Gasoline octane number prediction method, device, medium and electronic equipment

Abstract

The present disclosure relates to a gasoline octane number prediction method, device, medium and electronic device. The method comprises: determining the molecular composition characteristic information of the gasoline to be predicted, the molecular composition characteristic information includes the independent octane value contribution information of each molecule in the gasoline to be predicted, and the mixed octane value contribution information of every two molecules in the gasoline to be predicted; inputting the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain the target gasoline octane value of the gasoline to be predicted output by the gasoline octane number prediction model, and the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane values ​​between the molecules in the gasoline. Through the above scheme, the octane value of the gasoline to be predicted is predicted by the gasoline octane number prediction model, and the interaction and mutual influence of the molecular octane values ​​between different molecules are considered, so that the predicted gasoline octane value can be made more accurate, and the accuracy of the target gasoline octane value is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of gasoline technology, and in particular to a gasoline octane number prediction method, device, medium and electronic equipment. Background Art

[0002] Gasoline octane number is a numerical indicator that measures the ability of gasoline to resist knocking combustion in the cylinder. The higher the gasoline octane number, the better the gasoline's anti-knock performance and the higher the gasoline quality. In the gasoline blending process, octane number prediction is a major difficulty. The method of predicting gasoline octane number in related technologies is mainly based on the macroscopic properties of the component oils, such as the boiling point and density of the component oils. However, the versatility of this prediction method is poor and the prediction results are not accurate enough. Summary of the invention

[0003] The purpose of the present disclosure is to provide a gasoline octane number prediction method, device, medium and electronic equipment, which can make the predicted gasoline octane number more accurate.

[0004] In order to achieve the above-mentioned purpose, in a first aspect, the present disclosure provides a gasoline octane number prediction method, the method comprising: determining molecular composition characteristic information of the gasoline to be predicted, wherein the molecular composition characteristic information comprises independent octane value contribution information of each molecule in the gasoline to be predicted, and mixed octane value contribution information of every two molecules in the gasoline to be predicted, the independent octane value contribution information is used to characterize the contribution information of the molecule to the gasoline octane number of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions; inputting the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain a target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane values ​​between the molecules in the gasoline.

[0005] Optionally, determining the molecular composition characteristic information of the gasoline to be predicted includes: obtaining the mass fraction and molecular octane number of each molecule in the gasoline to be predicted; and determining the molecular composition characteristic information of the gasoline to be predicted according to the mass fraction and the molecular octane number of each molecule.

[0006] Optionally, determining the molecular composition characteristic information of the gasoline to be predicted based on the mass fraction and the molecular octane number of each molecule includes: for each molecule in the gasoline to be predicted, determining the independent octane value contribution information of the molecule based on the mass fraction and the molecular octane number of the molecule; for every two different molecules in the gasoline to be predicted, determining the mixed octane value contribution information of the two molecules based on the independent octane value contribution information of the two molecules; determining the molecular composition characteristic information of the gasoline to be predicted based on the independent octane value contribution information and the mixed octane value contribution information.

[0007] Optionally, determining the independent octane value contribution information of the molecule according to the mass fraction of the molecule and the molecular octane number includes: taking the product of the mass fraction of the molecule and the molecular octane number as the independent octane value contribution information of the molecule.

[0008] Optionally, determining the mixed octane value contribution information of the two molecules according to the independent octane value contribution information of the two molecules includes: taking the sum of the independent octane value contribution information of the two molecules as the mixed octane value contribution information of the two molecules.

[0009] Optionally, the gasoline octane number prediction model is a convolutional neural network model; the gasoline octane number prediction model is trained in the following manner: obtaining molecular composition feature information of training sample gasoline; inputting the molecular composition feature information of the training sample gasoline into the convolutional neural network model to obtain a first gasoline octane number of the training sample gasoline output by the convolutional neural network model; training the convolutional neural network model according to difference information between the first gasoline octane number and a pre-labeled second gasoline octane number of the training sample gasoline; and obtaining the gasoline octane number prediction model in response to completion of model training.

[0010] Optionally, the gasoline octane number prediction model is a convolutional neural network model, which includes an input layer, a convolutional layer, a pooling layer and an output layer, wherein the input layer is used to receive the molecular composition feature information of the gasoline to be predicted, the convolutional layer is used to perform convolution calculations, the pooling layer is used to perform maximum pooling, and the output layer includes a fully connected neural network layer for outputting a target gasoline octane number of the gasoline to be predicted.

[0011] In a second aspect, the present disclosure provides a gasoline octane number prediction device, the device comprising: a determination module, used to determine molecular composition characteristic information of the gasoline to be predicted, wherein the molecular composition characteristic information includes independent octane value contribution information of each molecule in the gasoline to be predicted, and mixed octane value contribution information of every two molecules in the gasoline to be predicted, the independent octane value contribution information is used to characterize the contribution information of the molecules to the gasoline octane number of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions; a first input module, used to input the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain the target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane values ​​between the molecules in the gasoline.

[0012] Optionally, the determination module includes: an acquisition submodule, used to obtain the mass fraction and molecular octane number of each molecule in the gasoline to be predicted; and a first determination submodule, used to determine the molecular composition characteristic information of the gasoline to be predicted based on the mass fraction and the molecular octane number of each molecule.

[0013] Optionally, the first determination submodule includes: a second determination submodule, used to determine, for each molecule in the gasoline to be predicted, the independent octane value contribution information of the molecule according to the mass fraction of the molecule and the molecular octane number; a third determination submodule, used to determine, for each two different molecules in the gasoline to be predicted, the mixed octane value contribution information of the two molecules according to the independent octane value contribution information of the two molecules; and a fourth determination submodule, used to determine the molecular composition characteristic information of the gasoline to be predicted according to the independent octane value contribution information and the mixed octane value contribution information.

[0014] Optionally, the second determination submodule is used to: use the product of the mass fraction of the molecule and the octane number of the molecule as the independent octane number contribution information of the molecule.

[0015] Optionally, the third determination submodule is used to: use the sum of the independent octane value contribution information of the two molecules as the mixed octane value contribution information of the two molecules.

[0016] Optionally, the gasoline octane number prediction model is a convolutional neural network model; the gasoline octane number prediction model is obtained by training a gasoline octane number prediction model training device, and the gasoline octane number prediction model training device includes: an acquisition module, used to obtain molecular composition feature information of training sample gasoline; a second input module, used to input the molecular composition feature information of the training sample gasoline into the convolutional neural network model to obtain the first gasoline octane number of the training sample gasoline output by the convolutional neural network model; a training module, used to train the convolutional neural network model according to the difference information between the first gasoline octane number and the second gasoline octane number of the training sample gasoline marked in advance; a model acquisition module, used to obtain the gasoline octane number prediction model in response to the completion of model training.

[0017] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present disclosure.

[0018] In a fourth aspect, the present disclosure provides an electronic device, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the steps of the method provided in the first aspect of the present disclosure.

[0019] Through the above technical solution, the molecular composition characteristic information of the gasoline to be predicted is first determined, and the molecular composition characteristic information may include the independent octane value contribution information of each molecule in the gasoline to be predicted, and the mixed octane value contribution information of every two molecules in the gasoline to be predicted. Then, the molecular composition characteristic information is input into the pre-trained gasoline octane value prediction model to obtain the target gasoline octane value of the gasoline to be predicted output by the model, wherein the parameters in the gasoline octane value prediction model are used to reflect the interaction information of the molecular octane values ​​between the molecules in the gasoline. In this way, since the molecular octanes of different molecules have certain interactions, the octane value of the gasoline to be predicted is predicted through the gasoline octane value prediction model, and the interaction and mutual influence of the molecular octanes between the molecules are considered, so that the predicted gasoline octane value can be made more accurate, the accuracy of the target gasoline octane value is improved, and the accurate basis for gasoline blending is improved.

[0020] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0022] Figure 1The figure is a flow chart of a gasoline octane number prediction method according to an exemplary embodiment.

[0023] Figure 2 The present invention is a flowchart of a method for determining characteristic information of molecular composition of gasoline to be predicted according to an exemplary embodiment.

[0024] Figure 3 The present invention is a flow chart showing a method for determining molecular composition characteristic information of gasoline to be predicted according to the mass fraction and molecular octane number of each molecule according to an exemplary embodiment.

[0025] Figure 4 is a schematic diagram showing molecular composition characteristic information according to an exemplary embodiment.

[0026] Figure 5 The present invention is a flowchart of a method for training a gasoline octane number prediction model according to an exemplary embodiment.

[0027] Figure 6 The figure is a block diagram of a gasoline octane number prediction device according to an exemplary embodiment.

[0028] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment.

[0029] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0030] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0031] Figure 1 is a flowchart of a gasoline octane number prediction method according to an exemplary embodiment. The method can be applied to an electronic device with processing capabilities, such as a terminal or a server. Figure 1 As shown, the method may include S101 and S102.

[0032] In S101, the molecular composition characteristic information of the gasoline to be predicted is determined.

[0033] In S102, the molecular composition characteristic information of the gasoline to be predicted is input into a pre-trained gasoline octane number prediction model to obtain a target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model.

[0034] Among them, the gasoline to be predicted can be gasoline for which octane number prediction is required. The method of predicting gasoline octane number in the related art is mainly based on the macroscopic properties of the component oil, such as the boiling point, density and other information of the component oil. However, since there may be many kinds of compositions corresponding to the macroscopic properties, and the octane number is closely related to the composition of gasoline, the versatility of this prediction method is poor. In addition, the gasoline octane number prediction model in the related art usually adopts the traditional parameter regression method to regress the parameters of a specific expression. Due to the limitation of the computing power of this method, the parameters set in the model cannot be too many, otherwise the training will not converge easily. Therefore, this model usually only considers the interaction between molecular types, and ignores the interaction between molecules. The molecular types mainly include alkanes, cycloalkanes, aromatics, etc., and the molecular types defined by the model are also relatively small, and the scalability is general.

[0035] In the present disclosure, when predicting the octane number of gasoline to be predicted, the molecular composition characteristic information of the gasoline to be predicted is first determined, and the molecular composition characteristic information may include the independent octane value contribution information of each molecule in the gasoline to be predicted, and the mixed octane value contribution information of every two molecules in the gasoline to be predicted. The independent octane value contribution information can be used to characterize the contribution information of the molecule to the gasoline octane value of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions.

[0036] Gasoline usually contains hundreds of molecules, such as benzene, cyclohexane, 1-pentene, n-butane, etc. The molecules of gasoline can also be represented in a lumped form, such as the lumping of carbon 10 aromatics. The octane numbers of each molecule have certain interactions, and the gasoline octane number cannot be calculated simply by adding up the contributions of each molecule to the gasoline octane number. In the present disclosure, after determining the molecular composition feature information of the gasoline to be predicted, the molecular composition feature information can be input into a pre-trained gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane numbers between the molecules in the gasoline. For example, the gasoline octane number prediction model can be a convolutional neural network model, and the gasoline octane number prediction model can be calculated according to the molecular composition feature information, and output the target gasoline octane number of the gasoline to be predicted. In this way, the octane number of the gasoline to be predicted is predicted by the gasoline octane number prediction model, and the interaction and mutual influence of the molecular octane numbers between the molecules are considered, so that the predicted gasoline octane number can be made more accurate.

[0037] Through the above technical solution, the molecular composition characteristic information of the gasoline to be predicted is first determined, and the molecular composition characteristic information may include the independent octane value contribution information of each molecule in the gasoline to be predicted, and the mixed octane value contribution information of every two molecules in the gasoline to be predicted. Then, the molecular composition characteristic information is input into the pre-trained gasoline octane value prediction model to obtain the target gasoline octane value of the gasoline to be predicted output by the model, wherein the parameters in the gasoline octane value prediction model are used to reflect the interaction information of the molecular octane values ​​between the molecules in the gasoline. In this way, since the molecular octanes of different molecules have certain interactions, the octane value of the gasoline to be predicted is predicted through the gasoline octane value prediction model, and the interaction and mutual influence of the molecular octanes between the molecules are considered, so that the predicted gasoline octane value can be made more accurate, the accuracy of the target gasoline octane value is improved, and the accurate basis for gasoline blending is improved.

[0038] Figure 2 is a flow chart showing a method for determining molecular composition characteristic information of gasoline to be predicted according to an exemplary embodiment. Figure 2 As shown, the above S101 may include S201 and S202.

[0039] In S201, the mass fraction and molecular octane number of each molecule in the gasoline to be predicted are obtained.

[0040] The molecular composition of the gasoline to be predicted may be the molecular composition data analyzed by an instrument or the molecular composition calculation data of a process kinetic model. The mass fraction of the molecule represents the ratio of the mass of the molecule to the total mass of the gasoline to be predicted. The molecular octane number of the molecule may be a pre-tested test value.

[0041] Since gasoline contains many molecules, usually hundreds of molecules, for the sake of illustration, gasoline contains four molecules, namely, n-butane, 1-pentene, cyclohexane, and benzene. It is worth noting that this example is only for explanation and does not constitute a limitation on the embodiments of the present disclosure. For example, the mass fraction of n-butane is 0.1, and the molecular octane number of n-butane is 94; the mass fraction of 1-pentene is 0.2, and the molecular octane number of 1-pentene is 90.9; the mass fraction of cyclohexane is 0.3, and the molecular octane number of cyclohexane is 83; the mass fraction of benzene is 0.4, and the molecular octane number of benzene is 101.

[0042] In S202, the molecular composition characteristic information of the gasoline to be predicted is determined according to the mass fraction and molecular octane number of each molecule.

[0043] For example, the implementation of step S202 may be as follows: Figure 3 As shown, including S2021 to S2023.

[0044] In S2021, for each molecule in the gasoline to be predicted, independent octane value contribution information of the molecule is determined according to the mass fraction and molecular octane value of the molecule.

[0045] The independent octane value contribution information is used to characterize the contribution information of the molecule to the gasoline octane value of the predicted gasoline under ideal conditions. According to the mass fraction and molecular octane value of the molecule, an exemplary implementation method for determining the independent octane value contribution information of the molecule can be: taking the product of the mass fraction and the molecular octane value of the molecule as the independent octane value contribution information of the molecule. Continuing with the above example, the independent octane value contribution information of n-butane can be 9.4, the independent octane value contribution information of 1-pentene can be 18.18, the independent octane value contribution information of cyclohexane can be 24.9, and the independent octane value contribution information of benzene can be 40.4.

[0046] In S2022, for every two different molecules in the gasoline to be predicted, the mixed octane number contribution information of the two molecules is determined according to the independent octane number contribution information of the two molecules.

[0047] An exemplary implementation of determining the mixed octane value contribution information of each two molecules may be: taking the sum of the independent octane value contribution information of the two molecules as the mixed octane value contribution information of the two molecules. Continuing with the above example, for example, the mixed octane value contribution information of n-butane and 1-pentene may be 27.58, and the mixed octane value contribution information of n-butane and cyclohexane may be 34.3.

[0048] In S2023, the molecular composition characteristic information of the gasoline to be predicted is determined according to the independent octane number contribution information and the mixed octane number contribution information.

[0049] For example, a data set consisting of independent octane number contribution information and mixed octane number contribution information may be used as molecular composition characteristic information of gasoline to be predicted.

[0050] Through the above technical solution, the independent octane value contribution information of each molecule in the gasoline to be predicted and the mixed octane value contribution information of every two molecules are determined, and the molecular composition characteristic information of the gasoline to be predicted is determined based on the independent octane value contribution information and the mixed octane value contribution information.

[0051] In an optional embodiment, the molecular composition characteristic information can be represented in the form of a two-dimensional matrix. The following describes an exemplary embodiment of determining the molecular composition characteristic information when the molecular composition characteristic information is represented in the form of a two-dimensional matrix. The rows and columns of the two-dimensional matrix are composed of all molecules contained in gasoline, and the arrangement order of the rows and columns of the matrix is ​​consistent. For example, the arrangement order of the molecules can be set by a technician, or the molecules can be sorted from large to small according to their boiling points.

[0052] Take the example of gasoline which contains four molecules: n-butane, 1-pentene, cyclohexane, and benzene. Figure 4 is a schematic diagram showing a molecular composition characteristic information according to an exemplary embodiment. Figure 4 As shown, the molecular composition characteristic information is represented by a two-dimensional matrix, and the arrangement order of the molecules in the rows and columns of the matrix is ​​consistent. The calculation method of the element value of the i-th row and j-th column in the matrix is ​​shown in the following formula (1):

[0053]

[0054] Where i represents the i-th row in the molecular composition feature information, j represents the j-th column in the molecular composition feature information, and E ij Represents the element value of the i-th row and j-th column in the molecular composition feature information, C i represents the mass fraction of the molecules corresponding to the i-th row, R i represents the molecular octane number of the molecule corresponding to the i-th row, C i* R i Indicates the independent octane number contribution information of the molecule corresponding to the i-th row, C j represents the mass fraction of molecules corresponding to the jth column, R j represents the molecular octane number of the molecule corresponding to the jth column, C j* R j Represents the independent octane number contribution information of the molecule corresponding to the jth column.

[0055] like Figure 4 As shown, taking the 1st row and the 1st column as an example, the element value of the 1st row and the 1st column in the matrix is ​​the independent octane number contribution information of benzene. Taking the 1st row and the 2nd column as an example, the molecule corresponding to the 1st row is benzene, and the molecule corresponding to the 2nd column is n-butane, then the element value of the 1st row and the 2nd column in the matrix is ​​the sum of the independent octane number contribution information of benzene and the independent octane number contribution information of n-butane.

[0056] Through the above scheme, the molecular composition characteristic information can be represented in the form of a two-dimensional matrix. The element values ​​in the matrix can include the independent octane value contribution information of each molecule and the mixed octane value contribution information of every two molecules. In this way, the molecular composition characteristic information in the form of a matrix of the gasoline to be predicted can be constructed.

[0057] In the related art, the gasoline octane number prediction model usually adopts the traditional parameter regression method to regress the parameters of a specific expression. The computing power of this model is limited, the parameters set in the model are generally small, and the interaction between gasoline molecules is usually not considered. In the present disclosure, the gasoline octane number prediction model can be a convolutional neural network model. The convolutional neural network is a deep learning method with stronger computing power and good effect on training models with large amounts of data and large amounts of parameters. Therefore, by selecting a convolutional neural network to train the gasoline octane number prediction model, more molecules can be defined and the interaction between the molecular octanes between molecules can be considered.

[0058] Figure 5 is a flow chart of a gasoline octane number prediction model training method according to an exemplary embodiment. Figure 5 As shown, the method may include S501 to S504.

[0059] In S501, molecular composition feature information of training sample gasoline is obtained.

[0060] The training sample gasoline may be a sample gasoline with an octane number marked, and the molecular composition feature information of the training sample gasoline may be determined based on the mass fraction and molecular octane number of each molecule in the training sample gasoline, including the independent octane value contribution information of each molecule in the training sample gasoline and the mixed octane value contribution information of every two molecules in the training sample gasoline. The molecular composition feature information of the training sample gasoline may also be represented in the form of a two-dimensional matrix.

[0061] It is worth noting that the present disclosure does not impose any specific limitation on the number of training sample gasolines, which can be multiple, and the molecular composition characteristic information of each training sample gasoline can be obtained separately.

[0062] In S502, the molecular composition characteristic information of the training sample gasoline is input into the convolutional neural network model to obtain the first gasoline octane number of the training sample gasoline output by the convolutional neural network model.

[0063] If there are multiple training sample gasolines, the molecular composition characteristic information of each of the multiple training sample gasolines can be simultaneously input into the convolutional neural network model to obtain the first gasoline octane number of each training sample gasoline output by the convolutional neural network model. The first gasoline octane number is the octane number of the training sample gasoline predicted by the convolutional neural network model.

[0064] In S503, the convolutional neural network model is trained according to the difference information between the first gasoline octane number and the second gasoline octane number of the pre-labeled training sample gasoline.

[0065] Among them, the parameters of the convolutional neural network model can be updated according to the difference information between the first gasoline octane number of the training sample gasoline output by the convolutional neural network model and the second gasoline octane number of the pre-labeled training sample gasoline, for example, by using the gradient descent method to update the parameters of the model to train the convolutional neural network model.

[0066] In S504, in response to the model training being completed, a gasoline octane number prediction model is obtained.

[0067] For example, the test set can be used to verify whether the model training is complete. If the average absolute error of the model prediction results is less than the preset error threshold, it can be indicated that the model training is complete, that is, a trained gasoline octane number prediction model is obtained. The parameters in the trained gasoline octane number prediction model can be used to reflect the interaction information of the molecular octane numbers between the molecules in gasoline.

[0068] For example, the gasoline octane number prediction model may include an input layer, a convolutional layer, a pooling layer and an output layer. When the gasoline octane number of the gasoline to be predicted is predicted, the input layer can be used to receive the molecular composition feature information of the gasoline to be predicted, the convolutional layer can be used to perform convolution calculation, and the pooling layer can be used to perform maximum pooling. In one embodiment, the convolutional layer and the pooling layer each have four layers, and alternately appear in the network structure, the number of convolution kernels of the four convolutional layers is, for example, 16, 32, 64, and 128, respectively, the convolution kernel size is 4, the step length is 1, the activation function is Relu, the pooling size of the pooling layer is, for example, 2, the step length is 2, the data is flattened after passing through the last pooling layer, and then proceeds to the output layer. The output layer may include a fully connected neural network layer for outputting the target gasoline octane number of the gasoline to be predicted.

[0069] Based on the same inventive concept, the present disclosure also provides a gasoline octane number prediction device. Figure 6 is a block diagram of a gasoline octane number prediction device according to an exemplary embodiment. Figure 6 As shown, the device may include:

[0070] A determination module 601 is used to determine the molecular composition characteristic information of the gasoline to be predicted, wherein the molecular composition characteristic information includes the independent octane value contribution information of each molecule in the gasoline to be predicted and the mixed octane value contribution information of every two molecules in the gasoline to be predicted, the independent octane value contribution information is used to characterize the contribution information of the molecule to the gasoline octane value of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions;

[0071] The first input module 602 is used to input the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain the target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane numbers between the molecules in the gasoline.

[0072] Optionally, the determination module 601 includes: an acquisition submodule, used to obtain the mass fraction and molecular octane number of each molecule in the gasoline to be predicted; and a first determination submodule, used to determine the molecular composition characteristic information of the gasoline to be predicted based on the mass fraction and the molecular octane number of each molecule.

[0073] Optionally, the first determination submodule includes: a second determination submodule, used to determine, for each molecule in the gasoline to be predicted, the independent octane value contribution information of the molecule according to the mass fraction of the molecule and the molecular octane number; a third determination submodule, used to determine, for each two different molecules in the gasoline to be predicted, the mixed octane value contribution information of the two molecules according to the independent octane value contribution information of the two molecules; and a fourth determination submodule, used to determine the molecular composition characteristic information of the gasoline to be predicted according to the independent octane value contribution information and the mixed octane value contribution information.

[0074] Optionally, the second determination submodule is used to: use the product of the mass fraction of the molecule and the octane number of the molecule as the independent octane number contribution information of the molecule.

[0075] Optionally, the third determination submodule is used to: use the sum of the independent octane value contribution information of the two molecules as the mixed octane value contribution information of the two molecules.

[0076] Optionally, the gasoline octane number prediction model is a convolutional neural network model; the gasoline octane number prediction model is obtained by training a gasoline octane number prediction model training device, and the gasoline octane number prediction model training device includes: an acquisition module, used to obtain molecular composition feature information of training sample gasoline; a second input module, used to input the molecular composition feature information of the training sample gasoline into the convolutional neural network model to obtain the first gasoline octane number of the training sample gasoline output by the convolutional neural network model; a training module, used to train the convolutional neural network model according to the difference information between the first gasoline octane number and the second gasoline octane number of the training sample gasoline marked in advance; a model acquisition module, used to obtain the gasoline octane number prediction model in response to the completion of model training.

[0077] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0078] Figure 7 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0079] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the gasoline octane number prediction method described above. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0080] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned gasoline octane number prediction method.

[0081] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the gasoline octane number prediction method described above are implemented. For example, the computer-readable storage medium may be the memory 702 including the program instructions, and the program instructions may be executed by the processor 701 of the electronic device 700 to complete the gasoline octane number prediction method described above.

[0082] Figure 8 1 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 8 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing a computer program executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processor 1922 may be configured to execute the computer program to perform the above-mentioned gasoline octane number prediction method.

[0083] In addition, the electronic device 1900 may further include a power supply component 1926 and a communication component 1950. The power supply component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to implement communication of the electronic device 1900, for example, wired or wireless communication. In addition, the electronic device 1900 may further include an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM , Linux TM etc.

[0084] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the gasoline octane number prediction method described above are implemented. For example, the computer-readable storage medium may be the memory 1932 including the program instructions, and the program instructions may be executed by the processor 1922 of the electronic device 1900 to complete the gasoline octane number prediction method described above.

[0085] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above gasoline octane number prediction method when executed by the programmable device.

[0086] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0087] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0088] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A gasoline octane number prediction method, characterized in that: The method comprises: Determine the molecular composition characteristic information of the gasoline to be predicted, wherein the molecular composition characteristic information includes the independent octane value contribution information of each molecule in the gasoline to be predicted and the mixed octane value contribution information of every two molecules in the gasoline to be predicted, the independent octane value contribution information is used to characterize the contribution information of the molecule to the gasoline octane value of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions; Inputting the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain a target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane numbers between molecules in gasoline, and the gasoline octane number prediction model is a convolutional neural network model; Wherein, the determining of the molecular composition characteristic information of the gasoline to be predicted includes: Obtaining the mass fraction and molecular octane number of each molecule in the gasoline to be predicted; Determining the molecular composition characteristic information of the gasoline to be predicted according to the mass fraction and the molecular octane number of each molecule; Wherein, determining the molecular composition characteristic information of the gasoline to be predicted according to the mass fraction and the molecular octane number of each molecule includes: For each of the molecules in the gasoline to be predicted, determining independent octane number contribution information of the molecule according to the mass fraction of the molecule and the molecular octane number; For every two different molecules in the gasoline to be predicted, determining the mixed octane number contribution information of the two molecules according to the independent octane number contribution information of the two molecules; Determining the molecular composition characteristic information of the gasoline to be predicted according to the independent octane number contribution information and the mixed octane number contribution information; Wherein, determining the independent octane number contribution information of the molecule according to the mass fraction and the molecular octane number of the molecule includes: Taking the product of the mass fraction of the molecule and the octane number of the molecule as the independent octane number contribution information of the molecule; Wherein, determining the mixed octane number contribution information of the two molecules according to the independent octane number contribution information of the two molecules includes: The sum of the independent octane value contribution information of the two molecules is taken as the mixed octane value contribution information of the two molecules.

2. The method according to claim 1, characterized in that The gasoline octane number prediction model is trained in the following way: Obtaining molecular composition characteristic information of training sample gasoline; Inputting the molecular composition characteristic information of the training sample gasoline into a convolutional neural network model to obtain a first gasoline octane number of the training sample gasoline output by the convolutional neural network model; Training the convolutional neural network model according to difference information between the first gasoline octane number and a pre-labeled second gasoline octane number of the training sample gasoline; In response to the model training being completed, the gasoline octane number prediction model is obtained.

3. The method according to claim 1, characterized in that The gasoline octane number prediction model includes an input layer, a convolution layer, a pooling layer and an output layer, wherein the input layer is used to receive the molecular composition feature information of the gasoline to be predicted, the convolution layer is used to perform convolution calculation, the pooling layer is used to perform maximum pooling, and the output layer includes a fully connected neural network layer, which is used to output the target gasoline octane number of the gasoline to be predicted.

4. A gasoline octane number prediction device, characterized in that: The device comprises: A determination module, used to determine the molecular composition characteristic information of the gasoline to be predicted, wherein the molecular composition characteristic information includes the independent octane value contribution information of each molecule in the gasoline to be predicted and the mixed octane value contribution information of every two molecules in the gasoline to be predicted, the independent octane value contribution information is used to characterize the contribution information of the molecule to the gasoline octane value of the gasoline to be predicted under ideal conditions, and the mixed octane value contribution information is a linear mixture of the independent octane value contribution information of the two molecules under ideal conditions; a first input module, used for inputting the molecular composition characteristic information of the gasoline to be predicted into a pre-trained gasoline octane number prediction model to obtain a target gasoline octane number of the gasoline to be predicted output by the gasoline octane number prediction model, wherein the parameters in the gasoline octane number prediction model are used to reflect the interaction information of the molecular octane numbers between molecules in gasoline, and the gasoline octane number prediction model is a convolutional neural network model; The determination module includes: an acquisition submodule for acquiring the mass fraction and molecular octane number of each molecule in the gasoline to be predicted; a first determination submodule for determining the molecular composition characteristic information of the gasoline to be predicted according to the mass fraction and molecular octane number of each molecule; Wherein, the first determination submodule includes: a second determination submodule, for determining, for each molecule in the gasoline to be predicted, the independent octane value contribution information of the molecule according to the mass fraction of the molecule and the molecular octane value; a third determination submodule, for determining, for each two different molecules in the gasoline to be predicted, the mixed octane value contribution information of the two molecules according to the independent octane value contribution information of the two molecules; a fourth determination submodule, for determining the molecular composition characteristic information of the gasoline to be predicted according to the independent octane value contribution information and the mixed octane value contribution information; Wherein, the second determination submodule is used to: take the product of the mass fraction of the molecule and the octane number of the molecule as the independent octane number contribution information of the molecule; The third determination submodule is used to: take the sum of the independent octane value contribution information of the two molecules as the mixed octane value contribution information of the two molecules.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 3 are implemented.

6. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 3.

Images