Yoshiharu, YAMADA, Akihiro, SHIMIZU, Satoru, SEKIAI, Takaaki, FUKAI, Masayuki
• Granted Patent: US 8,554,706 B2
• Time in Patent Office: Days
• US Class Current: 706/17
• 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 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, comprising:

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.

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

(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 extracted in step (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.

3. The gas concentration estimation method according to claim 2, wherein step (b) includes

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

(b2) filtering the specified data to eliminate the data.

4. The gas concentration estimation method according to claim 2, wherein step (b) includes

(b3) extracting the process data having input signals including one reference input signal and the other input signals each having a value within a predetermined threshold value range 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 the 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.

5. The gas concentration estimation method according to claim 4, further comprising the step of:

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