Method and system for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction
By using machine learning models and hydrogen peroxide coupled with low-temperature baking pretreatment technology, the problem of poor prediction of nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction reaction was solved, achieving higher prediction accuracy and control effect.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIANGJIANG LAB
- Filing Date
- 2024-08-27
- Publication Date
- 2026-04-21
AI Technical Summary
The existing technology has poor prediction effect on nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction reactions, mainly because the elemental composition detection methods are labor-intensive and have high errors, resulting in insufficient information on the reaction substrate.
By acquiring the first and second datasets, a machine learning model, particularly the random forest algorithm, was trained and optimized to predict and regulate the content of nitrogen-containing heterocycles, which was then regulated by combining hydrogen peroxide-coupled low-temperature baking pretreatment technology.
It improves the prediction accuracy and regulation effect of nitrogen-containing heterocyclic compounds, and achieves more precise control of nitrogen-containing heterocyclic content.
Smart Images
Figure CN119170147B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of regulating the content of nitrogen-containing heterocyclic compounds in biomass, and in particular to a method and system for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction. Background Technology
[0002] Due to the scarcity of fossil resources, coupled with the increasingly prominent climate and environmental problems caused by them, fossil resource substitution is imperative to achieve the "dual carbon" goals. High-value nitrogen-containing heterocyclic chemicals (hereinafter referred to as NH) in the pharmaceutical, solvent, and other fields are generally processed from fossil resources. Therefore, utilizing biomass raw materials to replace fossil resources in the production of high-value NH is of great significance.
[0003] The type and content of NH3 in liquefaction products vary greatly due to factors such as the composition of biomass feedstock and hydrothermal reaction parameters. Traditional experimental studies mainly measure the properties of the prepared nitrogen-containing heterocyclic products, primarily exploring the influence of reaction conditions on nitrogen-containing heterocycles. Currently, attempts are made to predict the content of nitrogen-containing heterocycles using the elemental composition of biomass and hydrothermal liquefaction conditions. However, elemental composition detection methods involve a large workload and high error in systematically analyzing the composition of biomass, resulting in poor prediction results due to insufficient information on the reaction substrates of biomass hydrothermal liquefaction reactions. Summary of the Invention
[0004] The present invention aims to at least solve the technical problems existing in the prior art. To this end, the present invention proposes a method and system for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction, which can improve the prediction accuracy and regulation effect of nitrogen-containing heterocyclic content.
[0005] In a first aspect, the present invention provides a method for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass, comprising the following steps:
[0006] Obtain a first dataset and a second dataset, wherein the first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured, and the second dataset includes the elemental composition of the second biomass to be regulated;
[0007] Based on the first dataset and the pre-built initial machine learning model, the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content are obtained.
[0008] The second biomass is regulated based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
[0009] The control method according to embodiments of the present invention has at least the following beneficial effects:
[0010] This method acquires a first dataset and a second dataset. The first dataset includes the measured elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content of the first biomass, while the second dataset includes the elemental composition of the second biomass to be regulated. Based on the first dataset and a pre-built initial machine learning model, the trained machine learning model and its outputs are obtained, including the highest nitrogen-containing heterocyclic content, the corresponding feature value, and the corresponding feature weight value. Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the corresponding feature weight value, the second biomass is regulated to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, thus improving the prediction accuracy and regulation effect of nitrogen-containing heterocyclic content.
[0011] According to some embodiments of the present invention, obtaining the trained machine learning model and its output, including the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, based on the first dataset and the pre-built initial machine learning model, includes:
[0012] Based on the elemental composition of the first biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the first biomass.
[0013] The first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocyclic content are input into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocyclic content, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content. The features include the first biomass elemental composition descriptor and the hydrothermal liquefaction conditions, and the hydrothermal liquefaction conditions include temperature, time, and solids content.
[0014] According to some embodiments of the present invention, the step of inputting the first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocycle content into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content includes:
[0015] The first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocyclic content are input into the initial machine learning model, and the loss value of the initial machine learning model is calculated by the random forest algorithm.
[0016] Based on the loss value, the initial machine learning model is back-optimized to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content.
[0017] According to some embodiments of the present invention, the formula for calculating the loss value of the initial machine learning model by inputting the first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocyclic content into the initial machine learning model and calculating the loss value of the initial machine learning model using the random forest algorithm is as follows:
[0018]
[0019] Where L is the loss value, y i Let i be the true value of the i-th sample in the first dataset. Let N be the predicted value of the i-th sample in the first dataset, and N be the total number of samples in the first dataset.
[0020] According to some embodiments of the present invention, the step of regulating the second biomass based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content to obtain the regulated nitrogen-containing heterocycle content of the second biomass includes:
[0021] Based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the second biomass.
[0022] The second biomass is regulated based on the elemental composition descriptor of the second biomass, the characteristic value corresponding to the highest nitrogen-containing heterocyclic content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocyclic content, to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
[0023] According to some embodiments of the present invention, the step of regulating the second biomass based on the second biomass elemental composition descriptor, the characteristic value corresponding to the highest nitrogen-containing heterocycle content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocycle content to obtain the regulated nitrogen-containing heterocycle content of the second biomass includes:
[0024] The second biomass elemental composition derivation derivation derivation is screened based on the feature weight value corresponding to the highest nitrogen-containing heterocyclic content and the preset derivation derivation ratio to obtain the second biomass screened derivation derivation derivation.
[0025] The second biomass is regulated based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening, so as to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
[0026] According to some embodiments of the present invention, the step of regulating the second biomass based on the characteristic value corresponding to the highest nitrogen-containing heterocycle content and the derivation descriptor after screening the second biomass to obtain the regulated nitrogen-containing heterocycle content of the second biomass includes:
[0027] Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening of the second biomass, the second biomass is regulated by hydrogen peroxide coupled low-temperature baking pretreatment technology to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
[0028] A second aspect of the present invention provides a system for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass, the system comprising:
[0029] The data acquisition module is used to acquire a first dataset and a second dataset, wherein the first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured, and the second dataset includes the elemental composition of the second biomass to be regulated.
[0030] The model training module is used to obtain the trained machine learning model and its output, the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, based on the first dataset and the pre-built initial machine learning model.
[0031] The regulation module is used to regulate the second biomass based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content, so as to obtain the nitrogen-containing heterocyclic content of the second biomass after regulation.
[0032] This system acquires a first dataset and a second dataset. The first dataset includes the measured elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content of the first biomass, while the second dataset includes the elemental composition of the second biomass to be regulated. Based on the first dataset and a pre-built initial machine learning model, the system obtains the trained machine learning model and its output: the highest nitrogen-containing heterocyclic content, the corresponding feature value, and the corresponding feature weight value. Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the corresponding feature weight value, the system regulates the second biomass to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, thereby improving the prediction accuracy and regulation effect of nitrogen-containing heterocyclic content.
[0033] A third aspect of the present invention provides an electronic device for regulating the content of nitrogen-containing heterocyclic compounds in biomass, comprising at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, the instructions being executed by the at least one control processor to enable the at least one control processor to perform the above-described method for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass.
[0034] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the above-described method for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass.
[0035] It should be noted that the beneficial effects of the second to fourth aspects of the present invention compared with the prior art are the same as the beneficial effects of the above-described biomass hydrothermal liquefaction nitrogen-containing heterocyclic compound regulation system compared with the prior art, and will not be described in detail here.
[0036] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0037] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:
[0038] Figure 1 This is a flowchart of a method for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass according to an embodiment of the present invention;
[0039] Figure 2 This is a schematic diagram illustrating the prediction results of the method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction provided in this application;
[0040] Figure 3 This is a schematic diagram showing the ranking of the characteristic importance of the method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction provided in this application;
[0041] Figure 4 This is a schematic diagram of the characteristic influence relationship data of the method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction provided in this application;
[0042] Figure 5 This is a schematic diagram of an embodiment of the regulation system for biomass hydrothermal liquefaction of nitrogen-containing heterocyclic compounds provided in this application;
[0043] Figure 6 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application. Detailed Implementation
[0044] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0045] In the description of this invention, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance, or implicitly indicating the number of technical features indicated, or implicitly indicating the order of the technical features indicated.
[0046] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the drawings and are only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.
[0047] In the description of this invention, it should be noted that, unless otherwise explicitly defined, terms such as "setting," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.
[0048] Due to the scarcity of fossil resources, coupled with the increasingly prominent climate and environmental problems caused by them, fossil resource substitution is imperative to achieve the "dual carbon" goals. High-value nitrogen-containing heterocyclic chemicals (hereinafter referred to as NH) in the pharmaceutical, solvent, and other fields are generally processed from fossil resources. Therefore, utilizing biomass raw materials to replace fossil resources in the production of high-value NH is of great significance.
[0049] The type and content of NH3 in liquefaction products vary greatly due to factors such as the composition of biomass feedstock and hydrothermal reaction parameters. Traditional experimental studies mainly measure the properties of the prepared nitrogen-containing heterocyclic products, primarily exploring the influence of reaction conditions on nitrogen-containing heterocycles. Currently, attempts are made to predict the content of nitrogen-containing heterocycles using the elemental composition of biomass and hydrothermal liquefaction conditions. However, elemental composition detection methods involve a large workload and high error in systematically analyzing the composition of biomass, resulting in poor prediction results due to insufficient information on the reaction substrates of biomass hydrothermal liquefaction reactions.
[0050] To address the aforementioned technical deficiencies, this application provides a method and system for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction.
[0051] Please see Figure 1This is a flowchart illustrating a method for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass, provided in an embodiment of this application. This method is applied to electronic devices, such as servers. Figure 1 As shown, the method for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass includes:
[0052] Step S101: Obtain the first dataset and the second dataset, wherein the first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured, and the second dataset includes the elemental composition of the second biomass to be regulated.
[0053] Step S102: Based on the first dataset and the pre-built initial machine learning model, obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content;
[0054] Step S103: Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content are used to regulate the second biomass to obtain the nitrogen-containing heterocyclic content of the regulated second biomass.
[0055] This method acquires a first dataset and a second dataset. The first dataset includes the measured elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content of the first biomass, while the second dataset includes the elemental composition of the second biomass to be regulated. Based on the first dataset and a pre-built initial machine learning model, the trained machine learning model and its outputs are obtained, including the highest nitrogen-containing heterocyclic content, the corresponding feature value, and the corresponding feature weight value. Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the corresponding feature weight value, the second biomass is regulated to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, thus improving the prediction accuracy and regulation effect of nitrogen-containing heterocyclic content.
[0056] In some embodiments, step S102, based on the first dataset and a pre-built initial machine learning model, obtains the trained machine learning model and its output: the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, including:
[0057] Step S201: Calculate the elemental composition descriptor based on the elemental composition of the first biomass and the molecular structure characteristics of the main components of the biomass to obtain the elemental composition descriptor of the first biomass.
[0058] Step S202: Input the first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocyclic content, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content. The features include the first biomass elemental composition descriptor and the hydrothermal liquefaction conditions, and the hydrothermal liquefaction conditions include temperature, time, and solids content.
[0059] Specifically, in some embodiments, the elemental composition descriptors are calculated based on the molecular structural characteristics of the main components of biomass, except for the first biomass elemental composition (Ash).
[0060] The calculated descriptors are based on elemental molar ratios, including but not limited to H / C, O / C, N / C, H / (0.5C+N+O+S), N / O, H / N, H / 3O, H / O, (H-2C) / (N+O), (CON) / (HN), (H+O+N+S) / C, (H-2N) / C, 2N / C, (HN) / C, (O+N) / C, S / H, S / N(HO) / C, 2O / C, 2H / C, 2H / 3C, S / C, H / (0.5C+N+O), (HNOS) / C, H / (C+O+N+S), (HNO) / C.
[0061] Hydrothermal liquefaction conditions include, but are not limited to, temperature, time, and solids content.
[0062] This embodiment improves the accuracy of model training by training the initial machine learning model using a first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content.
[0063] In some embodiments, in step S202, the first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocycle content are input into the initial machine learning model to obtain the trained machine learning model and its output: the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, including:
[0064] Step S301: Input the first biomass elemental composition descriptor, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content into the initial machine learning model, and calculate the loss value of the initial machine learning model through the random forest algorithm;
[0065] Step S302: Perform reverse optimization on the initial machine learning model based on the loss value to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content.
[0066] Specifically, the hyperparameters of the initial machine learning model used for random forest are adjusted by cross-validation error; the hyperparameters include the number of trees and the depth of the trees.
[0067] The training set is input into the initial machine learning model, and the loss function of the initial machine learning model is calculated using the random forest algorithm;
[0068] The initial machine learning model is trained under supervision using the objective loss function, resulting in a well-trained machine learning model.
[0069] Specifically, in some embodiments, a random forest algorithm is used to analyze the nitrogen-containing heterocyclic content prediction model to determine the impact of each input feature variable on the dependent variable and obtain the importance ranking of the input feature variables.
[0070] Importance score (VIM) is defined as follows: In each tree of the random forest, a tree is built using randomly drawn training bootstrap samples, and the prediction error rate for out-of-bag (OOB) data is calculated. Then, the variable X is randomly permuted. j After obtaining the observed values, a new tree is built and the prediction error rate of OOB is calculated. Finally, the difference between the two OOB error rates is calculated, and the average of the results across all trees after standardization is taken as the variable X. j Importance of substitution
[0071]
[0072] in, Y represents the number of observations in the O0B data of the i-th tree, I is an indicator function that takes the value 1 when the two values are equal and 0 when they are unequal; p ∈{0,1} represents the true result of the p-th observation. This represents the prediction result of the i-th tree for the p-th observation of the OOB data before random permutation. This represents the prediction result of the i-th tree for the p-th observation of the OOB data after random permutation.
[0073] When variable X j If it does not appear in the i-th tree,
[0074] VARIABLE X j In RF, the importance of permutation is defined as:
[0075]
[0076] Where n is the number of classification trees in RF.
[0077] Partial dependency analysis was applied to the nitrogen-containing heterocycle content prediction model to obtain the influence relationship between key features and output features. The nitrogen-containing heterocycle content affects the input feature z.s Partial dependencies can be defined as:
[0078]
[0079] Where x = {x1, x2, ..., xn} p} represents the predictor in the model, and the prediction function is z s It is necessary to plot the eigenvalues of the partially dependent functions, z. c Other features used; p c It is z c Boundary probability density:
[0080] p c (z c )=∫p(x)dz s
[0081]
[0082] Among them, z i,c (i = 1, 2, ..., n) represents the z-values found in the training samples. c value.
[0083] In some embodiments, in step S301, the first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content are input into the initial machine learning model, and the formula for calculating the loss value of the initial machine learning model using the random forest algorithm is as follows:
[0084]
[0085] Where L is the loss value, y i Let i be the true value of the i-th sample in the first dataset. Let N be the predicted value of the i-th sample in the first dataset, and N be the total number of samples in the first dataset.
[0086] Specifically, in some embodiments, a test set is obtained by dividing the tested sample dataset, and the test set is input into a trained machine learning model to obtain the prediction results output by the trained machine learning model;
[0087] The coefficient of determination, root mean square error, and mean absolute error of the trained machine learning model are calculated based on the prediction results. The formulas for calculating the coefficient of determination, root mean square error, and mean absolute error include:
[0088]
[0089] Among them, R 2 The coefficient of determination is given by RMSE (root mean square error), MAE (mean absolute error), and N² (number of samples in the test set). and These represent the i2th experimental value and the corresponding predicted value, respectively. This represents the average of N² experimental values;
[0090] The evaluation results of the trained machine learning model are calculated based on the coefficient of determination and the root mean square error.
[0091] In some embodiments, in step S103, the second biomass is regulated based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content to obtain the regulated nitrogen-containing heterocycle content of the second biomass, including:
[0092] Step S401: Calculate the elemental composition descriptor based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass to obtain the elemental composition descriptor of the second biomass.
[0093] Step S402: The second biomass is regulated according to the elemental composition descriptor of the second biomass, the characteristic value corresponding to the highest nitrogen-containing heterocyclic content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocyclic content, so as to obtain the nitrogen-containing heterocyclic content of the regulated second biomass.
[0094] In some embodiments, in step S402, the second biomass is regulated according to the second biomass elemental composition descriptor, the characteristic value corresponding to the highest nitrogen-containing heterocycle content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocycle content, to obtain the regulated nitrogen-containing heterocycle content of the second biomass, including:
[0095] Step S501: Based on the feature weight value corresponding to the highest nitrogen-containing heterocyclic content and the preset derivation descriptor ratio, the second biomass element composition derivation descriptor is screened to obtain the second biomass screened derivation descriptor.
[0096] Step S502: Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived from the second biomass after screening, the second biomass is regulated to obtain the nitrogen-containing heterocyclic content of the regulated second biomass.
[0097] In some embodiments, in step S502, the second biomass is regulated based on the characteristic value corresponding to the highest nitrogen-containing heterocycle content and the descriptor derived after screening the second biomass, to obtain the regulated nitrogen-containing heterocycle content of the second biomass, including:
[0098] Step S601: Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening of the second biomass, the second biomass is regulated by hydrogen peroxide coupled low-temperature baking pretreatment technology to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
[0099] Specifically, in some embodiments, the second biomass is stirred and mixed with hydrogen peroxide solution, filtered, and then subjected to low-temperature baking to obtain the final second biomass raw material.
[0100] A hydrothermal liquefaction experiment was conducted on the second biomass feedstock to obtain a product with high nitrogen heterocyclic content.
[0101] In some embodiments, the mass concentration of hydrogen peroxide ranges from 5% to 20%, the mass ratio of the second biomass to hydrogen peroxide is 1:30, and the stirring time is 1h to 3h.
[0102] In some embodiments, the baking temperature range is 100–150°C, and the baking time range is 30–90 min.
[0103] Specifically, refer to Figures 2 to 4 In some embodiments, the elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content characteristics of 116 samples were obtained. The elemental composition of the biomass was standardized, and the calculation formula included:
[0104] C + H + O + N + S + Ash = 100
[0105] The elements are derivation descriptors calculated according to their chemical molecular structure characteristics, as shown in Table 1. Table 1 shows the input features of elemental composition and its derivation descriptors and hydrothermal liquefaction conditions, with a total of 35 input features and 1 output variable.
[0106] Table 1
[0107]
[0108]
[0109] Multiple descriptors derived from the elemental composition of biomass and hydrothermal liquefaction conditions are used as input features, and the nitrogen-containing heterocyclic content of the product is used as the output feature to obtain the measured sample dataset.
[0110] The measured sample dataset is divided into a training set, and a pre-set target prediction model is trained using the training set to obtain the final target prediction model.
[0111] A random forest algorithm was used to analyze the prediction model for nitrogen-containing heterocyclic content, determining the impact of each input feature variable on the dependent variable and obtaining a ranking of the importance of the input feature variables. Partial dependency analysis was also applied to the prediction model to obtain the influence relationship between key features and output features.
[0112] Specifically, for the convenience of those skilled in the art, a set of preferred embodiments is provided below:
[0113] I. Data Acquisition:
[0114] Obtain a first dataset and a second dataset. The first dataset includes the elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content of the first biomass that have been measured. The second dataset includes the elemental composition of the second biomass to be regulated.
[0115] II. Model Training:
[0116] Based on the first dataset and the pre-built initial machine learning model, the trained machine learning model and its outputs are obtained, including the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content. Specifically:
[0117] Based on the elemental composition of the first biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the first biomass.
[0118] The descriptor of the first biomass elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content are input into the initial machine learning model. The loss value of the initial machine learning model is calculated using the random forest algorithm. The formula for calculating the loss value of the initial machine learning model using the random forest algorithm is as follows:
[0119]
[0120] Where L is the loss value, y i Let i be the true value of the i-th sample in the first dataset. Let N be the predicted value of the i-th sample in the first dataset, and N be the total number of samples in the first dataset.
[0121] The initial machine learning model is back-optimized based on the loss value to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocyclic content, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content. The features include the first biomass elemental composition descriptor and hydrothermal liquefaction conditions, which include temperature, time, and solids content.
[0122] III. Biomass Regulation:
[0123] The nitrogen-containing heterocycle content of the second biomass was regulated based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, to obtain the regulated nitrogen-containing heterocycle content of the second biomass, specifically:
[0124] Based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the second biomass.
[0125] The second biomass elemental composition derivation descriptors are screened based on the feature weight value corresponding to the highest nitrogen-containing heterocyclic content and the preset derivation descriptor ratio to obtain the second biomass screened derivation descriptors.
[0126] Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening of the second biomass, the nitrogen-containing heterocyclic content of the second biomass was regulated by hydrogen peroxide coupled low-temperature baking pretreatment technology to obtain the regulated second biomass.
[0127] Additionally, refer to Figure 5 One embodiment of the present invention provides a regulation system for the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass, comprising a data acquisition module 1100, a model training module 1200, and a regulation module 1300, wherein:
[0128] The data acquisition module 1100 is used to acquire a first dataset and a second dataset. The first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured. The second dataset includes the elemental composition of the second biomass to be regulated.
[0129] The model training module 1200 is used to obtain the trained machine learning model and its output, the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, based on the first dataset and the pre-built initial machine learning model.
[0130] The regulation module 1300 is used to regulate the second biomass based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the feature weight value corresponding to the highest nitrogen-containing heterocyclic content, so as to obtain the nitrogen-containing heterocyclic content of the regulated second biomass.
[0131] This system acquires a first dataset and a second dataset. The first dataset includes the measured elemental composition, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content of the first biomass, while the second dataset includes the elemental composition of the second biomass to be regulated. Based on the first dataset and a pre-built initial machine learning model, the system obtains the trained machine learning model and its output: the highest nitrogen-containing heterocyclic content, the corresponding feature value, and the corresponding feature weight value. Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocyclic content, and the corresponding feature weight value, the system regulates the second biomass to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, thereby improving the prediction accuracy and regulation effect of nitrogen-containing heterocyclic content.
[0132] In some implementations, the model training module is also specifically used for:
[0133] Based on the elemental composition of the first biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the first biomass.
[0134] The first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocycle content are input into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content. The features include the first biomass elemental composition descriptor and the hydrothermal liquefaction conditions, and the hydrothermal liquefaction conditions include temperature, time, and solids content.
[0135] In some implementations, the model training module is also specifically used for:
[0136] The first biomass elemental composition descriptor, hydrothermal liquefaction conditions, and nitrogen-containing heterocyclic content are input into the initial machine learning model, and the loss value of the initial machine learning model is calculated by the random forest algorithm.
[0137] The initial machine learning model is back-optimized based on the loss value to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content.
[0138] In some implementations, the control module is also specifically used for:
[0139] Based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the second biomass.
[0140] The nitrogen-containing heterocycle content of the second biomass is obtained by regulating the second biomass based on the elemental composition descriptor, the characteristic value corresponding to the highest nitrogen-containing heterocycle content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocycle content.
[0141] In some implementations, the control module is also specifically used for:
[0142] The second biomass elemental composition derivation descriptors are screened based on the feature weight value corresponding to the highest nitrogen-containing heterocyclic content and the preset derivation descriptor ratio to obtain the second biomass screened derivation descriptors.
[0143] The nitrogen-containing heterocyclic content of the second biomass was regulated based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening the second biomass.
[0144] In some implementations, the control module is also specifically used for:
[0145] Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening of the second biomass, the nitrogen-containing heterocyclic content of the second biomass was regulated by hydrogen peroxide coupled low-temperature baking pretreatment technology to obtain the regulated second biomass.
[0146] It should be noted that the system embodiments described above are based on the same inventive concept as the method embodiments described above. Therefore, the relevant content of the method embodiments described above is also applicable to the system embodiments described above, and will not be repeated here.
[0147] Figure 6 A schematic diagram of the hardware structure for regulating the content of nitrogen-containing heterocyclic compounds in biomass provided in an embodiment of this application is shown.
[0148] The device for regulating the nitrogen heterocyclic content of biomass may include a processor 501 and a memory 502 storing computer program instructions.
[0149] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0150] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.
[0151] In some embodiments, memory 502 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.
[0152] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any of the methods for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass in the above embodiments.
[0153] In one example, the device for regulating the nitrogen-containing heterocyclic content of biomass may further include a communication interface 503 and a bus 510. For example, Figure 6 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.
[0154] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.
[0155] Bus 510 includes hardware, software, or both, that couples components of a device for regulating the nitrogen heterocyclic content of biomass together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.
[0156] The device for regulating the content of nitrogen-containing heterocyclic compounds in biomass can execute the method for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds in biomass, as described in the embodiments of this application, based on a three-dimensional design model, thereby achieving a combination of... Figure 1 and Figure 5 The method and system for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction are described.
[0157] Furthermore, in conjunction with the methods for controlling nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods for controlling nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass described in the above embodiments.
[0158] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0159] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0160] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0161] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in 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, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.
[0162] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. A method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction, characterized in that, The method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction includes: Obtain a first dataset and a second dataset, wherein the first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured, and the second dataset includes the elemental composition of the second biomass to be regulated; Based on the first dataset and the pre-built initial machine learning model, the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content are obtained, specifically: Based on the elemental composition and molecular structure characteristics of the main components of the first biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the first biomass. The elemental composition descriptor of the first biomass includes H / C, O / C, N / C, H / (0.5C+N+O+S), N / O, H / N, H / 3O, H / O, (H-2C) / (N+O), (CON) / (HN), (H+O+N+S) / C, (H-2N) / C, 2N / C, (HN) / C, (O+N) / C, S / H, S / N, (HO) / C, 2O / C, 2H / C, 2H / 3C, S / C, H / (0.5C+N+O), (HNOS) / C, H / (C+O+N+S), (HNO) / C; The first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocycle content are input into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content. The features include the first biomass elemental composition descriptor and the hydrothermal liquefaction conditions, and the hydrothermal liquefaction conditions include temperature, time, and solids content. Based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, the second biomass is regulated to obtain the regulated nitrogen-containing heterocycle content of the second biomass, specifically: Based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the second biomass. The second biomass is regulated based on the elemental composition descriptor of the second biomass, the characteristic value corresponding to the highest nitrogen-containing heterocyclic content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocyclic content, to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
2. The method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction according to claim 1, characterized in that, The step of inputting the first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocycle content into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content includes: The first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocyclic content are input into the initial machine learning model, and the loss value of the initial machine learning model is calculated by the random forest algorithm. Based on the loss value, the initial machine learning model is back-optimized to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content.
3. The method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction according to claim 2, characterized in that, The formula for calculating the loss value of the initial machine learning model by inputting the first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocyclic content into the initial machine learning model and calculating the loss value of the initial machine learning model using the random forest algorithm is as follows: in, The loss value. Let i be the true value of the i-th sample in the first dataset. Let be the predicted value of the i-th sample in the first dataset. This represents the total number of samples in the first dataset.
4. The method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction according to claim 1, characterized in that, The step of regulating the second biomass based on the elemental composition descriptor of the second biomass, the characteristic value corresponding to the highest nitrogen-containing heterocyclic content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocyclic content, to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, includes: The second biomass elemental composition derivation derivation derivation is screened based on the feature weight value corresponding to the highest nitrogen-containing heterocyclic content and the preset derivation derivation ratio to obtain the second biomass screened derivation derivation derivation. The second biomass is regulated based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the derivation descriptor after screening, so as to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
5. The method for regulating nitrogen-containing heterocyclic compounds in biomass hydrothermal liquefaction according to claim 4, characterized in that, The step of regulating the second biomass based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived from the second biomass after screening, to obtain the regulated nitrogen-containing heterocyclic content of the second biomass, includes: Based on the characteristic value corresponding to the highest nitrogen-containing heterocyclic content and the descriptor derived after screening of the second biomass, the second biomass is regulated by hydrogen peroxide coupled low-temperature baking pretreatment technology to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
6. A system for regulating nitrogen-containing heterocyclic compounds in the hydrothermal liquefaction of biomass, characterized in that, The regulation system for the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass includes: The data acquisition module is used to acquire a first dataset and a second dataset, wherein the first dataset includes the elemental composition, hydrothermal liquefaction conditions and nitrogen-containing heterocyclic content of the first biomass that have been measured, and the second dataset includes the elemental composition of the second biomass to be regulated. The model training module is used to obtain, based on the first dataset and the pre-built initial machine learning model, the trained machine learning model and its output, the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, specifically: Based on the elemental composition and molecular structure characteristics of the main components of the first biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the first biomass. The elemental composition descriptor of the first biomass includes H / C, O / C, N / C, H / (0.5C+N+O+S), N / O, H / N, H / 3O, H / O, (H-2C) / (N+O), (CON) / (HN), (H+O+N+S) / C, (H-2N) / C, 2N / C, (HN) / C, (O+N) / C, S / H, S / N, (HO) / C, 2O / C, 2H / C, 2H / 3C, S / C, H / (0.5C+N+O), (HNOS) / C, H / (C+O+N+S), (HNO) / C; The first biomass elemental composition descriptor, the hydrothermal liquefaction conditions, and the nitrogen-containing heterocycle content are input into the initial machine learning model to obtain the trained machine learning model and its output of the highest nitrogen-containing heterocycle content, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content. The features include the first biomass elemental composition descriptor and the hydrothermal liquefaction conditions, and the hydrothermal liquefaction conditions include temperature, time, and solids content. The regulation module is used to regulate the second biomass based on the second dataset, the feature value corresponding to the highest nitrogen-containing heterocycle content, and the feature weight value corresponding to the highest nitrogen-containing heterocycle content, to obtain the regulated nitrogen-containing heterocycle content of the second biomass, specifically: Based on the elemental composition of the second biomass and the molecular structure characteristics of the main components of the biomass, the elemental composition descriptor is calculated to obtain the elemental composition descriptor of the second biomass. The second biomass is regulated based on the elemental composition descriptor of the second biomass, the characteristic value corresponding to the highest nitrogen-containing heterocyclic content, and the characteristic weight value corresponding to the highest nitrogen-containing heterocyclic content, to obtain the regulated nitrogen-containing heterocyclic content of the second biomass.
7. A device for regulating the nitrogen-containing heterocyclic content of biomass, characterized in that, It includes at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform a method for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass as described in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions for causing a computer to perform a method for regulating the hydrothermal liquefaction of nitrogen-containing heterocyclic compounds from biomass as described in any one of claims 1 to 5.