Method and device for predicting use amount of absorption liquid of alkaline washing water scrubber of ethylene unit

Abstract

The invention provides a method and a device for predicting the use amount of absorption liquid of an alkali washing water scrubber of an ethylene unit, and belongs to the technical field of pollutant treatment and intelligent management and control. According to the method, process parameters and characteristic parameters highly related to the use amount of the absorption liquid of the alkali washing water scrubber are selected and serve as input variables of an absorption liquid use amount prediction model for model training, and the use amount of the absorption liquid of the alkali washing water scrubber is predicted through the trained absorption liquid use amount prediction model. The addition amount of the alkali liquor of the alkali washing water scrubber can be accurately predicted, and accurate addition of the fresh alkali liquor is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of pollutant treatment, and in particular to a method for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device, a device for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device, a machine-readable storage medium and a processor. Background Art

[0002] H introduced and produced during the cracking process of the ethylene plant 2 S, CO 2 There are generally two methods for removing acidic gases such as sulfide and other gaseous sulfides: single alkaline washing method and ethanolamine-alkaline washing combined removal method.

[0003] The acid gas in the cracking gas mainly comes from the following aspects: sulfide and acid gas brought in by the gas raw material; sulfide contained in the liquid raw material reacts with hydrogen and water vapor at high temperature to generate hydrogen sulfide and acid gas; cracking raw material hydrocarbon and carbon in the furnace tube react with water vapor to generate carbon monoxide and acid gas; hydrocarbon reacts with water vapor to generate acid gas; when oxygen enters the cracking furnace, oxygen reacts with hydrocarbons to generate acid gas. In addition, a large amount of organic acid will be generated in the cracking raw material and during the cracking process. These acidic substances are mixed in the cracking condensate containing water and show high acidity. They react with metals to generate divalent iron and trivalent iron, which will cause corrosion to the device units, causing great harm, resulting in great economic losses and safety hazards. Removing H contained in the cracking gas is a 2 S, CO 2 Acidic gases such as pyrolysis gas are beneficial to the separation and purification of cracking gas, prevention of equipment corrosion and prevention of reactor catalyst poisoning. Therefore, research on the removal of acidic gas components in cracking gas is of great significance.

[0004] The alkaline washing method uses NaOH solution to remove H from the cracking gas. 2 S, CO 2 Acidic gases such as alkali are produced by the alkali solution. At present, the amount of alkali solution added is mainly adjusted based on work experience, which may easily lead to excessive alkali solution addition and excessive waste alkali solution generation. At present, the main technology is aimed at the treatment of waste alkali solution. There is a lack of technology for reducing the amount of waste alkali solution at the source, and there is a lack of facilities for reducing the amount of waste alkali at the source. In addition, the operation of the alkali washing tower is too extensive, which may easily lead to the input of a large amount of fresh alkali solution and the generation of waste alkali solution, bringing more environmental protection problems. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method and device for predicting the amount of absorption liquid used in the alkaline washing tower of an ethylene plant, so as to solve the problem in the prior art that the adjustment of the amount of alkaline solution added mainly relies on work experience, which easily causes excessive addition of alkaline solution and brings more environmental protection management problems.

[0006] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device, the method comprising:

[0007] Obtaining process parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device and characteristic parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device;

[0008] Determining a first characteristic parameter and a second characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device;

[0009] Constructing an absorption liquid dosage prediction model, taking the process parameters, the first characteristic parameters, and the second characteristic parameters related to the absorption liquid dosage of the alkali washing tower of the ethylene unit as the input layer of the absorption liquid dosage prediction model, taking the absorption liquid dosage of the alkali washing tower as the output layer of the absorption liquid dosage prediction model, training the absorption liquid dosage prediction model, and obtaining a trained absorption liquid dosage prediction model;

[0010] The process parameters, first characteristic parameters and second characteristic parameters related to the absorption liquid consumption of the alkali washing tower of the ethylene plant obtained in real time are used as input data, and the absorption liquid consumption of the alkali washing tower is predicted based on the trained absorption liquid consumption prediction model to obtain the predicted value of the absorption liquid consumption of the alkali washing tower.

[0011] Optionally, the characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device include the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the inlet acid gas concentration of the alkali washing tower of the ethylene device, the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the outlet acid gas concentration of the alkali washing tower of the ethylene device and the waste alkali liquid component data of the alkali washing tower of the ethylene device.

[0012] Optionally, determining a first characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device includes:

[0013] Calculating the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device based on the inlet ethylene cracking gas amount of the alkali washing and water washing tower of the ethylene device and the inlet acid gas concentration of the alkali washing and water washing tower of the ethylene device;

[0014] Calculating the output of the acid gas from the alkali washing and water washing tower of the ethylene device based on the outlet ethylene cracking gas volume of the alkali washing and water washing tower of the ethylene device and the outlet acid gas concentration of the alkali washing and water washing tower of the ethylene device;

[0015] The difference between the input amount of the acid gas of the alkaline washing water scrubber of the ethylene device and the output amount of the acid gas of the alkaline washing water scrubber of the ethylene device is calculated as the first characteristic parameter.

[0016] Optionally, determining the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameter related to the amount of absorption liquid used in the alkali washing tower of the ethylene device includes: calculating the NaHS and NaH2O in the waste alkali liquid according to the waste alkali liquid component data of the alkali washing tower of the ethylene device; 2 CO 3 The ratio of is taken as the second characteristic parameter.

[0017] Optionally, the process parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit include: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali liquid circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate and concentration of sodium hydroxide entering the alkali washing tower, and the product of the top flow rate and concentration of sodium hydroxide entering the alkali washing tower.

[0018] Optionally, before determining the first characteristic parameter and the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameters related to the absorption liquid usage of the alkali washing tower of the ethylene device, it also includes: preprocessing the process parameters and characteristic parameters.

[0019] Optionally, the preprocessing includes: data extraction processing during normal operating conditions and abnormal data elimination processing.

[0020] Optionally, the absorption liquid dosage prediction model is a BP neural network model.

[0021] The second aspect of the present application provides an intelligent control method for desulfurization of ethylene cracking gas acid gas alkaline washing, the method comprising:

[0022] The method for predicting the amount of absorption liquid in the alkaline washing tower of the ethylene device is used to predict the amount of absorption liquid in the alkaline washing tower of the ethylene device, and a predicted value of the amount of absorption liquid in the alkaline washing tower of the ethylene device is obtained;

[0023] The absorption liquid demand of the alkaline washing tower of the ethylene device is updated in real time according to the absorption liquid consumption prediction value, so as to control the absorption liquid demand of the alkaline washing tower of the ethylene device to be within a preset range.

[0024] The third aspect of the present application provides a device for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device, the device comprising:

[0025] An acquisition module, used to acquire process parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device and characteristic parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device;

[0026] A determination module, for determining a first characteristic parameter and a second characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device;

[0027] A training module is used to construct an absorption liquid dosage prediction model, wherein the process parameters, the first characteristic parameters, and the second characteristic parameters related to the absorption liquid dosage of the alkali washing tower of the ethylene unit are used as the input layer of the absorption liquid dosage prediction model, and the absorption liquid dosage of the alkali washing tower is used as the output layer of the absorption liquid dosage prediction model, and the absorption liquid dosage prediction model is trained to obtain a trained absorption liquid dosage prediction model;

[0028] The prediction module is used to use the process parameters, first characteristic parameters and second characteristic parameters related to the absorption liquid consumption of the alkali washing tower of the ethylene device obtained in real time as input data, predict the absorption liquid consumption of the alkali washing tower based on the trained absorption liquid consumption prediction model, and obtain the predicted value of the absorption liquid consumption of the alkali washing tower.

[0029] The fourth aspect of the present application provides a processor configured to execute the above-mentioned method for predicting the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device, and configured to execute the above-mentioned intelligent control method for alkaline washing and desulfurization of acidic gas of ethylene cracking gas.

[0030] The fifth aspect of the present application provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned method for predicting the amount of absorption liquid for the alkaline washing water washing tower of the ethylene device, and is configured to execute the above-mentioned intelligent control method for alkaline washing and desulfurization of acidic gas of ethylene cracking gas.

[0031] Compared with the prior art, the above technical solution of the present invention has the following beneficial effects:

[0032] The present application provides a method and device for predicting the amount of absorption liquid in an alkali washing tower of an ethylene device. The method determines a first characteristic parameter and a second characteristic parameter according to characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene device, and then trains an absorption liquid amount prediction model according to process parameters, the first characteristic parameter and the second characteristic parameter related to the amount of absorption liquid in the alkali washing tower of the ethylene device, and uses the trained absorption liquid amount prediction model to predict the amount of absorption liquid in the alkali washing tower of the ethylene device, so as to obtain a predicted value of the amount of absorption liquid in the alkali washing tower of the ethylene device. The method selects process parameters and characteristic parameters that are highly correlated with the amount of absorption liquid in the alkali washing tower, uses them as input variables of the algorithm model for model training, and predicts the amount of absorption liquid in the alkali washing tower through the trained model, so as to accurately predict the amount of alkali solution added to the alkali washing tower and realize the accurate addition of fresh alkali solution.

[0033] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0035] Figure 1 The schematic diagram shows a flow chart of a method for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device according to Example 1 of the present application;

[0036] Figure 2 The schematic diagram of the process of predicting the amount of absorption liquid for the alkaline washing tower of the ethylene device according to the second embodiment of the present application is shown;

[0037] Figure 3 The schematic diagram of the process of the intelligent control method for desulfurization of ethylene cracking gas acid gas alkaline washing according to the third embodiment of the present application is schematically shown;

[0038] Figure 4 The structural block diagram of the device for predicting the amount of absorption liquid for the alkaline washing tower of an ethylene plant according to the fourth embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0040] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0041] H introduced and produced during the cracking process of the ethylene plant 2 S, CO 2There are generally two methods for removing acidic gases such as sulfide and other gaseous gases: single alkaline washing method and ethanolamine-alkaline washing combined removal method. In theory, the alkaline washing process with sodium hydroxide solution as absorbent for cracked gas with low acidic impurity content is simpler and more economical; for cracked gas with high acidic impurity content, most of the acidic impurities are removed by using sodium hydroxide solution as absorbent and then alkaline washing, i.e. amine-alkaline combined washing process, is used. The present invention is mainly innovatively developed with single alkaline washing method.

[0042] The alkaline washing method is to use NaOH solution to wash the cracked gas. During the washing process, NaOH reacts chemically with the acidic gas in the cracked gas:

[0043] CO 2 +2NaOH → Na 2 CO 3 +H 2 O

[0044] H 2 S+2NaOH→Na 2 S+2H 2 O

[0045] Embodiment 1

[0046] Figure 1 The schematic diagram of the process flow of the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to the first embodiment of the present application is shown. Figure 1 As shown, in one embodiment of the present application, a method for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device is provided, comprising the following steps:

[0047] Step 110, obtaining process parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant and characteristic parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant.

[0048] Specifically, the process parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit include: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali liquid circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate and concentration of sodium hydroxide entering the alkali washing tower, and the product of the top flow rate and concentration of sodium hydroxide entering the alkali washing tower.

[0049] It should be noted that the process parameters here refer to the inlet ethylene cracking gas volume, inlet acid gas concentration data, outlet ethylene cracking gas volume, outlet acid gas concentration data, absorption liquid flow data, OH -The original process parameters other than the concentration data and the waste alkali liquid component data include but are not limited to the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali liquid circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate of the sodium hydroxide entering the alkali washing tower and the concentration, the product of the top flow rate of the sodium hydroxide entering the alkali washing tower and the concentration, etc.

[0050] The above twelve process parameters are obtained through Pearson correlation analysis. Studies have shown that the above twelve process parameters are highly correlated with the absorption liquid consumption of the alkaline washing tower of the ethylene unit. The absorption liquid here refers to alkaline solution.

[0051] Specifically, the characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device include the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the inlet acid gas concentration of the alkali washing tower of the ethylene device, the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the outlet acid gas concentration of the alkali washing tower of the ethylene device, the absorption liquid flow data of the alkali washing tower of the ethylene device and the waste alkali liquid component data of the alkali washing tower of the ethylene device.

[0052] Step 120, determining a first characteristic parameter and a second characteristic parameter of the alkaline washing tower of the ethylene plant based on characteristic parameters related to the amount of absorption liquid used in the alkaline washing tower of the ethylene plant.

[0053] Specifically, the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated based on the inlet ethylene cracking gas amount of the ethylene device alkali washing and water washing tower and the inlet acid gas concentration of the ethylene device alkali washing and water washing tower; the output amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated based on the outlet ethylene cracking gas amount of the ethylene device alkali washing and water washing tower and the outlet acid gas concentration of the ethylene device alkali washing and water washing tower; the difference between the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device and the output amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated as the first characteristic parameter.

[0054] Specifically, the NaHS and Na in the waste alkali liquor were calculated based on the waste alkali liquor component data. 2 CO 3 The ratio is taken as the second characteristic parameter.

[0055] After a large amount of data analysis and business analysis, it was found that although the six original process parameters of the ethylene plant's alkaline washing and water washing tower, namely the imported ethylene cracking gas volume, imported acid gas concentration data, exported ethylene cracking gas volume, exported acid gas concentration data, absorption liquid flow data and pH value, are highly correlated with the absorption liquid consumption of the ethylene plant's alkaline washing and water washing tower, the difference between the acid gas input and output (i.e., the first characteristic parameter) is more strongly correlated with the alkali liquid consumption of the ethylene plant's alkaline washing and water washing tower, which is of great help in accurately predicting the alkali liquid consumption of the ethylene plant's alkaline washing and water washing tower.

[0056] The study found that the second characteristic parameter (NaHS and Na 2 CO 3 The ratio can characterize the amount of sodium hydroxide in the alkali solution during the alkali washing tower reaction of the ethylene unit. The larger the ratio, the less sodium hydroxide in the alkali solution is relative to the amount of acid gas. When the amount of sodium hydroxide in the alkali solution is less than that of hydrogen sulfide, a large amount of NaHS will be produced. The Na 2 CO 3 It will also react with hydrogen sulfide to form NaHS, and the Na 2 CO 3 A large amount proves that the amount of sodium hydroxide in the alkali solution is greater than that of the acid gas, that is, the second characteristic parameter is negatively correlated with the amount of sodium hydroxide in the alkali solution of the alkali washing tower of the ethylene plant. After verification by Pearson correlation calculation, the amount of sodium hydroxide in the alkali solution of the alkali washing tower of the ethylene plant is more strongly correlated with the second characteristic parameter, which is of great help in accurately predicting the amount of absorption liquid used in the alkali washing tower of the ethylene plant.

[0057] Step 130, construct an absorption liquid usage prediction model, use the process parameters, first characteristic parameters, and second characteristic parameters related to the absorption liquid usage of the ethylene plant's alkaline washing tower as the input layer of the absorption liquid usage prediction model, use the absorption liquid usage of the alkaline washing tower as the output layer of the absorption liquid usage prediction model, train the absorption liquid usage prediction model, and obtain a trained absorption liquid usage prediction model.

[0058] Specifically, the process parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene device in step S110 (including but not limited to: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the amount of cracked gas at the inlet of the alkali washing tower to the amount of alkali liquid circulation, the pH value at the inlet of the circulating pump of the alkali washing tower, the product of the bottom flow rate and concentration of sodium hydroxide entering the alkali washing tower, the product of the top flow rate and concentration of sodium hydroxide and solution entering the alkali washing tower) and the first characteristic parameter and the second characteristic parameter calculated in step S120 are used as input variables of the prediction model for the amount of absorption liquid in the alkali washing tower of the ethylene device, and the output of the prediction model is the amount of absorption liquid (alkali liquid) in the alkali washing tower of the ethylene device, and the model is trained.

[0059] Optionally, the ethylene plant alkaline washing tower absorption liquid consumption prediction model can adopt a BP neural network model.

[0060] The construction process of the BP neural network model is as follows:

[0061] The first step is to set the initial weight value B.

[0062] The second step is to perform weighted summation on the input layer nodes of the BP neural network model and calculate the hidden layer y jSpecifically, the following formula (1) is used:

[0063]

[0064] Among them, x i is the value output by the i-th node in the input layer to the output layer; w ij is the connection weight of the corresponding nodes of the input layer and hidden layer neural network; θ j is the threshold of the jth node in the hidden layer.

[0065] The third step is to execute the sigmoid activation formula (2) as follows:

[0066]

[0067] The fourth step is to use formula (3) to calculate the predicted value of the alkali solution consumption of the alkali washing tower of the ethylene unit:

[0068]

[0069] Among them, B ik is the connection weight of the corresponding nodes of the hidden layer and output layer neural network; θ k is the threshold of the kth node in the output layer.

[0070] The fifth step is to calculate the error. When the error is close to zero, it converges. The calculation formula is as follows:

[0071]

[0072] in, is the expected output value of the nth sample at the kth node of the output layer, is the actual output value of the nth sample at the kth node in the output layer.

[0073] Step 6, repeat the calculations in steps 1 to 5 until convergence, and obtain the best predicted value of the amount of absorption liquid used in the alkaline washing tower of the ethylene plant.

[0074] Step 140, using the real-time acquired process parameters, first characteristic parameters, and second characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit as input data, predicting the amount of absorption liquid in the alkali washing tower based on the trained absorption liquid usage prediction model, and obtaining a predicted value of the absorption liquid usage in the alkali washing tower.

[0075] In this embodiment, the first characteristic parameter and the second characteristic parameter are calculated by the characteristic parameters related to the amount of absorption liquid in the alkaline washing water washing tower of the ethylene device, and the absorption liquid amount prediction model is trained using the process parameters, the first characteristic parameter and the second characteristic parameter related to the amount of absorption liquid in the alkaline washing water washing tower of the ethylene device. Since the first characteristic parameter and the second characteristic parameter can express the control mechanism of alkaline washing desulfurization to a certain extent compared with other directly selected process parameters, and have higher data correlation, the method of this embodiment can improve the prediction accuracy of the amount of absorption liquid in the alkaline washing water washing tower.

[0076] By adopting the method of this embodiment, the above-mentioned five original process parameters (the pyrolysis gas temperature at the inlet of the alkali washing tower, the ratio of the pyrolysis gas volume at the inlet of the alkali washing tower to the alkali solution circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate of sodium hydroxide entering the alkali washing tower and the concentration, and the product of the top flow rate of sodium hydroxide entering the alkali washing tower and the concentration) and the first characteristic parameter and the second characteristic parameter obtained by calculation are used as inputs of the BP neural network model to predict the amount of absorption liquid in the alkali washing tower of the ethylene device, and the prediction accuracy is higher.

[0077] The method described in this embodiment selects process parameters and characteristic parameters that are highly correlated with the amount of absorption liquid used in the alkali washing water washing tower, and uses them as input variables of the algorithm model for model training. The trained model is used to predict the amount of absorption liquid used in the alkali washing water washing tower, and the amount of alkali solution added in the alkali washing water washing tower can be accurately predicted to achieve the optimization of the amount of alkali solution added.

[0078] Figure 1 FIG. 1 is a flow chart of a method for predicting the amount of absorbent used in an alkaline washing tower of an ethylene plant in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0079] Embodiment 2

[0080] Figure 2 The schematic diagram shows the flow chart of the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to the second embodiment of the present application. Figure 2As shown, this embodiment is a preferred embodiment based on the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device in Example 1. This embodiment includes the following steps:

[0081] Step 210, obtaining process parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant and characteristic parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant.

[0082] This step is the same as step 110 in the first embodiment and will not be described again.

[0083] Step 220: pre-processing the process parameters and characteristic parameters.

[0084] Specifically, the data preprocessing includes but is not limited to: data extraction during normal working conditions and abnormal data elimination. Among them, the data extraction during normal working conditions is specifically: retaining the data during normal working conditions and deleting the data under the shutdown state. Abnormal data elimination is specifically: according to the pre-set process parameter threshold range, retaining the collected process parameters within the threshold range, and eliminating the data outside the threshold range. Specifically, the process parameters after the data extraction during the normal working condition period can be subjected to threshold calculation, and the process parameters included in the model input are uniformly calculated by three times the standard deviation after screening, and each obtains an accurate value range, and the value range is adjusted in combination with the properties of each process parameter and their actual rated conditions, and the value range of each process parameter is determined. After determining the threshold range, the abnormal data analysis is performed on the absorption liquid consumption data of the alkaline washing water washing tower of the ethylene unit in the model to obtain all the maximum and minimum values, and data analysis is performed on the maximum and minimum values ​​and all other process parameters to determine whether all the maximum and minimum values ​​are abnormal data, and the abnormal data is eliminated, and the fluctuations caused by normal working conditions are retained.

[0085] Step 230, determining a first characteristic parameter and a second characteristic parameter of the alkaline washing tower of the ethylene plant based on characteristic parameters related to the amount of absorption liquid used in the alkaline washing tower of the ethylene plant.

[0086] Specifically, the input amount of the acid gas of the alkali washing tower of the ethylene device is calculated based on the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device and the inlet acid gas concentration of the alkali washing tower of the ethylene device; the output amount of the acid gas of the alkali washing tower of the ethylene device is calculated based on the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device and the outlet acid gas concentration of the alkali washing tower of the ethylene device; the difference between the input amount of the acid gas of the alkali washing tower of the ethylene device and the output amount of the acid gas of the alkali washing tower of the ethylene device is calculated as the first characteristic parameter. Calculate the NaHS and NaOH content in the waste alkali liquor according to the waste alkali liquor component data 2 CO 3 The ratio is used as the second characteristic parameter. Calculate OH -The concentration characterizing the pH value is used as the third characteristic parameter. This step is the same as step S120 in the first embodiment, and will not be described again.

[0087] Step 240, construct an absorption liquid usage prediction model, use the process parameters, first characteristic parameters, and second characteristic parameters related to the absorption liquid usage of the alkali washing tower of the ethylene unit as the input layer of the absorption liquid usage prediction model, use the absorption liquid usage of the alkali washing tower as the output layer of the absorption liquid usage prediction model, train the absorption liquid usage prediction model, and obtain a trained absorption liquid usage prediction model.

[0088] Specifically, the process parameters in step 210 (including but not limited to: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali solution circulation volume, the pH value at the inlet of the alkali washing tower circulation pump, the product of the flow rate and concentration of the bottom of the sodium hydroxide entering the alkali washing tower, the product of the flow rate and concentration of the top of the sodium hydroxide and solution entering the alkali washing tower) and the first characteristic parameter, the second characteristic parameter and the third characteristic parameter calculated in step S230 are used as input variables of the prediction model for the amount of absorption liquid in the alkali washing tower of the ethylene device, and the output of the prediction model is the amount of absorption liquid in the alkali washing tower of the ethylene device, and the model is trained. The prediction model for the amount of absorption liquid in the alkali washing tower of the ethylene device can adopt the BP neural network model. This step is the same as step S130 in Example 1, and will not be repeated here.

[0089] Step 250, using the real-time acquired process parameters, first characteristic parameters, and second characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit as input data, predicting the amount of absorption liquid in the alkali washing tower based on the trained absorption liquid usage prediction model, and obtaining a predicted value of the amount of absorption liquid in the alkali washing tower.

[0090] This step is the same as step S140 in the first embodiment and will not be described again.

[0091] The method described in this embodiment selects process parameters and characteristic parameters that are highly correlated with the amount of absorption liquid used in the alkali washing water washing tower, and uses them as input variables of the algorithm model for model training. The trained model is used to predict the amount of absorption liquid used in the alkali washing water washing tower, and the amount of alkali solution added in the alkali washing water washing tower can be accurately predicted to achieve the optimization of the amount of alkali solution added.

[0092] Embodiment 3

[0093] Figure 3 The following is a schematic diagram showing the flow chart of the intelligent control method for desulfurization of ethylene cracking gas acid gas alkaline washing according to the third embodiment of the present application. Figure 3 As shown, this embodiment is a preferred embodiment based on the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device in Example 2. This embodiment includes the following steps:

[0094] Step 310, obtaining process parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant and characteristic parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant.

[0095] This step is the same as step 110 in the first embodiment and will not be described again.

[0096] Step 320: pre-processing the process parameters and characteristic parameters.

[0097] This step is the same as step 220 in the second embodiment and will not be described again.

[0098] Step 330, determining a first characteristic parameter and a second characteristic parameter of the alkali washing tower of the ethylene plant based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene plant.

[0099] Specifically, the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated based on the inlet ethylene cracking gas amount of the ethylene device alkali washing and water washing tower and the inlet acid gas concentration of the ethylene device alkali washing and water washing tower; the output amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated based on the outlet ethylene cracking gas amount of the ethylene device alkali washing and water washing tower and the outlet acid gas concentration of the ethylene device alkali washing and water washing tower; the difference between the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device and the output amount of the acid gas of the alkali washing and water washing tower of the ethylene device is calculated as the first characteristic parameter.

[0100] Specifically, the NaHS and Na in the waste alkali liquor were calculated based on the waste alkali liquor component data. 2 CO 3 The ratio is used as the second characteristic parameter. Calculate OH - The concentration characterizing the pH value is used as the third characteristic parameter. This step is the same as step 230 of the second embodiment and will not be described again.

[0101] Step 340, construct an absorption liquid usage prediction model, use the process parameters, first characteristic parameters, and second characteristic parameters related to the absorption liquid usage of the alkali washing tower of the ethylene unit as the input layer of the absorption liquid usage prediction model, use the absorption liquid usage of the alkali washing tower as the output layer of the absorption liquid usage prediction model, train the absorption liquid usage prediction model, and obtain a trained absorption liquid usage prediction model.

[0102] Specifically, the process parameters in step S210 (including but not limited to: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali solution circulation volume, the pH value at the inlet of the alkali washing tower circulation pump, the product of the flow rate and concentration of the bottom of the sodium hydroxide entering the alkali washing tower, the product of the flow rate and concentration of the top of the sodium hydroxide and solution entering the alkali washing tower) and the first characteristic parameter, the second characteristic parameter and the third characteristic parameter calculated in step S230 are used as input variables of the prediction model for the amount of absorption liquid in the alkali washing tower of the ethylene device, and the output of the prediction model is the amount of absorption liquid in the alkali washing tower of the ethylene device, and the model is trained. The prediction model for the amount of absorption liquid in the alkali washing tower of the ethylene device can adopt the BP neural network model. This step is the same as step S130 in Example 1, and will not be repeated here.

[0103] Step 350, using the real-time acquired process parameters, first characteristic parameters, and second characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit as input data, predicting the amount of absorption liquid in the alkali washing tower based on the trained absorption liquid usage prediction model, and obtaining a predicted value of the amount of absorption liquid in the alkali washing tower.

[0104] Step 360, updating the absorption liquid demand of the alkaline washing tower of the ethylene device in real time according to the absorption liquid consumption prediction value, so as to control the absorption liquid demand of the alkaline washing tower of the ethylene device to be within a preset range.

[0105] Specifically, the process of the alkali washing water washing tower of the ethylene device can be optimized by constructing a twin model of the absorption liquid consumption of the alkali washing water washing tower of the ethylene device and according to the predicted value of the absorption liquid consumption of the alkali washing water washing tower of the ethylene device obtained in step S350. The virtual twin model (i.e., an intelligent optimization unit) is mapped to the physical device of the ethylene device, and data is transmitted between the two through a communication channel. The ethylene physical device can transmit data to the communication channel, and the communication channel transmits feedback information to the catalytic cracking physical device; at the same time, the intelligent optimization unit sends data to the communication channel, and the communication channel transmits feedback information to the intelligent optimization unit. The ethylene physical device, the intelligent optimization unit and the communication channel form an information transmission closed loop.

[0106] The optimization process can be based on the alkaline washing method and the deacidification reaction principle. The absorption liquid demand can be obtained according to the predicted value of the absorption liquid concentration of the alkaline washing water washing tower and updated in real time until the absorption liquid consumption of the alkaline washing water washing tower of the ethylene unit is maintained within a reasonable range.

[0107] The method described in this embodiment selects process parameters and characteristic parameters that are highly correlated with the amount of absorption liquid used in the alkali washing water washing tower, uses them as input variables of the algorithm model for model training, and predicts the amount of absorption liquid used in the alkali washing water washing tower through the trained model, which can accurately predict the amount of alkali liquid added to the alkali washing water washing tower and improve the removal efficiency of acid gas. The method can also reasonably control the input of fresh alkali liquid, reduce the generation of waste alkali liquid, and assist in achieving energy saving and consumption reduction and green and low-carbon.

[0108] Embodiment 4

[0109] In one embodiment, Figure 4 As shown, a device for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene plant is provided, comprising an acquisition module, a determination module, a training module and a prediction module, wherein:

[0110] The acquisition module 410 is used to acquire process parameters related to the amount of absorption liquid used in the alkaline washing tower of the ethylene device and characteristic parameters related to the amount of absorption liquid used in the alkaline washing tower of the ethylene device.

[0111] The determination module 420 is used to determine the first characteristic parameter and the second characteristic parameter of the alkali washing tower of the ethylene plant based on the characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene plant.

[0112] The training module 430 is used to construct an absorption liquid usage prediction model, with the process parameters, first characteristic parameters and second characteristic parameters related to the absorption liquid usage of the alkaline washing tower of the ethylene unit as the input layer of the absorption liquid usage prediction model, and the absorption liquid usage of the alkaline washing tower as the output layer of the absorption liquid usage prediction model, to train the absorption liquid usage prediction model and obtain a trained absorption liquid usage prediction model.

[0113] The prediction module 440 is used to use the process parameters, first characteristic parameters, and second characteristic parameters related to the absorption liquid consumption of the alkali washing tower of the ethylene unit obtained in real time as input data, predict the absorption liquid consumption of the alkali washing tower based on the trained absorption liquid consumption prediction model, and obtain the predicted value of the absorption liquid consumption of the alkali washing tower.

[0114] The device for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device includes a processor and a memory. The acquisition module, determination module, training module and prediction module are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

[0115] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device is realized by adjusting the kernel parameters.

[0116] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0117] An embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device is implemented.

[0118] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the method for predicting the amount of absorption liquid used in an alkali washing tower of an ethylene device when it is running.

[0119] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, the following steps are implemented:

[0120] Step 110, obtaining process parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant and characteristic parameters related to the amount of absorbent used in the alkaline washing tower of the ethylene plant.

[0121] Step 120, determining a first characteristic parameter and a second characteristic parameter of the alkaline washing tower of the ethylene plant based on characteristic parameters related to the amount of absorption liquid used in the alkaline washing tower of the ethylene plant.

[0122] Step 130, construct an absorption liquid usage prediction model, use the process parameters, first characteristic parameters, and second characteristic parameters related to the absorption liquid usage of the ethylene plant's alkaline washing tower as the input layer of the absorption liquid usage prediction model, use the absorption liquid usage of the alkaline washing tower as the output layer of the absorption liquid usage prediction model, train the absorption liquid usage prediction model, and obtain a trained absorption liquid usage prediction model.

[0123] Step 140, using the real-time acquired process parameters, first characteristic parameters, and second characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit as input data, predicting the amount of absorption liquid in the alkali washing tower based on the trained absorption liquid usage prediction model, and obtaining a predicted value of the absorption liquid usage in the alkali washing tower.

[0124] Optionally, the characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device include the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the inlet acid gas concentration of the alkali washing tower of the ethylene device, the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the outlet acid gas concentration of the alkali washing tower of the ethylene device and the waste alkali liquid component data of the alkali washing tower of the ethylene device.

[0125] Optionally, the first characteristic parameter of the alkali washing tower of the ethylene device is determined based on the characteristic parameters related to the absorption liquid usage of the alkali washing tower of the ethylene device, including: calculating the input amount of the acid gas of the alkali washing tower of the ethylene device based on the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device and the inlet acid gas concentration of the alkali washing tower of the ethylene device; calculating the output amount of the acid gas of the alkali washing tower of the ethylene device based on the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device and the outlet acid gas concentration of the alkali washing tower of the ethylene device; calculating the difference between the input amount of the acid gas of the alkali washing tower of the ethylene device and the output amount of the acid gas of the alkali washing tower of the ethylene device as the first characteristic parameter.

[0126] Optionally, determining the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameter related to the amount of absorption liquid used in the alkali washing tower of the ethylene device includes: calculating the NaHS and NaH2O in the waste alkali liquid according to the waste alkali liquid component data of the alkali washing tower of the ethylene device; 2 CO 3 The ratio of is taken as the second characteristic parameter.

[0127] Optionally, the process parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene unit include: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali liquid circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate and concentration of sodium hydroxide entering the alkali washing tower, and the product of the top flow rate and concentration of sodium hydroxide entering the alkali washing tower.

[0128] Optionally, before determining the first characteristic parameter and the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameters related to the absorption liquid usage of the alkali washing tower of the ethylene device, it also includes: preprocessing the process parameters and characteristic parameters.

[0129] Optionally, the preprocessing includes: data extraction processing during normal operating conditions and abnormal data elimination processing.

[0130] Optionally, the neural network model is a BP neural network model.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0137] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0139] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting the amount of absorption liquid used in an ethylene plant alkaline washing tower. It is characterized in that The method comprises: Obtaining process parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device and characteristic parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device; Determining a first characteristic parameter and a second characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device; Constructing an absorption liquid dosage prediction model, taking the process parameters, the first characteristic parameters, and the second characteristic parameters related to the absorption liquid dosage of the alkali washing tower of the ethylene unit as the input layer of the absorption liquid dosage prediction model, taking the absorption liquid dosage of the alkali washing tower as the output layer of the absorption liquid dosage prediction model, training the absorption liquid dosage prediction model, and obtaining a trained absorption liquid dosage prediction model; The process parameters, first characteristic parameters and second characteristic parameters related to the absorption liquid consumption of the alkali washing tower of the ethylene plant obtained in real time are used as input data, and the absorption liquid consumption of the alkali washing tower is predicted based on the trained absorption liquid consumption prediction model to obtain the predicted value of the absorption liquid consumption of the alkali washing tower.

2. The method for predicting the amount of absorption liquid for alkali washing tower of ethylene device according to claim 1, It is characterized in that The characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device include the inlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the inlet acid gas concentration of the alkali washing tower of the ethylene device, the outlet ethylene cracking gas volume of the alkali washing tower of the ethylene device, the outlet acid gas concentration of the alkali washing tower of the ethylene device and the waste alkali liquid component data of the alkali washing tower of the ethylene device.

3. The method for predicting the amount of absorption liquid for alkali washing tower of ethylene device according to claim 2, It is characterized in that Determining a first characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device includes: Calculating the input amount of the acid gas of the alkali washing and water washing tower of the ethylene device based on the inlet ethylene cracking gas amount of the alkali washing and water washing tower of the ethylene device and the inlet acid gas concentration of the alkali washing and water washing tower of the ethylene device; Calculating the output of the acid gas from the alkali washing and water washing tower of the ethylene device based on the outlet ethylene cracking gas volume of the alkali washing and water washing tower of the ethylene device and the outlet acid gas concentration of the alkali washing and water washing tower of the ethylene device; The difference between the input amount of the acid gas of the alkaline washing water scrubber of the ethylene device and the output amount of the acid gas of the alkaline washing water scrubber of the ethylene device is calculated as the first characteristic parameter.

4. The method for predicting the amount of absorption liquid for alkali washing tower of ethylene device according to claim 2, It is characterized in that Determining the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameter related to the amount of absorption liquid in the alkali washing tower of the ethylene device comprises: calculating the NaHS and Na in the waste alkali liquid according to the waste alkali liquid component data of the alkali washing tower of the ethylene device. 2 CO 3 The ratio of is taken as the second characteristic parameter.

5. The method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to claim 1, It is characterized in that The process parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene device include: the cracked gas temperature at the inlet of the alkali washing tower, the ratio of the cracked gas volume at the inlet of the alkali washing tower to the alkali liquid circulation flow rate, the pH value at the inlet of the alkali washing tower circulation pump, the product of the bottom flow rate and concentration of sodium hydroxide entering the alkali washing tower, and the product of the top flow rate and concentration of sodium hydroxide entering the alkali washing tower.

6. The method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to claim 1, It is characterized in that Before determining the first characteristic parameter and the second characteristic parameter of the alkali washing tower of the ethylene device based on the characteristic parameters related to the amount of absorption liquid in the alkali washing tower of the ethylene device, the method further includes: The process parameters and characteristic parameters are preprocessed.

7. The method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to claim 6, It is characterized in that The preprocessing includes: normal operating period data extraction processing and abnormal data elimination processing.

8. The method for predicting the amount of absorption liquid used in the alkaline washing tower of the ethylene device according to claim 1, It is characterized in that The absorption liquid dosage prediction model is a BP neural network model.

9. An intelligent control method for desulfurization of ethylene cracking gas acid gas alkali washing, It is characterized in that The method comprises: The method for predicting the amount of absorbent in an alkali washing tower of an ethylene device according to any one of claims 1 to 8 is used to predict the amount of absorbent in an alkali washing tower of an ethylene device, and obtain a predicted value of the amount of absorbent in an alkali washing tower of an ethylene device; The absorption liquid demand of the alkaline washing tower of the ethylene device is updated in real time according to the absorption liquid consumption prediction value, so as to control the absorption liquid demand of the alkaline washing tower of the ethylene device to be within a preset range.

10. A device for predicting the amount of absorption liquid used in an ethylene plant alkaline washing tower. It is characterized in that The device comprises: An acquisition module, used to acquire process parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device and characteristic parameters related to the amount of absorption liquid used in the alkaline washing water washing tower of the ethylene device; A determination module, for determining a first characteristic parameter and a second characteristic parameter of the alkali washing tower of the ethylene device based on characteristic parameters related to the amount of absorption liquid used in the alkali washing tower of the ethylene device; A training module is used to construct an absorption liquid dosage prediction model, wherein the process parameters, the first characteristic parameters, and the second characteristic parameters related to the absorption liquid dosage of the alkali washing tower of the ethylene unit are used as the input layer of the absorption liquid dosage prediction model, and the absorption liquid dosage of the alkali washing tower is used as the output layer of the absorption liquid dosage prediction model, and the absorption liquid dosage prediction model is trained to obtain a trained absorption liquid dosage prediction model; The prediction module is used to use the process parameters, first characteristic parameters and second characteristic parameters related to the absorption liquid consumption of the alkali washing tower of the ethylene device obtained in real time as input data, predict the absorption liquid consumption of the alkali washing tower based on the trained absorption liquid consumption prediction model, and obtain the predicted value of the absorption liquid consumption of the alkali washing tower.

11. A processor, It is characterized in that The method is configured to execute the method for predicting the amount of absorbent used in the alkaline washing tower of an ethylene device according to any one of claims 1 to 8, and the intelligent control method for alkaline washing and desulfurization of acidic gas of ethylene cracking gas according to claim 9.

12. A machine-readable storage medium having instructions stored thereon, It is characterized in that When the instruction is executed by the processor, the processor is configured to execute the method for predicting the amount of absorption liquid used in the alkaline washing tower of an ethylene device as described in any one of claims 1 to 8, and is configured to execute the intelligent control method for alkaline washing and desulfurization of acidic gas of ethylene cracking gas as described in claim 9.

Images