A method, apparatus, device, and storage medium for production optimization of a catalytic cracking process

Abstract

The application relates to the technical field of petroleum processing, and particularly discloses a catalytic cracking process production optimization method, device, equipment and storage medium, the method comprising the following steps: according to the molecular composition and processing amount of the processing raw material, the molecular composition and product yield of products obtained under preset current reaction conditions are predicted; according to the molecular composition and product yield of the products, it is judged whether a target component has reached a catalytic cracking process optimization target; if not, the current reaction conditions are adjusted, and the foregoing steps are re-executed until the optimization target is reached, and production and processing information of corresponding catalytic cracking products is output. The catalytic cracking product prediction model established on the basis of molecular components can accurately reflect the molecular component conversion law of the production process, can significantly improve the adaptability to catalytic cracking operation changes, and can better solve the operation optimization problem of the catalytic cracking production device.

Description

Technical Field

[0001] This invention relates to the field of petroleum processing technology, and in particular to a method, apparatus, equipment and storage medium for optimizing the production of a catalytic cracking process. Background Technology

[0002] Catalytic cracking units are crucial processing units in petroleum refining. The product yield and key component content of these units directly impact the operating load and production efficiency of subsequent processing units such as polypropylene, MTBE, alkylation, and light gasoline etherification, thus significantly affecting the economic benefits of petroleum refining. Specifically, the feedstock for polypropylene units is propylene, the key feedstock for MTBE is isomeric C4, and the key feedstock for alkylation isomeric C4; different units require different key molecular components.

[0003] Currently, optimization of catalytic cracking production processes is typically conducted experimentally, requiring significant time and resources. Furthermore, the predictive analysis of catalytic cracking product properties is usually based on lumped composition. This approach, relying on lumped composition for product property prediction, lacks adaptability to significant adjustments in production operations. Summary of the Invention

[0004] To address the problems existing in the prior art, at least one embodiment of the present invention provides a method, apparatus, equipment, and storage medium for optimizing the production of a catalytic cracking process.

[0005] In a first aspect, embodiments of the present invention provide a method for optimizing the production of a catalytic cracking process, the method comprising:

[0006] Determine the molecular composition and processing quantity of the feedstock used in catalytic cracking production;

[0007] Based on the molecular composition and processing amount of the raw materials, a pre-trained product prediction model is used to predict the molecular composition and product yield of the products obtained under the preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model.

[0008] The content of the target component in the product is determined based on the molecular composition and yield of the product.

[0009] Determine whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component:

[0010] When the optimization objective has been achieved, output the production and processing information of the corresponding catalytic cracking products;

[0011] If the optimization target is not achieved, the current reaction conditions are adjusted, and the molecular composition and product yield of the product obtained under the adjusted reaction conditions are re-predicted, as well as the content of the target component in the product is re-determined, until the optimization target is achieved, and the production and processing information of the corresponding catalytic cracking product is output.

[0012] In one possible implementation, the molecular composition of the processing feedstock for catalytic cracking production is determined by searching a molecular database or by molecular reconstruction; wherein the molecular composition includes the types of molecules and the content of each type of molecule.

[0013] In one possible implementation, based on the molecular composition and processing amount of the raw material, a pre-trained product prediction model is used to predict the molecular composition and product yield of the product obtained under preset current reaction conditions, including:

[0014] Based on the molecular composition of the raw materials, a pre-trained product prediction model is used to predict a variety of products to be obtained under the preset current reaction conditions.

[0015] Determine the molecular composition and yield of each of the multiple products.

[0016] In one possible implementation, the product yield is the sum of the product of the percentage content of various molecules contained in the product and the amount of raw material processed.

[0017] In one possible implementation, the reaction conditions include at least one of temperature, pressure, fuel-to-oil ratio, and space velocity.

[0018] In one possible implementation, the optimization objective of the catalytic cracking process includes achieving a maximum or minimum content of the target component;

[0019] In one possible implementation, the product prediction model is trained through the following steps:

[0020] A product prediction model is established; wherein the product prediction model includes: a set of reaction rules and a reaction rate algorithm; the set of reaction rules includes multiple reaction rules;

[0021] Obtain sample raw material information;

[0022] Using the sample raw material information, the reaction rule set is trained, and the trained reaction rule set is fixed.

[0023] Using the sample raw material information, the reaction rate algorithm is trained, and the trained reaction rate algorithm is fixed to obtain the trained product prediction model.

[0024] In one possible implementation, the sample material information includes: the molecular composition of the sample material, the molecular content of each molecule in the sample material, the molecular composition of the actual product corresponding to the sample material, and the actual content of each molecule in the actual product.

[0025] In one possible implementation, the step of separating the product into corresponding catalytic cracking products and outputting the production and processing information of the corresponding catalytic cracking products includes:

[0026] The various products are separated into multiple products according to their actual boiling point or group composition to obtain catalytic cracking products under corresponding reaction conditions.

[0027] Determine the molecular composition and product yield of each product in the catalytic cracking products.

[0028] Output the production and processing information of the catalytic cracking product, which includes at least one of the following: current reaction conditions, molecular composition of each product in the current catalytic cracking product, and product yield;

[0029] The product yield is the sum of the product of the percentage content of various molecules contained in the product and the amount of raw materials processed.

[0030] In one possible implementation, the product is separated into multiple products according to its actual boiling point, including the following steps:

[0031] To obtain the temperature range covered by catalytic cracking data for the catalytic cracking process;

[0032] The temperature range is divided using the catalytic cracking data to obtain multiple temperature intervals;

[0033] Construct corresponding cutting sub-models using content data from each temperature range;

[0034] Merge all the cutting sub-models to obtain the cutting model;

[0035] Based on the temperature range of the boiling point falling within the cutting model, the products are divided into multiple products.

[0036] In one possible implementation, the raw materials and products are represented using a structure-oriented lumped approach;

[0037] The step of determining whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component includes:

[0038] The optimization objective is to determine the content of the target molecule in the product. An optimization model that maximizes the yield of the target product molecule is established using a product prediction model to optimize the reaction conditions.

[0039] In one possible implementation, the target molecule includes propylene, butene, n-butane, isobutane, n-C5 olefin, or iso-C5 olefin.

[0040] Secondly, embodiments of the present invention provide a catalytic cracking production optimization device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0041] Memory, used to store computer programs;

[0042] When the processor executes the program stored in the memory, it implements the steps of the above-described method for optimizing the production of the catalytic cracking process.

[0043] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the above-described catalytic cracking process production optimization method.

[0044] Fourthly, embodiments of the present invention provide a production optimization device for a catalytic cracking process, the device comprising:

[0045] The module determines the molecular composition and processing quantity of the feedstock used in catalytic cracking production;

[0046] The prediction module, based on the molecular composition and processing amount of the raw material, uses a pre-trained product prediction model to predict the molecular composition and product yield of the product obtained under preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model.

[0047] The analysis module determines the content of the target component in the product based on the molecular composition and product yield.

[0048] The judgment module determines whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component.

[0049] When the optimization target has been achieved, the output module outputs the production and processing information of the corresponding catalytic cracking product.

[0050] When the optimization target is not achieved, the current reaction conditions are adjusted, and the prediction module is called to re-predict the molecular composition and product yield of the product obtained under the adjusted reaction conditions. The analysis module is also called to redetermine the content of the target component in the product until the judgment module determines that the content of the target component has reached the optimization target. The output module then outputs the production and processing information of the corresponding catalytic cracking product.

[0051] In one possible implementation, the reaction conditions include at least one of temperature, pressure, fuel-to-oil ratio, and space velocity; the optimization objective of the catalytic cracking process includes achieving a maximum or minimum content of the target component.

[0052] Compared with the prior art, the above-mentioned technical solution of the present invention has the following advantages: The embodiments of the present invention determine the molecular composition and processing amount of the feedstock used for catalytic cracking production; based on the molecular composition and processing amount of the feedstock, a pre-trained product prediction model is used to predict the molecular composition and product yield of the product obtained under preset reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model; based on the molecular composition and product yield of the product, the content of the target component in the product is determined; based on the content of the target component, it is determined whether the optimization target of the catalytic cracking process has been achieved: if yes, the production and processing information of the corresponding catalytic cracking product is output; if no, the current reaction conditions are adjusted, and the molecular composition and product yield of the product obtained under the adjusted reaction conditions are re-predicted, and the content of the target component in the product is re-determined, until the optimization target is achieved, and the production and processing information of the corresponding catalytic cracking product is output. The molecular-level catalytic cracking product prediction model established by the present invention based on molecular components accurately reflects the molecular component transformation law of the production process, can significantly improve the adaptability to changes in catalytic cracking operation, and thus better solve the operation optimization problem of catalytic cracking production devices. One embodiment of the present invention establishes an optimization model with key components such as C3, C4, and C5 as target components to carry out production optimization of catalytic cracking units, which can significantly improve the yield of low-carbon olefin catalytic cracking products required by subsequent processing units, thereby improving the efficiency of refining and chemical production. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic diagram of a production optimization method for catalytic cracking provided in an embodiment of the present invention;

[0055] Figure 2 This is a flowchart illustrating the process of training the product prediction model in the catalytic cracking process production optimization method of Embodiment 1 of the present invention.

[0056] Figure 3 The diagram shown is a structural schematic of a catalytic cracking process production optimization device according to an embodiment of this specification.

[0057] Figure 4 The diagram shown is a schematic diagram of an optimized catalytic cracking production equipment provided in an embodiment of this specification.

[0058] [Explanation of Labels in the Attached Image]

[0059] 301. Determine the module;

[0060] 302. Prediction Module;

[0061] 303. Analysis Module;

[0062] 304, Judgment Module;

[0063] 305. Output module;

[0064] 402. Computing equipment;

[0065] 404. Processing equipment;

[0066] 406. Storage resources;

[0067] 408. Drive mechanism;

[0068] 410. Input / output module;

[0069] 412. Input devices;

[0070] 414. Output devices;

[0071] 416. Presentation equipment;

[0072] 418. Graphical User Interface;

[0073] 420. Network interface;

[0074] 422. Communication link;

[0075] 424. Communication bus. Detailed Implementation

[0076] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0077] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0078] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0079] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for optimizing the production of a catalytic cracking process. (Refer to...) Figure 1 As shown, the production optimization methods for the catalytic cracking process include:

[0080] Step 101: Determine the molecular composition and processing quantity of the feedstock for catalytic cracking.

[0081] In this embodiment, the relevant information of the catalytic cracking feedstock includes the molecular composition and processing amount of the catalytic cracking feedstock, wherein the molecular composition includes the types of molecules and the content of each type of molecule.

[0082] In this embodiment, the molecular composition can be determined by searching a molecular database or by using molecular reconstruction methods.

[0083] Step 102: Based on the molecular composition and processing amount of the catalytic cracking feedstock, use a pre-trained product prediction model to predict the molecular composition and product yield of the product obtained under preset reaction conditions.

[0084] In this embodiment, the product prediction model is used to predict the products of catalytic cracking reactions of feedstocks at the molecular level under preset reaction conditions. For example, the product prediction model can be a molecular-level catalytic cracking processing unit model. In this model, each chemical reaction has its corresponding reaction rule.

[0085] In this embodiment, based on the molecular composition of the raw materials being processed, a pre-trained product prediction model is used to predict a variety of products to be obtained under preset current reaction conditions.

[0086] Determine the molecular composition and yield of each of the multiple products.

[0087] In this embodiment, the reaction conditions may include at least one of the following parameters: temperature, pressure, catalyst-to-oil ratio, and space velocity. Space velocity refers to the amount of gas processed per unit volume of catalyst per unit time under specified conditions, measured in meters per second (m³). 3 / (m 3 Catalyst (h) can be simplified to h -1 .

[0088] Furthermore, in this embodiment, the product yield is the sum of the content of each molecule contained in the product and the amount of processing, that is, the product yield can be calculated by the following expression:

[0089] Y=∑(C j ×P);

[0090] Where Y is the product yield, C j The content of the j-th type of monomolecule contained in the product is given by denoted as ...

[0091] Step 103: Determine the content of the target component in the product based on the molecular composition and product yield of the product.

[0092] Step 104: Determine whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component.

[0093] If so, proceed to step 105;

[0094] If not, proceed to step 106.

[0095] Step 105: The product is divided into corresponding catalytic cracking products, and the production and processing information of the catalytic cracking products is output to provide a reference for the actual catalytic cracking production and processing process.

[0096] Step 106: Adjust the current reaction conditions and return to step 102.

[0097] In this embodiment, a global optimization algorithm with multiple starting points and random search can be used to determine whether the optimization objective has reached its maximum value. Alternatively, the optimization algorithm may also include: gradient descent algorithm, Newton's method, conjugate gradient method, and heuristic optimization method. The gradient descent algorithm may include: stochastic gradient descent algorithm or batch gradient descent algorithm. All of the above methods can be used to determine whether the optimization objective of all products has reached its maximum value.

[0098] In this embodiment, the step of separating the product into corresponding catalytic cracking products and outputting the production and processing information of the catalytic cracking products may further include:

[0099] The various products are separated into multiple products according to their actual boiling point or group composition to obtain catalytic cracking products under corresponding reaction conditions.

[0100] Determine the molecular composition and product yield of each product in the catalytic cracking products.

[0101] Output the production and processing information of the catalytic cracking product for application in actual catalytic cracking production.

[0102] In this embodiment, the multiple products are further divided into multiple products according to their actual boiling point or group composition, and the temperature range covered by the catalytic cracking data of the catalytic cracking process is obtained.

[0103] The temperature range is divided using the catalytic cracking data to obtain multiple temperature intervals;

[0104] Construct corresponding cutting sub-models using content data from each temperature range;

[0105] Merge all the cutting sub-models to obtain the cutting model;

[0106] Based on the temperature range of the boiling point falling within the cutting model, the products are divided into multiple products.

[0107] The construction of the segmentation sub-model is shown in Table 1 below:

[0108] Table 1

[0109]

[0110] Each part of the fraction cutting model in the table above is a cutting sub-model, where m ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0111] In this embodiment, preferably, the production and processing information includes at least one of the following: current reaction conditions, molecular composition of each product in the current catalytic cracking product, and product yield, wherein the product yield is the sum of the products of the content of each molecule contained in the product and the amount of the catalytic cracking feedstock processed.

[0112] In this embodiment, determining whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component includes: using the content of the target molecule in the product as the optimization target, establishing an optimization model that maximizes the yield of the target product molecule using a product prediction model, and performing an optimization process for the reaction conditions. Here, C3, C4, and C5 can be considered as key components in the target molecule. The optimization target can be the maximum sum of the contents of C3, C4, and C5 olefins, as shown in the following formula. This maximizes the production of low-carbon olefin catalytic cracking products and improves the economic efficiency of the enterprise's catalytic cracking production.

[0113] Max = Σ(C3 content + C4 content + C5 olefin content);

[0114] Catalytic cracking units are key processing units in refineries. The product yield and the content of key components directly affect the operating load and production efficiency of subsequent processing units such as polypropylene, MTBE, alkylation, and light gasoline etherification, and are crucial to the overall economic benefits of the plant. The feedstock for polypropylene is propylene, the key feedstock for MTBE is isomeric C4, and the key feedstock for alkylation isomeric C4; different units require different key molecular components.

[0115] The reaction mechanism model of catalytic cracking based on molecular components accurately reflects the molecular component transformation law of the production process. The model output is the molecular composition (content and type) of the product material. Establishing an optimization model targeting key components such as C3, C4, and C5, and carrying out production optimization of the catalytic cracking unit can significantly improve the yield of target products in subsequent processing units, thereby improving the overall production efficiency of the plant.

[0116] The steps are explained in detail below.

[0117] In some embodiments, such as Figure 2 As shown, in step 102, the product prediction model is trained through the following steps:

[0118] Step 201, establish a product prediction model; wherein, the product prediction model includes: a set of reaction rules and a reaction rate algorithm; the set of reaction rules includes multiple reaction rules;

[0119] Step 202: Obtain sample raw material information;

[0120] Step 203: Using the sample raw material information, train the reaction rule set and fix the trained reaction rule set;

[0121] Step 204: Using the sample raw material information, train the reaction rate algorithm and fix the trained reaction rate algorithm to obtain the trained product prediction model, wherein...

[0122] The sample material information includes: the molecular composition of the sample material, the molecular content of each molecule in the sample material, the molecular composition of the actual product corresponding to the sample material, and the actual content of each molecule in the actual product.

[0123] In some embodiments, step 203, training the reaction rule set using the sample raw material information, includes:

[0124] The molecular composition of the sample raw material is processed according to a preset set of reaction rules to obtain the reaction path corresponding to each molecule in the molecular composition of the sample raw material.

[0125] Based on the reaction pathway corresponding to each molecule in the molecular composition of the sample raw material, the first molecular composition of the device product is obtained; the device product includes: the sample raw material, intermediate product and predicted product;

[0126] Calculate the first relative deviation based on the first molecular composition of the product from the device and the second molecular composition of the actual product;

[0127] If the first relative deviation meets the preset conditions, then the set of reaction rules is fixed;

[0128] If the first relative deviation does not meet the preset conditions, the reaction rules in the reaction rule set are adjusted, and the first relative difference is recalculated according to the adjusted reaction rule set until the first relative deviation meets the preset conditions.

[0129] In this process, the reaction rules in the reaction rule set are adjusted, and the composition of the raw material molecules is processed according to the adjusted reaction rule set to obtain the reaction path corresponding to each single molecule again, until the first relative deviation between the composition of the first molecule and the composition of the second molecule meets the preset conditions.

[0130] Further, based on the first molecular composition of the product from the device and the second molecular composition of the actual product, a first relative deviation is calculated, including:

[0131] Obtain the types of individual molecules in the first molecule composition and form a first set;

[0132] Obtain the types of individual molecules in the second molecular composition to form a second set;

[0133] Determine whether the second set is a subset of the first set;

[0134] If the second set is not a subset of the first set, then the pre-stored relative deviation value that does not meet the preset conditions is obtained as the first relative deviation value;

[0135] If the second set is a subset of the first set, the first relative deviation is calculated using the following formula:

[0136]

[0137] Where x1 is the first relative deviation, M is the first set, M1 is the set of single molecules in the molecular composition of the sample raw material, M2 is the set of single molecules in the molecular composition of the intermediate product, N is the second set, and card represents the number of elements in the set.

[0138] In some embodiments, step 204, training the reaction rate algorithm using the sample raw material information, includes:

[0139] Based on the reaction rate algorithm, the reaction rate of each molecule in the molecular composition of the sample raw material is calculated for the corresponding reaction path.

[0140] Based on the molecular content of each molecule in the sample raw material and the reaction rate corresponding to the reaction path of the molecule, the predicted content of each molecule in the predicted product corresponding to the sample raw material is obtained;

[0141] The second relative deviation is calculated based on the predicted content of each molecule in the predicted product and the actual content of each molecule in the actual product;

[0142] If the second relative deviation meets the preset conditions, then the reaction rate algorithm is fixed;

[0143] If the second relative deviation does not meet the preset conditions, the parameters in the reaction rate algorithm are adjusted, and the second relative deviation is recalculated according to the adjusted reaction rate algorithm until the second relative deviation meets the preset conditions.

[0144] This process involves adjusting the reaction rate corresponding to each reaction path in the product prediction model to obtain new predicted products, until the second relative deviation between the predicted content and the actual content of each monomer meets preset conditions. Specifically, adjusting the reaction rate corresponding to each reaction path in the product prediction model includes adjusting the parameters in the reaction rate constant calculation formula within the reaction rate calculation method for each reaction path in the product prediction model. Feedback adjustments ensure the accuracy of the reaction rate calculation method in the product prediction model.

[0145] Further, based on the aforementioned reaction rate algorithm, the reaction rate of each molecule in the molecular composition of the sample raw material is calculated for each corresponding reaction pathway, including:

[0146] The reaction rate for each reaction path is calculated based on the reaction rate constant in the aforementioned reaction rate algorithm; where,

[0147] The reaction rate constant is determined according to the following formula:

[0148]

[0149] Where k is the reaction rate constant, k B Let be Boltzmann's constant, h be Planck's constant, R be the ideal gas constant, T be the temperature of the environment along the reaction path, exp be an exponential function with the natural constant as its base, ΔS be the entropy change before and after the reaction according to the reaction rule corresponding to the reaction path, and ΔE be the reaction energy barrier corresponding to the reaction rule corresponding to the reaction path. Catalyst activity factor, where P is the pressure value of the environment in which the reaction path is located, and α is the pressure influence factor corresponding to the reaction rule of the reaction path.

[0150] like Figure 3 The diagram shown is a structural schematic of a catalytic cracking process production optimization device according to an embodiment of this specification. In this embodiment, the modules and units can be configured as software modules, general-purpose chips, or dedicated chips, specifically including a determination module 301, a prediction module 302, an analysis module 303, a judgment module 304, and an output module 305, wherein:

[0151] Module 301 is used to determine the molecular composition and processing quantity of the feedstock used in catalytic cracking production;

[0152] The prediction module 302, based on the molecular composition and processing amount of the raw material, uses a pre-trained product prediction model to predict the molecular composition and product yield of the product obtained under preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model.

[0153] Analysis module 303 determines the content of the target component in the product based on the molecular composition and product yield of the product;

[0154] Module 304 determines whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component.

[0155] When the optimization target has been achieved, the output module 305 outputs the production and processing information of the corresponding catalytic cracking product.

[0156] When the optimization target is not achieved, the current reaction conditions are adjusted, and the prediction module 302 is called to re-predict the molecular composition and product yield of the product obtained under the adjusted reaction conditions. The analysis module 303 is called to redetermine the content of the target component in the product until the judgment module 304 determines that the content of the target component has reached the optimization target. Then, the output module 305 outputs the production and processing information of the corresponding catalytic cracking product.

[0157] like Figure 4 The diagram illustrates the structure of a catalytic cracking process production optimization device according to an embodiment of this specification. The methods described in the above embodiments can all be run on the computer in this embodiment, referred to as a computing device. The computing device 402 may include one or more processing devices 404, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The computing device 402 may also include any storage resource 406 for storing any kind of information, such as code, settings, data, etc. Without limitation, for example, the storage resource 406 may include any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any storage resource can use any technology to store information. Furthermore, any storage resource can provide volatile or non-volatile retention of information. Further, any storage resource may represent a fixed or removable component of the computing device 402. In one case, when the processing device 404 executes associated instructions stored in any storage resource or combination of storage resources, the computing device 402 can perform any operation of the associated instructions. The computing device 402 also includes one or more drive mechanisms 408 for interacting with any storage resources, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0158] The computing device 402 may also include an input / output module 410 (I / O) for receiving various inputs (via input device 412) and providing various outputs (via output device 414). A specific output mechanism may include a presentation device 416 and an associated graphical user interface (GUI) 418. The computing device 402 may also include one or more network interfaces 420 for exchanging data with other devices via one or more communication links 422. One or more communication buses 424 couple the components described above together.

[0159] Communication link 422 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 422 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0160] This specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps:

[0161] Determine the molecular composition and processing quantity of the feedstock used in catalytic cracking production;

[0162] Based on the molecular composition and processing amount of the raw materials, a pre-trained product prediction model is used to predict the molecular composition and product yield of the products obtained under the preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model.

[0163] The content of the target component in the product is determined based on the molecular composition and product yield of the product.

[0164] Determine whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component:

[0165] When the optimization objective has been achieved, output the production and processing information of the corresponding catalytic cracking products;

[0166] If the optimization target is not achieved, the current reaction conditions are adjusted, and the molecular composition and product yield of the product obtained under the adjusted reaction conditions are re-predicted, as well as the content of the target component in the product is re-determined, until the optimization target is achieved, and the production and processing information of the corresponding catalytic cracking product is output.

[0167] The computer device provided in the embodiments of this specification can also achieve the following: Figure 1 and Figure 2 The method in the middle.

[0168] Corresponding to Figure 1 and Figure 2 In addition to the methods described above, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the methods described above.

[0169] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the following... Figure 1 and Figure 2 The method.

[0170] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0171] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this specification generally indicates that the preceding and following related objects have an "or" relationship.

[0172] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0173] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0174] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0175] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0176] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0177] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0178] This specification uses specific embodiments to illustrate the principles and implementation methods of this specification. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this specification. Therefore, the content of this specification should not be construed as a limitation of this specification.

Claims

1. A method for optimizing the production of a catalytic cracking process, characterized in that, The method includes: Determine the molecular composition and processing quantity of the feedstock used in catalytic cracking production; Based on the molecular composition and processing amount of the raw materials, a pre-trained product prediction model is used to predict the molecular composition and product yield of the products obtained under the preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model. The content of the target component in the product is determined based on the molecular composition and product yield of the product. Determine whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component: When the optimization objective has been achieved, output the production and processing information of the corresponding catalytic cracking products; If the optimization target is not achieved, the current reaction conditions are adjusted, and the molecular composition and product yield of the product obtained under the adjusted reaction conditions are re-predicted, and the content of the target component in the product is re-determined until the optimization target is achieved, and the production and processing information of the corresponding catalytic cracking product is output. Output the production and processing information of the corresponding catalytic cracking products, including: The products are classified into multiple products according to their actual boiling point or group composition; Determine the molecular composition and product yield of each of the multiple products; Output the production and processing information of the multiple products, including the current reaction conditions, the molecular composition of each product in the multiple products, and the product yield, wherein the product yield is the sum of the product of the percentage content of each molecule contained in the product and the amount of raw materials processed; The product is separated into several products according to its actual boiling point, including the following steps: To obtain the temperature range covered by catalytic cracking data for the catalytic cracking process; The temperature range is divided using the catalytic cracking data to obtain multiple temperature intervals; Construct corresponding cutting sub-models m using content data from various temperature ranges. ij ×Y i , where m ij For the first i The fraction in the first j Content within a temperature range, Y i Indicates the first i Yield of the distillate; Merge all the cutting sub-models to obtain the cutting model; Based on the temperature range of the boiling point falling within the cutting model, the products are divided into multiple products.

2. The method according to claim 1, characterized in that, The molecular composition of the processing feedstock used for catalytic cracking production is determined by searching a molecular database or by molecular reconstruction. The molecular composition includes the types of molecules and the content of each type of molecule.

3. The method according to claim 1, characterized in that, Based on the molecular composition and processing quantity of the raw materials, a pre-trained product prediction model is used to predict the molecular composition and product yield of the product obtained under preset current reaction conditions, including: Based on the molecular composition of the raw materials, a pre-trained product prediction model is used to predict a variety of products to be obtained under the preset current reaction conditions. Determine the molecular composition and yield of each of the multiple products.

4. The method according to claim 3, characterized in that, The product yield is the sum of the percentage content of each molecule contained in the product and the amount of raw material processed.

5. The method according to claim 1, characterized in that, The reaction conditions include at least one of temperature, pressure, agent-to-oil ratio, and space velocity; The optimization objectives of the catalytic cracking process include achieving the maximum or minimum content of the target component.

6. The method according to claim 3, characterized in that, The product prediction model is trained through the following steps: A product prediction model is established; wherein the product prediction model includes a set of reaction rules and a reaction rate algorithm; the set of reaction rules includes multiple reaction rules; Obtain sample raw material information; Using the sample raw material information, the reaction rule set is trained, and the trained reaction rule set is fixed. Using the sample raw material information, the reaction rate algorithm is trained, and the trained reaction rate algorithm is fixed to obtain the trained product prediction model.

7. The method according to claim 6, characterized in that, The sample material information includes: the molecular composition of the sample material, the molecular content of each molecule in the sample material, the molecular composition of the actual product corresponding to the sample material, and the actual content of each molecule in the actual product.

8. The method according to claim 1, characterized in that, The raw materials and products are described using a structure-oriented lumped approach. The step of determining whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component includes: The optimization objective is to optimize the content of the target molecule in the product. An optimization model that maximizes the yield of the target product molecule is established using a product prediction model, and the reaction conditions are optimized accordingly.

9. The method according to claim 8, characterized in that, The target molecules include propylene, butene, n-butane, isobutane, n-C5 olefins, or iso-C5 olefins.

10. A production optimization device for a catalytic cracking process, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the steps of the catalytic cracking process production optimization method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the catalytic cracking process production optimization method according to any one of claims 1 to 9.

12. A production optimization device for a catalytic cracking process, characterized in that, The device includes: The module determines the molecular composition and processing quantity of the feedstock used in catalytic cracking production; The prediction module, based on the molecular composition and processing amount of the raw material, uses a pre-trained product prediction model to predict the molecular composition and product yield of the product obtained under preset current reaction conditions; wherein, the product prediction model is a molecular-level catalytic cracking device model. The analysis module determines the content of the target component in the product based on the molecular composition and product yield. The judgment module determines whether the optimization target of the catalytic cracking process has been achieved based on the content of the target component. When the optimization target has been achieved, the output module outputs the production and processing information of the corresponding catalytic cracking product. When the optimization target is not achieved, the current reaction conditions are adjusted, and the prediction module is called to re-predict the molecular composition and product yield of the product obtained under the adjusted reaction conditions. The analysis module is also called to redetermine the content of the target component in the product until the judgment module determines that the content of the target component has reached the optimization target. The output module then outputs the production and processing information of the corresponding catalytic cracking product. Output the production and processing information of the corresponding catalytic cracking products, including: The products are classified into multiple products according to their actual boiling point or group composition; Determine the molecular composition and product yield of each of the multiple products; Output the production and processing information of the multiple products, including the current reaction conditions, the molecular composition of each product in the multiple products, and the product yield, wherein the product yield is the sum of the product of the percentage content of each molecule contained in the product and the amount of raw materials processed; The product is separated into several products according to its actual boiling point, including the following steps: To obtain the temperature range covered by catalytic cracking data for the catalytic cracking process; The temperature range is divided using the catalytic cracking data to obtain multiple temperature intervals; Construct corresponding cutting sub-models m using content data from various temperature ranges. ij ×Y i , where m ij For the first i The fraction in the first j Content within a temperature range, Y i Indicates the first i Yield of the distillate; Merge all the cutting sub-models to obtain the cutting model; Based on the temperature range of the boiling point falling within the cutting model, the products are divided into multiple products.

13. The apparatus according to claim 12, characterized in that, The reaction conditions include at least one of temperature, pressure, agent-to-oil ratio, and space velocity; The optimization objectives of the catalytic cracking process include achieving the maximum or minimum content of the target component.

Images