Optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm

Abstract

The invention relates to an optimal process technology evaluation method for a biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm. The method comprises the following steps: collecting reaction data in an anaerobic fermentation-hydrothermal carbonization coupling reaction process; wherein the reaction data comprises biogas yield, free ammonia nitrogen content of biogas slurry and biochar yield; based on the reaction data, evaluating the anaerobic fermentation-hydrothermal carbonization coupling reaction process by using a whole-process comprehensive evaluation index; wherein the whole-process comprehensive evaluation indexes comprise fertilizer replacement, energy conversion and biochar carbon sequestration. According to the method, the whole coupling process and intermediate products thereof can be simulated, comprehensive indexes for evaluating the whole process can be constructed, and the optimal time point location of the coupling reaction can be evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of solid waste resource utilization, and in particular to an optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm. Background Art

[0002] Biomass energy utilization can be categorized into two types: biotechnology and thermochemical technology. While biotechnology primarily focuses on anaerobic fermentation, thermochemical technologies encompass a wider range, with hydrothermal carbonization being a representative example. As research into biomass energy utilization continues to deepen, traditional mainstream technologies have exposed some insurmountable challenges. For example, anaerobic fermentation suffers from long cycles, low conversion efficiency, and insufficient utilization of organic components, leading to direct discharge and environmental risks. Hydrothermal carbonization also faces limitations such as high energy consumption and slow reaction speed for high-dimensional carbon feedstocks. Current research suggests that coupling biotechnology with thermochemical technology can effectively circumvent these issues. For example, coupling anaerobic fermentation with hydrothermal carbonization can improve production efficiency, reduce reaction energy consumption, and mitigate environmental risks by incorporating byproducts (sludge and biogas liquid) from the anaerobic fermentation reaction into hydrothermal carbonization. However, controlling the reaction rate of anaerobic fermentation and optimizing the coupling design remain key challenges. Taking straw rich in lignocellulose as an example, how to moderately deconstruct the dense supramolecular structure in lignocellulose so that the hydrothermal carbonization process can be carried out in a controllable and orderly manner is a difficult point in the research. The key to solving this difficult problem lies in how to construct a comprehensive evaluation index for the process. Therefore, based on the above, the present invention proposes a comprehensive evaluation index of the anaerobic fermentation-hydrothermal carbonization coupling model based on machine learning, simulates the entire coupling process and its intermediate products, constructs a comprehensive index for evaluating the entire process, and evaluates the optimal time point of the coupling reaction.

[0003] A literature review revealed that no such indicator has yet been established. This is due to two factors: 1. The technology of coupling anaerobic fermentation with hydrothermal carbonization is relatively new, and research on this technology is relatively limited; 2. The coupled anaerobic fermentation and hydrothermal carbonization process involves complex material and energy flows, making it difficult to develop a comprehensive evaluation indicator for this process.

[0004] Coupling anaerobic fermentation with hydrothermal carbonization is considered a novel technology for improving biomass energy utilization. However, the complex material and energy flow variations in the coupling process make it difficult to determine the optimal coupling process technology evaluation method based on the characteristics of the biomass feedstock. Summary of the Invention

[0005] The purpose of the present invention is to propose an optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm to solve the problems existing in the above-mentioned prior art. The present invention is based on a machine learning algorithm to predict the direction of material flow and energy flow in the coupled reaction of anaerobic fermentation and hydrothermal carbonization, and proposes a comprehensive evaluation index based on carbon emission reduction to evaluate the optimal process technology of the coupled reaction process.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for evaluating the optimal process technology of biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm, including:

[0008] Collecting reaction data during the anaerobic fermentation-hydrothermal carbonization coupling reaction process; wherein the reaction data includes: biogas production, free ammonia nitrogen content in biogas slurry, and biochar production;

[0009] Based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using comprehensive evaluation indicators of the entire process; wherein the comprehensive evaluation indicators of the entire process include: fertilizer substitution, energy conversion, and biochar carbon sequestration.

[0010] Optionally, the method for collecting reaction data during the anaerobic fermentation-hydrothermal carbonization coupled reaction process includes: using a machine learning algorithm.

[0011] Optionally, based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using a comprehensive evaluation index of the entire process, including:

[0012] Based on the reaction data, a fertilizer substitution index, an energy conversion index, and a biochar carbon sequestration index are obtained respectively;

[0013] Based on the material substitution index, energy conversion index and biochar carbon sequestration index, the comprehensive evaluation index of the whole process is obtained; wherein, the higher the value of the comprehensive evaluation index of the whole process, the better the coupling time point; when the values of the comprehensive evaluation index of the whole process are the same, the lower the change rate of the comprehensive evaluation index of the whole process, the better the coupling time point.

[0014] Optionally, obtain fertilizer alternative indicators including:

[0015] Based on the free ammonia nitrogen content in the biogas slurry at a certain point in anaerobic fermentation and the ammonia nitrogen content per unit volume of industrial nitrogen fertilizer, the volume of industrial fertilizer that can be replaced by biogas slurry is obtained;

[0016] Based on the phosphorus content of the biochar produced by the hydrothermal carbonization reaction and the phosphorus content per unit volume of industrial phosphate fertilizer, the volume of industrial fertilizer that can be replaced by biochar is obtained;

[0017] The fertilizer substitution index is obtained based on the volume of industrial fertilizer that can be replaced by biogas slurry, the volume of industrial fertilizer that can be replaced by biochar, and the CO2 emissions generated per unit volume of industrial nitrogen fertilizer.

[0018] Optionally, the fertilizer substitution index is:

[0019]

[0020] Among them, X IN Refers to the content of free ammonia nitrogen in biogas slurry at a certain moment of anaerobic fermentation; C IN Refers to the content of ammonia nitrogen in unit volume of industrial nitrogen fertilizer; X c Refers to the phosphorus content of biochar produced by hydrothermal carbonization reaction; C FP Refers to the phosphorus content per unit volume of industrial phosphate fertilizer; T FCO2 Refers to the CO2 emissions generated by producing unit volume of industrial nitrogen fertilizer.

[0021] Optionally, obtaining the energy conversion index includes:

[0022] Based on the calorific value of biogas generated during anaerobic fermentation when completely burned and the calorific value of natural gas per cubic meter when completely burned, the volume of industrial natural gas replaced by biogas is obtained;

[0023] An energy conversion index is obtained based on the volume of industrial natural gas replaced by the biogas and the amount of carbon dioxide emitted per cubic meter of natural gas.

[0024] Optionally, the energy conversion index is:

[0025]

[0026] Among them, Q AD Refers to the calorific value of biogas generated during anaerobic fermentation when it is completely burned, Q gas It refers to the calorific value of natural gas per cubic meter when it is completely burned, T CO2 Refers to the amount of carbon dioxide emitted per cubic meter of natural gas produced.

[0027] Optionally, obtaining biochar carbon sequestration indicators includes:

[0028] The biochar carbon sequestration index is obtained based on the mass of biochar generated during the hydrothermal carbonization reaction.

[0029] Optionally, the biochar carbon sequestration index is:

[0030] CS=3.6X C

[0031] Among them, X c Refers to the mass of biochar generated during the hydrothermal carbonization reaction.

[0032] The beneficial effects of the present invention are:

[0033] The present invention first uses a machine learning algorithm to collect reaction data from the anaerobic fermentation-hydrothermal carbonization coupling reaction process; then, based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupling reaction process is evaluated using a comprehensive evaluation index for the entire process. The present invention proposes a comprehensive evaluation index for the anaerobic fermentation-hydrothermal carbonization coupling model based on machine learning, simulates the entire coupling process and its intermediate products, constructs a comprehensive index for evaluating the entire process, and evaluates the optimal time point of the coupling reaction. Based on this method, it can reduce reaction energy consumption, reduce process operating costs, and improve process production efficiency in actual application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 This is a schematic diagram of the effect of anaerobic fermentation simulating methane production according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of the change of anaerobic fermentation residue with fermentation time according to an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of how biochar production changes with fermentation time according to an embodiment of the present invention;

[0038] Figure 4 Schematic diagram of carbon emission reduction changes using the anaerobic fermentation-hydrothermal carbonization coupling technology according to an embodiment of the present invention; A. FE, GS, and CS values; B. FGC value and its rate of change;

[0039] Figure 5 Schematic diagram of the process flow of an optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] like Figure 5 As shown, this embodiment proposes an optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm, including:

[0043] Collecting reaction data during the anaerobic fermentation-hydrothermal carbonization coupling reaction process; wherein the reaction data includes: biogas production, free ammonia nitrogen content in biogas slurry, and biochar production;

[0044] Based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using comprehensive evaluation indicators of the entire process; wherein the comprehensive evaluation indicators of the entire process include: fertilizer substitution, energy conversion, and biochar carbon sequestration.

[0045] Furthermore, the method for collecting reaction data during the anaerobic fermentation-hydrothermal carbonization coupling reaction process includes: using a machine learning algorithm.

[0046] Specifically, this example utilizes a machine learning algorithm to accurately simulate the intermediate products of the coupled process. Based on carbon emission reduction values, the entire anaerobic fermentation-hydrothermal carbonization coupled process is evaluated from three perspectives: energy output, fertilizer production, and CO2 capture. This results in an indicator. The anaerobic fermentation-hydrothermal carbonization coupled process is simulated using a machine learning algorithm, predicting key intermediate products of the coupled process. The algorithm selected is Random Forest, executed in Python, and PyCharm is selected as the executor.

[0047] In the machine learning algorithm, the model uses the raw material element content (wt.%), anaerobic fermentation / hydrothermal carbonization reaction temperature (℃), anaerobic fermentation reactor size (ml), and hydrothermal carbonization reactor size (ml) as model input items, and predicts the coupling model products based on three model algorithms: artificial neural network, support vector machine, and random forest.

[0048] Furthermore, based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using comprehensive evaluation indicators of the entire process, including:

[0049] Based on the reaction data, a fertilizer substitution index, an energy conversion index, and a biochar carbon sequestration index are obtained respectively;

[0050] Based on the material substitution index, energy conversion index and biochar carbon sequestration index, the comprehensive evaluation index of the whole process is obtained; wherein, the higher the value of the comprehensive evaluation index of the whole process, the better the coupling time point; when the values of the comprehensive evaluation index of the whole process are the same, the lower the change rate of the comprehensive evaluation index of the whole process, the better the coupling time point.

[0051] Specifically, in this embodiment,

[0052] The biogas obtained from anaerobic fermentation of biomass raw materials is used to replace natural gas to achieve carbon emission reduction values. The remaining solid biogas residue is put into the hydrothermal carbonization process to produce biochar. In addition to its own ability to store CO2 and achieve carbon emission reduction values, biochar can also be used with biogas liquid to produce fertilizer to replace industrial fertilizers and achieve carbon emission reduction values. The calculation formula for the above process is shown in formula (1):

[0053] FGC=FE+GS+CS (1)

[0054] FGC is a comprehensive evaluation indicator for the entire process, which can be divided into three parts: fertilizer replacement (FE), energy conversion (GS), and biochar carbon sequestration (CS). The higher the FGC value, the better the integration effect.

[0055] The numerical calculation formulas for the three parts are shown in formulas (2)-(4):

[0056]

[0057] In the formula, X IN Refers to the content of free ammonia nitrogen in the biogas slurry at a certain time of anaerobic fermentation (mg / L); C IN Refers to the ammonia nitrogen content per unit volume of industrial nitrogen fertilizer (mg / L); X c Refers to the phosphorus content (mg / L) of biochar produced by hydrothermal carbonization reaction; C FP Refers to the phosphorus content per unit volume of industrial phosphate fertilizer (mg / L); T FCO2 Refers to the CO2 emissions (gCO2eq) generated per unit volume of industrial nitrogen fertilizer production. Data on biogas production, free ammonia nitrogen in biogas slurry, and biochar production.

[0058] Formula explanation: This study uses the amount of free ammonia nitrogen to calculate the amount of industrial fertilizer that can be replaced by biogas slurry. The free ammonia nitrogen content in biogas slurry at a certain time of anaerobic fermentation is X IN The content of ammonia nitrogen in unit volume of industrial nitrogen fertilizer C IN , the volume of industrial fertilizer that can be replaced by biogas slurry is calculated. The phosphorus content is used to calculate the amount of industrial fertilizer that can be replaced by biochar. The phosphorus content of the biochar produced by the hydrothermal carbonization reaction is divided by the phosphorus content per unit volume of industrial phosphate fertilizer to obtain the volume of industrial fertilizer that can be replaced by biochar. These two values are added together and multiplied by the CO2 emissions generated per unit volume of industrial nitrogen fertilizer (recommended value: 13.5 gCO2eq) to obtain the carbon reduction from fertilizer substitution.

[0059]

[0060] In the formula, Q AD Refers to the calorific value (J / mol) of biogas generated during anaerobic fermentation when it is completely burned. gas Refers to the calorific value of natural gas per cubic meter when it is completely burned (J / mol). CO2 Refers to the amount of carbon dioxide emitted per cubic meter of natural gas produced (gCO2eq).

[0061] Formula Explanation: This study uses calorific value to calculate the carbon reductions achieved through energy conversion. The calorific value of biogas produced during anaerobic fermentation, when completely burned, is calculated relative to the calorific value of natural gas per cubic meter. This value is used to determine the volume of industrial natural gas displaced by biogas. Multiplying this value by the amount of carbon dioxide emitted per cubic meter of natural gas yields the carbon reductions achieved through energy conversion.

[0062] CS=3.6X C (4)

[0063] In the formula, X c Refers to the mass (g) of biochar generated during the hydrothermal carbonization reaction.

[0064] Formula explanation: After inquiry, the amount of carbon dioxide that can be sequestered per unit mass of biochar is 3.6gCO2eq. Therefore, the mass of biochar generated during the hydrothermal carbonization reaction is multiplied by 3.6 to obtain the carbon emission reduction value of biochar carbon sequestration.

[0065] By collecting the biogas production, free ammonia nitrogen content in the biogas slurry, and biochar production during the anaerobic fermentation-hydrothermal carbonization coupling reaction process, the process technology of the coupling reaction process is evaluated using formulas (1)-(4). The higher the FGC value, the better the coupling time point, and vice versa. When the FGC values are the same, the lower the FGC change rate, the better the coupling time point. 1gCO2eq is regarded as the coupling reaction control threshold. When the carbon emission reduction value of the coupling process exceeds 1gCO2eq, the reaction time point is regarded as the optimized process time and can be used to guide the actual coupling process.

[0066] This example constructs a comprehensive evaluation index for the optimal time point of anaerobic fermentation-hydrothermal carbonization coupling based on a machine learning method, filling the corresponding gap in coupled reaction research.

[0067] The following example uses straw as the raw material and simulates the coupled anaerobic fermentation and hydrothermal carbonization process of biomass based on a machine learning algorithm. The coupled reaction products and key intermediates are predicted and fitted, and a comprehensive evaluation index is calculated based on this to evaluate the optimal time point for the coupled reaction.

[0068] Figure 1The figure in the middle shows the gas production during the anaerobic fermentation of straw: Methane production is primarily concentrated in the first 12 days. Subsequently, methane production gradually decreases, and gas production ceases. The first five days of anaerobic fermentation are the peak period for methane production, with an average daily methane production of 24.43 mL / g TS.

[0069] Figure 2 The simulation shows how the elemental content of biogas residue changes with anaerobic fermentation time. The organic element contents of C, H, O, and N in the raw material were 42.53%, 5.72%, 43.52%, and 0.59%, respectively. Due to the addition of a high-ash inoculant during the anaerobic fermentation reaction, C, H, and O all decreased to varying degrees. The nitrogen content increased to 2.22%. Therefore, the initial C, H, O, and N contents of the biogas residue were 33.14%, 4.15%, 30.02%, and 2.22%, respectively. The elemental content simulation results indicate that the overall content of C, H, and O decreased. The contents of the three elements decreased from an initial 33.14%, 4.15%, and 30.02% to 26.11%, 0.76%, and 24.11%, respectively. C and O showed a relatively significant downward trend during the first 12 days of anaerobic fermentation. During this period, the average reduction rate of C was 1.03%, and the average reduction rate of O was 1.05%. After 10-21 days of anaerobic fermentation, the rate of reduction of C and O elements slowed down. During this stage, the average reduction rate of C was 0.79%, and the average reduction rate of O was 0.85%. Compared with C and O, the content of H fluctuated during the AD reaction. After 6-9 days of reaction, the content of H showed an upward trend and then began to decline again (from 0.68% to 1.06%). During the first 6 days of anaerobic fermentation, the content of N fluctuated within a small range of 2.18-2.22%, and then increased by 2.57%.

[0070] Figure 3 The results show how the biochar content generated by the hydrothermal carbonization reaction changes with anaerobic fermentation reaction time. The results show that biochar yield generally decreases with anaerobic fermentation time. Specifically, biochar yield decreases significantly when the anaerobic fermentation reaction time is 1-7 days. However, the rate of decrease in biochar yield is not significant when the anaerobic fermentation reaction duration is between 9-21 days.

[0071] Figure 4 The carbon emission reduction changes of anaerobic fermentation-hydrothermal carbonization coupling technology are shown; A. FE, GS and CS values; B. FGC value and its change rate. The FGC value reflects the carbon emission reduction changes of the anaerobic fermentation-hydrothermal carbonization coupling reaction process. Figure 4According to the results of Figure 2, FGC reached its maximum value (1.097 gCO2eq) on the 13th day of the anaerobic fermentation reaction. In other words, the most effective coupling time point for the anaerobic fermentation-hydrothermal carbonization coupling reaction using the raw material (corn straw) in this study was on the 13th day. The AD reaction durations close to the maximum value were 11 days, 15 days, and 17 days. The carbon emission reductions generated by the three durations were 0.988, 1.0107, and 1.0102 gCO2eq, respectively. Therefore, according to the threshold value (1 gCO2eq), the 13th, 15th, and 17th days of the reaction can be regarded as the time points for guiding the actual coupling process in the next step.

[0072] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A method for evaluating the optimal process technology of biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on a machine learning algorithm, characterized in that: include: Collecting reaction data during the anaerobic fermentation-hydrothermal carbonization coupling reaction process; wherein the reaction data includes: biogas production, free ammonia nitrogen content in biogas slurry, and biochar production; Based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using comprehensive evaluation indicators of the entire process; wherein the comprehensive evaluation indicators of the entire process include: fertilizer substitution, energy conversion, and biochar carbon sequestration.

2. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 1 is characterized in that: The method for collecting reaction data in the anaerobic fermentation-hydrothermal carbonization coupling reaction process includes: using a machine learning algorithm.

3. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 1 is characterized in that: Based on the reaction data, the anaerobic fermentation-hydrothermal carbonization coupled reaction process is evaluated using comprehensive evaluation indicators of the entire process, including: Based on the reaction data, a fertilizer substitution index, an energy conversion index, and a biochar carbon sequestration index are obtained respectively; Based on the material substitution index, energy conversion index and biochar carbon sequestration index, the comprehensive evaluation index of the whole process is obtained; wherein, the higher the value of the comprehensive evaluation index of the whole process, the better the coupling time point; when the values of the comprehensive evaluation index of the whole process are the same, the lower the change rate of the comprehensive evaluation index of the whole process, the better the coupling time point.

4. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 3 is characterized in that: Indicators for obtaining fertilizer alternatives include: Based on the free ammonia nitrogen content in the biogas slurry at a certain point in anaerobic fermentation and the ammonia nitrogen content per unit volume of industrial nitrogen fertilizer, the volume of industrial fertilizer that can be replaced by biogas slurry is obtained; Based on the phosphorus content of the biochar produced by the hydrothermal carbonization reaction and the phosphorus content per unit volume of industrial phosphate fertilizer, the volume of industrial fertilizer that can be replaced by biochar is obtained; The fertilizer substitution index is obtained based on the volume of industrial fertilizer that can be replaced by biogas slurry, the volume of industrial fertilizer that can be replaced by biochar, and the CO2 emissions generated per unit volume of industrial nitrogen fertilizer.

5. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 4 is characterized in that: The fertilizer substitution index is: Among them, X IN Refers to the content of free ammonia nitrogen in biogas slurry at a certain moment of anaerobic fermentation; C IN Refers to the content of ammonia nitrogen in unit volume of industrial nitrogen fertilizer; X c Refers to the phosphorus content of biochar produced by hydrothermal carbonization reaction; C FP Refers to the phosphorus content per unit volume of industrial phosphate fertilizer; T FCO2 Refers to the CO2 emissions generated by producing unit volume of industrial nitrogen fertilizer.

6. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 3 is characterized in that: Obtaining energy conversion indicators includes: Based on the calorific value of biogas generated during anaerobic fermentation when completely burned and the calorific value of natural gas per cubic meter when completely burned, the volume of industrial natural gas replaced by biogas is obtained; An energy conversion index is obtained based on the volume of industrial natural gas replaced by the biogas and the amount of carbon dioxide emitted per cubic meter of natural gas.

7. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 6 is characterized in that: The energy conversion index is: Among them, Q AD Refers to the calorific value of biogas generated during anaerobic fermentation when it is completely burned, Q gas It refers to the calorific value of natural gas per cubic meter when it is completely burned, T CO2 Refers to the amount of carbon dioxide emitted per cubic meter of natural gas produced.

8. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 3 is characterized in that: Obtaining biochar carbon sequestration indicators includes: The biochar carbon sequestration index is obtained based on the mass of biochar generated during the hydrothermal carbonization reaction.

9. The optimal process technology evaluation method for biomass anaerobic fermentation-hydrothermal carbonization coupling technology based on machine learning algorithm according to claim 8 is characterized in that: The biochar carbon sequestration index is: CS=3.6X C Among them, X c Refers to the mass of biochar generated during the hydrothermal carbonization reaction.

Images