Boiler heating surface life monitoring method, device, medium and electronic equipment

Abstract

The present disclosure relates to a life monitoring method, device, medium and electronic device for a boiler heating surface. The method comprises: obtaining pipe section reference information of a pipe section to be detected, ash accumulation reference information of ash accumulation to be detected attached to the inner wall of the pipe section to be detected and air volume for adjusting the combustion rate of a mixed fuel, the pipe section reference information comprises pipe section thickness and pipe section material, and the ash accumulation reference information comprises mass fractions of different compounds in the ash accumulation; determining the ash accumulation attachment rate; determining the solid erosion coefficient according to the mass fractions of different compounds in the ash accumulation; determining the ratio between different types of fuels in the mixed fuel according to the ash accumulation attachment rate and the solid erosion coefficient; determining the remaining life of the heating surface according to the pipe section reference information, air volume and ratio. By determining the ratio between different types of fuels, the influencing factors between ash accumulation and corrosive gas can be taken into account when determining the remaining life of the heating surface, thereby effectively improving the accuracy of the determined remaining life of the heating surface.

Description

Technical Field

[0001] The present disclosure relates to the technical field of boiler pipeline detection, and in particular to a method, device, medium and electronic equipment for monitoring the life of a boiler heating surface. Background Art

[0002] Coal-fired power plants coupled with biomass power generation are the means of transforming coal-fired units to low-carbon. This method not only realizes the disposal principle of "harmless, reduced, and resourceful" waste, but also reduces the use of fossil fuels. Therefore, power plants are increasingly inclined to use a mixture of multiple types of fuels to generate electricity. During the power generation process, the inner wall of the boiler pipe is gradually corroded after long-term use. In order to ensure the safety of the production process, it is necessary to monitor the life of the boiler heating surface.

[0003] However, the current methods for predicting the life of heating surface pipelines are difficult to achieve accurate monitoring of life. For example, the patent with publication number CN112014539A provides a method for monitoring the life loss of boiler tubes. The patent cleans the pipeline and obtains the thickness of the inner wall of the pipeline, and calculates the loss of the pipeline through the thickness of the inner wall of the pipeline, so as to predict the life of the heating surface pipeline. However, corrosion usually includes high-temperature solid corrosion and high-temperature gaseous corrosion. High-temperature gaseous corrosion is the corrosion of the inner wall of the pipeline by corrosive gases, while high-temperature solid corrosion is mainly the corrosion of the inner wall of the pipeline by dust accumulation. Since dust accumulation adheres to the inner wall of the pipeline, dust accumulation can avoid large-scale contact between corrosive gases and the inner wall of the pipeline, and can inhibit high-temperature gaseous corrosion to a certain extent. The aforementioned method does not take the above factors into consideration, so that the life monitoring results of the heating surface are not accurate. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method, device, medium and electronic equipment for monitoring the life of a boiler heating surface, so as to achieve accurate monitoring of the life of the boiler heating surface.

[0005] In order to achieve the above-mentioned object, the present disclosure provides a first aspect of a life monitoring method for a boiler heating surface, comprising:

[0006] Obtaining pipe section reference information of the pipe section to be detected, ash accumulation reference information of the ash accumulation to be detected attached to the inner wall of the pipe section to be detected, and air volume for adjusting the combustion rate of the mixed fuel, wherein the pipe section reference information includes pipe section thickness and pipe section material, and the ash accumulation reference information includes mass fractions of different compounds in the ash accumulation;

[0007] Determine the dust deposition rate;

[0008] Determining a solid erosion coefficient according to the mass fractions of different compounds in the ash deposits;

[0009] Determining the ratio of different types of fuel in the mixed fuel according to the dust deposition rate and the solid erosion coefficient;

[0010] The remaining life of the heating surface is determined based on the pipe section reference information, the air volume and the ratio.

[0011] Optionally, the ash accumulation reference information further includes ash accumulation mass and ash accumulation combustion time; and the step of determining the ash accumulation attachment rate includes:

[0012] Determining the dust accumulation thickness according to the dust accumulation mass;

[0013] The ash deposition rate is determined according to the ash deposition thickness and the ash deposition combustion time.

[0014] Optionally, the pipe section reference information further includes the pipe section length and the pipe section radius, and the determining of the dust deposition thickness according to the dust deposition mass includes:

[0015] Determine the type of dust accumulation;

[0016] Determining a standard unit density corresponding to the dust accumulation category;

[0017] Determining the dust accumulation volume of the dust accumulation to be detected according to the dust accumulation mass and the standard unit density;

[0018] The dust accumulation thickness is determined according to the dust accumulation volume, the pipe section length and the pipe section radius.

[0019] Optionally, determining the dust accumulation category includes:

[0020] Acquire the surface image of the dust accumulation to be detected;

[0021] Inputting the surface image into a pre-trained dust accumulation classification model to obtain the dust accumulation category;

[0022] The dust accumulation classification model is trained in the following way:

[0023] Acquire multiple classification samples, each of which includes a historical surface image and a historical dust accumulation category;

[0024] The historical surface image is used as input data of the classifier, and the historical dust accumulation category is used as the target output data of the classifier. The classifier is trained until a first training end condition is met, thereby obtaining the dust accumulation classification model.

[0025] Optionally, the cross section of the pipe section to be detected is circular; and determining the dust accumulation thickness according to the dust accumulation volume, the pipe section length and the pipe section radius includes:

[0026] The dust deposition thickness is determined by the following formula:

[0027]

[0028] Wherein, TDP is the dust adhesion thickness, Rps is the radius of the pipe section, Rve is the dust volume, π is the pi, and Lps is the length of the pipe section.

[0029] Optionally, the mixed fuel includes garbage fuel and coal fuel; the mass fractions of different compounds in the ash deposit include carbonate mass fraction, oxide mass fraction and alkali metal chloride mass fraction; and the solid erosion coefficient is determined according to the mass fractions of different compounds in the ash deposit, including:

[0030] The solid erosion coefficient is determined by the following formula:

[0031]

[0032] Among them, SEC is the solid erosion coefficient, Omf is the oxide mass fraction, u1 is the first weight corresponding to the oxide mass fraction Omf, Amf is the alkali metal chloride mass fraction, u2 is the second weight corresponding to the alkali metal chloride mass fraction Amf, Cmf is the carbonate mass fraction, and u3 is the third weight corresponding to the carbonate mass fraction Cmf.

[0033] Optionally, the mixed fuel includes garbage fuel and coal fuel; and determining the ratio of different types of fuels in the mixed fuel according to the ash deposition rate and the solid erosion coefficient includes:

[0034] Inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel;

[0035] The ratio determination model is trained in the following way:

[0036] Acquire multiple proportion samples, each of which includes a historical solid erosion coefficient, a historical ash deposition rate, and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel;

[0037] The historical solid erosion coefficient and the historical dust deposition rate are used as input data of the first regression network, and the historical fuel ratio is used as the target output data of the first regression network. The first regression network is trained until the second training end condition is met to obtain the ratio determination model.

[0038] Optionally, determining the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio includes:

[0039] Determining the pipe section temperature of the pipe section to be detected according to the air volume and the ratio;

[0040] Inputting the pipe section temperature, the pipe section thickness and the pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface;

[0041] The life prediction model is trained in the following way:

[0042] Acquire multiple life samples, each of which includes historical pipe section temperature, historical pipe section thickness, historical pipe section material, and historical remaining life;

[0043] The historical pipe section temperature, the historical pipe section thickness and the historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain the life prediction model.

[0044] A second aspect of the present disclosure provides a life monitoring device for a boiler heating surface, comprising:

[0045] an acquisition module, used to acquire pipe section reference information of the pipe section to be detected, ash accumulation reference information of ash accumulation to be detected attached to the inner wall of the pipe section to be detected, and air volume for adjusting the combustion rate of the mixed fuel, wherein the pipe section reference information includes pipe section thickness and pipe section material, and the ash accumulation reference information includes mass fractions of different compounds in the ash accumulation;

[0046] A first determination module is used to determine the dust deposition rate;

[0047] A second determination module is used to determine the solid erosion coefficient according to the mass fraction of different compounds in the ash deposit;

[0048] A third determination module is used to determine the ratio between different types of fuels in the mixed fuel according to the dust deposition rate and the solid erosion coefficient;

[0049] The fourth determination module is used to determine the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio.

[0050] Optionally, the ash accumulation reference information further includes ash accumulation mass and ash accumulation combustion time; the first determination module includes:

[0051] A first determination submodule is used to determine the dust deposition thickness according to the dust deposition mass;

[0052] The second determination submodule is used to determine the ash adhesion rate according to the ash adhesion thickness and the ash combustion time.

[0053] Optionally, the pipe section reference information further includes a pipe section length and a pipe section radius, and the first determining submodule further includes:

[0054] The third determination submodule is used to determine the dust accumulation category;

[0055] A fourth determination submodule is used to determine a standard unit density corresponding to the dust accumulation category;

[0056] A fifth determination submodule, configured to determine the dust accumulation volume of the dust accumulation to be detected according to the dust accumulation mass and the standard unit density;

[0057] The sixth determination submodule is used to determine the dust deposition thickness according to the dust deposition volume, the pipe section length and the pipe section radius.

[0058] Optionally, the third determination submodule is used to determine the dust accumulation category in the following manner:

[0059] Acquire the surface image of the dust accumulation to be detected;

[0060] Inputting the surface image into a pre-trained dust accumulation classification model to obtain the dust accumulation category;

[0061] The dust accumulation classification model is trained in the following way:

[0062] Acquire multiple classification samples, each of which includes a historical surface image and a historical dust accumulation category;

[0063] The historical surface image is used as input data of the classifier, and the historical dust accumulation category is used as the target output data of the classifier. The classifier is trained until a first training end condition is met, thereby obtaining the dust accumulation classification model.

[0064] Optionally, the cross section of the pipe section to be detected is circular, and the sixth determination submodule is used to determine the dust deposition thickness by the following formula:

[0065]

[0066] Wherein, TDP is the dust adhesion thickness, Rps is the radius of the pipe section, Rve is the dust volume, π is the pi, and Lps is the length of the pipe section.

[0067] Optionally, the mixed fuel includes garbage fuel and coal fuel; the mass fractions of different compounds in the ash accumulation include carbonate mass fraction, oxide mass fraction and alkali metal chloride mass fraction; the second determination module is used to determine the solid erosion coefficient by the following formula:

[0068]

[0069] Among them, SEC is the solid erosion coefficient, Omf is the oxide mass fraction, u1 is the first weight corresponding to the oxide mass fraction Omf, Amf is the alkali metal chloride mass fraction, u2 is the second weight corresponding to the alkali metal chloride mass fraction Amf, Cmf is the carbonate mass fraction, and u3 is the third weight corresponding to the carbonate mass fraction Cmf.

[0070] Optionally, the mixed fuel includes garbage fuel and coal fuel; the third determination module is used to determine the ratio between different types of fuel in the mixed fuel by:

[0071] Inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel;

[0072] The ratio determination model is trained in the following way:

[0073] Acquire multiple proportion samples, each of which includes a historical solid erosion coefficient, a historical ash deposition rate, and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel;

[0074] The historical solid erosion coefficient and the historical dust deposition rate are used as input data of the first regression network, and the historical fuel ratio is used as the target output data of the first regression network. The first regression network is trained until the second training end condition is met to obtain the ratio determination model.

[0075] Optionally, the fourth determining module includes:

[0076] A sixth determination submodule, used to determine the pipe section temperature of the pipe section to be detected according to the air volume and the ratio;

[0077] A seventh determination submodule is used to input the pipe section temperature, the pipe section thickness and the pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface;

[0078] The life prediction model is trained in the following way:

[0079] Acquire multiple life samples, each of which includes historical pipe section temperature, historical pipe section thickness, historical pipe section material, and historical remaining life;

[0080] The historical pipe section temperature, the historical pipe section thickness and the historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain the life prediction model.

[0081] A third aspect of the present disclosure provides an electronic device, including:

[0082] a memory having a computer program stored thereon;

[0083] A processor is used to execute a computer program in a memory to implement the steps of the method provided in the first aspect of the present disclosure.

[0084] A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present disclosure.

[0085] In the above technical scheme, the pipe section reference information of the pipe section to be detected, the ash reference information of the ash to be detected attached to the inner wall of the pipe section to be detected, and the air volume for adjusting the combustion rate of the mixed fuel are obtained, wherein the pipe section reference information includes the pipe section thickness and the pipe section material, and the ash reference information includes the mass fraction of different compounds in the ash; the ash attachment rate is determined; the solid erosion coefficient is determined according to the mass fraction of different compounds in the ash; the ratio between different types of fuels in the mixed fuel is determined according to the ash attachment rate and the solid erosion coefficient; the remaining life of the heating surface is determined according to the pipe section reference information, the air volume and the ratio. The amount of corrosive gas and ash generated by different types of garbage in the mixed fuel is different, and the ash can prevent the corrosive gas from contacting the inner wall of the pipeline in large quantities, and inhibit high-temperature gaseous corrosion to a certain extent. Therefore, by determining the ratio between different types of fuels in the mixed fuel, the influencing factors between ash and corrosive gas can be taken into account when determining the remaining life of the heating surface, and the accuracy of the determined remaining life of the heating surface can be effectively improved.

[0086] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0088] Figure 1It is a flow chart of a method for monitoring the life of a boiler heating surface provided by an exemplary embodiment of the present disclosure.

[0089] Figure 2 It is a schematic cross-sectional view of a pipe section to be inspected provided by an exemplary embodiment of the present disclosure.

[0090] Figure 3 It is a flow chart of a method for monitoring the life of a boiler heating surface provided by an exemplary embodiment of the present disclosure.

[0091] Figure 4 It is a block diagram of a life monitoring device for a boiler heating surface provided by an exemplary embodiment of the present disclosure.

[0092] Figure 5 is a block diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0093] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0094] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0095] Figure 1 FIG. 1 is a flow chart of a method for monitoring the life of a boiler heating surface provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the method may include S101 to S105.

[0096] S101, obtaining pipe section reference information of the pipe section to be inspected, ash accumulation reference information of ash accumulation to be inspected attached to the inner wall of the pipe section to be inspected, and air volume for adjusting the combustion rate of the mixed fuel.

[0097] The pipe section reference information includes the pipe section thickness and pipe section material, and the dust accumulation reference information includes the mass fractions of different compounds in the dust accumulation.

[0098] For example, the boiler heating surface is the high-temperature heating surface of the boiler, which is composed of multiple pipe sections. The fly ash particles generated after the fuel is burned will adhere to the inner wall of the pipe section to form ash accumulation. The pipe section to be tested can be a pipe section of the boiler heating surface or a combination of multiple pipe sections.

[0099] For example, the pipe thickness of the pipe segment to be inspected can be obtained in the following way:

[0100] The real-time thickness of M detection points on the pipe section to be detected is obtained, and the real-time thickness of N detection points is screened out according to the real-time thickness of the M detection points; the average thickness is determined according to the real-time thickness of the N detection points, and the average thickness is used as the pipe section thickness of the pipe section to be detected, wherein M is greater than or equal to N.

[0101] For example, the real-time thicknesses of the M detection points can be arranged in order from small to large, and the first N data in the arrangement order are determined as the real-time thicknesses of the screened N detection points. In this way, the reliability of the thickness of the pipe section to be detected can be improved.

[0102] By way of example, pipe segment materials include, but are not limited to, carbon steel pipes and stainless steel pipes.

[0103] For example, the ash to be detected can be obtained by cleaning the pipe section to be detected. Among them, the mixed fuel is a mixture of multiple types of fuels, and the types of compounds in the ash produced by different types of fuels are different. Taking the mixed fuel including garbage fuel and coal fuel as an example, garbage fuel is usually a composite material, and its chemical composition may be relatively complex and diverse. During its combustion, it will produce more alkali metal chlorides and oxides, while coal fuel is usually a mineral mainly composed of elements such as carbon, hydrogen, oxygen, nitrogen and sulfur. Coal fuel is more likely to produce carbonates during combustion. Therefore, the different compounds in the ash to be detected attached to the inner wall of the pipe section to be detected may include but are not limited to carbonates, oxides and alkali metal chlorides. Among them, the mass fraction of carbonates can be determined by pyrolysis, the mass fraction of oxides can be determined by X-ray fluorescence analysis, and the alkali metal chlorides can be determined by ion chromatography.

[0104] For example, the air volume used to adjust the combustion rate of the mixed fuel can be retrieved from a database associated with historical combustion data.

[0105] S102, determining the dust deposition rate.

[0106] Taking mixed fuel including garbage fuel and coal fuel as an example, during the combustion of garbage fuel, more corrosive gases are generated, but fewer fly ash particles are generated. On the contrary, during the combustion of coal fuel, more fly ash particles are generated. Therefore, the ash adhesion rate can characterize the proportion of garbage fuel and coal fuel in the mixed fuel to a certain extent. The faster the ash adhesion rate, the greater the proportion of coal fuel.

[0107] S103, determining the solid erosion coefficient according to the mass fraction of different compounds in the ash deposits.

[0108] Still taking the mixed fuel including garbage fuel and coal fuel as an example, the mass fractions of different compounds in the ash include the mass fraction of carbonate, the mass fraction of oxide and the mass fraction of alkali metal chloride.

[0109] Under the same mass, during the combustion of coal fuel, the mass fraction of carbonate in the ash is relatively high, while during the combustion of garbage fuel, the mass fraction of oxide and alkali chloride in the ash is relatively high. Therefore, the first reference value can be determined according to the sum of the product of the mass fraction of oxide and its corresponding weight and the product of the mass fraction of alkali chloride and its corresponding weight; the second reference value is determined according to the ratio of the mass fraction of carbonate and its corresponding weight, and the solid erosion coefficient is determined according to the ratio of the first reference value to the second reference value. Specifically, the solid erosion coefficient can be determined by the following formula, including:

[0110]

[0111] Wherein, SEC is the solid erosion coefficient, Omf is the oxide mass fraction, u1 is the first weight corresponding to the oxide mass fraction Omf, Amf is the alkali metal chloride mass fraction, u2 is the second weight corresponding to the alkali metal chloride mass fraction Amf, Cmf is the carbonate mass fraction, and u3 is the third weight corresponding to the carbonate mass fraction Cmf. The first weight u1, the second weight u2 and the third weight u3 are pre-calibrated based on actual needs.

[0112] In this way, the larger the solid erosion coefficient is, the greater the proportion of garbage fuel in the mixed fuel produced by coal fuel and garbage fuel. On the contrary, the smaller the solid erosion coefficient is, the greater the proportion of coal fuel in the mixed fuel produced by coal fuel and garbage fuel.

[0113] S104, determining the ratio of different types of fuels in the mixed fuel according to the dust deposition rate and the solid erosion coefficient.

[0114] Still taking the mixed fuel including garbage fuel and coal fuel as an example, the ratio between different types of fuel in the mixed fuel can be determined according to the ash deposition rate and solid erosion coefficient in the following way:

[0115] The ash deposition rate and solid erosion coefficient are input into the pre-trained ratio determination model to obtain the ratio between garbage fuel and coal fuel.

[0116] Among them, the proportion determination model can be trained in the following way:

[0117] A plurality of proportion samples are obtained, each proportion sample including a historical solid erosion coefficient, a historical ash deposition rate and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel;

[0118] The historical solid erosion coefficient and the historical ash deposition rate are used as input data of the first regression network, and the historical fuel ratio is used as the target output data of the first regression network. The first regression network is trained until the second training end condition is met to obtain a ratio determination model.

[0119] For example, the second training end condition may be that the loss value of the proportional determination model is less than the corresponding model loss threshold, or that the number of training times of the proportional determination model reaches the corresponding model training times threshold. Specifically, a plurality of proportional samples may be divided into a proportional sample training set and a proportional sample test set, and the historical solid erosion coefficient and the historical dust deposition rate in the proportional sample training set are used as input data of the first regression network, and the historical fuel ratio in the proportional sample training set is used as the target output data of the first regression network. The first regression network is trained to obtain an initial first regression network for determining the fuel ratio, and the initial first regression network is tested using the proportional sample test set, and the first regression network that satisfies the error less than the first preset error value is output as the proportional determination model, wherein the first regression network is preferably a neural network model.

[0120] The above-mentioned proportion samples can be determined in advance through experiments. For example, technical personnel in this field first mix garbage fuel and coal fuel in a certain proportion, and then burn the mixed fuel to generate electricity. After a certain period of time, the pipe section of the heating surface is taken out and the ash attached to the inner wall is obtained. Finally, the solid erosion coefficient and ash adhesion rate corresponding to the ash are obtained, so as to establish a connection between the historical solid erosion coefficient, the historical ash adhesion rate and the historical fuel ratio to form sample data.

[0121] It should be noted that, usually in the actual production process of a power plant, the power plant only generates electricity through mixed fuels, but does not participate in the production of mixed fuels. The production of mixed fuels is completed by the waste energy plant that cooperates with the power plant, so the power plant is not clear about the fuel ratio in the mixed fuel. In the present disclosure, the ratio between different types of fuels in the mixed fuel can be determined, so that when determining the remaining life of the heating surface, the influencing factors between ash accumulation and corrosive gases are taken into account, thereby improving the accuracy and reliability of the remaining life monitoring results of the heating surface.

[0122] S105, determining the remaining life of the heating surface according to the pipe section reference information, air volume and ratio.

[0123] In one embodiment, the remaining life of the heating surface can be determined according to the pipe section reference information, air volume and ratio in the following manner:

[0124] Determine the pipe section temperature of the pipe section to be tested according to the air volume and ratio;

[0125] The pipe section temperature, pipe section thickness and pipe section material are input into the pre-trained life prediction model to obtain the remaining life of the heated surface.

[0126] For example, the pipe section temperature corresponding to the current air volume and the current ratio can be determined based on the correspondence between the ratio of different types of fuels in the pre-calibrated mixed fuel, the air volume and the pipe section temperature. Under the same air volume, garbage fuel usually contains more volatile substances, such as organic waste, plastics, etc. These substances will release a large amount of heat when burned. Therefore, the greater the proportion of garbage fuel, the higher the corresponding pipe temperature. In the experimental process of calibrating the above-mentioned correspondence, the air volume and ratio can be controlled by a technician in this field, and the pipe temperature can be obtained by contact measurement or non-contact measurement. Exemplarily, the non-contact measurement method is infrared thermal imaging.

[0127] For example, the lifespan prediction model is trained in the following way:

[0128] Obtain multiple life samples, each life sample includes historical pipe section temperature, historical pipe section thickness, historical pipe section material and historical remaining life;

[0129] The historical pipe section temperature, historical pipe section thickness and historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain a life prediction model.

[0130] For example, the third training end condition may be that the loss value of the life prediction model is less than the corresponding model loss threshold, or that the number of training times of the life prediction model reaches the corresponding model training times threshold. Specifically, multiple life samples can be divided into a life sample training set and a life sample test set, and the historical pipe section temperature, historical pipe section thickness and historical pipe section material in the life sample training set are used as input data of the second regression network, and the historical remaining life in the life sample training set is used as the target output data of the second regression network to train the second regression network, and an initial second regression network for determining the remaining life of the heating surface is obtained, and the initial second regression network is tested using the life sample test set, and a second regression network that satisfies a second preset error value is output as the life prediction model, wherein the second regression network is preferably a neural network model.

[0131] In the above technical scheme, the pipe section reference information of the pipe section to be detected, the ash reference information of the ash to be detected attached to the inner wall of the pipe section to be detected, and the air volume for adjusting the combustion rate of the mixed fuel are obtained, wherein the pipe section reference information includes the pipe section thickness and the pipe section material, and the ash reference information includes the mass fraction of different compounds in the ash; the ash attachment rate is determined; the solid erosion coefficient is determined according to the mass fraction of different compounds in the ash; the ratio between different types of fuels in the mixed fuel is determined according to the ash attachment rate and the solid erosion coefficient; the remaining life of the heating surface is determined according to the pipe section reference information, the air volume and the ratio. The amount of corrosive gas and ash generated by different types of garbage in the mixed fuel is different, and the ash can prevent the corrosive gas from contacting the inner wall of the pipeline in large quantities, and inhibit high-temperature gaseous corrosion to a certain extent. Therefore, by determining the ratio between different types of fuels in the mixed fuel, the influencing factors between ash and corrosive gas can be taken into account when determining the remaining life of the heating surface, and the accuracy of the determined remaining life of the heating surface can be effectively improved.

[0132] In an optional embodiment, the ash accumulation reference information may further include ash accumulation mass and ash accumulation combustion time; in S102, determining the ash accumulation attachment rate may include:

[0133] Determine the dust adhesion thickness according to the dust quality;

[0134] The ash adhesion rate is determined based on the ash adhesion thickness and the ash combustion time.

[0135] For example, the mass of the ash deposit to be detected attached to the inner wall of the pipe section to be detected is the weight of the ash deposit to be detected attached to the inner wall of the pipe section to be detected, which can be obtained based on a weight sensor. The combustion time of the ash deposit to be detected attached to the inner wall of the pipe section to be detected can be called from a database related to historical combustion data.

[0136] In one embodiment, the dust accumulation thickness can be determined according to the dust accumulation mass in the following manner:

[0137] Determine the type of dust accumulation;

[0138] Determine the standard unit density corresponding to the dust accumulation category;

[0139] Determine the volume of the dust accumulation to be tested according to the dust accumulation mass and the standard unit density;

[0140] Determine the dust adhesion thickness based on the dust accumulation volume, pipe section length and pipe section radius.

[0141] For example, the dust accumulation category can be determined in the following way:

[0142] Acquire a surface image of dust accumulation to be detected;

[0143] Input the surface image into the pre-trained dust accumulation classification model to obtain the dust accumulation category;

[0144] The dust accumulation categories include crystalline dust accumulation and non-crystalline dust accumulation; the dust accumulation classification model can be trained in the following ways:

[0145] Acquire multiple classification samples, each classification sample includes a historical surface image and a historical dust accumulation category;

[0146] The historical surface image is used as the input data of the classifier, and the historical dust accumulation category is used as the target output data of the classifier. The classifier is trained until the first training end condition is met, and a dust accumulation classification model is obtained.

[0147] For example, the first training end condition may be that the loss value of the dust accumulation classification model is less than the corresponding model loss threshold, or that the number of training times of the dust accumulation classification model reaches the corresponding model training times threshold. Specifically, multiple classification samples can be divided into a classification sample training set and a classification sample test set; the historical surface images in the classification sample training set are used as the input data of the classifier, and the historical dust accumulation categories in the classification sample training set are used as the target output data of the classifier, and the classifier is trained to obtain an initial classifier, and the initial classifier is tested using the classification sample test set, and the classifier that satisfies the error value less than the third preset error value is output as the dust accumulation classification model. Among them, the classifier is preferably a naive Bayes model or a support vector machine model.

[0148] The presence of alkali chloride in the dust to be detected can easily react with the inner wall of the pipe section to be detected to form crystals. The standard unit density is the mass of the substance contained in the unit volume, and the standard unit density of crystalline dust is different from that of non-crystalline dust. Therefore, by determining the dust category, the standard unit density that is compatible with the actual dust can be determined, thereby improving the reliability of the determined dust volume. For example, the standard unit density corresponding to the current dust category can be determined based on the correspondence between the pre-calibrated dust category and the standard unit density. In this way, the standard unit density corresponding to the dust category can be determined simply and quickly, thereby determining the dust volume.

[0149] For example, the cross section of the pipe to be tested is a circle. Figure 2 The inner wall of the pipe section to be inspected is covered with dust. Figure 2 In the calculation, TDP is the dust deposition thickness, Rps is the pipe radius, and the dust deposition thickness can be determined by the following formula:

[0150]

[0151] Wherein, TDP is the dust deposition thickness, Rps is the pipe radius, Rve is the dust deposition volume, π is the pi ratio, and Lps is the pipe length. It can be understood that the above method for calculating the dust deposition thickness is calculated when the cross section of the pipe to be detected is circular. If the cross section of the pipe to be detected is rectangular, it can be calculated by a method corresponding to a rectangle, and this embodiment will not be repeated in detail.

[0152] In one embodiment, the dust deposition rate ADR may be determined by the following formula:

[0153]

[0154] Among them, HCT is the ash combustion time.

[0155] Figure 3 is a flow chart of a method for monitoring the life of a boiler heating surface provided by an exemplary embodiment of the present disclosure. Figure 3 , the implementation process of the boiler heating surface life monitoring method provided by the present disclosure can be more clearly understood, such as Figure 3 As shown, the method may include S301 to S310.

[0156] S301, obtaining pipe section reference information of the pipe section to be inspected, ash accumulation reference information of ash accumulation to be inspected attached to the inner wall of the pipe section to be inspected, air volume for adjusting the combustion rate of the mixed fuel, and a surface image of the ash accumulation to be inspected.

[0157] Among them, the pipe section reference information includes the pipe section thickness, pipe section material, pipe section length and pipe section radius; the ash accumulation reference information includes the mass fraction of different compounds in the ash accumulation, the ash accumulation mass and the ash accumulation combustion time; the pipe section material includes carbon steel pipe and stainless steel pipe; the mixed fuel includes garbage fuel and coal fuel; the mass fraction of different compounds in the ash accumulation includes the mass fraction of carbonate, the mass fraction of oxide and the mass fraction of alkali metal chloride.

[0158] S302, inputting the surface image into a pre-trained dust accumulation classification model to obtain a dust accumulation category.

[0159] Among them, the dust accumulation categories include crystalline dust accumulation and non-crystalline dust accumulation.

[0160] S303, determining a standard unit density corresponding to the dust accumulation category.

[0161] S304: Determine the volume of the dust accumulation to be detected according to the dust accumulation mass and the standard unit density.

[0162] S305, determining the dust deposition thickness according to the dust deposition volume, the pipe section length and the pipe section radius.

[0163] S306, determining the ash deposition rate according to the ash deposition thickness and the ash deposition combustion time.

[0164] S307, determining the solid erosion coefficient according to the mass fraction of different compounds in the ash deposits.

[0165] S308, inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel.

[0166] S309, determining the pipe section temperature of the pipe section to be inspected according to the air volume and the ratio.

[0167] S310, inputting the pipe section temperature, pipe section thickness and pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface.

[0168] Different types of garbage in the mixed fuel produce different amounts of corrosive gas and ash accumulation, and ash accumulation can prevent corrosive gas from contacting the inner wall of the pipeline in large quantities, inhibiting high-temperature gaseous corrosion to a certain extent. Therefore, by determining the ratio between different types of fuel in the mixed fuel, the influencing factors between ash accumulation and corrosive gas can be taken into account when determining the remaining life of the heating surface, effectively improving the accuracy of the determined remaining life of the heating surface.

[0169] The specific implementation of the above steps S301 to S310 has been described in detail above, and the repeated content will not be repeated here. In addition, the model involved in the present disclosure can be stored locally in the electronic device and called locally each time it is used, or can be stored on a third-party platform and called from a third party each time it is used, which is not specifically limited here.

[0170] Based on the same inventive concept, the present disclosure also provides a life monitoring device for a boiler heating surface. Figure 4 4 is a block diagram of a boiler heating surface life monitoring device 400 provided by an exemplary embodiment of the present disclosure.

[0171] Reference Figure 4 The boiler heating surface life monitoring device 400 may include:

[0172] An acquisition module 401 is used to acquire pipe section reference information of the pipe section to be detected, ash accumulation reference information of the ash accumulation to be detected attached to the inner wall of the pipe section to be detected, and air volume for adjusting the combustion rate of the mixed fuel, wherein the pipe section reference information includes pipe section thickness and pipe section material, and the ash accumulation reference information includes mass fractions of different compounds in the ash accumulation;

[0173] The first determination module 402 is used to determine the dust deposition rate;

[0174] A second determination module 403 is used to determine a solid erosion coefficient according to the mass fractions of different compounds in the ash deposits;

[0175] A third determination module 404 is used to determine the ratio between different types of fuels in the mixed fuel according to the dust deposition rate and the solid erosion coefficient;

[0176] The fourth determination module 405 is used to determine the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio.

[0177] Different types of garbage in the mixed fuel produce different amounts of corrosive gas and ash accumulation, and ash accumulation can prevent corrosive gas from contacting the inner wall of the pipeline in large quantities, inhibiting high-temperature gaseous corrosion to a certain extent. Therefore, by determining the ratio between different types of fuel in the mixed fuel, the influencing factors between ash accumulation and corrosive gas can be taken into account when determining the remaining life of the heating surface, effectively improving the accuracy of the determined remaining life of the heating surface.

[0178] Optionally, the ash accumulation reference information further includes ash accumulation mass and ash accumulation combustion time; the first determination module 402 includes:

[0179] A first determination submodule is used to determine the dust deposition thickness according to the dust deposition mass;

[0180] The second determination submodule is used to determine the ash adhesion rate according to the ash adhesion thickness and the ash combustion time.

[0181] Optionally, the pipe section reference information further includes a pipe section length and a pipe section radius, and the first determining submodule further includes:

[0182] The third determination submodule is used to determine the dust accumulation category;

[0183] A fourth determination submodule is used to determine a standard unit density corresponding to the dust accumulation category;

[0184] A fifth determination submodule, configured to determine the dust accumulation volume of the dust accumulation to be detected according to the dust accumulation mass and the standard unit density;

[0185] The sixth determination submodule is used to determine the dust deposition thickness according to the dust deposition volume, the pipe section length and the pipe section radius.

[0186] Optionally, the third determination submodule is used to determine the dust accumulation category in the following manner:

[0187] Acquire the surface image of the dust accumulation to be detected;

[0188] Inputting the surface image into a pre-trained dust accumulation classification model to obtain the dust accumulation category;

[0189] The dust accumulation classification model is trained in the following way:

[0190] Acquire multiple classification samples, each of which includes a historical surface image and a historical dust accumulation category;

[0191] The historical surface image is used as input data of the classifier, and the historical dust accumulation category is used as the target output data of the classifier. The classifier is trained until a first training end condition is met, thereby obtaining the dust accumulation classification model.

[0192] Optionally, the cross section of the pipe section to be detected is circular, and the sixth determination submodule is used to determine the dust deposition thickness by the following formula:

[0193]

[0194] Wherein, TDP is the dust adhesion thickness, Rps is the radius of the pipe section, Rve is the dust volume, π is the pi, and Lps is the length of the pipe section.

[0195] Optionally, the mixed fuel includes garbage fuel and coal fuel; the mass fractions of different compounds in the ash include carbonate mass fraction, oxide mass fraction and alkali metal chloride mass fraction; the second determination module 403 is used to determine the solid erosion coefficient by the following formula:

[0196]

[0197] Among them, SEC is the solid erosion coefficient, Omf is the oxide mass fraction, u1 is the first weight corresponding to the oxide mass fraction Omf, Amf is the alkali metal chloride mass fraction, u2 is the second weight corresponding to the alkali metal chloride mass fraction Amf, Cmf is the carbonate mass fraction, and u3 is the third weight corresponding to the carbonate mass fraction cmf.

[0198] Optionally, the mixed fuel includes garbage fuel and coal fuel; the third determination module 404 is used to determine the ratio between different types of fuel in the mixed fuel by:

[0199] Inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel;

[0200] The ratio determination model is trained in the following way:

[0201] Acquire multiple proportion samples, each of which includes a historical solid erosion coefficient, a historical ash deposition rate, and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel;

[0202] The historical solid erosion coefficient and the historical dust deposition rate are used as input data of the first regression network, and the historical fuel ratio is used as the target output data of the first regression network. The first regression network is trained until the second training end condition is met to obtain the ratio determination model.

[0203] Optionally, the fourth determining module 405 includes:

[0204] A sixth determination submodule, used to determine the pipe section temperature of the pipe section to be detected according to the air volume and the ratio;

[0205] A seventh determination submodule is used to input the pipe section temperature, the pipe section thickness and the pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface;

[0206] The life prediction model is trained in the following way:

[0207] Acquire multiple life samples, each of which includes historical pipe section temperature, historical pipe section thickness, historical pipe section material, and historical remaining life;

[0208] The historical pipe section temperature, the historical pipe section thickness and the historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain the life prediction model.

[0209] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0210] Figure 5 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 5 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0211] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned boiler heating surface life monitoring method. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0212] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned boiler heating surface life monitoring method.

[0213] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned boiler heating surface life monitoring method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned boiler heating surface life monitoring method.

[0214] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned boiler heating surface life monitoring method when executed by the programmable device.

[0215] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0216] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0217] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0218] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0219] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0220] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0221] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0222] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0223] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the life of a boiler heating surface, characterized in that: The life monitoring method comprises: Obtaining pipe section reference information of the pipe section to be detected, ash accumulation reference information of the ash accumulation to be detected attached to the inner wall of the pipe section to be detected, and air volume for adjusting the combustion rate of the mixed fuel, wherein the pipe section reference information includes pipe section thickness and pipe section material, and the ash accumulation reference information includes mass fractions of different compounds in the ash accumulation; Determine the dust deposition rate; Determining a solid erosion coefficient according to the mass fractions of different compounds in the ash deposits; Determining the ratio of different types of fuel in the mixed fuel according to the dust deposition rate and the solid erosion coefficient; Determining the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio; The ash accumulation reference information also includes ash accumulation mass and ash accumulation combustion time; and determining the ash accumulation attachment rate includes: Determining the dust accumulation thickness according to the dust accumulation mass; Determining the ash deposition rate according to the ash deposition thickness and the ash deposition combustion time; The mixed fuel includes garbage fuel and coal fuel; the mass fractions of different compounds in the ash deposit include carbonate mass fraction, oxide mass fraction and alkali metal chloride mass fraction; the solid erosion coefficient is determined according to the mass fractions of different compounds in the ash deposit, including: The solid erosion coefficient is determined by the following formula: SEC = ； in, SEC is the solid erosion coefficient, is the mass fraction of the oxide, is the mass fraction of the oxide The corresponding first weight is is the mass fraction of the alkali metal chloride, is the mass fraction of the alkali metal chloride The corresponding second weight is, is the carbonate mass fraction, is the carbonate mass fraction The corresponding third weight; The mixed fuel includes garbage fuel and coal fuel; and the ratio of different types of fuel in the mixed fuel is determined according to the ash deposition rate and the solid erosion coefficient, including: Inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel; The ratio determination model is trained in the following way: Acquire multiple proportion samples, each of which includes a historical solid erosion coefficient, a historical ash deposition rate, and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel; Taking the historical solid erosion coefficient and the historical dust deposition rate as input data of a first regression network, taking the historical fuel ratio as target output data of the first regression network, training the first regression network until a second training end condition is met, and obtaining the ratio determination model; The determining the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio includes: Determining the pipe section temperature of the pipe section to be detected according to the air volume and the ratio; Inputting the pipe section temperature, the pipe section thickness and the pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface; The life prediction model is trained in the following way: Acquire multiple life samples, each of which includes historical pipe section temperature, historical pipe section thickness, historical pipe section material, and historical remaining life; The historical pipe section temperature, the historical pipe section thickness and the historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain the life prediction model.

2. The life monitoring method according to claim 1, characterized in that: The pipe section reference information also includes the pipe section length and the pipe section radius. The determining of the dust deposition thickness according to the dust deposition mass includes: Determine the type of dust accumulation; Determining a standard unit density corresponding to the dust accumulation category; Determining the dust accumulation volume of the dust accumulation to be detected according to the dust accumulation mass and the standard unit density; The dust accumulation thickness is determined according to the dust accumulation volume, the pipe section length and the pipe section radius.

3. The life monitoring method according to claim 2, characterized in that: Determining the dust accumulation category includes: Acquire the surface image of the dust accumulation to be detected; Inputting the surface image into a pre-trained dust accumulation classification model to obtain the dust accumulation category; The dust accumulation classification model is trained in the following way: Acquire multiple classification samples, each of which includes a historical surface image and a historical dust accumulation category; The historical surface image is used as input data of the classifier, and the historical dust accumulation category is used as target output data of the classifier. The classifier is trained until a first training end condition is met, thereby obtaining the dust accumulation classification model.

4. The life monitoring method according to claim 3, characterized in that: The cross section of the pipe section to be detected is circular; the dust accumulation thickness is determined according to the dust accumulation volume, the pipe section length and the pipe section radius, including: The dust deposition thickness is determined by the following formula: TDP = ； in, TDP is the dust deposition thickness, is the radius of the pipe segment, is the dust accumulation volume, is the circumference of a circle, is the length of the pipe section.

5. A life monitoring device for a boiler heating surface, characterized in that: The life monitoring device comprises: an acquisition module, used to acquire pipe section reference information of the pipe section to be detected, ash accumulation reference information of ash accumulation to be detected attached to the inner wall of the pipe section to be detected, and air volume for adjusting the combustion rate of the mixed fuel, wherein the pipe section reference information includes pipe section thickness and pipe section material, and the ash accumulation reference information includes mass fractions of different compounds in the ash accumulation; A first determination module is used to determine the dust deposition rate; A second determination module is used to determine the solid erosion coefficient according to the mass fraction of different compounds in the ash deposit; A third determination module is used to determine the ratio between different types of fuels in the mixed fuel according to the dust deposition rate and the solid erosion coefficient; A fourth determination module, used to determine the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio; The ash accumulation reference information also includes ash accumulation mass and ash accumulation combustion time; and determining the ash accumulation attachment rate includes: Determining the dust accumulation thickness according to the dust accumulation mass; Determining the ash deposition rate according to the ash deposition thickness and the ash deposition combustion time; The mixed fuel includes garbage fuel and coal fuel; the mass fractions of different compounds in the ash deposit include carbonate mass fraction, oxide mass fraction and alkali metal chloride mass fraction; the solid erosion coefficient is determined according to the mass fractions of different compounds in the ash deposit, including: The solid erosion coefficient is determined by the following formula: SEC = ； in, SEC is the solid erosion coefficient, is the mass fraction of the oxide, is the mass fraction of the oxide The corresponding first weight is is the mass fraction of the alkali metal chloride, is the mass fraction of the alkali metal chloride The corresponding second weight is, is the carbonate mass fraction, is the carbonate mass fraction The corresponding third weight; The mixed fuel includes garbage fuel and coal fuel; and the ratio of different types of fuel in the mixed fuel is determined according to the ash deposition rate and the solid erosion coefficient, including: Inputting the dust deposition rate and the solid erosion coefficient into a pre-trained ratio determination model to obtain the ratio between the garbage fuel and the coal fuel; The ratio determination model is trained in the following way: Acquire multiple proportion samples, each of which includes a historical solid erosion coefficient, a historical ash deposition rate, and a historical fuel ratio, wherein the historical fuel ratio is a ratio between historical garbage fuel and historical coal fuel; Taking the historical solid erosion coefficient and the historical dust deposition rate as input data of a first regression network, taking the historical fuel ratio as target output data of the first regression network, training the first regression network until a second training end condition is met, and obtaining the ratio determination model; The determining the remaining life of the heating surface according to the pipe section reference information, the air volume and the ratio includes: Determining the pipe section temperature of the pipe section to be detected according to the air volume and the ratio; Inputting the pipe section temperature, the pipe section thickness and the pipe section material into a pre-trained life prediction model to obtain the remaining life of the heating surface; The life prediction model is trained in the following way: Acquire multiple life samples, each of which includes historical pipe section temperature, historical pipe section thickness, historical pipe section material, and historical remaining life; The historical pipe section temperature, the historical pipe section thickness and the historical pipe section material are used as input data of the second regression network, and the historical remaining life is used as the target output data of the second regression network. The second regression network is trained until the third training end condition is met to obtain the life prediction model.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

7. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 4.

Images