Combustor nozzle air volume prediction method based on numerical simulation and neural network
A burner nozzle and neural network technology, applied in the field of burners, can solve the problems of low measurement accuracy and efficiency, and achieve the effects of reducing human influence, omitting operation steps, and improving measurement accuracy
Pending Publication Date: 2020-11-13
HARBIN BOILER
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is to propose a method for predicting the air volume of the burner nozzle based on numerical simulation and neural network in view of the low measurement accuracy and efficiency of the traditional furnace internal air volume measurement method
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0032] Specific implementation mode one: refer to Figure 5 This embodiment is specifically described. The present invention proposes a method for predicting the air volume of burner nozzles based on numerical simulation and neural network, which simulates and predicts the flow of thermal secondary air in the thermal secondary air duct of thermal power units and the distribution of air volumes at each nozzle. To improve boiler combustion efficiency.
[0033] Based on the collected off-line data, the physical model of the hot secondary air passage of the boiler is established with numerical simulation software, and the relevant air volume, the distribution of the damper and the corresponding data files are generated. Get the data results, get the data results; use the data processing method to process the numerical simulation results; use the neural network prediction, and finally realize the prediction of the air volume of the burner nozzle under different working conditions, ...
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
Login to View More Abstract
The invention discloses a combustor nozzle air volume prediction method based on numerical simulation and a neural network. Aimed at the problems of low measurement precision and low efficiency of thetraditional hearth internal air volume measurement method, the method comprises the following steps of: 1, establishing a physical model of a boiler thermal secondary air duct by utilizing numericalsimulation software, carrying out simulation operation, and generating burner nozzle air volume simulation data under each working condition; 2, performing data cleaning on the generated combustor nozzle air volume simulation data under each working condition; 3, training a neural network according to the processed data, and predicting the air volume of the burner nozzle by using the trained neural network. Artificially set typical working conditions are used as algorithm input to train a neural network, and the combustor nozzle air volume under a large number of other working conditions can be predicted through the model. Algorithms are used for replacing a large amount of work such as artificial grid drawing and numerical simulation. Prediction time is shortened to a great extent, simulation efficiency is improved, an measurement precision is improved.
Description
technical field [0001] The invention relates to the technical field of burners, in particular to a method for predicting the air volume of burner nozzles based on numerical simulation and neural network. Background technique [0002] In order to ensure the stable operation of the boiler, the combustion process of pulverized coal fuel in the boiler furnace must be within a controllable range, which requires an accurate understanding of the distribution of the air volume entering the furnace. However, traditional measurement methods need to be improved in terms of measurement accuracy and efficiency, and are greatly affected by human factors. CFD (Computational Fluid Dynamics) numerical simulation technology has a rich mathematical calculation model, which can accurately reflect fluid flow, heat transfer, and combustion. Wait for the process. But only using CFD prediction, there will be problems such as many operation steps, heavy workload, slow simulation speed, long numeric...
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
Login to View More IPC IPC(8): G06F30/28G06F30/27G06F111/10
CPCG06F30/28G06F30/27G06F2111/10
Inventor 崔宇佳赵明潇夏良伟于强黄莺孙浩马孝纯王静杰沈涛杜宪涛
Owner HARBIN BOILER