A real-time online monitoring method for low calorific value and volatile matter of coal entering a boiler

By installing ash meter and moisture meter at the inlets of each coal mill of the boiler, and combining neural networks and genetic algorithms, the low-level calorific value and volatile components of the boiler coal entering the boiler are monitored online in real time, which solves the problem that cannot be monitored in real time in the existing technology. Improves the operating efficiency and safety of the boiler.

CN115081312BActive Publication Date: 2024-11-12SOUTHEAST UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210561690.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-23
Publication Date
2024-11-12
Estimated Expiration
2042-05-23

AI Technical Summary

Technical Problem

The existing technology cannot monitor the low-level calorific value and volatile components of the boiler coal in real time, resulting in the inability to adjust the boiler operation efficiency in time, affecting safe, economical and environmentally friendly operations.

Method used

By installing ash meter and moisture meter at the inlets of each coal mill of the boiler, data is collected and a neural network model is established, and the low-level calorific value and volatile components of the coal entering the furnace are calculated in combination with genetic algorithms to achieve real-time online monitoring.

Benefits of technology

Real-time online calculation of boiler efficiency is realized, operators monitor boiler performance changes, key data is provided to optimize combustion parameters, and the safe, economic and environmentally friendly operation level of the boiler is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115081312B_ABST
    Figure CN115081312B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of boiler operation in thermal power plants, and in particular to a real-time online monitoring method for the low calorific value and volatile matter of coal entering the boiler. The method comprises the following steps: online monitoring to obtain the received ash content and received moisture content of coal entering the boiler from each mill, calculating the average received ash content and received moisture content of coal entering the boiler, and sending the data to the DCS of the unit; establishing a neural network model with dry basis ash content and volatile matter as input and dry basis low calorific value as output; and using a genetic algorithm to calculate the low calorific value and volatile matter of coal. The method of the present invention can be used to effectively monitor the calorific value and volatile matter of coal entering the boiler in real time online, making it possible to calculate the boiler efficiency in real time online, and providing key data for optimizing and adjusting boiler combustion, which is beneficial to improving the safe, economical and environmentally friendly operation level of the boiler.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of boiler operation in thermal power plants, and in particular to a real-time online monitoring method for low calorific value and volatile matter of coal fed into a boiler. Background Art

[0002] The quality of coal entering the furnace, especially the calorific value and volatile matter of coal, has a great impact on the combustion operation of the boiler. The calorific value and volatile matter of coal are physical properties of the mixture and cannot be directly measured by hardware. At present, the quality of coal entering the furnace of a power plant is mainly obtained through offline analysis in the laboratory. The coal quality data of offline analysis generally lags behind by about 8 hours, resulting in the inability to monitor the efficiency of the boiler in real time, which is not conducive to the operator to monitor the changes in the operating performance of the boiler; for boilers with frequent changes in the quality of coal entering the furnace, their combustion parameters cannot be adjusted in a timely and effective manner, which seriously affects the safe, economical and environmentally friendly operation of the boiler.

[0003] Affected by the coal market environment, the quality of coal entering the boiler generally changes greatly and frequently. Real-time online monitoring of the calorific value and volatile matter of the coal entering the boiler has great practical significance for improving the energy-saving and emission-reduction operation level of the boiler. Summary of the invention

[0004] The purpose of the present invention is to solve the problems existing in the background technology and to provide a real-time online monitoring method for the low calorific value and volatile matter of coal fed into a boiler.

[0005] The technical solution of the present invention is a real-time online monitoring method for low calorific value and volatile matter of coal fed into a boiler, comprising the following specific steps:

[0006] S1. Online monitoring is used to obtain the received ash content and received moisture content of coal fed into each mill, and the average received ash content and received moisture content of coal fed into the boiler are calculated and sent to the unit DCS.

[0007] S11. Install an ash meter at the inlet of each coal mill of the boiler to measure the received ash content A of the coal at the inlet of each coal mill. i , i=1,2,3···,N, N is the number of grinding stations;

[0008] S12. Install moisture meters at the inlet of each coal mill in the boiler to measure the received basic moisture M of the coal at the inlet of each coal mill. i , i=1,2,3···,N, N is the number of grinding stations;

[0009] S13. Calculate the average received basis ash content A and received basis moisture content M of the coal fed into the boiler according to the following formula;

[0010]

[0011]

[0012] S2. Establish a neural network model with dry basis ash and volatile matter as input and dry basis lower heating value as output;

[0013] S21. Collect the offline analysis data of coal quality entering the unit in the past two years to obtain the dry basis ash content A of the coal. d , Volatile matter V d And dry basis lower calorific value Q net,d (KJ / Kg);

[0014] S22, using the obtained dry basis ash A d , Volatile matter V d And dry basis lower calorific value Q net,d (KJ / Kg) sample pairs are used to train the neural network and obtain the following neural network model:

[0015] Q net,d =NNet(V d , A d ) (3)

[0016] S3, using genetic algorithm to calculate the lower heating value and volatile matter of coal;

[0017] S31. Collect the average ash content A and moisture M of the coal entering the furnace, as well as the total coal feed B (Kg / H) and total air volume D from the unit DCS online. air (Kg / H) and flue gas oxygen content O2 (%);

[0018] S32, based on the received low calorific value Q net As the optimization variable of the genetic algorithm, the initial population of the genetic algorithm is randomly generated is a population individual, P is the number of individuals in the population, and the individual is calculated as follows The fitness function value of is:

[0019] (A) Calculate each individual Corresponding volatile matter on dry ash-free basis

[0020]

[0021] Where x is the characteristic parameter of coal;

[0022] (B) will receive the base ash A and dry ash-free base volatile matter Converted to dry basis ash A d and volatile matter

[0023]

[0024]

[0025] (C) Ash content on dry basis A d and volatile matter The lower calorific value on a dry basis is calculated using formula (3): And convert it into the received lower heating value using the following formula

[0026]

[0027] (D) Calculate each individual The fitness function value f:

[0028]

[0029] Where c is a real number greater than 0;

[0030] S33, using genetic algorithm to optimize Q net , The individual with the largest fitness function value is the one that receives the base low calorific value Q of the coal entering the furnace. net ;

[0031] S34, by A, M and Q net Calculate the dry ash-free volatile matter V of coal according to formula (4): daf ;

[0032] S35, V daf Convert to received base volatile matter V:

[0033]

[0034] S36, will receive the basic low calorific value Q net The volatile matter V is sent to the DCS monitoring screen to realize real-time online monitoring of the basic low calorific value and volatile matter of the coal entering the furnace.

[0035] Compared with the prior art, the present invention has the following beneficial technical effects: the present invention makes it possible to realize real-time online calculation of boiler efficiency, thereby facilitating operators to monitor changes in boiler operating performance and improve boiler operating levels; the implementation of the present invention provides key data for boiler combustion optimization and adjustment, which can effectively improve the safety, economy and environmental protection operation level of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of the method for monitoring the lower calorific value and volatile matter of coal fed into a boiler according to the present invention;

[0037] Figure 2 It is a monitoring curve diagram of average ash content and moisture content of the coal fed into the furnace according to the present invention;

[0038] Figure 3It is a monitoring curve diagram of the lower calorific value and volatile matter of the coal fed into the furnace according to the present invention. DETAILED DESCRIPTION

[0039] Example 1

[0040] In order to better illustrate the technical solution disclosed in the present invention, further elaboration is given below in conjunction with the accompanying drawings and specific implementation cases.

[0041] like Figure 1 As shown,

[0042] Step 1: Online monitoring of the received ash content and moisture content of the coal at the inlet of each coal mill of the boiler, and then calculating the average received ash content A (%) and moisture content M (%) of the coal entering the boiler.

[0043] (1) Install an ash meter at the inlet of each coal mill in the boiler to measure the received ash content A of the coal at the inlet of each coal mill. i , i=1,2,3···,N, N is the number of grinding stations;

[0044] (2) Install a moisture meter at the inlet of each coal mill in the boiler to measure the received basic moisture M of the coal at the inlet of each coal mill. i

[0045] (3) Calculate the average ash content A and moisture content M of the coal fed into the boiler using the following two formulas:

[0046]

[0047]

[0048] Implementation Case The boiler has 6 coal mills, N = 6. A passive ash analyzer and microwave moisture meter are installed on the coal feeder at the entrance of each mill, and the measurement results are sent to the unit DCS. Figure 2 It is the average ash and moisture monitoring curve of the coal entering the furnace in a certain period of time;

[0049] Step 2: Collect the unit's coal quality offline analysis data for the past two years to obtain the dry basis ash content A of the coal d , Volatile matter V d (%) and lower calorific value Q net,d (KJ / Kg) samples, and use this sample to train the neural network to establish a dry basis ash content A d and volatile matter V d As input, the lower heating value of coal on a dry basis Q net,d The output neural network model is as follows:

[0050] Q net,d =NNet(V d , A d ) (3)

[0051] The implementation case used BP neural network to establish the above model.

[0052] Step 3: Using the results of Step 1 and Step 2, a genetic algorithm is used to calculate the incoming coal’s received lower calorific value Q in real time. net and volatile matter V, as follows:

[0053] (1) Collect the average ash content A and moisture M of the coal entering the boiler, as well as the total coal feed B (Kg / H) and total air volume D from the unit DCS online. air (Kg / H) and flue gas oxygen content O2 (%);

[0054] (2) Based on the received low calorific value Q net As the optimization variable of the genetic algorithm, the initial population of the genetic algorithm is randomly generated is a population individual, P is the number of individuals in the population, and the individual is calculated as follows The fitness function value of is:

[0055] (A) Calculate each individual Corresponding volatile matter on dry ash-free basis

[0056]

[0057] Where x is the characteristic parameter of coal;

[0058] (B) will receive the base ash A and dry ash-free base volatile matter Converted to dry basis ash A d and volatile matter

[0059]

[0060]

[0061] (C) Ash content on dry basis A d and volatile matter The lower calorific value on a dry basis is calculated using formula (3): And convert it into the received lower heating value using the following formula

[0062]

[0063] (D) Calculate each individual The fitness function value f:

[0064]

[0065] Where c is a real number greater than 0;

[0066] (3) Using genetic algorithm to optimize Q net , The individual with the largest fitness function value is the one that receives the base low calorific value Q of the coal entering the furnace. net ;

[0067] (4) From A, M and Q net Calculate the dry ash-free volatile matter V of coal according to formula (4): daf ;

[0068] (5) V daf Convert to received base volatile matter V:

[0069]

[0070] (6) The received basic low calorific value Q net The volatile matter V is sent to the DCS monitoring screen to realize real-time online monitoring of the basic low calorific value and volatile matter of the coal entering the furnace.

[0071] In the embodiment, the number of individuals in the genetic algorithm population P=50, the real number c=1.0, Figure 3 Monitoring curve of received base lower calorific value and volatile matter over a certain period of time.

[0072] The present invention is beneficial for operators to monitor changes in boiler operating performance and improve boiler operating levels; implementation of the present invention provides key data for boiler combustion optimization and adjustment, and can effectively improve the safety, economy and environmental protection operation level of the boiler.

[0073] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. The above describes the embodiment of the present invention in detail in conjunction with the accompanying drawings, but the present invention is not limited to this. Various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A real-time online monitoring method for lower calorific value and volatile matter of coal fed into a boiler, characterized in that: The specific steps include: S1. Online monitoring is used to obtain the received ash content and received moisture content of coal fed into each mill, and the average received ash content and received moisture content of coal fed into the boiler are calculated and sent to the unit DCS. S11. Install an ash meter at the inlet of each coal mill of the boiler to measure the received ash content A of the coal at the inlet of each coal mill. i , i=1,2,3···,N, N is the number of grinding stations; S12. Install moisture meters at the inlet of each coal mill in the boiler to measure the received basic moisture M of the coal at the inlet of each coal mill. i , i=1,2,3···,N, N is the number of grinding stations; S13. Calculate the average received basis ash content A and received basis moisture content M of the coal fed into the boiler according to the following formula; S2. Establish a neural network model with dry basis ash and volatile content as input and dry basis lower heating value as output; S21. Collect the offline analysis data of coal quality entering the unit in the past two years to obtain the dry basis ash content A of the coal. d , Volatile matter V d And dry basis lower calorific value Q net,d ; S22, using the obtained dry basis ash A d , Volatile matter V d And dry basis lower calorific value Q net,d The sample trains the neural network and obtains the following neural network model: Q net,d =NNet(V d ,A d )(3) S3, using genetic algorithm to calculate the lower heating value and volatile matter of coal; S31. Collect the average ash content A and moisture M of the coal entering the furnace, as well as the total coal feed B and total air volume D of the boiler online from the unit DCS. air and flue gas oxygen content O2; S32, based on the received low calorific value Q net As the optimization variable of the genetic algorithm, the initial population of the genetic algorithm is randomly generated is a population individual, P is the number of individuals in the population, and the individual is calculated as follows The fitness function value of is: (A) Calculate each individual Corresponding volatile matter on dry ash-free basis Where x is the characteristic parameter of coal; (B) will receive the base ash A and dry ash-free base volatile matter Converted to dry basis ash A d and volatile matter (C) Ash content on dry basis A d and volatile matter The lower calorific value on a dry basis is calculated using formula (3): And convert it into the received lower heating value using the following formula (D) Calculate each individual The fitness function value f: Where c is a real number greater than 0; S33, using genetic algorithm to optimize Q net , The individual with the largest fitness function value is the one that receives the base low calorific value Q of the coal entering the furnace. net ; S34, by A, M and Q net Calculate the dry ash-free volatile matter V of coal according to formula (4): daf ; S35, V daf Convert to received base volatile matter V: S36, will receive the basic low calorific value Q net The volatile matter V is sent to the DCS monitoring screen to realize real-time online monitoring of the basic low calorific value and volatile matter of the coal entering the furnace.