Methods, apparatus and equipment for predicting stripping steam consumption in catalytic cracking units

Abstract

This invention provides a method, apparatus, and equipment for predicting the stripping steam consumption of a catalytic cracking unit, belonging to the field of catalytic cracking reaction control technology. The method includes: acquiring characteristic parameters of the catalytic cracking unit; using the characteristic parameters as input, predicting the stripping steam consumption of the catalytic cracking unit through a stripping steam prediction model; and adjusting the stripping steam consumption of the catalytic cracking unit based on the obtained stripping steam consumption. This invention determines the characteristic parameters of the catalytic cracking unit and establishes a stripping steam prediction model characterizing the relationship between the characteristic parameters and the stripping steam consumption of the catalytic cracking unit to predict the stripping steam consumption of the catalytic cracking unit in real time, and adjusts the stripping steam consumption of the catalytic cracking unit in real time based on the obtained stripping steam consumption. This allows for dynamic adjustment of the stripping steam consumption of the catalytic cracking unit, which is beneficial for achieving pollution reduction and carbon reduction in the catalytic cracking unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of catalytic cracking reaction control, in particular to a catalytic cracking unit stripping steam consumption prediction method, a catalytic cracking unit stripping steam consumption prediction device and a terminal device. BACKGROUND

[0002] In the production and operation of the catalytic cracking unit, part of the oil gas exists in the gap between the catalyst particles or is adsorbed on the surface of the catalyst in the settler stripping section of the reactor, and the total amount of the oil gas entering the stripper is equivalent to 2-4% of the feed amount, of which about 70-80% is included in the gap between the catalyst particles, and 20-30% is adsorbed inside the catalyst. At present, the method of water vapor stripping is used to separate this part of the oil gas, and the steam used for this part is called stripping steam in the catalytic cracking process. The amount of stripping steam is related to the amount of sulfur-containing wastewater produced and the utilization of steam resources. The stripping steam can be recycled by steam purging to recover part of the usable oil vapor, reduce the coke burning load of the regenerator, and improve the product yield. Too little stripping steam will cause the oil gas to enter the regenerator with the spent catalyst, resulting in material loss, and excessive injection of steam will cause energy waste and produce more pollutants such as sulfur-containing wastewater.

[0003] At present, the research on pollution reduction and carbon reduction of the catalytic cracking unit mainly focuses on the structure of the settler and the adjustment of the number of stripping steam, and the amount of steam is often determined by empirical calculation. However, the amount of stripping steam cannot be adjusted in a timely and reasonable manner according to the actual operation state of the device, and the adjustment of the amount of stripping steam by the operating personnel of the catalytic cracking unit mainly relies on the design value and the experience of the personnel, which has the problem of a large fluctuation range of the amount of steam, and unreasonable adjustment may cause serious problems in the operation of the device. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a catalytic cracking unit stripping steam consumption prediction method, a catalytic cracking unit stripping steam consumption prediction device and a terminal device to solve the problem that the amount of stripping steam cannot be adjusted in real time in the prior art.

[0005] In order to achieve the above-mentioned purpose, in the first aspect of the present application, a catalytic cracking unit stripping steam consumption prediction method is provided, comprising:

[0006] obtaining characteristic parameters of the catalytic cracking unit;

[0007] inputting the characteristic parameters into a stripping steam prediction model to predict the stripping steam consumption of the catalytic cracking unit;

[0008] adjusting the stripping steam consumption of the catalytic cracking unit according to the obtained stripping steam consumption;

[0009] The stripping steam prediction model is obtained by training a preset neural network model by characteristic parameters of the catalytic cracking device under different working conditions and corresponding stripping steam consumption.

[0010] Preferably, the characteristic parameters of the catalytic cracking device are determined by the following method:

[0011] Obtaining process parameters of the catalytic cracking device, and taking the process parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device;

[0012] The process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of the small distribution ring of the regenerator, pressure of the dilute phase section of the regenerator, regenerator slide valve position, regenerator top outlet oxygen content, and settler stripping section inventory.

[0013] Preferably, the training process of the stripping steam prediction model includes:

[0014] Determining initial network parameters of a preset neural network model;

[0015] Taking total feed amount of the catalytic cracking device, main air flow of the small distribution ring of the regenerator, pressure of the dilute phase section of the regenerator, regenerator slide valve position, regenerator top outlet oxygen content, and settler stripping section inventory under different working conditions as inputs, and predicting the stripping steam consumption corresponding to the current working condition by the preset neural network model;

[0016] Obtaining the measured stripping steam consumption corresponding to the current working condition, and updating the network parameters of the preset neural network model in the case that the difference between the obtained stripping steam consumption and the measured stripping steam consumption is greater than the stripping steam consumption threshold, until the difference between the obtained stripping steam consumption and the measured stripping steam consumption is not greater than the stripping steam consumption threshold, and taking the preset neural network model with the updated network parameters as the stripping steam prediction model.

[0017] Preferably, the characteristic parameters of the catalytic cracking device are determined by the following method:

[0018] Obtaining process parameters of the catalytic cracking device, and determining sub-characteristic parameters of the catalytic cracking device according to the process parameters of the catalytic cracking device;

[0019] Determining the process parameters of the catalytic cracking device and the sub-characteristic parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device;

[0020] The process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of the small distribution ring of the regenerator, pressure of the dilute phase section of the regenerator, regenerator slide valve position, regenerator top outlet oxygen content, and settler stripping section inventory.

[0021] Preferably, the sub-characteristic parameters of the catalytic cracking unit include:

[0022] The ratio of the total feed amount of the catalytic cracking unit to the amount of the settler stripping section.

[0023] Preferably, the training process of the stripping steam prediction model includes:

[0024] Determining the initial network parameters of the preset neural network model;

[0025] Taking the total feed amount of the catalytic cracking unit, the regenerator small distribution ring main air flow, the regenerator dilute phase section pressure, the regenerator slide valve position, the reactor regeneration inclined pipe temperature, the oxygen content of the regenerator top outlet, the amount of the settler stripping section, and the ratio of the total feed amount of the catalytic cracking unit to the amount of the settler stripping section as inputs, the preset neural network model is used to predict the stripping steam consumption corresponding to the current working condition;

[0026] The measured stripping steam consumption corresponding to the current working condition is obtained, and in the case that the difference between the obtained stripping steam consumption and the measured stripping steam consumption is greater than the stripping steam consumption threshold, the network parameters of the preset neural network model are updated until the difference between the obtained stripping steam consumption and the measured stripping steam consumption is not greater than the stripping steam consumption threshold. The preset neural network model with the updated network parameters is used as the stripping steam prediction model.

[0027] In the second aspect of the present application, a catalytic cracking unit stripping steam consumption prediction device is provided, comprising:

[0028] A data acquisition module configured to acquire characteristic parameters of the catalytic cracking unit;

[0029] A prediction module configured to take the characteristic parameters as inputs and use a stripping steam prediction model to predict the stripping steam consumption of the catalytic cracking unit;

[0030] A control module configured to adjust the stripping steam consumption of the catalytic cracking unit according to the obtained stripping steam consumption;

[0031] The stripping steam prediction model is obtained by training a preset neural network model using the characteristic parameters and corresponding stripping steam consumptions of the catalytic cracking unit under different working conditions.

[0032] Preferably, the device further comprises a characteristic parameter determination module; the characteristic parameter determination module is configured to:

[0033] Acquire process parameters of the catalytic cracking unit, and take the process parameters of the catalytic cracking unit as the characteristic parameters of the catalytic cracking unit;

[0034] The process parameters of the catalytic cracking device include total feed quantity of the catalytic cracking device, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of a top outlet of the regenerator, and settler stripping section inventory.

[0035] Preferably, the device further comprises a characteristic parameter determination module; the characteristic parameter determination module is configured to:

[0036] obtain process parameters of the catalytic cracking device, and determine sub-characteristic parameters of the catalytic cracking device according to the process parameters of the catalytic cracking device;

[0037] determine the process parameters of the catalytic cracking device and the sub-characteristic parameters of the catalytic cracking device as characteristic parameters of the catalytic cracking device;

[0038] The process parameters of the catalytic cracking device include total feed quantity of the catalytic cracking device, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of a top outlet of the regenerator, and settler stripping section inventory.

[0039] Preferably, the sub-characteristic parameters of the catalytic cracking device include:

[0040] The ratio of the total feed quantity of the catalytic cracking device to the settler stripping section inventory.

[0041] In a third aspect of the present application, a computer readable medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the catalytic cracking device stripping steam consumption prediction method described above.

[0042] In a fourth aspect of the present application, a terminal device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor, when executing the computer program, implements the catalytic cracking device stripping steam consumption prediction method described above.

[0043] The above technical solutions of the present application can predict the stripping steam consumption of the catalytic cracking device in real time by determining the characteristic parameters of the catalytic cracking device and establishing a stripping steam prediction model representing the relationship between the characteristic parameters of the catalytic cracking device and the stripping steam consumption of the catalytic cracking device, and adjusting the stripping steam consumption of the catalytic cracking device in real time according to the obtained stripping steam consumption, so as to dynamically adjust the stripping steam consumption of the catalytic cracking device, which is conducive to realizing pollution reduction and carbon reduction of the catalytic cracking device.

[0044] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings are included to provide a further understanding of embodiments of the application, and are incorporated in and constitute a part of this specification, illustrate embodiments of the application, and together with the description serve to explain embodiments of the application, but are not intended to limit the present application in any manner. In the drawings:

[0046] Figure 1 is a method flow chart of a catalytic cracking unit stripping steam consumption prediction method provided by the preferred embodiment of the present application;

[0047] Figure 2 is a schematic block diagram of a catalytic cracking unit stripping steam consumption prediction device provided by the preferred embodiment of the present application;

[0048] Figure 3 is a schematic block diagram of a terminal device provided by the preferred embodiment of the present application.

[0049] Explanation of reference signs

[0050] 10-terminal device, 100-processor, 101-memory, 102-computer program. DETAILED DESCRIPTION

[0051] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0052] As shown in Figure 1 , the first aspect of the present embodiment provides a catalytic cracking unit stripping steam consumption prediction method, comprising:

[0053] obtaining characteristic parameters of the catalytic cracking unit;

[0054] using the characteristic parameters as input, predicting the stripping steam consumption of the catalytic cracking unit through a stripping steam prediction model;

[0055] adjusting the stripping steam consumption of the catalytic cracking unit according to the obtained stripping steam consumption;

[0056] The stripping steam prediction model is obtained by training a preset neural network model through the characteristic parameters and corresponding stripping steam consumptions of the catalytic cracking unit under different working conditions.

[0057] Thus, the embodiment determines the characteristic parameters of the catalytic cracking unit and establishes a stripping steam prediction model representing the relationship between the characteristic parameters of the catalytic cracking unit and the stripping steam consumption of the catalytic cracking unit to predict the stripping steam consumption of the catalytic cracking unit in real time, and adjusts the stripping steam consumption of the catalytic cracking unit in real time according to the obtained stripping steam consumption, so as to dynamically adjust the stripping steam consumption of the catalytic cracking unit, which is conducive to realizing the pollution reduction and carbon reduction of the catalytic cracking unit.

[0058] In one specific example of the embodiment, the characteristic parameters of the catalytic cracking unit are determined by the following method:

[0059] The process parameters of the catalytic cracking unit are obtained, and the process parameters of the catalytic cracking unit are taken as the characteristic parameters of the catalytic cracking unit. The process parameters of the catalytic cracking unit include the total feed amount of the catalytic cracking unit, the main air flow of the regenerator small distribution ring, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the regenerator top outlet, and the stripping section inventory of the settler.

[0060] Specifically, the determination method of the characteristic parameters of the catalytic cracking unit is as follows:

[0061] The historical process parameter data of the catalytic cracking unit in a set time period, i.e. the historical data of the total feed amount of the catalytic cracking unit, the main air flow of the regenerator small distribution ring, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the regenerator top outlet, and the stripping section inventory of the settler under different working conditions are automatically read from the DCS system of the catalytic cracking unit, and the original data are processed by the following steps:

[0062] The collected historical data are preprocessed, and the data during shutdown are deleted, and the data during normal working conditions are retained;

[0063] The threshold value of the process parameters cleaned in the previous step is calculated, for example, the three times standard deviation of each process parameter is calculated, so as to obtain the value range corresponding to each parameter, and the value range of each process parameter is adjusted in combination with the properties of each process parameter and the actual rated working condition of each process parameter, so as to determine the value range of each process parameter;

[0064] After obtaining the value range of each process parameter, further abnormal data mining is performed on all data, and the abnormal data outside the value range of each process parameter is removed;

[0065] The key parameters are analyzed for the processed process parameters, and the training set and the test set are constructed based on the mined key parameters. For example, it is determined through the above analysis that the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the top outlet of the regenerator, and the amount of the stripper section of the settler have high correlation with the stripping steam consumption of the catalytic cracking device, and therefore, the above process parameters are determined as the characteristic parameters of the catalytic cracking reaction.

[0066] In the embodiment, the preset neural network model can be a convolutional neural network model, a BP neural network model, etc. In one specific example of the embodiment, the preset neural network model adopts a BP neural network model, and the training process of the stripping steam prediction model includes:

[0067] determining the initial network parameters of the preset neural network model;

[0068] taking the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the top outlet of the regenerator, and the amount of the stripper section of the settler under different working conditions as inputs, and predicting the stripping steam consumption corresponding to the current working condition through the preset neural network model;

[0069] obtaining the measured stripping steam consumption corresponding to the current working condition, and updating the network parameters of the preset neural network model in the case where the difference between the obtained stripping steam consumption and the measured stripping steam consumption is greater than the stripping steam consumption threshold, until the difference between the obtained stripping steam consumption and the measured stripping steam consumption is not greater than the stripping steam consumption threshold, so as to take the preset neural network model with the updated network parameters as the stripping steam prediction model.

[0070] Specifically, the DCS historical data of the catalytic cracking device in a preset time period are automatically read to obtain data such as the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the top outlet of the regenerator, and the amount of the stripper section of the settler under different working conditions, and the training set and the validation set are constructed according to the obtained data. Based on the constructed training set and the validation set, the BP neural network model is trained through the following steps:

[0071] Step S1: setting the initial weight value k and b of the BP neural network model.

[0072] Step S2: performing weighted summation on the input layer nodes of the BP neural network through the following formula to calculate the hidden layer values: Ff,j=∑ n n·knj;

[0073] Wherein, j is the numerical index of the hidden layer, n is the process parameter under various working conditions, i.e. the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the regenerator top outlet, and the amount of the stripper section of the settler.

[0074] Step S3: Perform the sigmoid activation formula:

[0075] Step S4: Calculate the predicted value of the sulfur content of the catalytic cracking reaction raw material by the following formula:

[0076]

[0077] Step S5: Calculate the error between the predicted value and the true value, and converge when the error is close to zero.

[0078] Step S6: If the error value does not meet the convergence standard, then the weight value k, b of the BP neural network model is updated by the following formula:

[0079]

[0080]

[0081] Wherein, X is the set learning rate.

[0082] Step S7: Repeat the calculation of steps S1 to S6 using the updated weight value until convergence is obtained, and the trained stripping steam prediction model is obtained.

[0083] In another specific example of the present embodiment, the characteristic parameters of the catalytic cracking device are determined by the following method:

[0084] Obtain the process parameters of the catalytic cracking device, determine the sub-feature parameters of the catalytic cracking device according to the process parameters of the catalytic cracking device, determine the process parameters of the catalytic cracking device and the sub-feature parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device, and the process parameters of the catalytic cracking device include the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the temperature of the reactor regeneration inclined pipe, the oxygen content of the regenerator top outlet, and the amount of the stripper section of the settler.

[0085] In order to further improve the prediction accuracy, in the embodiment, the sub-feature parameters of the catalytic cracking device include: a ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory. Through analysis of the catalytic cracking reaction process, it is determined that the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory is the sub-feature parameter of the catalytic cracking device, and the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory can effectively represent the material amount per unit of catalyst, that is, the unit load capacity of the stripping steam. Therefore, taking the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory as the sub-feature parameter can effectively improve the accuracy of the stripping steam consumption.

[0086] The sub-feature parameters of the catalytic cracking device can also be determined by the following steps:

[0087] Taking the ratio of any two of the total feed amount of the catalytic cracking device, the regenerator small distribution ring main air flow, the regenerator dilute phase section pressure, the regenerator slide valve position, the reactor regeneration inclined pipe temperature, the oxygen content of the regenerator top outlet and the settling vessel stripping section inventory as the initial sub-feature parameter, the Pearson correlation coefficient between the initial sub-feature parameter and the stripping steam consumption of the catalytic cracking device is calculated; the initial sub-feature parameter with a Pearson correlation coefficient greater than the Pearson correlation coefficient threshold value between the catalytic cracking device and the stripping steam consumption is determined as the sub-feature parameter of the catalytic cracking device, or the initial sub-feature parameters corresponding to the first n Pearson correlation coefficients arranged from large to small in the obtained Pearson correlation coefficients are determined as the sub-feature parameters of the catalytic cracking device.

[0088] For example, if the ratio of the total feed amount of the catalytic cracking device to the regenerator small distribution ring main air flow is greater than the preset Pearson correlation coefficient threshold value, the ratio of the total feed amount of the catalytic cracking device to the regenerator small distribution ring main air flow is determined as the sub-feature parameter of the catalytic cracking device. For another example, if the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory is greater than the preset Pearson correlation coefficient threshold value, the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory is determined as the sub-feature parameter of the catalytic cracking device. And so on. Specifically, through the Pearson correlation calculation of the related parameters, it is obtained that the Pearson correlation coefficient between the stripping steam consumption of the catalytic cracking device and the total feed amount of the catalytic cracking device is 0.392, the Pearson correlation coefficient between the stripping steam consumption of the catalytic cracking device and the settling vessel stripping section inventory is 0.098, and the Pearson correlation coefficient between the stripping steam consumption of the catalytic cracking device and the sub-feature parameter, that is, the ratio of the total feed amount of the catalytic cracking device to the settling vessel stripping section inventory, is 0.568.

[0089] As can be seen from the above, although the total feed amount, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the valve position of the regenerator slide valve, the temperature of the regeneration inclined pipe of the reactor, the oxygen content of the top outlet of the regenerator and the inventory of the stripping section of the settler all have high correlation with the stripping steam consumption of the stripping section of the settler, but the material amount per unit of catalyst, that is, the ratio of the total feed amount of the catalytic cracking device to the inventory of the stripping section of the settler, can represent the amount of raw material input per unit mass of catalyst, and can effectively represent the unit load capacity of the stripping steam. Compared with the total feed amount and the inventory of the stripping section of the settler, the sub-characteristic parameter can more accurately represent the unit catalyst material amount in the settler. Taking the sub-characteristic parameter as the input of the stripping steam prediction model can effectively improve the accuracy of the stripping steam consumption.

[0090] The training process of the stripping steam prediction model includes:

[0091] determining the initial network parameters of the preset neural network model;

[0092] taking the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the valve position of the regenerator slide valve, the temperature of the regeneration inclined pipe of the reactor, the oxygen content of the top outlet of the regenerator, the inventory of the stripping section of the settler and the ratio of the total feed amount of the catalytic cracking device to the inventory of the stripping section of the settler under different working conditions as inputs, and predicting the stripping steam consumption corresponding to the current working condition by the preset neural network model;

[0093] obtaining the measured stripping steam consumption corresponding to the current working condition, and updating the network parameters of the preset neural network model in the case where the difference between the obtained stripping steam consumption and the measured stripping steam consumption is greater than the stripping steam consumption threshold, until the difference between the obtained stripping steam consumption and the measured stripping steam consumption is not greater than the stripping steam consumption threshold, and taking the preset neural network model with the updated network parameters as the stripping steam prediction model.

[0094] It can be understood that the preset neural network model is a BP neural network, and its training process is the same as the above training process, which will not be described here.

[0095] The following is described with a specific example:

[0096] First, the original data of a catalytic cracking device from January 1, 2019 to December 31, 2019 is collected for data analysis and correlation analysis, and a total of 7 process parameters are retained: total feed amount, main air flow of small distribution ring of regenerator, pressure of dilute phase section of regenerator, valve position of regenerator slide valve, temperature of regeneration inclined pipe of reactor, oxygen content of top outlet of regenerator and inventory of stripping section of settler.

[0097] Secondly, according to the respective value range of the process parameters, data is deleted, the values in the value range of the process parameters are retained, and data of a continuous time period from July 1, 2019 to July 10, 2019 is divided into two parts, 3360 pieces of data from July 1, 2019 to July 7, 2019 are taken as model training sample data, and 1440 pieces of data from July 8, 2019 to July 10, 2019 are taken as model test data.

[0098] Thirdly, seven process parameters, including total feed quantity, regenerator small distribution ring main air flow, regenerator dilute phase section pressure, regenerator slide valve position, reactor regenerator inclined pipe temperature, regenerator top outlet oxygen content and settler stripping section inventory, are taken as inputs of the BP neural network model, that is, the number of input layer neurons of the BP neural network model is 7, the number of hidden layers is 2, the network structure of the model is 7-2-1, and the output is the stripping steam consumption of the settler stripping section; five process parameters, including the regenerator small distribution ring main air flow, the regenerator dilute phase section pressure, the regenerator slide valve position, the reactor regenerator inclined pipe temperature and the regenerator top outlet oxygen content, and a calculated sub-feature parameter, that is, the material quantity of the unit catalyst in the settler, that is, the ratio of the total feed quantity of the catalytic cracking device to the settler stripping section inventory, are taken as inputs of the BP neural network model, that is, the number of input layer neurons of the model is 6, the number of hidden layers is 2, the model structure is 6-2-1, and the output is the stripping steam consumption of the settler stripping section.

[0099] Finally, the two are compared, and the prediction result shows that the prediction accuracy of the BP neural network model using the BP neural network model with six input parameters including the sub-feature parameter is 95.5%, and the prediction accuracy of the BP neural network model using the original seven input parameters is only 88.6%, that is, the prediction accuracy of the sub-feature parameter constructed by the application for predicting the stripping steam consumption of the settler stripping section is obviously higher than that of the prediction using only the original process parameters with higher correlation.

[0100] As shown in FIG. 1, Figure 2 In the second aspect of the application, a catalytic cracking device stripping steam consumption prediction device is provided, which comprises:

[0101] A data acquisition module configured to acquire feature parameters of the catalytic cracking device;

[0102] A prediction module configured to take the feature parameters as inputs and predict the stripping steam consumption of the catalytic cracking device through a stripping steam prediction model;

[0103] A control module configured to adjust the stripping steam consumption of the catalytic cracking device according to the obtained stripping steam consumption;

[0104] The stripping steam prediction model is obtained by training a preset neural network model through characteristic parameters of the catalytic cracking unit under different working conditions and corresponding stripping steam consumptions.

[0105] Preferably, the device further comprises a characteristic parameter determination module; the characteristic parameter determination module is configured to:

[0106] Obtaining process parameters of the catalytic cracking unit, and taking the process parameters of the catalytic cracking unit as characteristic parameters of the catalytic cracking unit;

[0107] The process parameters of the catalytic cracking unit include total feed amount of the catalytic cracking unit, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of a top outlet of the regenerator, and settling vessel stripping section inventory.

[0108] Preferably, the device further comprises a characteristic parameter determination module; the characteristic parameter determination module is configured to:

[0109] Obtaining process parameters of the catalytic cracking unit, and determining sub-characteristic parameters of the catalytic cracking unit according to the process parameters of the catalytic cracking unit;

[0110] Determining the process parameters of the catalytic cracking unit and the sub-characteristic parameters of the catalytic cracking unit as characteristic parameters of the catalytic cracking unit;

[0111] The process parameters of the catalytic cracking unit include total feed amount of the catalytic cracking unit, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of a top outlet of the regenerator, and settling vessel stripping section inventory.

[0112] Preferably, the sub-characteristic parameters of the catalytic cracking unit include:

[0113] A ratio of the total feed amount of the catalytic cracking unit to the settling vessel stripping section inventory.

[0114] In a third aspect of the present application, a computer readable medium is provided, the computer readable medium storing a computer program, the computer program being executed by a processor to implement the catalytic cracking unit stripping steam consumption prediction method described above.

[0115] In a fourth aspect of the present application, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the catalytic cracking unit stripping steam consumption prediction method described above.

[0116] As shown in Figure 3 is a schematic diagram of a terminal device provided by an embodiment of the present application. As shown in Figure 3As shown, the terminal device 10 of this embodiment includes a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. The processor 100 implements the steps in the above method embodiments when executing the computer program 102. Alternatively, the processor 100 implements the functions of the modules / units in the above apparatus embodiments when executing the computer program 102.

[0117] By way of example, the computer program 102 can be segmented into one or more modules / units, which are stored in the memory 101 and executed by the processor 100 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 102 in the terminal device 10. For example, the computer program 102 can be segmented into a data acquisition module, a prediction module, and a control module.

[0118] The terminal device 10 can be a desktop computer, a notebook, a palm computer, a cloud server, and the like. The terminal device 10 can include, but is not limited to, the processor 100 and the memory 101. Those skilled in the art can understand that the terminal device 10 can include more or fewer components, or combine certain components, or different components, for example, the terminal device can also include an input / output device, a network access device, a bus, and the like. Figure 3 The terminal device 10 is merely an example and does not constitute a limitation on the terminal device 10, and can include more or fewer components than shown, or combine certain components, or different components, for example, the terminal device can also include an input / output device, a network access device, a bus, and the like.

[0119] The processor 100 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0120] The memory 101 can be an internal storage unit of the terminal device 10, for example, a hard disk or a memory of the terminal device 10. The memory 101 can also be an external storage device of the terminal device 10, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 10. Further, the memory 101 can also include both the internal storage unit and the external storage device of the terminal device 10. The memory 101 is used to store computer programs and other programs and data required by the terminal device 10. The memory 101 can also be used to temporarily store data that has been output or will be output.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0122] In summary, the present embodiment can predict the stripping steam consumption of the catalytic cracking unit in real time by constructing the characteristic parameters of the sub-feature parameters and process parameters that have a significant correlation with the stripping steam consumption, establishing a stripping steam prediction model representing the relationship between the characteristic parameters of the catalytic cracking unit and the stripping steam consumption of the catalytic cracking unit, and adjusting the stripping steam consumption of the catalytic cracking unit in real time according to the obtained stripping steam consumption, so as to dynamically adjust the stripping steam consumption of the catalytic cracking unit, which is conducive to realizing the pollution reduction and carbon reduction of the catalytic cracking unit.

[0123] The above describes the optional embodiments of the present application in detail in combination with the drawings, but the embodiments of the present application are not limited to the specific details in the above embodiments. Within the technical concept range of the embodiments of the present application, the technical solutions of the embodiments of the present application can be subjected to various simple modifications, and these simple modifications all belong to the protection range of the embodiments of the present application.

[0124] It should be further noted that various specific technical features described in the above detailed description can be combined in any suitable manner without departing from the scope of the present application, and the various possible combinations have been disclosed in the embodiments of the present application. In order to avoid unnecessary repetition, the various possible combinations will not be described again.

[0125] Those skilled in the art can understand that all or part of the steps in the methods for implementing the above embodiments can be completed by a program instructing related hardware. The program is stored in a storage medium, and includes a plurality of instructions for enabling a single-chip microcomputer, a chip or a processor to perform all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.

[0126] In addition, various different embodiments of the present application can be combined in any suitable manner without departing from the spirit of the embodiments of the present application, and should be considered as disclosed in the embodiments of the present application.

Claims

1. A method of predicting the amount of stripping steam for a catalytic cracking unit, characterized by, The method comprises the following steps: obtaining characteristic parameters of the catalytic cracking device; using the characteristic parameters as input, predicting the amount of stripping steam of the catalytic cracking device through a stripping steam prediction model; adjusting the amount of stripping steam of the catalytic cracking device according to the obtained amount of stripping steam; the stripping steam prediction model is obtained by training a preset neural network model through characteristic parameters and corresponding amounts of stripping steam of the catalytic cracking device under different working conditions; the characteristic parameters of the catalytic cracking device are determined by the following method: obtaining process parameters of the catalytic cracking device, and using the process parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device; the process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of the small distribution ring of the regenerator, pressure of the dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of the top outlet of the regenerator, and settler stripping section inventory; the training process of the stripping steam prediction model comprises: determining initial network parameters of the preset neural network model; using the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the regenerator regeneration inclined pipe temperature, the oxygen content of the top outlet of the regenerator, and the settler stripping section inventory under different working conditions as input, predicting the corresponding amount of stripping steam of the current working condition through the preset neural network model; obtaining the measured amount of stripping steam corresponding to the current working condition, and updating the network parameters of the preset neural network model in the case that the difference between the obtained amount of stripping steam and the measured amount of stripping steam is greater than the stripping steam amount threshold, until the difference between the obtained amount of stripping steam and the measured amount of stripping steam is not greater than the stripping steam amount threshold, using the preset neural network model with updated network parameters as the stripping steam prediction model.

2. The method for predicting stripping steam consumption in a catalytic cracking unit according to claim 1, characterized in that, the characteristic parameters of the catalytic cracking device are determined by the following method: obtaining process parameters of the catalytic cracking device, and determining sub-characteristic parameters of the catalytic cracking device according to the process parameters of the catalytic cracking device; determining the process parameters of the catalytic cracking device and the sub-characteristic parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device; the process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of the small distribution ring of the regenerator, pressure of the dilute phase section of the regenerator, regenerator slide valve position, regenerator regeneration inclined pipe temperature, oxygen content of the top outlet of the regenerator, and settler stripping section inventory.

3. The method for predicting stripping steam consumption in a catalytic cracking unit according to claim 2, characterized in that, the sub-characteristic parameters of the catalytic cracking device include: the ratio of the total feed amount of the catalytic cracking device to the settler stripping section inventory.

4. The method for predicting the stripping steam consumption of a catalytic cracking unit according to claim 3, characterized in that, the training process of the stripping steam prediction model comprises: determining initial network parameters of the preset neural network model; using the total feed amount of the catalytic cracking device, the main air flow of the small distribution ring of the regenerator, the pressure of the dilute phase section of the regenerator, the regenerator slide valve position, the regenerator regeneration inclined pipe temperature, the oxygen content of the top outlet of the regenerator, the settler stripping section inventory, and the ratio of the total feed amount of the catalytic cracking device to the settler stripping section inventory under different working conditions as input, predicting the corresponding amount of stripping steam of the current working condition through the preset neural network model; The measured stripping steam consumption corresponding to the current working condition is obtained, and in a case where a difference between the obtained stripping steam consumption and the measured stripping steam consumption is greater than a stripping steam consumption threshold, network parameters of the preset neural network model are updated until the difference between the obtained stripping steam consumption and the measured stripping steam consumption is not greater than the stripping steam consumption threshold, so as to take the preset neural network model after the network parameters are updated as a stripping steam prediction model.

5. A catalytic cracking apparatus steam stripping steam consumption prediction device applied to the catalytic cracking apparatus steam stripping steam consumption prediction method according to any one of claims 1 to 4, characterized by, The device comprises: a data acquisition module configured to acquire characteristic parameters of the catalytic cracking device; a prediction module configured to predict, by taking the characteristic parameters as input, a stripping steam consumption of the catalytic cracking device through a stripping steam prediction model; a control module configured to adjust the stripping steam consumption of the catalytic cracking device according to the obtained stripping steam consumption; The stripping steam prediction model is obtained by training a preset neural network model through characteristic parameters and corresponding stripping steam consumptions of the catalytic cracking device under different working conditions; The device further comprises a characteristic parameter determination module; the characteristic parameter determination module is configured to: acquire process parameters of the catalytic cracking device, and take the process parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device; The process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator top outlet oxygen content, and settler stripping section inventory of the catalytic cracking device.

6. The catalytic cracking unit stripping steam usage prediction apparatus of claim 5, wherein, The device further comprises a characteristic parameter determination module; The characteristic parameter determination module is configured to: acquire process parameters of the catalytic cracking device, and determine sub-characteristic parameters of the catalytic cracking device according to the process parameters of the catalytic cracking device; determine the process parameters of the catalytic cracking device and the sub-characteristic parameters of the catalytic cracking device as the characteristic parameters of the catalytic cracking device; The process parameters of the catalytic cracking device include total feed amount of the catalytic cracking device, main air flow of a small distribution ring of a regenerator, pressure of a dilute phase section of the regenerator, regenerator slide valve position, regenerator top outlet oxygen content, and settler stripping section inventory of the catalytic cracking device.

7. The catalytic cracking unit stripping steam usage prediction apparatus of claim 6, wherein, The sub-characteristic parameters of the catalytic cracking device include: a ratio of the total feed amount of the catalytic cracking device to the settler stripping section inventory.

8. A computer readable medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the catalytic cracking device stripping steam consumption prediction method in any one of claims 1-4.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the catalytic cracking device stripping steam consumption prediction method in any one of claims 1-4.

Images