Predictive control method and system for boiler fuel based on machine learning
A boiler fuel and predictive control technology, applied in general control systems, control/regulation systems, adaptive control, etc., can solve the dynamic characteristics of steam temperature adjustment objects and the influence of model parameters, it is difficult to establish accurate mathematical models, and it is difficult to obtain Control performance and other issues to achieve the effect of reducing the range of motion and the number of motions, being easy to use and increasing the lifespan
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] refer to figure 1 and figure 2 , is a machine learning-based boiler fuel predictive control method disclosed in the present invention, comprising the following steps:
[0059] S1. Obtain a temperature signal after water spraying. Wherein, the temperature signal after water spraying is obtained once every preset time, and step S2 is entered after each time the temperature signal after water spraying is obtained.
[0060] S2. Judging whether the currently obtained temperature signal after water spraying is normal; if it is judged that the temperature signal after water spraying is normal, go to step S3; if it is judged that the temperature signal after water spraying is abnormal, go back to step S1.
[0061] Specifically, by comparing the detected temperature parameter with the preset upper limit parameter and lower limit parameter, it is judged whether the temperature signal is normal after water spraying, when the temperature parameter is between the preset upper lim...
Embodiment 2
[0072] refer to Figure 4 , is a machine learning-based boiler fuel predictive control system disclosed in the present invention, comprising a main superheated main steam temperature adjustment module (10), a secondary temperature adjustment module (20) after superheated water spraying, an accumulative learning module (30) and a temperature Deviation calculation module (40). The input pin SP of the temperature sub-adjustment module (20) is connected with the output pin AV of the superheated main steam temperature main adjustment module (10) after superheated water spraying, and the output pin OT of the cumulative learning module (30) is connected with the superheated main steam temperature. The input pin OT of the main adjustment module (10) is connected, the output pin OB of the cumulative learning module (30) is connected with the input pin OB of the superheated main steam temperature main adjustment module (10), and the temperature deviation calculation module (40) The out...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


