A Steam Volume Control Method for Thermal Power Boilers Based on Error Estimation and Steam Load Prediction
A technology of load forecasting and error estimation, applied in control systems, combustion methods, steam generation, etc., can solve problems such as relying on experienced operators, failing to meet load demands, and low operating efficiency, so as to improve safety and stability The effects of reliability, extended operating time and life, and reduced operating costs
Inactive Publication Date: 2017-04-26
UNIV OF JINAN
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0009] The purpose of the present invention is to provide a method for controlling the steam volume of a thermoelectric boiler based on error estimation and steam load prediction, aiming to solve the problem that the automation level of the existing boiler operation is low, and it relies too much on experienced operators. Low, can not meet the demand of load, the problem of unsatisfactory combustion efficiency under manual control
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
Embodiment 1
[0105] Step 1. Select the fuel amount at 100 moments as the input in the RBF neural network. The number of neurons is determined to be 5 through repeated experiments. The center, weight and base width of the network are trained by the gradient descent method; then the calculation is performed by The reliability of the main steam pressure obtained by the model; the final RBF neural network model obtained is:
[0106]
[0107] in:
[0108] weight w i =[39.7305321 96.1073312 19.1010052 114.9258460 73.9998213];
[0109] center
[0110] base width σ i =[-56.4155849 39.8366447 23.1554569 124.0135543 31.5568741];
[0111] The fitting error of the RBF neural network model is as follows Figure 5 shown;
[0112] Step 2, compare the main steam pressure value output by the model with 0.33MPa (the expected main steam pressure value), and obtain the error e, and judge that the absolute value of the error e is less than 0.004MPa, then adopt the fuzzy control strategy; specificall...
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 method for controlling the steam volume of a thermoelectric boiler based on error estimation and steam load prediction. A radial basis function neural network based on a Gaussian kernel function is used to establish a model, and an error estimation is performed between the established model and the actual value; Credibility; design bang-bang controllers and fuzzy controllers, and compare the credibility of the model with the output value of the model. The invention can effectively reduce the operating cost of the circulating fluidized bed boiler, improve the safety and stability of the circulating fluidized bed boiler operation, prolong the operating time and life; improve the combustion efficiency, and achieve the purpose of energy saving and emission reduction, preferably It solves the problem that the automation level of the existing boiler operation is low, too much reliance on experienced operators, improper operation will lead to low operating efficiency, failure to meet the load demand, and unsatisfactory combustion efficiency under manual control.
Description
technical field [0001] The invention belongs to the technical field of thermoelectric boilers, and in particular relates to a method for controlling steam volume of a thermoelectric boiler based on error estimation and steam load prediction. Background technique [0002] Today, my country's air quality has been threatened, and the haze weather is serious. Its origin is mainly the gas produced during the consumption of energy. my country's annual coal consumption has reached nearly 2.1 billion tons, mainly in coal-fired boilers. Except for large-scale power generation boilers, most of my country's thermal power boilers and industrial boilers have low operating efficiency, high unit coal consumption, and serious waste. In order to meet the needs of modern low-carbon economic development, combined with the characteristics of the thermal power industry, only by accurately estimating and reasonably controlling the load of thermal power boilers can energy saving and emission redu...
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 Patent Type & Authority Patents(China)
IPC IPC(8): F22B35/00F23C10/28
Inventor 申涛郑鉴君代桃桃任万杰栾维磊
Owner UNIV OF JINAN