Method, device, equipment and storage medium for determining operating parameters of asphalt production

Abstract

The present invention discloses a method, device, equipment and computer-readable storage medium for determining operation parameters in asphalt production. The method includes: obtaining crude oil detection data and setting initial operation parameters; estimating asphalt property index parameters according to a pre-trained estimation model based on a neural network and the initial operation parameters; performing economic benefit calculation on the initial operation parameters that meet the asphalt property index requirements to obtain economic benefit data; updating the initial operation parameters using a nonlinear programming algorithm based on the economic benefit data and repeating the above steps until operation parameters corresponding to economic benefit data meeting the set requirements are obtained. In this application, the estimation model is used to judge whether the asphalt produced with the initial operation parameters meets the property index requirements, and the initial operation parameters are optimized according to the economic benefit data, so that the finally obtained operation parameters can take into account both the economic benefits meeting the set requirements and the asphalt products meeting the asphalt property index requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of petrochemical engineering, and particularly to a method, device, equipment and computer-readable storage medium for determining operating parameters in asphalt production. Background Art

[0002] Petroleum asphalt is one of the main products of petroleum processing. At normal temperature, it is a black or dark brown viscous liquid, semi-solid or solid, with good adhesiveness, insulation and water impermeability, and is widely used in road facilities, building construction, water conservancy projects, etc. Usually, petroleum processing enterprises generally use distillation process to directly produce distilled asphalt. In the actual distillation production of asphalt, there are a large number of operating parameters such as temperature, pressure and flow rate that need to be regulated on the asphalt production device, and these operating parameters directly affect the economic benefits of asphalt production and the product performance of asphalt. Therefore, how to select more reasonable operating parameters for the asphalt production device during the asphalt production process is one of the key research issues in the industry. Summary of the Invention

[0003] The object of the present invention is to provide a method, device, equipment and computer-readable storage medium for determining operating parameters in asphalt production, which can reasonably determine operating parameters and ensure asphalt properties and economic benefits.

[0004] To solve the above technical problems, the present invention provides a method for determining operating parameters in asphalt production, including:

[0005] Obtain crude oil detection data and set initial operating parameters;

[0006] According to a prediction model obtained by pre-training based on a neural network and the initial operating parameters, predict and obtain asphalt property index parameters corresponding to the initial operating parameters;

[0007] If the asphalt property index parameters meet the asphalt property index requirements, perform economic benefit calculation according to the initial operating parameters to obtain economic benefit data corresponding to the initial operating parameters;

[0008] Based on the economic benefit data, update the initial operating parameters using a non-linear programming algorithm, and repeat the step of predicting and obtaining asphalt property index parameters corresponding to the initial operating parameters according to the prediction model obtained by pre-training based on a neural network and the initial operating parameters until the economic benefit data reaches the set requirements, then use the initial operating parameters corresponding to the economic benefit data that reaches the set requirements as the operating parameters for asphalt production.

[0009] Optionally, the creation process of the prediction model includes:

[0010] Obtain historical crude oil detection data samples, as well as corresponding operation parameter samples and asphalt index parameter samples;

[0011] Use a neural network to learn and train the historical crude oil detection data samples, the operation parameter samples, and the asphalt index parameter samples to obtain the prediction model that characterizes the corresponding relationship between the operation parameters and the asphalt property index parameters for different types of crude oil;

[0012] Correspondingly, based on the prediction model obtained by pre-training with a neural network and the initial operation parameters, predict and obtain the asphalt property index parameters corresponding to the initial operation parameters, including:

[0013] Input the crude oil detection data and the initial operation parameters into the prediction model to obtain the asphalt property index parameters.

[0014] Optionally, setting the initial operation parameters includes:

[0015] Divide the initial operation parameters into a first part of operation parameters and a second part of operation parameters;

[0016] Based on historical operation parameters, set the first part of the operation parameters in the initial operation parameters;

[0017] Input the crude oil detection data and the first part of the operation parameters into a mechanism model obtained by mechanism modeling based on AspenPlus software to predict and obtain the second part of the operation parameters in the initial operation parameters;

[0018] Correspondingly, update the initial operation parameters using a nonlinear programming algorithm based on the economic benefit data, including:

[0019] Use a nonlinear programming algorithm to perform an optimization operation on the first part of the operation parameters in the initial operation parameters according to the economic benefit data, and use the optimized first part of the operation parameters as the first part of the updated initial operation parameters;

[0020] Input the optimized and updated first part of the operation parameters and the crude oil detection data into the mechanism model to obtain the updated second part of the operation parameters of the initial operation parameters.

[0021] Optionally, after setting the first part of the operation parameters in the initial operation parameters based on historical operation parameters, it further includes:

[0022] Divide the first part of the operation parameters into sample operation parameters and verification operation parameters;

[0023] Input the crude oil detection data and the sample operation parameters into the mechanism model to predict and obtain the predicted values corresponding to the verification operation parameters;

[0024] Compare the predicted value with the verification operation parameters to determine the accuracy rate of the mechanism model;

[0025] If the accuracy rate is lower than the preset accuracy rate, correct at least one model parameter including tray efficiency, heat exchanger efficiency, component ratio, flow rate, etc. in the mechanism model, and repeat the operation of dividing the first part of the operation parameters into sample operation parameters and verification operation parameters until the accuracy rate of the mechanism model reaches the preset accuracy rate; then perform the operation of inputting the crude oil detection data and the first part of the operation parameters into the mechanism model obtained by mechanism modeling based on AspenPlus software in advance.

[0026] Optionally, obtaining the crude oil detection data includes:

[0027] Obtain the crude oil detection data including at least one of density, sulfur content, nitrogen content, water content, viscosity, residual carbon, and ASTM D2887 distillation curve through rapid crude oil evaluation detection and simulated distillation detection.

[0028] An operating parameter determination device for asphalt production, comprising:

[0029] A data acquisition module, configured to acquire crude oil detection data and set initial operating parameters;

[0030] An index estimation module, configured to estimate asphalt property index parameters corresponding to the initial operating parameters according to a pre-trained estimation model based on a neural network and the initial operating parameters;

[0031] A revenue evaluation module, configured to perform an economic revenue calculation according to the initial operating parameters if the asphalt property index parameters meet the asphalt property index requirements, and obtain economic revenue data corresponding to the initial operating parameters;

[0032] A parameter optimization module, configured to update the initial operating parameters by using a nonlinear programming algorithm based on the economic revenue data, and repeat the step of estimating asphalt property index parameters corresponding to the initial operating parameters according to a pre-trained estimation model based on a neural network and the initial operating parameters until the obtained economic revenue data meets the set requirements, and then use the initial operating parameters corresponding to the economic revenue data that meets the set requirements as the operating parameters for asphalt production.

[0033] Optionally, it further includes a model creation module, and the model creation module includes:

[0034] A sample acquisition unit, configured to acquire historical crude oil detection data samples, as well as corresponding operating parameter samples and asphalt index parameter samples;

[0035] A model training unit for learning and training the historical crude oil detection data samples, the operation parameter samples, and the asphalt index parameter samples using a neural network to obtain the prediction model that characterizes the corresponding relationship between the operation parameters and the asphalt property index parameters corresponding to different types of crude oil;

[0036] Correspondingly, the index prediction module is specifically configured to jointly input the crude oil detection data and the initial operation parameters into the prediction model to obtain the asphalt property index parameters.

[0037] Optionally, the data acquisition module is specifically configured to divide the initial operation parameters into a first part of operation parameters and a second part of operation parameters; set the first part of operation parameters in the initial operation parameters based on historical operation parameters; input the crude oil detection data and the first part of operation parameters into a mechanism model obtained by mechanism modeling based on AspenPlus software in advance to predict and obtain the second part of operation parameters in the initial operation parameters;

[0038] Correspondingly, the parameter optimization module is specifically configured to perform an optimization operation on the first part of operation parameters in the initial operation parameters using a nonlinear programming algorithm according to the economic benefit data, and use the optimized first part of operation parameters as the updated first part of operation parameters in the initial operation parameters; input the optimized and updated first part of operation parameters and the crude oil detection data into the mechanism model to obtain the updated second part of operation parameters in the initial operation parameters.

[0039] An operation parameter determination device for asphalt production, comprising:

[0040] A memory for storing a computer program;

[0041] A processor for implementing the steps of the operation parameter determination method for asphalt production as described in any one of the above when executing the computer program.

[0042] A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the operation parameter determination method for asphalt production as described in any one of the above are implemented.

[0043] A method for determining operating parameters in asphalt production provided by the present invention includes: obtaining crude oil detection data and setting initial operating parameters; predicting asphalt property index parameters corresponding to the initial operating parameters based on a prediction model obtained by pre-training a neural network and the initial operating parameters; if the asphalt property index parameters meet the asphalt property index requirements, performing an economic benefit calculation based on the initial operating parameters to obtain economic benefit data corresponding to the initial operating parameters; updating the initial operating parameters using a nonlinear programming algorithm based on the economic benefit data, and repeating the step of predicting asphalt property index parameters corresponding to the initial operating parameters based on the prediction model obtained by pre-training a neural network and the initial operating parameters until the economic benefit data reaches the set requirements, then taking the initial operating parameters corresponding to the economic benefit data that meets the set requirements as the operating parameters for asphalt production.

[0044] In this application, during the process of using crude oil for asphalt production, first, a prediction model obtained by pre-training a neural network is used to predict the asphalt property index parameters corresponding to the set initial operating parameters, so as to determine whether the asphalt produced with the initial operating parameters meets the property index requirements. Then, an economic benefit calculation is performed on the initial operating parameters that are predicted to meet the property index requirements, and a nonlinear programming algorithm optimization calculation is performed on the initial operating parameters based on the obtained economic benefit results, so as to realize cyclic optimization of the initial operating parameters, so that the finally obtained operating parameters can not only obtain better economic benefits but also ensure that the asphalt products produced with these operating parameters meet the property index requirements.

[0045] This application also provides an operating parameter determination device, equipment, and computer-readable storage medium for asphalt production, which have the above beneficial effects. Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a flowchart showing a method for determining operating parameters in asphalt production provided by an embodiment of this application;

[0048] Figure 2 It is a structural block diagram of an operating parameter determination device for asphalt production provided by an embodiment of the present invention. Detailed Embodiments

[0049] In the process of asphalt production, the operation parameter control of the distillation unit for producing asphalt is significantly different from that of a conventional petroleum distillation unit. The adjustment of the operation parameters of the distillation unit directly affects the quality of the products obtained in production. If the petroleum asphalt components obtained at the bottom of the distillation column meet a certain specific asphalt product specification, it is a petroleum asphalt product; otherwise, it becomes vacuum residue. However, when setting operation parameters based on the requirements of asphalt product properties currently, it is often through the combination of chemical engineering principles, mathematical equations, and empirical formulas to roughly determine a reasonable range of operation parameters. But there is currently no relatively mature empirical formula, and the operation parameters determined thereby cannot guarantee good properties of the asphalt product.

[0050] On this basis, it is also necessary to further adjust the operation parameters considering the economic benefits of asphalt production. Ultimately, it is often difficult to determine the most reasonable operation parameters, resulting in the asphalt products obtained in production being difficult to achieve a good balance between property indicators and economic benefits in both aspects.

[0051] Therefore, in this application, a technical solution for determining the operation parameters of asphalt production is provided, so that the determined asphalt products can not only meet the property indicators but also have better economic benefits.

[0052] To enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0053] As Figure 1 shown, Figure 1 is a schematic flowchart of a method for determining operation parameters of asphalt production provided by an embodiment of the present application. The method may include:

[0054] S11: Obtain crude oil detection data and set initial operation parameters.

[0055] This crude oil is also the petroleum crude oil for producing asphalt products; the characteristics of the crude oil also affect the setting of operation parameters to a certain extent.

[0056] The crude oil detection data is also the data obtained by detecting the characteristics of the crude oil for producing asphalt products, and specifically may include one or more of various characteristic parameters such as density, sulfur content, nitrogen content, water content, viscosity, carbon residue, and ASTM D2887 distillation curve.

[0057] It should be noted that the method for determining the operating parameters in this embodiment can be a process of online real-time optimization of the operating parameters during asphalt production. Therefore, in order to avoid the time-consuming detection of the characteristic parameters of crude oil, at least one of the fast evaluation detection or simulated distillation detection of crude oil can be preferentially used to obtain all or part of the above-mentioned crude oil detection data.

[0058] In addition, the operating parameters in this embodiment mainly refer to the adjustment of parameters such as temperature, pressure, flow rate, and flow rate at the operating control nodes in different parts of the distillation unit. There are a large number of operating control nodes in the entire distillation unit. Correspondingly, the operating parameters that need to be set in the entire distillation unit also include a series of parameter data such as temperature, pressure, and flow rate corresponding to different node positions.

[0059] S12: According to the prediction model obtained by pre-training based on a neural network and the initial operating parameters, predict the asphalt property index parameters corresponding to the initial operating parameters.

[0060] The prediction model can be a prediction model obtained by training a neural network using historical operating parameter data and the corresponding asphalt property index parameters, which represents the corresponding relationship between the operating parameters and the physical and chemical property index parameters.

[0061] Furthermore, considering that for crude oils with different characteristics, the corresponding relationship between their operating parameters and asphalt property index parameters may be different. Therefore, in order to ensure the accuracy of the prediction model, in an optional embodiment of the present application, the creation process of the prediction model may include:

[0062] Obtain historical crude oil detection data samples, as well as the corresponding operating parameter samples and asphalt index parameter samples;

[0063] Use a neural network to learn and train the historical crude oil detection data samples, operating parameter samples, and asphalt index parameter samples to obtain a prediction model that represents the corresponding relationship between the operating parameters and asphalt property index parameters corresponding to different types of crude oils.

[0064] Correspondingly, when predicting the asphalt property index parameters corresponding to the set initial operating parameters based on the prediction model, the initial operating parameters and the crude oil detection data should also be used as input data and input into the prediction model to finally obtain the asphalt property index parameters.

[0065] For the neural network in this embodiment, a BP neural network or other neural networks with similar functions can be used, and no specific limitation is made in this embodiment.

[0066] S13: Determine whether the asphalt property index parameters meet the asphalt property index requirements. If not, enter S14; if so, enter S15.

[0067] By using this prediction model to predict the asphalt property index parameters corresponding to the set initial operating parameters, the property indexes of the asphalt produced according to the initial operating parameters can be roughly determined, so as to determine whether the initial operating parameters can produce asphalt products that meet the requirements. This is equivalent to first screening and judging the initial operating parameters from the perspective of asphalt property indexes, and then ensuring that the finally determined operating parameters can meet the requirements of the asphalt product property indexes.

[0068] The asphalt property index parameters can include one or more of penetration, softening point, dynamic viscosity, ductility, flash point. The predicted asphalt property index parameters can be compared with the standard asphalt property index parameters one by one. If the deviation between each asphalt property index parameter and the standard asphalt property index parameter is too large, it is considered that the asphalt property index parameter does not meet the requirements. On the contrary, if the deviation is within the allowable range, it is considered that the asphalt property index parameter meets the requirements.

[0069] S14: Adjust and update the initial operating parameters, and enter S12.

[0070] When adjusting and updating the initial operating parameters, the adjustment of the initial operating parameters can be based on which asphalt property index parameter does not meet the requirements specifically.

[0071] For example, if the temperatures at several specific nodes on the distillation unit are too high, it often leads to a decrease in dynamic viscosity. Therefore, when the predicted dynamic viscosity is too low, the temperature parameters of these specific nodes can be considered to be appropriately reduced.

[0072] The initial operating parameters can also be optimized by using algorithms similar to the nonlinear programming algorithm or other optimization algorithms, and finally the parameter data that meets the requirements of the asphalt property index parameters can be determined.

[0073] Of course, in actual applications, the method of trial and error one by one is not excluded. Increase or decrease a certain operating parameter, and try repeatedly until a set of initial operating data whose corresponding asphalt performance index parameters are closest to the asphalt standard index parameters is finally obtained.

[0074] S15: Perform an economic benefit calculation on the initial operating parameters to obtain the economic benefit data corresponding to the initial operating parameters.

[0075] For the economic benefit data corresponding to the initial operating parameters, specifically, it can be the net income obtained from consuming 1 ton of crude oil.

[0076] Calculate the economic benefits based on the initial operating parameters, mainly using the flow parameters in the initial operating parameters. For example, it can be based on the product of the product flow rate and the product unit price minus the product of the crude oil flow rate and the crude oil unit price minus the product of the energy consumption flow rate and the energy consumption unit price. The energy consumption flow rate and the energy consumption unit price can be similar to the water flow rate, water unit price, etc. Of course, it does not rule out energy consumption in other aspects. The calculation of the product economic benefits belongs to the conventional calculation in the industry and will not be elaborated in detail in this embodiment.

[0077] S16: Determine whether the economic benefit data meets the set requirements. If not, enter S17; if so, enter S18.

[0078] S17: Update the initial operating parameters based on the economic benefit data using the nonlinear programming algorithm and enter S12.

[0079] The nonlinear programming algorithm belongs to one of the optimization algorithms. In this embodiment, on the basis that the economic benefit data does not meet the set requirements, the nonlinear programming algorithm is used to optimize the initial operating parameters with the goal of obtaining the highest economic benefit, which can improve the optimization speed of the initial operating parameters to a certain extent, and then improve the operation efficiency of determining the most suitable operating parameters.

[0080] S18: Use the initial operating parameters corresponding to the economic benefit data as the operating parameters for asphalt production.

[0081] In practical applications, the operation steps of S12, S13, S14, S15, S16, and S17 can be repeatedly executed in a loop to continuously optimize and update the initial operating parameters, and finally obtain higher economic benefit data. Therefore, when updating the initial operating parameters based on the economic benefit data in S17 above, it should be a process of optimizing and updating the initial operating parameters with the goal of obtaining the highest economic benefit data; and the judgment in S16 above whether the economic benefit data meets the set requirements can be regarded as a process of judging whether the loop optimization termination condition is reached. Specifically, as the initial operating parameters are updated, the growth of the economic benefit is very small, or the size of the economic benefit has reached the expected size, both can be considered that the economic benefit data meets the set requirements.

[0082] In summary, in this application, when optimizing the operation parameters in the asphalt production process, the prediction model obtained by neural network training is incorporated. On the basis of taking the highest economic benefit as the optimization goal, the asphalt product property indexes are further predicted through the prediction model, so as to ensure that the finally determined operation parameters can not only ensure good product properties but also obtain higher economic benefits.

[0083] As described above, for the distillation unit for producing asphalt, there are a large number of operating parameters that need to be set. However, in actual applications, it is generally impossible to set each operating parameter manually, and there is also a certain correlation between some operating parameters. Therefore, based on the above embodiments, a mechanism model can be further introduced when determining the operating parameters in the asphalt production process.

[0084] In an alternative embodiment of the present application, the steps of the method for determining the operating parameters of asphalt production may include:

[0085] S21: Obtain the crude oil detection data, and divide the initial operating parameters into a first part of operating parameters and a second part of operating parameters.

[0086] To facilitate the setting of the initial operating parameters, the initial operating parameters can be divided into two parts, and only one part of the operating parameters is set, while the other part of the operating parameters can be determined based on the relationship between the set operating parameters and the un-set operating parameters; for the division method of dividing the initial operating parameters into a first part of operating parameters and a second part of operating parameters, no specific limitation is made in this embodiment, and a random division method can be adopted.

[0087] S22: Based on the historical operating parameters, set the first part of the operating parameters in the initial operating parameters.

[0088] For example, for a certain operating parameter in the first part of the operating parameters, the operating parameter corresponding to better asphalt properties obtained during production in the historical operating parameters can be referred to, and finally the average value can be taken as the average value of this operating parameter; it is also possible to determine the value range of each operating parameter based on the historical operating parameters, and randomly select a value within this value range as the set value of this operating parameter, etc., all of which belong to the optional implementation manners in the present application.

[0089] Of course, in order to reduce the workload of setting the first part of the operating parameters, when dividing the first part of the operating parameters and the second part of the operating parameters, the number of the first part of the operating parameters can be made as small as possible, and the number of the second part of the operating parameters can be made as large as possible, as long as it does not affect the subsequent determination of the second part of the operating parameters based on the first part of the operating parameters.

[0090] S23: Input the crude oil detection data and the first part of the operating parameters into the mechanism model obtained by mechanism modeling based on Aspen Plus software in advance, and predict and obtain the second part of the operating parameters in the initial operating parameters.

[0091] To a certain extent, this mechanism model is equivalent to a simulation model of a distillation unit for asphalt production. This mechanism model may include a raw material processing module, a heat exchange network module, a pre-fractionating column module, an atmospheric column module, a vacuum column module, and necessary temperature, pressure, and flow instrument sensors that match each module.

[0092] Among them, the raw material pretreatment module is responsible for the virtual component cutting of the raw material and the calculation of the electro-desalting process; the heat exchange network module is responsible for the calculation of the heat load, heat transfer efficiency, and material temperature of all heat exchangers; the pre-fractionating column module is responsible for the calculation of the column efficiency, separation accuracy, mass balance, and heat balance of the pre-fractionating column; the atmospheric column module is responsible for the calculation of the column efficiency, separation accuracy, mass balance, and heat balance of the atmospheric column and the attached atmospheric stripping column; the vacuum column module is responsible for the calculation of the column efficiency, separation accuracy, mass balance, and heat balance of the vacuum column and the attached vacuum stripping column.

[0093] Based on this mechanism model, it is possible to determine another part of the operating parameters through some operating parameters and crude oil detection data, and it is also possible to determine another part of the crude oil detection data through the operating parameters and some crude oil detection data. Even determining another part of the operating parameters and another part of the crude oil detection data through some operating parameters and some crude oil detection data all belong to the conventional functions that the mechanism model can achieve, and will not be elaborated in detail in this application.

[0094] In addition, in order to further ensure the accuracy of the mechanism model, in an optional embodiment of this application, before inputting the crude oil detection data and the first part of the operating parameters into the mechanism model obtained by mechanism modeling based on AspenPlus software in advance, it may further include:

[0095] Dividing the first part of the operating parameters into sample operating parameters and verification operating parameters;

[0096] Inputting the crude oil detection data and the sample operating parameters into the mechanism model to predict the predicted values corresponding to the verification operating parameters;

[0097] Comparing the predicted values with the verification operating parameters to determine the accuracy rate of the mechanism model;

[0098] If the accuracy rate is lower than the preset accuracy rate, at least one model parameter including tray efficiency, heat exchanger efficiency, component ratio, and flow rate in the mechanism model is corrected, and the operation of dividing the first part of the operating parameters into sample operating parameters and verification operating parameters is repeated until the accuracy rate of the mechanism model reaches the preset accuracy rate.

[0099] It should be noted that the above steps are equivalent to the process of calibrating each model parameter in the mechanism model. In practical applications, the mechanism model can also be directly calibrated and trained based on historical crude oil detection data and corresponding historical operating parameter data. However, for different types and production batches of crude oil, there will inevitably be certain differences. Therefore, in this embodiment, the first part of the set operating parameters is directly divided into a training set and a validation set, and the mechanism model is learned and trained through this training set and validation set to calibrate the model parameters, so that the mechanism model can more accurately determine the second part of the operating parameters.

[0100] In practical applications, the calibration of the mechanism model can be carried out online in real time. After each optimization of the operating parameters, the mechanism model can be calibrated using the optimized operating parameters.

[0101] S24: Based on the prediction model obtained by pre-training based on a neural network and the initial operating parameters, predict the asphalt property index parameters corresponding to the initial operating parameters.

[0102] When predicting the asphalt property index parameters based on the initial operating parameters, some randomly selected operating parameters from the initial operating parameters can be used as the input values of the prediction model, or all the initial operating parameters can be used as the input values of the prediction model. Of course, the first part of the operating parameters or the second part of the operating parameters divided above can also be directly used as the input values. No specific restrictions are made in this embodiment.

[0103] S25: If the asphalt property index parameters meet the asphalt property index requirements, perform an economic benefit calculation on the initial operating parameters to obtain the economic benefit data corresponding to the initial operating parameters.

[0104] S26: Determine whether the economic benefit data meets the set requirements. If so, enter S27; if not, enter S28.

[0105] S27: Use the initial operating parameters corresponding to the economic benefit data as the operating parameters for asphalt production.

[0106] S28: Update the first part of the operating parameters in the initial operating parameters using a nonlinear programming algorithm based on the economic benefit data, and enter S23.

[0107] In this embodiment, the prediction model obtained based on a neural network, the mechanism model, and the cyclic optimization algorithm are combined to finally realize the optimization calculation of the operating parameters of the asphalt product, providing a reliable data guidance basis for the production of the asphalt product, and ensuring the product properties and economic benefits of asphalt production.

[0108] The operation parameter determination device for asphalt production provided by the embodiments of the present invention will be introduced below. The operation parameter determination device for asphalt production described below can be correspondingly referred to the operation parameter determination method for asphalt production described above.

[0109] Figure 2 It is a structural block diagram of the operation parameter determination device for asphalt production provided by the embodiments of the present invention. Referring to Figure 2 the operation parameter determination device for asphalt production may include:

[0110] A data acquisition module 100, configured to acquire crude oil detection data and set initial operation parameters;

[0111] An index estimation module 200, configured to estimate asphalt property index parameters corresponding to the initial operation parameters according to a pre-trained estimation model based on a neural network and the initial operation parameters;

[0112] A revenue evaluation module 300, configured to perform an economic revenue calculation according to the initial operation parameters if the asphalt property index parameters meet the asphalt property index requirements, and obtain economic revenue data corresponding to the initial operation parameters;

[0113] A parameter optimization module 400, configured to update the initial operation parameters by using a non-linear programming algorithm based on the economic revenue data, and repeat the step of estimating asphalt property index parameters corresponding to the initial operation parameters according to a pre-trained estimation model based on a neural network and the initial operation parameters until the economic revenue data reaches the set requirements, and then use the initial operation parameters corresponding to the economic revenue data as the operation parameters for asphalt production.

[0114] In an optional embodiment of the present application, it further includes a model creation module, and the model creation module includes:

[0115] A sample acquisition unit, configured to acquire historical crude oil detection data samples, as well as corresponding operation parameter samples and asphalt index parameter samples;

[0116] A model training unit, configured to learn and train the historical crude oil detection data samples, the operation parameter samples and the asphalt index parameter samples by using a neural network, and obtain the estimation model representing the corresponding relationship between the operation parameters corresponding to different types of crude oil and the asphalt property index parameters;

[0117] Correspondingly, the index estimation module 200 is specifically configured to jointly input the crude oil detection data and the initial operation parameters into the estimation model to obtain the asphalt property index parameters.

[0118] In an alternative embodiment of the present application, the data acquisition module 100 is specifically configured to divide the initial operation parameters into a first part of operation parameters and a second part of operation parameters; set the first part of operation parameters in the initial operation parameters based on historical operation parameters; input the crude oil detection data and the first part of operation parameters into a mechanism model obtained by mechanism modeling based on AspenPlus software in advance, and predict to obtain the second part of operation parameters in the initial operation parameters;

[0119] Correspondingly, the parameter optimization module 400 is specifically configured to perform an optimization operation on the first part of operation parameters in the initial operation parameters by using a nonlinear programming algorithm according to the economic benefit data, and use the optimized first part of operation parameters as the updated first part of operation parameters in the initial operation parameters; input the optimized and updated first part of operation parameters and the crude oil detection data into the mechanism model to obtain the updated second part of operation parameters in the initial operation parameters.

[0120] In an alternative embodiment of the present application, a model optimization module is further included, and this model optimization module includes:

[0121] A sample division unit, configured to divide the first part of operation parameters into sample operation parameters and verification operation parameters after setting the first part of operation parameters in the initial operation parameters based on historical operation parameters;

[0122] A prediction training unit, configured to input the crude oil detection data and the sample operation parameters into the mechanism model, and predict to obtain a predicted value corresponding to the verification operation parameters;

[0123] A parameter comparison unit, configured to compare the predicted value and the verification operation parameters to determine the accuracy rate of the mechanism model;

[0124] A parameter correction unit, configured to, if the accuracy rate is lower than a preset accuracy rate, correct at least one model parameter in the mechanism model including tray efficiency, heat exchanger efficiency, component ratio, flow rate, etc., and repeat the operation of dividing the first part of operation parameters into sample operation parameters and verification operation parameters until the accuracy rate of the mechanism model reaches the preset accuracy rate; then perform the operation of inputting the crude oil detection data and the first part of operation parameters into a mechanism model obtained by mechanism modeling based on AspenPlus software in advance.

[0125] In an alternative embodiment of the present application, the data acquisition module is specifically configured to obtain the crude oil detection data including at least one of density, sulfur content, nitrogen content, water content, viscosity, carbon residue, and ASTM D2887 distillation curve through rapid crude oil evaluation detection and simulated distillation detection.

[0126] The operating parameter determination device for asphalt production in this embodiment is used to implement the aforementioned method for determining the operating parameters of asphalt production. Therefore, the specific implementation in the operating parameter determination device for asphalt production can be seen in the embodiment part of the method for determining the operating parameters of asphalt production in the previous text, and will not be elaborated here.

[0127] This application also provides an operating parameter determination device for asphalt production, which may include:

[0128] A memory for storing computer programs;

[0129] A processor for implementing the steps of the method for determining the operating parameters of asphalt production described in any one of the above when executing the computer program.

[0130] The method for determining the operating parameters of asphalt production executed by the processor may include:

[0131] Obtain crude oil detection data and set initial operating parameters;

[0132] Based on the prediction model obtained by pre-training based on a neural network and the initial operating parameters, predict and obtain the asphalt property index parameters corresponding to the initial operating parameters;

[0133] If the asphalt property index parameters meet the asphalt property index requirements, perform an economic benefit calculation based on the initial operating parameters to obtain the economic benefit data corresponding to the initial operating parameters;

[0134] Update the initial operating parameters using a non-linear programming algorithm based on the economic benefit data, and repeat the step of predicting and obtaining the asphalt property index parameters corresponding to the initial operating parameters based on the prediction model obtained by pre-training based on a neural network and the initial operating parameters until the economic benefit data reaches the set requirements, then use the initial operating parameters corresponding to the economic benefit data as the operating parameters for asphalt production.

[0135] The operating parameter determination device for asphalt production provided in this embodiment can continuously optimize and update the operating parameters in real time based on the changes in the characteristics of crude oil in the on-line process of asphalt product production in the distillation device, which not only ensures the properties of asphalt products but also improves the economic benefits of producing asphalt products.

[0136] This application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for determining the operating parameters of asphalt production described in any one of the above.

[0137] The computer-readable storage medium may include a random access memory (RAM), internal memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0138] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes the elements inherent in the process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element. In addition, parts of the above technical solutions provided in the embodiments of the present application that are consistent with the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid unnecessary repetition.

[0139] In this article, specific examples are used to illustrate the principles and implementation manners of the present invention. The description of the above embodiments is only for helping to understand the method and its core idea of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. A method for determining operating parameters of asphalt production, characterized in that, Including: Obtain crude oil detection data and set initial operation parameters; Based on a prediction model obtained by pre-training with a neural network and the initial operation parameters, predict and obtain asphalt property index parameters corresponding to the initial operation parameters; If the asphalt property index parameters meet the requirements of asphalt property indexes, perform economic benefit calculation according to the initial operation parameters to obtain economic benefit data corresponding to the initial operation parameters; Update the initial operation parameters using a nonlinear programming algorithm based on the economic benefit data, and repeat the step of predicting and obtaining asphalt property index parameters corresponding to the initial operation parameters according to the prediction model obtained by pre-training with a neural network and the initial operation parameters until the economic benefit data reaches the set requirements, then use the initial operation parameters corresponding to the economic benefit data that reaches the set requirements as the operation parameters for asphalt production; Among them, setting the initial operation parameters includes: Divide the initial operation parameters into a first part of operation parameters and a second part of operation parameters; Based on historical operation parameters, set the first part of operation parameters in the initial operation parameters; Input the crude oil detection data and the first part of operation parameters into a mechanism model obtained by pre-mechanism modeling based on Aspen Plus software to predict and obtain the second part of operation parameters in the initial operation parameters; Correspondingly, updating the initial operation parameters using a nonlinear programming algorithm based on the economic benefit data includes: Perform optimization calculation on the first part of operation parameters in the initial operation parameters using a nonlinear programming algorithm according to the economic benefit data, and use the optimized first part of operation parameters as the first part of operation parameters in the updated initial operation parameters; Input the optimized and updated first part of operation parameters and the crude oil detection data into the mechanism model to obtain the updated second part of operation parameters in the initial operation parameters.

2. The method for determining the operating parameters of asphalt production according to claim 1, characterized in that, The creation process of the prediction model includes: Obtain historical crude oil detection data samples, as well as corresponding operation parameter samples and asphalt index parameter samples; Use a neural network to learn and train the historical crude oil detection data samples, the operation parameter samples and the asphalt index parameter samples to obtain the prediction model representing the corresponding relationship between operation parameters and asphalt property index parameters corresponding to different types of crude oil; Correspondingly, based on a prediction model obtained by pre-training with a neural network and the initial operation parameters, predicting and obtaining asphalt property index parameters corresponding to the initial operation parameters includes: Input the crude oil detection data and the initial operation parameters into the prediction model together to obtain the asphalt property index parameters.

3. The method for determining the operating parameters of asphalt production according to claim 1, characterized in that, After setting the first part of operation parameters in the initial operation parameters based on historical operation parameters, it further includes: Divide the first part of operation parameters into sample operation parameters and verification operation parameters; Input the crude oil detection data and the sample operation parameters into the mechanism model to predict and obtain the predicted value corresponding to the verification operation parameters; Compare the predicted value with the verification operation parameters to determine the accuracy rate of the mechanism model. If the accuracy rate is lower than the preset accuracy rate, at least one model parameter in the mechanism model, including tray efficiency, heat exchanger efficiency, component ratio, flow rate, etc., is corrected, and the operation of dividing the first part of the operation parameters into sample operation parameters and verification operation parameters is repeated until the accuracy rate of the mechanism model reaches the preset accuracy rate; then the operation of inputting the crude oil detection data and the first part of the operation parameters into the mechanism model obtained by mechanism modeling based on Aspen Plus software in advance is performed.

4. The method for determining the operating parameters of asphalt production according to claim 1, characterized in that, Obtain crude oil detection data, including: Obtain the crude oil detection data including at least one of density, sulfur content, nitrogen content, water content, viscosity, carbon residue, and ASTM D2887 distillation curve through rapid crude oil evaluation detection and simulated distillation detection.

5. An operating parameter determination device for asphalt production, characterized in that, Including: A data acquisition module for obtaining crude oil detection data and setting initial operation parameters; An index estimation module for estimating asphalt property index parameters corresponding to the initial operation parameters according to a pre-trained estimation model based on a neural network and the initial operation parameters; A revenue evaluation module for performing economic revenue calculation according to the initial operation parameters if the asphalt property index parameters meet the asphalt property index requirements to obtain economic revenue data corresponding to the initial operation parameters; A parameter optimization module for updating the initial operation parameters using a non-linear programming algorithm based on the economic revenue data, and repeating the step of estimating asphalt property index parameters corresponding to the initial operation parameters according to a pre-trained estimation model based on a neural network and the initial operation parameters until the economic revenue data reaches the set requirements, and then using the initial operation parameters corresponding to the economic revenue data that reaches the set requirements as the operation parameters for asphalt production; Among them, the data acquisition module is specifically used to divide the initial operation parameters into a first part of operation parameters and a second part of operation parameters; set the first part of the operation parameters in the initial operation parameters based on historical operation parameters; input the crude oil detection data and the first part of the operation parameters into a mechanism model obtained by mechanism modeling based on Aspen Plus software in advance to predict and obtain the second part of the operation parameters in the initial operation parameters; Correspondingly, the parameter optimization module is specifically used to perform optimization calculation on the first part of the operation parameters in the initial operation parameters using a non-linear programming algorithm according to the economic revenue data, and use the optimized first part of the operation parameters as the first part of the updated initial operation parameters; input the optimized and updated first part of the operation parameters and the crude oil detection data into the mechanism model to obtain the updated second part of the operation parameters of the initial operation parameters.

6. The operating parameter determination device for asphalt production according to claim 5, characterized in that, It further includes a model creation module, and the model creation module includes: A sample acquisition unit for acquiring historical crude oil detection data samples, as well as corresponding operation parameter samples and asphalt index parameter samples; A model training unit for learning and training the historical crude oil detection data samples, the operation parameter samples, and the asphalt index parameter samples by using a neural network to obtain the prediction model that characterizes the corresponding relationship between the operation parameters corresponding to different types of crude oil and the asphalt property index parameters; Correspondingly, the index prediction module is specifically configured to jointly input the crude oil detection data and the initial operation parameters into the prediction model to obtain the asphalt property index parameters.

7. An operating parameter determination device for asphalt production, characterized in that, Comprising: A memory for storing a computer program; A processor for implementing the steps of the method for determining the operation parameters of asphalt production according to any one of claims 1 to 4 when executing the computer program.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for determining the operation parameters of asphalt production according to any one of claims 1 to 4 are implemented.

Images