Method and device for predicting penetration of blended asphalt

Abstract

The invention provides a blended asphalt penetration prediction method and device. The method comprises the following steps: determining a raw oil formula of blended asphalt; inputting the raw oil formula into the kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; determining the penetration of the blended asphalt based on the kinematic viscosity prediction result; wherein the kinematic viscosity prediction model is obtained by training based on a sample raw oil formula and corresponding sample kinematic viscosity. According to the blended asphalt penetration prediction method and device provided by the invention, the kinematic viscosity prediction result of the blended asphalt can be accurately obtained on the basis of the kinematic viscosity prediction model, so that the penetration of the blended asphalt can be accurately and quickly determined on the basis of the kinematic viscosity prediction result; and the problems of relatively large workload and relatively long period caused by experimental detection and analysis in a traditional method are avoided.

Description

Technical Field

[0001] The invention relates to the technical field of asphalt blending, and in particular to a method and device for predicting the needle penetration of blended asphalt. Background Art

[0002] The production of asphalt is limited by the properties of the processed crude oil, resulting in some deficiencies in the properties of the produced asphalt, making it difficult to ship out of the factory normally. A blending process is used to blend different raw oils to achieve a state that can be shipped out of the factory or used.

[0003] However, affected by the quality factors of the raw oil components, the performance penetration of the blended asphalt corresponding to different raw oil components is different. In order to ensure the performance of the blended asphalt, the penetration of the blended asphalt is currently determined through repeated experiments and tests, but the experimental test operation is difficult and time-consuming. Summary of the invention

[0004] The present invention provides a method and device for predicting the penetration of blended asphalt, which are used to solve the defects in the prior art that experimental detection of the penetration is difficult and time-consuming.

[0005] The present invention provides a method for predicting the penetration of blended asphalt, comprising:

[0006] Determine the raw oil formula for blending asphalt;

[0007] Inputting the feedstock oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model;

[0008] Determining the needle penetration of the blended asphalt based on the kinematic viscosity prediction result;

[0009] The kinematic viscosity prediction model is obtained based on sample crude oil formula and corresponding sample kinematic viscosity training.

[0010] According to a blended asphalt penetration prediction method provided by the present invention, the step of determining the sample crude oil formula comprises:

[0011] Blend various raw oils according to the current proportions and determine the current blending formula;

[0012] Based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determine whether to use the current blending formula as the current sample raw oil formula.

[0013] According to a method for predicting needle penetration of blended asphalt provided by the present invention, the method determines whether to use the current blending formula as the current sample crude oil formula based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample crude oil formula, including:

[0014] When the absolute value of the difference between the kinematic viscosity of the previous sample stock oil recipe and the kinematic viscosity of the current blending recipe is greater than a threshold value, the current blending recipe is used as the current sample stock oil recipe.

[0015] According to a method for predicting needle penetration of blended asphalt provided by the present invention, the method determines whether to use the current blending formula as the current sample crude oil formula based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample crude oil formula, including:

[0016] When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is less than or equal to a threshold value, the current blending formula is eliminated.

[0017] According to a blending asphalt penetration prediction method provided by the present invention, the step of determining whether to use the current blending formula as the current sample crude oil formula further includes:

[0018] The current ratio is updated, and the step of determining the sample crude oil formula is returned to be executed until the number of sample crude oil formulas reaches a preset number.

[0019] According to a method for predicting the penetration of blended asphalt provided by the present invention, the method for determining the penetration of the blended asphalt based on the kinematic viscosity prediction result comprises:

[0020] Based on the mapping relationship between needle penetration and kinematic viscosity, the kinematic viscosity prediction result is applied to determine the needle penetration of the blended asphalt.

[0021] The present invention also provides a blended asphalt penetration prediction device, comprising:

[0022] A formula determination unit, used to determine the raw oil formula for blending asphalt;

[0023] A first prediction unit, used for inputting the feedstock oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model;

[0024] A second prediction unit, used to determine the needle penetration of the blended asphalt based on the kinematic viscosity prediction result;

[0025] The kinematic viscosity prediction model is obtained based on sample crude oil formula and corresponding sample kinematic viscosity training.

[0026] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for predicting the needle penetration of blended asphalt as described above is implemented.

[0027] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the blended asphalt penetration prediction method described in any one of the above is implemented.

[0028] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting the penetration of blended asphalt.

[0029] The method and device for predicting the needle penetration of blended asphalt provided by the present invention can accurately obtain the prediction result of the kinematic viscosity of the blended asphalt based on the dynamic viscosity prediction model, so that the needle penetration of the blended asphalt can be accurately and quickly determined based on the kinematic viscosity prediction result, avoiding the problem of large workload and long cycle caused by experimental detection and analysis in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a schematic flow chart of the method for predicting the penetration of blended asphalt provided by the present invention;

[0032] Figure 2 It is a schematic flow chart of the kinematic viscosity prediction model training method provided by the present invention;

[0033] Figure 3 It is a schematic diagram of the structure of the blended asphalt penetration prediction device provided by the present invention;

[0034] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Affected by the quality factors of raw oil components, the performance penetration of blended asphalt corresponding to different raw oil components is different. In order to ensure the performance of blended asphalt, the penetration of blended asphalt is currently determined through repeated experiments and tests, but the experimental test operation is difficult and time-consuming.

[0037] To this end, the present invention provides a method for predicting the needle penetration of blended asphalt. Figure 1 : is a flow chart of the method for predicting the penetration of blended asphalt provided by the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0038] Step 110, determine the raw oil formula for blending asphalt.

[0039] Here, blended asphalt refers to the asphalt product that needs to be predicted for penetration. Generally, blended asphalt is obtained by mixing different raw materials in corresponding proportions. The raw material oil formula can be understood as the type of raw material oil and the proportion of each raw material oil. Among them, the raw material oil may include petroleum residue, softener, additives, solvents, etc.

[0040] Step 120, inputting the raw oil formula into the kinematic viscosity prediction model to obtain the kinematic viscosity prediction result output by the kinematic viscosity prediction model;

[0041] Among them, the kinematic viscosity prediction model is obtained based on the sample crude oil formula and the corresponding sample kinematic viscosity training.

[0042] Specifically, the kinematic viscosity prediction model is used to predict the kinematic viscosity of blended asphalt based on the raw oil formula to obtain a kinematic viscosity prediction result. Among them, the kinematic viscosity prediction model can be constructed based on a double logarithmic model, a Crago model, a support vector machine algorithm, a differential evolution algorithm, etc. Kinematic viscosity refers to the index value measured by the kinematic viscosity determination method of petroleum products specified in the standard.

[0043] Optionally, before the feedstock oil formula is input into the kinematic viscosity prediction model, the kinematic viscosity prediction model can be pre-trained, which can be achieved by performing the following steps: First, a large number of sample feedstock oil formulas are collected, and the sample kinematic viscosity of the asphalt product corresponding to the sample feedstock oil formula is determined by experimental measurement. Then, the initial model is trained based on the sample feedstock oil formula and the corresponding sample kinematic viscosity to obtain the kinematic viscosity prediction model. Among them, when measuring the sample kinematic viscosity of the asphalt product corresponding to the sample feedstock oil formula, the measurement temperature can be 50°C to 150°C, preferably 60°C.

[0044] Step 130: Determine the needle penetration of the blended asphalt based on the kinematic viscosity prediction result.

[0045] Specifically, the needle penetration index refers to the index value measured by the petroleum asphalt needle penetration test method specified in the standard.

[0046] The needle penetration is usually measured by mixing a conical or conical needle into the asphalt, and the value obtained by the needle penetration instrument used in the measurement process is small, which leads to the low accuracy of the measured needle penetration value.

[0047] In contrast, since kinematic viscosity can be obtained through a more direct fluid flow measurement method without relying on indirect measurement of the needle penetration instrument, the measured value of kinematic viscosity is larger than the measured value of needle penetration, and the experimental measurement accuracy is higher.

[0048] Therefore, in order to obtain more accurate needle penetration data, the embodiment of the present invention experimentally measures the kinematic viscosity of the asphalt product corresponding to the sample crude oil formula, and obtains a kinematic viscosity prediction model based on the measured sample kinematic viscosity and the sample crude oil formula training, and then the kinematic viscosity prediction model can accurately determine the kinematic viscosity prediction result of the blended asphalt.

[0049] On this basis, based on the mapping relationship between needle penetration and kinematic viscosity, a functional expression between needle penetration and kinematic viscosity can be established, and then on the basis of the kinematic viscosity prediction results, the needle penetration of blended asphalt can be accurately derived based on the functional expression.

[0050] The method for predicting the penetration of blended asphalt provided in an embodiment of the present invention is based on a dynamic viscosity prediction model and can accurately obtain a prediction result of the kinematic viscosity of the blended asphalt. Thus, based on the kinematic viscosity prediction result, the penetration of the blended asphalt can be accurately and quickly determined, thereby avoiding the problem of large workload and long cycle caused by experimental detection and analysis in traditional methods.

[0051] Based on the above embodiment, the steps of determining the sample feedstock oil formula include:

[0052] Blend various raw oils according to the current proportions and determine the current blending formula;

[0053] Based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample crude oil formula, determine whether to use the current blending formula as the current sample crude oil formula.

[0054] Specifically, the current ratio refers to the current proportion of each raw material oil when blending asphalt based on each raw material oil. It can be understood that the sum of the current proportions of each raw material oil is 1. Among them, the current ratio can be randomly generated or generated according to a preset rule, and the embodiment of the present invention does not specifically limit this.

[0055] In order to ensure the uniformity of the distribution of sample data used to train the kinematic viscosity prediction model, when obtaining the sample crude oil formula, it is necessary to compare the similarity between the current blending formula and the previous sample crude oil formula. If the similarity is small, it indicates that the sample data distribution is dense, which will affect the performance of the model.

[0056] In this regard, the embodiment of the present invention determines the similarity between the current blending formula and the previous sample raw oil formula based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula. When the similarity is greater than a threshold value, it indicates that the current blending formula is qualified, and the current blending formula can be used as the current sample raw oil formula. When the similarity is less than or equal to the threshold value, it indicates that the current blending formula is unqualified, and the current blending formula is not used as the current sample raw oil formula, that is, the current blending formula is eliminated and the next blending formula is regenerated. Among them, the kinematic viscosity can be determined by experimental measurement.

[0057] Based on any of the above embodiments, based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determining whether to use the current blending formula as the current sample raw oil formula includes:

[0058] When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is greater than a threshold value, the current blending formula is used as the current sample raw oil formula.

[0059] Specifically, if the absolute value of the difference between the kinematic viscosity of the previous sample crude oil formula and the kinematic viscosity of the current blending formula is greater than a threshold, it indicates that the current blending formula has a large degree of similarity with the previous sample crude oil formula and meets the sample data distribution uniformity requirement. Therefore, the current blending formula can be used as the current sample crude oil formula.

[0060] Based on any of the above embodiments, based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determining whether to use the current blending formula as the current sample raw oil formula includes:

[0061] When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is less than or equal to a threshold value, the current blending formula is eliminated.

[0062] Specifically, if the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is less than or equal to the threshold, it indicates that the current blending formula is less similar to the previous sample raw oil formula and does not meet the sample data distribution uniformity requirement. At this time, the current blending formula can be eliminated and the next blending formula is generated.

[0063] Based on any of the above embodiments, determining whether to use the current blending formula as the current sample raw oil formula further includes:

[0064] Update the current ratio and return to the step of determining the sample raw oil formula until the number of sample raw oil formulas reaches the preset number.

[0065] Specifically, after determining whether to use the current blending formula as the current sample crude oil formula, if the number of sample crude oil formulas does not reach the preset number, it is necessary to continue to obtain sample crude oil formulas, update the current ratio, and return to the step of determining the sample crude oil formula until the number of sample crude oil formulas reaches the preset number. The preset number can be determined based on the total number of crude oil types. For example, if the total number of crude oil types is n, the preset number can be 10*(n-1) 2 -n 2 .

[0066] Based on any of the above embodiments, the needle penetration of the blended asphalt is determined based on the kinematic viscosity prediction result, including:

[0067] Based on the mapping relationship between needle penetration and kinematic viscosity, the kinematic viscosity prediction results are used to determine the needle penetration of blended asphalt.

[0068] Specifically, since the penetration value is greatly affected by factors such as the precision of experimental measurement and the sensitivity of instrument detection, the experimental measurement accuracy is low. In contrast, since kinematic viscosity can be measured by a more precise experimental method, the experimental measurement accuracy is relatively high. Therefore, based on the mapping relationship between penetration and kinematic viscosity, and on the basis of the kinematic viscosity prediction results, the penetration of blended asphalt is accurately obtained.

[0069] Among them, the mapping relationship between needle penetration and kinematic viscosity can be obtained through experimental measurement, a large number of needle penetrations and corresponding kinematic viscosities are obtained, and through regression analysis and other methods, the relevant laws and mathematical models between the two are found to obtain the mapping relationship between the two, and then, based on the known kinematic viscosity prediction results, the needle penetration of the blended asphalt can be accurately obtained.

[0070] It should be noted that since the mapping relationship between needle penetration and kinematic viscosity is determined by a large number of needle penetrations and corresponding kinematic viscosities obtained through experiments, the error in the needle penetration value caused by factors such as the accuracy of experimental measurement and the sensitivity of instrument detection can be reduced, and the mapping relationship between needle penetration and kinematic viscosity can be accurately determined.

[0071] Based on any of the above embodiments, the present invention also provides a kinematic viscosity prediction model training method, such as Figure 2 As shown, the method includes:

[0072] S1. Obtain a plurality of raw oils and measure the kinematic viscosity of each raw oil.

[0073] S2. Randomly generate the current blending formula and predict the kinematic viscosity of the current blending formula.

[0074] S3. When the absolute value of the difference between the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula is greater than a threshold value, it indicates that the similarity between the two is low and the similarity requirement is met. The current blending formula is used as the current sample raw oil formula and added to the formula sample set. When the absolute value of the difference between the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula is less than or equal to a threshold value, it indicates that the two are highly similar and do not meet the similarity requirement. The current blending formula is regenerated and S2-S3 is repeated until the number of sample raw oil formulas in the formula sample set reaches a threshold value, and a kinematic viscosity prediction model is obtained based on the sample raw oil formulas in the formula sample set and the corresponding sample kinematic viscosity training.

[0075] Among them, the kinematic viscosity prediction model is used to predict the kinematic viscosity corresponding to the blended asphalt, so that the penetration degree can be accurately obtained based on the prediction results and the mapping relationship between the penetration degree and the kinematic viscosity.

[0076] The sample crude oil formula in the formula sample set can be determined based on the following steps:

[0077] S11. Measure the kinematic viscosity of n (n≥2) types of crude oil;

[0078] S12, blending the n raw oils in S11 to obtain m blending formulas, and measuring the kinematic viscosity Y of the i-th blending formula i The sample search step length (i.e., the absolute value of the difference between the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula) is controlled to satisfy:

[0079] |Y i -Y j |>Gap, 1≤i, j≤n

[0080] S13, after generating the i-th blending formula, starting from the first blending formula (j=1), the search step length of each blending formula and the newly generated i blending formula is checked in turn. If any search step length is less than the threshold (Gap), the blending formula is regenerated until the total number of sample crude oil formulas in the formula sample set reaches 10*(n-1) 2 until.

[0081] The following are relevant data and results of experimental verification using the method provided in an embodiment of the present invention. After analysis, it can be seen that the method provided in an embodiment of the present invention can not only accurately predict the needle penetration, but also greatly shorten the period of batch prediction of the needle penetration of blended asphalt (the prediction in the embodiment of the present invention requires about 1-2 days, while the period required by the traditional experimental detection method is generally 3-5 days).

[0082] The kinematic viscosity of the raw oil used for blending asphalt was tested and analyzed. The raw oils were specifically T1, T2, and T3, and their kinematic viscosities at 60°C were 41433 cSt, 21.97 cSt, and 1192 cSt, respectively.

[0083] Randomly generate initial blending formula samples and use the data model to predict the kinematic viscosity after mixing:

[0084] A blending formula 1 is randomly generated, with T1 accounting for 48%, T2 accounting for 33%, and T3 accounting for 19%; its kinematic viscosity is predicted to be 778.68 cSt.

[0085] A blending formula 2 is randomly generated, with T1 accounting for 45%, T2 accounting for 45%, and T3 accounting for 10%; its mixed viscosity is predicted to be 399.02 cSt.

[0086] Set the search step control parameters and create a sample set of kinematic viscosity and blending ratio formulas:

[0087] Set the threshold Gap = 50 and calculate |Y i -Y j |=|Y 1 -Y 2 |=379.66,where Y 1 Indicates the kinematic viscosity of blending formula 1, Y 2 It represents the kinematic viscosity of blending formula 2.

[0088] Because |Y 1 -Y 2 |>50, then add blending formula 1 and blending formula 2 to the recipe sample set, and update the blending formula until the total number of samples in the recipe sample set reaches 10*(n-1) 2 =40.

[0089] In addition, Table 1 is a list of target formulation penetrations obtained using the method provided by the embodiment of the present invention. As shown in Table 1, the predicted penetration obtained by the method provided by the embodiment of the present invention is slightly different from the actual penetration, that is, the accuracy is higher.

[0090] Table 1

[0091] project T1 T2 T3 Predicted penetration Measured needle penetration Target recipe 1 66 18 16 74 76 Target recipe 2 54 21 25 127 123 Target recipe 3 48 33 19 381 387

[0092] The blended asphalt penetration prediction device provided by the present invention is described below. The blended asphalt penetration prediction device described below and the blended asphalt penetration prediction method described above can be referenced to each other.

[0093] Based on any of the above embodiments, the present invention also provides a blended asphalt penetration prediction device, such as Figure 3As shown, the device comprises:

[0094] A formula determination unit 310 is used to determine the raw oil formula for blending asphalt;

[0095] The first prediction unit 320 is used to input the raw oil formula into the kinematic viscosity prediction model to obtain the kinematic viscosity prediction result output by the kinematic viscosity prediction model;

[0096] The second prediction unit 330 is used to determine the penetration of the blended asphalt based on the kinematic viscosity prediction result;

[0097] Among them, the kinematic viscosity prediction model is obtained based on the sample crude oil formula and the corresponding sample kinematic viscosity training.

[0098] Based on any of the above embodiments, the step of determining the sample feedstock oil formula includes:

[0099] Blend various raw oils according to the current proportions and determine the current blending formula;

[0100] Based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample crude oil formula, determine whether to use the current blending formula as the current sample crude oil formula.

[0101] Based on any of the above embodiments, based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determining whether to use the current blending formula as the current sample raw oil formula includes:

[0102] When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is greater than a threshold value, the current blending formula is used as the current sample raw oil formula.

[0103] Based on any of the above embodiments, based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determining whether to use the current blending formula as the current sample raw oil formula includes:

[0104] When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is less than or equal to a threshold value, the current blending formula is eliminated.

[0105] Based on any of the above embodiments, determining whether to use the current blending formula as the current sample raw oil formula further includes:

[0106] Update the current ratio and return to the step of determining the sample raw oil formula until the number of sample raw oil formulas reaches the preset number.

[0107] Based on any of the above embodiments, the needle penetration of the blended asphalt is determined based on the kinematic viscosity prediction result, including:

[0108] Based on the mapping relationship between needle penetration and kinematic viscosity, the kinematic viscosity prediction results are used to determine the needle penetration of blended asphalt.

[0109] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a memory 420, a communications interface 430 and a communications bus 440, wherein the processor 410, the memory 420 and the communications interface 430 communicate with each other through the communications bus 440. The processor 410 may call the logic instructions in the memory 420 to execute a blended asphalt penetration prediction method, the method comprising: determining a raw oil formula of the blended asphalt; inputting the raw oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; determining the kinematic viscosity penetration of the blended asphalt based on the kinematic viscosity prediction result; wherein the kinematic viscosity prediction model is obtained based on a sample raw oil formula and a corresponding sample kinematic viscosity training.

[0110] In addition, the logic instructions in the above-mentioned memory 420 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0111] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the blending asphalt penetration prediction method provided by the above-mentioned methods, and the method includes: determining the raw oil formula of the blending asphalt; inputting the raw oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; based on the kinematic viscosity prediction result, determining the needle penetration of the blending asphalt; wherein the kinematic viscosity prediction model is obtained based on a sample raw oil formula and a corresponding sample kinematic viscosity training.

[0112] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned blending asphalt penetration prediction methods, the methods comprising: determining the raw oil formula of the blending asphalt; inputting the raw oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; determining the penetration of the blending asphalt based on the kinematic viscosity prediction result; wherein the kinematic viscosity prediction model is obtained based on a sample raw oil formula and a corresponding sample kinematic viscosity training.

[0113] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the penetration of blended asphalt. It is characterized in that include: Determine the raw oil formula for blending asphalt; Inputting the feedstock oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; Determining the needle penetration of the blended asphalt based on the kinematic viscosity prediction result; The kinematic viscosity prediction model is obtained based on sample crude oil formula and corresponding sample kinematic viscosity training.

2. The method for predicting the penetration of blended asphalt according to claim 1, It is characterized in that The steps of determining the sample crude oil formula include: Blend various raw oils according to the current proportions and determine the current blending formula; Based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample raw oil formula, determine whether to use the current blending formula as the current sample raw oil formula.

3. The method for predicting the penetration of blended asphalt according to claim 2, It is characterized in that The step of determining whether to use the current blending formula as the current sample stock oil formula based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample stock oil formula comprises: When the absolute value of the difference between the kinematic viscosity of the previous sample stock oil recipe and the kinematic viscosity of the current blending recipe is greater than a threshold value, the current blending recipe is used as the current sample stock oil recipe.

4. The method for predicting the penetration of blended asphalt according to claim 2, It is characterized in that The step of determining whether to use the current blending formula as the current sample stock oil formula based on the kinematic viscosity of the current blending formula and the kinematic viscosity of the previous sample stock oil formula comprises: When the absolute value of the difference between the kinematic viscosity of the previous sample raw oil formula and the kinematic viscosity of the current blending formula is less than or equal to a threshold value, the current blending formula is eliminated.

5. The method for predicting the penetration of blended asphalt according to claim 2, It is characterized in that The step of determining whether to use the current blending formula as the current sample crude oil formula further includes: The current ratio is updated, and the step of determining the sample crude oil formula is returned to be executed until the number of sample crude oil formulas reaches a preset number.

6. The method for predicting the penetration of blended asphalt according to any one of claims 1 to 5, It is characterized in that Determining the needle penetration of the blended asphalt based on the kinematic viscosity prediction result includes: Based on the mapping relationship between needle penetration and kinematic viscosity, the kinematic viscosity prediction result is applied to determine the needle penetration of the blended asphalt.

7. A device for predicting the penetration of blended asphalt. It is characterized in that include: A formula determination unit, used to determine the raw oil formula for blending asphalt; A first prediction unit, used for inputting the feedstock oil formula into a kinematic viscosity prediction model to obtain a kinematic viscosity prediction result output by the kinematic viscosity prediction model; A second prediction unit, used to determine the needle penetration of the blended asphalt based on the kinematic viscosity prediction result; The kinematic viscosity prediction model is obtained based on sample crude oil formula and corresponding sample kinematic viscosity training.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the blended asphalt penetration prediction method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for predicting the penetration of blended asphalt as described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method for predicting the penetration of blended asphalt as described in any one of claims 1 to 6 is implemented.

Images