Direct coal liquefaction performance evaluation method, storage medium and electronic equipment
By constructing a target evaluation model and using a variety of machine learning algorithms, the problem of high time cost of direct coal liquefaction performance evaluation in the existing technology is solved, and a fast, effective and accurate performance evaluation is achieved, providing guidance for experimental regulation.
Patent Information
- Application Number
- CN202510149824.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-11
- Publication Date
- 2025-05-30
AI Technical Summary
The prior art is difficult to quickly, effectively and accurately evaluate the direct liquefaction performance of coal, and the time cost is high when considering various influencing factors.
By constructing a target evaluation model, real-time impact factor information is obtained and input into the model, and training is performed using linear regression, random forest, mild-level gradient enhancement and extreme gradient enhancement algorithms to obtain liquefaction performance evaluation indexes.
It has achieved rapid, effective and accurate evaluation of the direct liquefaction performance of coal in a short period of time, providing guidance for the regulation of direct liquefaction experiments of coal.
Smart Images
Figure CN120068015A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of coal liquefaction, and particularly to a method for evaluating the direct coal liquefaction performance, a storage medium, and an electronic device. Background Art
[0002] The direct coal liquefaction reaction is a process in which an oil-coal slurry prepared by mixing coal, a solvent, and a catalyst generates oil, water, and gas under high temperature and high pressure. At present, the free radical reaction mechanism of direct coal hydrogenation liquefaction has been widely recognized by many scholars. The coal liquefaction process is a process in which weak bonds in the coal molecular structure are broken to initiate free radical reactions. The complex molecular structure of coal is broken at high temperature to form free radicals with a single atomic structure, and under the action of a catalyst and a hydrogen-donating solvent, active hydrogen combines with the free radicals to stabilize the free radicals by hydrogenation, generating low-molecular-weight gases, water, oil, asphaltene and other products, and at the same time, it can also remove some heteroatoms such as nitrogen, oxygen, and sulfur.
[0003] However, there are many factors affecting the direct coal liquefaction performance. It is of great significance to explore the influence of each influencing factor on the direct coal liquefaction performance. For example, some experimental parameters such as reaction conditions have certain commonalities in their influence on the direct coal liquefaction performance, but there are differences in the liquefaction reactivity of different coal types. Therefore, if we explore the influence of each factor on the direct coal liquefaction performance, it will consume a large amount of time cost, and if we consider the influence of more factors on the direct coal liquefaction performance, the time consumed will increase exponentially.
[0004] Therefore, how to provide an effective, accurate, and rapid method for evaluating the direct coal liquefaction performance of a reaction kettle has become an urgent problem to be solved. Summary of the Invention
[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a method for evaluating the direct coal liquefaction performance, a storage medium, and an electronic device. By constructing a target evaluation model, it is possible to quickly, effectively, and accurately evaluate the direct coal liquefaction performance using a variety of influencing factors within a short time, which plays a guiding role in the regulation of direct coal liquefaction experiments.
[0006] The technical solution of the present invention provides a method for evaluating the direct coal liquefaction performance, including:
[0007] Obtaining real-time influence factor information that determines the direct coal liquefaction performance, where the real-time influence factor information includes coal factor information, catalyst factor information, hydrogen-donating solvent factor information, and reaction condition factor information;
[0008] Inputting the real-time influence factor information into a preset target evaluation model to obtain a liquefaction performance evaluation index, where the liquefaction performance evaluation index includes conversion rate, oil yield, water yield, gas yield, hydrogen consumption, and asphaltene yield;
[0009] Determine the direct coal liquefaction performance according to the liquefaction performance evaluation index.
[0010] In one alternative technical solution, the target evaluation model is determined by the following method:
[0011] Obtain historical influence factor information;
[0012] Divide the historical influence factor information into a training set and a test set;
[0013] Use the linear regression algorithm, random forest algorithm, light gradient boosting algorithm, and extreme gradient boosting algorithm to train the training set, and construct corresponding linear regression training models, random forest training models, light gradient boosting training models, and extreme gradient boosting training models;
[0014] Use the test set to test the linear regression training model, the random forest training model, the light gradient boosting training model, and the extreme gradient boosting training model to obtain a linear regression model, a random forest model, a light gradient boosting model, and an extreme gradient boosting model;
[0015] Evaluate the model fitting performance of the linear regression model, the random forest model, the light gradient boosting model, and the extreme gradient boosting model to determine the target evaluation model.
[0016] In one alternative technical solution, after using the test set to test the linear regression training model, the random forest training model, the light gradient boosting training model, and the extreme gradient boosting training model to obtain a linear regression model, a random forest model, a light gradient boosting model, and an extreme gradient boosting model, it further includes:
[0017] Use the grid search method and cross-validation method to optimize the model parameters of the linear regression model, the random forest model, the light gradient boosting model, and the extreme gradient boosting model respectively.
[0018] In one alternative technical solution, evaluating the model fitting performance of the linear regression model, the random forest model, the light gradient boosting model, and the extreme gradient boosting model to determine the target evaluation model includes:
[0019] Use the coefficient of determination, mean square error, root mean square error, and mean absolute error to evaluate the model fitting performance of the linear regression model, the random forest model, the light gradient boosting model, and the extreme gradient boosting model;
[0020] Determine the model corresponding to the largest judgment coefficient and the minimum mean square error, root mean square error, and mean absolute error as the target evaluation model.
[0021] In one alternative technical solution, the real-time impact factor information is determined by the following method:
[0022] Arrange and combine the historical impact factor information in ascending order to obtain a historical information set;
[0023] Input the historical information set into the linear regression model, random forest model, light gradient boosting model, or extreme gradient boosting model respectively to obtain the importance ranking and Shapley value of the historical information set;
[0024] Determine the real-time impact factor information according to the importance ranking and the Shapley value.
[0025] In one alternative technical solution, the division of the historical impact factor information into a training set and a test set includes:
[0026] Divide the historical impact factor information into the training set and the test set according to 8:2.
[0027] In one alternative technical solution, after obtaining the determined real-time impact factor information that affects the direct coal liquefaction performance, it further includes:
[0028] Process the real-time impact factor information using the deletion method and the interpolation method to obtain sub-target impact factor information;
[0029] Perform one-hot encoding and sequence encoding on the qualitative variables in the sub-target impact factor information to obtain target impact factor information, where the qualitative variables are the classification information in the sub-target impact factor information.
[0030] In one alternative technical solution, the coal factor information includes proximate analysis, ultimate analysis, ash composition analysis, and maceral analysis, the catalyst factor information includes catalyst, catalyst addition amount, promoter, promoter sulfur, catalyst type, and sulfur-iron molar ratio, the hydrogen-donating solvent factor information includes hydrogen-donating solvent, coal-solvent ratio, and solvent element composition, and the reaction condition factor information includes reaction temperature, reaction pressure, and constant temperature time.
[0031] The technical solution of the present invention also provides a computer-readable storage medium that stores computer instructions, and when a computer executes the computer instructions, it is used to execute all steps of the direct coal liquefaction performance evaluation method described above.
[0032] The technical solution of the present invention further provides an electronic device, including:
[0033] at least one processor; and,
[0034] a memory communicatively connected to the at least one processor; wherein,
[0035] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the coal direct liquefaction performance evaluation method as described above.
[0036] After adopting the above technical solution, the following beneficial effects are achieved: By obtaining the real-time influence factor information that determines the coal direct liquefaction performance, inputting the real-time influence factor information into a preset target evaluation model to obtain the liquefaction performance evaluation index, and determining the coal direct liquefaction performance according to the liquefaction performance evaluation index, it is possible to quickly, effectively, and accurately evaluate the coal direct liquefaction performance using multiple influencing factors within a short time, which plays a guiding role in the regulation of coal direct liquefaction experiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Referring to the drawings, the disclosure of the present invention will become easier to understand. It should be understood that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In the drawings:
[0038] Figure 1 is a flowchart of a method for evaluating the coal direct liquefaction performance provided by an embodiment of the present invention;
[0039] Figure 2 is a flowchart of a method for evaluating the coal direct liquefaction performance provided by another embodiment of the present invention;
[0040] Figure 3 is a schematic hardware structure diagram of an electronic device for evaluating the coal direct liquefaction performance provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0041] The following further describes the specific embodiments of the present invention with reference to the drawings.
[0042] It is easy to understand that according to the technical solution of the present invention, under the condition of not changing the essence of the present invention, those of ordinary skill in the art can use various structural ways and implementation ways that can be mutually replaced. Therefore, the following specific embodiments and the drawings are only illustrative descriptions of the technical solution of the present invention, and should not be regarded as the whole of the present invention or as a limitation or restriction on the technical solution of the invention.
[0043] In this specification, orientation terms such as up, down, left, right, front, back, front side, back side, top, bottom, etc., which are mentioned or may be mentioned, are defined relative to the structures shown in the respective drawings. They are relative concepts and may therefore change accordingly depending on their different positions and usage states. Therefore, these or other orientation terms should not be construed as restrictive terms.
[0044] This application is mainly applied to the direct liquefaction of coal in a reactor, such as Figure 1 As shown, a method for evaluating the direct liquefaction performance of coal provided by an embodiment of the present invention includes:
[0045] Step S101: Obtain real-time influence factor information that determines the direct liquefaction performance of coal. The real-time influence factor information includes coal factor information, catalyst factor information, hydrogen-donating solvent factor information, and reaction condition factor information;
[0046] Step S102: Input the real-time influence factor information into a preset target evaluation model to obtain liquefaction performance evaluation indicators. The liquefaction performance evaluation indicators include conversion rate, oil yield, water yield, gas yield, hydrogen consumption, and asphaltene yield;
[0047] Step S103: Determine the direct liquefaction performance of coal according to the liquefaction performance evaluation indicators.
[0048] Specifically, when the direct liquefaction of coal is carried out in a reactor and the direct liquefaction performance of coal needs to be evaluated, the controller executes Step S101 to obtain real-time influence factor information. The real-time influence factor information refers to the factors that affect the direct liquefaction performance of coal during the direct liquefaction reaction process. The real-time influence factor information includes coal factor information, catalyst factor information, hydrogen-donating solvent factor information, and reaction condition factor information; then executes Step S102 to input the real-time influence factor information into a preset target evaluation model to obtain liquefaction performance evaluation indicators. The target evaluation model is trained by using linear regression algorithm, random forest method, light gradient boosting algorithm, and extreme gradient boosting algorithm; finally executes Step S103 to determine the direct liquefaction performance of coal according to the liquefaction performance evaluation indicators. For example, the higher the conversion rate, oil yield, water yield, gas yield, and asphaltene yield, and the lower the hydrogen consumption, the better the direct liquefaction performance of coal, thus realizing a rapid, effective, and accurate evaluation of the direct liquefaction performance of coal, and at the same time providing a guiding role for the regulation of the direct liquefaction experiment through the liquefaction performance evaluation indicators.
[0049] In this embodiment, by obtaining the real-time influencing factor information that determines the direct coal liquefaction performance, inputting the real-time influencing factor information into a preset target evaluation model to obtain a liquefaction performance evaluation index, and determining the direct coal liquefaction performance according to the liquefaction performance evaluation index, it is possible to quickly, effectively, and accurately evaluate the direct coal liquefaction performance with multiple influencing factors in a short time, which plays a guiding role in the regulation of direct coal liquefaction experiments.
[0050] In one embodiment, after step S101, it further includes:
[0051] Processing the real-time influencing factor information by deletion method and interpolation method to obtain sub-target influencing factor information;
[0052] Performing one-hot encoding and sequence encoding on the qualitative variables in the sub-target influencing factor information to obtain target influencing factor information, where the qualitative variable is the classification information in the sub-target influencing factor information.
[0053] Specifically, preprocessing the missing, repeated, and abnormal real-time influencing factor information by deletion method and interpolation method to obtain more accurate influencing factor information, and then using one-hot encoding to convert n real-time influencing factor information and d variables of different categories into d binary variables, which formally looks like an n-row d-column boolean matrix (a matrix with all elements being 0 or 1), and using sequence encoding to assign a unique integer value to each category in the qualitative variable, so as to realize the encoding of qualitative variables for the real-time influencing factor information, which is convenient for the target evaluation model to identify. The qualitative variables include catalyst, promoter, sulfur additive, catalyst type, and hydrogen-donating solvent.
[0054] In one embodiment, the coal factor information includes proximate analysis, ultimate analysis, ash composition analysis, and maceral analysis, the catalyst factor information includes catalyst, catalyst addition amount, promoter, sulfur additive, catalyst type, and sulfur-iron molar ratio, the hydrogen-donating solvent factor information includes hydrogen-donating solvent, coal-solvent ratio, and solvent element composition, and the reaction condition factor information includes reaction temperature, reaction pressure, and isothermal time.
[0055] Based on the above embodiment, as Figure 2 shown, another embodiment of the present invention provides a method for evaluating the direct coal liquefaction performance, including:
[0056] Step S201: Obtain historical influencing factor information;
[0057] Step S202: Divide the historical influencing factor information into a training set and a test set;
[0058] Step S203: Use the linear regression algorithm, random forest algorithm, light gradient boosting algorithm, and extreme gradient boosting algorithm to train the training set, and construct the corresponding linear regression training model, random forest training model, light gradient boosting training model, and extreme gradient boosting training model;
[0059] Step S204: Use the test set to test the linear regression training model, random forest training model, light gradient boosting training model, and extreme gradient boosting training model to obtain the linear regression model, random forest model, light gradient boosting model, and extreme gradient boosting model;
[0060] Step S205: Use the coefficient of determination, mean squared error, root mean squared error, and mean absolute error to evaluate the model fitting performance of the linear regression model, random forest model, light gradient boosting model, and extreme gradient boosting model;
[0061] Step S206: Determine the model with the largest coefficient of determination and the smallest mean squared error, root mean squared error, and mean absolute error as the target evaluation model;
[0062] Step S207: Obtain real-time impact factor information;
[0063] Step S208: Input the real-time impact factor information into the target evaluation model to obtain the liquefaction performance evaluation index;
[0064] Step S209: Determine the direct coal liquefaction performance according to the liquefaction performance evaluation index.
[0065] Specifically, when it is necessary to evaluate the direct coal liquefaction performance, the controller executes steps S201 - S204 to construct a linear regression model (MLR), random forest model (RF), light gradient boosting model (LightGBM), and extreme gradient boosting model (XGBoost). As shown in Table 1 below, the training and validation results of different models for the training set and test set (only one combination of influencing factors).
[0066] Table 1 Training and validation results of different models on the training set and test set
[0067]
[0068]
[0069] Then, the controller executes steps S205 - S206 to compare the coefficient of determination (R 2 ), mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) of different models to evaluate the model fitting performance, where R 2The result is between 0 and 1. The closer the result is to 1, the better the fitting performance of the model. Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) etc. represent the error between the predicted value and the true value. The smaller this value is, the better the fitting performance of the model. The model with the largest determination coefficient and the smallest mean squared error, root mean squared error, and mean absolute error is determined as the target evaluation model.
[0070] Finally, steps S207 - S209 are executed to determine the direct coal liquefaction performance, so as to realize a rapid, effective, and accurate evaluation of the direct coal liquefaction performance. At the same time, the liquefaction performance evaluation index plays a guiding role in the regulation of the direct coal liquefaction experiment.
[0071] In this embodiment, by constructing a target evaluation model, a rapid, effective, and accurate evaluation of the direct coal liquefaction performance using multiple influencing factors within a short time is realized, which plays a guiding role in the regulation of the direct coal liquefaction experiment.
[0072] In one of the embodiments, after step S204, it further includes:
[0073] Using the grid search method and the cross - validation method to optimize the model parameters of the linear regression model, random forest model, light gradient boosting model, and extreme gradient boosting model respectively.
[0074] Specifically, the grid search method systematically traverses all possible combinations of the set parameters to find the best parameter combination; the cross - validation method divides the training set data into five parts (five - fold), and each part takes turns as the validation set, while the other four parts are used for training to ensure the model performance and improve the generalization ability of the model in actual applications.
[0075] In one of the embodiments, the real - time impact factor information is determined by the following method:
[0076] Arrange and combine the historical impact factor information in ascending order to obtain a historical information set;
[0077] Input the historical information set into the linear regression model, random forest model, light gradient boosting model, or extreme gradient boosting model respectively to obtain the importance ranking and Shapley values of the historical information set;
[0078] Determine the real - time impact factor information according to the importance ranking and Shapley values.
[0079] Specifically, the historical impact factor information is analyzed using the contribution degree analysis method to determine the impact factor information. Specifically: variable importance analysis and Shapley additive explanation are respectively used. Variable importance analysis can obtain the order of the contribution degree of impact factors to the liquefaction performance, understand which impact factors have the greatest contribution degree to the liquefaction performance, and which impact factors have a very small contribution degree to the liquefaction performance; Shapley additive explanation assigns a data to the contribution of each impact factor in the model to the direct coal liquefaction performance, so as to understand how each impact factor affects the evaluation index of the direct coal liquefaction performance, and then judge and adjust the priority of the impact factors affecting the direct coal liquefaction performance of the reactor to determine the impact factor information.
[0080] In one embodiment, to improve the accuracy of the target evaluation model, step S202 includes:
[0081] The historical impact factor information is divided into a training set and a test set according to 8:2.
[0082] The following is an example to illustrate the evaluation of the direct liquefaction performance of the reactor under different reaction conditions. The catalyst is selected as Fe 2 O 3 , the hydrogen-donating solvent is tetralin, the catalyst addition amount is 3%, n S :n Fe is 2, the coal dissolution ratio is 3, and the above-mentioned direct coal liquefaction performance evaluation method is used to obtain the evaluation results shown in Table 2 below.
[0083] Table 2 Coal direct liquefaction evaluation results under different experimental parameters
[0084]
[0085]
[0086] An embodiment of the present invention provides a computer-readable storage medium, which is used to store computer instructions. When the computer executes the computer instructions, it is used to execute all steps of the direct coal liquefaction performance evaluation method in any of the above method embodiments.
[0087] As Figure 3 shown, a schematic hardware structure diagram of an electronic device for evaluating the direct coal liquefaction performance provided by an embodiment of the present invention includes:
[0088] At least one processor 301; and,
[0089] A memory 302 communicatively connected to at least one processor 301; wherein,
[0090] The memory 302 stores instructions executable by at least one processor 301. The instructions are executed by at least one processor 301 to enable at least one processor 301 to execute the coal direct liquefaction performance evaluation method in any of the foregoing method embodiments.
[0091] Figure 3 Taking one processor 301 as an example.
[0092] The electronic device is preferably a coal direct liquefaction performance evaluation controller.
[0093] The electronic device may further include: an input device 303 and an output device 304.
[0094] The processor 301, the memory 302, the input device 303, and the output device 304 may be connected through a bus or other means. In the figure, connection through a bus is taken as an example.
[0095] As a non-volatile computer-readable storage medium, the memory 302 can be used to obtain non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the coal direct liquefaction performance evaluation method in the embodiments of the present application. For example, Figure 1 - Figure 2 The method flow shown. The processor 301 executes various functional applications and information processing by running and obtaining the non-volatile software programs, instructions, and modules in the memory 302, that is, implementing the coal direct liquefaction performance evaluation method in the above embodiments.
[0096] The memory 302 may include an acquisition program area and an acquisition information area. Among them, the acquisition program area can acquire an operating system and application programs required for at least one function; the acquisition information area can acquire information created according to the use of the coal direct liquefaction performance evaluation method, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 302 may optionally include a memory remotely set relative to the processor 301, and these remote memories can be connected to the device for executing the coal direct liquefaction performance evaluation method through a network. Examples of the above networks include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.
[0097] The input device 303 can receive input user clicks and generate signal inputs related to user settings and function controls of the coal direct liquefaction performance evaluation method. The output device 304 may include a display device such as a display screen.
[0098] In the one or more modules, obtain the method for evaluating the performance of direct coal liquefaction in any of the above method embodiments when run by the one or more processors 301 in the memory 302.
[0099] The above product can execute the method provided in the embodiments of the present application, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided in the embodiments of the present application.
[0100] The above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them; although the embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for evaluating the performance of direct coal liquefaction, characterized in that: include: Acquire the determined real-time influencing factor information affecting the direct coal liquefaction performance, wherein the real-time influencing factor information includes coal factor information, catalyst factor information, hydrogen supply solvent factor information and reaction condition factor information; Inputting the real-time influencing factor information into a preset target evaluation model to obtain liquefaction performance evaluation indicators, wherein the liquefaction performance evaluation indicators include conversion rate, oil yield, water yield, gas yield, hydrogen consumption and asphaltene yield; The direct liquefaction performance of coal is determined according to the liquefaction performance evaluation index.
2. The method for evaluating the performance of direct coal liquefaction according to claim 1, characterized in that: The target evaluation model is determined by the following method: Get historical impact factor information; Dividing the historical impact factor information into a training set and a test set; The training set is trained using a linear regression algorithm, a random forest algorithm, a light gradient boosting algorithm, and an extreme gradient boosting algorithm to construct corresponding linear regression training models, random forest training models, light gradient boosting training models, and extreme gradient boosting training models; Using the test set to test the linear regression training model, the random forest training model, the mild gradient boosting training model and the extreme gradient boosting training model, to obtain a linear regression model, a random forest model, a mild gradient boosting model and an extreme gradient boosting model; The linear regression model, the random forest model, the mild gradient boosting model and the extreme gradient boosting model are evaluated for model fitting performance to determine the target evaluation model.
3. The method for evaluating the performance of direct coal liquefaction according to claim 2, characterized in that: The method further comprises: testing the linear regression training model, the random forest training model, the light gradient boosting training model and the extreme gradient boosting training model using the test set to obtain a linear regression model, a random forest model, a light gradient boosting model and an extreme gradient boosting model, and then: The linear regression model, the random forest model, the mild gradient boosting model and the extreme gradient boosting model are optimized by grid search and cross validation respectively.
4. The method for evaluating the performance of direct coal liquefaction according to claim 2, characterized in that: The performing model fitting performance evaluation on the linear regression model, the random forest model, the mild gradient boosting model and the extreme gradient boosting model to determine the target evaluation model includes: The linear regression model, the random forest model, the mild gradient boosting model and the extreme gradient boosting model are evaluated for model fitting performance using the determination coefficient, mean square error, root mean square error and mean absolute error; The model with the largest judgment coefficient and the smallest mean square error, root mean square error and mean absolute error is determined as the target evaluation model.
5. The method for evaluating the performance of direct coal liquefaction according to claim 2, characterized in that: The real-time impact factor information is determined by the following method: Arrange and combine the historical impact factor information in order from least to most to obtain a historical information set; Inputting the historical information set into the linear regression model, the random forest model, the mild gradient boosting model or the extreme gradient boosting model respectively to obtain the importance ranking and Shapley value of the historical information set; The real-time impact factor information is determined according to the importance ranking and the Shapley value.
6. The method for evaluating the performance of direct coal liquefaction according to claim 2, characterized in that: The dividing the historical impact factor information into a training set and a test set includes: The historical impact factor information is divided into the training set and the test set according to an 8:2 ratio.
7. The method for evaluating the performance of direct coal liquefaction according to claim 1, characterized in that: The step of obtaining and determining the real-time influencing factor information affecting the direct coal liquefaction performance further includes: The real-time impact factor information is processed by using a deletion method and an interpolation method to obtain sub-goal impact factor information; The qualitative variables in the sub-target influencing factor information are subjected to one-hot encoding and sequence encoding to obtain the target influencing factor information, wherein the qualitative variables are the classification information in the sub-target influencing factor information.
8. The method for evaluating the performance of direct coal liquefaction according to any one of claims 1 to 7, characterized in that: The coal factor information includes industrial analysis, elemental analysis, ash composition analysis and microscopic component analysis; the catalyst factor information includes catalyst, catalyst addition amount, promoter, promoter sulfur, catalyst type and sulfur-iron molar ratio; the hydrogen supply solvent factor information includes hydrogen supply solvent, coal dissolution ratio and solvent element composition; the reaction condition factor information includes reaction temperature, reaction pressure and constant temperature time.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when a computer executes the computer instructions, it is used to execute all steps of the coal direct liquefaction performance evaluation method as described in any one of claims 1-8.
10. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the coal direct liquefaction performance evaluation method as described in any one of claims 1-8.