Method, device, equipment and storage medium for determining oil friction

Abstract

The present application discloses a method, device, equipment and storage medium for determining the friction resistance of oil products, belonging to the technical field of oil product transportation. The method first obtains the first oil product characteristics corresponding to the current time of the oil pipeline, and then inputs the first oil product characteristics into the friction resistance determination model to obtain the first friction resistance value; moreover, based on the first oil product characteristics and the first relationship data, a second friction resistance value is determined, and then the first friction resistance value is compared with the second friction resistance value, and whether there is an abnormality in the friction resistance of the oil product is determined according to the comparison result. It can be seen that this method compares the friction resistance value determined by the model with the friction resistance value determined by the relationship data, so that it is not necessary for manual judgment, and misjudgment can be avoided, thereby improving the accuracy of determining the abnormality of the friction resistance of the oil product.

Description

Technical Field

[0001] The present application relates to the technical field of oil product transportation, and particularly relates to a method, device, equipment and storage medium for determining oil product friction. Background Art

[0002] During the transportation of refined oil products, it often occurs that different types of oil products are alternately transported in a pipeline. For example, during alternate transportation, the front section in the pipeline is the first oil product and the rear section is the second oil product, then a small section of mixed oil of the first oil product and the second oil product will be generated in the middle. Among them, the interface between the first oil product and the second oil product is called the batch interface. During the transportation process, as the position of the batch interface changes, the friction of the oil products in the pipeline will also change. Since the abnormal change of the oil product friction has an important impact on the safe transportation of oil products, therefore, how to determine whether the oil product friction has an abnormality has become an urgent problem to be solved.

[0003] In the related art, mainly the friction of the oil product corresponding to the current time is first determined by a formula, and then relevant personnel determine whether the friction of the oil product has an abnormality according to the change rule of the historical friction.

[0004] However, determining whether the oil product friction has an abnormality manually is easily affected by subjective factors and experience, and there is a situation of misjudgment, and the accuracy is relatively low. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, equipment and storage medium for determining oil product friction, which can improve the accuracy of determining the abnormality of oil product friction. The specific technical solutions are as follows:

[0006] On the one hand, the embodiments of the present application provide a method, device, equipment and storage medium for determining oil product friction, and the method includes:

[0007] Obtain the first oil product characteristics corresponding to the current time of the oil transportation pipeline, where the first oil product characteristics are characteristics that affect the oil product friction;

[0008] Input the first oil product characteristics into the friction determination model to obtain a first friction value; wherein, the friction determination model includes at least one of a first friction determination model and a second friction determination model; the first friction determination model is trained based on a sample set and multiple first sample oil product frictions, and the sample set includes multiple first sample oil product characteristics; the second friction determination model is trained based on multiple training sets and the multiple first sample oil product frictions; wherein, for each training set, the training set is obtained by randomly sampling the sample set multiple times, and after each random sampling, the sampled first sample oil product characteristics are put back into the sample set, and each training set is obtained by the same number of sampling times;

[0009] Determine a second friction value based on the first oil product characteristic and the first relationship data; the first relationship data is used to represent the relationship between the first oil product characteristic and the oil product friction;

[0010] Determine the abnormal situation of the oil product friction based on the first friction value and the second friction value.

[0011] In a possible implementation manner, the friction determination model includes a first friction determination model and a second friction determination model;

[0012] The step of inputting the first oil product characteristic into the friction determination model to obtain a first friction value includes:

[0013] Input the first oil product characteristic into the first friction determination model to obtain a third friction value;

[0014] Input the first oil product characteristic into the second friction determination model to obtain a fourth friction value;

[0015] Determine the first friction value based on the third friction value and the fourth friction value.

[0016] In another possible implementation manner, the training process of the first friction determination model includes:

[0017] Use the multiple first sample oil product frictions as the target values of the current machine learning model, and perform model training based on the target values of the current machine learning model, the sample set, and multiple initial weights until the model meets the convergence condition to obtain the current machine learning model; the initial weights are the weights corresponding to the first sample oil product characteristics;

[0018] Determine the first difference between the output value output by the current machine learning model and its corresponding target value;

[0019] Update the weights of the first sample oil product characteristics based on the first difference;

[0020] Use the first difference as the target value of the next machine learning model, and perform model training based on the target value of the next machine learning model, the sample set, and the updated weights of the multiple first sample oil product characteristics to obtain the next machine learning model;

[0021] Use the next machine learning model as the current machine learning model, and execute the step of determining the first difference between the output value output by the current machine learning model and its corresponding target value until a preset number of machine learning models are obtained;

[0022] Determine the first friction determination model based on the preset number of machine learning models.

[0023] In another possible implementation, the first sample oil product characteristics include a plurality of first sub-characteristics;

[0024] The process of determining the first sample oil product characteristics includes:

[0025] Obtain a plurality of second sub-characteristics and the first sample oil product friction corresponding to the plurality of second sub-characteristics;

[0026] Determine a plurality of first correlation parameters and a plurality of second correlation parameters; the first correlation parameters are parameters used to represent the correlation degree between every two second sub-characteristics; the second correlation parameters are parameters used to represent the correlation degree between each second sub-characteristic and its corresponding first sample friction;

[0027] Based on the plurality of first correlation parameters and the plurality of second correlation parameters, screen the plurality of second sub-characteristics to obtain the plurality of first sub-characteristics.

[0028] In another possible implementation, the step of screening the plurality of second sub-characteristics based on the plurality of first correlation parameters and the plurality of second correlation parameters to obtain the plurality of first sub-characteristics includes:

[0029] For each first correlation parameter, if the first correlation parameter is greater than a first preset threshold, select one second sub-characteristic from the two second sub-characteristics corresponding to the first correlation parameter, and use the selected second sub-characteristic as a first sub-characteristic;

[0030] For each second correlation parameter, if the second correlation parameter is greater than a second preset threshold, use the second sub-characteristic in the second correlation parameter as a candidate sub-characteristic;

[0031] Perform fitting on the plurality of candidate sub-characteristics and their corresponding first sample oil product frictions to obtain second relationship data; wherein, the second relationship data is used to represent the relationship between the plurality of candidate sub-characteristics and the first sample friction;

[0032] Determine the characteristic constant corresponding to each candidate sub-characteristic in the second relationship data;

[0033] Determine the candidate sub-characteristics with characteristic constants greater than a third preset threshold as first sub-characteristics to obtain the plurality of first sub-characteristics.

[0034] In another possible implementation, the training process of the second friction determination model includes:

[0035] In one round of sampling process, perform multiple random samplings on the sample set to obtain a training set; wherein, after each random sampling, the first sample oil product characteristics of the sampling are put back into the sample set again;

[0036] For each training set, randomly select a part of the first sample oil product features included in the training set;

[0037] Based on the randomly selected part of the first sample oil product features and their corresponding first sample oil product friction, perform model training until the number of iterations reaches the target number of iterations, and obtain the first machine learning model;

[0038] Based on multiple first machine learning models, determine the second friction determination model, where one training set corresponds to one first machine learning model.

[0039] In another possible implementation, the first oil product features include: the elevation difference between the first transfer station and the second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil product is output from the first transfer station, the second pressure at which the oil product enters the second transfer station, and the first instantaneous flow rate at which the oil product is output from the first transfer station; wherein, the oil product is transported from the first transfer station to the second transfer station;

[0040] The determining the second friction value based on the eigenvalue of the first oil product feature and the first relationship data includes:

[0041] Perform conversion processing on the first instantaneous flow rate to obtain a second instantaneous flow rate;

[0042] Based on the density of the oil product, the acceleration due to gravity, and the elevation difference, determine a third pressure;

[0043] Substitute the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relationship data to obtain the second friction value.

[0044] In another possible implementation, the determining the abnormal situation of the oil product friction based on the first friction value and the second friction value includes:

[0045] Determine the difference between the first friction value and the second friction value;

[0046] If the difference is not within the first preset range, determine that there is an abnormality in the oil product friction.

[0047] In another possible implementation, the method further includes:

[0048] Based on the first oil product features, use the friction determination model to predict the friction value within a preset time range;

[0049] Display the friction value within the preset time range.

[0050] In another possible implementation, the method further includes:

[0051] Determine the maximum value and the minimum value of the friction resistance within the preset time range;

[0052] If the maximum value or the minimum value is not within the second preset range, display a warning message.

[0053] On the other hand, an embodiment of the present application provides an oil product friction resistance determination device, and the device includes:

[0054] A first acquisition module, configured to acquire a first oil product feature corresponding to the current time of the oil pipeline, where the first oil product feature is a feature affecting the friction resistance of the oil product;

[0055] A first input module, configured to input the first oil product feature into a friction resistance determination model to obtain a first friction resistance value; where the friction resistance determination model includes at least one of a first friction resistance determination model and a second friction resistance determination model; the first friction resistance determination model is trained based on a sample set and multiple first sample oil product friction resistances, and the sample set includes multiple first sample oil product features; the second friction resistance determination model is trained based on multiple training sets and the multiple first sample oil product friction resistances; where, for each training set, the training set is obtained by performing multiple random samplings on the sample set, and after each random sampling, the sampled first sample oil product features are put back into the sample set, and each training set is obtained through the same number of sampling times;

[0056] A first determination module, configured to determine a second friction resistance value based on the first oil product feature and first relationship data; the first relationship data is used to represent the relationship between the first oil product feature and the friction resistance of the oil product;

[0057] A second determination module, configured to determine an abnormal condition of the friction resistance of the oil product based on the first friction resistance value and the second friction resistance value.

[0058] In a possible implementation, the friction resistance determination model includes a first friction resistance determination model and a second friction resistance determination model;

[0059] The first input module is configured to input the first oil product feature into the first friction resistance determination model to obtain a third friction resistance value; input the first oil product feature into the second friction resistance determination model to obtain a fourth friction resistance value; and determine the first friction resistance value based on the third friction resistance value and the fourth friction resistance value.

[0060] In another possible implementation, the device further includes:

[0061] The first training module is configured to use the friction resistances of the multiple first sample oils as the target values of the current machine learning model, and perform model training based on the target values of the current machine learning model, the sample set, and multiple initial weights until the model meets the convergence condition, thereby obtaining the current machine learning model; the initial weights are the weights corresponding to the first sample oil characteristics.

[0062] The third determination module is configured to determine a first difference between the output value output by the current machine learning model and its corresponding target value.

[0063] The update module is configured to update the weights of the first sample oil characteristics based on the first difference.

[0064] The second training module is configured to use the first difference as the target value of the next machine learning model, and perform model training based on the target value of the next machine learning model, the sample set, and the updated weights of the multiple first sample oil characteristics, thereby obtaining the next machine learning model.

[0065] The fourth determination module is further configured to determine the first friction resistance determination model based on the preset number of machine learning models.

[0066] In another possible implementation, the first sample oil characteristics include multiple first sub-characteristics.

[0067] The apparatus further includes:

[0068] The second acquisition module is configured to acquire multiple second sub-characteristics and the friction resistances of the first sample oils corresponding to the multiple second sub-characteristics.

[0069] The fifth determination module is configured to determine multiple first correlation parameters and multiple second correlation parameters; the first correlation parameters are parameters used to represent the correlation degree between every two second sub-characteristics; the second correlation parameters are parameters used to represent the correlation degree between each second sub-characteristic and its corresponding first sample friction resistance.

[0070] The screening module is configured to screen the multiple second sub-characteristics based on the multiple first correlation parameters and the multiple second correlation parameters, thereby obtaining the multiple first sub-characteristics.

[0071] In another possible implementation, the screening module is configured to, for each first relevant parameter, if the first relevant parameter is greater than a first preset threshold, select one second sub-feature from two second sub-features corresponding to the first relevant parameter, and use the selected second sub-feature as the first sub-feature; for each second relevant parameter, if the second relevant parameter is greater than a second preset threshold, use the second sub-feature in the second relevant parameter as a candidate sub-feature; fit multiple candidate sub-features and their corresponding first sample oil frictions to obtain second relationship data; wherein the second relationship data is used to represent the relationship between the multiple candidate sub-features and the first sample friction; determine the characteristic constant corresponding to each candidate sub-feature in the second relationship data; and determine the candidate sub-features with characteristic constants greater than a third preset threshold as the first sub-features to obtain the multiple first sub-features.

[0072] In another possible implementation, the apparatus further includes:

[0073] A sampling module, configured to perform multiple random samplings on the sample set during one round of sampling to obtain a training set; wherein the first sample oil features sampled each time are put back into the sample set again;

[0074] A selection module, configured to, for each training set, randomly select some first sample oil features from the first sample oil features included in the training set;

[0075] A third training module, configured to perform model training based on the randomly selected some first sample oil features and their corresponding first sample oil frictions until the number of iterations reaches the target number of iterations to obtain a first machine learning model;

[0076] A sixth determination module, configured to determine the second friction determination model based on multiple first machine learning models, where one training set corresponds to one first machine learning model.

[0077] In another possible implementation, the first oil feature includes: the elevation difference between a first transfer station and a second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil is output from the first transfer station, the second pressure at which the oil enters the second transfer station, and the first instantaneous flow rate at which the oil is output from the first transfer station; wherein the oil is transported from the first transfer station to the second transfer station.

[0078] The first determination module is configured to perform conversion processing on the first instantaneous flow rate to obtain a second instantaneous flow rate; determine a third pressure based on the density of the oil product, the acceleration due to gravity, and the elevation difference; substitute the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relationship data to obtain the second friction value.

[0079] In another possible implementation manner, the second determination module is configured to determine the difference between the first friction value and the second friction value; if the difference is not within a first preset range, it is determined that there is an abnormality in the oil product friction.

[0080] In another possible implementation manner, the device further includes:

[0081] A prediction module, configured to predict the friction value within a preset time range based on the first oil product characteristics through the friction determination model;

[0082] A first display module, configured to display the friction value within the preset time range.

[0083] In another possible implementation manner, the device further includes:

[0084] A seventh determination module, configured to determine the maximum value and the minimum value of the friction value within the preset time range;

[0085] A second display module, configured to display a warning message if the maximum value or the minimum value is not within a second preset range.

[0086] On the other hand, an electronic device is provided, where the electronic device includes a processor and a memory, and at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the oil product friction determination method described in any one of the above.

[0087] On the other hand, a computer-readable storage medium is provided, where at least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by the processor to implement the oil product friction determination method described in any one of the above.

[0088] On the other hand, a computer program product is provided, where at least one program code is stored in the computer program product, and the at least one program code is loaded and executed by the processor to implement the oil product friction determination method described in any one of the above.

[0089] The beneficial effects brought by the technical solution provided in the embodiments of the present application are:

[0090] An embodiment of the present application provides an oil product friction resistance determination method. This method determines a first friction resistance value through a friction resistance determination model. Moreover, a second friction resistance value is determined through first relationship data, and then the first friction resistance value is compared with the second friction resistance value. According to the comparison result, it is determined whether there is an abnormality in the oil product friction resistance. It can be seen that this method compares the friction resistance value determined by the model with the friction resistance value determined through relationship data, so that it is not necessary for manual judgment, which can avoid misjudgment, thereby improving the accuracy of determining the abnormality of the oil product friction resistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 is a schematic diagram of the implementation environment of an oil product friction resistance determination method provided by an embodiment of the present application;

[0092] Figure 2 is a flowchart of an oil product friction resistance determination method provided by an embodiment of the present application;

[0093] Figure 3 is a flowchart of training to obtain a first friction resistance determination model provided by an embodiment of the present application;

[0094] Figure 4 is a flowchart of training to obtain a second friction resistance determination model provided by an embodiment of the present application;

[0095] Figure 5 is a schematic diagram of determining the friction resistance through the first friction resistance determination model and the second friction resistance determination model provided by an embodiment of the present application;

[0096] Figure 6 is a schematic structural diagram of an oil product friction resistance determination device provided by an embodiment of the present application;

[0097] Figure 7 is a structural block diagram of a terminal provided by an embodiment of the present application;

[0098] Figure 8 is a structural block diagram of a server provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0099] To make the technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below.

[0100] In the description, claims and drawings of this application, terms such as "first", "second", "third" and "fourth" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0101] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the oil product characteristics, oil product friction resistance, sub-characteristics, etc. involved in this application are obtained under full authorization.

[0102] Figure 1 is a schematic diagram of the implementation environment of a method for determining oil product friction resistance provided by an embodiment of this application. Refer to Figure 1 This implementation environment includes: an electronic device. The electronic device can be provided as the terminal 101, can be provided as the server 102, or can be provided as both the terminal 101 and the server 102. If the electronic device is provided as both the terminal 101 and the server 102, the terminal 101 and the server 102 can be connected through a wired or wireless network. In the embodiments of this application, the electronic device is not specifically limited.

[0103] In the embodiments of this application, the friction resistance determination model includes at least one of a first friction resistance determination model and a second friction resistance determination model. Next, only the case where the friction resistance determination model includes a first friction resistance determination model and a second friction resistance determination model will be used as an example for description.

[0104] If the electronic device is provided as the terminal 101, the first friction resistance determination model and the second friction resistance determination model are deployed to the terminal 101, and the terminal 101 determines a third friction resistance value and a fourth friction resistance value based on the first friction resistance determination model and the second friction resistance determination model respectively. Moreover, the terminal 101 also determines a second friction resistance value through first relationship data, and then determines the abnormal situation of the oil product friction resistance based on the third friction resistance value, the fourth friction resistance value and the second friction resistance value.

[0105] If the electronic device is provided as the server 102, the first friction resistance determination model and the second friction resistance determination model are deployed into the server 102. The server 102 respectively determines the third friction resistance value and the fourth friction resistance value based on the first friction resistance determination model and the second friction resistance determination model. Moreover, the server 102 also determines the second friction resistance value through the first relationship data, and then determines the abnormal situation of the oil product friction resistance based on the third friction resistance value, the fourth friction resistance value, and the second friction resistance value.

[0106] If the electronic device is provided as the terminal 101 and the server 102, the first friction resistance determination model and the second friction resistance determination model are deployed into the server 102. The server 102 respectively determines the third friction resistance value and the fourth friction resistance value based on the first friction resistance determination model and the second friction resistance determination model. Moreover, the server 102 also determines the second friction resistance value through the first relationship data, and then determines the abnormal situation of the oil product friction resistance based on the third friction resistance value, the fourth friction resistance value, and the second friction resistance value. After the server 102 determines the abnormal situation of the oil product friction resistance, it can send the determination result to the terminal 101, and the terminal 101 displays the result.

[0107] Among them, the first friction resistance determination model and the second friction resistance determination model can be trained by the electronic device or can be trained by other devices, and no specific limitation is made thereto. In addition, the oil product friction resistance determined in the embodiments of the present application is the friction resistance of the oil product in the pipeline during the batch interface migration process. For example, if the front section of the pipeline is gasoline and the rear section is diesel, then the diesel pushes the gasoline during the transportation process. Another example is that if the front section of the pipeline is diesel and the rear section is gasoline, then the gasoline pushes the diesel during the transportation process.

[0108] The terminal 101 is at least one of devices such as a mobile phone, a tablet computer, a PC (Personal Computer) device, a smart voice interaction device, and a vehicle-mounted terminal. The server 102 can be at least one of a single server, a server cluster composed of multiple servers, a cloud server, a cloud computing platform, and a virtualization center.

[0109] In the embodiments of the present application, the friction resistance determination model includes at least one of the first friction resistance determination model and the second friction resistance determination model, that is, the electronic device can determine the first friction resistance value only through the first friction resistance determination model, can also determine the first friction resistance value only through the second friction resistance determination model, or can determine the first friction resistance value through the first friction resistance determination model and the second friction resistance determination model. Hereinafter, only the example in which the electronic device determines the first friction resistance value through the first friction resistance determination model and the second friction resistance determination model is used for illustration.

[0110] Figure 2 It is a flowchart of a method for determining the friction resistance of an oil product provided by the embodiments of the present application, which is executed by an electronic device. The method includes:

[0111] Step 201: The electronic device obtains the first oil product characteristics corresponding to the current time of the oil pipeline.

[0112] The first oil product characteristics are characteristics that affect the frictional resistance of the oil product. For example, the first oil product characteristics include the elevation difference between the first transfer station and the second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil product is output from the first transfer station, the second pressure at which the oil product enters the second transfer station, and the first instantaneous flow rate at which the oil product is output from the first transfer station. Among them, the oil product is transported from the first transfer station to the second transfer station.

[0113] The first oil product characteristics may also include the oil product type, the batch interface position, the oil temperature, and the ground temperature. Among them, the batch interface position is the position of the interface between the first oil product and the second oil product. For example, the batch interface position is the interface position between gasoline and diesel, which can reflect the respective proportions of gasoline and diesel in the pipe section between the first transfer station and the second transfer station.

[0114] Step 202: The electronic device inputs the first oil product characteristics into the first frictional resistance determination model to obtain the third frictional resistance value.

[0115] The first frictional resistance determination model is trained based on a sample set and multiple first sample oil product frictional resistances. Among them, the sample set includes multiple first sample oil product characteristics. The training process of the first frictional resistance determination model will be introduced in detail below and will not be elaborated here for the time being.

[0116] The first frictional resistance determination model includes a preset number of machine learning models. Except for the first machine learning model, the target value of each of the remaining machine learning models is the difference between the output value of the previous machine learning model and the target value, that is, the next machine learning model is trained based on the difference between the output value of the current machine learning model and the target value. The electronic device inputs the first oil product characteristics into the preset number of machine learning models respectively to obtain a preset number of frictional resistance values, and based on the weights corresponding to each machine learning model, the preset number of frictional resistance values are weighted and summed to obtain the third frictional resistance value.

[0117] It should be noted that the weights of the preset number of machine learning models can be the same or different. If the weights of the preset number of machine learning models are the same, the weight can be set to 1. Then the process for the electronic device to determine the third frictional resistance value is: the electronic device sums the preset number of frictional resistance values to obtain the third frictional resistance value.

[0118] Step 203: The electronic device inputs the first oil product characteristics into the second frictional resistance determination model to obtain the fourth frictional resistance value.

[0119] The second friction determination model is trained based on multiple training sets and the friction of multiple first sample oils. For each training set, the training set is obtained by randomly sampling the sample set multiple times, and after each random sampling, the first sample oil characteristics of the sampling are put back into the sample set. Each training set is obtained through the same number of samplings. The training process of the second friction determination model will be introduced in detail below and will not be elaborated here for the time being.

[0120] The second friction determination model includes multiple first machine learning models. The electronic device inputs the first oil characteristics into the multiple first machine learning models respectively to obtain multiple friction values, and takes the average value of the multiple friction values as the fourth friction value.

[0121] Step 204: The electronic device determines the first friction value based on the third friction value and the fourth friction value.

[0122] The electronic device obtains the first weight and the second weight. The first weight is the weight corresponding to the third friction value, and the second weight is the weight corresponding to the fourth friction value; based on the first weight and the second weight, the third friction value and the fourth friction value are weighted and summed to obtain the first friction value.

[0123] In this implementation manner, the first weight can be greater than, equal to, or less than the second weight, and no specific limitation is made in this regard. When the first weight is equal to the second weight, the first friction value is the average value of the third friction value and the fourth friction value.

[0124] It should be noted that when the friction determination model includes the first friction determination model and the second friction determination model, the first friction determination model and the second friction determination model can be two independent models, or can be integrated into one friction determination model. If the first friction determination model and the second friction determination model are two independent models, the electronic device needs to input the first oil characteristics twice, that is, input the first oil characteristics into the first friction determination model once and input the first oil characteristics into the second friction determination model once. If the electronic device integrates the first friction determination model and the second friction determination model into one friction determination model, the electronic device only needs to input the first oil characteristics into the friction determination model once.

[0125] Step 205: The electronic device determines the second friction value based on the first oil characteristics and the first relationship data.

[0126] In this step, the first oil characteristics include: the elevation difference, mileage difference, first pressure, second pressure, and first instantaneous flow rate between the first transfer station and the second transfer station.

[0127] The electronic device processes and converts the first instantaneous flow rate to obtain a second instantaneous flow rate; determines a third pressure based on the density of the oil product, the acceleration due to gravity, and the elevation difference; substitutes the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relational data to obtain a fourth friction value. Among them, the first relational data can be expressed as:

[0128]

[0129] Among them, h f represents the fourth friction value, Q represents the first instantaneous flow rate, represents the second instantaneous flow rate, P C represents the first pressure, P R represents the second pressure, represents the third pressure, ρ represents the density of the oil product, g represents the acceleration due to gravity, ΔH represents the elevation difference, and ΔL represents the mileage difference.

[0130] Step 206: The electronic device determines the abnormal situation of the oil product friction based on the first friction value and the second friction value.

[0131] The electronic device determines the difference between the first friction value and the second friction value. If the difference is not within the first preset range, it is determined that there is an abnormality in the oil product friction.

[0132] In the case where there is an abnormality in the oil product friction, the electronic device can give an alarm based on a preset alarm method. For example, the electronic device displays an alarm message, or the electronic device sends a call request to the terminal of a specified person, and this call request is used to request an alarm, or the electronic device gives an audible and visual alarm through an alarm, etc.

[0133] In the embodiments of the present application, the electronic device can also predict the friction value within a preset time range. Correspondingly, this process can be: The electronic device predicts the friction value within a preset time range based on the first oil product characteristics through a friction determination model; displays the friction value within a preset time range.

[0134] When the friction determination model includes a first friction determination model and a second friction determination model, the electronic device predicts the friction value within a preset time range through the first friction determination model and the second friction determination model. Correspondingly, in step 202, when the first friction determination model outputs a third friction value, it will also output a fifth friction value within a preset time range. Similarly, in step 203, when the second friction determination model outputs a fourth friction value, it will also output a sixth friction value within a preset time range. The electronic device determines the friction value within a preset time range based on the fifth friction value and the sixth friction value within a preset time range.

[0135] Among them, when the electronic device determines the third friction value through the first friction determination model, it uses the first oil product characteristic at the current moment. The electronic device keeps the characteristics such as flow rate and temperature in the first oil product characteristic unchanged, determines the batch interface position within a preset time range according to the current conveying speed, and based on the re-determined batch interface position and other unchanged characteristics, makes a prediction through the first friction determination model to obtain the fifth friction value. The process of the electronic device determining the sixth friction value through the second friction determination model is the same as the process of the electronic device determining the fifth friction value through the first friction determination model, and will not be elaborated here.

[0136] After the electronic device determines the friction values within a preset time range, it can display the friction values within the preset time range through a preset display method. For example, the electronic device displays the friction values within the preset time range in the form of a line graph, or the electronic device displays the friction values within the preset time range in other ways.

[0137] In the embodiment of the present application, the electronic device can also determine the maximum and minimum values of the friction values within a preset time range; if the maximum or minimum value is not within the second preset range, an early warning message is displayed. Alternatively, the electronic device determines the difference between the maximum value and the minimum value. If the difference is not within the third preset range, it indicates that the friction change is large. In this case, the electronic device displays an early warning message.

[0138] In the embodiment of the present application, the electronic device can automatically determine the oil product friction at the current time through the first friction determination model and the second friction determination model, avoiding misjudgment due to subjective factors. The electronic device visually displays the friction value determined by the model in a graph, which can reduce the workload of dispatchers and improve work efficiency. In addition, by predicting the friction values for a period of time through the first friction determination model and the second friction determination model, sufficient time can be provided for business personnel to analyze and process, improving the control operation level.

[0139] The embodiment of the present application provides a method for determining oil product friction. This method determines the first friction value through a friction determination model. And, the second friction value is determined through first relationship data, and then the first friction value and the second friction value are compared. According to the comparison result, it is determined whether there is an abnormality in the oil product friction. It can be seen that this method compares the friction value determined by the model with the friction value determined through relationship data, so that no manual judgment is required, and misjudgment can be avoided, thereby improving the accuracy of determining the abnormality of the oil product friction.

[0140] Next, the training process of the first friction determination model is introduced. This training process can be executed by an electronic device or by other devices. In the embodiment of the present application, only the case where the electronic device trains to obtain the first friction determination model is taken as an example for illustration. Refer to Figure 3 , the method includes:

[0141] Step 301: The electronic device obtains a sample set and multiple first sample oil frictions.

[0142] The sample set includes multiple first sample oil characteristics, and the multiple first sample oil characteristics are oil characteristics corresponding to different times. For each first sample oil characteristic, the first sample oil characteristic includes multiple first sub-characteristics.

[0143] In the embodiment of the present application, the process of the electronic device determining the first sample oil characteristic can be implemented through the following steps (1) to (3), including:

[0144] (1) The electronic device obtains multiple second sub-characteristics and the first sample oil frictions corresponding to the multiple second sub-characteristics.

[0145] The multiple second sub-characteristics include elevation difference, mileage difference, first pressure, second pressure, first instantaneous flow rate, temperature, pipe diameter, etc. The multiple second sub-characteristics at the same time correspond to a first sample oil friction.

[0146] In this step, the electronic device can access the SCADA system through an interface and obtain multiple third sub-characteristics from the SCADA system. After the electronic device obtains the multiple third sub-characteristics, it can first perform a difference operation on the multiple third sub-characteristics to determine whether there is a data missing problem. If the number of missing data is greater than the first preset number, an alarm message is displayed. If the number of missing data is less than or equal to the first preset number, the missing data is interpolated and filled, and it is determined whether the filled data is abnormal, the abnormal data is removed, and the remaining data is used as the second sub-characteristics. And the first sample oil friction is determined through the first relational data.

[0147] Among them, the interpolation method can be set and changed as needed. For example, Lagrange interpolation method, Newton interpolation method, Neville interpolation method, etc. The method for determining whether the data is abnormal can be set and changed as needed. For example, threshold method, Pauta criterion method, box plot method, etc.

[0148] (2) The electronic device determines multiple first correlation parameters and multiple second correlation parameters.

[0149] The first correlation parameter is a parameter used to represent the correlation degree between every two second sub-characteristics, and the second correlation parameter is a parameter used to represent the correlation degree between each second sub-characteristic and its corresponding first sample friction.

[0150] In an embodiment of the present application, the electronic device may use the Pearson correlation coefficient to characterize the first correlation parameter and the second correlation parameter. That is, the electronic device determines the Pearson correlation coefficient between every two second sub-features, as well as the Pearson correlation coefficient between each second sub-feature and the friction of the first sample oil product, and uses these two Pearson correlation coefficients as the first correlation parameter and the second correlation parameter respectively.

[0151] When using the Pearson correlation coefficient to characterize the first correlation parameter and the second correlation parameter, for the first correlation parameter, the electronic device may use the quotient of the covariance and the standard deviation between two second sub-features as the first correlation parameter, and use the quotient of the covariance and the standard deviation between the second sub-feature and the friction of the first sample oil product as the second correlation parameter. Of course, the electronic device may also use other methods to characterize the first correlation parameter and the second correlation parameter, and no specific limitation is made in this regard.

[0152] (3) The electronic device screens multiple second sub-features based on multiple first correlation parameters and multiple second correlation parameters to obtain multiple first sub-features.

[0153] For each first correlation parameter, if the first correlation parameter is greater than the first preset threshold, the electronic device selects one second sub-feature from the two second sub-features corresponding to the first correlation parameter, and uses the selected second sub-feature as the first sub-feature.

[0154] In this implementation manner, the first preset threshold can be set and changed as needed. For example, if the first preset threshold is 0.9, the electronic device selects the first correlation parameters greater than 0.9 from multiple first correlation parameters. For the selected first correlation parameters, it selects any one of the two second sub-features in the first correlation parameter as the first sub-feature.

[0155] For each second correlation parameter, if the second correlation parameter is greater than the second preset threshold, the electronic device uses the second sub-feature in the second correlation parameter as a candidate sub-feature; fits multiple candidate sub-features and their corresponding friction of the first sample oil product to obtain second relationship data; determines the characteristic constant corresponding to each candidate sub-feature in the second relationship data; and determines the candidate sub-features with characteristic constants greater than the third preset threshold as the first sub-features to obtain multiple first sub-features. Among them, the second relationship data is used to represent the relationship between multiple candidate sub-features and the friction of the first sample oil product.

[0156] In this implementation manner, the second preset threshold can be set and changed as needed. For example, if the second preset threshold is 0.2, the electronic device determines the absolute value of each second correlation parameter, selects the second correlation parameters with absolute values greater than 0.2 from them, and uses the second sub-features in the selected second correlation parameters as candidate sub-features.

[0157] The electronic device fits multiple candidate sub - features and the friction resistance of the first sample oil product to obtain second relationship data. The second relationship data is a multiple - linear equation with multiple candidate sub - features as independent variables and the friction resistance of the first sample oil product as the dependent variable. For example, the second relationship data is expressed as: Y = K 1 X 1 +K 2 X 2 +…K 3 X 3 +b; where Y represents the friction resistance of the first sample oil product, and X 1 、X 2 ……X 3 represent multiple candidate sub - features, and K 1 、K 2 ……K 3 represent characteristic constants.

[0158] The electronic device takes the candidate sub - features with characteristic constants greater than the third preset threshold as the first sub - features, and finally obtains multiple first sub - features.

[0159] Among them, the third preset threshold can be set and changed as needed. For example, if the third preset threshold is 0.1, the electronic device takes the candidate sub - features with characteristic constants greater than 0.1 as the first sub - features. The fitting method can be set and changed as needed. For example, the fitting method is Lasso regression, and no specific limitation is made here.

[0160] In the embodiments of the present application, screening the first sub - features based on the first correlation parameter and the second correlation parameter can exclude redundant features among two second sub - features with strong correlation and second sub - features with poor correlation with the friction resistance of the sample oil product, so as to determine sub - features with a higher degree of importance. Then, a model is trained according to the sub - features with a higher degree of importance, improving the efficiency and accuracy of model training.

[0161] Step 302: The electronic device takes multiple friction resistances of the first sample oil product as the target values of the current machine - learning model, and performs model training based on the target values of the current machine - learning model, the sample set, and multiple initial weights until the model meets the convergence condition, and obtains the current machine - learning model.

[0162] The initial weights are the weights corresponding to the first sample oil product features. The convergence condition can be set and changed as needed. For example, the convergence condition is that the first sample oil product features are divided up or the difference between two consecutive trainings is less than a preset difference.

[0163] Step 303: The electronic device determines the first difference between the output value output by the current machine - learning model and its corresponding target value.

[0164] For each first sample oil product feature, the electronic device inputs the first sample oil product feature into the first machine learning model to obtain a first output value. The electronic device determines the difference between the first output value and the first sample oil product friction corresponding to the first sample oil product feature as the first difference. Therefore, multiple first differences are obtained in this step.

[0165] Step 304: The electronic device updates the weight of the first sample oil product feature based on the first difference.

[0166] Based on multiple first differences, the electronic device can update the weights of the first sample oil product features with first differences greater than the difference threshold, that is, update the weights of the first sample oil product features with larger first differences; or update the weights of a preset number of first sample oil product features.

[0167] Step 305: The electronic device uses the first difference as the target value of the next machine learning model, and performs model training based on the target value of the next machine learning model, the sample set, and the updated weights of multiple first sample oil product features to obtain the next machine learning model.

[0168] The electronic device uses the first difference as the training target of the next machine learning model, and performs model training again based on the first difference, the sample set, and the updated weights of multiple first sample oil product features until the model meets the convergence condition to obtain the next machine learning model.

[0169] Step 306: The electronic device uses the next machine learning model as the current machine learning model and executes step 303 until a preset number of machine learning models are obtained.

[0170] The electronic device uses the next machine learning model as the current machine learning model, then determines the difference between the output value output by the current machine learning model and its corresponding target value, updates the weights of the first sample oil product features again based on the difference, and then re-performs model training until a preset number of machine learning models are obtained. Among them, the preset number can be set and changed as needed, and no specific limitation is made in this regard.

[0171] It can be seen from this that among the preset number of machine learning models, the target value of the first machine learning model is the first sample oil product friction, and the target value of each of the remaining machine learning models is the difference between the output value and the target value of the previous machine learning model. Through such continuous iterative training, the error between the total output value of the preset number of machine learning models and the first sample oil product friction is gradually reduced.

[0172] Moreover, since the training target of each machine learning model is obtained based on the previous machine learning model, there is a dependency relationship between the preset number of machine learning models.

[0173] Step 307: The electronic device determines a first friction resistance determination model based on a preset number of machine learning models.

[0174] The electronic device integrates a preset number of machine learning models to obtain a first friction resistance determination model, that is, the electronic device forms a first friction resistance determination model with a preset number of machine learning models.

[0175] In the embodiment of the present application, the method for the electronic device to train the first friction resistance determination model is the GBDT (Gradient Boosting Decision Tree) algorithm. This algorithm is an iterative decision tree algorithm, composed of multiple decision trees, and the results of all decision trees are accumulated as the final result. The core idea of the GBDT algorithm is to find a weak learner of a regression tree model, that is, a machine learning model, in each iteration, so that the loss value of this iteration is the smallest. Through multiple iterations, the error is gradually reduced and approaches the true value.

[0176] The GBDT algorithm has the following advantages: (1) It can flexibly process various types of data, including continuous values and discrete values; (2) The prediction accuracy is relatively high; (3) It uses some robust loss functions and has very strong robustness to outliers. For example, the Huber loss function and the Quantile loss function. The GBDT algorithm is a representative algorithm of the boosting algorithm in the ensemble algorithm, and in the oil product friction resistance scenario, compared with other conventional machine learning algorithms, the ensemble algorithm has better effects. Therefore, the embodiment of the present application adopts the GBDT algorithm to determine the first friction resistance determination model.

[0177] Next, the training process of the second friction resistance determination model is introduced. This training process can be executed by the electronic device or by other devices. In the embodiment of the present application, only the case where the electronic device trains to obtain the second friction resistance determination model is taken as an example for illustration. Refer to Figure 4 , and the method includes:

[0178] Step 401: The electronic device obtains a sample set and multiple first sample oil product friction resistances.

[0179] In the embodiment of the present application, the electronic device can first train to obtain the first friction resistance determination model or first train to obtain the second friction resistance determination model.

[0180] If the electronic device first trains to obtain the first friction resistance determination model, since the electronic device has obtained the sample set and multiple first sample oil product friction resistances during the process of training to obtain the first friction resistance determination model, there is no need to repeat the acquisition in this step, and the electronic device can directly execute Step 402.

[0181] If the electronic device first trains to obtain the second friction resistance determination model, the electronic device first executes step 401, and this step 404 is the same as step 301. And in this case, when the electronic device trains to obtain the first friction resistance determination model, there is no need to repeat the acquisition, and it can directly execute step 302.

[0182] Step 402: In one round of sampling, the electronic device performs multiple random samplings on the sample set to obtain a training set.

[0183] After each random sampling, the first sample oil product feature sampled is put back into the sample set again. Among them, the number of random samplings can be set and changed according to needs, and no specific limitation is made in this regard.

[0184] It should be noted that the electronic device obtains multiple training sets through the method in step 402, and each training set is obtained through the same number of samplings. However, due to random sampling and the first sample oil product feature sampled being put back into the sample set again, during subsequent sampling, it is possible to sample the first sample oil product feature that has been sampled before. Therefore, the number of first sample oil product features included in each training set may be the same or different.

[0185] Step 403: For each training set, the electronic device randomly selects some of the first sample oil product features included in the training set.

[0186] For each training set, the number of first sample oil product features randomly selected by the electronic device can be the same or different, and no specific limitation is made in this regard.

[0187] If the number of some first sample oil product features selected from each training set is the same, the electronic device can randomly select a second preset number of first sample oil product features from each training set. If the number of some first sample oil product features selected from each training set is different, the electronic device can randomly select a preset proportion of the first sample oil product features according to the number of first sample oil product features included in the training set.

[0188] Step 404: The electronic device performs model training based on the randomly selected part of the first sample oil product features and their corresponding first sample oil product friction resistances until the number of iterations reaches the target number of iterations to obtain the first machine learning model.

[0189] For each training set, the electronic device performs model training based on the randomly selected part of the first sample oil product features and their corresponding first sample oil product friction resistances until the number of iterations reaches the target number of iterations or the difference between the loss values of two consecutive generations of training is less than the preset difference to obtain the first machine learning model.

[0190] Step 405: The electronic device determines a second friction resistance determination model based on multiple first machine learning models.

[0191] One training set corresponds to one first machine learning model. Therefore, for multiple training sets, the electronic device trains multiple first machine learning models. Since the multiple training sets are independent, there is no dependency relationship between the multiple first machine learning models.

[0192] The electronic device integrates the multiple first machine learning models to obtain a second friction resistance determination model, that is, the electronic device combines the multiple first machine learning models to form a second friction resistance determination model.

[0193] In the embodiment of the present application, the method for the electronic device to train the second friction resistance determination model is the random forest algorithm. This algorithm includes multiple decision trees, and the output result is determined by the mode of the results output by individual trees. This algorithm belongs to the bagging (bootstrap aggregating) algorithm. The core idea is to randomly sample and learn multiple weak learners of improved regression tree models, that is, machine learning models, and then combine multiple weak learners to form a strong learner through decision-making, that is, the second friction resistance determination model. Among them, the improved regression tree model randomly selects some first sample oil product features, and then selects an optimal first sample oil product feature from the selected first sample oil product features to divide the left and right subtrees of the decision tree, thereby enhancing the generalization ability of the model.

[0194] The random forest algorithm has the following advantages: (1) Training can be highly parallelized, which has an advantage in the training speed of large samples in the big data era; (2) Since the decision tree node division features can be randomly selected, when the sample feature dimension is relatively high, the model can still be trained efficiently; (3) After training, the importance of each sample feature for the output can be given; (4) Due to the use of random sampling, the variance of the trained model is small and the generalization ability is strong; (5) It is not sensitive to partial feature loss.

[0195] In the embodiment of the present application, in the case of conventional throughput transportation (most of the time) of the pipeline section, the first friction resistance value determined only by the first friction resistance determination model or the second friction resistance determination model can also meet the requirements, and the friction resistance value determined by the second friction resistance determination model is more accurate. During low throughput transportation (occurring occasionally), the friction resistance value determined by the first friction resistance determination model is more accurate. Therefore, based on the idea of ensemble learning and using the algorithm fusion technology, the accuracy of jointly determining the first friction resistance value by the first friction resistance determination model and the second friction resistance determination model is higher.

[0196] It should be noted that the electronic device can periodically obtain the second sample oil product characteristics and the second sample oil product friction, and train the first friction determination model and the second friction determination model through the second sample oil product characteristics and the second sample oil product friction, so as to update the first friction determination model and the second friction determination model.

[0197] See Figure 5 , from Figure 5 it can be seen that: the electronic device obtains a plurality of third sub-features by accessing the SCADA system, and then preprocesses the plurality of third sub-features to obtain a plurality of second sub-features. A plurality of first sub-features are screened out from the plurality of second sub-features, and then model training is performed based on the first sample oil product characteristics composed of the plurality of first sub-features and their corresponding first sample oil product frictions to obtain a first friction determination model and a second friction determination model respectively. If the friction values determined by the first friction determination model and the second friction determination model in the subsequent process differ greatly from the friction values determined by the first relationship data, an alarm is issued. If the friction values predicted by the first friction determination model and the second friction determination model in the subsequent process are not within the second preset range, a warning is issued.

[0198] In summary, the method provided by the embodiments of the present application can improve the efficiency of diagnosing the batch interface friction of the refined oil pipeline and avoid the influence of subjective factors. This method can utilize the powerful learning power of machine learning to deeply explore the variation law of friction during the transfer process of the refined oil batch interface, predict the friction in the future for a period of time, assist the dispatching work of business personnel, and improve the control operation level.

[0199] Figure 6 is a schematic structural diagram of an oil product friction determination device provided by an embodiment of the present application. See Figure 6 , the device includes:

[0200] A first acquisition module 601, configured to acquire the first oil product characteristics corresponding to the current time of the oil pipeline, where the first oil product characteristics are characteristics that affect the oil product friction;

[0201] A first input module 602, configured to input the first oil product characteristics into a friction determination model to obtain a first friction value; where the friction determination model includes at least one of a first friction determination model and a second friction determination model; the first friction determination model is trained based on a sample set and a plurality of first sample oil product frictions, and the sample set includes a plurality of first sample oil product characteristics; the second friction determination model is trained based on a plurality of training sets and a plurality of first sample oil product frictions; where, for each training set, the training set is obtained by performing multiple random samplings on the sample set, and after each random sampling, the sampled first sample oil product characteristics are put back into the sample set, and each training set is obtained by the same number of sampling times;

[0202] The first determination module 603 is configured to determine a second friction value based on the first oil product feature and the first relationship data; the first relationship data is used to represent the relationship between the first oil product feature and the oil product friction.

[0203] The second determination module 604 is configured to determine the abnormal condition of the oil product friction based on the first friction value and the second friction value.

[0204] In a possible implementation manner, the friction determination model includes a first friction determination model and a second friction determination model;

[0205] The first input module 602 is configured to input the first oil product feature into the first friction determination model to obtain a third friction value; input the first oil product feature into the second friction determination model to obtain a fourth friction value; and determine the first friction value based on the third friction value and the fourth friction value.

[0206] In another possible implementation manner, the apparatus further includes:

[0207] The first training module is configured to use multiple first sample oil product frictions as the target values of the current machine learning model, and perform model training based on the target values of the current machine learning model, the sample set, and multiple initial weights until the model meets the convergence condition, so as to obtain the current machine learning model; the initial weights are the weights corresponding to the first sample oil product features;

[0208] The third determination module is configured to determine a first difference between the output value output by the current machine learning model and its corresponding target value;

[0209] The update module is configured to update the weights of the first sample oil product features based on the first difference;

[0210] The second training module is configured to use the first difference as the target value of the next machine learning model, and perform model training based on the target value of the next machine learning model, the sample set, and the updated weights of the multiple first sample oil product features, so as to obtain the next machine learning model;

[0211] The fourth determination module is further configured to determine the first friction determination model based on a preset number of machine learning models.

[0212] In another possible implementation manner, the first sample oil product features include multiple first sub-features;

[0213] The apparatus further includes:

[0214] The second acquisition module is configured to acquire multiple second sub-features and the first sample oil product frictions corresponding to the multiple second sub-features;

[0215] A fourth determination module, configured to determine a plurality of first correlation parameters and a plurality of second correlation parameters; the first correlation parameter is a parameter used to represent the correlation degree between every two second sub-features; the second correlation parameter is a parameter used to represent the correlation degree between each second sub-feature and its corresponding first sample friction

[0216] A screening module, configured to screen a plurality of second sub-features based on the plurality of first correlation parameters and the plurality of second correlation parameters, to obtain a plurality of first sub-features.

[0217] In another possible implementation manner, the screening module is configured to, for each first correlation parameter, if the first correlation parameter is greater than a first preset threshold, select one second sub-feature from the two second sub-features corresponding to the first correlation parameter, and use the selected second sub-feature as a first sub-feature; for each second correlation parameter, if the second correlation parameter is greater than a second preset threshold, use the second sub-feature in the second correlation parameter as a candidate sub-feature; fit the plurality of candidate sub-features and their corresponding first sample oil product frictions to obtain second relationship data; wherein, the second relationship data is used to represent the relationship between the plurality of candidate sub-features and the first sample friction; determine the characteristic constant corresponding to each candidate sub-feature in the second relationship data; and determine the candidate sub-features with characteristic constants greater than a third preset threshold as first sub-features, to obtain a plurality of first sub-features.

[0218] In another possible implementation manner, the apparatus further includes:

[0219] A sampling module, configured to perform multiple random samplings on a sample set during one round of sampling, to obtain a training set; wherein, after each random sampling, the sampled first sample oil product feature is put back into the sample set again;

[0220] A selection module, configured to, for each training set, randomly select some first sample oil product features from the first sample oil product features included in the training set;

[0221] A third training module, configured to perform model training based on the randomly selected part of the first sample oil product features and their corresponding first sample oil product frictions until the number of iterations reaches a target number of iterations, to obtain a first machine learning model;

[0222] A sixth determination module, configured to determine a second friction determination model based on the plurality of first machine learning models, where one training set corresponds to one first machine learning model.

[0223] In another possible implementation, the first oil product feature includes: the elevation difference between the first transfer station and the second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil product is output from the first transfer station, the second pressure at which the oil product enters the second transfer station, and the first instantaneous flow rate at which the oil product is output from the first transfer station; wherein, the oil product is transported from the first transfer station to the second transfer station.

[0224] The first determination module 603 is configured to perform conversion processing on the first instantaneous flow rate to obtain a second instantaneous flow rate; determine a third pressure based on the density of the oil product, the acceleration due to gravity, and the elevation difference; substitute the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relationship data to obtain a second friction value.

[0225] In another possible implementation, the second determination module 604 is configured to determine the difference between the first friction value and the second friction value; if the difference is not within the first preset range, determine that there is an abnormality in the oil product friction.

[0226] In another possible implementation, the device further includes:

[0227] A prediction module, configured to predict the friction value within a preset time range based on the first oil product feature through a friction determination model.

[0228] A first display module, configured to display the friction value within a preset time range.

[0229] In another possible implementation, the device further includes:

[0230] A fifth determination module, configured to determine the maximum value and the minimum value of the friction value within a preset time range.

[0231] A second display module, configured to display a warning message if the maximum value or the minimum value is not within the second preset range.

[0232] The embodiment of the present application provides an oil product friction determination device, which determines a first friction value through a friction determination model. And, a second friction value is determined through the first relationship data, and then the first friction value is compared with the second friction value, and whether there is an abnormality in the oil product friction is determined according to the comparison result. It can be seen that the device compares the friction value determined by the model with the friction value determined by the relationship data, so that it is not necessary to make a manual judgment, which can avoid misjudgment, thereby improving the accuracy of determining the abnormality of the oil product friction.

[0233] If the electronic device is provided as a terminal, refer to Figure 7 , Figure 7The structural block diagram of a terminal 700 provided by an exemplary embodiment of the present application is shown. The terminal 700 may be a portable mobile terminal, such as: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a notebook computer or a desktop computer. The terminal 700 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

[0234] Generally, the terminal 700 includes: a processor 701 and a memory 702.

[0235] The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 701 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 701 may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0236] The memory 702 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 702 is used to store at least one program code, and the at least one program code is used to be executed by the processor 701 to implement the operations performed by the terminal in the oil friction determination method provided in the method embodiments of the present application.

[0237] In some embodiments, the terminal 700 may further optionally include: a peripheral device interface 703 and at least one peripheral device. The processor 701, the memory 702, and the peripheral device interface 703 may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 703 through a bus, signal lines, or a circuit board. Specifically, the peripheral device includes at least one of: a radio frequency circuit 704, a display screen 705, a camera assembly 706, an audio circuit 707, and a power supply 708.

[0238] The peripheral device interface 703 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 701 and the memory 702. In some embodiments, the processor 701, the memory 702, and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral device interface 703 can be implemented on a separate chip or circuit board, and this embodiment does not limit this.

[0239] The radio frequency circuit 704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 704 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 704 converts an electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on. The radio frequency circuit 704 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, each generation of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 704 may further include a circuit related to NFC (Near Field Communication), and this application does not limit this.

[0240] The display screen 705 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to collect touch signals on or above the surface of the display screen 705. The touch signals can be input as control signals to the processor 701 for processing. At this time, the display screen 705 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, there can be one display screen 705, which is disposed on the front panel of the terminal 700; in other embodiments, there can be at least two display screens 705, which are respectively disposed on different surfaces of the terminal 700 or are in a foldable design; in other embodiments, the display screen 705 can be a flexible display screen, which is disposed on the curved surface or the folding surface of the terminal 700. Even further, the display screen 705 can also be set to an irregular non-rectangular shape, that is, a special-shaped screen. The display screen 705 can be prepared using materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0241] The camera module 706 is used to capture images or videos. Optionally, the camera module 706 includes a front camera and a rear camera. Generally, the front camera is disposed on the front panel of the terminal, and the rear camera is disposed on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to achieve functions such as background blurring by fusing the main camera and the depth-of-field camera, panoramic shooting by fusing the main camera and the wide-angle camera, and VR (Virtual Reality) shooting functions or other fused shooting functions. In some embodiments, the camera module 706 can also include a flash. The flash can be a single-color-temperature flash or a dual-color-temperature flash. A dual-color-temperature flash refers to a combination of a warm-light flash and a cold-light flash, which can be used for light compensation under different color temperatures.

[0242] The audio circuit 707 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals for input to the processor 701 for processing, or input to the radio frequency circuit 704 to enable voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 700. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signal from the processor 701 or the radio frequency circuit 704 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for uses such as ranging. In some embodiments, the audio circuit 707 may further include a headphone jack.

[0243] The power supply 708 is used to supply power to each component in the terminal 700. The power supply 708 may be alternating current, direct current, a disposable battery or a rechargeable battery. When the power supply 708 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charging technology.

[0244] In some embodiments, the terminal 700 further includes one or more sensors 709. The one or more sensors 709 include but are not limited to: an acceleration sensor 710, a gyroscope sensor 711, a pressure sensor 712, an optical sensor 713, and a proximity sensor 714.

[0245] The acceleration sensor 710 can detect the magnitudes of accelerations on the three coordinate axes of the coordinate system established with the terminal 700. For example, the acceleration sensor 710 can be used to detect the components of the gravitational acceleration on the three coordinate axes. The processor 701 can control the display screen 705 to display the user interface in a landscape view or a portrait view based on the gravitational acceleration signal collected by the acceleration sensor 710. The acceleration sensor 710 can also be used for collecting game or user's motion data.

[0246] The gyroscope sensor 711 can detect the body direction and rotation angle of the terminal 700. The gyroscope sensor 711 can cooperate with the acceleration sensor 710 to collect the 3D actions of the user on the terminal 700. Based on the data collected by the gyroscope sensor 711, the processor 701 can implement the following functions: motion sensing (such as changing the UI based on the user's tilting operation), image stabilization during shooting, game control, and inertial navigation.

[0247] The pressure sensor 712 can be disposed on the side frame of the terminal 700 and / or the lower layer of the display screen 705. When the pressure sensor 712 is disposed on the side frame of the terminal 700, it can detect the holding signal of the user on the terminal 700, and the processor 701 performs left / right hand recognition or quick operation based on the holding signal collected by the pressure sensor 712. When the pressure sensor 712 is disposed on the lower layer of the display screen 705, the processor 701 controls the operable controls on the UI interface based on the pressure operation of the user on the display screen 705. The operable controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0248] The optical sensor 713 is used to collect the ambient light intensity. In one embodiment, the processor 701 can control the display brightness of the display screen 705 based on the ambient light intensity collected by the optical sensor 713. Specifically, when the ambient light intensity is high, the display brightness of the display screen 705 is increased; when the ambient light intensity is low, the display brightness of the display screen 705 is decreased. In another embodiment, the processor 701 can also dynamically adjust the shooting parameters of the camera module 706 based on the ambient light intensity collected by the optical sensor 713.

[0249] The proximity sensor 714, also known as a distance sensor, is usually disposed on the front panel of the terminal 700. The proximity sensor 714 is used to collect the distance between the user and the front of the terminal 700. In one embodiment, when the proximity sensor 714 detects that the distance between the user and the front of the terminal 700 is gradually decreasing, the processor 701 controls the display screen 705 to switch from the lit state to the off state; when the proximity sensor 714 detects that the distance between the user and the front of the terminal 700 is gradually increasing, the processor 701 controls the display screen 705 to switch from the off state to the lit state.

[0250] Those skilled in the art can understand that Figure 7 the structure shown in does not limit the terminal 700, and it may include more or fewer components than shown in the figure, or combine some components, or adopt different component arrangements.

[0251] If the electronic device is provided as a server, the structural block diagram of the server can be referred to Figure 8, the server 800 can vary significantly due to different configurations or performances, and may include a central processing unit (CPU) 801 and a memory 802. Among them, at least one program code is stored in the memory 802, and the at least one program code is loaded and executed by the processor 801 to implement the operations performed by the server in the above-mentioned method for determining the frictional resistance of oil products. Of course, the server 800 may also have components such as a wired or wireless network interface, a keyboard, and an input / output interface for input and output. The server 800 may also include other components for implementing the functions of the device, which will not be elaborated here.

[0252] If the electronic device is provided as a terminal and a server, the structural block diagrams of the terminal and the server can be respectively referred to Figure 7 and Figure 8 .

[0253] In an exemplary embodiment, a computer-readable storage medium is also provided. The computer-readable medium stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the method for determining the frictional resistance of oil products in the above-mentioned embodiment.

[0254] In an exemplary embodiment, a computer program product is also provided. The computer program product stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the method for determining the frictional resistance of oil products in the above-mentioned embodiment.

[0255] The above is only for the convenience of those skilled in the art to understand the technical solution of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining the friction resistance of an oil product, characterized in that, the method includes: obtaining a first oil product characteristic corresponding to the current time of the oil pipeline, where the first oil product characteristic is a characteristic affecting the friction resistance of the oil product; inputting the first oil product characteristic into a friction resistance determination model to obtain a first friction resistance value; wherein, the friction resistance determination model includes at least one of a first friction resistance determination model and a second friction resistance determination model; the first friction resistance determination model is trained based on a sample set and multiple first sample oil product friction resistances, and the sample set includes multiple first sample oil product characteristics; the second friction resistance determination model is trained based on multiple training sets and the multiple first sample oil product friction resistances; wherein, for each training set, the training set is obtained by randomly sampling the sample set multiple times, and after each random sampling, the sampled first sample oil product characteristics are put back into the sample set, and each training set is obtained through the same number of sampling times; determining a second friction resistance value based on the first oil product characteristic and first relationship data; the first relationship data is used to represent the relationship between the first oil product characteristic and the friction resistance of the oil product; determining an abnormal situation of the friction resistance of the oil product based on the first friction resistance value and the second friction resistance value.

2. The method according to claim 1, characterized in that, the friction resistance determination model includes a first friction resistance determination model and a second friction resistance determination model; the step of inputting the first oil product characteristic into the friction resistance determination model to obtain a first friction resistance value includes: inputting the first oil product characteristic into the first friction resistance determination model to obtain a third friction resistance value; inputting the first oil product characteristic into the second friction resistance determination model to obtain a fourth friction resistance value; determining the first friction resistance value based on the third friction resistance value and the fourth friction resistance value.

3. The method according to claim 1 or 2, characterized in that, the training process of the first friction resistance determination model includes: using the multiple first sample oil product friction resistances as the target values of the current machine learning model, and performing model training based on the target values of the current machine learning model, the sample set, and multiple initial weights until the model meets the convergence condition to obtain the current machine learning model; the initial weights are the weights corresponding to the first sample oil product characteristics; determining a first difference between the output value output by the current machine learning model and its corresponding target value; updating the weights of the first sample oil product characteristics based on the first difference; using the first difference as the target value of the next machine learning model, and performing model training based on the target value of the next machine learning model, the sample set, and the updated weights of the multiple first sample oil product characteristics to obtain the next machine learning model; using the next machine learning model as the current machine learning model, and performing the step of determining the first difference between the output value output by the current machine learning model and its corresponding target value until a preset number of machine learning models are obtained; determining the first friction resistance determination model based on the preset number of machine learning models.

4. The method according to claim 3, It is characterized in that the first sample oil product characteristics include multiple first sub-characteristics; the process of determining the first sample oil product characteristics includes: obtaining multiple second sub-characteristics and the first sample oil product friction corresponding to the multiple second sub-characteristics; determining multiple first correlation parameters and multiple second correlation parameters; the first correlation parameters are parameters used to represent the correlation degree between every two second sub-characteristics; the second correlation parameters are parameters used to represent the correlation degree between each second sub-characteristic and its corresponding first sample friction; based on the multiple first correlation parameters and the multiple second correlation parameters, screening the multiple second sub-characteristics to obtain the multiple first sub-characteristics.

5. The method according to claim 4, It is characterized in that the screening the multiple second sub-characteristics based on the multiple first correlation parameters and the multiple second correlation parameters to obtain the multiple first sub-characteristics includes: for each first correlation parameter, if the first correlation parameter is greater than a first preset threshold, selecting one second sub-characteristic from the two second sub-characteristics corresponding to the first correlation parameter, and taking the selected second sub-characteristic as a first sub-characteristic; for each second correlation parameter, if the second correlation parameter is greater than a second preset threshold, taking the second sub-characteristic in the second correlation parameter as a candidate sub-characteristic; fitting the multiple candidate sub-characteristics and their corresponding first sample oil product friction to obtain second relationship data; wherein, the second relationship data is used to represent the relationship between the multiple candidate sub-characteristics and the first sample friction; determining the characteristic constant corresponding to each candidate sub-characteristic in the second relationship data; determining the candidate sub-characteristics with characteristic constants greater than a third preset threshold as first sub-characteristics to obtain the multiple first sub-characteristics.

6. The method according to claim 1 or 2, It is characterized in that the training process of the second friction determination model includes: in one round of sampling process, performing multiple random samplings on the sample set to obtain a training set; wherein, after each random sampling, the sampled first sample oil product characteristics are put back into the sample set again; for each training set, randomly selecting some first sample oil product characteristics from the first sample oil product characteristics included in the training set; performing model training based on the randomly selected part of the first sample oil product characteristics and their corresponding first sample oil product friction until the number of iterations reaches the target number of iterations to obtain a first machine learning model; determining the second friction determination model based on multiple first machine learning models, one training set corresponding to one first machine learning model.

7. The method according to claim 1, It is characterized in that the first oil product characteristics include: the elevation difference between the first transfer station and the second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil product is output from the first transfer station, the second pressure at which the oil product enters the second transfer station, and the first instantaneous flow rate at which the oil product is output from the first transfer station; wherein, the oil product is transported from the first transfer station to the second transfer station; Determining a second friction value based on the eigenvalue of the first oil product characteristic and the first relationship data includes: Performing conversion processing on the first instantaneous flow rate to obtain a second instantaneous flow rate; Determining a third pressure based on the density of the oil product, the acceleration due to gravity, and the elevation difference; Substituting the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relationship data to obtain the second friction value.

8. The method according to claim 1, wherein, Determining an abnormal condition of the oil product friction based on the first friction value and the second friction value includes: Determining the difference between the first friction value and the second friction value; If the difference is not within a first preset range, it is determined that there is an abnormality in the oil product friction.

9. The method according to claim 1, wherein, The method further includes: Predicting the friction value within a preset time range based on the first oil product characteristic through the friction determination model; Displaying the friction value within the preset time range.

10. The method according to claim 9, wherein, The method further includes: Determining the maximum value and the minimum value of the friction value within the preset time range; If the maximum value or the minimum value is not within a second preset range, a warning message is displayed.

11. An oil product friction determination device, wherein, The device includes: A first acquisition module for acquiring the first oil product characteristic corresponding to the current time of the oil pipeline, and the first oil product characteristic is a characteristic affecting the oil product friction; A first input module for inputting the first oil product characteristic into the friction determination model to obtain a first friction value; wherein, the friction determination model includes at least one of a first friction determination model and a second friction determination model; the first friction determination model is trained based on a sample set and multiple first sample oil product frictions, and the sample set includes multiple first sample oil product characteristics; the second friction determination model is trained based on multiple training sets and the multiple first sample oil product frictions; wherein, for each training set, the training set is obtained by performing multiple random samplings on the sample set, and after each random sampling, the sampled first sample oil product characteristic is put back into the sample set, and each training set is obtained through the same number of sampling times; A first determination module for determining a second friction value based on the first oil product characteristic and the first relationship data; the first relationship data is used to represent the relationship between the first oil product characteristic and the oil product friction; A second determination module for determining an abnormal condition of the oil product friction based on the first friction value and the second friction value.

12. The device according to claim 11, wherein, The friction determination model includes a first friction determination model and a second friction determination model; The first input module is configured to input the first oil product characteristics into the first friction resistance determination model to obtain a third friction resistance value; input the first oil product characteristics into the second friction resistance determination model to obtain a fourth friction resistance value; and determine the first friction resistance value based on the third friction resistance value and the fourth friction resistance value.

13. The device according to claim 11 or 12, wherein, the device further comprises: a first training module configured to use the multiple first sample oil product friction resistances as the target values of the current machine learning model, and perform model training based on the target values of the current machine learning model, the sample set, and multiple initial weights until the model meets the convergence condition to obtain the current machine learning model; the initial weights are the weights corresponding to the first sample oil product characteristics; a third determination module configured to determine a first difference between the output value output by the current machine learning model and its corresponding target value; an update module configured to update the weights of the first sample oil product characteristics based on the first difference; a second training module configured to use the first difference as the target value of the next machine learning model, and perform model training based on the target value of the next machine learning model, the sample set, and the updated weights of the multiple first sample oil product characteristics to obtain the next machine learning model; the fourth determination module is further configured to use the next machine learning model as the current machine learning model, and execute the step of determining the first difference between the output value output by the current machine learning model and its corresponding target value until a preset number of machine learning models are obtained; and determine the first friction resistance determination model based on the preset number of machine learning models.

14. The device according to claim 13, wherein, the first sample oil product characteristics include multiple first sub-characteristics; the device further comprises: a second acquisition module configured to acquire multiple second sub-characteristics and the first sample oil product friction resistances corresponding to the multiple second sub-characteristics; a fifth determination module configured to determine multiple first correlation parameters and multiple second correlation parameters; the first correlation parameters are parameters used to represent the correlation degree between every two second sub-characteristics; the second correlation parameters are parameters used to represent the correlation degree between each second sub-characteristic and its corresponding first sample friction resistance; a screening module configured to screen the multiple second sub-characteristics based on the multiple first correlation parameters and the multiple second correlation parameters to obtain the multiple first sub-characteristics.

15. The device according to claim 14, wherein, for each first correlation parameter, if the first correlation parameter is greater than a first preset threshold, the screening module is configured to select one second sub-characteristic from the two second sub-characteristics corresponding to the first correlation parameter, and use the selected second sub-characteristic as the first sub-characteristic; for each second correlation parameter, if the second correlation parameter is greater than a second preset threshold, the screening module is configured to use the second sub-characteristic in the second correlation parameter as a candidate sub-characteristic; Fit multiple candidate sub - features and their corresponding first - sample oil product frictional resistances to obtain second relationship data; wherein, the second relationship data is used to represent the relationship between the multiple candidate sub - features and the first - sample frictional resistance; determine the characteristic constant corresponding to each candidate sub - feature in the second relationship data; determine the candidate sub - features with characteristic constants greater than a third preset threshold as first sub - features, and obtain the multiple first sub - features.

16. The device according to claim 11 or 12, wherein, the device further comprises: a sampling module, configured to perform multiple random samplings on the sample set during one round of sampling to obtain a training set; wherein, after each random sampling, the sampled first - sample oil product features are put back into the sample set again; a selection module, configured to, for each training set, randomly select some first - sample oil product features from the first - sample oil product features included in the training set; a third training module, configured to perform model training based on the randomly selected part of the first - sample oil product features and their corresponding first - sample oil product frictional resistances until the number of iterations reaches the target number of iterations to obtain a first machine - learning model; a sixth determination module, configured to determine the second frictional - resistance determination model based on multiple first machine - learning models, where one training set corresponds to one first machine - learning model.

17. The device according to claim 11, wherein, the first oil product features include: the elevation difference between a first transfer station and a second transfer station, the mileage difference between the first transfer station and the second transfer station, the first pressure at which the oil product is output from the first transfer station, the second pressure at which the oil product enters the second transfer station, and the first instantaneous flow rate at which the oil product is output from the first transfer station; wherein, the oil product is transported from the first transfer station to the second transfer station; the first determination module, configured to perform conversion processing on the first instantaneous flow rate to obtain a second instantaneous flow rate; determine a third pressure based on the density of the oil product, the acceleration due to gravity, and the elevation difference; substitute the second instantaneous flow rate, the first pressure, the second pressure, the third pressure, and the mileage difference into the first relationship data to obtain the second frictional - resistance value.

18. The device according to claim 11, wherein, the second determination module, configured to determine the difference between the first frictional - resistance value and the second frictional - resistance value; if the difference is not within a first preset range, determine that there is an abnormality in the oil product frictional resistance.

19. The device according to claim 11, wherein, the device further comprises: a prediction module, configured to predict the frictional - resistance values within a preset time range based on the first oil product features through the frictional - resistance determination model; a first display module, configured to display the frictional - resistance values within the preset time range.

20. The device according to claim 19, wherein, the device further comprises: a seventh determination module, configured to determine the maximum value and the minimum value of the frictional - resistance values within the preset time range; a second display module, configured to display a warning message if the maximum value or the minimum value is not within a second preset range.

21. An electronic device, Characterized in that, The electronic device includes a processor and a memory, and at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the method for determining the frictional resistance of oil products according to any one of claims 1 to 10.

22. A computer-readable storage medium, Characterized in that, At least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor to implement the method for determining the frictional resistance of oil products according to any one of claims 1 to 10.

23. A computer program product, Characterized in that, At least one program code is stored in the computer program product, and the at least one program code is loaded and executed by a processor to implement the method for determining the frictional resistance of oil products according to any one of claims 1 to 10.

Images