Method and device for predicting thermal weight loss characteristic of fuel

Abstract

The invention provides a method and device for predicting the thermal weight loss characteristic of fuel, and the method comprises the steps: obtaining to-be-predicted fuel with known physical composition, and determining the mass ratio of organic urban solid waste single components in the fuel and a first standard thermal weight loss characteristic; obtaining a first element and a second standard thermal weight loss characteristic corresponding to the organic urban solid waste single component according to the element correspondence table; based on the mass ratio, the first standard thermal weight loss characteristic, the element and the second standard thermal weight loss characteristic of the organic urban solid waste single component, obtaining an element characterization coefficient and a total element characterization coefficient of the organic urban solid waste single component; and taking the primitive characterization coefficient, the total primitive characterization coefficient and the environmental condition as input, and predicting the thermal weight loss characteristic of the to-be-predicted fuel under the given environmental condition by using the thermal weight loss characteristic prediction model. According to the method and the device, homogeneous replacement of the fuel containing infinite single components is realized through the finite elements, and the method and the device can be suitable for the fuel mixed by the single components of any number and variety.

Description

Technical Field

[0001] This application relates to the field of data prediction technology, and in particular to a method and apparatus for predicting the thermogravimetric properties of fuel. Background Technology

[0002] With the increasing demand for global energy structure transformation and carbon emission reduction, the efficient and clean utilization of complex fuels (such as organic solid waste, biomass, industrial organic waste, and mixed plastics) has become a research hotspot. Complex fuels are usually composed of a mixture of various organic and inorganic components, and their composition is highly variable. Their physicochemical properties are significantly affected by factors such as source, storage conditions, and pretreatment methods. For example, municipal solid waste may contain biomass (such as kitchen waste, paper, and wood), plastics, textiles, and inert ash; industrial waste may involve high-calorific-value components such as rubber, sludge, and waste solvents. This complexity makes it difficult to fully characterize their thermochemical conversion (such as combustion, pyrolysis, and gasification) behavior using traditional experimental methods. In particular, when the fuel mixing ratio changes, the interactions between different components (such as synergistic or inhibitory effects) will significantly affect the overall conversion efficiency and product distribution. This synergistic thermal conversion effect is directly reflected in the difference in thermogravimetric characteristics before and after mixing. The complex interactions between different fuels have a significant impact on both the regulation of the thermal conversion process and the normal operation of the conversion equipment itself. Therefore, developing a convenient, versatile, and highly accurate method for analyzing the thermogravimetric characteristics of fuels is of great significance for optimizing waste energy recovery processes, reducing processing costs, and further promoting the industrial application of complex fuel energy utilization technologies.

[0003] Currently, research on the thermochemical conversion of complex fuels mainly relies on experimental methods such as thermogravimetric analysis (TGA), summarizing patterns through experimental data of single components or specific mixing ratios. Studies have shown that different fuel components (such as cellulosic biomass, plastics, and rubber) exhibit significantly different weight loss characteristics during combustion or pyrolysis. For complex mixed fuel components, the combustion or pyrolysis process is not a simple linear superposition of the thermogravimetric losses of individual components, but rather a nonlinear coupling caused by the interaction of volatiles, heat and mass transfer effects, etc. In addition, reaction conditions (such as heating rate and atmosphere) also significantly affect the intensity of the interaction. Obtaining synergistic thermal conversion characteristics experimentally by simply enumerating all possible combinations of fuel types is undoubtedly extremely difficult and inefficient. Machine learning methods can capture the patterns of synergistic thermal conversion in complex fuels based on limited experimental data and are currently widely used in predicting the thermogravimetric characteristics and product distribution of complex fuels. Although existing research has accumulated a large amount of data, due to the differences in the physicochemical properties of the aforementioned multiple factors, the data results are isolated and even contradictory. Therefore, traditional predictive models based on limited experimental data are difficult to generalize to real-world complex and variable fuel systems. Summary of the Invention

[0004] In view of this, this application provides a method and apparatus for predicting the thermogravimetric properties of fuel to solve at least one of the aforementioned problems.

[0005] To achieve the above objectives, this application adopts the following approach:

[0006] According to a first aspect of this application, a method for predicting the thermogravimetric properties of a fuel is provided. The method includes: obtaining a fuel to be predicted with a known physical composition; determining the mass percentage of an organic municipal solid waste component in the fuel to be predicted and its first standard thermogravimetric property; obtaining a first primitive corresponding to the organic municipal solid waste component and its second standard thermogravimetric property according to a preset primitive correspondence table; obtaining the primitive characterization coefficient and the total primitive characterization coefficient of the organic municipal solid waste component based on the mass percentage of the organic municipal solid waste component, the first standard thermogravimetric property, the first primitive, and the second standard thermogravimetric property, using a primitive characterization algorithm; and using the primitive characterization coefficient, the total primitive characterization coefficient, and the environmental conditions under which weight loss occurs as inputs, predicting the thermogravimetric properties of the fuel to be predicted under given environmental conditions using a thermogravimetric property prediction model.

[0007] As an embodiment of this application, the method described above, which uses an elementary characterization algorithm to obtain the elementary characterization coefficients of individual components of the organic municipal solid waste and the total elementary characterization coefficients, includes: determining the elementary characterization coefficients of individual components of the organic municipal solid waste using the elementary characterization process function of the following formula:

[0008] ;

[0009] Where A is a one-dimensional vector composed of the first standard thermogravimetric characteristics, B is a one-dimensional vector obtained by linearly superimposing the second standard thermogravimetric characteristics according to the primitive characterization coefficients, n is the number of data points in the one-dimensional vector, an and bn represent the values ​​corresponding to the nth element of vectors A and B, respectively, X is a matrix composed of the second standard thermogravimetric characteristics of all primitives, K is a one-dimensional vector composed of the primitive characterization coefficients corresponding to the single component of organic urban solid waste, ki is the primitive characterization coefficient of the i-th primitive of the single component of organic urban solid waste, and m is the number of primitives.

[0010] Based on the mass proportion of the individual components of the organic urban solid waste and their element characterization coefficients, a weighted sum is performed to obtain the total element characterization coefficient.

[0011] As an embodiment of this application, the above method further includes: selecting single-component experimental samples of organic municipal solid waste covering various fuel types based on the actual physical composition and chemical properties of the fuel to be tested; obtaining the third standard thermogravimetric characteristics of the single-component experimental samples of organic municipal solid waste; classifying the types based on the third standard thermogravimetric characteristics using principal component analysis and hierarchical clustering analysis; and determining the corresponding second primitives through chemical composition analysis; obtaining the fourth standard thermogravimetric characteristics of the second primitives in a preset experimental environment using a thermogravimetric analyzer; and establishing the preset primitive correspondence table based on the determined second primitives, their corresponding single-component organic municipal solid waste samples, and the fourth standard thermogravimetric characteristics.

[0012] As an embodiment of this application, the above method further includes: for the determined second primitive, obtaining the fifth standard thermogravimetric characteristic of each second primitive under given environmental conditions; obtaining the sixth standard thermogravimetric characteristic of a proportional mixture of two primitives under the given environmental conditions, and selecting a combination of primitives with a synergistic thermal conversion effect that meets the set requirements; obtaining the seventh standard thermogravimetric characteristic of a variable-proportion mixture of the primitive combination under the given environmental conditions; and training the thermogravimetric characteristic prediction model using a machine learning method based on the fifth standard thermogravimetric characteristic, the sixth standard thermogravimetric characteristic, and the seventh standard thermogravimetric characteristic, so that the thermogravimetric characteristic prediction model can output the thermogravimetric characteristic of the fuel to be predicted under given environmental conditions based on the input primitive characterization coefficients, the total primitive characterization coefficients, and the environmental conditions under which weight loss occurs.

[0013] As an embodiment of this application, the criterion for determining the synergistic thermal conversion effect that meets the set requirements in the above method is that the R² of the actual thermogravimetric characteristics of the proportionally mixed basic elements and the fitted thermogravimetric characteristics after linearly superimposing the thermogravimetric characteristics of the two basic elements in the same proportion is ≤0.96.

[0014] As an embodiment of this application, the experimental environment preset in the above method is as follows: the mass of the experimental sample is 5-10 mg, the atmosphere is nitrogen gas at 100 ml / min, the temperature range is from 30°C to 1000°C, and the heating rate is 10°C / min.

[0015] As an embodiment of this application, the environmental conditions given in the above method are: constant temperature of 800°C and atmosphere of nitrogen at 100 ml / min.

[0016] According to a second aspect of this application, a fuel thermogravimetric characteristic prediction device is provided. The device includes: a first data determination unit, configured to acquire a fuel to be predicted with known physical composition, and determine the mass percentage of organic municipal solid waste single component and a first standard thermogravimetric characteristic of the fuel to be predicted; a second data determination unit, configured to acquire a first primitive corresponding to the organic municipal solid waste single component and a second standard thermogravimetric characteristic of the first primitive according to a preset primitive correspondence table; a characterization coefficient determination unit, configured to obtain the primitive characterization coefficient and total primitive characterization coefficient of the organic municipal solid waste single component using a primitive characterization algorithm based on the mass percentage of the organic municipal solid waste single component, the first standard thermogravimetric characteristic, the first primitive, and the second standard thermogravimetric characteristic; and a thermogravimetric prediction unit, configured to use the primitive characterization coefficient, the total primitive characterization coefficient, and the environmental conditions in which weight loss occurs as inputs, and use a thermogravimetric characteristic prediction model to predict the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions.

[0017] As an embodiment of this application, the aforementioned characterization coefficient determination unit is specifically used to: determine the basic characterization coefficients of the single component of the organic municipal solid waste using the basic characterization process function of the following formula:

[0018] ;

[0019] Where A is a one-dimensional vector composed of the first standard thermogravimetric characteristics, B is a one-dimensional vector obtained by linearly superimposing the second standard thermogravimetric characteristics according to the primitive characterization coefficients, n is the number of data points in the one-dimensional vector, an and bn represent the values ​​corresponding to the nth element of vectors A and B, respectively, X is a matrix composed of the second standard thermogravimetric characteristics of all primitives, K is a one-dimensional vector composed of the primitive characterization coefficients corresponding to the single component of organic urban solid waste, ki is the primitive characterization coefficient of the i-th primitive of the single component of organic urban solid waste, and m is the number of primitives.

[0020] Based on the mass proportion of the individual components of the organic urban solid waste and their element characterization coefficients, a weighted sum is performed to obtain the total element characterization coefficient.

[0021] As an embodiment of this application, the above-mentioned apparatus further includes: an experimental sample determination unit, used to select single-component experimental samples of organic municipal solid waste covering fuel types according to the actual physical composition and chemical properties of the fuel to be tested; a corresponding basic element determination unit, used to obtain the third standard thermogravimetric characteristics of the single-component experimental samples of organic municipal solid waste, classify them into categories based on the third standard thermogravimetric characteristics using principal component analysis and hierarchical clustering analysis, and determine the corresponding second basic element through chemical composition analysis; a third data determination unit, used to obtain the fourth standard thermogravimetric characteristics of the second basic element in a preset experimental environment using a thermogravimetric analyzer; and a correspondence table establishment unit, used to establish the preset basic element correspondence table based on the determined second basic element, its corresponding single-component organic municipal solid waste, and the fourth standard thermogravimetric characteristics.

[0022] As an embodiment of this application, the above-mentioned apparatus further includes: a fourth data determination unit, configured to acquire, for the determined second basic element, a fifth standard thermogravimetric characteristic of each second basic element under given environmental conditions; a basic element combination selection unit, configured to acquire, for the sixth standard thermogravimetric characteristic of a proportional mixture of two basic elements under given environmental conditions, and select a basic element combination having a synergistic thermal conversion effect that meets set requirements; a fifth data determination unit, configured to acquire, for the seventh standard thermogravimetric characteristic of a variable-proportion mixture of the basic element combination under given environmental conditions; and a model training unit, configured to train the thermogravimetric characteristic prediction model using machine learning methods based on the fifth standard thermogravimetric characteristic, the sixth standard thermogravimetric characteristic, and the seventh standard thermogravimetric characteristic, so that the thermogravimetric characteristic prediction model can output the thermogravimetric characteristic of the fuel to be predicted under given environmental conditions based on the input basic element characterization coefficients, the total basic element characterization coefficients, and the environmental conditions under which weight loss occurs.

[0023] As an embodiment of this application, the criterion for determining the synergistic thermal conversion effect that meets the set requirements is that the R² of the actual thermogravimetric characteristics of the proportionally mixed basic elements and the fitted thermogravimetric characteristics of the two basic elements after linearly superimposing them in a proportional weighted manner is ≤0.96.

[0024] As an embodiment of this application, the above-mentioned preset experimental environment is as follows: the mass of the experimental sample is 5-10 mg, the atmosphere is nitrogen gas at 100 ml / min, the temperature range is from 30°C to 1000°C, and the heating rate is 10°C / min.

[0025] As an embodiment of this application, the above-mentioned environmental conditions are: constant temperature of 800°C and atmosphere of nitrogen at 100 ml / min.

[0026] According to a third aspect of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0027] According to a fourth aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0028] As can be seen from the above technical solutions, the fuel thermogravimetric characteristic prediction method and apparatus provided in this application, with its elementary characterization system, can effectively address the problem of complex fuels with diverse types and varying physicochemical properties. By using a finite number of elementary elements, it achieves homogenization substitution for complex fuels containing an infinite number of single components, giving the established prediction model good universality and applicability to complex fuel mixtures of any number and type of single components. The combination of the elementary system proposed in this application with machine learning methods can effectively capture the synergistic thermal conversion effect between complex fuels, achieving high accuracy in predicting the thermogravimetric characteristics of complex fuels, outperforming traditional regression models. Finally, the elementary system of this application is independent of the conditions of complex fuel thermal conversion, making this method applicable to the prediction of thermogravimetric characteristics under different operating conditions (such as heating rate and atmosphere). Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0030] Figure 1 This is a flowchart illustrating a method for predicting the thermogravimetric characteristics of fuel provided in an embodiment of this application;

[0031] Figure 2 This is a schematic diagram illustrating the process of establishing the primitive correspondence table provided in the embodiments of this application;

[0032] Figure 3 This is a diagram showing the results of fuel difference analysis and clustering classification provided in the embodiments of this application;

[0033] Figure 4 This is a schematic diagram of fuel classification and corresponding basic components provided in the embodiments of this application;

[0034] Figure 5 This is a schematic diagram of the training process of the thermogravimetric characteristic prediction model provided in the embodiments of this application;

[0035] Figure 6This is a schematic diagram illustrating the determination results of the basic combination of fuels with strong synergistic thermal conversion effect provided in the embodiments of this application;

[0036] Figure 7 This is a schematic diagram of the evaluation results of the fuel thermogravimetric characteristic prediction model provided in the embodiments of this application;

[0037] Figure 8 This is a schematic diagram illustrating the application effect evaluation of the fuel thermogravimetric characteristic prediction method provided in the embodiments of this application;

[0038] Figure 9 This is a schematic diagram of the structure of a fuel thermogravimetric characteristics prediction device provided in an embodiment of this application;

[0039] Figure 10 This is a schematic block diagram of the system configuration of the electronic device provided in the embodiments of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of this application are used to explain this application, but are not intended to limit this application.

[0041] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include plural forms. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0042] Furthermore, it should be noted that the use of terms such as "first" and "second" to define related concepts is merely for the purpose of distinguishing the corresponding concepts. Unless otherwise stated, these terms have no special meaning and therefore should not be construed as limiting the scope of protection of this application. In addition, although the terminology used in this application is selected from commonly known and used terms, some terms mentioned in this application's specification may have been chosen by the applicant according to his or her judgment, and their detailed meanings are explained in the relevant sections of this description. Moreover, this application should be understood not only through the actual terms used, but also through the meaning implied by each term.

[0043] like Figure 1 The diagram shown is a flowchart illustrating a method for predicting the thermogravimetric characteristics of fuel according to an embodiment of this application. Here, the fuel refers to the complex fuels mentioned in the background art. The method includes the following steps:

[0044] Step S101: Obtain the fuel to be predicted with known physical composition, and determine the mass percentage of organic urban solid waste single component and the first standard thermogravimetric characteristics in the fuel to be predicted.

[0045] This step aims to collect basic information about the fuel to be predicted. First, the fuel with a known physical composition is obtained; the fuel to be predicted should be organic municipal solid waste (such as a mixture of kitchen waste, paper, and plastics). Then, the mass percentage of each organic municipal solid waste component is determined. Simultaneously, the first standard thermogravimetric characteristics of these components are obtained, i.e., thermogravimetric data obtained through standard experiments or database queries.

[0046] Step S102: Obtain the first basic element corresponding to the single component of the organic urban solid waste and the second standard thermogravimetric characteristics of the first basic element according to the preset basic element correspondence table.

[0047] This step utilizes a pre-defined elementary component mapping table to map the individual components of organic municipal solid waste to the elementary component system, achieving homogeneous fuel substitution. Elementary components are a limited number of representative components (such as cellulose, lignin, PE, etc.) determined based on principal component analysis and chemical composition analysis, used to simplify the prediction of an unlimited number of individual components.

[0048] The pre-defined elementary component correspondence table can be established based on previous experiments. For each organic municipal solid waste component, its corresponding first elementary component is obtained according to the correspondence table (e.g., kitchen waste corresponds to starch, hemicellulose, cellulose, and lignin). Then, the second standard thermogravimetric characteristics of these first elementary components are obtained according to the correspondence table.

[0049] Step S103: Based on the mass ratio of the single component of the organic urban solid waste, the first standard thermogravimetric characteristics, and the first and second standard thermogravimetric characteristics, the elementary characterization coefficients and the total elementary characterization coefficients of the single component of the organic urban solid waste are obtained using the elementary characterization algorithm.

[0050] In the elementary characterization algorithm, the coefficient vector K is a set of coefficients calculated for each fuel component. These coefficients represent the weights by which the component can be linearly fitted by a finite number of elementary elements (e.g., starch, hemicellulose, cellulose, lignin, PE, PP, PS, PVC, PET, etc.). These coefficients ensure that the fitted thermogravimetric characteristics have minimal error compared to the actual standard thermogravimetric characteristics, thus transforming an infinite number of fuel components into a finite element characterization.

[0051] This primitive characterization coefficient can address the challenges of diverse fuel types and varying physicochemical properties, enabling homogeneous substitution. It also provides input features for subsequent thermogravimetric characteristic prediction models and supports capturing synergistic thermal conversion effects between individual components. This coefficient makes the corresponding thermogravimetric characteristic prediction model universal and highly accurate, capable of handling different operating conditions (such as heating rate and atmosphere) without enumerating all combinations.

[0052] Step S104: Using the primitive characterization coefficient, the total primitive characterization coefficient, and the environmental conditions for weight loss as inputs, the thermogravimetric characteristic prediction model is used to predict the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions.

[0053] The primitive characterization coefficients and total primitive characterization coefficients from step S103 are used as the main input features, combined with the weightlessness environmental conditions (such as heating rate, atmosphere, temperature, etc., for example, constant temperature at 800℃, nitrogen atmosphere) as auxiliary input features. Thermogravimetric characteristic prediction model (trained based on machine learning methods, such as gradient boosting tree, random forest or deep neural network) is used to predict the thermogravimetric characteristics of fuel under given conditions (such as weightlessness curve, rate, etc.).

[0054] As can be seen from the above technical solutions, the fuel thermogravimetric characteristic prediction method provided in this application, with its elementary characterization system, can effectively address the problem of diverse fuel types and varying physicochemical properties. By using a finite number of elementary elements, it achieves homogenization substitution for fuels containing an infinite number of single components, giving the established prediction model good universality and applicability to fuel mixtures of any number and type of single components. The combination of the elementary system proposed in this application with machine learning methods can effectively capture the synergistic thermal conversion effect between fuels, achieving high accuracy in predicting fuel thermogravimetric characteristics, superior to traditional regression models. Finally, the elementary system of this application is independent of the conditions of fuel thermal conversion, making this method applicable to the prediction of thermogravimetric characteristics under different operating conditions (such as heating rate and atmosphere).

[0055] In one embodiment of this application, the step S103 above, which uses an elementary characterization algorithm to obtain the elementary characterization coefficients of the single components and the total elementary characterization coefficients of the organic municipal solid waste, includes:

[0056] The elementary characterization coefficients of the single components of the organic municipal solid waste are determined using the elementary characterization process function of the following formula:

[0057] ;

[0058] Wherein, A is a one-dimensional vector composed of the first standard thermogravimetric characteristics, B is a one-dimensional vector obtained by linearly superimposing the second standard thermogravimetric characteristics according to the primitive characterization coefficients, n is the number of data points in the one-dimensional vector, an and bn represent the values ​​corresponding to the nth elements of vectors A and B, respectively, X is a matrix composed of the second standard thermogravimetric characteristics of all first primitives, K is a one-dimensional vector composed of the primitive characterization coefficients corresponding to the single components of organic urban solid waste, ki is the primitive characterization coefficient of the i-th first primitive of the single component of organic urban solid waste, and m is the number of first primitives.

[0059] Based on the mass proportion of the individual components of the organic urban solid waste and their element characterization coefficients, a weighted sum is performed to obtain the total element characterization coefficient.

[0060] As described above, the optimization objective of this embodiment is to maximize the characterization accuracy RA(A,B), which means minimizing the mean absolute error between the actual vector A and the fitted vector B. In this embodiment, data points can be extracted from all standard thermogravimetric data in steps of 1℃, for example, a total of 970 data points. Therefore, both vectors A and B are one-dimensional vectors containing 970 data points. After determining the primitive composition corresponding to a single component, an optimization algorithm (such as finite field optimization) is applied to solve for vector K to maximize RA. The optimized K is the primitive characterization coefficient of that single component.

[0061] The total primitive characterization coefficients mentioned above can be obtained by the following formula:

[0062] ;

[0063] Where K tot w is the total primitive characterization coefficient. i Let K be the mass percentage of the i-th type of organic urban solid waste. i Let be the elementary characterization coefficient of the i-th organic urban solid waste single component.

[0064] The advantage of the above-mentioned primitive characterization algorithm is that it can represent an infinite number of single components through finite primitives, and has high universality and accuracy.

[0065] In another embodiment of this application, such as Figure 2 As shown, the above method also includes the process of establishing a primitive correspondence table, that is, the above method also includes:

[0066] Step S201: Based on the actual physical composition and chemical properties of the fuel to be tested, select single-component experimental samples of organic urban solid waste covering various fuel types.

[0067] Based on the actual physical composition (such as biomass, plastics, and textiles in municipal solid waste) and chemical properties (such as high-calorific-value components and volatile matter content) of the fuels to be tested, experimental samples that can cover various fuel types are selected. The number of samples should be ≥15 to ensure the accuracy and universality of the basic system. For example, this embodiment selects 24 typical organic municipal solid waste single components, including kitchen waste (such as rice and grapefruit peel), wood (such as poplar branches and leaves), paper (such as printing paper), textiles, and plastics (such as PE and PP).

[0068] These samples are used for subsequent clustering and primitive determination, avoiding inefficient experiments that enumerate all possible combinations, and ensuring sample representativeness to address differences in fuel physicochemical properties.

[0069] Step S202: Obtain the third standard thermogravimetric characteristics of the single-component experimental sample of organic urban solid waste. Based on the third standard thermogravimetric characteristics, classify the types by principal component analysis and hierarchical cluster analysis, and determine the corresponding second elementary unit by chemical composition analysis.

[0070] Thermogravimetric analysis (TGA) was performed on selected single-component experimental samples of organic municipal solid waste to obtain the third-standard thermogravimetric characteristics of each component. This can be achieved by querying existing standard thermogravimetric databases or through experiments using a thermogravimetric analyzer.

[0071] Based on the third standard thermogravimetric characteristics, principal component analysis (PCA) was used to extract key features for preliminary dimensionality reduction; then, hierarchical clustering analysis methods (such as Euclidean distance) were used for category classification. For example, Figure 3 The clustering results for 24 samples are shown.

[0072] By analyzing chemical composition (such as elemental analysis or component decomposition), the corresponding elementary unit (secondary elementary unit) for each category is determined, and the results can be entered into... Figure 4 As shown. Figure 4 In this study, kitchen waste corresponds to four basic components: starch, hemicellulose, cellulose, and lignin; wood-based solid waste corresponds to three basic components: hemicellulose, cellulose, and lignin; and textile solid waste corresponds to four basic components: hemicellulose, cellulose, lignin, and PET. This achieves a homogeneous substitution of an infinite number of single components by a finite number of basic components.

[0073] Step S203: Obtain the fourth standard thermogravimetric characteristics of the second element in a preset experimental environment using a thermogravimetric analyzer.

[0074] In this embodiment, the preset experimental environment is as follows: the sample mass is 5-10 mg, the atmosphere is nitrogen gas at a flow rate of 100 ml / min, the temperature range is from 30°C to 1000°C, and the heating rate is 10°C / min.

[0075] For the second primitive determined in step S202 (such as...) Figure 4 Thermogravimetric experiments were conducted on the nine basic elements of the fuel, and weight loss curves and characteristic data (such as weight loss rate and temperature range) were recorded. These data are independent of specific fuel thermal conversion conditions and have universal applicability.

[0076] Step S204: Based on the determined second basic unit and its corresponding organic urban solid waste single component and the fourth standard thermogravimetric characteristics, establish the preset basic unit correspondence table.

[0077] Based on the classification in step S202, the second basic unit and its correspondence with the single components of organic municipal solid waste, and combined with the fourth standard thermogravimetric characteristics of the second basic unit, a correspondence table is established. The table includes the single component category, the corresponding basic unit list, and the thermogravimetric data of the basic unit.

[0078] The establishment of this primitive correspondence table makes the method applicable to thermogravimetric prediction under different operating conditions (such as heating rate and atmosphere) without the need for repeated experiments. For subsequent applications of the established table, only the table needs to be referenced for prediction.

[0079] exist Figure 2 Based on the corresponding embodiments, the method described in this embodiment further includes a training process for a thermogravimetric characteristic prediction model, i.e., as follows: Figure 5 As shown, the method in this embodiment further includes the following steps:

[0080] Step S501: For the determined second primitive, obtain the fifth standard thermogravimetric property of each second primitive under given environmental conditions.

[0081] This step is the starting point for data preparation for model training. For the second primitive determined in step S202 (such as 9 primitives: starch, hemicellulose, cellulose, lignin, PE, PP, PS, PVC, PET), obtain its thermogravimetric data under given environmental conditions.

[0082] Based on the previously established primitive correspondence table ( Figure 4 The second primitive is selected. These primitives are obtained through principal component analysis, hierarchical clustering, and chemical composition analysis, and are used to achieve homogeneous substitution of complex fuels.

[0083] Experiments were conducted using a thermogravimetric analyzer (TGA) under given environmental conditions, and the thermogravimetric characteristics of each unit were recorded. The given environmental conditions were: a constant temperature of 800℃ and a nitrogen atmosphere of 100 ml / min.

[0084] Step S502: Obtain the sixth standard thermogravimetric properties of a mixture of two elementary components in equal proportions under the given environmental conditions, and select the combination of elementary components that has a synergistic thermal conversion effect that meets the set requirements.

[0085] For each mixture of two basic components in equal proportions, thermogravimetric analysis (TGA) was used to obtain the thermogravimetric characteristics under the same given environmental conditions (i.e., constant temperature at 800℃, nitrogen gas at 100 ml / min). Data included weight loss curves and rates. The coefficient of determination (R²) was calculated for the fitting characteristics of the actual mixture TGA and the TGA of the two individual components linearly superimposed in equal proportions. If R² ≤ 0.96, it was determined to have a synergistic thermal conversion effect that met the set requirements (i.e., a strong synergistic effect). For example, Figure 6 This shows the elementary combinations with strong synergistic effects in organic municipal solid waste, where asterisks and circles represent strong synergistic effects (such as PET with cellulose, PS with hemicellulose, etc.).

[0086] Identifying the primary combinations with significant interactions can avoid the errors of simple linear superposition and ensure that the prediction model can handle the nonlinear coupling of complex fuels.

[0087] Step S503: Obtain the seventh standard thermogravimetric properties of the elementary combination under the given environmental conditions for variable-proportion mixing.

[0088] For the primitive combination with strong synergistic effect selected in step S502, variable-proportion mixing experiments (mixing different weight ratios) are conducted under the same given environmental conditions (i.e., constant temperature of 800℃ and nitrogen atmosphere), and the thermogravimetric characteristics are recorded using a thermogravimetric analyzer. These experiments cover multiple proportions to capture the impact of proportion changes on the synergistic effect. For example, combining single-primary-value data and proportionally mixed data to form a comprehensive dataset can enrich the training data and simulate the variable composition of real, complex fuels.

[0089] Step S504: Based on the fifth standard thermogravimetric characteristic, the sixth standard thermogravimetric characteristic, and the seventh standard thermogravimetric characteristic, the thermogravimetric characteristic prediction model is trained using machine learning methods, so that the thermogravimetric characteristic prediction model can output the thermogravimetric characteristic of the fuel to be predicted under given environmental conditions based on the input primitive characterization coefficients, the total primitive characterization coefficients, and the environmental conditions in which weight loss occurs.

[0090] The training datasets are the fifth standard thermogravimetric characteristic (single primitive) from step S501, the sixth standard thermogravimetric characteristic (uniformly mixed) from step S502, and the seventh standard thermogravimetric characteristic (variablely mixed) from step S503. The data includes primitive characterization coefficients, total primitive characterization coefficients, and environmental conditions (such as heating rate and atmosphere) as inputs, and thermogravimetric characteristics (such as weight loss curves) as outputs.

[0091] In this embodiment, methods including but not limited to gradient boosting trees, random forests, and deep neural networks can be used to train the model. This embodiment uses gradient boosting trees and neural network models to build prediction models respectively, and compares them with multiple quadratic regression. The comparison results are as follows: Figure 7 As shown, the results indicate that the neural network model has the highest R² (close to 0.995) and the lowest RMSE on both the training and test sets, demonstrating the best ability to capture synergistic effects.

[0092] It should be noted that the innovation of this embodiment lies in the way the input data of the prediction model is obtained. Therefore, the specific method of model training will not be described in detail in this embodiment, and existing model training methods can be referred to.

[0093] The trained model can output the thermogravimetric characteristics of complex fuels based on the input primitive characterization coefficients, total primitive characterization coefficients, and weightlessness environmental conditions. For the trained model, subsequent predictions only need to be performed according to steps S101-S104 above. The verification experiment results sampled in this embodiment and the prediction results obtained by the prediction method proposed in this embodiment are as follows: Figure 8 As shown.

[0094] As can be seen from the above technical solutions, the fuel thermogravimetric characteristic prediction method provided in this application, with its elementary characterization system, can effectively address the problem of complex fuels with diverse types and varying physicochemical properties. By using a finite number of elementary elements, it achieves homogenization substitution for complex fuels containing an infinite number of single components, giving the established prediction model good universality and applicability to complex fuel mixtures of any number and type of single components. The combination of the elementary system proposed in this application with machine learning methods can effectively capture the synergistic thermal conversion effect between complex fuels, achieving high accuracy in predicting the thermogravimetric characteristics of complex fuels, outperforming traditional regression models. Finally, the elementary system of this application is independent of the conditions of complex fuel thermal conversion, making this method applicable to the prediction of thermogravimetric characteristics under different operating conditions (such as heating rate and atmosphere).

[0095] like Figure 9 The diagram shown is a schematic representation of a fuel thermogravimetric characteristic prediction device according to an embodiment of this application. The device includes: a first data determination unit 910, a second data determination unit 920, a characterization coefficient determination unit 930, and a thermogravimetric prediction unit 940, which are connected sequentially.

[0096] The first data determination unit 910 is used to acquire the fuel to be predicted with known physical composition, and to determine the mass percentage of organic urban solid waste single component and the first standard thermogravimetric characteristics in the fuel to be predicted.

[0097] The second data determination unit 920 is used to obtain the first basic element corresponding to the single component of the organic urban solid waste and the second standard thermogravimetric characteristics of the first basic element according to the preset basic element correspondence table.

[0098] The characterization coefficient determination unit 930 is used to obtain the element characterization coefficients and total element characterization coefficients of the organic urban solid waste single component based on the mass ratio of the single component, the first standard thermogravimetric characteristics, the first element and the second standard thermogravimetric characteristics, using the element characterization algorithm.

[0099] Thermogravimetric prediction unit 940 is used to take the basic element characterization coefficient, the total basic element characterization coefficient and the environmental conditions in which weight loss occurs as inputs, and use the thermogravimetric characteristic prediction model to predict the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions.

[0100] In one embodiment of this application, the characterization coefficient determination unit 930 is specifically used to: determine the basic characterization coefficients of the single component of the organic municipal solid waste using the basic characterization process function of the following formula:

[0101] ;

[0102] Where A is a one-dimensional vector composed of the first standard thermogravimetric characteristics, B is a one-dimensional vector obtained by linearly superimposing the second standard thermogravimetric characteristics according to the primitive characterization coefficients, n is the number of data points in the one-dimensional vector, an and bn represent the values ​​corresponding to the nth elements of vectors A and B, respectively, X is a matrix composed of the second standard thermogravimetric characteristics of all first primitives, K is a one-dimensional vector composed of the primitive characterization coefficients corresponding to the single components of organic urban solid waste, ki is the primitive characterization coefficient of the i-th first primitive of the single component of organic urban solid waste, and m is the number of first primitives.

[0103] Based on the mass proportion of the individual components of the organic urban solid waste and their element characterization coefficients, a weighted sum is performed to obtain the total element characterization coefficient.

[0104] In one embodiment of this application, the above-described apparatus further includes:

[0105] The experimental sample determination unit is used to select single-component experimental samples of organic urban solid waste covering complex fuel types based on the actual physical composition and chemical properties of the fuel to be tested.

[0106] The corresponding primitive determination unit is used to obtain the third standard thermogravimetric characteristics of the single-component experimental sample of organic urban solid waste, classify the types based on the third standard thermogravimetric characteristics by principal component analysis and hierarchical cluster analysis, and determine the corresponding second primitive by chemical composition analysis.

[0107] The third data determination unit is used to obtain the fourth standard thermogravimetric characteristics of the second element in a preset experimental environment using a thermogravimetric analyzer.

[0108] The correspondence table establishment unit is used to establish the preset correspondence table of basic elements based on the determined second basic element and its corresponding organic urban solid waste single component and the fourth standard thermogravimetric characteristics.

[0109] In one embodiment of this application, the above-described apparatus further includes:

[0110] The fourth data determination unit is used to obtain the fifth standard thermogravimetric characteristics of each second element under given environmental conditions for the determined second element;

[0111] The elementary component combination selection unit is used to obtain the sixth standard thermogravimetric characteristics of a mixture of two elementary components in equal proportion under the given environmental conditions, and select the elementary component combination that has a synergistic thermal conversion effect that meets the set requirements.

[0112] The fifth data determination unit is used to obtain the seventh standard thermogravimetric characteristics of the variable-proportion mixing of the elementary components under the given environmental conditions;

[0113] The model training unit is used to train the thermogravimetric characteristic prediction model based on the fifth standard thermogravimetric characteristic, the sixth standard thermogravimetric characteristic, and the seventh standard thermogravimetric characteristic using machine learning methods. This enables the thermogravimetric characteristic prediction model to output the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions, based on the input primitive characterization coefficients, the total primitive characterization coefficients, and the environmental conditions under which weight loss occurs.

[0114] In one embodiment of this application, the criterion for determining the synergistic thermal conversion effect that meets the set requirements is that the R² of the actual thermogravimetric characteristics of the proportionally mixed basic elements and the fitted thermogravimetric characteristics of the two basic elements after linearly superimposing them in a proportional weighted manner is ≤0.96.

[0115] In one embodiment of this application, the above-mentioned preset experimental environment is as follows: the mass of the experimental sample is 5-10 mg, the atmosphere is nitrogen gas at 100 ml / min, the temperature range is from 30°C to 1000°C, and the heating rate is 10°C / min.

[0116] In one embodiment of this application, the above-mentioned environmental conditions are: a constant temperature of 800°C and an atmosphere of nitrogen at a flow rate of 100 ml / min.

[0117] For detailed descriptions of the above-mentioned units and modules, please refer to the corresponding descriptions in the foregoing method embodiments, which will not be repeated here.

[0118] As can be seen from the above technical solutions, the fuel thermogravimetric characteristic prediction device provided in this application, with its basic characterization system, can effectively address the problem of complex fuels with diverse types and varying physicochemical properties. By using a finite number of basic elements, it achieves homogenization substitution for complex fuels containing an infinite number of single components, giving the established prediction model good universality and applicability to complex fuel mixtures of any number and type of single components. The combination of the basic system proposed in this application with machine learning methods can effectively capture the synergistic thermal conversion effect between complex fuels, achieving high accuracy in predicting the thermogravimetric characteristics of complex fuels, outperforming traditional regression models. Finally, the basic system of this application is independent of the conditions of complex fuel thermal conversion, making this method applicable to the prediction of thermogravimetric characteristics under different operating conditions (such as heating rate and atmosphere).

[0119] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method.

[0120] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0121] like Figure 10 As shown, the electronic device 600 may also include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 10 All components shown; in addition, the electronic device 600 may also include Figure 10 For components not shown, please refer to existing technologies.

[0122] like Figure 10 As shown, the central processing unit 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The central processing unit 100 receives inputs and controls the operation of various components of the electronic device 600.

[0123] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0124] Input unit 120 provides input to central processing unit 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0125] The memory 140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142 for storing application programs and function programs or processes for executing the operation of the electronic device 600 via the central processing unit 100.

[0126] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various drivers for the electronic device for communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0127] The communication module 110 is a transmitter / receiver that transmits and receives signals via the antenna 111. The communication module 110 (transmitter / receiver) is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0128] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module 110 (transmitter / receiver) is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby enabling typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to a central processing unit 100, enabling on-device recording via the microphone 132 and on-device playback of stored audio via the speaker 131.

[0129] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0131] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] This application uses specific embodiments to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting the thermogravimetric properties of fuel, characterized in that, The method includes: Obtain the fuel to be predicted with known physical composition, and determine the mass percentage of organic urban solid waste single component and the first standard thermogravimetric characteristics of the fuel to be predicted. According to the preset elementary correspondence table, the first elementary element corresponding to the single component of the organic urban solid waste and the second standard thermogravimetric characteristics of the first elementary element are obtained. Based on the mass percentage of the single component of the organic urban solid waste, the first standard thermogravimetric characteristics, and the first and second standard thermogravimetric characteristics, the element characterization coefficients and total element characterization coefficients of the single component of the organic urban solid waste are obtained. Using the primitive characterization coefficients, the total primitive characterization coefficients, and the environmental conditions under which weight loss occurs as inputs, the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions are predicted using a thermogravimetric characteristic prediction model.

2. The method for predicting the thermogravimetric characteristics of fuel as described in claim 1, characterized in that, The process of obtaining the individual element characterization coefficients and total element characterization coefficients of the single component of the organic municipal solid waste includes: The elementary characterization coefficients of the single components of the organic municipal solid waste are determined using the elementary characterization process function of the following formula: ； Where A is a one-dimensional vector composed of the first standard thermogravimetric characteristics, B is a one-dimensional vector obtained by linearly superimposing the second standard thermogravimetric characteristics according to the primitive characterization coefficients, n is the number of data points in the one-dimensional vector, an and bn represent the values ​​corresponding to the nth elements of vectors A and B, respectively, X is a matrix composed of the second standard thermogravimetric characteristics of all first primitives, K is a one-dimensional vector composed of the primitive characterization coefficients corresponding to the single components of organic urban solid waste, ki is the primitive characterization coefficient of the i-th first primitive of the single component of organic urban solid waste, and m is the number of first primitives. Based on the mass proportion of the individual components of the organic urban solid waste and their element characterization coefficients, a weighted sum is performed to obtain the total element characterization coefficient.

3. The method for predicting the thermogravimetric characteristics of fuel as described in claim 1, characterized in that, The method further includes: Based on the actual physical composition and chemical properties of the fuels to be tested, single-component experimental samples of organic urban solid waste covering various fuel types were selected. The third standard thermogravimetric characteristics of the single-component experimental samples of organic urban solid waste were obtained, and the types were classified based on the third standard thermogravimetric characteristics. The corresponding second elementary elements were determined by chemical composition analysis. The fourth standard thermogravimetric characteristics of the second element were obtained using a thermogravimetric analyzer in a preset experimental environment. Based on the determined second basic unit and its corresponding organic urban solid waste single component and the fourth standard thermogravimetric characteristics, the preset basic unit correspondence table is established.

4. The method for predicting the thermogravimetric characteristics of fuel as described in claim 3, characterized in that, The method further includes: For a given second primitive, obtain the fifth standard thermogravimetric property of each second primitive under given environmental conditions; Obtain the sixth standard thermogravimetric properties of a mixture of two elementary elements in equal proportions under the given environmental conditions, and select the combination of elementary elements that has a synergistic thermal conversion effect that meets the set requirements; Obtain the seventh standard thermogravimetric properties of the variable-proportion mixture of the elementary components under the given environmental conditions; The thermogravimetric characteristic prediction model is trained based on the fifth standard thermogravimetric characteristic, the sixth standard thermogravimetric characteristic, and the seventh standard thermogravimetric characteristic, so that the thermogravimetric characteristic prediction model can output the thermogravimetric characteristic of the fuel to be predicted under given environmental conditions based on the input primitive characterization coefficients, the total primitive characterization coefficients, and the environmental conditions in which weight loss occurs.

5. The method for predicting the thermogravimetric characteristics of fuel as described in claim 4, characterized in that, The criterion for determining the synergistic thermal conversion effect that meets the set requirements is that the R² of the actual thermogravimetric characteristics of the proportionally mixed basic elements and the fitted thermogravimetric characteristics of the two basic elements after linearly superimposing them in a proportional weighted manner is ≤0.

96.

6. The method for predicting the thermogravimetric characteristics of fuel as described in claim 3, characterized in that, The preset experimental environment is as follows: the sample mass is 5-10 mg, the atmosphere is nitrogen at 100 ml / min, the temperature range is from 30℃ to 1000℃, and the heating rate is 10℃ / min.

7. The method for predicting the thermogravimetric characteristics of fuel as described in claim 4, characterized in that, The given environmental conditions are: constant temperature of 800℃ and nitrogen atmosphere of 100ml / min.

8. A device for predicting the thermogravimetric characteristics of fuel, characterized in that, The device includes: The first data determination unit is used to acquire the fuel to be predicted with known physical composition, and to determine the mass percentage of organic urban solid waste single component and the first standard thermogravimetric characteristics in the fuel to be predicted. The second data determination unit is used to obtain the first basic element corresponding to the single component of the organic urban solid waste and the second standard thermogravimetric characteristics of the first basic element according to the preset basic element correspondence table. The characterization coefficient determination unit is used to obtain the element characterization coefficient and the total element characterization coefficient of the organic urban solid waste single component based on the mass ratio of the single component, the first standard thermogravimetric characteristics, the first element and the second standard thermogravimetric characteristics, and the element characterization algorithm. Thermogravimetric prediction unit is used to take the basic element characterization coefficient, the total basic element characterization coefficient and the environmental conditions in which weight loss occurs as inputs, and use the thermogravimetric characteristic prediction model to predict the thermogravimetric characteristics of the fuel to be predicted under given environmental conditions.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images