Method and device for calculating attenuation value of oil product quality index of product oil pipeline

Abstract

The invention discloses a method and device for calculating an attenuation value of an oil product quality index of a product oil pipeline, and relates to the technical field of oil and gas pipelines, and the method comprises the steps: obtaining the operation state information of the product oil pipeline, the operation state information comprises the flow of the product oil pipeline, the pipeline mileage, the pipeline elevation fluctuation rate, and the pipe diameter change rate; based on the operation state information and an attenuation value prediction model, the attenuation value of the quality index of the product oil transmitted through the product oil pipeline is determined, and the attenuation value prediction model is used for predicting the attenuation value of the quality index of the product oil transmitted through the product oil pipeline according to the operation state information of the product oil pipeline. According to the method, the attenuation value of the product oil quality index is calculated based on the flow of the product oil pipeline, the pipeline mileage, the pipeline elevation fluctuation rate and the pipe diameter change rate, and the accuracy of calculation of the attenuation value of the product oil quality index can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas pipelines, and in particular to a method and device for calculating an attenuation value of an oil quality indicator of a finished oil pipeline. Background Art

[0002] When refined oil is transported sequentially in the refined oil pipeline, the oil will adhere to the inner wall of the refined oil pipeline to varying degrees, and as it is flushed by the following oil, it will mix into the following oil, causing the composition of the following oil to change, resulting in deviations in its chemical composition and purity, which is the quality degradation phenomenon.

[0003] The quality attenuation phenomenon may cause the quality indicators of finished oil to fail to meet relevant quality standards when it reaches the pipeline terminal, making it difficult to apply it to the production process, thereby causing a waste of resources.

[0004] Therefore, how to calculate the attenuation value of the quality indicators of refined oil during transportation is the problem we need to solve. Summary of the Invention

[0005] The present application provides a method and device for calculating the attenuation value of the oil quality index of a finished oil pipeline, which can calculate the attenuation value of the finished oil quality index based on the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the finished oil pipeline, thereby improving the accuracy of the calculation of the attenuation value of the finished oil quality index.

[0006] In a first aspect, the present application provides a method for calculating the attenuation value of an oil product quality indicator in a refined oil pipeline. The method comprises: obtaining operational status information of the refined oil pipeline, the operational status information including the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the refined oil pipeline; and determining the attenuation value of the refined oil quality indicator after transmission through the refined oil pipeline based on the operational status information and an attenuation value prediction model. The attenuation value prediction model is configured to predict the attenuation value of the refined oil quality indicator after transmission through the refined oil pipeline based on the operational status information of the refined oil pipeline.

[0007] According to the above technical solution, the attenuation prediction model can establish a mapping relationship between multi-dimensional operational status information of the refined oil pipeline and the attenuation value of the quality indicator, overcoming the limitations of traditional methods that rely on simple calculations based on a single factor. Furthermore, by inputting the real-time operating information of the refined oil pipeline into the attenuation prediction model, the attenuation law of the quality indicator fitted by the attenuation prediction model can be used to more accurately predict the attenuation value of the quality indicator that conforms to the actual operating conditions, providing data support for refined oil quality control.

[0008] In one possible implementation, the attenuation value prediction model satisfies the following formula:

[0009]

[0010] Among them, Y represents the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline. represents the intercept term, Q represents the flow rate of the finished oil pipeline, represents the regression coefficient of the flow rate of the finished oil pipeline, L represents the pipeline mileage, represents the regression coefficient of pipeline mileage, H represents the pipeline elevation fluctuation rate, represents the regression coefficient of pipeline elevation fluctuation rate, D represents the pipe diameter change rate, Regression coefficient representing the rate of change of pipe diameter.

[0011] In a possible implementation, the method further includes: determining the input oil quality of the finished oil pipeline based on the attenuation value and the output oil quality requirement.

[0012] In one possible implementation, the refined oil product includes gasoline or diesel. The refined oil quality indicators for gasoline include the final distillation point, and the refined oil quality indicators for diesel include the flash point. The input oil quality of the refined oil pipeline is determined based on the attenuation value and the output oil quality requirements. This includes: if the refined oil transported by the refined oil pipeline is gasoline, the input oil quality of the refined oil pipeline is determined based on the difference between the attenuation value and the output oil quality requirements. If the refined oil transported by the refined oil pipeline is diesel, the input oil quality of the refined oil pipeline is determined based on the sum of the output oil quality requirements and the attenuation value.

[0013] In one possible implementation, the method further includes: obtaining a training sample set, the training sample set including multiple training samples, each training sample including operating status information at a monitoring point in a refined oil pipeline and an attenuation value of an oil quality index at the monitoring point. The operating status information at the monitoring point includes: flow rate at the monitoring point, pipeline mileage between the first pump of the refined oil pipeline and the monitoring point, pipeline elevation fluctuation rate between the first pump of the refined oil pipeline and the monitoring point, and pipeline diameter change rate between the first pump of the refined oil pipeline and the monitoring point. The attenuation value of the oil quality index at the monitoring point is the absolute value of the difference between the oil quality index at the first pump of the refined oil pipeline and the oil quality index at the monitoring point. Based on the training sample set, an initial model of the attenuation value prediction model is trained to obtain the attenuation value prediction model.

[0014] In one possible implementation method, the initial model includes a least squares regression model. Based on the training sample set, the initial model of the attenuation value prediction model is trained to obtain the attenuation value prediction model, including: using the operating status information in the training sample as the independent variable, using the attenuation value of the oil quality indicator in the training sample as the dependent variable, and using the least squares method to determine the regression coefficient corresponding to each independent variable in the least squares regression model until the model training end condition is met, thereby obtaining the attenuation value prediction model.

[0015] In one possible implementation, each independent variable is assigned a Pearson correlation coefficient, which represents the degree of correlation between the corresponding independent variable and the oil quality indicator attenuation value. Model training termination conditions include: the error between the oil quality indicator attenuation value predicted by the least squares regression model and the oil quality indicator attenuation value at the monitoring point in the training sample is less than a difference threshold, and the first and second sorting results are the same. The first sorting result is the result of sorting the independent variables in order of the corresponding regression coefficients, while the second sorting result is the result of sorting the independent variables in order of the corresponding Pearson correlation coefficients.

[0016] In a second aspect, the present application provides a device for calculating the attenuation value of the quality index of oil products in a finished oil pipeline, which includes various functional modules used in the method described in the first aspect above.

[0017] In a third aspect, the present application provides an electronic device comprising: a processor and a memory. The memory stores instructions executable by the processor. When the processor is configured to execute the instructions, the electronic device implements the method described in the first aspect above.

[0018] In a fourth aspect, the present application provides a computer program product, comprising: computer instructions. When the computer instructions are executed on an electronic device, the electronic device implements the method described in the first aspect.

[0019] The beneficial effects of the second to fourth aspects mentioned above can be referred to the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in 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 only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 A flow chart of a method for calculating the attenuation value of a product quality index of a refined oil pipeline provided in an embodiment of the present application;

[0022] Figure 2 A flow chart of a method for determining the quality of oil input into a refined oil pipeline provided in an embodiment of the present application;

[0023] Figure 3 A flowchart of a method for training an attenuation value prediction model provided in an embodiment of the present application;

[0024] Figure 4A schematic diagram of the composition of a device for calculating the attenuation value of a quality indicator of a finished oil pipeline provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] It should be noted that in the embodiments of this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described in the embodiments of this application as "exemplarily" or "for example" should not be interpreted as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in a concrete manner.

[0028] In order to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order.

[0029] The final distillation point of gasoline refers to the temperature at which the last drop of liquid evaporates during the distillation process. A gasoline final distillation point that is too high may mean that the gasoline contains a large amount of heavy components. This will cause incomplete combustion of the gasoline, resulting in carbon deposits in the engine, and reduced engine performance and efficiency. The flash point of diesel refers to the lowest temperature at which diesel can flash when its vapor mixes with air and encounters an open flame during the heating process. A diesel flash point that is too low means that it is highly volatile and can easily form a combustible mixture during storage, transportation, and use. It may cause a fire or explosion when encountering a fire source or static electricity, posing a major safety hazard.

[0030] The quality attenuation of finished oil caused by long-distance transportation through pipelines will cause the final distillation point of gasoline or diesel flash point to attenuate. For example, in a domestic finished oil pipeline, from the entry to the exit of the refinery, the flash point of No. 0 diesel attenuates by an average of 7.4°C, and the final distillation point of No. 92 gasoline attenuates by an average of 2.9°C.

[0031] At present, although the industry has a certain understanding of the quality attenuation phenomenon of refined oil, the calculation method of the quality attenuation value of refined oil is relatively simple, and the accuracy of the calculated quality attenuation value of refined oil is not high.

[0032] In light of this, embodiments of the present application provide a method for calculating the attenuation value of a product quality indicator in a refined oil pipeline. This method, through an attenuation value prediction model, establishes a mapping relationship between multi-dimensional operational status information of the refined oil pipeline and the attenuation value of the quality indicator. Furthermore, by inputting the attenuation value prediction model into the real-time operating condition information of the refined oil pipeline, the attenuation law of the quality indicator fitted by the attenuation value prediction model can be used to accurately predict the attenuation value of the quality indicator that conforms to the actual operating conditions, providing data support for refined oil quality control.

[0033] The method for calculating the attenuation value of a product quality indicator in a refined oil pipeline provided in the embodiments of this application can be applied to a computing device, where the computing device can be a server cluster consisting of multiple servers, a single server, a computer, or a processor or processing chip in a server or computer. The embodiments of this application do not limit the specific form factor of the computing device.

[0034] Figure 1 A flow chart of a method for calculating the attenuation value of a product quality index of a finished oil pipeline provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes the following steps:

[0035] S101. Obtaining the operating status information of the refined oil pipeline.

[0036] The operating status information includes the flow rate of the finished oil pipeline, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate.

[0037] The flow rate of a refined oil product pipeline can be understood as the volume or weight of oil passing through the pipeline's cross-section per unit time. Specifically, at high flow rates, the oil's residence time in the pipeline is short, resulting in limited contact time with the pipeline's inner wall. While the flushing effect is strong, mixing is inadequate, and quality indicators are minimally affected. At low flow rates, the oil's residence time in the pipeline is long, providing more opportunities for mixing with oil adhering to the inner wall.

[0038] Pipeline mileage refers to the actual physical distance that oil products travel from their starting point to their destination. Specifically, as pipeline mileage increases, the contact area and time between the oil and the pipeline's inner wall accumulate, making it more likely for oil to adhere to the pipeline's inner wall and subsequently be washed and mixed into the rest of the oil. Furthermore, increasing pipeline mileage increases the likelihood of physical and chemical reactions between the oil and the pipeline.

[0039] Pipeline elevation fluctuation refers to the severity of elevation changes along the pipeline, specifically the magnitude of elevation change per unit length of pipeline. When pipeline elevation fluctuation is high, the pressure and flow rate of oil products fluctuate frequently and dramatically during transportation. During rising sections, the oil flow rate decreases, extending its contact time with the pipeline's inner wall, promoting adhesion and quality changes. During falling sections, the flow rate increases, increasing erosion of the pipeline's inner wall and potentially introducing more impurities into the oil.

[0040] The pipe diameter change rate refers to the ratio of the change in pipe diameter at different locations along the pipeline to the original diameter. Pipe diameter changes alter the flow pattern of the oil. When the pipe diameter decreases, the oil flow rate increases, intensifying erosion of the pipe wall. This can lead to more debris entering the oil, accelerating the degradation of oil quality indicators. When the pipe diameter increases, the oil flow rate decreases and the residence time increases, potentially causing separation or reactions of some oil components, also affecting oil quality.

[0041] In some embodiments, the computing device may pre-calculate or obtain the pipeline mileage, pipeline elevation fluctuation rate, and pipeline diameter change rate for each product pipeline to be calculated. Because pipeline mileage, pipeline elevation fluctuation rate, and pipeline diameter change rate are relatively fixed operational status information, the computing device can, when executing S101, only obtain the current flow rate of the product pipeline.

[0042] S102: Determine the attenuation value of the quality index of the refined oil after being transmitted through the refined oil pipeline based on the operation status information and the attenuation value prediction model.

[0043] Among them, the attenuation value prediction model is used to predict the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline based on the operating status information of the finished oil pipeline.

[0044] In some embodiments, the attenuation value prediction model may include multiple attenuation value prediction models, each corresponding to a type of refined oil. In this case, when executing S102, the computing device needs to select the corresponding attenuation value prediction model based on the type and model of refined oil transported by the current refined oil pipeline.

[0045] Specifically, refined oil products can include gasoline or diesel. Furthermore, gasoline can include 92-octane gasoline or 95-octane gasoline, and diesel can include 0-octane diesel, -10-octane diesel, or -20-octane diesel. When different types of refined oil products, or different types of refined oil products of the same type, experience attenuation through a refined oil pipeline, their attenuation values may vary due to differences in the composition of the refined oil products. Therefore, before using an attenuation value prediction model, multiple attenuation value prediction models can be obtained, and then the attenuation value prediction model corresponding to the type and type of refined oil currently being transported in the refined oil pipeline can be selected.

[0046] Specifically, the attenuation value prediction model satisfies the following formula:

[0047]

[0048] Among them, Y represents the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline. represents the intercept term, Q represents the flow rate of the finished oil pipeline, represents the regression coefficient of the flow rate of the finished oil pipeline, L represents the pipeline mileage, represents the regression coefficient of pipeline mileage, H represents the pipeline elevation fluctuation rate, represents the regression coefficient of pipeline elevation fluctuation rate, D represents the pipe diameter change rate, Regression coefficient representing the rate of change of pipe diameter.

[0049] For example, assuming that the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the refined oil pipeline are 2500 m3 / h, 300 km, 3.41, and 1.04, respectively, and the attenuation value prediction model equation is: Y = 0.1 + 0.0002Q + 0.002L + 0.05H + (-00.1)D. Substituting the above operating status information into formula (1), we obtain: 0.1 + (0.0002 × 2500) + (0.002 × 300) + (0.05 × 3.41) + (-0.01 × 1.04) = 0.1 + 0.5 + 0.6 + 0.17 - 0.0104 = 1.36°C, which means that the attenuation value of the refined oil is 1.36°C.

[0050] As can be seen from steps S101-S102, each type of operating status information in the refined oil pipeline may cause refined oil quality degradation. By constructing a degradation value prediction model, the different operating status information of the refined oil pipeline is fitted, thereby comprehensively considering the impact of various factors on refined oil quality degradation and clarifying the relationship between operating status information and refined oil quality degradation. Furthermore, by identifying the current operating status information of the refined oil pipeline, the degradation value of refined oil quality can be predicted according to the actual operating conditions of the refined oil pipeline.

[0051] The following introduces how to obtain each type of operating status information in the finished oil pipeline.

[0052] In some embodiments, the method for obtaining each type of operating status information in step S101 may be the following:

[0053] For the flow of the finished oil pipeline, the computing device can obtain the average value of the flow detected at multiple flow meters of the finished oil pipeline through flow meters installed along the finished oil pipeline (such as turbine flow meters, electromagnetic flow meters, etc.) as the flow of the finished oil pipeline.

[0054] For pipeline mileage, a 3D model of the refined oil pipeline can be created using a geographic information system to determine the mileage of the refined oil pipeline. Alternatively, inspection personnel can determine the mileage of the pipeline by observing the markings and mileage signs on the refined oil pipeline.

[0055] For pipeline elevation fluctuation rate, the calculation equipment can use the global positioning system to collect elevation values at certain time intervals or distance intervals along the finished oil pipeline, and then calculate the standard deviation of multiple elevation signal values as the pipeline elevation fluctuation rate.

[0056] For example, the calculation process of pipeline elevation fluctuation rate can be expressed as:

[0057]

[0058] Where xi represents the i-th elevation value, μ represents the arithmetic mean of multiple elevation information, and N represents the total number of elevation values.

[0059] For example, suppose the elevation values of 5 measuring points along a pipeline are: [100m, 105m, 98m, 102m, 95m], the average value is (100+105+98+102+95)÷5=100m, and the variance is 11.6. Then the standard deviation is

[0060] Regarding the pipe diameter change rate, the computing device can obtain the lengths of different pipe diameters based on the geometric parameters of the pipeline construction drawings or through internal inspection tools (such as intelligent pipe cleaning devices).

[0061] For example, the calculation process of the pipe diameter change rate can be expressed as:

[0062]

[0063] Among them, di represents the size of the i-th pipe diameter, lt represents the length of the i-th pipe diameter in the finished oil pipeline, and L represents the mileage of the finished oil pipeline.

[0064] For example, suppose a pipeline has a total length of L = 10 km and is divided into three sections. The first section has a pipe diameter of 1 m and a length of 6 km. The second section has a pipe diameter of 1.2 m and a length of 3 km. The third section has a pipe diameter of 0.8 m and a length of 1 km. Substituting this information into formula (2), we obtain D = ((1.0 × 6) + (1.2 × 3) + (0.8 × 1)) / 10 = 1.04.

[0065] In some embodiments, after determining the attenuation value of the quality index of the finished oil after transmission, the computing device may further determine the quality index of the finished oil input into the finished oil pipeline. In this case, Figure 2 As shown, after step S102, the following steps may also be included:

[0066] S103. Determine the input oil quality of the finished oil pipeline based on the attenuation value and the output oil quality requirement.

[0067] One possible implementation method is to determine the input oil quality of the finished oil pipeline based on the difference between the attenuation value and the output oil quality requirement when the finished oil is gasoline.

[0068] It should be noted that when the finished oil product is gasoline, its quality indicators include the final distillation point, and the output oil quality requirements include the output oil quality requirements for the gasoline final distillation point. The lower the final distillation point of gasoline, the better its combustion performance. However, when the finished oil product undergoes quality degradation, the final distillation point of gasoline may increase.

[0069] Therefore, after obtaining the attenuation value of the finished oil quality index after gasoline is transported through the finished oil pipeline through the attenuation prediction model, the output oil quality requirement of the gasoline terminal distillation point minus the attenuation value can be used to obtain the quality index of gasoline when it is input into the finished oil pipeline.

[0070] For example, the quality requirement for No. 92 gasoline is a final distillation point no higher than 205°C. Assume that the attenuation prediction model indicates that the final distillation point attenuation of gasoline after transportation through a refined oil pipeline is 2.16°C. To meet the final distillation point quality requirement for gasoline output, assuming the final distillation point of the output gasoline is controlled at the standard upper limit of 205°C, the final distillation point quality index value of the gasoline entering the refined oil pipeline should be 205°C - 2.16°C ≈ 203°C.

[0071] Another possible implementation is that when the finished oil is diesel, the input oil quality of the finished oil pipeline is determined based on the sum of the output oil quality requirement and the attenuation value.

[0072] It should be noted that when the finished oil product is diesel, the quality indicators of diesel include flash point, and the output oil quality requirements include the output oil quality requirements for diesel. The higher the flash point of diesel, the safer it is during storage and use. However, when the quality of the finished oil product deteriorates, the flash point of diesel may decrease.

[0073] Therefore, after obtaining the attenuation value of the finished oil quality index after diesel is transported through the finished oil pipeline through the attenuation prediction model, the output oil quality requirement of the diesel flash point plus the attenuation value can be used to obtain the quality index value of the diesel when it is input into the finished oil pipeline.

[0074] For example, the quality requirement for No. 0 diesel is a flash point of no less than 55°C. Assume that the attenuation prediction model indicates that the flash point attenuation of diesel after transport through a refined oil pipeline is 1.53°C. To meet the output fuel quality requirement for diesel flash point, assuming the output diesel flash point is controlled at the standard lower limit of 55°C, the flash point quality index value of the diesel entering the refined oil pipeline should be 55°C + 1.53°C ≈ 57°C.

[0075] As can be seen from step S103, based on the attenuation value and the output oil quality requirements, the quality of the oil input to the finished oil pipeline can be reversely calculated, ensuring that the quality of each type of finished oil meets the oil quality requirements when it is output. Furthermore, this method can also quantify the quality redundancy of the finished oil input, reducing the quality waste caused by excessively increasing the input finished oil quality due to the inability to accurately determine the finished oil quality attenuation value in traditional methods, thereby achieving rational resource allocation.

[0076] The following introduces the process of obtaining the refined oil attenuation value prediction model in the attenuation value prediction model corresponding to any refined oil.

[0077] In some embodiments, the computing device may further obtain an attenuation value prediction model before step S102 .

[0078] In one possible implementation, a computing device may obtain a trained attenuation value prediction model from other computing devices.

[0079] For example, the computing device may obtain the trained attenuation value prediction model from other devices by downloading or transferring it from an intermediate storage medium.

[0080] Another possible implementation method is that the computing device can also train itself to obtain the attenuation value prediction model. In this case, Figure 3 As shown, the method may further include the following steps:

[0081] S201: Obtain a training sample set.

[0082] The training sample set includes multiple training samples, each of which includes operating status information at a monitoring point in a refined oil pipeline and an oil quality index attenuation value at the monitoring point. The monitoring point can be a monitoring point deployed along the refined oil pipeline.

[0083] Specifically, the operating status information at the monitoring point includes: the flow rate at the monitoring point, the pipeline mileage between the first pump of the refined oil pipeline and the monitoring point, the pipeline elevation fluctuation rate between the first pump of the refined oil pipeline and the monitoring point, and the pipe diameter change rate between the first pump of the refined oil pipeline and the monitoring point. The oil quality index attenuation value at the monitoring point is the absolute value of the difference between the oil quality index at the first pump of the refined oil pipeline and the oil quality index at the monitoring point.

[0084] It should be noted that the method for obtaining the operating status information at the monitoring point can refer to the above introduction to the acquisition of each type of operating status information in the finished oil pipeline, and will not be repeated here.

[0085] It should also be noted that, for the monitoring method of the attenuation value of the oil quality index at the monitoring point, the online density meter and optical cross-section detector deployed at the monitoring point can be used to directly detect the finished oil passing through the monitoring point to obtain the attenuation value of the oil quality index of the finished oil, or the finished oil passing through the monitoring point can be sampled, and then the sampled oil can be sent to the laboratory for testing to obtain the oil quality index of the finished oil.

[0086] In some embodiments, the computing device can calculate the time points at which different monitoring points sample the passing finished oil based on the transportation speed of the finished oil pipeline, the start time of transportation, the amount of oil distributed along the way, etc. The computing device can then control the monitoring points to obtain the operating status information of the finished oil pipeline and the attenuation value of the oil quality indicator at the corresponding sampling time points.

[0087] In one possible implementation, the same tank of finished oil can be divided into multiple batches for transportation, and the operating status information at each monitoring point in each batch and the oil quality index attenuation value at the monitoring point are used as a training sample.

[0088] For example, the same tank of refined oil can be divided into four batches for transportation. During each transportation, 20 monitoring points along the refined oil pipeline can be set up to sample the refined oil. Finally, 80 training samples can be obtained.

[0089] S202: Based on the training sample set, the initial model of the attenuation value prediction model is trained to obtain the attenuation value prediction model.

[0090] In some embodiments, the attenuation value prediction model may also be a neural network model. In this case, the attenuation value of the oil quality index at the monitoring point in each training sample may be used as the label of the training sample for iterative training based on the training sample set.

[0091] Specifically, a neural network structure consisting of an input layer, hidden layers, and an output layer is first constructed. The number of neurons in the input layer corresponds to the dimensions of the operating status information at the monitoring point, such as flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate. This operating status information is used as input data. Multiple hidden layers can be set up, and through different neuron combinations and weight assignments, complex feature extraction and nonlinear transformation are performed on the input data. During the training process, the operating status information in the training sample set is sequentially input into the neural network. After layer-by-layer calculations in the hidden layers, the predicted oil quality indicator attenuation value is obtained in the output layer. Next, a loss function (such as the mean squared error function) is used to calculate the error between the predicted value and the actual attenuation value used as the label. The weights and biases between each layer of the neural network are adjusted through the backpropagation algorithm to continuously reduce the error. After multiple rounds of iterative training, the neural network gradually learns the intrinsic mapping relationship between operating status information and oil quality indicator attenuation value, ultimately forming an attenuation value prediction model that can accurately predict the attenuation value of oil quality indicators.

[0092] In some embodiments, the initial model of the attenuation value prediction model in S202 may also be a least squares regression model. In this case, the computing device uses the operating status information in the training samples as the independent variable and the oil quality indicator attenuation value in the training samples as the dependent variable. The computing device uses the least squares method to determine the regression coefficient corresponding to each independent variable in the least squares regression model until the model training termination condition is met, thereby obtaining the attenuation value prediction model.

[0093] The process of training the least squares regression model using the training sample set is:

[0094] S2021. Substitute the independent variables in each training sample into the initial least squares regression model equation to obtain the predicted oil quality index attenuation value corresponding to each training sample.

[0095] Specifically, the regression coefficients in the initial least squares regression model are randomly set values.

[0096] For example, the process of obtaining the predicted oil quality index attenuation value corresponding to each training sample can be expressed as:

[0097] yi=β0+β1Qi+β2Li+β3Hi+β4Di Formula (4)

[0098] Where yi represents the predicted oil quality index attenuation value corresponding to the i-th training sample, β0 represents the intercept term, Qi represents the flow rate of the finished oil pipeline in the i-th training sample, β1 represents the regression coefficient corresponding to the flow rate of the finished oil pipeline, L represents the pipeline mileage of the i-th training sample, Hi represents the pipeline elevation fluctuation rate of the i-th training sample, and Di represents the pipe diameter change rate of the i-th training sample. β0, β1, β2, β3, and β4 are the regression coefficients in the least squares regression model.

[0099] S2022. Calculate the square of the difference between the predicted oil quality index attenuation value and the actual oil quality index attenuation value corresponding to each training sample.

[0100] Specifically, the square of the difference reflects the prediction error of the model on the training sample.

[0101] S2023. Determine the total sum of squared differences of all training samples based on the squared differences of all training samples.

[0102] Specifically, the calculation process of the total sum of squared differences can be expressed as:

[0103]

[0104] Among them, S(β0,β1,β2,β3,β4) represents the total sum of squared differences, n represents the total number of training samples, μi2 represents the squared difference of the i-th training sample, Yi represents the actual oil quality index attenuation value of the i-th training sample (that is, the dependent variable), and β0+β1Qi+β2Li+β3Hi+β4Di represents the predicted oil quality index attenuation value corresponding to the i-th training sample.

[0105] S2024. Based on the total sum of squared differences and the chain rule, calculate the partial derivatives of the total sum of squared differences with respect to each regression coefficient.

[0106] Specifically, the process of obtaining the partial derivative of β0 is as follows: first, derive S with respect to μi, and obtain Then take the derivative of ui with respect to β0 and get By the chain rule, we can substitute the above derivative into The partial derivative of β0 can be obtained. The process can be expressed as

[0107]

[0108] Specifically, the process of obtaining the partial derivative of β1 is as follows: first, derive S with respect to μi, and obtain Then take the derivative of ui with respect to β1 and get By the chain rule, we can substitute the above derivative into The partial derivative of β1 can be obtained. The process can be expressed as:

[0109]

[0110] It should be noted that β2 can be obtained by referring to formula (7) 、 β3 、 Partial derivative of β4.

[0111] S2025. Based on the partial derivatives of each regression coefficient, update the regression coefficient according to the gradient descent algorithm.

[0112] It should be noted that the partial derivatives of the total sum of squared differences for each regression coefficient can be combined to form the gradient vector of the least squares regression model. The partial derivatives reflect the rate of change of the total sum of squared differences with respect to a single regression coefficient. The gradient vector integrates the information of all partial derivatives. It points in the direction of the fastest increase in the function value, and in the opposite direction, it points in the direction of the fastest decrease in the function value. During model training, we use this characteristic of the gradient vector to update the regression coefficients based on its opposite direction (combined with the learning rate), so that the total sum of squared differences changes in the direction of decrease, thereby updating the values of each regression coefficient.

[0113] Specifically, taking the update of β0 as an example, the process of updating the regression coefficient according to the gradient descent algorithm can be expressed as:

[0114]

[0115] in, Represents the updated value of β0 for this model training, Represents the randomly set value of β0 at the beginning of training or the updated value during the last training process, It represents the partial derivative of the total sum of squared differences with respect to β0 during this training process, and α represents the hyperparameter learning rate of model training.

[0116] It should also be noted that the hyperparameter learning rate for model training can be set according to the actual needs of model training. The embodiment of the present application does not limit the specific value of the hyperparameter learning rate for model training.

[0117] S2026. Repeat steps S2021-2025 to perform multiple iterative trainings. Stop the training when the end conditions of the model training are met, and obtain the trained least squares regression model.

[0118] Specifically, the regression coefficients updated in the last training are substituted into formula (1) to obtain the prediction model of the attenuation value of refined oil.

[0119] The following describes the end conditions of the least squares regression model training process.

[0120] One possible implementation method is to set a threshold for the number of model training times as the end condition. In this case, when the number of model training times reaches the preset threshold, the computing device can stop model training and construct a least squares regression model with the regression coefficients obtained from the last model training.

[0121] Specifically, the preset number threshold can be 500, 1000 or 2000. The embodiment of the present application does not limit the specific value of the number threshold of model training.

[0122] Another possible implementation method is to use the error between the oil quality index attenuation value predicted by the least squares regression model and the oil quality index attenuation value at the monitoring point in the training sample as the end condition, and the first sorting result is the same as the second sorting result.

[0123] The first sorting result is the result of sorting the independent variables in the order of the corresponding regression coefficients, and the second sorting result is the result of sorting the independent variables in the order of the corresponding Pearson correlation coefficients.

[0124] Specifically, the process can be expressed as:

[0125] S301: Input each training sample into the least squares regression model being trained to obtain the predicted oil quality index attenuation value corresponding to each training sample.

[0126] Specifically, a least squares regression model can be constructed using the regression coefficients updated in the current round to obtain the predicted oil quality index attenuation value corresponding to each training sample.

[0127] It should be noted that the computing device may execute step S103 when the number of model training rounds reaches a preset number of model training rounds, for example, when the model training reaches 200 times, 500 times, etc., execute step S301.

[0128] S302: Calculate the difference between the predicted oil quality index attenuation value of each training sample and its corresponding actual oil quality index attenuation value, and compare the maximum difference among multiple training samples with a preset difference threshold.

[0129] It should be noted that if the maximum difference is greater than or equal to the preset difference threshold, it means that the effect of the current model training has not reached the end condition. Therefore, the computing device can stop the execution of subsequent steps S303-S305 and continue to execute the model training steps S2021-S2025.

[0130] For example, when the refined oil is diesel, the difference threshold may be 1.7° C., 1.8° C., or 2° C. When the refined oil is gasoline, the difference threshold may be 3° C., 3.3° C., or 3.5° C. The embodiment of the present application does not limit the specific value of the difference threshold.

[0131] S303: When the maximum difference is less than the difference threshold, the independent variables are sorted in order of the regression coefficient corresponding to each variable in the trained least squares regression model to obtain a first sorting result.

[0132] It's important to note that the first ranking result represents the relationship between the regression coefficients obtained after model training. This actually indicates the relative influence of each independent variable on the dependent variable within the mathematical relationship constructed by the least squares regression model. A larger absolute value of the regression coefficient indicates a more significant impact of the independent variable on the dependent variable in the model, and a greater change in the dependent variable per unit change in the independent variable.

[0133] S304: Calculate the Pearson coefficient between each independent variable and the dependent variable in the training sample set, and sort the independent variables in the order of the Pearson coefficient between each independent variable and the dependent variable to obtain a second sorting result.

[0134] It should be noted that the Pearson coefficient is used to indicate the strength of the correlation between two variables, and the Pearson coefficient ranges from -1 to 1. The closer the absolute value of the correlation is to 1, the stronger the correlation between the corresponding independent variable and the dependent variable. In the embodiment of the present application, the Pearson coefficient between each independent variable and the dependent variable is calculated separately, and the independent variables are sorted according to the size of the Pearson coefficient corresponding to each independent variable. The sorting results are used to indicate the importance of different independent variables to the changes in the dependent variable (i.e., the attenuation value of the oil quality index).

[0135] One possible implementation method is to extract the dependent variables of multiple training samples from the training sample set to form the dependent variable set corresponding to the training sample set, and extract the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of each training sample from the training sample set to form different types of independent variable sets respectively. Each independent variable set and dependent variable set are substituted into formula (9) to calculate the Pearson correlation coefficient of each independent variable and dependent variable.

[0136]

[0137] Among them, n represents the total number of dependent variable sets or independent variable sets, Xi represents the value of the i-th independent variable, represents the mean value of the dependent variable, and Yi represents the value of the i-th dependent variable. represents the mean value of the dependent variable.

[0138] For example, assuming there are five training samples in the training sample set, the pipeline mileage independent variable set corresponding to the training sample set is: [20 km, 25 km, 30 km, 45 km, 50 km], and the dependent variable set corresponding to the training sample set is: [0.24°C, 0.3°C, 0.35°C, 0.48°C, 0.52°C]. First, the average value of the independent variable set is calculated to be 34 km, and the average value of the dependent variable set is calculated to be 0.38°C. Then, according to formula (9), the correlation between pipeline mileage and the attenuation value of the oil quality index is calculated, and the final result is 0.996, which indicates that there is a strong positive correlation between pipeline mileage and the dependent variable.

[0139] S305: When the first sorting result is the same as the second sorting result, stop training the least squares regression model.

[0140] It's important to note that when the first and second ranking results are identical, the influence of the independent variables determined by the least squares regression model is consistent with the importance of the independent variables determined based on the linear correlation of the data. This demonstrates that the model not only numerically fits the training sample data well and accurately predicts the attenuation of oil quality indicators, but also aligns with the inherent statistical laws of the data in its understanding and grasp of the relationship between the independent and dependent variables. Therefore, model training can be stopped at this point. The resulting least squares regression model can be effectively used in subsequent practical applications, such as predicting the attenuation of oil quality indicators in refined oil pipelines.

[0141] It should also be noted that when the first sorting result is different from the second sorting result, it means that the regression coefficient updated by the model training cannot meet the consistency requirements of the inherent laws of the data. This means that although the current model may fit the data to a certain extent, there is a deviation in the grasp of the relationship between the independent variable and the dependent variable. In this case, the model can be optimized and adjusted. For example, the training data can be re-examined, the model structure can be adjusted, and then steps S2021-S2025 are continued until the first sorting result is consistent with the second sorting result, ensuring that a least squares regression model that can accurately reflect the relationship between the independent variable and the dependent variable, is stable and reliable, and is suitable for the actual prediction scenario of the quality attenuation value of the finished oil pipeline is obtained.

[0142] As can be seen from steps S301-S305, this process accurately assesses the model's predictive capabilities. By calculating the difference between the predicted and actual values and comparing it with a threshold, it determines whether the model's prediction error is within an acceptable range. It also provides in-depth analysis of the influence of variables, ranking independent variables based on regression coefficients and Pearson coefficients to understand their importance to the dependent variable. Stopping training when the two rankings are identical ensures model stability and reliability.

[0143] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed herein, and the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0144] In an exemplary embodiment, the present application also provides a device for calculating the attenuation value of the oil product quality index of a finished oil pipeline in the form of a virtual device, such as Figure 4 As shown, the device includes: an acquisition module 410 and a processing module 420.

[0145] The acquisition module 410 is used to acquire the operational status information of the refined oil pipeline, including the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the refined oil pipeline.

[0146] Processing module 420 is configured to determine the attenuation value of the quality index of the refined oil after being transported through the refined oil pipeline based on the operating status information and the attenuation value prediction model. The attenuation value prediction model is configured to predict the attenuation value of the quality index of the refined oil after being transported through the refined oil pipeline based on the operating status information of the refined oil pipeline.

[0147] In one possible implementation, the attenuation value prediction model satisfies the following formula:

[0148]

[0149] Among them, Y represents the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline. represents the intercept term, Q represents the flow rate of the finished oil pipeline, represents the regression coefficient of the flow rate of the finished oil pipeline, L represents the pipeline mileage, represents the regression coefficient of pipeline mileage, H represents the pipeline elevation fluctuation rate, represents the regression coefficient of pipeline elevation fluctuation rate, D represents the pipe diameter change rate, Regression coefficient representing the rate of change of pipe diameter.

[0150] In a possible implementation, the processing module 420 is further configured to determine the quality of the input oil product of the refined oil pipeline based on the attenuation value and the output oil product quality requirement.

[0151] In one possible implementation, the refined oil product includes gasoline or diesel, and the refined oil quality indicators for gasoline include the final distillation point, while the refined oil quality indicators for diesel include the flash point. Processing module 420 is further configured to determine the input oil quality of the refined oil pipeline based on the attenuation value and the output oil quality requirement. This includes: if the refined oil transported by the refined oil pipeline is gasoline, determining the input oil quality of the refined oil pipeline based on the difference between the attenuation value and the output oil quality requirement; and if the refined oil transported by the refined oil pipeline is diesel, determining the input oil quality of the refined oil pipeline based on the sum of the output oil quality requirement and the attenuation value.

[0152] In one possible implementation, processing module 420 is specifically configured to obtain a training sample set, the training sample set comprising multiple training samples, each training sample comprising operating status information at a monitoring point in a refined oil pipeline and an attenuation value of an oil quality indicator at that monitoring point. The operating status information at the monitoring point comprises: the flow rate at the monitoring point, the pipeline mileage between the first pump of the refined oil pipeline and the monitoring point, the pipeline elevation fluctuation rate between the first pump of the refined oil pipeline and the monitoring point, and the rate of change in the pipeline diameter between the first pump of the refined oil pipeline and the monitoring point. The attenuation value of the oil quality indicator at the monitoring point is the absolute value of the difference between the oil quality indicator at the first pump of the refined oil pipeline and the oil quality indicator at the monitoring point. Based on the training sample set, an initial model of the attenuation value prediction model is trained to obtain the attenuation value prediction model.

[0153] In one possible implementation, the initial model includes a least squares regression model, and the processing module 420 is specifically used to train the initial model of the attenuation value prediction model based on the training sample set to obtain the attenuation value prediction model, including: using the operating status information in the training sample as an independent variable, using the oil quality indicator attenuation value in the training sample as a dependent variable, and using the least squares method to determine the regression coefficient corresponding to each independent variable in the least squares regression model until the model training end condition is met, thereby obtaining the attenuation value prediction model.

[0154] In one possible implementation, each independent variable is assigned a Pearson correlation coefficient, which represents the degree of correlation between the corresponding independent variable and the oil quality indicator attenuation value. Model training termination conditions include: the error between the oil quality indicator attenuation value predicted by the least squares regression model and the oil quality indicator attenuation value at the monitoring point in the training sample is less than a difference threshold, and the first and second sorting results are the same. The first sorting result is the result of sorting the independent variables in order of the corresponding regression coefficients, while the second sorting result is the result of sorting the independent variables in order of the corresponding Pearson correlation coefficients.

[0155] It should be noted that Figure 4The module division described is illustrative and represents only one logical functional division. Actual implementations may employ different divisions. For example, two or more functions may be integrated into a single processing module. These integrated modules may be implemented as either hardware or software functional modules.

[0156] In an exemplary embodiment, as described above, the computing device may be a computer or a server or other electronic device with computing and processing functions. In this case, the present application also provides an electronic device, Figure 5 This is a schematic diagram of the composition of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device includes: a processor 10 , a memory 20 , a communication line 30 , a communication interface 40 , and an input / output interface 50 .

[0157] The processor 10 , the memory 20 , the communication interface 40 , and the input / output interface 50 may be connected via a communication line 30 .

[0158] The processor 10 is used to execute the instructions stored in the memory 20 to implement the method for calculating the attenuation value of the quality index of the finished oil pipeline provided in the above embodiment of the present application. The processor 10 can be a CPU, a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller (MCU) / single-chip microcomputer / single-chip microcomputer, a programmable logic device (PLD) or any combination thereof. The processor 10 can also be any other device with processing functions, such as a circuit, a device or a software module, which is not limited in the embodiment of the present application. In one example, the processor 10 may include one or more CPUs, such as Figure 5 As an optional implementation, the electronic device may include multiple processors, for example, in addition to the processor 10, it may also include a processor 60 ( Figure 5 The dashed line is used as an example.

[0159] The memory 20 is used to store instructions. For example, the instruction may be a computer program. Optionally, the memory 20 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, etc., and the embodiments of the present application are not limited thereto.

[0160] It should be noted that the memory 20 may exist independently of the processor 10 or may be integrated with the processor 10. The memory 20 may be located inside the electronic device or outside the electronic device, which is not limited in the embodiment of the present application.

[0161] The communication line 30 is used to transmit information between the components included in the electronic device.

[0162] Communication interface 40 is used to communicate with other devices or other communication networks. Such other communication networks may be Ethernet, radio access networks (RAN), wireless local area networks (WLAN), etc. Communication interface 40 may be a module, circuit, transceiver, or any other device capable of communication.

[0163] The input / output interface 50 is used to implement human-computer interaction between a user and the electronic device, for example, to implement action interaction or information interaction between the user and the electronic device.

[0164] For example, the input / output interface 50 may be a mouse, keyboard, display screen, or touch screen screen, etc. Action interaction or information interaction between a user and the electronic device may be achieved through the mouse, keyboard, display screen, or touch screen screen, etc.

[0165] It should be noted that Figure 5 The structure shown in the figure does not constitute a limitation on the electronic device, except Figure 5 In addition to the components shown, the electronic device may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0166] In an exemplary embodiment, the present application also provides a computer program product, which includes computer instructions. When the computer instructions are executed in an electronic device, the electronic device implements the method in the aforementioned method embodiment.

[0167] In an exemplary embodiment, the present application also provides a computer-readable storage medium including software instructions. When the software instructions are executed in an electronic device, the electronic device implements the method in the aforementioned method embodiment. The computer-readable storage medium can be a non-transitory computer-readable storage medium, for example, a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0168] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0169] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0170] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

[0171] The above is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for calculating the attenuation value of oil quality indicators in a finished oil pipeline, characterized in that: The method comprises: Acquiring operational status information of a refined oil pipeline; the operational status information includes flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the refined oil pipeline; Determining, based on the operating status information and the attenuation value prediction model, an attenuation value of a quality index of the refined oil after being transported through the refined oil pipeline; The attenuation value prediction model is used to predict the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline based on the operating status information of the finished oil pipeline.

2. The method according to claim 1, characterized in that The attenuation value prediction model satisfies the following formula: Wherein, Y represents the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline; represents the intercept term; Q represents the flow rate of the product oil pipeline; represents the regression coefficient of the flow rate of the finished oil pipeline; L represents the mileage of the pipeline; represents the regression coefficient of the pipeline mileage; H represents the pipeline elevation fluctuation rate; represents the regression coefficient of the pipeline elevation fluctuation rate; D represents the pipe diameter change rate, Represents the regression coefficient of the pipe diameter change rate.

3. The method according to claim 1, characterized in that The method further comprises: Based on the attenuation value and the output oil quality requirement, the input oil quality of the finished oil pipeline is determined.

4. The method according to claim 3, characterized in that The refined oil includes gasoline or diesel; the refined oil quality index of gasoline includes the final distillation point; the refined oil quality index of diesel includes the flash point; the determining the input oil quality of the refined oil pipeline based on the attenuation value and the output oil quality requirement includes: In a case where the refined oil transported by the refined oil pipeline is gasoline, determining the input oil quality of the refined oil pipeline based on the difference between the attenuation value and the output oil quality requirement; In the case where the finished oil transported by the finished oil pipeline is diesel, the input oil quality of the finished oil pipeline is determined based on the output oil quality requirement and the sum of the attenuation value.

5. The method according to claim 1, wherein The method further comprises: Acquire a training sample set; the training sample set includes multiple training samples, each training sample includes operating status information at a monitoring point in the finished oil pipeline and an attenuation value of an oil quality index at the monitoring point; the operating status information at the monitoring point includes: flow rate at the monitoring point, pipeline mileage between the first pump of the finished oil pipeline and the monitoring point, pipeline elevation fluctuation rate of the pipeline between the first pump of the finished oil pipeline and the monitoring point, and pipe diameter change rate of the pipeline between the first pump of the finished oil pipeline and the monitoring point; the attenuation value of the oil quality index at the monitoring point is the absolute value of the difference between the oil quality index at the first pump of the finished oil pipeline and the oil quality index at the monitoring point; Based on the training sample set, the initial model of the attenuation value prediction model is trained to obtain the attenuation value prediction model.

6. The method according to claim 5, characterized in that The initial model includes a least squares regression model; and the initial model of the attenuation value prediction model is trained based on the training sample set to obtain the attenuation value prediction model, including: The operating status information in the training sample is used as the independent variable, and the attenuation value of the oil quality index in the training sample is used as the dependent variable. The least squares method is used to determine the regression coefficient corresponding to each independent variable in the least squares regression model until the model training end condition is met, thereby obtaining the attenuation value prediction model.

7. The method according to claim 6, characterized in that Each independent variable corresponds to a Pearson correlation coefficient, which is used to indicate the degree of correlation between the corresponding independent variable and the attenuation value of the oil quality index; The conditions for ending model training include: the error between the oil quality index attenuation value predicted by the least squares regression model and the oil quality index attenuation value at the monitoring point in the training sample is less than a difference threshold, and the first sorting result is the same as the second sorting result; the first sorting result is the result of sorting the independent variables in order of the corresponding regression coefficients; the second sorting result is the result of sorting the independent variables in order of the corresponding Pearson correlation coefficients.

8. A device for calculating the attenuation value of oil quality indicators in a finished oil pipeline, characterized in that: The device includes: an acquisition module and a processing module; The acquisition module is used to acquire the operating status information of the refined oil pipeline; the operating status information includes the flow rate, pipeline mileage, pipeline elevation fluctuation rate, and pipe diameter change rate of the refined oil pipeline; The processing module is used to determine the attenuation value of the quality index of the refined oil after being transmitted through the refined oil pipeline based on the operating status information and the attenuation value prediction model; The attenuation value prediction model is used to predict the attenuation value of the quality index of the finished oil after being transmitted through the finished oil pipeline based on the operating status information of the finished oil pipeline.

9. An electronic device, characterized in that: include: processor and memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The readable storage medium includes: computer instructions; When the computer instructions are executed in an electronic device, the electronic device is enabled to implement the method according to any one of claims 1 to 7.

Images