Intelligent optimization control method and system for ethylbenzene synthesis device

Abstract

The invention provides an intelligent optimization control method and system for an ethylbenzene synthesis device, which includes querying a plurality of alkylation reactors arranged in parallel; obtaining the upper and lower limits of raw materials that can be received by each alkylation reactor; filling the raw material portions into the alkylation reactor with the upper and lower limits of the raw materials as restrictions, forming a plurality of alkylation reactor combinations containing different raw material portions, and outputting them as initial combinations; obtaining ethylbenzene synthesis requirements, and converting the ethylbenzene synthesis requirements into optimization targets; using a gray wolf optimization algorithm to process the initial combinations based on the optimization targets, and obtaining an optimal combination; transporting the raw materials to the corresponding alkylation reactors according to the optimal combination for ethylbenzene synthesis; the raw material portions in the alkylation reactor in the optimal combination obtained by the gray wolf optimization algorithm are the optimal portions, and when ethylbenzene synthesis is performed based on the optimal portions, the requirements of the factory for output speed, production output or environmental impact can be met to the maximum extent.

Description

Technical Field

[0001] The present invention relates to the technical field of ethylbenzene preparation, and in particular to an intelligent optimization control method and system for an ethylbenzene synthesis device. Background Art

[0002] Ethylbenzene is an important organic chemical raw material, mainly used for the production of styrene, and then for the manufacture of high molecular materials such as polystyrene and ABS resin. The ethylbenzene synthesis unit is an industrial facility for the production of ethylbenzene, which mainly includes an alkylation reactor, a raw material supply system, a separation system, a catalyst regeneration or recovery system, and a control system. The alkylation reactor is the core equipment of the ethylbenzene synthesis unit. The raw materials benzene and ethylene are added to the reactor, and after heating and reacting under the action of a catalyst, ethylbenzene is generated. In some large factories, there are generally multiple sets of alkylation reactors. These alkylation reactors are connected in series or in parallel. The series connection of the alkylation reactors can make the raw materials flow in multiple reactors, thereby improving the yield and conversion rate, while the parallel connection can improve the total production capacity, increase operational flexibility and ease of maintenance.

[0003] At present, multiple sets of alkylation reactors installed in parallel in factories have been used for a long time. Due to differences in heating temperature and reaction time, the equipment has aged to varying degrees, resulting in different synthesis rates, outputs and energy consumption of each alkylation reactor during ethylbenzene synthesis. When multiple sets of alkylation reactors are synthesizing ethylbenzene at the same time, intelligent optimization of input raw materials is not performed based on the status of the alkylation reactors. Most of them are based on manual experience, resulting in slow synthesis rate, low output and high energy consumption. In addition, when synthesizing ethylbenzene, the manufacturer's requirements for ethylbenzene output or output speed are mostly not taken into account, thereby affecting the manufacturer's ethylbenzene supply. Summary of the invention

[0004] In view of this, the present invention proposes an intelligent optimization control method and system for an ethylbenzene synthesis device, which can determine the optimal number of raw materials for multiple sets of alkylation reactors arranged in parallel to meet the manufacturer's demand for ethylbenzene synthesis.

[0005] The technical solution of the present invention is achieved in this way:

[0006] An intelligent optimization control method for an ethylbenzene synthesis device comprises the following steps:

[0007] S1. Query multiple sets of alkylation reactors arranged in parallel;

[0008] S2. Obtaining the upper and lower limits of the raw materials that each alkylation reactor can accept;

[0009] S3, filling the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, forming several sets of alkylation reactor combinations containing different raw material portions, and outputting them as initial combinations;

[0010] S4, obtaining ethylbenzene synthesis demand, and converting the ethylbenzene synthesis demand into an optimization target;

[0011] S5. Using the Grey Wolf Optimization Algorithm to process the initial combination based on the optimization target and obtain the optimal combination;

[0012] S6. According to the optimal combination, the raw materials are transported to the corresponding alkylation reactor for ethylbenzene synthesis.

[0013] Preferably, the specific steps of step S1 are: querying the alkylation reactor in use from the plant management system, and determining the connection mode of the alkylation reactor, and determining multiple sets of alkylation reactors connected in parallel through the connection mode.

[0014] Preferably, the specific steps of step S2 are:

[0015] S21, obtaining historical usage data of the alkylation reactor, wherein the historical usage data includes reaction time, reaction temperature, reaction pressure, and heat transfer efficiency;

[0016] S22, training the neural network using historical usage data, and testing the trained neural network;

[0017] S23, inputting the complete usage data of the alkylation reactors arranged in parallel into the trained neural network for processing, and obtaining the upper and lower limits of the raw materials that the alkylation reactors can accept.

[0018] Preferably, the specific steps of step S3 are:

[0019] S31, determining the increase or decrease interval of the number of raw materials;

[0020] S32, determining the number of multiple groups of raw material portions that can be filled in each alkylation reactor based on the increase and decrease interval of the raw material portion and the upper and lower limits of the raw material;

[0021] S33, randomly arranging and combining the alkylation reactors with the raw material portions, outputting the initial combination and then screening and eliminating them.

[0022] Preferably, the specific steps of screening and eliminating in step S33 are: determining the total amount of raw materials, calculating the sum of the raw material portions of all alkylation reactors in each initial combination, and eliminating the initial combination whose sum of the raw material portions is not equal to the total amount of raw materials.

[0023] Preferably, the specific steps of step S4 are:

[0024] S41, determining whether there is a time requirement for the current ethylbenzene synthesis, and if there is a time requirement, outputting the output speed as an optimization target;

[0025] S42, determining whether there is an emission requirement for the current ethylbenzene synthesis, and if there is an emission requirement, outputting the impact on the environment as an optimization target;

[0026] S43. If there is no time requirement or emission requirement for the current ethylbenzene synthesis, the production cost is output as the optimization target.

[0027] Preferably, the specific steps of step S5 are:

[0028] S51, initializing the gray wolf population and the number of iterations;

[0029] S52, randomly selecting an initial combination, and calculating the fitness value of the gray wolf based on the optimization target;

[0030] S53, selecting another initial combination, calculating the fitness value of the gray wolf, and comparing it with the fitness value calculated last time, and retaining the initial combination with the larger fitness value;

[0031] S54, perform iterative calculations, and output the initial combination with the largest fitness value as the optimal combination.

[0032] Preferably, the number of iterations is the number of initial combinations.

[0033] An intelligent optimization control system for an ethylbenzene synthesis device, comprising:

[0034] Equipment query unit, used to query multiple sets of alkylation reactors arranged in parallel;

[0035] A raw material upper and lower limit acquisition unit is used to obtain the upper and lower limits of raw materials that each alkylation reactor can receive;

[0036] A combination unit is used to fill the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, to form a plurality of alkylation reactor combinations containing different raw material portions, and output them as initial combinations;

[0037] A demand acquisition unit, used for acquiring the demand for ethylbenzene synthesis and converting the demand for ethylbenzene synthesis into an optimization target;

[0038] An intelligent optimization unit, used to process the initial combination based on the optimization target using the Grey Wolf optimization algorithm and obtain the optimal combination;

[0039] A conveying unit, used for conveying the raw materials to the corresponding alkylation reactor for ethylbenzene synthesis according to the optimal combination;

[0040] The equipment query unit, the raw material upper and lower limit acquisition unit, the combination unit, the intelligent optimization unit and the conveying unit are connected in data in sequence, and the demand acquisition unit is connected in data with the intelligent optimization unit.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention provides an intelligent optimization control method and system for an ethylbenzene synthesis device. After obtaining the upper and lower limits of raw materials of multiple sets of alkylation reactors arranged in parallel in a manufacturer, the number of raw materials that can be received in each alkylation reactor is determined, and then different alkylation reactors are randomly combined to obtain multiple initial combinations, each of which contains multiple sets of alkylation reactors arranged in parallel, and the number of raw materials of the alkylation reactors in different initial combinations is different. Then, the ethylbenzene synthesis demand of the manufacturer can be obtained, and after the ethylbenzene synthesis demand is converted into an optimization target, the gray wolf optimization algorithm is used to optimize the initial combination based on the optimization target, and an optimal combination is obtained. When ethylbenzene synthesis is performed based on the number of raw materials of the alkylation reactor in the optimal combination, the ethylbenzene synthesis demand of the manufacturer can be met to the maximum extent, and the intelligent optimization control of ethylbenzene synthesis can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 This is a flow chart of an intelligent optimization control method for an ethylbenzene synthesis device of the present invention;

[0045] Figure 2 This is a flow chart of step S2 of an intelligent optimization control method for an ethylbenzene synthesis device of the present invention;

[0046] Figure 3 This is a flow chart of step S3 of an intelligent optimization control method for an ethylbenzene synthesis device of the present invention;

[0047] Figure 4 This is a flow chart of step S4 of an intelligent optimization control method for an ethylbenzene synthesis device of the present invention;

[0048] Figure 5 This is a flow chart of step S5 of an intelligent optimization control method for an ethylbenzene synthesis device of the present invention;

[0049] Figure 6 The schematic diagram of an intelligent optimization control system for an ethylbenzene synthesis device of the present invention;

[0050] In the figure, 1. Equipment query unit; 2. Raw material upper and lower limit acquisition unit; 3. Combination unit; 4. Demand acquisition unit; 5. Intelligent optimization unit; 6. Transportation unit. DETAILED DESCRIPTION

[0051] In order to better understand the technical content of the present invention, a specific embodiment is provided below, and the present invention is further described in conjunction with the accompanying drawings.

[0052] See also Figures 1 to 5 The present invention provides an intelligent optimization control method for an ethylbenzene synthesis device, comprising the following steps:

[0053] S1. Query multiple sets of alkylation reactors arranged in parallel;

[0054] S2. Obtaining the upper and lower limits of the raw materials that each alkylation reactor can accept;

[0055] S3, filling the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, forming several sets of alkylation reactor combinations containing different raw material portions, and outputting them as initial combinations;

[0056] S4, obtaining ethylbenzene synthesis demand, and converting the ethylbenzene synthesis demand into an optimization target;

[0057] S5. Using the Grey Wolf Optimization Algorithm to process the initial combination based on the optimization target and obtain the optimal combination;

[0058] S6. According to the optimal combination, the raw materials are transported to the corresponding alkylation reactor for ethylbenzene synthesis.

[0059] The core equipment in the ethylbenzene synthesis unit is the alkylation reactor. In order to meet order requirements, manufacturers will set up multiple sets of parallel alkylation reactors, which can process benzene and ethylene raw materials at the same time and generate styrene. However, due to the different scheduling and use of the alkylation reactors and the usage habits of production workers, the usage status of the alkylation reactors is different, including heating time, heating temperature, internal pressure and component wear, which will cause the alkylation reactor to have different processing capabilities for raw materials. When synthesizing ethylbenzene, different alkylation reactors will have different processing capabilities for different amounts of raw materials. If ethylbenzene is synthesized only according to experience or by inputting the maximum amount of raw materials into the alkylation reactor, it will affect the actual output rate and output. Therefore, it is necessary to determine the amount of raw materials that can be processed by multiple sets of parallel alkylation reactors, and then determine the optimal amount of raw materials that can be processed by the alkylation reactor based on the demand for ethylbenzene synthesis, so that the ethylbenzene synthesis result meets the actual needs of the manufacturer.

[0060] Since the raw materials processed by the alkylation reactors arranged in series are fixed, when performing intelligent optimization control, it is necessary to first determine the alkylation reactors arranged in parallel in the manufacturer, and then determine the upper and lower limits of the raw materials that each alkylation reactor can receive, to ensure that the number of raw materials determined later is within the upper and lower limits of the raw materials of the alkylation reactor, and then determine the number of raw materials that each alkylation reactor can accommodate. Since there are upper and lower limits of raw materials, the number of raw materials can be increased or decreased within the upper and lower limits of raw materials, so each alkylation reactor can be filled with a variety of raw material portions, and after multiple sets of alkylation reactors arranged in parallel are combined, it can be Several initial combinations are obtained, each of which contains a plurality of alkylation reactors arranged in parallel, and the proportions of raw materials in the alkylation reactors in different initial combinations are different. After obtaining the ethylbenzene synthesis demand of the manufacturer, the ethylbenzene synthesis demand is converted into an optimization target, and the initial combinations can be optimized based on the optimization target by the Gray Wolf optimization algorithm. The Gray Wolf optimization algorithm can process the initial combinations to obtain a combination that best meets the optimization target and output it as an optimal combination. When ethylbenzene is synthesized according to the proportions of raw materials in the alkylation reactors in the optimal combination, the ethylbenzene synthesis demand of the manufacturer can be met to the maximum extent, such as the maximum output or the fastest yield.

[0061] Preferably, the specific steps of step S1 are: querying the alkylation reactor in use from the plant management system, and determining the connection mode of the alkylation reactor, and determining multiple sets of alkylation reactors connected in parallel through the connection mode.

[0062] The plant management system of the processing plant will centrally manage all the equipment in the plant. All the alkylation reactors in use can be queried through the plant management system, and then the connection method of the alkylation reactor can be checked, and multiple sets of alkylation reactors connected in parallel can be output.

[0063] Preferably, the specific steps of step S2 are:

[0064] S21, obtaining historical usage data of the alkylation reactor, wherein the historical usage data includes reaction time, reaction temperature, reaction pressure, and heat transfer efficiency;

[0065] S22, training the neural network using historical usage data, and testing the trained neural network;

[0066] S23, inputting the complete usage data of the alkylation reactors arranged in parallel into the trained neural network for processing, and obtaining the upper and lower limits of the raw materials that the alkylation reactors can accept.

[0067] The upper and lower limits of raw materials are set for the alkylation reactor when it leaves the factory. As the number of ethylbenzene synthesis increases, the use status of the alkylation reactor changes, resulting in changes in the upper and lower limits of its raw materials. The present invention uses a deep learning network to identify the upper and lower limits of the alkylation reactor, and the deep learning network is implemented using a neural network. After the historical use data of the alkylation reactor is divided into a training set and a test set, the neural network is trained using the training set, and after the training is completed, the neural network is tested using the test set. After the test accuracy meets the requirements, the complete use data of the alkylation reactors arranged in parallel can be input into the trained neural network, and the upper and lower limits of raw materials that can be received by the alkylation reactors arranged in parallel can be obtained after processing by the neural network.

[0068] Preferably, the specific steps of step S3 are:

[0069] S31, determining the increase or decrease interval of the number of raw materials;

[0070] S32, determining the number of multiple groups of raw material portions that can be filled in each alkylation reactor based on the increase and decrease interval of the raw material portion and the upper and lower limits of the raw material;

[0071] S33, randomly arranging and combining the alkylation reactors with the raw material portions, outputting them as initial combinations and then screening and eliminating them, the specific steps of screening and eliminating are: determining the total amount of raw materials, calculating the sum of the raw material portions of all alkylation reactors in each initial combination, and eliminating the initial combinations whose sum of the raw material portions is not equal to the total amount of raw materials.

[0072] For the alkylation reactor, in order to facilitate the internal management of the factory, when adding raw materials, it is generally increased or decreased at a certain interval. For example, 2 tons is used as the increase or decrease interval of the raw material portion. When increasing or decreasing, it is done in multiples of 2 tons. Since the upper and lower limits of the raw materials of each alkylation reactor are known, the number of raw materials that can be filled in each alkylation reactor can be obtained by combining the increase or decrease interval of the raw material portion and the upper and lower limits of the raw materials. After randomly combining alkylation reactors with different raw material portions, several initial combinations can be formed. Each initial combination contains multiple sets of alkylation reactors with the same number, and the raw material portion ratios of alkylation reactors in different initial combinations are Different, and in order to compare the production effects of different initial combinations, the present invention adopts the form of a single variable. First, after determining the total amount of raw materials, the initial combinations can be screened, and the raw material portions of all alkylation reactors in each initial combination are added. The initial combination whose total raw material portion is equal to the total amount of raw materials is qualified, and the unequal initial combinations can be eliminated, so as to avoid too many initial combinations from entering the subsequent steps and reduce the amount of calculation. Finally, the total amount of raw materials of all initial combinations obtained is the same. Under the premise of the same total amount of raw materials, the results of ethylbenzene synthesis are compared by comparing the different proportions of the raw material portions of the alkylation reactors, so as to determine the optimal raw material portion that meets the ethylbenzene synthesis requirements.

[0073] The total amount of raw materials is not fixed and can be determined by the manufacturer based on the factory's raw material storage and supply conditions.

[0074] Preferably, the specific steps of step S4 are:

[0075] S41, determining whether there is a time requirement for the current ethylbenzene synthesis, and if there is a time requirement, outputting the output speed as an optimization target;

[0076] S42, determining whether there is an emission requirement for the current ethylbenzene synthesis, and if there is an emission requirement, outputting the impact on the environment as an optimization target;

[0077] S43. If there is no time requirement or emission requirement for the current ethylbenzene synthesis, the production cost is output as the optimization target.

[0078] The ethylbenzene synthesis demand of the manufacturer includes time requirements and emission requirements. When there are time requirements, the output speed of ethylbenzene synthesis is required to be the fastest, and when there are emission requirements, the impact of ethylbenzene synthesis on the environment is required to be the smallest, that is, the amount of pollutant gas emitted to the environment is the least. If the manufacturer has no time requirements and emission requirements, it only needs to consider the manufacturer's production cost. Different optimization targets can be determined through different ethylbenzene synthesis requirements.

[0079] Preferably, the specific steps of step S5 are:

[0080] S51, initializing the gray wolf population and the number of iterations, where the number of iterations is the number of initial combinations;

[0081] S52, randomly selecting an initial combination, and calculating the fitness value of the gray wolf based on the optimization target;

[0082] S53, selecting another initial combination, calculating the fitness value of the gray wolf, and comparing it with the fitness value calculated last time, and retaining the initial combination with the larger fitness value;

[0083] S54, perform iterative calculations, and output the initial combination with the largest fitness value as the optimal combination.

[0084] After determining the optimization target and multiple initial combinations, the present invention adopts the gray wolf optimization algorithm to optimize the initial combinations. After initializing the gray wolf population, the number of iterations can be determined according to the number of initial combinations. Then, after randomly selecting an initial combination, the fitness value of the gray wolf is calculated based on the optimization target, for example, the calculation is based on the fastest output speed, the smallest environmental impact or the lowest production cost. At the same time, the fitness values ​​of all other initial combinations are calculated. After each calculation, the fitness values ​​are compared, and the initial combination with the larger fitness value is retained. Finally, the initial combination with the largest fitness value can be obtained and output as the optimal combination. The number of raw materials in the alkylation reactor in the optimal combination is the optimal number of raw materials. Finally, the corresponding number of raw materials can be transported to the alkylation reactor for ethylbenzene synthesis according to the number of raw materials in the optimal combination, thereby meeting the ethylbenzene synthesis needs of the manufacturer to the greatest extent.

[0085] Reference Figure 6 An intelligent optimization control system for an ethylbenzene synthesis unit is shown, comprising:

[0086] Equipment query unit 1, used to query multiple sets of alkylation reactors arranged in parallel;

[0087] A raw material upper and lower limit acquisition unit 2 is used to acquire the upper and lower limits of raw materials that each alkylation reactor can receive;

[0088] The combination unit 3 is used to fill the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, to form a plurality of alkylation reactor combinations containing different raw material portions, and output them as the initial combination;

[0089] A demand acquisition unit 4 is used to acquire the ethylbenzene synthesis demand and convert the ethylbenzene synthesis demand into an optimization target;

[0090] The intelligent optimization unit 5 is used to process the initial combination based on the optimization target by using the gray wolf optimization algorithm and obtain the optimal combination;

[0091] A conveying unit 6 is used to convey the raw materials to the corresponding alkylation reactor for ethylbenzene synthesis according to the optimal combination;

[0092] The equipment query unit 1 , the raw material upper and lower limit acquisition unit 2 , the combination unit 3 , the intelligent optimization unit 5 and the conveying unit 6 are connected in data in sequence, and the demand acquisition unit 4 is connected in data with the intelligent optimization unit 5 .

[0093] The equipment query unit 1 can be used to obtain the alkylation reactors connected in parallel in the factory, and then the raw material upper and lower limit acquisition unit 2 can obtain the raw material upper and lower limits of the alkylation reactors connected in parallel, and the combination unit 3 can fill the raw material portions into the alkylation reactor according to the raw material upper and lower limits, and randomly combine the alkylation reactors with different raw material portions, so as to obtain multiple initial combinations, and the demand acquisition unit 4 can obtain the ethylbenzene synthesis demand of the manufacturer, including the demand for output speed, environmental pollution and production cost, and then the ethylbenzene synthesis demand can be converted into an optimization target, and the intelligent optimization unit 5 can obtain the optimal combination after optimizing the initial combination through the gray wolf optimization algorithm, and the raw material portions in the alkylation reactor in the optimal combination are the optimal raw material portions, and finally the transportation unit 6 can transport the optimal combination to the factory, and the factory can add the raw materials to the corresponding alkylation reactor according to the optimal raw material portions for ethylbenzene synthesis, which can maximize the satisfaction of the factory's ethylbenzene synthesis demand.

[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent optimization control method for an ethylbenzene synthesis unit, characterized in that: The following steps are involved: S1. Query multiple sets of alkylation reactors arranged in parallel; S2. Obtaining the upper and lower limits of the raw materials that each alkylation reactor can accept; S3, filling the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, forming several sets of alkylation reactor combinations containing different raw material portions, and outputting them as initial combinations; S4, obtaining ethylbenzene synthesis demand, and converting the ethylbenzene synthesis demand into an optimization target; S5. Using the Grey Wolf Optimization Algorithm to process the initial combination based on the optimization target and obtain the optimal combination; S6. transporting the raw materials to the corresponding alkylation reactor according to the optimal combination to synthesize ethylbenzene; Wherein, the step S3 is specifically as follows: S31, determining the increase or decrease interval of the number of raw materials; S32, determining the number of multiple groups of raw material portions that can be filled in each alkylation reactor based on the increase and decrease interval of the raw material portion and the upper and lower limits of the raw material; S33, randomly arranging and combining the alkylation reactors with the raw material portions, outputting the initial combination and then screening and eliminating them; The step S4 is specifically as follows: S41, determining whether there is a time requirement for the current ethylbenzene synthesis, and if there is a time requirement, outputting the output speed as an optimization target; S42, determining whether there is an emission requirement for the current ethylbenzene synthesis, and if there is an emission requirement, outputting the impact on the environment as an optimization target; S43. If there is no time requirement or emission requirement for the current ethylbenzene synthesis, the production cost is output as the optimization target; The step S5 is specifically as follows: S51, initializing the gray wolf population and the number of iterations; S52, randomly selecting an initial combination, and calculating the fitness value of the gray wolf based on the optimization target; S53, selecting another initial combination, calculating the fitness value of the gray wolf, and comparing it with the fitness value calculated last time, and retaining the initial combination with the larger fitness value; S54, perform iterative calculations, and output the initial combination with the largest fitness value as the optimal combination.

2. The intelligent optimization control method for an ethylbenzene synthesis device according to claim 1, characterized in that: The specific steps of step S1 are: querying the alkylation reactor in use from the plant management system, and determining the connection mode of the alkylation reactor, and determining multiple sets of alkylation reactors connected in parallel through the connection mode.

3. The intelligent optimization control method of an ethylbenzene synthesis device according to claim 1, characterized in that: The specific steps of step S2 are: S21, obtaining historical usage data of the alkylation reactor, wherein the historical usage data includes reaction time, reaction temperature, reaction pressure, and heat transfer efficiency; S22, training the neural network using historical usage data, and testing the trained neural network; S23, inputting the complete usage data of the alkylation reactors arranged in parallel into the trained neural network for processing, and obtaining the upper and lower limits of the raw materials that the alkylation reactors can accept.

4. The intelligent optimization control method for an ethylbenzene synthesis device according to claim 1, characterized in that: The specific steps of screening and eliminating in step S33 are: determining the total amount of raw materials, calculating the sum of the raw material portions of all alkylation reactors in each initial combination, and eliminating the initial combination whose sum of the raw material portions is not equal to the total amount of raw materials.

5. The intelligent optimization control method for an ethylbenzene synthesis device according to claim 1, characterized in that: The number of iterations is the number of initial combinations.

6. A system using the intelligent optimization control method for an ethylbenzene synthesis device according to any one of claims 1 to 5, characterized in that: include: Equipment query unit, used to query multiple sets of alkylation reactors arranged in parallel; A raw material upper and lower limit acquisition unit is used to obtain the upper and lower limits of raw materials that each alkylation reactor can receive; A combination unit is used to fill the raw material portions into the alkylation reactor with the upper and lower limits of the raw material as restrictions, to form a plurality of alkylation reactor combinations containing different raw material portions, and output them as initial combinations; A demand acquisition unit, used for acquiring the demand for ethylbenzene synthesis and converting the demand for ethylbenzene synthesis into an optimization target; An intelligent optimization unit, used to process the initial combination based on the optimization target using the Grey Wolf optimization algorithm and obtain the optimal combination; A conveying unit, used for conveying the raw materials to the corresponding alkylation reactor for ethylbenzene synthesis according to the optimal combination; The equipment query unit, the raw material upper and lower limit acquisition unit, the combination unit, the intelligent optimization unit and the conveying unit are connected in data in sequence, and the demand acquisition unit is connected in data with the intelligent optimization unit.

Images