An Online Measuring Method of Carbon Content in Fly Ash Based on BP Neural Network
A technology of BP neural network and fly ash carbon content, which is applied in the direction of neural learning method, biological neural network model, measuring device, etc., can solve the problems of measurement accuracy interference, need to calibrate, difficult maintenance, etc., and achieve the effect of accurate measurement
Active Publication Date: 2021-05-18
西安帝和电子科技有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The physical measurement methods mainly include: combustion weight loss method, electrostatic method, microwave method, etc. There are many products that measure the carbon content of fly ash based on physical measurement methods, which have high measurement accuracy and high real-time performance, but most of them require calibration. , maintenance is not easy, the measurement accuracy is disturbed by many factors, etc.
Soft-sensing methods have the advantages of good generalization performance and high prediction accuracy, and have good application prospects, but most of them only stay in the theoretical stage at present, only for modeling and simulation, offline prediction, and no practical application products
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 Construction
[0029] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.
[0030] An online measurement method of fly ash carbon content based on BP (Back Propagation) neural network,
[0031] Step 1: Based on the electrostatic sensor, build a 3-layer BP neural network model with input as signal energy, fly ash sample concentration, and output as fly ash carbon content, and use training samples to conduct online parameter training of BP neural network model;
[0032] When the temperature T of the fly ash sample is constant and the fly ash flows through the air powder pipeline, the energy of the AC electrostatic signal collected by the electrostatic sensor has a nonlinear relationship with the concentration and carbon content of the fly ash sample. The carbon content of the existing m types are respectively c 1 ,c 2 ,...,c m Fly ash sample, record c i is the carbon content of the i-th fly ash sample, i=1, 2,...,m,...
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 an on-line measurement method of fly ash carbon content based on BP neural network. Based on electrostatic sensors, a three-layer BP neural network model is constructed with the input as signal energy, fly ash sample concentration and the output as fly ash carbon content , using the training samples to train the BP neural network online parameters; using the Genetic Algorithm to optimize the BP neural network to obtain the global optimal solution of the BP neural network parameters; Online parameter training is carried out, and the electrostatic signal sequence and concentration of fly ash samples with unknown carbon content are collected in real time based on electrostatic sensors. After normalization, they are used as prediction input to predict the carbon content of fly ash online. In order to solve the problems of modeling simulation and offline prediction in the current soft measurement method of fly ash carbon content, the real-time and online accurate measurement of the fly ash carbon content flowing through the pipeline is realized.
Description
technical field [0001] The invention belongs to the technical field of sensor detection and digital signal processing, and in particular relates to a method for measuring the carbon content of fly ash based on a BP neural network. Background technique [0002] In actual thermal power generation, the content of fly ash in the flue gas at the tail of coal-fired boilers can reach more than 90%, which is an important indicator of the combustion efficiency of boilers in thermal power plants. Different coal types, different structural characteristics of the boiler combustion system, and different combustion conditions will lead to insufficient combustion of coal powder, and the carbon content of fly ash in the flue gas at the tail of the boiler is too high, which often leads to insufficient burner output and reduced combustion efficiency , The unit is prone to malfunctions and other problems. In severe cases, the boiler will be extinguished, which will cause the unit to stop opera...
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): G01N15/06G06N3/08
CPCG01N15/06G06N3/084G06N3/086
Inventor 弋英民税莹
Owner 西安帝和电子科技有限公司