Cost prediction method based on solid waste heat treatment neural network model

Abstract

The invention discloses a cost prediction method based on a solid waste heat treatment neural network model, and belongs to the technical field of solid waste heat treatment. The problem of accurate prediction of the heat treatment cost of the solid waste is solved. The method comprises the following steps: constructing a first hidden layer of a solid waste heat treatment prediction model based on deep learning; constructing a second hidden layer of the solid waste heat treatment prediction model based on deep learning; constructing an output layer of the solid waste heat treatment prediction model based on deep learning; designing a loss function of the solid waste heat treatment prediction model based on deep learning; the input layer, the first hidden layer, the second hidden layer and the output layer are sequentially connected to obtain a solid waste heat treatment prediction model based on deep learning; and performing reverse normalization based on the prediction result to obtain the prediction result of the solid waste heat treatment prediction model with the actual physical quantity and based on deep learning, and constructing the cost prediction method based on the solid waste heat treatment neural network model.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of solid waste heat treatment, and particularly relates to a cost prediction method based on a solid waste heat treatment neural network model. BACKGROUND

[0002] The solid waste heat treatment process involves complex conversion of matter and energy. First, the components of solid waste have high heterogeneity and uncertainty, including combustibles, moisture, inorganics, and other ingredients, the proportions of which change over time and source. Second, drying, pyrolysis, combustion, and other physical and chemical processes occur simultaneously during the heat treatment process, and these processes have significant coupling effects. The drying process affects the subsequent pyrolysis and combustion effects, the composition of pyrolysis products affects the combustion characteristics, and the combustion heat release in turn affects drying and pyrolysis. At the same time, the distribution of temperature field, flow field, and concentration field also interact with each other, forming a complex multi-field coupling. In addition, there are multi-scale processes such as heat and mass transfer, chemical reaction, and phase change in the furnace, and the nonlinear characteristics and dynamic changes of these processes bring great challenges to process control.

[0003] In the solid waste heat treatment process, conversion efficiency directly reflects the degree of material conversion and is related to the completeness of incineration and the generation of pollutants. For example, carbon conversion rate affects the completeness of combustion and carbon dioxide emissions, and sulfur and chlorine conversion rates are closely related to the generation of acid gases. Product distribution determines the pollution control strategy and resource utilization direction, and accurate prediction helps to optimize the subsequent treatment process. Energy conversion reflects the level of energy utilization, which is of great significance to improve system efficiency and reduce operating costs. Accurate prediction of these indicators can provide decision-making basis for process optimization and intelligent control, and is of great significance to improve system operation efficiency, reduce pollutant emissions, and ensure safe and stable operation.

[0004] Currently, the prediction of key indicators in the solid waste heat treatment process mainly has the following shortcomings: First, the prediction accuracy is generally not high, especially when the working conditions fluctuate greatly, the predicted results deviate significantly from the actual values. Second, the existing models consider only a single influencing factor, often focusing on only some major process parameters, while ignoring the influence of important factors such as material properties and environmental conditions, resulting in poor adaptability of the model to complex working conditions. In addition, most models only predict a single or a few indicators, and lack comprehensive prediction capability for conversion efficiency, product distribution, and energy conversion of multiple key indicators. It is urgent to establish a comprehensive model that considers more comprehensive factors and has better prediction effect to meet the actual engineering needs.

[0005] On the other hand, the solid waste heat treatment cost prediction method is the inevitable demand for scientific management of modern solid waste treatment facilities. The lack of cost prediction method will make enterprises unable to accurately evaluate the treatment cost of solid waste with different characteristics, resulting in lack of scientific basis for treatment strategy making; it is difficult to predict the influence of process parameter adjustment on cost, which increases the risk of operation decision; it is difficult to respond to the cost change caused by the fluctuation of solid waste characteristics in time, which affects the economic benefit of enterprises. SUMMARY

[0006] The problem to be solved by the present application is the accurate prediction of the cost of solid waste heat treatment, and a cost prediction method based on a solid waste heat treatment neural network model is proposed.

[0007] To achieve the above-mentioned purpose, the present application realizes by the following technical scheme:

[0008] A cost prediction method based on a solid waste heat treatment neural network model, comprising the following steps:

[0009] S1. Determine the input parameters of the input layer of the solid waste heat treatment prediction model based on deep learning, including material characteristic parameters, process operation parameters and process parameters;

[0010] S2. Construct the first hidden layer in the main layer of the solid waste heat treatment prediction model based on deep learning;

[0011] S3. Construct the second hidden layer in the main layer of the solid waste heat treatment prediction model based on deep learning, and the first hidden layer is connected to the second hidden layer;

[0012] S4. Construct the output layer of the solid waste heat treatment prediction model based on deep learning, divide the output layer into conversion efficiency group, product distribution group and energy conversion group, and determine the output parameters of the output layer of the solid waste heat treatment prediction model based on deep learning;

[0013] S5. Design the loss function of the solid waste heat treatment prediction model based on deep learning;

[0014] S6. Connect the input layer, main layer and output layer of the solid waste heat treatment prediction model based on deep learning in sequence to obtain the solid waste heat treatment prediction model based on deep learning;

[0015] S7. Collect data through the solid waste treatment plant and the automatic control system, and normalize the data; divide the data into training set, validation set and test set according to the ratio of 7:2:1, train, validate and test the solid waste heat treatment prediction model based on deep learning obtained in step S6 to obtain the trained solid waste heat treatment prediction model based on deep learning;

[0016] S8. Based on the prediction results of the trained deep learning-based solid waste thermal treatment prediction model, the prediction results of the deep learning-based solid waste thermal treatment prediction model with actual physical quantities are obtained after inverse normalization, and a cost prediction method based on the solid waste thermal treatment neural network model is constructed.

[0017] Further, the number of nodes of the input layer in step S1 is determined as 35, respectively denoted as X1-X 35 ;

[0018] X1~X 14 is a material characteristic parameter, and the specific parameters are as follows: X1 is moisture content, X2 is ash content, X3 is combustible content, X4 is carbon content, X5 is hydrogen content, X6 is oxygen content, X7 is nitrogen content, X8 is sulfur content, X9 is chlorine content, X 10 is calorific value, X 11 is bulk density, X 12 is particle size, X 13 is sand content, X 14 is metal content;

[0019] X 15 ~X 25 is a process operating parameter, and the specific parameters are as follows: X 15 is grate speed, X 16 is feed rate, X 17 is primary air volume, X 18 is secondary air volume, X 19 is furnace temperature, X 20 is furnace negative pressure, X 21 is flue gas temperature, X 22 is steam temperature, X 23 is steam pressure, X 24 is steam flow, X 25 is ambient temperature;

[0020] X 26 ~X 35 is a process parameter, and the specific parameters are as follows: X 26 is feed moisture content, X 27 is discharge moisture content, X 28 is feed volatile matter, X 29 is discharge volatile matter, X 30 is feed mass flow rate, X 31 is discharge mass flow rate, X 32 is feed calorific value, X 33 is discharge calorific value, X 34 is smoke oxygen concentration, X 35 is ash content.

[0021] Further, step S2 divides the nodes of the first hidden layer into a material property group, a reaction property group, and an energy property group.

[0022] The specific implementation method of step S2 includes the following steps:

[0023] S2.1. Temperature correction and material moisture correction are introduced in the construction of the material property group. The temperature correction considers the driving effect of temperature on the conversion rate of the material and reflects the differences in the conversion law of the material in different temperature intervals. The material moisture correction considers the influence of the water evaporation process on the subsequent conversion;

[0024] S2.2. The mass conversion term is introduced in the construction of the reaction property group to directly reflect the reaction degree of the material and embody the depth of the reaction. The air excess term is added to represent the sufficiency of the combustion environment and reflect the influence of the oxidation reaction condition on the conversion effect;

[0025] S2.3. The heat value conversion term is introduced in the construction of the energy property group to directly represent the energy conversion effect. The temperature gradient term is added to reflect the driving force and intensity of heat transfer and describe the spatial distribution law of energy.

[0026] Further, step S3 divides the nodes of the second hidden layer into a drying process group, a pyrolysis process group, and a combustion process group. The drying process group describes the influence of the drying process on the subsequent pyrolysis and combustion, contains 15 neuron nodes, and the ith4 neuron node takes a value of 1-15. The pyrolysis process group describes the composition change characteristics of the pyrolysis products, contains 20 neuron nodes, and the ith5 neuron node takes a value of 16-35. The combustion process group describes the process characteristics of the final oxidation stage, contains 15 neuron nodes, and the ith6 neuron node takes a value of 36-50.

[0027] The specific implementation method of step S3 includes the following steps:

[0028] S3.1. The drying process group is constructed to represent the process characteristics of water removal in solid waste, reflect the driving effect of temperature on water evaporation, and describe the influence of the drying process on the subsequent pyrolysis and combustion;

[0029] S3.2. The pyrolysis process group is constructed to reflect the influence law of temperature on the volatilization, describe the composition change characteristics of the pyrolysis products, and realize the extraction of the key characteristics of the pyrolysis stage through the kinetic characteristics of organic matter pyrolysis decomposition;

[0030] S3.3. The combustion process group is constructed to represent the oxidation process of fixed carbon and volatile matter, reflect the influence of oxygen concentration on the combustion effect, and describe the process characteristics of the final oxidation stage

[0031] Further, step S4 divides the output layer into conversion efficiency group, product distribution group and energy conversion group based on the evaluation needs of the solid waste heat treatment process; the conversion efficiency group indexes reflect the integrity and sufficiency of material conversion, the product distribution group indexes reveal the migration law and environmental impact of the material, and the energy conversion group indexes embody the energy utilization level;

[0032] The conversion efficiency group indexes include Y1-Y6, Y1 is water conversion rate, Y2 is volatile conversion rate, Y3 is fixed carbon conversion rate, Y4 is carbon conversion rate, Y5 is sulfur conversion rate, and Y6 is chlorine conversion rate;

[0033] The product distribution group indexes include material distribution proportion indexes Y 71 ~Y 75 and residue distribution indexes Y8-Y9, Y 71 is the mass distribution proportion of water after drying into flue gas, Y 72 is the mass distribution proportion of volatile after pyrolysis into flue gas, Y 73 is the distribution proportion of carbon converted into carbon dioxide into flue gas, Y 74 is the distribution proportion of sulfur converted into sulfur dioxide into flue gas, Y 75 is the distribution proportion of chlorine converted into hydrogen chloride into flue gas; Y8 is the mass distribution proportion of fixed carbon remaining in the slag after combustion, and Y9 is the mass distribution proportion of fly ash component into fly ash after combustion of fixed carbon;

[0034] The energy conversion group indexes include Y 10 ~Y 12 , Y 10 is thermal efficiency, Y 11 is combustion efficiency, and Y 12 is heat loss rate.

[0035] Further, the loss function of step S5 considers the prediction loss and the heat treatment loss, and the specific implementation method includes the following steps:

[0036] S5.1. Constructing a prediction loss based on conversion efficiency prediction loss, product distribution prediction loss and energy conversion prediction loss, the expression is:

[0037]

[0038] Among them, is the conversion efficiency prediction loss; is the product distribution prediction loss; is the energy conversion prediction loss;

[0039]

[0040] Among them, is the mean square error calculation function; is the model predicted conversion efficiency group different index output value; is the actual measured conversion efficiency group different index output value;

[0041]

[0042] wherein, is the model predicted product distribution group different index output value; is the actual measured product distribution group different index output value;

[0043]

[0044] wherein, is the model predicted energy conversion group different index output value; is the actual measured energy conversion group different index output value;

[0045] S5.2. Constructing heat treatment loss based on material conversion constraint, component conversion constraint and heat conversion constraint , the expression is:

[0046]

[0047] wherein, is the material conversion constraint, is the weight corresponding to the material conversion constraint; is the component conversion constraint, is the weight corresponding to the component conversion constraint; is the heat conversion constraint, is the weight corresponding to the heat conversion constraint;

[0048] The material conversion constraint is established as:

[0049]

[0050] wherein, is the volatile matter conversion term; is the fixed carbon distribution term;

[0051] The component conversion constraint is established as:

[0052]

[0053] wherein, is the sulfur element conversion constraint, is the chlorine element conversion constraint;

[0054] The heat conversion constraint is established as:

[0055] ;

[0056] S5.3. Constructing total loss based on predicted loss and heat treatment loss ;

[0057]

[0058] wherein, is the weight corresponding to the predicted loss, is the weight corresponding to the heat treatment loss, which is determined by expert experience.

[0059] Further, the model training in step S7 adopts a back propagation algorithm; in the training process, the model calculates a predicted value through forward propagation, substitutes the predicted value and a true value into a loss function to calculate a loss, and then updates network parameters through back propagation; to prevent overfitting, an early stopping strategy is adopted, and when the loss of a verification set does not decrease for 10 consecutive epochs, the training is stopped; and the output result is restored to an actual physical quantity through inverse normalization.

[0060] Further, step S8 considers the close correlation among material conversion, energy utilization and environmental influence in the system operation process, and comprehensively evaluates the influence of material conversion efficiency on power generation cost, the reagent consumption caused by different material conversion paths, the cascade utilization benefits of primary and secondary energy recovery, the equipment full life cycle cost and the environmental treatment cost.

[0061] Advantages of the present application:

[0062] The cost prediction method based on the solid waste heat treatment neural network model has been designed and optimized for the solid waste heat treatment characteristics in the input parameters, the first hidden layer, the second hidden layer and the output layer, and the scientificity and rationality of the prediction of the conversion efficiency, the product distribution and the energy conversion in the solid waste heat treatment process are realized.

[0063] The cost prediction method based on the solid waste heat treatment neural network model establishes a comprehensive cost evaluation system, which includes five sub-models of the power generation cost under the influence of the conversion efficiency, the reagent cost of the material conversion path, the energy cascade utilization benefit, the equipment full life cycle cost and the environmental cost. The method provides a reliable calculation method for the solid waste heat treatment cost prediction, and can help enterprises to evaluate the treatment cost under different solid waste characteristics and operation conditions in advance, and provide a scientific basis for operation optimization and decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 The flowchart of the cost prediction method based on the solid waste heat treatment neural network model is shown in the drawings.

[0065] Figure 2 Loss curve diagram for the solid waste heat treatment prediction model training process of the present application;

[0066] Figure 3 Comparison chart of predicted value and true value of the solid waste heat treatment prediction model of the present application;

[0067] Figure 4 Total cost calculation result chart under different working conditions of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical scheme and advantages of the present application clearer and more understandable, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application, that is, the described specific embodiments are only a part of the embodiments of the present application, but not all the specific embodiments. The components of the specific embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations, and the present application can also have other embodiments.

[0069] Therefore, the detailed description of the specific embodiments of the present application provided in the drawings below is not intended to limit the scope of the claimed present application, but only represents selected specific embodiments of the present application. Based on the specific embodiments of the present application, all other specific embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0070] In order to further understand the invention content, characteristics and effects of the present application, the following specific embodiments are exemplified, and the drawings are Figure 1 - the drawings Figure 4 The detailed description is as follows:

[0071] Example 1:

[0072] A cost prediction method based on a solid waste heat treatment neural network model, comprising the following steps:

[0073] S1. Determine the input parameters of the input layer of the solid waste heat treatment prediction model based on deep learning, including material characteristic parameters, process operation parameters and process parameters;

[0074] In step S1, the number of nodes of the input layer is determined to be 35, respectively denoted as X1-X 35 ;

[0075] X1~X 14For material characteristic parameters, the corresponding specific parameters are as follows: X1 is moisture content, X2 is ash content, X3 is combustible content, X4 is carbon content, X5 is hydrogen content, X6 is oxygen content, X7 is nitrogen content, X8 is sulfur content, X9 is chlorine content, X 10 is heat value, X 11 is bulk density, X 12 is particle size, X 13 is sand content, X 14 is metal content;

[0076] X 15 ~X 25 For process operation parameters, the corresponding specific parameters are as follows: X 15 is grate speed, X 16 is feed rate, X 17 is primary air volume, X 18 is secondary air volume, X 19 is hearth temperature, X 20 is hearth negative pressure, X 21 is flue gas temperature, X 22 is steam temperature, X 23 is steam pressure, X 24 is steam flow, X 25 is ambient temperature;

[0077] X 26 ~X 35 For process parameters, the corresponding specific parameters are as follows: X 26 is feed moisture content, X 27 is discharge moisture content, X 28 is feed volatile matter, X 29 is discharge volatile matter, X 30 is feed mass flow rate, X 31 is discharge mass flow rate, X 32 is feed heat value, X 33 is discharge heat value, X 34 is fume oxygen concentration, X 35 is ash content.

[0078] Further, among the above parameters, all can be directly collected by an automatic control system. The data is derived from historical data of the solid waste treatment plant. In order to ensure the training effect and prediction accuracy of the deep learning model, it is necessary to normalize the input parameters and output parameters. Normalization processing can eliminate the influence of different dimensions on the model, so that all features are in the same scale range, which helps to speed up the model convergence speed and improve the model performance. At the same time, the normalization processing can also avoid the problem of numerical overflow or underflow in numerical calculation. For the element content indicators X1~X9 in the material characteristic parameters, since they are all mass percentages, they are directly divided by 100 to map to the 0-1 interval; X 10 12 Then linearly map based on the maximum and minimum value range of historical data statistics; X 13 and X 14 are directly divided by 100 as percentages. In the process operation parameters, X 15 and X 16 are mapped based on the rated range of the equipment, X 17 and X 18 are mapped based on the rated range of the blower, X 19 ~ X 25 are all linearly mapped based on the statistical range of historical operation data. In the process parameters, X 26 ~ X 29 are directly divided by 100 as percentages, X 30 , X 31 are mapped based on the design operating condition range, X 32 , X 33 are mapped based on the historical data range, X 34 is mapped based on the theoretical air excess coefficient range, and X 35 is directly divided by 100 as a percentage. Through such normalization processing, all parameters are uniformly mapped to the 0-1 interval, laying a foundation for subsequent training and prediction of the deep learning model.

[0079] S2. Constructing a first hidden layer in the main body layer of the solid waste thermal treatment prediction model based on deep learning;

[0080] Further, step S2 divides the nodes of the first hidden layer into a material characteristic group, a reaction characteristic group and an energy characteristic group. The material characteristic group focuses on the physical and chemical property changes of the material in the thermal treatment process, contains 30 neuron nodes, and the ith neuron node takes a value of 1~30. The reaction characteristic group focuses on describing the degree of progress of various chemical reactions, contains 25 neuron nodes, and the ith neuron node takes a value of 31~55. The energy characteristic group focuses on representing energy conversion and transmission characteristics, contains 25 neuron nodes, and the ith neuron node takes a value of 56~80. ​

[0081] The specific implementation method of step S2 includes the following steps:

[0082] S2.1. Temperature correction and material moisture correction are introduced in the material property group. The temperature correction considers the driving effect of temperature on material conversion rate and reflects the difference in material conversion law in different temperature intervals. The material moisture correction considers the influence of water evaporation process on subsequent conversion. The calculation method of 30 neuron nodes in the material property group is as follows:

[0083]

[0084] wherein, represents the output value of the i1th neuron node in the first hidden layer, i1 takes a value of 1~30; is an activation function, used to introduce nonlinear characteristics; is the weight coefficient of the i1th neuron node in the first hidden layer corresponding to the jth input parameter; is the input parameter, ; is the bias term of the i1th neuron node in the first hidden layer corresponding to the jth input parameter; is a temperature correction coefficient, determined by expert experience, design documents, experimental research, etc. is a moisture correction coefficient, determined by expert experience, design documents, experimental research, etc. is a temperature correction term; is a material moisture correction term;

[0085] S2.2. The mass conversion term is introduced in the reaction property group, which directly reflects the reaction degree of the material and embodies the depth of the reaction. The air excess term is added to represent the sufficiency of the combustion environment and reflect the influence of oxidation reaction conditions on the conversion effect. The calculation method of 25 neuron nodes in the reaction property group is as follows:

[0086]

[0087] wherein, is the output value of the i2th neuron node in the first hidden layer, i2 takes a value of 31~55; is the weight coefficient of the i2th neuron node in the first hidden layer corresponding to the jth input parameter; is the bias term of the i2th neuron node in the first hidden layer corresponding to the jth input parameter; is a mass conversion coefficient, determined by expert experience, design documents, experimental research, etc. is an air excess coefficient, determined by expert experience, design documents, experimental research, etc. is air density, determined by actual measurement; for mass conversion term; for air excess term;

[0088] S2.3. Constructing energy characteristic group to introduce heat value conversion term to directly represent energy conversion effect; adding temperature gradient term to reflect driving force and transfer strength of heat transfer and describe energy distribution in space; 25 neuron nodes in energy characteristic group are calculated as follows:

[0089]

[0090] wherein, is output value of the i3th neuron node in the first hidden layer, i3 takes value of 56-80; is weight coefficient of the jth input parameter and the i3th neuron node in the first hidden layer corresponding to the jth input parameter; is bias term of the i3th neuron node in the first hidden layer corresponding to the jth input parameter; is heat value conversion term; is heat value conversion coefficient, which is determined by expert experience, design file, test research and the like; is temperature gradient term; is temperature gradient coefficient, which can be determined by expert experience, design file, test research and the like.

[0091] S3. Constructing second hidden layer in main body layer of solid waste heat treatment prediction model based on deep learning, the first hidden layer being connected to the second hidden layer;

[0092] Further, step S3 divides nodes of the second hidden layer into drying process group, pyrolysis process group and combustion process group, wherein the drying process group describes influence of drying process on subsequent pyrolysis and combustion, contains 15 neuron nodes, the i4th neuron node taking value of 1-15; the pyrolysis process group describes composition change characteristics of pyrolysis products, contains 20 neuron nodes, the i5th neuron node taking value of 16-35; the combustion process group describes process characteristics of final oxidation stage, contains 15 neuron nodes, the i6th neuron node taking value of 36-50;

[0093] The specific implementation method of step S3 includes the following steps:

[0094] S3.1. Constructing drying process group to represent process characteristics of water removal in solid waste, reflect driving action of temperature on water evaporation and describe influence of drying process on subsequent pyrolysis and combustion; 15 neuron nodes in the drying process group are calculated as follows:

[0095]

[0096] wherein, is the output value of the i4th neuron node of the second hidden layer, i4 takes values from 1 to 15; is the weight coefficient of the i4th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer, =1~80; is the bias term of the i4th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer; is the output value of the kth neuron of the first hidden layer; is the drying process term, is the drying process coefficient, determined by expert experience, design documents, experimental research, etc;

[0097] S3.2. The pyrolysis process group is constructed to reflect the influence of temperature on the volatilization, describe the composition change characteristics of the pyrolysis products, and realize the extraction of the key characteristics of the pyrolysis stage. The calculation method of the 20 neuron nodes in the pyrolysis process group is as follows:

[0098]

[0099] wherein, is the output value of the i5th neuron node of the second hidden layer, i5 takes values from 16 to 35; is the weight coefficient of the i5th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer; is the bias term of the i5th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer; is the pyrolysis process term, is the pyrolysis process coefficient, determined by expert experience, design documents, experimental research, etc;

[0100] S3.3. The combustion process group is constructed to reflect the influence of oxygen concentration on the combustion effect, describe the process characteristics of the final oxidation stage; the calculation method of the 15 neuron nodes in the combustion process group is as follows:

[0101]

[0102] wherein, is the output value of the i6th neuron node of the second hidden layer, i6 takes values from 36 to 50; is the weight coefficient of the i6th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer; is the bias term of the i6th neuron node of the second hidden layer corresponding to the kth neuron of the first hidden layer; is the combustion process term, For the combustion process coefficient, For the reference oxygen concentration, determined by expert experience, design documents, experimental research methods.

[0103] S4. The output layer of the deep learning-based solid waste thermal treatment prediction model is constructed, and the output layer is divided into a conversion efficiency group, a product distribution group and an energy conversion group. The output parameters of the output layer of the deep learning-based solid waste thermal treatment prediction model are determined.

[0104] Further, step S4 divides the output layer into a conversion efficiency group, a product distribution group and an energy conversion group based on the evaluation requirements of the solid waste thermal treatment process. The conversion efficiency group index reflects the integrity and sufficiency of material conversion, the product distribution group index reveals the migration rule of material and environmental impact, and the energy conversion group index embodies the energy utilization level.

[0105] The conversion efficiency group index includes Y1-Y6, Y1 is the moisture conversion rate, Y2 is the volatile conversion rate, Y3 is the fixed carbon conversion rate, Y4 is the carbon conversion rate, Y5 is the sulfur conversion rate, and Y6 is the chlorine conversion rate.

[0106] The product distribution group index includes the material distribution proportion index Y 71 ~Y 75 and the residue distribution index Y8-Y9, Y 71 is the mass distribution proportion of moisture after drying into flue gas, Y 72 is the mass distribution proportion of volatile after pyrolysis into flue gas, Y 73 is the distribution proportion of carbon converted into carbon dioxide into flue gas, Y 74 is the distribution proportion of sulfur converted into sulfur dioxide into flue gas, Y 75 is the distribution proportion of chlorine converted into hydrogen chloride into flue gas; Y8 is the mass distribution proportion of fixed carbon remaining in the slag after combustion, and Y9 is the mass distribution proportion of fly ash component into fly ash after combustion of fixed carbon.

[0107] The energy conversion group index includes Y 10 ~Y 12 , Y 10 is the thermal efficiency, Y 11 is the combustion efficiency, and Y 12 is the heat loss rate.

[0108] The specific implementation method of step S4 includes the following steps:

[0109] S4.1. The calculation method of the output value of different indexes in the conversion efficiency group is as follows:

[0110]

[0111] wherein, s1 is the output value of different indicators in the conversion efficiency group; is the weight coefficient of the output value of different indicators in the conversion efficiency group corresponding to the vth neuron of the second hidden layer; is the bias term of the output value of different indicators in the conversion efficiency group corresponding to the vth neuron of the second hidden layer; is the output value of the vth neuron of the second hidden layer;

[0112] s1=1, v∈{1,2,…,15}; s1=2, v∈{16,17,…,35}; s1=3~6, v∈{36,37,…,50};

[0113] S4.2. The calculation method of the output value of different indicators in the product distribution group is as follows:

[0114]

[0115] wherein, s2 is the output value of different indicators in the product distribution group; is the weight coefficient of the output value of different indicators in the product distribution group corresponding to the vth neuron of the second hidden layer; is the bias term of the output value of different indicators in the product distribution group corresponding to the vth neuron of the second hidden layer;

[0116] s2=71, v∈{1,2,…,15}; s2=72, v∈{16,17,…,35}; s2=73,74,75,8,9, v∈{36,37,…,50};

[0117] S4.3. The calculation method of the output value of different indicators in the energy conversion group is as follows:

[0118]

[0119] wherein, s3 is the output value of different indicators in the energy conversion group; is the weight coefficient of the output value of different indicators in the energy conversion group corresponding to the vth neuron of the second hidden layer; is the bias term of the output value of different indicators in the energy conversion group corresponding to the vth neuron of the second hidden layer;

[0120] s3=10,12, v∈{1,2,…,50}; s3=11, v∈{36,37,…,50}.

[0121] Further, the above data is derived from historical data of a solid waste treatment plant during model training.

[0122] S5. Design the loss function of the solid waste heat treatment prediction model based on deep learning;

[0123] Further, the loss function in step S5 considers the prediction loss and the heat treatment loss, and the specific implementation method includes the following steps:

[0124] S5.1. Construct the prediction loss based on the conversion efficiency prediction loss, the product distribution prediction loss and the energy conversion prediction loss, and the expression is:

[0125]

[0126] wherein, is the conversion efficiency prediction loss; is the product distribution prediction loss; is the energy conversion prediction loss;

[0127]

[0128] wherein, is the mean square error calculation function; is the output value of different indicators in the conversion efficiency group predicted by the model; is the output value of different indicators in the conversion efficiency group actually measured;

[0129]

[0130] wherein, is the output value of different indicators in the product distribution group predicted by the model; is the output value of different indicators in the product distribution group actually measured;

[0131]

[0132] wherein, is the output value of different indicators in the energy conversion group predicted by the model; is the output value of different indicators in the energy conversion group actually measured;

[0133] S5.2. Construct the heat treatment loss based on the material conversion constraint, the component conversion constraint and the heat conversion constraint , and the expression is:

[0134]

[0135] wherein, is the material conversion constraint, is the weight corresponding to the material conversion constraint; is the component conversion constraint, is the weight corresponding to the component conversion constraint; is the heat conversion constraint, is the weight corresponding to the heat conversion constraint;

[0136] Material conversion constraints are established as:

[0137]

[0138] in, is the volatile matter conversion item; Allocate items for fixed carbon;

[0139] The component conversion constraints are established as:

[0140]

[0141] in, For the sulfur element transformation constraints, The conversion constraint for chlorine element;

[0142] The heat conversion constraint is established as:

[0143] ;

[0144] S5.3. Constructing Total Losses Based on Predicted Losses and Heat Treatment Losses ;

[0145]

[0146] in, is the weight corresponding to the prediction loss, is the weight corresponding to the heat treatment loss, determined by expert experience.

[0147] S6. sequentially connect the input layer, main layer, and output layer of the deep learning-based solid waste thermal treatment prediction model to obtain a deep learning-based solid waste thermal treatment prediction model;

[0148] S7. Data is collected from the solid waste treatment plant and automated control system, normalized, and divided into training, validation, and test sets in a ratio of 7:2:1. The deep learning-based solid waste thermal treatment prediction model obtained in step S6 is trained, validated, and tested to obtain a trained deep learning-based solid waste thermal treatment prediction model.

[0149] Furthermore, the model parameters are set as hyperparameters that need to be set manually based on expert experience, including: network structure parameters, the number of neurons in each layer; hyperparameters that need to be set manually during the model training process include: learning rate, batch size, training rounds, and weight coefficients in the loss function; parameters that need to be determined by the model during training: weight coefficients and bias terms in the model.

[0150] Further, the model training in step S7 adopts a back propagation algorithm; during the training process, the model calculates a predicted value through forward propagation, substitutes the predicted value and a true value into a loss function to calculate a loss, and then updates network parameters through back propagation; to prevent overfitting, an early stopping strategy is adopted, and when the loss of a verification set does not decrease for 10 consecutive epochs, the training is stopped; the output result is recovered into an actual physical quantity through inverse normalization.

[0151] S8. After the prediction result of the trained deep learning-based solid waste heat treatment prediction model is inverse normalized, the prediction result of the deep learning-based solid waste heat treatment prediction model with an actual physical quantity is obtained, and a cost prediction method based on the solid waste heat treatment neural network model is constructed.

[0152] Further, step S8 starts from the overall operation characteristics of the solid waste heat treatment system, considers the close correlation among material conversion, energy utilization and environmental impact during system operation, and comprehensively evaluates the influence of material conversion efficiency on power generation cost, the consumption of reagents caused by different material conversion paths, the step utilization benefits of primary and secondary energy recovery, the equipment life cycle cost and the environmental governance cost.

[0153] Further, the specific implementation method of step S8 includes the following steps:

[0154] S8.1. The cost under the influence of conversion efficiency is predicted by establishing a multi-level efficiency correction system, and the expression of the actual power generation cost FD is obtained as follows:

[0155]

[0156] wherein, , , are efficiency correction coefficients related to element conversion, turbine efficiency and combustion temperature deviation, respectively; is the price per kilowatt-hour; is the total amount of electricity required;

[0157]

[0158] wherein, is a carbon conversion influence coefficient, is a sulfur conversion influence coefficient, is a chlorine conversion influence coefficient, which is determined by expert experience, design documents and experimental research methods; , , are standard conversion rates of carbon conversion rate, sulfur conversion rate and Y chlorine conversion rate, respectively, which are determined by expert experience, design documents and experimental research methods.

[0159]

[0160] wherein, is the temperature influence coefficient, is the pressure influence coefficient, determined by expert experience, design documents, experimental research methods; is the design steam temperature, is the design steam pressure, which can be determined by expert experience, design documents, experimental research, etc;

[0161]

[0162] wherein, is the temperature deviation influence coefficient, determined by expert experience, design documents, experimental research, etc; is the optimal combustion temperature related to the process, determined by expert experience, design documents, experimental research, etc;

[0163] The calculation of power generation cost needs to consider the comprehensive influence of material conversion efficiency, steam parameters and combustion temperature. The conversion efficiency of elements such as carbon, sulfur and chlorine directly affects the combustion quality, and then affects the power generation efficiency; the fluctuation of steam temperature and pressure will cause the change of turbine efficiency; the deviation of combustion temperature from the optimal value will reduce the overall thermal efficiency. By establishing a multi-level efficiency correction system, the actual power generation cost can be accurately evaluated;

[0164] S8.2. In the solid waste incineration process, the conversion path of different substances will affect the consumption of reagents, so a reagent consumption model considering multiple factors is established to accurately evaluate the actual operation cost. The calculation of deacidifying agent dosage TS is as follows:

[0165]

[0166] wherein, is the reference deacidifying agent dosage; is the model prediction value, =73、74 and 75; is the corresponding standard value; is the corresponding standard value; is the stoichiometric coefficient, CO2 takes 0.1, SO2 takes 1.0, and HCl takes 1.0; is the reaction activity coefficient, determined by expert experience, design documents, experimental research, etc; is the adjustment coefficient related to the combustion efficiency, is the adjustment coefficient related to the furnace negative pressure, determined by expert experience, design documents, experimental research methods;

[0167] Then the cost PTS of the material conversion path is calculated as follows:

[0168]

[0169] wherein, is the price of deacidification agent, obtained from the market;

[0170] S8.3. Energy utilization in solid waste incineration process includes primary energy recovery and secondary energy recovery. Primary energy is mainly achieved through steam power generation, and its efficiency is affected by thermal efficiency and heat loss. Secondary energy includes flue gas waste heat and cooling system waste heat. By establishing a complete energy recovery system, the overall energy utilization efficiency of the system can be improved.

[0171] The expression of the primary energy recovery amount NY is:

[0172]

[0173] wherein, is the primary energy recovery coefficient, determined by expert experience, design documents, and experimental research methods;

[0174] The expression of the secondary energy recovery amount NE is:

[0175]

[0176] wherein, m3=71, 72, 73, 74, and 75; D m3 is the specific heat capacity of each component, determined from the chemical handbook or experimental research; is the initial temperature, directly obtained from the automatic control system; is the secondary energy recovery coefficient, determined by expert experience, design documents, and experimental research methods;

[0177] The total energy cascade utilization benefit ZN is:

[0178]

[0179] wherein, is the unit price of energy, determined by querying the local market price;

[0180] S8.4. Equipment life is affected by material conversion characteristics, corrosion environment, and thermal stress. Different material conversions will cause different degrees of equipment wear, and acid gas will accelerate equipment corrosion. By establishing a life prediction model considering multiple influences, the full life cycle cost of equipment can be accurately evaluated;

[0181] The equipment predicted life SM is calculated as follows:

[0182]

[0183] wherein, The design life of the equipment is determined by the design specification; The coefficient of wear contribution, The value is 1~6; The basic corrosion coefficient is determined by expert experience; The corrosion contribution coefficient is determined by expert experience, The value is 74 and 75; The standard value corresponding to The standard value corresponding to The standard value corresponding to The standard value corresponding to is determined by expert experience, design documents, experimental research, etc;

[0184] The cost NH of the equipment is calculated as follows:

[0185]

[0186] Among them, The initial investment; The annual maintenance cost is determined according to market conditions; The discount rate is determined according to market conditions; The discounting period;

[0187] S8.5. The environmental cost includes direct treatment cost and indirect environmental impact cost. The direct treatment cost is affected by the amount of pollutants generated and the treatment process, considering the change of treatment efficiency caused by working condition fluctuation; The indirect environmental cost is related to the regional environmental carrying capacity and sensitivity; At the same time, the carbon emission cost as a special environmental cost, considering the influence of carbon trading market and emission reduction policy;

[0188] The direct treatment cost CLz is calculated as follows:

[0189]

[0190] Among them, The value is 71~75, The treatment unit price is determined by market research; The working condition correction coefficient is determined by expert experience, design documents, experimental research;

[0191] The indirect environmental cost CLj is calculated as follows:

[0192]

[0193] Among them, The indirect treatment unit price is determined by market research; The regional sensitivity coefficient is related to the regional environmental quality, which is determined by expert experience, design documents, experimental research;

[0194] The carbon emission cost CBc is calculated as follows:

[0195]

[0196] wherein, is the molecular weight ratio of carbon dioxide to carbon; is the price of carbon, obtained from the market; is the carbon emission reduction contribution rate, determined by investigation;

[0197] The total environmental cost CBh is calculated as follows:

[0198]

[0199] S8.6. Calculate the total operating cost .

[0200] The embodiment proposes a solid waste thermal treatment process characteristic analysis deep learning model construction method. The method is designed and optimized for the characteristics of solid waste thermal treatment in the input parameters, the first hidden layer, the second hidden layer, and the output layer, and realizes the scientificity and rationality of the prediction of the conversion efficiency, product distribution, and energy conversion in the solid waste thermal treatment process.

[0201] The embodiment proposes a solid waste thermal treatment cost prediction method. This solid waste thermal treatment cost prediction method establishes a comprehensive cost evaluation system, including five sub-models of power generation cost under the influence of conversion efficiency, reagent cost of material conversion path, energy cascade utilization benefit, equipment full life cycle cost, and environmental cost. The method provides a reliable calculation method for solid waste thermal treatment cost prediction, which can help enterprises to evaluate the treatment cost under different solid waste characteristics and operating conditions in advance, and provide scientific basis for operation optimization and decision-making.

[0202] It should be noted that the relational terms, such as "first" and "second", and the like, are used solely to distinguish one from another entity or action, without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0203] ​Although the present application has been described with reference to the specific embodiments thereof, it should be understood by those skilled in the art that various changes can be made and equivalents can be substituted for elements thereof without departing from the scope of the present application. In particular, various features and aspects of the present application can be used individually or in any combination depending on the specific application and implementation. Therefore, it is expressly intended that the specific embodiments of the present application both as set forth and including any equivalents thereof should not limit the present application or scope of the claims herein, but rather the overall scope of pertaining solely to the methods and the articles of manufacture specifically recited in the following claims.

Claims

1. A cost prediction method based on a neural network model for solid waste thermal treatment, characterized in that: The steps include: S1. Determine the input parameters of the input layer of the deep learning-based solid waste thermal treatment prediction model, including material characteristic parameters, process operation parameters, and process parameters; S2. Construct the first hidden layer in the main layer of the deep learning-based solid waste thermal treatment prediction model; S3. Constructing a second hidden layer in the main layer of a deep learning-based solid waste thermal treatment prediction model, wherein the first hidden layer is connected to the second hidden layer; S4. Construct an output layer for the deep learning-based solid waste thermal treatment prediction model, divide the output layer into conversion efficiency groups, product distribution groups, and energy conversion groups, and determine output parameters for the output layer of the deep learning-based solid waste thermal treatment prediction model. S5. Design a loss function for a deep learning-based solid waste thermal treatment prediction model. S6. sequentially connect the input layer, main layer, and output layer of the deep learning-based solid waste thermal treatment prediction model to obtain a deep learning-based solid waste thermal treatment prediction model; S7. Data is collected from the solid waste treatment plant and automated control system, normalized, and divided into training, validation, and test sets in a ratio of 7:2:

1. The deep learning-based solid waste thermal treatment prediction model obtained in step S6 is trained, validated, and tested to obtain a trained deep learning-based solid waste thermal treatment prediction model. S8. After denormalizing the prediction results of the trained deep learning-based solid waste thermal treatment prediction model, the prediction results of the deep learning-based solid waste thermal treatment prediction model with actual physical quantities are obtained, and a cost prediction method based on the solid waste thermal treatment neural network model is constructed.

2. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 1 is characterized in that: In step S1, the number of nodes in the input layer is determined to be 35, which are denoted as X1-X 35 ; X1~X 14 The material characteristic parameters are as follows: X1 is the moisture content, X2 is the ash content, X3 is the combustible content, X4 is the carbon content, X5 is the hydrogen content, X6 is the oxygen content, X7 is the nitrogen content, X8 is the sulfur content, X9 is the chlorine content, X 10 is the calorific value, X 11 is the bulk density, X 12 is the particle size, X 13 is the sand content, X 14 is the metal content; X 15 ~X 25 is the process operating parameter, and the corresponding specific parameters are as follows: X 15 is the grate speed, X 16 is the feeding rate, X 17 is the primary air volume, X 18 is the secondary air volume, X 19 is the furnace temperature, X 20 is the furnace negative pressure, X 21 is the flue temperature, X 22 is the steam temperature, X 23 is the steam pressure, X 24 is the steam flow rate, X 25 is the ambient temperature; X 26 ~X 35 is the process parameter, and the corresponding specific parameters are as follows: X 26 is the feed moisture content, X 27 is the moisture content of the discharge material, X 28 is the feed volatile matter, X 29 is the volatile matter of the discharge, X 30 is the feed mass flow rate, X 31 is the discharge mass flow rate, X 32 is the feed calorific value, X 33 is the calorific value of the discharge material, X 34 is the smoke oxygen concentration, X 35 is the ash content.

3. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 2 is characterized in that: Step S2 divides the nodes of the first hidden layer into a material property group, a reaction property group, and an energy property group. The material property group focuses on the changes in the physical and chemical properties of the material during the heat treatment process, and includes 30 neuron nodes, with the value of the i1th neuron node ranging from 1 to 30. The reaction property group focuses on describing the degree of various chemical reactions, and includes 25 neuron nodes, with the value of the i2th neuron node ranging from 31 to 55. The energy property group focuses on characterizing energy conversion and transfer characteristics, and includes 25 neuron nodes, with the value of the i3th neuron node ranging from 56 to 80. The specific implementation method of step S2 includes the following steps: S2.

1. Introduce temperature correction and material moisture correction into the material property group. The temperature correction considers the driving effect of temperature on the material conversion rate and reflects the differences in material conversion patterns within different temperature ranges. The material moisture correction considers the impact of water evaporation on subsequent conversion. The calculation method for the 30 neuron nodes in the material property group is as follows: in, Represents the output value of the i1th neuron node in the first hidden layer, where i1 ranges from 1 to 30; is an activation function used to introduce nonlinear features; is the weight coefficient of the i1th neuron node in the first hidden layer corresponding to the jth input parameter; is the input parameter, ; is the bias term of the i1th neuron node in the first hidden layer corresponding to the jth input parameter; is the temperature correction factor, which is determined by expert experience, design documents, experimental research, etc. is the moisture correction factor, which is determined by expert experience, design documents, experimental research, etc. is the temperature correction term; is the material moisture correction item; S2.

2. The reaction characteristic group is constructed by introducing a mass conversion term to directly reflect the degree of material reaction and the depth of the reaction. An excess air term is added to characterize the adequacy of the combustion environment and reflect the impact of oxidation reaction conditions on the conversion effect. The 25 neuron nodes in the reaction characteristic group are calculated as follows: in, is the output value of the i2th neuron node in the first hidden layer, and i2 ranges from 31 to 55; is the weight coefficient of the i2th neuron node in the first hidden layer corresponding to the jth input parameter; is the bias term of the i2th neuron node in the first hidden layer corresponding to the jth input parameter; is the mass conversion coefficient, which is determined by expert experience, design documents, experimental research, etc. is the excess air coefficient, which is determined by expert experience, design documents, experimental research, etc. is the air density, determined by actual measurement; is the quality conversion item; is the excess air term; S2.

3. Construct an energy property group by introducing a calorific value conversion term to directly characterize the energy conversion effect. A temperature gradient term is added to reflect the driving force and transfer intensity of heat transfer and describe the spatial distribution of energy. The 25 neuron nodes in the energy property group are calculated as follows: in, is the output value of the i3th neuron node in the first hidden layer, and the value of i3 ranges from 56 to 80; is the weight coefficient of the jth input parameter and the corresponding i3th neuron node in the first hidden layer; is the bias term of the i3th neuron node in the first hidden layer corresponding to the jth input parameter; is the calorific value conversion item; is the calorific value conversion coefficient, which is determined by expert experience, design documents, experimental research, etc. is the temperature gradient term; is the temperature gradient coefficient, which can be determined by expert experience, design documents, experimental research, etc.

4. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 3 is characterized in that: Step S3 divides the nodes of the second hidden layer into a drying process group, a pyrolysis process group, and a combustion process group. The drying process group describes the effect of the drying process on subsequent pyrolysis and combustion, and includes 15 neuron nodes, with the i4th neuron node taking a value of 1 to 15. The pyrolysis process group describes the composition change characteristics of the pyrolysis products, and includes 20 neuron nodes, with the i5th neuron node taking a value of 16 to 35. The combustion process group describes the process characteristics of the final oxidation stage, and includes 15 neuron nodes, with the i6th neuron node taking a value of 36 to 50. The specific implementation method of step S3 includes the following steps: S3.

1. Construct a drying process group to characterize the process of water removal from solid waste, reflect the driving effect of temperature on water evaporation, and describe the impact of the drying process on subsequent pyrolysis and combustion. The 15 neuron nodes in the drying process group are calculated as follows: in, is the output value of the i4th neuron node in the second hidden layer, and i4 ranges from 1 to 15; is the weight coefficient of the i4th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer, =1~80; is the bias term of the i4th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer; is the output value of the kth neuron in the first hidden layer; is the drying process item, is the drying process coefficient, which is determined by expert experience, design documents, experimental research, etc. S3.

2. Construct a pyrolysis process group. This group uses the kinetic characteristics of organic matter pyrolysis to reflect the influence of temperature on volatile analysis, describe the compositional changes of pyrolysis products, and extract key features of the pyrolysis stage. The 20 neuron nodes in the pyrolysis process group are calculated as follows: in, is the output value of the i5th neuron node in the second hidden layer, and i5 ranges from 16 to 35; is the weight coefficient of the i5th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer; is the bias term of the i5th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer; is the pyrolysis process term, is the pyrolysis process coefficient, which is determined by expert experience, design documents, experimental research, etc. S3.

3. Construct a combustion process group to characterize the oxidation of fixed carbon and volatile matter, reflect the effect of oxygen concentration on combustion, and describe the process characteristics of the final oxidation stage. The calculation method for the 15 neuron nodes in the combustion process group is as follows: in, is the output value of the i6th neuron node in the second hidden layer, and the value of i6 ranges from 36 to 50; is the weight coefficient of the i6th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer; is the bias term of the i6th neuron node in the second hidden layer corresponding to the kth neuron in the first hidden layer; is the combustion process term, is the combustion process coefficient, It is the reference oxygen concentration, determined by expert experience, design documents, and experimental research methods.

5. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 4 is characterized in that: Step S4 divides the output layer into conversion efficiency group, product distribution group, and energy conversion group based on the evaluation requirements of the solid waste thermal treatment process; the conversion efficiency group indicators reflect the completeness and adequacy of material conversion, the product distribution group indicators reveal the migration patterns and environmental impacts of materials, and the energy conversion group indicators reflect the level of energy utilization; The conversion efficiency group indicators include Y1~Y6, where Y1 is water conversion rate, Y2 is volatile matter conversion rate, Y3 is fixed carbon conversion rate, Y4 is carbon conversion rate, Y5 is sulfur conversion rate, and Y6 is chlorine conversion rate; Product distribution group indicators include material distribution ratio indicator Y 71 ~Y 75 and residue allocation index Y8~Y9, Y 71 is the mass distribution ratio of water entering the flue gas after drying, Y 72 Y is the mass distribution ratio of volatile matter entering the flue gas after pyrolysis, 73 Y is the distribution ratio of carbon into flue gas after being converted into carbon dioxide, 74 Y is the distribution ratio of sulfur into flue gas after being converted into sulfur dioxide, 75 Y is the distribution ratio of chlorine into the flue gas after conversion to hydrogen chloride; Y8 is the mass distribution ratio of the fixed carbon remaining in the slag after combustion; Y9 is the mass distribution ratio of the fly ash components into the fly ash after combustion of fixed carbon; Energy conversion group indicators include Y 10 ~Y 12 , Y 10 is the thermal efficiency, Y 11 is the combustion efficiency, Y 12 is the heat loss rate; The specific implementation method of step S4 includes the following steps: S4.

1. The calculation method for constructing the output values ​​of different indicators in the conversion efficiency group is as follows: in, are the output values ​​of different indicators in the conversion efficiency group, and s1 are the different indicators in the conversion efficiency group; is the weight coefficient of the output values ​​of different indicators in the conversion efficiency group corresponding to the vth neuron in the second hidden layer; is the bias term for the output values ​​of different indicators in the conversion efficiency group corresponding to the vth neuron in the second hidden layer; is the output value of the vth neuron in the second hidden layer; When s1=1, v∈{1,2,…,15}; when s1=2, v∈{16,17,…,35}; when s1=3~6, v∈{36,37,…,50}; S4.

2. The calculation method for the output values ​​of different indicators in the product distribution group is as follows: in, are the output values ​​of different indicators in the product distribution group, and s2 are the different indicators in the product distribution group; is the weight coefficient of the output values ​​of different indicators in the product distribution group corresponding to the vth neuron in the second hidden layer; is the bias term for the output values ​​of different indicators in the product distribution group corresponding to the vth neuron in the second hidden layer; When s2=71, v∈{1,2,…,15}; when s2=72, v∈{16,17,…,35}; when s2=73,74,75,8,9, v∈{36,37,…,50}; S4.

3. The calculation method for constructing the output values ​​of different indicators in the energy conversion group is as follows: in, are the output values ​​of different indicators in the energy conversion group, and s3 are the different indicators in the energy conversion group; is the weight coefficient of the output value of different indicators in the energy conversion group corresponding to the vth neuron in the second hidden layer; is the bias term for the output values ​​of different indicators in the energy conversion group corresponding to the vth neuron in the second hidden layer; When s3=10,12, v∈{1,2,…,50}; when s3=11, v∈{36,37,…,50}.

6. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 5 is characterized in that: The loss function of step S5 takes into account the prediction loss and the heat treatment loss. The specific implementation method includes the following steps: S5.

1. Construct the predicted loss based on the conversion efficiency predicted loss, product distribution predicted loss, and energy conversion predicted loss. The expression is: in, Predict losses for conversion efficiency; Predict losses for product distribution; Energy conversion prediction losses; in, is the mean square error calculation function; Output values ​​for different indicators in the conversion efficiency group predicted by the model; Output values ​​for different indicators in the actual measured conversion efficiency group; in, Output values ​​for different indicators in the product distribution group predicted by the model; Output values ​​for different indicators in the actual measured product distribution group; in, Output values ​​of different indicators in the energy conversion group predicted by the model; Output values ​​of different indicators in the energy conversion group actually measured; S5.

2. Constructing heat treatment losses based on material conversion constraints, component conversion constraints, and heat conversion constraints , the expression is: in, is the material conversion constraint, The weight corresponding to the material conversion constraint; is the component transformation constraint, is the weight corresponding to the component transformation constraint; is the heat conversion constraint, is the weight corresponding to the heat conversion constraint; Material conversion constraints are established as: in, is the volatile matter conversion item; Allocate items for fixed carbon; The component conversion constraints are established as: in, For the sulfur element transformation constraints, The conversion constraint for chlorine element; The heat conversion constraint is established as: ； S5.

3. Constructing Total Losses Based on Predicted Losses and Heat Treatment Losses ; in, is the weight corresponding to the prediction loss, is the weight corresponding to the heat treatment loss, determined by expert experience.

7. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 6 is characterized in that: In step S7, the model training adopts the back-propagation algorithm. During the training process, the model calculates the predicted value through forward propagation, substitutes the predicted value and the true value into the loss function to calculate the loss, and then updates the network parameters through back-propagation. To prevent overfitting, an early stopping strategy is adopted, and training is stopped when the validation set loss does not decrease for 10 consecutive epochs. The output result is restored to the actual physical quantity through denormalization.

8. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 7 is characterized in that: Step S8 starts from the overall operating characteristics of the solid waste thermal treatment system, takes into account the close relationship between material conversion, energy utilization and environmental impact during the operation of the system, and comprehensively evaluates the impact of material conversion efficiency on power generation costs, reagent consumption caused by different material conversion pathways, cascade utilization benefits of primary and secondary energy recovery, equipment full life cycle costs, and environmental governance costs.

9. The cost prediction method based on the neural network model of solid waste thermal treatment according to claim 7, characterized in that: The specific implementation method of step S8 includes the following steps: S8.

1. By establishing a multi-level efficiency correction system to predict the cost under the influence of conversion efficiency, the expression for the actual power generation cost FD is obtained as follows: in, 、 、 are the efficiency correction factors related to element conversion, turbine efficiency, and combustion temperature deviation, respectively; is the price per kilowatt-hour; is the total amount of electricity required; in, is the carbon conversion influence coefficient, is the sulfur conversion influence coefficient, is the chlorine conversion influence coefficient, which is determined by expert experience, design documents, and experimental research methods; 、 、 These are the standard conversion rates for carbon conversion, sulfur conversion, and Y-chlorine conversion, determined by expert experience, design documents, experimental studies, etc.; in, is the temperature influence coefficient, is the pressure influence coefficient, which is determined by expert experience, design documents, and experimental research methods; is the design steam temperature, The design steam pressure can be determined by expert experience, design documents, experimental research, etc. in, is the temperature deviation influence coefficient, which is determined by expert experience, design documents, experimental research, etc. The optimum combustion temperature related to the process is determined by expert experience, design documents, experimental research, etc. S8.

2. During solid waste incineration, the transformation pathways of different substances affect reagent consumption. A multi-factor reagent consumption model is developed to accurately assess actual operating costs. The deacidification agent dosage, TS, is calculated as follows: in, is the base deacidification agent dosage; is the model prediction value, =73, 74 and 75; For Corresponding standard value; is the stoichiometric coefficient, CO2 is taken as 0.1, SO2 is taken as 1.0, and HCl is taken as 1.0; is the reaction activity coefficient, which is determined by expert experience, design documents, experimental research, etc. is the adjustment coefficient related to combustion efficiency, It is the adjustment coefficient related to the furnace negative pressure, which is determined by expert experience, design documents, and experimental research methods; The cost PTS of the material transformation path is calculated as follows: in, is the price of deacidification agent, obtained from the market; S8.

3. Energy utilization during solid waste incineration includes primary and secondary energy recovery. Primary energy is primarily generated through steam power generation, the efficiency of which is affected by thermal efficiency and heat loss. Secondary energy includes waste heat from flue gases and waste heat from the cooling system. By establishing a complete energy recovery system, the overall energy utilization efficiency of the system can be improved. The expression of primary energy recovery NY is: in, is the primary energy recovery coefficient, which is determined by expert experience, design documents, and experimental research methods; The expression of secondary energy recovery NE is: Where m3=71, 72, 73, 74 and 75; D m3 is the specific heat capacity of each component, which can be determined from a chemical handbook or experimental research; is the initial temperature, obtained directly from the automatic control system; is the secondary energy recovery coefficient, which is determined by expert experience, design documents, and experimental research methods; The total energy cascade utilization benefit ZN is: in, The unit price of energy is determined by querying the local market price; S8.

4. Equipment life is affected by a combination of material conversion characteristics, corrosive environment, and thermal stresses. The conversion of different substances will cause varying degrees of equipment wear, and acidic gases will accelerate equipment corrosion. By establishing a life prediction model that considers multiple impacts, the full life cycle cost of the equipment can be accurately assessed. The predicted equipment life SM is calculated as follows: in, It is the design life of the equipment, determined by the design specifications; is the wear contribution coefficient, The value ranges from 1 to 6; is the basic corrosion coefficient, determined by expert experience; is the corrosion contribution coefficient, determined by expert experience, The values ​​are 74 and 75; For The corresponding standard value, For The corresponding standard values ​​are determined by expert experience, design documents, experimental research, etc.; The cost of the equipment NH is calculated as follows: in, is the initial investment amount; It is the annual maintenance fee, determined according to market conditions; is the discount rate, determined based on market conditions; The converted years; S8.

5. Environmental costs include direct treatment costs and indirect environmental impact costs. Direct treatment costs are affected by the amount of pollutants generated and the treatment process, taking into account variations in treatment efficiency due to fluctuations in operating conditions. Indirect environmental costs are related to the regional environmental carrying capacity and sensitivity. Furthermore, carbon emission costs, as a special environmental cost, take into account the impact of carbon trading markets and emission reduction policies. The direct processing cost CLz is calculated as follows: in, The value ranges from 71 to 75. To process the unit price, it is determined by market research; is the working condition correction factor, which is determined by expert experience, design documents, and experimental research methods; The indirect environmental cost CLj is calculated as follows: in, To indirectly process the unit price, it is determined by market research; is the regional sensitivity coefficient, which is related to the regional environmental quality and is determined by expert experience, design documents, and experimental research methods; The carbon emission cost CBc is calculated as follows: in, is the molecular weight ratio of carbon dioxide to carbon; is the price of carbon, obtained from the market; The contribution rate to carbon emission reduction is determined by the survey results; The total environmental cost CBh is calculated as follows: ； S8.

6. Calculate total operating costs .

Images