Method and apparatus for predicting hydrogen content in refined wax oil

Abstract

The application provides a method and device for predicting hydrogen content in refined wax oil. The method comprises: obtaining relevant raw material parameters and operation parameters of a raw material wax oil sample; comparing the raw material parameters with a preset range, determining raw material wax oil samples within the preset range as in-range samples, and determining raw material wax oil samples outside the preset range as out-of-range samples; in the case that the raw material wax oil sample is determined as an in-range sample, inputting the raw material parameters and operation parameters into a wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw material wax oil sample; and in the case that the raw material wax oil sample is determined as an out-of-range sample, predicting the refined wax oil hydrogen content of the raw material wax oil sample according to the raw material parameter input and a hydrogen atom material balance function. In this way, the extrapolation and extension of the data model are taken into account, and in the case that the amount of modeling data is small, the problem of large prediction error of the data model for out-of-range samples is solved.

Description

Technical Field

[0001] This application relates to the chemical industry, specifically to a method and apparatus for predicting the hydrogen content in refined wax oil, and a machine-readable storage medium. Background Technology

[0002] There are many ways for refineries to save energy and reduce carbon emissions, including water conservation, electricity conservation, gas / steam conservation, and air conservation. Among these, reducing hydrogen consumption has become a key focus for refinery managers. Hydrogen consumption primarily originates from chemical reactions; therefore, from the perspective of reducing carbon emissions at the source of chemical reactions, the efficient utilization of hydrogen has become an important energy-saving and carbon-reduction measure.

[0003] Wax oil hydrotreating, as an important feedstock pretreatment process, plays a significant role in improving feedstock parameters for catalytic cracking or hydrocracking. The main reactions involving hydrogen in wax oil hydrotreating include hydrodesulfurization, hydrodenitrogenation, hydrodeoxygenation, and olefin and aromatic saturation, all of which occur on different catalysts. Establishing a pilot-scale evaluation model for the catalyst and, based on the scale-up effect, roughly estimating the hydrogen consumption of actual industrial production units is undoubtedly an effective tool for addressing this issue. Summary of the Invention

[0004] The inventors of this application discovered that, due to the limited amount of pilot-scale evaluation data for catalysts, established data models (e.g., wax oil hydrogen content prediction models) are prone to exhibiting good interpolation results but poor extrapolation results. Therefore, it is crucial to adopt different methods to ensure the predictive performance of the model based on the characteristics of the novel test dataset. This invention divides the value ranges of relevant raw material parameters for the wax oil samples and designs separate prediction schemes for samples within and outside the boundary. This significantly improves the predictive performance of the data model for samples outside the boundary, even with limited modeling data.

[0005] To achieve the above objectives, a first aspect of this application provides a method for predicting the hydrogen content in refined wax oil, comprising: acquiring relevant raw material parameters of a raw material wax oil sample and operating parameters applied to the raw material wax oil sample for preparing refined wax oil; comparing the raw material parameters with a preset range, identifying raw material wax oil samples within the preset range as in-range samples, and identifying raw material wax oil samples outside the preset range as out-of-range samples; when a raw material wax oil sample is identified as an in-range sample, inputting the raw material parameters and operating parameters into a wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw material wax oil sample; and when a raw material wax oil sample is identified as an out-of-range sample, predicting the refined wax oil hydrogen content of the raw material wax oil sample based on the raw material parameters and a hydrogen atom material balance function.

[0006] In the embodiments of this application,

[0007]

[0008] In this embodiment of the application, the preset range is based on the range of raw material parameters of the raw material wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

[0009] In this embodiment, the hydrogen atom material balance function includes a functional relationship expression and corresponding constraints.

[0010] In this embodiment of the application, the functional relationship expression is:

[0011]

[0012] Wherein, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil; N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil; δ(H) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation, and deoxide treatment; 32 represents the atomic weight of sulfur removed, 12 represents the atomic weight equivalent to hydrogenation of sulfides; 14 represents the atomic weight of nitrogen removed, and 7 represents the atomic weight equivalent to hydrogenation of nitrides.

[0013] In this embodiment, the initial assumption is that δ(H) is zero. The hydrogen content H2% of the refined wax oil is calculated using the aforementioned functional relationship expression. If the hydrogen content H2% of the refined wax oil does not meet the following constraints, a correction term δ(H) is determined according to these constraints. This correction term δ(H) is then substituted into the aforementioned functional relationship expression, and the hydrogen content H2% of the refined wax oil is recalculated as a prediction of the hydrogen content of the refined wax oil.

[0014] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0015]

[0016] In the embodiments of this application, the raw material parameters include one or more of the following: density, distillation range, S content, N content, carbon content, and hydrogen content.

[0017] In the embodiments of this application, the operating parameters include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio.

[0018] A second aspect of this application provides an apparatus for predicting the hydrogen content in refined wax oil, the apparatus comprising: a memory; and a processor configured to predict the hydrogen content in refined wax oil using the method described above.

[0019] A third aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the method described above for predicting the hydrogen content in refined wax oil.

[0020] A fourth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, causes the processor to perform the above-described method for predicting the hydrogen content in refined wax oil.

[0021] The above technical solution establishes a new standard for dividing test samples into in-boundary and out-of-boundary test samples in the test dataset. If the raw material wax oil sample to be predicted is an in-boundary test sample, the trained model's prediction result is used directly. If the raw material wax oil sample to be predicted is an out-of-boundary test sample, a newly designed hydrogen atom material balance function is used for calculation, replacing the model's test result. This approach balances the extrapolation and internalization of the data model, solving the problem of large prediction errors for out-of-boundary samples when the amount of modeling data is relatively small.

[0022] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0024] Figure 1 The schematic diagram illustrates a process flow diagram of a method for predicting the hydrogen content in refined wax oil according to an embodiment of this application.

[0025] Figure 2 The schematic diagram illustrates a process flow diagram of a method for predicting the hydrogen content in refined wax oil according to another embodiment of this application.

[0026] Figure 3 This is a comparison chart showing the predicted and measured values ​​of out-of-bounds samples in the new test dataset.

[0027] Figure 4 This is a comparison chart of the calculated and measured values ​​of samples outside the boundary of the new test dataset in an embodiment of this application. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0029] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0030] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0031] It should be noted that the terms "feature," "feature variable," and "input parameter" appear repeatedly in this case. These terms can refer to the characteristics of a "data prediction model" used to predict "output parameters" based on "input parameters," and are used interchangeably. Additionally, the terms "model," "data prediction model," and "data-driven model" appear repeatedly in this case; these terms are also used interchangeably.

[0032] Figure 1 A schematic flowchart illustrating a method for predicting the hydrogen content in refined wax oil according to an embodiment of this application is shown. Figure 1 As shown in one embodiment of this application, a method for predicting the hydrogen content in refined wax oil is provided, the method comprising the following steps:

[0033] Step S110: Obtain relevant raw material parameters of the raw material wax oil sample and operating parameters applied to the raw material wax oil sample for preparing refined wax oil.

[0034] The feedstock parameters here may include one or more of the following: density, distillation range, sulfur content, nitrogen content, carbon content, and hydrogen content. The operating parameters may include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio. Of course, the invention is not limited to these parameters and may include other feedstock and operating parameters besides those listed herein.

[0035] Step S120: Compare the raw material parameters with a preset range, determine the raw material wax oil samples within the preset range as in-boundary samples, and determine the raw material wax oil samples outside the preset range as out-of-boundary samples.

[0036] The preset range can be determined based on the range of raw material parameters of the raw material wax oil sample used in the modeling process of the wax oil hydrogen content prediction model. For example, the preset range should be within the range of raw material parameters of the raw material wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

[0037] Specifically, a raw material wax oil sample is considered an in-boundary sample only if all raw material parameters are within the preset range corresponding to those parameters; otherwise, it is considered an out-of-boundary sample. This determination is expressed as follows:

[0038]

[0039] Step S130: If the raw material wax oil sample is determined to be within the acceptable range, the raw material parameters and operating parameters are input into the wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw material wax oil sample. The process of establishing this wax oil hydrogen content prediction model will be described later.

[0040] Step S140: If the raw material wax oil sample is determined to be an out-of-bounds sample, predict the hydrogen content of the refined wax oil in the raw material wax oil sample based on the raw material parameters and the hydrogen atom material balance function.

[0041] Figure 1 This is a flowchart illustrating a feature selection method for a data prediction model in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0042] The above technical solution establishes a new standard for dividing test samples into in-boundary and out-of-boundary test samples in the test dataset. If the raw material wax oil sample to be predicted is an in-boundary test sample, the trained model's prediction result is used directly. If the raw material wax oil sample to be predicted is an out-of-boundary test sample, a newly designed hydrogen atom material balance function is used for calculation, replacing the model's test result. This approach balances the extrapolation and internalization of the data model, solving the problem of large prediction errors for out-of-boundary samples when the amount of modeling data is relatively small.

[0043] Figure 2 A schematic flowchart illustrating a method for predicting the hydrogen content in refined wax oil according to another embodiment of this application is shown. Figure 2 As shown, its general content is similar to Figure 1 It simply reflects the specific form of the hydrogen atom material balance function.

[0044] Specifically, the hydrogen atom material balance function includes a functional relationship expression and corresponding constraints, wherein the functional relationship expression is:

[0045]

[0046] Wherein, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil; N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil; δ(H) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation, and deoxide treatment; 32 represents the atomic weight of sulfur removed, 12 represents the atomic weight equivalent to hydrogenation of sulfides; 14 represents the atomic weight of nitrogen removed, and 7 represents the atomic weight equivalent to hydrogenation of nitrides. The sulfur content of the refined wax oil represented by S2% and the nitrogen content of the refined wax oil represented by N2% can be predicted using corresponding refined wax oil sulfur and nitrogen content prediction models, or they can be obtained through other methods. These refined wax oil sulfur and nitrogen content prediction models can be modeled similarly to the wax oil hydrogen content prediction model.

[0047] In the initial prediction of the hydrogen content of the refined wax oil sample, δ(H) can be assumed to be zero. The hydrogen content H2% of the refined wax oil is calculated using the aforementioned functional relationship expression. If the hydrogen content H2% of the refined wax oil does not meet the following constraints, a correction term δ(H) is determined according to the following constraints. This correction term δ(H) is then substituted into the aforementioned functional relationship expression, and the hydrogen content H2% of the refined wax oil is recalculated to serve as the final predicted hydrogen content of the refined wax oil.

[0048] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0049]

[0050] Of course, specific functional expressions and constraints, as well as the numerical ranges of these constraints, are given here. Appropriate modifications of these functional expressions and constraints should also be considered within the scope of protection of this case.

[0051] This invention addresses the shortcomings of small-data models, which exhibit ideal interpolation results but poor extrapolation results on novel test data. It proposes a new method to overcome the poor extrapolation effect of small-data models. The first step involves collecting pilot-scale evaluation data of a catalyst for the hydrogenation of wax oil to establish a data-driven model. The second step determines the value ranges of each parameter of the raw materials used as modeling inputs. The third step involves classifying the parameter value ranges of the novel test dataset. Samples within the range of the modeling data are considered in-range samples; those outside the range are considered out-of-range samples. The fourth step involves designing a hydrogen content function for refined wax oil. The fifth step involves using the model for prediction if the new test dataset is classified as an in-range sample; otherwise, the function is used for calculation.

[0052] For data models, when faced with entirely new test data, users desire both good interpolation performance and good extension. Models built from small datasets typically offer some interpolation performance but have poor extension capabilities. By dividing the new test dataset into in-bound and out-of-bounds samples and designing different solutions, the practical application of small-data models becomes possible.

[0053] This invention uses the Keras deep learning architecture to build the model. Keras is a deep learning framework for building models and a high-level neural network application programming interface written in Python. It consists of a series of independent, fully configurable modules that can be assembled according to actual needs. In particular, neural network layers, loss functions, optimizers, initialization methods, activation functions, and regularization methods are all modules that can be combined to build the model.

[0054] When building the model, Python was used to write the model code, and the Keras deep learning framework was used to build the model. Model training requires calling the input and output features and data from Excel. The input features are mainly divided into two parts: raw material parameters and operating parameters. Raw material parameters include: raw material density, sulfur content, nitrogen content, carbon content, hydrogen content, and boiling range (IBP, 10%, 30%, ..., FBP), etc. Operating parameters include: reaction temperature, reaction pressure, space velocity, and hydrogen-to-oil ratio. The output parameter is the hydrogen content of the refined wax oil. If a model for predicting the sulfur and nitrogen content of refined wax oil is established, the output parameter can be the corresponding sulfur and nitrogen content of the refined wax oil.

[0055] The features and data corresponding to the input and output are cleaned, ensuring a one-to-one correspondence between them. These are then organized into separate Excel spreadsheets for easy reading by the algorithm. All data is randomly divided into training, validation, and test sets in an 8:1:1 ratio. The training set is used for model training, the validation set for hyperparameter optimization, and the test set for evaluating the model's prediction performance. The evaluation metrics for the model are Mean Absolute Error (MAE), Mean Relative Error (MRE), and Coefficient of Determination (R²). 2 The relevant statistical parameters required to build the model are as follows, where,

[0056]

[0057]

[0058]

[0059] In the above formula, n is the number of samples in the test set, and y i,actual y represents the measured value of the sample. i,predicted Represents the sample predicted value. MAE reflects the degree to which all sample predicted values ​​deviate from the true value, while MRE reflects the reliability of all sample prediction results. R 2 It reflects how well the model's predicted values ​​fit the actual values.

[0060] If the new test data is determined to be within the bounds, the trained model is used to predict the new test data; if the new test data is determined to be outside the bounds, a newly designed function calculation method is used.

[0061] The present invention will be further described in detail below with examples, but the present invention is not limited thereto.

[0062] (1) Collected pilot-scale catalyst evaluation data for wax oil hydrogenation were organized and divided into input and output data. Input data included: feed parameters (density, distillation range, S content, N content, etc.) and operating parameters (reaction pressure, reaction temperature, space velocity, hydrogen-to-oil ratio); output data was the hydrogen content of refined wax oil.

[0063] (2) All data are divided into two parts. One part is used for modeling. The modeling dataset is divided into a training set, a validation set, and a test set in an 8:1:1 ratio. The training set is used to train the model, the validation set is used to determine the hyperparameters of the model, and the test set is used to test the model's performance. The other part of the dataset is used to create a new test dataset. This dataset is used to compare the hydrogen content of refined wax oil determined in the embodiments of this invention with the hydrogen content of refined wax oil predicted by the model in the comparative examples.

[0064] (3) Using Python to write a program, build a deep learning framework, and establish a prediction model M1 for the sulfur content of hydrogenated wax oil.

[0065] (4) Rules for determining the range of raw material parameters in the new test dataset. If the range of a certain parameter is within the range of the raw material parameters in the modeling data, it is determined to be an in-bound sample (all parameters must meet the requirements); if the new test data is outside the range of the raw material parameters in the modeling data, it is determined to be an out-of-bounds sample.

[0066] (5) Calculate the value range of each parameter of the raw materials in all modeling datasets. These parameters include raw material density, sulfur content, nitrogen content, distillation range, etc. Let Ci be the value range of the i-th parameter among the raw material parameters. (min) ≤Ci≤Ci (max) The minimum value is Ci (min) The maximum value is Ci (max) .

[0067] (6) Divide the new dataset to be tested into inbound samples and outbound samples. Suppose that the value of a certain parameter in the raw material parameters of the new dataset to be tested is Ci′, and the corresponding discriminant expression for inbound and outbound samples is as shown in Equation (1).

[0068]

[0069] (7) If an array in the new test dataset is identified as an inbound sample, then use model M1 to make a prediction directly;

[0070] (8) If an array in the new test dataset is identified as an out-of-bounds sample, then design an implementation example and a comparative example.

[0071] (9) For the example, a method for calculating the hydrogen content of hydrogenated wax oil in the sample outside the boundary was designed. The design of the calculation function relationship of hydrogen content is based on the hydrogen balance calculation from raw materials to products. The sulfur, nitrogen, oxygen and other impurities removed during the reaction are converted into hydrogen removal. The hydrogenation part of aromatic saturation and olefin saturation is converted into hydrogen addition. According to the hydrogen element material balance, the newly designed function expression is as shown in equation (2).

[0072]

[0073] Wherein, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil product, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil product (e.g., the sulfur content predicted by a refined wax oil sulfur content prediction model); N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil product (e.g., the nitrogen content predicted by a refined wax oil nitrogen content prediction model); δ(H) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation, and deoxides; 32 represents the atomic weight of sulfur removed, 12 represents the atomic weight equivalent to hydrogenation of sulfides; 14 represents the atomic weight of nitrogen removed, and 7 represents the atomic weight equivalent to hydrogenation of nitrides.

[0074] (10) For the embodiment, the standard for the value of δ(H) is set. According to process experience, the increase in hydrogen consumption is within a certain range. If the result of the function relationship calculation is outside the range, δ(H) should be introduced as a correction term. The corresponding constraints and the value of δ(H) are as follows: If the result of the function relationship calculation is within the range, then δ(H) is equivalent to an infinitesimal (e.g., 0), as detailed in Equation (3).

[0075] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0076]

[0077] Before applying the constraints, δ(H) is taken as an equivalent infinitesimal (e.g., 0), and H2% is calculated based on this and the above function (2). Then, H2% and H1% are substituted into the above constraints (3) to redetermine δ(H). Based on the redetermined δ(H) and the above function (2), H2% is recalculated and used as the predicted hydrogen content in the refined wax oil product.

[0078] (11) The method of the embodiment calculates the value of hydrogen content of refined wax oil using a new out-of-bounds sample function relationship expression. The difference between this value and the measured value is as follows: Figure 3 As shown. The comparative method uses model M1 to predict out-of-bounds samples, and the difference between the predicted and measured values ​​is shown in the figure. Figure 2As shown, the hydrogen content of refined wax oil calculated by the newly designed function expression is compared with the hydrogen content of refined wax oil predicted by model M1 in the comparative example.

[0079] To compare the differences in prediction performance between the examples and comparative examples on the new test array, the measured values, the predicted values ​​of the comparative examples, the calculated values ​​of the examples, the differences between the comparative and measured values, and the differences between the examples and the measured values ​​are listed in Table 1. Detailed results are shown in Table 1, where difference 1 represents the difference between the predicted value and the measured value of the comparative examples, and difference 2 represents the difference between the calculated value and the measured value of the examples. The comparison revealed that for the new out-of-bounds samples, the newly designed function expression's calculated value for the hydrogen content of refined wax oil in the new test array is significantly closer to the measured value, with a deviation within 0.1%, demonstrating the effectiveness of the method in the examples.

[0080] Table 1 Comparison of prediction performance of the new test array between the examples and the comparative examples.

[0081]

[0082]

[0083] Comparison revealed that the newly defined functional expression for the hydrogen content of refined wax oil in the embodiments significantly reduced the prediction error of out-of-bounds samples compared to the model in the comparative embodiment, fully demonstrating the effectiveness of the method.

[0084] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0086] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0088] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0089] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0090] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0091] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0092] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting the hydrogen content in refined wax oil, comprising: Obtain the relevant raw material parameters of the raw material wax oil sample and the operating parameters applied to the raw material wax oil sample for preparing refined wax oil; The raw material parameters are compared with a preset range. Raw material wax oil samples within the preset range are identified as in-boundary samples, and raw material wax oil samples outside the preset range are identified as out-of-boundary samples. When the raw material wax oil sample is determined to be an in-boundary sample, the raw material parameters and operating parameters are input into the wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw material wax oil sample. as well as If the raw material wax oil sample is determined to be an out-of-bounds sample, the hydrogen content of the refined wax oil from the raw material wax oil sample is predicted based on the raw material parameters and the hydrogen atom material balance function. The hydrogen atom material balance function includes a functional relationship expression and corresponding constraints. The functional relationship expression is as follows: in, H1% This indicates the hydrogen content in the raw material wax oil. H2% Indicates the hydrogen content in refined wax oil. S1% This indicates the sulfur content in the raw material wax oil. S2% Indicates the sulfur content of refined wax oil; N1% This indicates the nitrogen content in the raw material wax oil. N2% Indicates the nitrogen content of refined wax oil; δ ( H ) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation, and deoxide treatment; 32 represents the atomic weight of sulfur removal, 12 represents the atomic weight of sulfide hydrogenation; 14 represents the atomic weight of nitrogen removal, and 7 represents the atomic weight of nitride hydrogenation. Among them, the initial assumptions δ ( H If the hydrogen content of the refined wax oil is zero, the hydrogen content can be calculated using the aforementioned functional relationship expression. H2% The hydrogen content of this refined wax oil H2% If the following constraints are not met, determine the correction term δ(H) based on the following constraints, and then apply this correction term... δ ( H Substitute the above functional relationship expression and recalculate the hydrogen content of the refined wax oil. H2% To be used as a predictor of the hydrogen content of refined wax oil, 2. The method according to claim 1, wherein, 3. The method according to claim 1, wherein, The preset range is based on the range of raw material parameters of the raw material wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

4. The method according to any one of claims 1-3, wherein, The raw material parameters include one or more of the following: density, distillation range, sulfur content, nitrogen content, carbon content, and hydrogen content.

5. The method according to any one of claims 1-3, wherein, The operating parameters include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio.

6. An apparatus for predicting the hydrogen content in refined wax oil, characterized in that, The device includes: Memory; and A processor configured to perform the method for predicting the hydrogen content in refined wax oil according to any one of claims 1-5.

7. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform a method for predicting the hydrogen content in refined wax oil according to any one of claims 1 to 5.

Images