Method, device, medium and electronic equipment for determining operating parameter values of processing device

Abstract

The present disclosure relates to a method, device, storage medium and electronic equipment for determining the operating parameter values of a processing device. The method includes: determining the parameter priority of each operating parameter of the processing device; based on the parameter priority, determining the optimal parameter value of each operating parameter in sequence through the following steps: obtaining a set of operating data of the processing device; inputting the operating data into a target impurity content prediction model corresponding to the target operating parameter to be determined this time, to obtain a target impurity content prediction value; and determining the optimal parameter value of the target operating parameter based on the content prediction value and the target impurity content control point. The purpose of the present disclosure is to provide a method, device, storage medium and electronic equipment for determining the operating parameter values of a processing device, which can determine the optimal operating value of each operating parameter while ensuring that the product quality indicators are qualified, thereby reducing the energy consumption required by the processing device during the production process.

Description

Technical Field

[0001] The present disclosure relates to the technical field of petroleum processing, and in particular to a method, device, medium and electronic equipment for determining an operating parameter value of a processing device. Background Art

[0002] During normal production in a wax oil hydrogenation unit, the values of various operating parameters are primarily determined by the experience of the production personnel. This approach presents two problems: First, due to insufficient experience, inappropriate operating parameter values can lead to products that do not meet product specifications. Second, to ensure product quality, production personnel tend to be conservative in controlling and setting operating parameters. While this can yield acceptable products, it results in significant energy losses during the wax oil hydrogenation unit's production process. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a method, device, medium and electronic equipment for determining the operating parameter values of a processing device to solve the above-mentioned technical problems.

[0004] In order to achieve the above-mentioned object, the present disclosure provides, in a first aspect, a method for determining an operating parameter value of a processing device, comprising:

[0005] Determining a parameter priority of each operating parameter of the processing device, wherein the parameter priority is used to indicate an order in which the optimal parameter value of each operating parameter is determined in sequence;

[0006] Based on the parameter priorities, the optimal parameter values of the operating parameters are determined in sequence through the following steps:

[0007] Acquiring a set of operating data of the processing device, the operating data including raw material data of the raw material to be processed and parameter values of each of the operating parameters, the parameter values of each of the operating parameters including initial parameter values of the operating parameters to be determined and optimal parameter values of the determined operating parameters;

[0008] Inputting the operating data into a target impurity content prediction model corresponding to the target operating parameters to be determined this time to obtain a predicted value of the target impurity content;

[0009] The optimal parameter value of the target operating parameter is determined according to the content prediction value and the content control point of the target impurity.

[0010] Optionally, determining the optimal parameter value of the target operating parameter according to the content prediction value and the content control point of the target impurity includes:

[0011] If the content prediction value is greater than the content control point of the target impurity, adjusting the parameter value of the target operating parameter in the operating data, and re-inputting the new operating data into the content prediction model until the obtained target impurity content prediction value is less than or equal to the content control point of the target impurity;

[0012] The current parameter value of the target operating parameter is determined as the optimal parameter value.

[0013] Optionally, determining the parameter priority of each operating parameter of the processing device includes:

[0014] Determining the importance of each type of impurity based on the content analysis index of each type of impurity to be removed in the raw material to be processed;

[0015] Determining the order of removing each type of impurity according to the importance of each type of impurity;

[0016] The parameter priority of each operating parameter is determined according to the removal order of each type of impurities, the importance of each type of impurities and the operating parameters corresponding to each type of impurities.

[0017] Optionally, determining the importance of each type of impurity based on content analysis indicators of each type of impurity to be removed from the raw material to be processed includes:

[0018] For each type of impurity that exists in the form of a compound, determine the conversion ratio of the easily removable compound based on the content analysis indicators of that type of impurity;

[0019] The importance of this type of impurity is determined based on the conversion ratio and a conversion ratio threshold value pre-set for the easily removable compound.

[0020] Optionally, determining the importance of each type of impurity based on content analysis indicators of each type of impurity to be removed from the raw material to be processed includes:

[0021] For each type of impurity existing in the form of a single substance, the importance of this type of impurity is determined based on the content analysis index of this type of impurity and the content analysis index threshold set in advance for this type of impurity.

[0022] Optionally, determining the order of removing each type of impurities according to the importance of each type of impurities includes:

[0023] determining, based on the importance of each type of impurity, whether the importance of each type of impurity is the same;

[0024] For each type of impurities with the same importance, the removal order of the corresponding type of impurities is determined according to the preset removal order;

[0025] For each type of impurities with different importance, the removal order of the corresponding type of impurities is determined according to the importance of each type of impurities.

[0026] Optionally, determining the parameter priority of each operating parameter according to the removal order of each type of impurities, the importance of each type of impurities, and the operating parameters corresponding to each type of impurities includes:

[0027] Determining the initial parameter priority of each operating parameter based on the removal order of each type of impurity and the operating parameters corresponding to each type of impurity, and determining the importance of each operating parameter based on the importance of each type of impurity;

[0028] determining, based on the importance of each of the operating parameters, whether the importance of each of the operating parameters is the same;

[0029] For each of the operation parameters having the same importance, determining the parameter priority of the corresponding operation parameter according to the preset operation parameter priority and the initial parameter priority;

[0030] For each of the operating parameters with different importance, the initial parameter priority is determined as the parameter priority of the corresponding operating parameter.

[0031] Optionally, the training process of the target impurity content prediction model includes:

[0032] Acquire multiple sets of sample operation data marked with labels, each set of sample operation data including sample raw material data and sample values of each of the operating parameters, the labels being used to indicate that the true value of the target impurity content is generated based on the corresponding sample raw material data and the sample values;

[0033] Inputting the sample raw material data and the sample value into the content prediction model to obtain a content prediction value corresponding to the sample raw material data and the sample value, and determining a loss function value based on the content prediction value and the true value of the content indicated by the label;

[0034] The parameters of the content prediction model are updated according to the loss function value.

[0035] A second aspect of the present disclosure provides a device for determining an operating parameter value of a processing device, comprising:

[0036] a first determining module, configured to determine a parameter priority of each operating parameter of the processing device, wherein the parameter priority is used to indicate an order in which optimal parameter values of each operating parameter are sequentially determined;

[0037] The second determination module is configured to determine the optimal parameter value of each of the operating parameters in sequence through the following submodules:

[0038] an acquisition submodule, configured to acquire a set of operating data of the processing device, wherein the operating data includes raw material data of the raw material to be processed and parameter values of each of the operating parameters, wherein the parameter values of each of the operating parameters include initial parameter values of the operating parameters to be determined and optimal parameter values of the determined operating parameters;

[0039] A prediction submodule, configured to input the operating data into a target impurity content prediction model corresponding to the target operating parameters to be determined this time, to obtain a predicted value of the target impurity content;

[0040] The determination submodule is used to determine the optimal parameter value of the target operating parameter according to the content prediction value and the content control point of the target impurity.

[0041] A third aspect of the present disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0042] A fourth aspect of the present disclosure provides an electronic device, including:

[0043] a memory having a computer program stored thereon;

[0044] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods described in the first aspect.

[0045] Through the above technical solution, according to the parameter priority of each operating parameter of the processing device, the corresponding content prediction model and the corresponding impurity content control point are used to determine the optimal operating value of each operating parameter one by one, so as to achieve the optimal operating value of each operating parameter while ensuring that the product quality indicators are qualified, thereby reducing the energy consumption required by the processing device during the production process.

[0046] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0048] Figure 1 is a flow chart showing a method for determining an operating parameter value of a processing device according to an exemplary embodiment of the present disclosure;

[0049] Figure 2 is a schematic diagram showing the importance of each type of impurity in the raw material to be processed according to an exemplary embodiment of the present disclosure;

[0050] Figure 3 is a schematic diagram showing a sequence for determining optimal parameter values of various operating parameters according to an exemplary embodiment of the present disclosure;

[0051] Figure 4 is a structural block diagram of a device for determining an operating parameter value of a processing device according to an exemplary embodiment of the present disclosure;

[0052] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0054] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0055] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0056] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0057] First, the application scenario of the present disclosure is explained. In recent years, with the slowdown in demand for fuel oil, overcapacity in refining, and high requirements for energy conservation and emission reduction, the problems have become increasingly prominent. Improving the production quality and efficiency of refining units and achieving better survival and development have become issues that refinery production / management personnel must face. In the actual production of wax oil hydrogenation units, the parameter values of each operating parameter mainly depend on the work experience of the production personnel. There are two problems in determining the parameter values of each operating parameter based on the work experience of the production personnel: on the one hand, due to the lack of work experience of the production personnel, there is a problem that the parameter values of the operating parameters are not set appropriately, resulting in the production of products that do not meet the product index requirements; on the other hand, in order to ensure that the products produced meet the product index requirements, the production personnel are more conservative in controlling / setting the operating parameters. Therefore, although qualified products can be obtained, the wax oil hydrogenation unit suffers from large energy consumption losses during the production process.

[0058] In order to solve the above technical problems, the relevant technology proposes a model prediction method to determine the optimal parameter value of each operating parameter, that is, based on the parameter value of each operating parameter of the wax oil hydrogenation unit and the raw material data, the content value of each type of impurity in the product is synchronously predicted, thereby determining the parameter value of each operating parameter. Due to the mutual influence between the various operating parameters, if the parameter value of a certain operating parameter changes, the parameter values of other operating parameters will also change accordingly, and the changes in these values are unknown. As a result, during the use of the model, although only the parameter value of a certain operating parameter is modified, the parameter values of other operating parameters will also change, and the changed parameter values cannot be determined. This poses a great challenge to solving the above technical problems.

[0059] In view of this, the embodiments of the present disclosure provide a method, device, medium and electronic equipment for determining the operating parameter values of a processing device, which can determine the optimal operating value of each operating parameter one by one according to the parameter priority of each operating parameter of the processing device, using the corresponding content prediction model and the control point of the corresponding impurity, so as to achieve the determination of the optimal operating value of each operating parameter while ensuring that the product meets the product index requirements, thereby reducing the energy consumption required by the processing device during the production process.

[0060] The following further explains the embodiments of the present disclosure with reference to the accompanying drawings.

[0061] Figure 1 is a flow chart of a method for determining an operating parameter value of a processing device according to an exemplary embodiment of the present disclosure, with reference to Figure 1 , the method for determining the operating parameter value may include the following steps:

[0062] S101, determine the parameter priority of each operating parameter of the processing device, the parameter priority is used to indicate the order of determining the optimal parameter value of each operating parameter in sequence, based on the parameter priority, determine the optimal parameter value of each operating parameter in sequence through steps S102 to S104.

[0063] It should be understood that a wax oil hydrogenation unit generally includes multiple operating parameters, and various impurities in the raw materials to be processed are removed by adjusting the parameter values of the multiple operating parameters.

[0064] It should also be understood that, when removing various types of impurities from the raw materials to be processed, the relevant technology assumes that the various types of impurities are removed synchronously. Therefore, when adjusting the parameter values of the various operating parameters, it is necessary to adjust the parameter values of the various operating parameters synchronously to ensure that the removal efficiency of the various types of impurities is optimal at any time. However, the inventors have found through a large number of observations that each type of impurity in the raw materials to be processed is not removed synchronously in the wax oil hydrogenation device, but there is a certain order of removal, and the order of removal is related to the content analysis index of each type of impurity. Based on this, the inventors determined the operating parameters mainly required to remove each type of impurity according to the characteristics of the hydrogenation reaction of each type of impurity, and cleverly adopted the idea of divide and conquer, and determined the parameter priority of each operating parameter by the order of removal of each type of impurity, and then combined with the corresponding content prediction model and the content control point of the corresponding impurity to determine the optimal operating value of each operating parameter one by one. Since the order of removing each type of impurity is different, when removing the next type of impurity, the current type of impurity has been almost removed. Therefore, even if the parameter value of the current operating parameter changes during the process of adjusting the parameter value of the next operating parameter, it will not have much impact on the content of the current type of impurity. Therefore, it is possible to determine the optimal operating value of each operating parameter while ensuring that the product quality indicators are qualified, thereby reducing the energy consumption required by the processing device during the production process. That is, according to one embodiment of the present disclosure, the parameter priority of each operating parameter of the processing device can include:

[0065] Determine the importance of each type of impurity based on the content analysis index of each type of impurity to be removed in the raw material to be processed; determine the removal order of each type of impurity based on the importance of each type of impurity; determine the parameter priority of each operating parameter based on the removal order of each type of impurity, the importance of each type of impurity and the operating parameters corresponding to each type of impurity.

[0066] It should be understood that various impurities exist in different forms. Some impurities exist as compounds (easily removable compounds and difficult-to-remove compounds), some impurities exist as simple substances, and some impurities exist in both compound and simple substance forms. Illustratively, the impurities contained in wax oil include sulfur impurities, nitrogen impurities, and carbon residue. Of these, sulfur impurities and nitrogen impurities exist as compounds, while carbon residue exists as a simple substance. To better determine the importance of each impurity, the importance of each impurity can be determined based on its form of existence.

[0067] In a possible embodiment, for each type of impurity present in the form of a compound, the conversion ratio of the easily removable compound that is easily removed by the reactor can be determined based on the content analysis index of the impurity, and the importance of the impurity can be determined based on the removal ratio and a conversion ratio threshold pre-set for the easily removable compound. That is, according to one embodiment of the present disclosure, determining the importance of each type of impurity to be removed from the raw material to be processed based on the content analysis index of each type of impurity can include:

[0068] For each type of impurity in the form of a compound, the conversion ratio of the easily removable compound is determined based on the content analysis index of the impurity; the importance of the impurity is determined based on the conversion ratio and the conversion ratio threshold set in advance for the easily removable compound.

[0069] Schematically, for sulfur impurities and nitrogen impurities in wax oil, the conversion ratio of easily removable sulfides and the conversion ratio of easily removable nitrides can be determined based on the content analysis index of sulfur impurities and the content analysis index of nitrogen impurities, respectively. Among them, the content analysis index of sulfur impurities can include the content of wax oil from different sources, the ratio of easily removable sulfides in wax oil from different sources to the total sulfides in wax oil from corresponding sources, and the ratio of difficult-to-remove sulfides in wax oil from different sources to the total sulfides in wax oil from corresponding sources; the content analysis index of nitrogen impurities can include the content of wax oil from different sources, the ratio of easily removable nitrides in wax oil from different sources to the total nitrides in wax oil from corresponding sources, and the ratio of difficult-to-remove nitrides in wax oil from different sources to the total nitrides in wax oil from corresponding sources.

[0070] In a possible embodiment, the content of easily removable sulfides in wax oils from different sources can be determined based on the content of wax oils from different sources, the ratio of easily removable sulfides in the wax oils from different sources to the total sulfur, and the ratio of difficult-to-remove sulfides in the wax oils from different sources to the total sulfur. Then, the content of easily removable sulfides in the wax oils from different sources is added together, and finally the addition result is divided by the total wax oil content to obtain the conversion ratio of easily removable sulfides. That is, the conversion ratio of easily removable sulfides can be determined by the following formula:

[0071]

[0072] Among them, r S represents the conversion ratio of easily removed sulfides, A, B and C represent the wax oil content of different sources in the wax oil to be processed, x SA ( easy ) represents the ratio of easily removable sulfides in A to the total sulfides in A, x SA ( hard ) represents the ratio of difficult-to-remove sulfides in A to the total sulfides in A; x SB(easy) It represents the ratio of easily removable sulfides in B to the total sulfides in B, x SB ( hard ) represents the ratio of difficult-to-remove sulfides in B to the total sulfides in B; x SC ( easy ) represents the ratio of easily removable sulfides in C to the total sulfides in C, x SC ( hard ) represents the ratio of difficult-to-remove sulfides in C to the total sulfides in C. For example, A represents the content of vacuum gas oil, B represents the content of tank area gas oil, and C represents the content of coking gas oil, then x SA ( easy ) represents the ratio of easily removable sulfides in vacuum gas oil to the total sulfides in vacuum gas oil, x SA(hard) It indicates the ratio of difficult-to-remove sulfides in vacuum gas oil to the total sulfides in vacuum gas oil; x SB(easy) It represents the ratio of easily removable sulfides in the tank area wax oil to the total sulfides in the tank area wax oil, x SB(hard) Indicates the ratio of difficult-to-remove sulfides in the tank area wax oil to the total sulfides in the tank area wax oil; x SC(easy) It indicates the ratio of easily removable sulfides in coker gas oil to the total sulfides in coker gas oil, x SC(hard) It indicates the ratio of difficult-to-remove sulfides in coker wax oil to the total sulfides in coker wax oil.

[0073] Similarly, the conversion ratio of easily removable nitrides can be determined based on the following formula:

[0074]

[0075] Among them, r N represents the conversion ratio of easily removed nitrides, x NA(easy) It represents the ratio of easily removable nitrides in A to the total nitrides in A, x NA(hard) It represents the ratio of the difficult-to-remove nitrides in A to the total nitrides in A; x NB(easy) It represents the ratio of easily removable nitrides in B to the total nitrides in B, x NB(hard) It represents the ratio of difficult-to-remove nitrides in B to the total nitrides in B; x NC(easy) It represents the ratio of easily removable nitrides in C to the total nitrides in C, x NC(hard)It indicates the ratio of difficult-to-remove nitrides in C to the total nitrides in C.

[0076] After determining the conversion ratios of easily removable sulfides and easily removable nitrides, the importance of the sulfur and nitrogen impurities is determined by comparing the conversion ratios of the easily removable sulfides and the conversion ratios of the easily removable nitrides with their respective conversion ratio thresholds. For example, if the conversion ratio of the easily removable sulfides is greater than or equal to the preset conversion ratio threshold, the importance of the sulfur impurities is considered high. If the conversion ratio of the easily removable sulfides is less than the preset conversion ratio threshold, the importance of the sulfur impurities is considered low.

[0077] In a possible implementation, for each type of impurity present in elemental form, since the removal process in the wax oil hydrogenation unit is not that complicated, the importance of this type of impurity can be determined based on the content analysis index of this type of impurity and a preset content analysis index threshold. That is, according to one embodiment of the present disclosure, determining the importance of each type of impurity based on the content analysis index of each type of impurity to be removed from the raw material to be processed may include:

[0078] For each type of impurity existing in the form of a single substance, the importance of this type of impurity is determined based on the content analysis index of this type of impurity and the content analysis index threshold set in advance for this type of impurity.

[0079] Schematically, for the carbon residue in wax oil, the carbon residue content of the carbon residue (the content analysis index corresponding to the carbon residue) is first obtained, and then the carbon residue content is compared with the preset carbon residue content threshold (the content analysis index threshold corresponding to the carbon residue). If the carbon residue content is greater than or equal to the carbon residue content threshold, the importance of the carbon residue impurity is considered to be high. When the carbon residue content is less than the carbon residue content threshold, the importance of the carbon residue impurity is considered to be low.

[0080] After determining the importance of each type of impurity, the order of removing each type of impurity can be determined based on the importance of each type of impurity. In a possible embodiment, determining the order of removing each type of impurity based on the importance of each type of impurity may include:

[0081] According to the importance of each type of impurity, determine whether the importance of each type of impurity is the same; for each type of impurity with the same importance, determine the removal order of the corresponding type of impurity according to a preset removal order; for each type of impurity with different importance, determine the removal order of the corresponding type of impurity according to the importance of each type of impurity.

[0082] Schematically, for the sulfur impurities, nitrogen impurities and residual carbon contained in wax oil, the preset removal order is: the removal order of sulfur impurities takes precedence over the removal order of nitrogen impurities, and the removal order of nitrogen impurities takes precedence over the removal order of residual carbon.

[0083] If the importance of sulfur impurities, nitrogen impurities and residual carbon are all high, the removal order of sulfur impurities, nitrogen impurities and residual carbon is determined based on the preset removal order, that is, the removal order of sulfur impurities, nitrogen impurities and residual carbon is: the removal order of sulfur impurities takes precedence over the removal order of nitrogen impurities, and the removal order of nitrogen impurities takes precedence over the removal order of residual carbon.

[0084] If the importance of sulfur impurities, nitrogen impurities and residual carbon is high, low and high respectively, since the importance of residual carbon is greater than that of nitrogen impurities, the removal order of nitrogen impurities and residual carbon is determined according to the importance, that is, the removal order of residual carbon takes precedence over the removal order of nitrogen impurities; since the importance of sulfur impurities is the same as that of residual carbon, the removal order of sulfur impurities and residual carbon is determined according to the preset removal order, and since the removal order of sulfur impurities takes precedence over that of residual carbon in the preset removal order, the removal order of sulfur impurities takes precedence over that of residual carbon, that is, the removal order of sulfur impurities, nitrogen impurities and residual carbon is: the removal order of sulfur impurities takes precedence over that of residual carbon, and the removal order of residual carbon takes precedence over that of nitrogen impurities.

[0085] It should be understood that when using a wax oil hydrogenation unit to remove various impurities in wax oil, different impurities can be removed by adjusting the parameter values of different operating parameters. Among them, sulfur impurities can be removed by adjusting the average temperature T2 of the second bed in the wax oil hydrogenation unit, nitrogen impurities can be removed by adjusting the average temperature T3 of the third bed and the reactor pressure Pin in the wax oil hydrogenation unit, and residual carbon can be removed by adjusting the average temperature T1 of the first bed in the wax oil hydrogenation unit. Therefore, after determining the removal order and importance of each type of impurity, the parameter priority of each operating parameter can be determined according to the removal order of each type of impurity, the importance of each type of impurity and the operating parameters corresponding to each type of impurity. In a possible embodiment, the parameter priority of each operating parameter determined according to the removal order of each type of impurity, the importance of each type of impurity and the operating parameters corresponding to each type of impurity may include:

[0086] According to the removal order of each type of impurities and the operating parameters corresponding to each type of impurities, the initial parameter priority of each operating parameter is determined, and according to the importance of each type of impurities, the importance of each operating parameter is determined; according to the importance of each operating parameter, it is determined whether the importance of each operating parameter is the same; for each operating parameter with the same importance, the parameter priority of the corresponding operating parameter is determined according to the preset operating parameter priority and the initial parameter priority; for each operating parameter with different importance, the initial parameter priority is determined as the parameter priority of the corresponding operating parameter.

[0087] Schematically, as Figure 2 and Figure 3 As shown, Figure 3 The numbers in represent priorities, with 1 representing a higher priority than 2, 2 representing a higher priority than 3, and 3 representing a higher priority than 4. Assume that a certain wax oil contains sulfur impurities, nitrogen impurities, and carbon residue, where the importance of sulfur impurities, nitrogen impurities, and carbon residue is low, high, and high, respectively. The order of removing these impurities is as follows: nitrogen impurities take precedence over carbon residue, which takes precedence over sulfur impurities. Furthermore, the preset operating parameter priority is that temperature-related operating parameters take precedence over reaction pressure-related operating parameters.

[0088] Based on the above assumptions, the initial parameter priority of each operating parameter, determined based on the order of impurity removal for each type and the corresponding operating parameters for each type of impurity, is: T3 and Pin take precedence over T1, and T1 takes precedence over T2. The importance of each operating parameter, determined based on the importance of each impurity type, is T3:Pin:T1:T2 = High:High:High:Low. Since T3, Pin, and T1 have the same importance, the parameter priority of the corresponding operating parameters can be determined based on the preset operating parameter priority and the initial parameter priority. Since the preset operating parameter priority prioritizes temperature-related operating parameters over reaction pressure-related operating parameters, the parameter priority of Pin needs to be adjusted. Specifically, the initial parameter priority of T3 and Pin taking precedence over T1 is adjusted to: T3 takes precedence over T1, and T1 takes precedence over Pin. Furthermore, since Pin and T2 have different importance, the initial parameter priority can be determined as the parameter priority of the corresponding operating parameter, with Pin taking precedence over T2. Therefore, the final parameter priority of each operating parameter is: T3 takes precedence over T1, T1 takes precedence over Pin, and Pin takes precedence over T2.

[0089] After determining the parameter priorities of the various operating parameters, the optimal parameter values of the various operating parameters are determined in sequence based on the parameter priorities through the following steps:

[0090] S102, obtaining a set of operating data of the processing device, wherein the operating data includes raw material data of the raw material to be processed and parameter values of each operating parameter, and the parameter value of each operating parameter includes an initial parameter value of the operating parameter to be determined and an optimal parameter value of the determined operating parameter.

[0091] It should be understood that raw material data includes raw material density, distillation range, sulfur content, nitrogen content, and residual carbon content, and that different raw materials to be processed will have different corresponding raw material density, distillation range, sulfur content, nitrogen content, and residual carbon content. Operating parameters include raw material feed rate, circulating hydrogen amount, reaction pressure, and average temperature of each bed layer. Different raw materials to be processed will have different corresponding operating parameter values.

[0092] S103: Input the operation data into a target impurity content prediction model corresponding to the target operation parameters to be determined this time, to obtain a predicted value of the target impurity content.

[0093] It should be understood that the content prediction model can be implemented based on a linear model or a neural network model in the relevant technology, and the embodiments of the present disclosure do not impose any restrictions on this. In a possible implementation, the computer programming language python can be used to call the deep learning framework Keras to realize the construction of the content prediction model. After the content prediction model is built, in order to be able to use the built content prediction model to realize the content prediction of various impurities in the product, it is also necessary to obtain a large number of training samples to train the built content prediction model. Since the content prediction model corresponding to each type of impurity has the same structure and the same training process, the content prediction model corresponding to sulfur impurities is taken as an example below to illustrate the training process of the content prediction model.

[0094] In a possible implementation, the raw material data of the raw materials to be processed and the sulfur content in the product (if it is a content prediction model corresponding to other types of impurities, the content of other impurities in the product is collected) can be collected from the laboratory information management system (LIMS), and the operating parameters of the wax oil hydrogenation unit can be collected from the integrated control system (DCS). After the training sample collection is completed, in order to ensure that all training samples are valid samples, the collected training samples can be cleaned to eliminate missing, abnormal, erroneous and incomplete data points. After the above data cleaning, all training samples are divided into input data (raw material data and operating parameters) and output data (sulfur content), and it is ensured that the input data and output data correspond one to one in time series. After obtaining the input data and output data, the content prediction model can be trained with the one-to-one corresponding input data and output data to obtain a content prediction model that can predict the target impurity content based on the operating data. That is, according to one embodiment of the present disclosure, the training process of the content prediction model of the target impurity may include:

[0095] Acquire multiple groups of sample operation data marked with labels, each group of sample operation data includes sample raw material data and sample values of each of the operating parameters, and the labels are used to indicate the true value of the target impurity content generated according to the corresponding sample raw material data and the sample values; input the sample raw material data and the sample values into the content prediction model to obtain the content prediction values corresponding to the sample raw material data and the sample values, and determine the loss function value based on the content prediction value and the true content value indicated by the label; and update the parameters of the content prediction model according to the loss function value.

[0096] In order to further ensure the prediction accuracy of the content prediction model, in a possible implementation method, the one-to-one corresponding input data and output data can be divided into a training set, a test set and a validation set according to a preset ratio, wherein the training set is used for training the content prediction model, the validation set is used to determine the optimal hyperparameters of the content prediction model based on the average relative error and the determination coefficient, and the test set is used to determine the prediction effect of the content prediction model based on the average absolute error. When the prediction effect of the content prediction model reaches the preset prediction effect, the content prediction model training is considered to be completed.

[0097] In a possible embodiment, the content prediction model is first trained with the input data and output data in the training set until a preset number of iterations or a preset accuracy is reached. The input data and output data in the validation set are then used to adjust the hyperparameters of the content prediction model, that is, by inputting the input data in the validation set into the content prediction model trained with the training set, the content prediction values corresponding to the input data are obtained, and then the hyperparameters of the content prediction model are adjusted based on the average relative error and determination coefficient calculated for each content prediction value and the corresponding output data. Specifically, if any one of the average relative error and the determination coefficient does not reach the preset value, it indicates that the hyperparameter setting of the content prediction model is inappropriate, and it is necessary to adjust the hyperparameters in the content prediction model until both the average relative error and the determination coefficient reach the preset value. Finally, the input data and output data in the test set are used to verify the training effect of the content prediction model, that is, by inputting the input data in the test set into the content prediction model, the content prediction values corresponding to the input data are obtained, and then the training effect of the content prediction model is judged based on the average absolute error calculated for each content prediction value and the corresponding output data. Specifically, if the mean absolute error reaches a preset mean absolute error threshold, it indicates that the training effect is good and the content prediction model is usable; otherwise, retraining is required to adjust the parameters and / or hyperparameters of the content prediction model.

[0098] The calculation formula for the mean absolute error is:

[0099]

[0100] Among them, MAE represents the mean absolute error, n represents the number of samples, and y i,actual Represents the output data of the i-th sample, y i,predicted Represents the predicted value of the i-th sample.

[0101] The calculation formula for the mean relative error is:

[0102]

[0103] Here, MRE stands for mean relative error.

[0104] The calculation formula of the coefficient of determination is:

[0105]

[0106] Among them, R 2 represents the coefficient of determination, Represents the average value of the input data for each sample.

[0107] S104: Determine the optimal parameter value of the target operating parameter according to the content prediction value and the content control point of the target impurity.

[0108] It should be understood that the raw material to be processed is processed by the wax oil hydrogenation unit to obtain product wax oil, and the content values of various impurities in the wax oil cannot exceed the corresponding standard values (i.e., the content control point). Therefore, when predicting the content prediction value of the target impurity based on the operation data, it is also necessary to compare the content prediction value of the target impurity with the content control point of the target impurity to determine whether the parameter value of the target operating parameter is set reasonably. In other words, if the content prediction value of the target impurity is greater than the content control point of the target impurity, it means that the parameter value setting of the target operating parameter in the operation data is unreasonable, resulting in the target impurity failing to be effectively removed in the reactor. Therefore, it is necessary to adjust the parameter value of the target operating parameter in the operation data, and re-predict the content of the target impurity based on the adjusted operation data until the content prediction value of the target impurity is less than or equal to the content control point of the target impurity. That is, according to one embodiment of the present disclosure, the optimal parameter value of the target operating parameter is determined based on the content prediction value and the content control point of the target impurity, which may include:

[0109] In the case where the content prediction value is greater than the content control point of the target impurity, the parameter value of the target operating parameter in the operating data is adjusted, and the new operating data is re-input into the content prediction model until the obtained target impurity content prediction value is less than or equal to the content control point of the target impurity; and the current parameter value of the target operating parameter is determined as the optimal parameter value.

[0110] It should also be understood that the prediction accuracy of the content prediction model cannot reach 100%, that is, there is a certain error between the predicted value of the content prediction model and the true value. Therefore, in a possible embodiment, the content control point corresponding to each type of impurity can be determined by the standard value of that type of impurity and the prediction accuracy value of the model, that is, content control point = standard value - prediction accuracy value. In a possible embodiment, the prediction accuracy value of the content prediction model corresponding to each type of impurity is determined by the absolute value of the maximum deviation between the predicted value and the true value in the test set.

[0111] In order to verify the feasibility of the solution provided in the present disclosure, in a possible implementation method, the current operating conditions of the wax oil hydrogenation unit can also be simulated using process simulation software to obtain the optimal parameter values of various operating parameters. As shown in Table 1, Zone represents the variation range of the wax oil to be processed, VGO represents the vacuum wax oil consumption of the wax oil to be processed, in t / h; CGO represents the coking wax oil consumption of the wax oil to be processed, in t / h; Rw(S) represents the mass fraction of sulfur impurities in the wax oil to be processed, in μg / g; Rw(N) represents the mass fraction of nitrogen impurities in the wax oil to be processed, in μg / g; Residues_C represents the content of residual carbon, and since its content in the wax oil to be processed is relatively low, its unit is set to %; T1 represents the average temperature of the first bed, in °C; T2 represents the average temperature of the second bed, in °C; T3 represents the average temperature of the third bed, in °C; Pin represents the reactor pressure, in MPa; Pw(S) represents the control point of the content of sulfur impurities, in μg / g; Pw(N) represents the control point of the content of nitrogen impurities, in μg / g.

[0112] Table 1 Optimal parameter values of various operating parameters simulated by process simulation software

[0113]

[0114] Under the same conditions, the optimal parameter values of each operating parameter obtained according to the operating parameter value determination method provided by the present disclosure are shown in Table 2.

[0115] Table 2 Optimal parameter values of various operating parameters obtained by the method for determining operating parameter values disclosed herein

[0116]

[0117] According to the data in Table 1 and Table 2, under the premise of ensuring that the product indicators are qualified, the optimal parameter values of each operating parameter of the method disclosed in the present invention are all smaller than the optimal parameter values obtained by simulation of the process simulation software, indicating that the method for determining the operating parameter values disclosed in the present invention has good feasibility.

[0118] In summary, through the above technical scheme, on the one hand, according to the parameter priority of each operating parameter of the processing device, the corresponding content prediction model and the corresponding impurity content control point can be used to determine the optimal operating value of each operating parameter one by one, so as to achieve the optimal operating value of each operating parameter while ensuring that the product quality indicators are qualified, thereby reducing the energy consumption required by the processing device in the production process; on the other hand, since the removal order of each type of impurity is different, when the next type of impurity is removed, the current type of impurity has been almost removed. Therefore, even if the parameter value of the current operating parameter is changed during the process of adjusting the parameter value of the next operating parameter, it will not have much impact on the content of the current type of impurity.

[0119] Based on the same concept, the embodiment of the present disclosure also provides a device for determining the operating parameter value of a processing device, such as Figure 4 As shown, the operating parameter value determining device 400 may include:

[0120] A first determining module 410 is configured to determine a parameter priority of each operating parameter of the processing device, wherein the parameter priority indicates an order in which the optimal parameter values of each operating parameter are sequentially determined;

[0121] The second determining module 420 is configured to determine the optimal parameter value of each of the operating parameters in sequence through the following submodules:

[0122] an acquisition submodule, configured to acquire a set of operating data of the processing device, wherein the operating data includes raw material data of the raw material to be processed and parameter values of each of the operating parameters, wherein the parameter values of each of the operating parameters include initial parameter values of the operating parameters to be determined and optimal parameter values of the determined operating parameters;

[0123] A prediction submodule, configured to input the operating data into a target impurity content prediction model corresponding to the target operating parameters to be determined this time, to obtain a predicted value of the target impurity content;

[0124] The first determination submodule is configured to determine an optimal parameter value of the target operating parameter according to the content prediction value and the content control point of the target impurity.

[0125] Optionally, the first determining submodule may include:

[0126] an adjusting unit, configured to adjust the parameter value of the target operating parameter in the operating data when the content prediction value is greater than the content control point of the target impurity, and re-input the new operating data into the content prediction model until the obtained content prediction value of the target impurity is less than or equal to the content control point of the target impurity;

[0127] A determining unit is configured to determine a current parameter value of the target operating parameter as an optimal parameter value.

[0128] Optionally, the first determining module 410 may include:

[0129] The second determination submodule is configured to determine the importance of each type of impurity according to the content analysis index of each type of impurity to be removed in the raw material to be processed;

[0130] A third determining submodule is configured to determine a removal order of each type of impurity according to the importance of each type of impurity;

[0131] The fourth determining submodule is configured to determine the parameter priority of each operating parameter according to the removal order of each type of impurities, the importance of each type of impurities, and the operating parameters corresponding to each type of impurities.

[0132] Optionally, the second determining submodule may include:

[0133] The first determination unit is configured to determine, for each type of impurity present in the form of a compound, a conversion ratio of the easily removable compound based on a content analysis index of the impurity;

[0134] The second determining unit is configured to determine the importance of the impurity according to the conversion ratio and a conversion ratio threshold value pre-set for the easily removable compound.

[0135] Optionally, the second determining submodule may include:

[0136] The third determining unit is configured to determine the importance of each type of impurity in the form of a single substance according to the content analysis index of the impurity and a content analysis index threshold value pre-set for the impurity.

[0137] Optionally, the third determining submodule may include:

[0138] a fourth determining unit, configured to determine whether the importance of each type of impurity is the same according to the importance of each type of impurity;

[0139] a fifth determining unit, configured to determine, for each type of impurities having the same importance, a removal order of the corresponding type of impurities according to a preset removal order;

[0140] The sixth determining unit is configured to determine, for each type of impurities having different importance, a removal order of the corresponding type of impurities according to the importance of each type of impurities.

[0141] Optionally, the fourth determining submodule may include:

[0142] a seventh determining unit, configured to determine an initial parameter priority of each operating parameter according to a removal order of each type of impurity and an operating parameter corresponding to each type of impurity, and to determine an importance of each operating parameter according to an importance of each type of impurity;

[0143] an eighth determining unit, configured to determine whether the importance of the operation parameters is the same according to the importance of the operation parameters;

[0144] a ninth determining unit, configured to determine, for each of the operation parameters having the same importance, the parameter priority of the corresponding operation parameter according to a preset operation parameter priority and the initial parameter priority;

[0145] A tenth determining unit is configured to determine, for each of the operating parameters having different importances, the initial parameter priority as the parameter priority of the corresponding operating parameter.

[0146] Optionally, the operating parameter value determining device 400 may further include:

[0147] an acquisition module, configured to acquire a plurality of sets of sample operation data annotated with labels, each set of sample operation data including sample raw material data and sample values of each of the operating parameters, wherein the labels are used to indicate the true value of the target impurity content generated based on the corresponding sample raw material data and the sample values;

[0148] a third determination module, configured to input the sample raw material data and the sample value into the content prediction model, obtain a content prediction value corresponding to the sample raw material data and the sample value, and determine a loss function value based on the content prediction value and the true content value indicated by the label;

[0149] An updating module is used to update the parameters of the content prediction model according to the loss function value.

[0150] Through the above-mentioned device, on the one hand, according to the parameter priority of each operating parameter of the processing device, the corresponding content prediction model and the corresponding impurity content control point can be used to determine the optimal operating value of each operating parameter one by one, so as to achieve the optimal operating value of each operating parameter while ensuring that the product quality indicators are qualified, thereby reducing the energy consumption required by the processing device in the production process; on the other hand, since the removal order of each type of impurity is different, when the next type of impurity is removed, the current type of impurity has been almost removed. Therefore, even if the parameter value of the current operating parameter is changed during the process of adjusting the parameter value of the next operating parameter, it will not have much impact on the content of the current type of impurity.

[0151] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0152] Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 , a memory 502 , and may further include one or more of a multimedia component 503 , an input / output (I / O) interface 504 , and a communication component 505 .

[0153] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned method for determining the operating parameter value. The memory 502 is used to store various types of data to support the operation of the electronic device 500. For example, these data may include instructions for any application or method operating on the electronic device 500, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 502 or transmitted via the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more thereof, is not limited here. Therefore, the corresponding communication component 505 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0154] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned method for determining the operating parameter value.

[0155] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the above-described method for determining the operating parameter value are implemented. For example, the computer-readable storage medium may be the above-described memory 502 including the program instructions. The above-described program instructions may be executed by the processor 501 of the electronic device 500 to implement the above-described method for determining the operating parameter value.

[0156] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and has a code portion for executing the above-mentioned method for determining an operating parameter value when the computer program is executed by the programmable device.

[0157] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0158] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0159] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for determining an operating parameter value of a processing device, characterized in that: The method comprises: Determining a parameter priority of each operating parameter of the processing device, wherein the parameter priority is used to indicate an order in which the optimal parameter value of each operating parameter is determined in sequence; Based on the parameter priorities, the optimal parameter values of the operating parameters are determined in sequence through the following steps: Acquiring a set of operating data of the processing device, the operating data including raw material data of the raw material to be processed and parameter values of each of the operating parameters, the parameter values of each of the operating parameters including initial parameter values of the operating parameters to be determined and optimal parameter values of the determined operating parameters; Inputting the operating data into a target impurity content prediction model corresponding to the target operating parameters to be determined this time to obtain a predicted value of the target impurity content; If the content prediction value is greater than the content control point of the target impurity, adjusting the parameter value of the target operating parameter in the operating data, and re-inputting the new operating data into the content prediction model until the obtained target impurity content prediction value is less than or equal to the content control point of the target impurity; The current parameter value of the target operating parameter is determined as the optimal parameter value.

2. The method according to claim 1, characterized in that The determining of the parameter priority of each operating parameter of the processing device includes: Determining the importance of each type of impurity based on the content analysis index of each type of impurity to be removed in the raw material to be processed; Determining the order of removing each type of impurity according to the importance of each type of impurity; The parameter priority of each operating parameter is determined according to the removal order of each type of impurities, the importance of each type of impurities and the operating parameters corresponding to each type of impurities.

3. The method according to claim 2, characterized in that The step of determining the importance of each type of impurity to be removed from the raw material to be processed based on the content analysis index of each type of impurity to be removed includes: For each type of impurity that exists in the form of a compound, determine the conversion ratio of the easily removable compound based on the content analysis indicators of that type of impurity; The importance of this type of impurity is determined based on the conversion ratio and a conversion ratio threshold value pre-set for the easily removable compound.

4. The method according to claim 2, characterized in that The step of determining the importance of each type of impurity to be removed from the raw material to be processed based on the content analysis index of each type of impurity to be removed includes: For each type of impurity existing in the form of a single substance, the importance of this type of impurity is determined based on the content analysis index of this type of impurity and the content analysis index threshold set in advance for this type of impurity.

5. The method according to claim 2, characterized in that Determining the order of removing each type of impurity according to the importance of each type of impurity includes: determining, based on the importance of each type of impurity, whether the importance of each type of impurity is the same; For each type of impurities with the same importance, the removal order of the corresponding type of impurities is determined according to the preset removal order; For each type of impurities with different importance, the removal order of the corresponding type of impurities is determined according to the importance of each type of impurities.

6. The method according to claim 2, characterized in that Determining the parameter priority of each operating parameter according to the removal order of each type of impurities, the importance of each type of impurities, and the operating parameters corresponding to each type of impurities includes: Determining the initial parameter priority of each operating parameter based on the removal order of each type of impurity and the operating parameters corresponding to each type of impurity, and determining the importance of each operating parameter based on the importance of each type of impurity; determining, based on the importance of each of the operating parameters, whether the importance of each of the operating parameters is the same; For each of the operation parameters having the same importance, determining the parameter priority of the corresponding operation parameter according to the preset operation parameter priority and the initial parameter priority; For each of the operating parameters with different importance, the initial parameter priority is determined as the parameter priority of the corresponding operating parameter.

7. The method according to any one of claims 1 to 6, characterized in that The training process of the target impurity content prediction model includes: Acquire multiple sets of sample operation data marked with labels, each set of sample operation data including sample raw material data and sample values of each of the operating parameters, the labels being used to indicate that the true value of the target impurity content is generated based on the corresponding sample raw material data and the sample values; Inputting the sample raw material data and the sample value into the content prediction model to obtain a content prediction value corresponding to the sample raw material data and the sample value, and determining a loss function value based on the content prediction value and the true value of the content indicated by the label; The parameters of the content prediction model are updated according to the loss function value.

8. A device for determining an operating parameter value of a processing device, characterized in that: include: a first determining module, configured to determine a parameter priority of each operating parameter of the processing device, wherein the parameter priority is used to indicate an order in which optimal parameter values of each operating parameter are sequentially determined; The second determination module is configured to determine the optimal parameter value of each of the operating parameters in sequence through the following submodules: an acquisition submodule, configured to acquire a set of operating data of the processing device, wherein the operating data includes raw material data of the raw material to be processed and parameter values of each of the operating parameters, wherein the parameter values of each of the operating parameters include initial parameter values of the operating parameters to be determined and optimal parameter values of the determined operating parameters; A prediction submodule, configured to input the operating data into a target impurity content prediction model corresponding to the target operating parameters to be determined this time, to obtain a predicted value of the target impurity content; A determination submodule is used to adjust the parameter value of the target operating parameter in the operating data when the content prediction value is greater than the content control point of the target impurity, and re-input the new operating data into the content prediction model until the obtained target impurity content prediction value is less than or equal to the content control point of the target impurity; and determine the current parameter value of the target operating parameter as the optimal parameter value.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images