Boiler operation parameter processing method and device, boiler controller and medium

A technology for operating parameters and parameter processing, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as technical faults, increase in boiler failure rate, and decline in economic benefits of boiler energy supply.

Pending Publication Date: 2020-04-17
青岛特利尔科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it does not rule out that some parts of the boiler have problems that are difficult to find before the heating season is over. Therefore, such problems generally do not have a large impact on the operation of the boiler in a short period of time, that is, the characteristics are not obvious.
Therefore, in the case of experienced technicians resigning, technical faults are prone to occur, resulting in a decline in the economic benefits of boiler energy supply and an increase in boiler failure rates

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Boiler operation parameter processing method and device, boiler controller and medium
  • Boiler operation parameter processing method and device, boiler controller and medium
  • Boiler operation parameter processing method and device, boiler controller and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] See figure 1 , figure 1 A flow chart of a method for processing boiler operating parameters provided in an embodiment of the present application, which includes the following steps:

[0082] S101: Obtain the first operating parameter of the boiler;

[0083] This step aims at obtaining the first operating parameter of the boiler, which is collected when the boiler is in an actual operating state. Specifically, the first operating parameter can be obtained through feedback or reading from various sensors and indicator light devices arranged on the boiler, and it is not specifically limited here.

[0084] S102: Input the first operating parameter as input data into the trained long-short-term memory network;

[0085] Wherein, the long-short-term memory network is pre-trained using the historical first operating parameters of the boiler in the historical operating process.

[0086] On the basis of S101, this step aims to input the first operating parameter as input data...

Embodiment 2

[0097] On the basis of Embodiment 1, considering the actual use state of the heating boiler, there may be as many as 200 parameters that can be used as input parameters, but if the parameter weights of these 200 different types of boiler physical variables are input as input parameters The long-short-term memory network not only requires extremely long calculation time, but also considers that a considerable part of the network is not highly correlated with the second operating parameter to be used as an output parameter, and the calculation is of little significance, which will reduce the calculation efficiency.

[0098] Therefore, on the basis of Embodiment 1, this embodiment passes figure 2 The flow chart shown provides a flow chart of a method for obtaining the first operating parameter, which specifically includes the following steps:

[0099] S201: Obtain all physical variables related to boiler operation;

[0100] S202: Screen all the physical variables through the mu...

Embodiment 3

[0124] On the basis of any of the above embodiments, this step considers that the first operating parameter containing multiple types of data may cause problems such as the existence of wrong characters, loss, and invalid data due to various reasons. Based on the image 3 The flow chart of a data cleaning method shown includes the following steps:

[0125] S301: Obtain the first operating parameter of the boiler;

[0126] S302: Using regular expressions to correct wrong characters in the first operating parameter;

[0127] S303: Fill in the missing part in the middle according to the mean value of the parameters within the preset duration before and after;

[0128] For example, for missing data, it is filled with the mean value of the data of 60 seconds before and after.

[0129] S304: Eliminate the maximum error in the first operating parameter by using the Leite rule;

[0130] S305: Input the first operating parameter after data cleaning into the trained long short-term ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a boiler operation parameter processing method. A long-term and short-term memory network is obtained by training historical operation parameters of a boiler; deeper processingcan be carried out on boiler operation parameters by means of a deep learning algorithm; the hidden features hidden below the data surface layer are mined, so that the parameters capable of feeding back the actual operation condition of the boiler more comprehensively and more accurately are extracted, whether the boiler has potential safety hazards or not can be judged more accurately and more timely, and the operation state can be adjusted in time. Meanwhile, different from other deep learning algorithms, the long-term and short-term memory network can significantly enhance the discriminating ability of operating parameters which are low in occurrence frequency, long in interval and capable of causing serious consequences, and is especially suitable for the actual use condition of a heat supply boiler. The invention further discloses a boiler operation parameter processing device, a boiler controller and a readable storage medium which have the above beneficial effects.

Description

technical field [0001] The present application relates to the technical field of operation and maintenance of heating boilers, in particular to a method and device for processing boiler operating parameters, a boiler controller and a readable storage medium. Background technique [0002] The load of the heating boiler is mainly based on the energy supply demand. When the demand is certain, technicians can operate and maintain the boiler through a series of control methods such as adjusting the ratio of primary and secondary air supply, and the amount of fuel supplied. For the same boiler, different operation and maintenance methods have different energy consumption and output ratios. On the premise of ensuring the safety of boiler operation, how to use appropriate control methods to improve the economic benefits of heating has become a topic of increasing concern to heating companies and technicians. [0003] The boiler is a pressure vessel, and safe production is the top p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06Q10/00
CPCG06N3/08G06Q10/20G06N3/044G06N3/045G06F18/2135G06F18/24
Inventor 白彧梅宁李瑞国刘思杰郭成科黄贤坤闫蕾
Owner 青岛特利尔科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products