Boiler efficiency obtaining method and system

Abstract

The invention discloses a boiler efficiency obtaining method and system, and relates to the technical field of power station boiler efficiency measurement, and the method comprises the following steps: determining a plurality of corresponding energies based on the boiler fly ash and slag carbon content and operation parameters obtained in real time, and calculating the initial boiler efficiency through the plurality of energies; obtaining the low heating value of the current coal type based on the initial boiler efficiency; inputting the lower calorific value of the current coal type and the measured value of the O2 content in the flue gas into the virtual combined coal quality set to obtain coal quality data of the current coal type; the updated boiler efficiency is obtained through the coal quality data of the current coal type, if the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not smaller than a set threshold value, the updated boiler efficiency serves as the initial boiler efficiency to repeat the iteration process, and otherwise, the updated boiler efficiency is output to serve as the final boiler efficiency. According to the method, the boiler efficiency can be calculated in real time without obtaining the in-boiler coal quality data of the coal sample in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of power station boiler efficiency measurement, and in particular to a boiler efficiency acquisition method and system. Background Art

[0002] At present, technical optimization and equipment transformation are needed to achieve the goal of efficient energy conservation and emission reduction. With the development of non-fossil energy power generation industry and measures such as improving the combustion efficiency of coal-fired units, the power industry has reduced carbon dioxide emissions by about 18.53 billion tons. Among them, measures to improve combustion efficiency can provide about 36% of the contribution rate to the power industry's carbon dioxide emission reduction goals. How to obtain boiler combustion efficiency in real time is a common problem that coal-fired units need to face.

[0003] At present, data-driven soft measurement can be used to approximate the calculation of boiler combustion efficiency. This method is based on the historical operation data of the power plant and fits the constructed data set through intelligent algorithms to obtain a prediction model for boiler efficiency. This method can reflect the combustion operation of the boiler to a certain extent, but it directly transitions to boiler efficiency through operating parameters and cannot obtain the size of various heat losses. Therefore, it cannot optimize and improve the boiler efficiency in a targeted manner.

[0004] In the actual operation of the boiler, due to the limitations of analytical instruments and technical conditions, the calculation method of the power plant boiler efficiency is mainly the counter-balance method, which has five main influencing factors: the quality data of the coal entering the furnace, the carbon content of fly ash and slag, the exhaust temperature, the oxygen content of the exhaust gas, and the volume fraction of CO. The power plant adjusts the proportion of coal samples every day due to the increase and decrease of load, but only samples are taken once a day for industrial analysis of coal quality. Therefore, it is usually impossible to obtain the coal quality data of the coal sample entering the furnace in real time, resulting in the inability to obtain the boiler efficiency in real time. Summary of the invention

[0005] Based on the defects of the above-mentioned prior art, the present invention provides a method and system for obtaining boiler efficiency, which solves the problem that the power plant adjusts the proportion of coal samples every day due to load fluctuations, but only takes samples once a day for industrial analysis of coal quality. Therefore, it is usually impossible to obtain the coal quality data of the coal samples entering the furnace in real time, resulting in the inability to obtain the boiler efficiency in real time.

[0006] The present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for obtaining boiler efficiency, comprising the following steps:

[0008] Determine the corresponding multiple energies based on the real-time obtained carbon content of boiler fly ash and slag and operating parameters, and calculate the initial boiler efficiency through multiple energies;

[0009] Obtain the lower calorific value of the current coal type based on the initial boiler efficiency, and collect the measured values of the O2 content and the measured value of the SO2 content in the current flue gas;

[0010] Find multiple relevant coal types corresponding to the lower calorific value of the current coal type through the virtual combined coal quality set, obtain the theoretical values of the SO2 content corresponding to the multiple relevant coal types based on the measured value of the O2 content in the flue gas, compare the multiple theoretical values of the SO2 content with the measured value of the SO2 content, and screen the multiple relevant coal types according to the comparison results to obtain the coal quality data of the current coal type; wherein, the virtual combined coal quality set is indexed by the lower calorific value of different coal types and the theoretical value of the SO2 content in the flue gas generated by coal combustion, with the coal quality data of different coal types as the set, and the theoretical value of the SO2 content in the flue gas is a single function of the measured value of the O2 content;

[0011] Obtain the updated boiler efficiency through the coal quality data of the current coal type. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not less than the set threshold, use the updated boiler efficiency as the initial boiler efficiency to re-obtain the new updated boiler efficiency, otherwise output the updated boiler efficiency as the final boiler efficiency.

[0012] Preferably, the determination of the corresponding multiple energies based on the carbon content and operation parameters of boiler fly ash and slag in real time includes the following steps:

[0013] The operation parameters include inlet and outlet steam and water parameters, flue gas parameters, blowdown parameters, mill reject parameters, and boiler load;

[0014] Determine the energy Q output by fly ash according to the carbon content of fly ash and slag fh and the heat Q output by slag lz ;

[0015] Determine the heat Q absorbed by superheated steam according to the inlet and outlet steam and water parameters gq and the heat Q absorbed by reheated steam zq ;

[0016] Determine the energy Q output by the flue gas at the boiler thermal boundary outlet according to the flue gas parameters py ;

[0017] Determine the energy Q output by blowdown according to the blowdown parameters pw ;

[0018] Determine the heat Q output by the mill rejects discharged by the mill according to the mill reject parameters sm ;

[0019] Determine the heat Q of heat dissipation loss according to the boiler load sr ;

[0020] The initial boiler efficiency is calculated through multiple energies, and specifically, the initial boiler efficiency is as follows:

[0021] η i =(Q gq +Q zq ) / (Q gq +Q zq +Q py +Q fh +Q lz +Q sr +Q pw +Q sm );

[0022] In the formula, η i is the initial boiler efficiency.

[0023] Preferably, the lower calorific value of the current coal type is obtained based on the initial boiler efficiency, and specifically, the lower calorific value is as follows:

[0024] Q net,ar =Q1 / (η i ·q m );

[0025] In the formula, Q net,ar is the lower calorific value, Q1 is the output heat, and q m is the coal feed rate.

[0026] Preferably, the coal quality data are the content values of multiple elements in the as-received basis of the coal type.

[0027] Preferably, the construction of the virtual combined coal quality set specifically includes the following steps:

[0028] Obtain the historical data of moisture and ash in the as-received basis of the coal burned in the target power plant and the ultimate analysis of the dry ash-free basis;

[0029] Eliminate the error outliers from the historical data of moisture and ash in the as-received basis, and cluster the historical data of moisture and ash in the as-received basis after elimination to obtain n categories of moisture data and n categories of ash data, and each category of data includes n data;

[0030] Obtain the typical values of the content of various coal quality elements in the ultimate analysis of the dry ash-free basis, select m kinds of coal quality components and convert them into the as-received basis components, and combine the n categories of moisture data, n categories of ash data and m kinds of coal quality as-received basis components to obtain a coal quality set;

[0031] Obtain the lower calorific value of the as-received basis of each coal in the coal quality set and the theoretical value of the SO2 content in the flue gas as the index of the virtual combined coal quality set to obtain the virtual combined coal quality set.

[0032] Preferably, the updated boiler efficiency is obtained based on the coal quality data of the current coal type and multiple heat losses. Specifically, the updated boiler efficiency is as follows:

[0033]

[0034] In the formula, η j is the updated boiler efficiency, Q2 is the heat loss of flue gas, Q3 is the heat loss of incomplete combustion of gas, Q4 is the heat loss of incomplete combustion of solid, Q5 is the heat dissipation loss, Q6 is the sensible heat loss of ash and slag, and Q7 is other heat losses.

[0035] Preferably, the carbon content of fly ash and slag is obtained in real time by a machine learning method. The input of the machine learning method is the adjustable parameters of boiler operation, and the adjustable parameters of boiler operation include boiler load, air distribution mode, working state of coal mill, oxygen content at the flue gas outlet, and CO concentration at the flue gas outlet.

[0036] In a second aspect, the present invention provides a boiler efficiency acquisition system, including:

[0037] An acquisition module, configured to determine corresponding multiple energies based on the carbon content of boiler fly ash and slag and operation parameters obtained in real time, and calculate the initial boiler efficiency through the multiple energies;

[0038] A calculation module, configured to obtain the low calorific value of the current coal type based on the initial boiler efficiency, and collect the measured values of O2 content and SO2 content in the current flue gas;

[0039] A searching module, configured to search for multiple relevant coal types corresponding to the low calorific value of the current coal type through a virtual combined coal quality set, obtain the theoretical values of SO2 content corresponding to the multiple relevant coal types based on the measured value of O2 content in the flue gas, compare the multiple theoretical values of SO2 content with the measured value of SO2 content, and screen the multiple relevant coal types according to the comparison result to obtain the coal quality data of the current coal type; wherein, the virtual combined coal quality set is indexed by the low calorific value of different coal types and the theoretical value of SO2 content in the flue gas generated by coal combustion, and the coal quality data of different coal types is used as a set, and the theoretical value of SO2 content in the flue gas is a single function of the measured value of O2 content;

[0040] An iteration module, configured to obtain the updated boiler efficiency through the coal quality data of the current coal type. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not less than a set threshold, the updated boiler efficiency is used as the initial boiler efficiency to re-obtain a new updated boiler efficiency, otherwise the updated boiler efficiency is output as the final boiler efficiency.

[0041] Compared with the prior art, at least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects:

[0042] The present invention determines a variety of corresponding energies based on the carbon content and operating parameters of boiler fly ash and slag obtained in real time, calculates the initial boiler efficiency through the various energies, and provides a reference value for the real-time acquisition of the boiler efficiency. Then, a virtual combined coal quality set is constructed, which is indexed by the low calorific value of different coal types and the theoretical value of the SO2 content in the flue gas generated by coal combustion, and the coal quality data of different coal types is used as the coal quality set. Based on the initial boiler efficiency, the low calorific value of the current coal type is obtained, and the measured value of the low calorific value of the current coal type and the O2 content in the flue gas are input into the virtual combined coal quality set to obtain the coal quality data of the current coal type. The updated boiler efficiency is obtained through the coal quality data of the current coal type. Finally, the initial boiler efficiency is compared with the updated boiler efficiency. If the error is within an acceptable range, the boiler efficiency is output. Therefore, the present invention does not need to obtain the in-furnace coal quality data of coal samples in real time and can calculate the boiler efficiency in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of a method for obtaining the boiler efficiency of the present invention;

[0045] Figure 2 It is a flowchart for calculating the initial boiler efficiency of the present invention;

[0046] Figure 3 It is a flowchart for constructing the virtual combined coal quality set of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0048] I. Explanation of the embodiments. This part is an explanatory embodiment that expands and explains the technical solutions of the claims to enable those skilled in the art to fully understand how the present invention is specifically implemented.

[0049] Figure 1 It is a flowchart of a method for obtaining the boiler efficiency provided by an embodiment of the present invention. The following combines Figure 1A method for obtaining boiler efficiency provided by an embodiment of the present invention is introduced in detail, which specifically includes the following steps:

[0050] S1: Based on the carbon content in fly ash and slag and operating parameters obtained in real time, obtain corresponding multiple energies and multiple heat losses, and obtain the initial boiler efficiency through the multiple energies.

[0051] In this embodiment, a machine learning method is used to predict the carbon content in fly ash and slag. The adjustable operating parameters of the boiler are used as its input variables, such as boiler load, air distribution mode (the air volume, temperature, air pressure, and damper opening of primary air, secondary air, and overfire air), the working state of the coal mill (the output of the coal mill, the particle size and uniformity of coal), the main feed water flow rate, the desuperheating water flow rate, and the oxygen content at the flue gas outlet. In addition, since CO represents the heat loss due to incomplete combustion of gas and reflects the burnout of pulverized coal in the furnace to a certain extent, and the carbon content in fly ash and slag represents the heat loss due to incomplete combustion of solids and has a certain correlation with the CO concentration, the CO concentration at the flue gas outlet is added to the input variable data structure; the output parameter is the carbon content in fly ash and slag. The machine learning method can be gradient boosting tree, support vector machine, or neural network, etc.

[0052] The present invention uses a machine learning method to realize the online monitoring and prediction of the carbon content in fly ash and slag. After deep learning, the accuracy of parameter measurement can be improved, and the time cost and economic cost of installing a large number of measuring points are saved. The input parameters of the machine learning method are adjustable, real and reliable operating parameters, such as boiler load, air distribution mode, the working state of the coal mill, the oxygen content at the flue gas outlet, and the CO concentration at the flue gas outlet, etc., which do not involve the errors brought by measuring instruments and have guiding significance for improving boiler efficiency.

[0053] Use a monitoring device to obtain the steam-water parameters, flue gas parameters, blowdown water parameters, and coal mill reject coal parameters (if the amount of reject coal is very small, it can be ignored) at the inlet and outlet of the boiler thermal boundary and the boiler load.

[0054] Refer to Figure 2 , obtain the energy Q fh output by fly ash and the heat Q lz output by slag according to the carbon content in fly ash and slag, obtain the heat Q gq absorbed by superheated steam and the heat Q zq absorbed by reheated steam according to the steam-water parameters at the inlet and outlet, obtain the energy Q py output by the flue gas at the outlet of the boiler thermal boundary according to the flue gas parameters, obtain the energy Q pw output by the blowdown water according to the blowdown water parameters, obtain the heat Q sm output by the reject coal discharged from the coal mill according to the coal mill reject coal parameters, and obtain the heat Q sr of heat dissipation loss according to the boiler load.

[0055] Obtain the steam and water parameters, flue gas parameters, blowdown water parameters, and pulverized coal mill reject coal parameters at the inlet and outlet of the boiler thermal boundary on the same day, and calculate the heat Q absorbed by the superheated steam based on these operating parameters on the same day. gq and the heat Q absorbed by the reheated steam zq and the energy Q output by the flue gas at the outlet of the boiler thermal boundary py and the energy Q output by the fly ash fh and the heat Q output by the slag lz and the heat Q loss due to heat dissipation sr and the energy Q output by the blowdown water pw and the heat Q output by the reject coal discharged from the pulverized coal mill sm .

[0056] Combined with the positive balance method to calculate the initial boiler efficiency, based on the unit operation monitoring parameters (steam-water system and flue gas parameters), and using the carbon content of fly ash and slag predicted in real time by machine learning, the boiler thermal efficiency can be calculated without coal quality testing. The specific equation uses the heat absorbed by the superheated steam and the heat Q gq +Q zq as the numerator, and uses Q zq +Q gq plus the energy Q output by the flue gas at the outlet of the boiler thermal boundary py and the energy Q output by the fly ash fh and the heat Q output by the slag lz and the heat Q loss due to heat dissipation sr and the energy Q output by the blowdown water pw and the heat Q output by the reject coal discharged from the pulverized coal mill sm as the denominator. The initial boiler efficiency is specifically as follows:

[0057] η i =(Q gq +Q zq ) / (Q gq +Q zq +Q py +Q fh +Q lz +Q sr +Q pw +Q sm ) (1).

[0058] Combined with the carbon content of fly ash and slag under variable load conditions predicted by machine learning and other relevant data from the power plant monitoring device, calculate the output heat Q1 (Q gq +Q zq ), the heat loss Q2 due to flue gas heat, the heat loss Q3 due to incomplete combustion of gas, and the heat loss Q4 due to incomplete combustion of solids.

[0059] S2: Obtain the lower calorific value of the blended coal type at this time based on the initial boiler efficiency, and obtain the SO2 and O2 contents in the flue gas.

[0060] Take the initial boiler efficiency η i as the initial value, and combine the coal feed quantity q m and the output heat Q1 to calculate the lower calorific value Q of the blended coal type at this time using the positive balance method net,ar . And monitor the SO2 and O2 contents in the flue gas in real time.

[0061] When calculating the lower calorific value of the coal type using the positive balance method, the formula is as follows:

[0062] Q net,ar = Q1 / (η i ·q m ) (2);

[0063] where q m is the coal feed quantity.

[0064] S3: Refer to Figure 3 to establish a virtual combined coal quality set.

[0065] The coal used in thermal power plants comes from complex sources and has variable coal quality. To adapt to the power grid load demand and coal supply situation, each power plant determines several different coal blending methods according to the load requirements of the units by the power grid dispatching. In these coal blending methods, each coal blending plan is composed of different coal types through technical and economic comparison. This means that the coal quality burned by the power plant changes with the load every day, and the coal quality under fixed load conditions also changes due to the change of the coal blending method. Establishing a virtual combined coal quality set can form a huge virtual coal sample set by combining multiple coal samples in multiple blending ratios, so as to cover all possible coal blending methods that may occur in the power plant.

[0066] Using the historical coal quality of a large number of actual power plants, a virtual combined coal quality set is established using the clustering algorithm of machine learning, which can cover almost all coal types used in domestic power plants at present. The parameters of each coal type include its ultimate analysis and proximate analysis, and the lower calorific value of the coal quality and the theoretical value of the SO2 content in the flue gas at the thermal boundary outlet are jointly used as the index of the coal type.

[0067] First, the historical data of the as-received basis moisture and ash of coal fired in a power plant were analyzed, and outliers with statistical errors were removed. Then, the moisture and ash data were clustered using the k-means function provided by MATLAB software. According to the actual situation and other comprehensive considerations, they were clustered into n categories, and the mean values ​​of moisture and ash in each cluster after clustering were obtained. Each cluster had n data, which can fully reflect the original distribution characteristics and can be used as the representative of the corresponding cluster. Secondly, the elemental analysis of the as-received basis was obtained and converted into the elemental analysis of the dry ash-free basis. Each data has 5 attributes, which are C daf , H daf , O daf 、N daf and S daf . With the help of the PAM algorithm of MATLAB software, typical coal quality data is imported and k=m is input during calculation to obtain m representative coal quality components. Combining the received basis moisture, ash and dry ash-free basis elemental components, a coal quality set containing n×n×m kinds of "virtual combined coal quality" can be obtained. Next, the elemental components in the virtual combined coal quality set are converted into received basis components. Finally, the received basis low calorific value Q is calculated. net,ar , calculate the theoretical value of SO2 content per unit mass of each type of coal after combustion based on elemental analysis (due to the existence of excess air coefficient, this theoretical value of SO2 content is also related to the oxygen content of flue gas, and needs to be used in conjunction with actual flue gas measurement, so it is temporarily used The forms are listed in the table, where is the actual measured volume fraction of O2 in the flue gas). Finally, a virtual combined coal quality set is obtained. This data set is based on Q net,ar and c SO2 As an index, the content includes C, H, O, N, S, ash A, and moisture M content of coal on a received basis.

[0068] Through a systematic analysis of the constituent elements of coal and their correlations, it can be seen that the complexity and variability of coal is mainly subject to its unstable moisture and ash content. After excluding their influence, the dry ash-free elemental composition shows corresponding stability and regularity. Especially for coal produced in the same mining area or adjacent mining areas, the stability and regularity of the content of each element are more obvious. First, the historical data of the received basis moisture and ash of coal burned in a power plant are analyzed, and outliers with statistical errors are eliminated. Then, the k-means function provided by MATLAB software is used to cluster the moisture and ash data. According to the actual situation and other comprehensive considerations, they are clustered into n categories. The execution format is as follows:

[0069] [IDX,C]=kmeans(X,n) (3).

[0070] The average moisture and ash content within each cluster after clustering are obtained, with n data points each, which can fully reflect the original distribution characteristics and can be used as representatives of the corresponding clusters. Secondly, the elemental data is processed to obtain the as-received elemental analysis of the coal and convert it into the dry ash-free elemental analysis. Each data point has 5 attributes, namely C daf 、H daf 、O daf 、N daf and S daf . By using the PAM algorithm in MATLAB software, typical coal quality data is imported during the calculation and k = m is input to obtain m representative coal quality components. Combining the as-received moisture, ash content, and dry ash-free elemental components, a coal quality set containing n×n×m kinds of "virtual combined coal quality" can be obtained. Next, the elemental components in the virtual combined coal quality set are converted into as-received components. Finally, the lower calorific value Q net,ar of the as-received basis is calculated using the following empirical formula:

[0071] Q ar,gr = 4.19(87C ar + 300H ar + 26S ar - 26O ar ) (4);

[0072] Q net,ar = Q ar,gr - 206H ar - 26M ar (5).

[0073] Actual data shows that the heat intervals are mostly distributed within 10 kJ / kg, and only a few have relatively large heat differences. Therefore, using only the lower calorific value as an index is not sufficient, and other parameters are also needed. For example, the SO2 content in the flue gas. The theoretical value of the SO2 content after combustion of each coal quality per unit mass can be calculated based on the elemental analysis, and the formula is as follows:

[0074]

[0075] ω ar (K) = ω ar (C) + 0.375ω ar (S) (7);

[0076] V 0 = 8.89ω ar (K) + 26.5ω ar (H) - 3.33ω ar (O) (8);

[0077]

[0078]

[0079] Among them, ω ar (S) represents the mass fraction of the as-received basis S, ω ar (C) represents the mass fraction of the as-received basis C, ω ar (H) represents the mass fraction of the as-received basis H, ω ar (O) represents the mass fraction of the as-received basis O, ω ar (N) represents the mass fraction of the as-received basis N, V 0 represents the theoretical air quantity required for the complete combustion of 1 kg of coal, represents the theoretical dry flue gas quantity of 1 kg of fuel, α is the excess air coefficient, V gy represents the dry flue gas quantity after the complete combustion of 1 kg of coal with an excess air coefficient of α, represents the concentration of SO2 in the flue gas when the excess air coefficient is α. Therefore, after substituting the elemental analysis results into Equations (7)-(12), the concentration of SO2 in the coal quality concentration is a single-variable function of the O2 content in the flue gas, that is, Finally, a virtual combined coal quality set is obtained. This data set uses Q net,ar and as indexes, and the form is as follows:

[0080]

[0081] The present invention uses the k-means algorithm to cluster the historical data of the moisture and ash content of the as-received basis of the coal burned in the power plant to obtain the typical values of the moisture and ash content of each cluster. Then, the elemental analysis of the as-received basis of the coal quality is obtained and converted into the elemental analysis of the dry ash-free basis, and the PAM algorithm is used to obtain the typical values of the elemental content of the coal type; by combining the obtained moisture and ash content of the as-received basis with the dry ash-free basis components, and converting the elemental components of each coal into the as-received basis components, a virtual combined coal quality set is obtained. Calculate the lower calorific value of the as-received basis of each coal and the theoretical value of the SO2 content in the flue gas (due to the existence of the excess air coefficient, this theoretical value of the SO2 content is also related to the oxygen content in the flue gas and needs to be used in combination with the measured oxygen content in the flue gas. Therefore, it is temporarily in the form of listed in the table, where is the volume fraction of O2 actually measured in the flue gas), as the index of the virtual combined coal quality set.

[0082] S4: Using the lower calorific value as the index, find several coals in the virtual combined coal quality set that are closest to the lower calorific value, and substitute the O2 content into these coals in the coal quality set Calculation formula: Calculate the theoretical values of the SO2 content generated by these several types of coal, compare with the measured SO2 content, select the most suitable coal quality, and obtain the corresponding contents of C, H, O, N, S, ash A, and moisture M.

[0083] S5: Update the boiler efficiency by determining the contents of multiple components in the as-received basis of the coal quality and multiple heat losses. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is greater than the set threshold, output the updated boiler efficiency; otherwise, repeat the above iterative process based on the updated boiler efficiency.

[0084] When calculating the boiler efficiency η using the indirect method j : Obtain the ultimate analysis of the coal quality found in the virtual combined coal quality set, calculate the heat loss due to flue gas heat Q2 and the heat loss due to incomplete combustion of gas Q3 using the monitored flue gas parameters (including flue gas flow rate, flue gas temperature, oxygen content in the flue gas, CO content in the flue gas, etc.), calculate the heat loss due to incomplete combustion of solids Q4 using the predicted carbon content in fly ash and slag, calculate the heat loss due to heat dissipation Q5 using the boiler load. In addition, the sensible heat loss of ash and slag Q6 and other heat losses Q7 account for a very small proportion and have little impact on the results. Simply take the two as fixed values. Then the calculation formula of the indirect method is as follows:

[0085]

[0086] Compare the boiler efficiency η obtained by the "effective / total output heat method" i with the boiler efficiency η obtained by the "indirect method" j : If the error is greater than a certain threshold, assign the boiler efficiency obtained by the indirect method to the boiler efficiency reference value and return to S2 for cycling; if the error is less than the threshold, output the boiler efficiency.

[0087] The present invention uses the above-obtained unit monitoring parameters, combines with the predicted carbon content in fly slag, and calculates the boiler efficiency η at this time. The calculated boiler efficiency η is used as the initial value η of the boiler efficiency when the load changes i , and according to the coal feeding amount q m and the output heat (Q gq +Q zq ), use the direct method to calculate the lower calorific value Q of the proportioned fuel at this time net,ar , and monitor the theoretical value of the SO2 content in the flue gas at the outlet of the thermal boundary in real time. Use the lower calorific value Q calculated by the direct method net,ar, compare the theoretical value of the SO2 content in the flue gas measured under the current load with the corresponding data of various coals in the virtual combined coal quality set to find the coal type closest to the current fuel data. Obtain the coal quality elemental analysis from the virtual combined coal quality set, and combine it with the carbon content in fly ash and slag under variable load conditions predicted by machine learning to calculate the exhaust gas loss Q2, incomplete combustion heat loss of gas Q3, incomplete combustion heat loss of solid Q4, heat dissipation loss Q5, physical sensible heat loss of ash and slag Q6, and other heat losses Q oth , and calculate the boiler efficiency η using the inverse balance method j . Compare the boiler efficiency η calculated by the inverse balance method j with the boiler efficiency η calculated by the combined forward and inverse balance method i . If the error is less than a certain threshold ε, output the boiler efficiency η; if the error is greater than the threshold ε, assign the boiler efficiency η obtained by the inverse balance j to the initial value η of the boiler efficiency i , and perform a loop

[0088] The present invention does not rely solely on one method to obtain the boiler efficiency. It is necessary to compare the boiler efficiency η obtained by the "effective / total output heat method" i with the boiler efficiency η obtained by the "inverse balance method" j . Only when the two are very close is it considered that the boiler efficiency is calculated correctly; otherwise, iteration is performed to improve the calculation accuracy

[0089] Based on the same concept, the present invention also provides a boiler efficiency acquisition system. It includes an acquisition module, a calculation module, a search module, and an iteration module

[0090] The acquisition module is used to determine corresponding multiple energies based on the carbon content in fly ash and slag of the boiler and the operating parameters obtained in real time, and calculate the initial boiler efficiency through the multiple energies

[0091] The calculation module is used to obtain the lower calorific value of the current coal type based on the initial boiler efficiency, and collect the measured values of the O2 content and SO2 content in the current flue gas

[0092] The search module is used to search for multiple relevant coal types corresponding to the lower calorific value of the current coal type through the virtual combined coal quality set, obtain the theoretical values of the SO2 content corresponding to the multiple relevant coal types based on the measured value of the O2 content in the flue gas, compare the multiple theoretical values of the SO2 content with the measured value of the SO2 content, and screen the multiple relevant coal types according to the comparison results to obtain the coal quality data of the current coal type; among them, the virtual combined coal quality set is indexed by the lower calorific values of different coal types and the theoretical values of the SO2 content in the flue gas generated by the combustion of the coal types, and the coal quality data of different coal types is used as the set, and the theoretical value of the SO2 content in the flue gas is a single function of the measured value of the O2 content

[0093] The iterative module is used to obtain the updated boiler efficiency through the coal quality data of the current coal type. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not less than the set threshold, the updated boiler efficiency is used as the initial boiler efficiency to re-obtain the new updated boiler efficiency; otherwise, the updated boiler efficiency is output as the final boiler efficiency.

[0094] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0095] Obviously, those skilled in the art can make various changes and deformations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and deformations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and deformations.

Claims

1. A method for obtaining boiler efficiency, characterized in that: The following steps are involved: Determine the corresponding multiple energies based on the real-time obtained carbon content of boiler fly ash and slag and operating parameters, and calculate the initial boiler efficiency through multiple energies; Based on the initial boiler efficiency, the low calorific value of the current coal type is obtained, and the actual measured values ​​of the O2 content and SO2 content in the current flue gas are collected; Through a virtual combined coal quality set, multiple related coal types corresponding to the low calorific value of the current coal type are found, and based on the actual measured value of the O2 content in the flue gas, the theoretical values ​​of the SO2 content corresponding to the multiple related coal types are obtained, and the multiple theoretical values ​​of the SO2 content are compared with the actual measured values ​​of the SO2 content. According to the comparison results, multiple related coal types are screened to obtain the coal quality data of the current coal type; wherein the virtual combined coal quality set is indexed by the low calorific value of different coal types and the theoretical value of the SO2 content in the flue gas generated by the combustion of the coal types, and the coal quality data of different coal types are set, and the theoretical value of the SO2 content in the flue gas is a single function of the actual measured value of the O2 content; The updated boiler efficiency is obtained through the coal quality data of the current coal type. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not less than the set threshold, the updated boiler efficiency is used as the initial boiler efficiency to re-obtain a new updated boiler efficiency, otherwise the updated boiler efficiency is output as the final boiler efficiency.

2. A method for obtaining boiler efficiency according to claim 1, characterized in that: The method of determining the corresponding multiple energies based on the real-time obtained carbon content of boiler fly ash and slag and operating parameters includes the following steps: The operating parameters include inlet and outlet steam and water parameters, flue gas parameters, wastewater parameters, coal mill stone coal parameters and boiler load; Determine the energy Q output from fly ash based on the carbon content of fly ash and slag fh and the heat output of the slag Q lz ; Determine the heat Q absorbed by superheated steam based on the inlet and outlet steam parameters gq and the heat absorbed by the reheat steam Q zq ; Determine the energy Q of the flue gas output at the boiler thermal boundary outlet based on the flue gas parameters py ; Determine the energy Q of sewage output according to sewage parameters pw ; Determine the heat output Q of the coal discharged from the coal mill according to the coal mill parameters sm ; Determine the heat loss Q according to the boiler load sr ; The initial boiler efficiency is calculated by using multiple energies, wherein the initial boiler efficiency is specifically as follows: η i =(Q gq +Q zq ) / (Q gq +Q zq +Q py +Q fh +Q lz +Q sr +Q pw +Q sm ); Where η i is the initial boiler efficiency.

3. A method for obtaining boiler efficiency according to claim 2, characterized in that: The low calorific value of the current coal type is obtained based on the initial boiler efficiency, wherein the low calorific value is specifically as follows: Q net,ar =Q1 / (η i ·q m ); In the formula, Q net,ar is the low heat, Q1 is the output heat, q m For coal supply.

4. A method for obtaining boiler efficiency according to claim 1, characterized in that: The coal quality data refers to the content values ​​of multiple elements in the received basis of the coal.

5. A method for obtaining boiler efficiency according to claim 1, characterized in that: The construction of the virtual combined coal quality set specifically includes the following steps: Obtain historical data on moisture and ash content on a received basis and elemental analysis on a dry ash-free basis for the target power plant coal; Eliminate erroneous outliers from the historical data of moisture and ash content of the received base, and cluster the eliminated historical data of moisture and ash content of the received base to obtain n types of moisture data and n types of ash data, each type of data including n data; Obtain typical values ​​of various coal element contents in elemental analysis on a dry ash-free basis, select m types of coal components and convert them into as-received basis components, combine n types of moisture data and n types of ash data and m types of coal as-received basis components to obtain a coal quality set; The received base lower calorific value and theoretical value of SO2 content in flue gas of each type of coal in the coal quality set are obtained as the index of the virtual combined coal quality set to obtain the virtual combined coal quality set.

6. A method for obtaining boiler efficiency as claimed in claim 3, characterized in that: The boiler efficiency is updated by obtaining the coal quality data of the current coal type and multiple heat losses, wherein the updated boiler efficiency is specifically as follows: Where η j To update the boiler efficiency, Q2 is the heat loss of flue gas, Q3 is the heat loss of incomplete combustion of gas, Q4 is the heat loss of incomplete combustion of solid, Q5 is the heat loss, Q6 is the physical sensible heat loss of ash, and Q7 is other heat losses.

7. A method for obtaining boiler efficiency according to claim 1, characterized in that: The carbon content of fly ash and slag is obtained in real time through machine learning methods, where the input of the machine learning method is the adjustable parameters of boiler operation, which include boiler load, air distribution method, working state of pulverizer, oxygen content at the exhaust gas and CO concentration at the exhaust gas.

8. A boiler efficiency acquisition system, characterized in that: include: An acquisition module, used to determine corresponding multiple energies based on the real-time acquired carbon content of boiler fly ash and slag and operating parameters, and calculate the initial boiler efficiency through the multiple energies; The calculation module is used to obtain the low calorific value of the current coal type based on the initial boiler efficiency, and collect the actual measured values ​​of the O2 content and the SO2 content in the current flue gas; A search module is used to search for multiple related coal types corresponding to the low calorific value of the current coal type through a virtual combined coal quality set, obtain theoretical values ​​of SO2 content corresponding to multiple related coal types based on the actual measured value of O2 content in flue gas, compare multiple theoretical values ​​of SO2 content with the actual measured value of SO2 content, and screen multiple related coal types according to the comparison results to obtain coal quality data of the current coal type; wherein the virtual combined coal quality set is indexed by the low calorific value of different coal types and the theoretical value of SO2 content in the flue gas generated by the combustion of different coal types, and takes the coal quality data of different coal types as a set, and the theoretical value of SO2 content in the flue gas is a single function of the actual measured value of O2 content; The iteration module is used to obtain the updated boiler efficiency through the coal quality data of the current coal type. If the absolute value of the difference between the updated boiler efficiency and the initial boiler efficiency is not less than the set threshold, the updated boiler efficiency is used as the initial boiler efficiency to re-obtain a new updated boiler efficiency, otherwise the updated boiler efficiency is output as the final boiler efficiency.

Images