Method, system and storage medium for ethylene cracker cluster depth optimization

Abstract

The application provides a cracking depth optimization method for an ethylene cracking furnace group, a cracking depth optimization system for the ethylene cracking furnace group, and a computer readable storage medium. The cracking depth optimization method for the ethylene cracking furnace group provided by the application comprises the following steps: determining a multi-dimensional optimization variable based on each operation variable of each cracking furnace, determining a constraint condition of the optimization variable according to an upper limit and a lower limit of the optimization variable, and determining an optimization target function based on a minimum constraint value of ethylene production of the cracking furnace group; and inputting the multi-dimensional optimization variable into a depth optimization model, and determining an optimized cracking depth value of the cracking furnace group by the depth optimization model according to the optimization target function within the constraint condition of the optimization variable, wherein the depth optimization model is constructed by a whale optimization algorithm of a reinforcement exploration mechanism.

Description

Technical Field

[0001] This invention relates to the field of ethylene production, and more particularly to a method for optimizing the cracking depth of an ethylene cracking furnace group, a system for optimizing the cracking depth of an ethylene cracking furnace group, and a computer-readable storage medium. Background Technology

[0002] Ethylene is a crucial petrochemical product and one of the fundamental raw materials for manufacturing organic products in the entire petrochemical industry. The technology, output, and scale of ethylene production signify the level of development of a country's petrochemical industry. The ethylene cracking furnace is a key unit in the olefin thermal cracking process, and its operational level directly affects the yield of various products, thus influencing the economic efficiency of the cracking unit. Due to the highly complex composition and operation of the cracking furnace, modeling, simulating, and optimizing the cracking process are currently common and effective methods for improving the economic efficiency of the ethylene industry.

[0003] Cracking depth is a crucial indicator of the extent of reaction in a cracking furnace. Many parameters characterize cracking depth, such as methane yield, methane-to-propylene yield ratio, propylene-to-ethylene yield ratio (propylene-to-ethylene ratio), and coil outlet temperature (COT). However, regardless of the parameter used, the controlled variable is COT. Existing ethylene cracking units all use COT control to adjust cracking depth, and the COT setpoint is often selected based on the specified or empirical values ​​provided by the cracking furnace manufacturer under the designed feedstock conditions. However, given the complexity of feedstock sources and the large fluctuations in oil properties, a fixed COT operating mode cannot promptly reflect changes in cracking depth and cracked product yield caused by variations in feedstock composition and cracking furnace operating conditions.

[0004] In order to overcome the above-mentioned defects in the existing technology, there is an urgent need in the field for a cracking depth optimization technology for ethylene cracking furnace groups, which can determine the optimal cracking depth in real time based on the current real-time operation of the cracking furnace. Summary of the Invention

[0005] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form to prepare for the more detailed descriptions that follow.

[0006] In order to overcome the above-mentioned defects of the existing technology, the present invention provides a cracking depth optimization technology for ethylene cracking furnace groups, which can determine the optimal cracking depth in real time based on the current real-time operation of the cracking furnace.

[0007] Specifically, the above-described method for optimizing the cracking depth of an ethylene cracking furnace group according to the first aspect of the present invention includes the steps of: determining multidimensional optimization variables based on the operating variables of each cracking furnace; determining the constraints of the optimization variables according to the upper and lower limits of the optimization variables; and determining an optimization objective function based on the minimum ethylene production constraint value of the cracking furnace group; and inputting the multidimensional optimization variables into a depth optimization model, wherein the depth optimization model determines the optimized cracking depth value of the cracking furnace group within the constraint conditions of the optimization variables according to the optimization objective function, wherein the depth optimization model is constructed by a whale optimization algorithm with an enhanced exploration mechanism.

[0008] Preferably, in one embodiment of the present invention, the step of determining the optimized pyrolysis depth value of the pyrolysis furnace group includes: within the range of the constraints, using the enhanced exploration mechanism whale optimization algorithm, to determine the optimized pyrolysis depth value of the pyrolysis furnace group by iteratively calculating and adjusting the multidimensional optimization variables.

[0009] Preferably, in one embodiment of the present invention, the step of determining the pyrolysis depth value of the optimized pyrolysis furnace group by iteratively calculating and adjusting the multidimensional optimization variables within the constraints includes: S1: initializing control parameters and a set of whale populations, and determining the optimal whale individual according to the fitness function, wherein the whale population includes n whale individuals; S2: updating the control parameters, and determining the first position vector and its fitness function value for each whale individual according to the control parameters, wherein the dimension of the first position vector is within the upper and lower limits of the dimension; S3: determining the second position vector and its fitness function value for each whale individual using a back-learning method, wherein the dimension of the second position vector is within the upper and lower limits of the dimension; S4: determining the optimal position vector and its fitness function value using a random candidate method. S5: Determine the third position vector and its fitness function value for each whale individual using a random assignment method, wherein the dimension of the third position vector is within the upper and lower bounds of the dimension; S6: Based on the fitness function value, sort the first, second, third, and fourth position vectors of all determined whale individuals in ascending order, select the top n position vectors as the positions of each whale individual in the next generation whale population, and update the position vector of the whale individual with the highest fitness function value as the optimal whale individual; and S7: Repeat steps S2 to S6 until the number of iterations reaches the maximum number of population iterations or the convergence condition of the deep optimization model is met.

[0010] Preferably, in one embodiment of the present invention, the control parameters include the maximum number of population iterations, population size, target prey position, current whale position, current iteration number, first coefficient vector, second coefficient vector, first variable controlling the position update method, second variable controlling the coefficient vector, logarithmic spiral shape constant, and random number.

[0011] Preferably, in one embodiment of the present invention, the step of determining the first position vector of each individual whale according to the control parameters includes: determining the first position vector according to a contraction encirclement mechanism with a convergent adaptive weighting strategy in response to a first variable of the control update position method being less than 0.5 and a first coefficient vector being less than 1; determining the first position vector according to a random update mechanism with a convergent adaptive weighting strategy in response to a first variable being less than 0.5 and a first coefficient vector being greater than or equal to 1; and determining the first position vector according to a spiral update position mechanism in response to a first variable being greater than or equal to 0.5.

[0012] Preferably, in one embodiment of the present invention, steps S2 to S5 include: updating the value of the dimension when the dimension of the first position vector and / or the second position vector and / or the third position vector and / or the fourth position vector violates the upper and lower limit constraints of the dimension.

[0013] Preferably, in one embodiment of the present invention, steps S2 to S5 further include: converting the first position vector and / or the second position vector and / or the third position vector and / or the fourth position vector into integer vectors according to the encoding conversion function.

[0014] Preferably, in one embodiment of the present invention, the optimization objective function includes maximizing ethylene yield and / or maximizing propylene yield and / or maximizing diene yield.

[0015] Preferably, in one embodiment of the present invention, the step of determining the constraint conditions of the optimization variable based on the upper and lower limits of the optimization variable includes: discretizing the upper and lower limits of the optimization variable to determine the constraint conditions of the optimization variable.

[0016] Furthermore, the above-described cracking depth optimization system for an ethylene cracking furnace group provided according to a second aspect of the present invention includes a memory and a processor. The memory stores computer instructions. The processor is connected to the memory and configured to execute the computer instructions stored in the memory to implement the cracking depth optimization method for an ethylene cracking furnace group provided in any of the above embodiments.

[0017] Furthermore, the computer-readable storage medium provided according to the third aspect of the present invention stores computer instructions. When the computer instructions are executed by a processor, the cracking depth optimization method for ethylene cracking furnace groups provided in any of the above embodiments is implemented. Attached Figure Description

[0018] The above-described features and advantages of the present invention will be better understood after reading the following detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings. In the drawings, components are not necessarily drawn to scale, and components having similar related characteristics or features may have the same or similar reference numerals.

[0019] Figure 1 A flowchart of a method for optimizing the cracking depth of an ethylene cracking furnace group, according to some embodiments of the present invention, is shown.

[0020] Figure 2 A schematic diagram of an ethylene cracking furnace according to some embodiments of the present invention is shown;

[0021] Figure 3A flowchart of the whale optimization algorithm, an enhanced exploration mechanism for a depth optimization model provided according to some embodiments of the present invention, is shown.

[0022] Figure 4 A schematic diagram of a spiral position update mechanism provided according to some embodiments of the present invention is shown;

[0023] Figure 5 The diagram shows the effect of the cracking depth optimization method for ethylene cracking furnace groups; and

[0024] Figure 6 The diagram shows the effect of the method for optimizing the cracking depth for ethylene cracking furnace groups.

[0025] Figure label:

[0026] 100: A method for optimizing the cracking depth of ethylene cracking furnace groups;

[0027] S110~S120: Steps;

[0028] 200: Ethylene cracking furnace;

[0029] 201: Liquid phase feed line;

[0030] 202: Boiler feedwater preheater;

[0031] 203: Dilution steam distributor;

[0032] 204: Phosphate-free feedwater preheater;

[0033] 205: Ultra-high pressure steam superheater;

[0034] 206: Fuel gas feed line;

[0035] 207: Steam drum;

[0036] 208: Sewage discharge device;

[0037] 209: Pyrolysis gas outlet;

[0038] S1~S7: Steps; and

[0039] 501, 502, 601, 602: lines. Detailed Implementation

[0040] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should be noted that the aspects described below with reference to the accompanying drawings and specific embodiments are merely exemplary and should not be construed as limiting the scope of protection of the present invention in any way.

[0041] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0042] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood as the orientations shown in the relevant paragraphs and accompanying drawings. These relative terms are for illustrative purposes only and do not imply that the described apparatus must be manufactured or operated in a specific orientation, and therefore should not be construed as limiting the invention.

[0043] It is understood that although terms such as "first," "second," and "third" may be used herein to describe various components, regions, layers, and / or parts, these components, regions, layers, and / or parts should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers, and / or parts. Therefore, the first components, regions, layers, and / or parts discussed below may be referred to as second components, regions, layers, and / or parts without departing from some embodiments of the present invention.

[0044] As mentioned above, existing ethylene cracking furnaces all use COT (Cost-to-Operate) control to adjust the cracking depth, and the COT setpoint is often selected based on the specified value or experience value provided by the cracking furnace manufacturer under the design feedstock conditions. However, facing factors such as complex feedstock sources and large fluctuations in oil properties, a fixed COT production operation mode cannot reflect in a timely manner the changes in cracking depth and cracked product yield caused by changes in the composition of the cracking feedstock and the operating conditions of the cracking furnace.

[0045] In order to overcome the above-mentioned defects of the existing technology, the present invention provides a cracking depth optimization technology for ethylene cracking furnace groups, which can determine the optimal cracking depth in real time based on the current real-time operation of the cracking furnace.

[0046] In some non-limiting embodiments, the method for optimizing the cracking depth of an ethylene cracking furnace group provided in the first aspect of the present invention can be implemented via the system for optimizing the cracking depth of an ethylene cracking furnace group provided in the second aspect of the present invention. Specifically, the system for optimizing the cracking depth of an ethylene cracking furnace group may be configured with a memory and a processor. The memory includes, but is not limited to, the computer-readable storage medium provided in the third aspect of the present invention, on which computer instructions are stored. The processor is connected to the memory and configured to execute the computer instructions stored in the memory to implement the method for optimizing the cracking depth of an ethylene cracking furnace group provided in the first aspect of the present invention.

[0047] The following will first describe the working principle of the above-mentioned pyrolysis depth optimization system for ethylene cracking furnace groups using some embodiments of pyrolysis depth optimization methods for ethylene cracking furnace groups. Those skilled in the art will understand that these embodiments of the pyrolysis depth optimization methods for ethylene cracking furnace groups are merely non-limiting implementations provided by the present invention, intended to clearly demonstrate the main concepts of the invention and provide specific solutions convenient for public implementation, rather than limiting all functions or operating methods of the pyrolysis depth optimization system for ethylene cracking furnace groups. Similarly, the pyrolysis depth optimization system for ethylene cracking furnace groups is also only one non-limiting implementation provided by the present invention, and does not limit the executing entity and execution order of the steps in these pyrolysis depth optimization methods for ethylene cracking furnace groups.

[0048] Please refer to Figure 1 , Figure 1 A flowchart of a method for optimizing the cracking depth of an ethylene cracking furnace group, according to some embodiments of the present invention, is shown.

[0049] like Figure 1 As shown, the method for optimizing the cracking depth of an ethylene cracking furnace group may include step S110: determining multidimensional optimization variables based on the operating variables of each cracking furnace, determining the constraints of the optimization variables according to the upper and lower limits of the optimization variables, and determining the optimization objective function based on the minimum constraint value of the ethylene production of the cracking furnace group.

[0050] Please refer to Figure 2 , Figure 2 A schematic diagram of an ethylene cracking furnace according to some embodiments of the present invention is shown.

[0051] like Figure 2As shown, in a non-limiting embodiment, the ethylene cracking furnace 200 is an STR-V type cracking furnace, including a liquid feedstock pipeline 201, a boiler feedwater preheater 202, a dilution steam distributor 203, a phosphorus-free feedwater preheater 204, an ultra-high pressure steam superheater 205, a fuel gas feedstock pipeline 206, a steam drum 207, a blowdown device 208, a cracked gas outlet 209, and a quench heat exchanger 210. Hydrocarbon feedstock can be fed into the ethylene cracking furnace 200 through the liquid feedstock pipeline 201. After preheating, it is mixed with dilution steam and then undergoes a cracking reaction under high temperature and oxygen-free conditions to produce small molecule olefins. After cracking, the high-temperature cracked gas can be rapidly cooled by the quench heat exchanger 210 to recover the heat of the cracked gas and generate ultra-high pressure steam. Finally, the cracked gas is discharged from the cracked gas outlet 209 for subsequent processing.

[0052] The operating variables of a single cracking furnace can include operating conditions and feed properties. Operating conditions can include information such as feed load, dilution steam ratio, feed temperature, feed pressure, outlet temperature, and outlet pressure. Feed properties can be oil properties, including feed density, mass percentage of alkanes and olefins, and real-time data from online cracking gas analyzers.

[0053] Based on the operating variables of each cracking furnace, the cracking depth optimization system can construct input elements for multidimensional optimization variables. The number of rows in the matrix of input elements for multidimensional optimization variables represents the number of cracking furnaces in the cracking furnace group, and the number of columns represents the number of selected operating variables. In one example, the columns can be outlet temperature, dilution steam ratio, feed flow rate, outlet pressure, cross-section feed temperature, and cross-section feed pressure, respectively. The input elements of each cracking furnace can then constitute the multidimensional optimization variables.

[0054] The optimization variable for each cracking furnace can be the outlet temperature (COT) in the operating conditions. Based on the upper and lower limits of the optimization variable COT, the constraints of the optimization variable can be determined. Here, the cracking depth optimization system can discretize the original continuous optimization problem into a combinatorial optimization problem, that is, discretize the upper and lower limits of the optimization variable COT. The feasible set formed after discretization is the constraint of the optimization variable.

[0055] Preferably, the cracking depth optimization system can establish a cracking furnace mechanism model based on the furnace type information of the currently operating cracking furnace to predict products, thereby determining the yields of key components such as ethylene and propylene under the current operating conditions. The cracking furnace mechanism model can be a mechanism model established based on chemical engineering principles and chemical reaction engineering, wherein the cracking reaction mechanism is a free radical reaction mechanism.

[0056] Based on the on-site operating conditions, the cracking depth optimization system can determine the minimum constraint value for ethylene production of the cracking furnace group and further select an optimization objective function. Here, the optimization objective function can include maximizing ethylene yield, maximizing propylene yield, or maximizing diene yield. In a preferred embodiment, the optimization objective function is maximizing ethylene yield or maximizing diene yield. Depending on the actual ethylene production, the cracking depth optimization system can choose to use increasing ethylene production as the optimization objective, or it can use the selected optimization objective function as the optimization objective. For example, when the actual ethylene production is lower than the minimum constraint value for ethylene production, the cracking depth optimization system selects increasing ethylene production as the optimization objective.

[0057] like Figure 1 As shown, the method for optimizing the cracking depth of an ethylene cracking furnace group may include step S120: inputting multidimensional optimization variables into a depth optimization model, and the depth optimization model determining the optimized cracking depth value of the cracking furnace group within the constraint conditions of the optimization variables according to the optimization objective function, wherein the depth optimization model is constructed by the whale optimization algorithm with enhanced exploration mechanism.

[0058] Specifically, the pyrolysis depth optimization system can determine the optimal pyrolysis depth value of the pyrolysis furnace group by using the whale optimization algorithm with an enhanced exploration mechanism within the constraints, through iterative calculation and adjustment of multidimensional optimization variables.

[0059] Please refer to Figure 3 , Figure 3 A flowchart of the whale optimization algorithm, an enhanced exploration mechanism for a depth optimization model provided according to some embodiments of the present invention, is shown.

[0060] like Figure 3 As shown, the deep optimization model constructed by the whale optimization algorithm with enhanced exploration mechanism first executes step S1: initializing control parameters and a set of whale populations, and determining the best whale individual according to the fitness function, wherein the whale population includes n whale individuals.

[0061] Here, the control parameters include the maximum number of population iterations (Max_iters), the population size (population_size), and the target prey location (X). best (i.e., the current best individual whale), current whale position X(t), current iteration number t, first coefficient vector A, second coefficient vector C, first variable p controlling the method of updating the position, second variable h controlling the range of coefficient vector A, logarithmic spiral shape constant b, and random number l. The first variable p controls the method of updating the position, including shrinking the bounding box and spiral updating, etc. The value of the second variable h decreases linearly from 2 to 0. The logarithmic spiral shape constant b is generally set to 0, and the random number l can be a random number in [0, 1].

[0062] In an initialized population of whales, the position vector of the i-th whale individual is:

[0063] X i (t)=[x 0，i (t), x 1，i (t), ..., x N-1，i (t)],

[0064] Each dimension corresponds to the pyrolysis depth of a single pyrolysis furnace in the pyrolysis furnace group. Therefore, each dimension is constrained by the upper and lower limits of the pyrolysis depth of its corresponding furnace. Here, the upper and lower limits of the pyrolysis depth of the corresponding furnace can be:

[0065] x j，min ≤x j，i (t)≤x j，max j = 0, 1, 2, ..., N-1,

[0066] Where the subscript j represents the dimension number, i.e., the j-th pyrolysis furnace; the subscript i represents the i-th individual in the whale population. The number of individuals in the whale population can be determined by the population size (population_size). In this example, the number of individuals in the whale population is n. Therefore, the formula for randomly initializing the upper and lower limits of each pyrolysis furnace is:

[0067] x j，i (0)=x j，min +rand·(x j，max -x j，min ),

[0068] Here, rand is a random number between 0 and 1. Repeating the above random initialization steps generates the initial position of each individual whale in the whale population. By calculating the fitness function value of each individual whale, the whale with the optimal fitness function value is selected and marked as the best whale individual X. best .

[0069] Then, when the number of iterations iter is less than the maximum number of iterations Max_iters, step S2 is executed: update the control parameters, and determine the first position vector and its fitness function value for each individual whale based on the control parameters. The dimension of the first position vector is within the upper and lower bounds of the dimension.

[0070] Here, the cleavage depth optimization can update the first coefficient vector A, the second coefficient vector C, the first variable p that controls the way the update position is, the second variable h that controls the range of the coefficient vector A, and the random number l in the control parameters.

[0071] The cleavage depth optimization system first updates the second variable h within the range of the control coefficient vector A:

[0072]

[0073] Then, based on the updated second variable h, the first coefficient vector A is updated, and the second coefficient vector C, the first variable p controlling the update position, and the random number l are continued to be updated:

[0074] A = 2h·rand-h,

[0075] C = 2·rand,

[0076] p = rand(0, 1),

[0077]

[0078] Subsequently, in a preferred embodiment, based on the first variable p and the first coefficient vector A in the updated control parameters, the cleavage depth optimization system can determine the method of updating the position and determine the first position vector of each individual whale based on the determined method of updating the position.

[0079] Specifically, when the first variable p is less than 0.5, the first coefficient vector A is evaluated. When the first coefficient vector A is less than 1, the fragmentation depth optimization system can determine the first position vector X according to the shrinking encirclement mechanism with a convergent adaptive weighting strategy. local (t+1).

[0080] The update formula for the shrinking encirclement mechanism with convergent adaptive weighting strategy is as follows:

[0081] X local (t+1)=r×X best (t)-A·B,

[0082] The formula for calculating the weight r is as follows:

[0083]

[0084] The formula for calculating B is:

[0085] B = |C·X best (t)-X local (t)|,

[0086] Among them, X local (t) is the position vector X(t) of the whale individual selected to update its position in the current population.

[0087] When the first variable p is less than 0.5 and the first coefficient vector A is greater than or equal to 1, the cleavage depth optimization system can determine the first position vector X according to the stochastic update mechanism with a convergent adaptive weighting strategy. local (t+1).

[0088] The update formula for the stochastic update mechanism with convergent adaptive weighting strategy is as follows:

[0089] X local (t+1)=r×X best (t)-A·B,

[0090] The formula for calculating the weight r is the same as that for the shrinking encirclement mechanism with convergent adaptive weighting strategy:

[0091]

[0092] The formula for calculating B is:

[0093] B = |C·X rand (t)-X local (t)|,

[0094] Among them, X rand (t) is the position vector of a randomly selected whale individual in the current population.

[0095] Furthermore, when the first variable p is greater than or equal to 0.5, the cleavage depth optimization system can determine the first position vector X according to the spiral update position mechanism. local (t+1).

[0096] Please refer to Figure 4 , Figure 4 A schematic diagram of a spiral position update mechanism provided according to some embodiments of the present invention is shown.

[0097] like Figure 4 As shown, the horizontal axis 1 represents the parameters in the spiral position update mechanism, and the vertical axis x represents the whale's position. The spiral position update mechanism can mimic the spiral movement of a humpback whale hunting. First, it calculates the position of the whale at (X, Y) and the position of the whale at (X... * Y * The distance D between the whale and its prey is calculated, and a spiral equation is then created between the positions of the whale and its prey to simulate the whale's spiral movement.

[0098] The equation for this spiral is as follows:

[0099] X local (t+1)=X best (t)+B p ·e bl cos(2πl),

[0100] Among them, B p The calculation formula is as follows:

[0101] B p =|X best (t)-X local (t)|.

[0102] Thus, based on the control parameters, the first position vector of each individual whale in the whale population is updated to complete the update of the first position vector of all individual whales in the whale population.

[0103] Furthermore, each dimension of the determined first position vector of the whale individual is within the upper and lower bounds of its corresponding dimension, that is, within the upper and lower bounds of the operation variables corresponding to the dimension. When a dimension of the first position vector violates the upper and lower bounds of its corresponding dimension, the value of that dimension needs to be updated so that each dimension is within the upper and lower bounds of its corresponding dimension. Specifically, the value of the dimension can be updated using the following formula:

[0104]

[0105]

[0106] Where, x j，i (t) represents the j-th dimension of the i-th whale individual in the whale population during the t-th iteration, x j，i `new` represents the j-th dimension of the position vector to be updated for the i-th whale individual. Here, this position vector is the first position vector X. local (t+1).

[0107] Then, based on the updated first position vectors of all whale individuals, the fitness function value of each whale individual is calculated to determine the optimal whale individual X for the next generation of whale population. best (t+1).

[0108] Please continue to refer to this. Figure 3 Perform steps S3 to S5 respectively:

[0109] S3: Use reverse learning to determine the second position vector and its fitness function value for each individual whale. The dimension of the second position vector is within the upper and lower bounds of the dimension.

[0110] S4: Use a random candidate method to determine the third position vector and its fitness function value for each individual whale. The dimension of the third position vector is within the upper and lower bounds of the dimension.

[0111] S5: Use a random assignment method to determine the fourth position vector and its fitness function value for each individual whale. The dimension of the fourth position vector is within the upper and lower bounds of the dimension.

[0112] For step S3, the reverse learning method can be used to obtain the reverse solution set of the whale population. Specifically, in multidimensional space, assume the solution set of the whale population is: IP = (X1, X2, ..., X...). n), that is, the set of all current whale positions X(t). Thus, the reverse solution set of the whale population is: OP = (X... 1op X 2op ,..,X nop The search range of the solution space is [Lb, Ub]. Thus, the inverse solution set OP of the solution set IP of the whale population can be realized by the following equation:

[0113] X iop =Lb+Ub-X i ,

[0114] Among them, X iop Let X be the second position vector of the determined i-th individual whale. i Let X(t) be the current position of the whale.

[0115] Similar to the first position vector, the second position vector X iop Each dimension must also be within the upper and lower bounds of the corresponding dimension. When the second position vector X iop When a dimension violates the upper and lower bound constraints of a dimension, the value of that dimension needs to be updated. Specifically, the second position vector X iop The dimension can be updated using the following formula:

[0116]

[0117]

[0118] Where, x j,i `new` represents the j-th dimension of the position vector to be updated for the i-th whale individual; here, this position vector is the second position vector X. iop .

[0119] Thus, based on the reverse learning method, the split depth optimization system can update the second position vector of each individual whale in the whale population, thereby updating the second position vectors of all whale individuals in the population, and forming a new solution set X from the second position vectors of all whale individuals. op Furthermore, based on the updated second position vector X of each individual whale... iop Calculate the fitness function value for each individual whale.

[0120] Furthermore, the splitting depth optimization system can better protect the position of the best whale by using a randomized alternative method to gather individual whales into the optimal position after each iteration. While the randomized alternative method can accelerate the convergence of the depth optimization model, it also carries the risk of the model getting trapped in local optima.

[0121] Specifically, the random candidate selection method, under certain probability conditions, replaces the spatial position of an individual whale with the spatial position of the best individual whale in each iteration of the whale population, thus forming a third position vector. Here, the probability condition is:

[0122]

[0123] Each dimension of the third position vector must also be within the upper and lower bounds of its corresponding dimension. When a dimension of the third position vector violates the upper and lower bounds of its dimension, the value of that dimension needs to be updated. Specifically, the dimension of the third position vector can be updated using the following formula:

[0124]

[0125]

[0126] Where, x j,i `new` represents the j-th dimension of the position vector to be updated for the i-th whale individual, where this position vector is the third position vector.

[0127] Thus, according to the random candidate method, the split depth optimization system can update the third position vector of each individual whale in the whale population, thereby updating the third position vectors of all whale individuals in the population, and forming a new solution set X from the third position vectors of all whale individuals. rs Furthermore, based on the updated third position vector of each individual whale, the fitness function value of each individual whale is calculated.

[0128] Furthermore, the cleavage depth optimization system can enhance the global search capability of the depth optimization model based on the whale optimization algorithm with a reinforcement exploration mechanism using a random assignment method. Specifically, after each iteration, the position of each individual whale is randomly redistributed within a region of radius k:

[0129] X ird =X i +k×rand×sgin(rand-0.5),

[0130]

[0131] Among them, X ird X is the fourth position vector. i Let X(t) be the current whale position, [Lb, Ub] be the search range of the solution space, and sgin be the sign function, which is a function that returns a corresponding result based on the sign of the input value. Specifically, when the input value is greater than 0, sgin be returns 1; when the input value is equal to 0, sgin be returns 0; and when the input value is less than 0, sgin be returns -1.

[0132] Fourth position vector X ird Each dimension must also be within the upper and lower bounds of the corresponding dimension. When the fourth position vector X ird When a dimension violates the upper and lower bounds of the dimension, the value of that dimension needs to be updated. Specifically, the fourth position vector X ird The dimension can be updated using the following formula:

[0133]

[0134]

[0135] Where, x j，i `new` represents the j-th dimension of the position vector to be updated for the i-th whale individual; here, this position vector is the fourth position vector X. ird .

[0136] Thus, based on the random candidate method, the cleavage depth optimization system can update the fourth position vector X of each individual whale in the whale population. ird To complete the fourth position vector X of all whale individuals in the whale population. ird The update is thus determined by the fourth position vector X of all individual whales. ird Form a new solution set X rd Furthermore, based on the updated fourth position vector X of each individual whale... ird Calculate the fitness function value for each individual whale.

[0137] Thus, after determining the first, second, third, and fourth position vectors for each individual whale in the initial whale population, the cleavage depth optimization system obtains 4n position vectors (n being the number of individual whales in the whale population).

[0138] More preferably, after determining the first, second, third, and fourth position vectors that do not violate the upper and lower bound constraints of the dimension, the fraction depth optimization system can also convert the first, second, third, and fourth position vectors into integer vectors according to the encoding conversion function.

[0139] After that, as Figure 3 As shown, the split depth optimization system continues to execute step S6 of the offline training phase: based on the fitness function value, the first position vector, second position vector, third position vector and fourth position vector of all determined whale individuals are sorted in ascending order, the top n position vectors are selected as the positions of each whale individual in the next generation whale population, and the position vector of the whale individual with the highest fitness function value is updated as the best whale individual.

[0140] Please continue to refer to this. Figure 3 The split depth optimization system continues to execute step S7 of the offline training phase: repeat steps S2 to S6 above until the number of iterations reaches the maximum population iterations Max_iters or the convergence condition of the depth optimization model is met.

[0141] By execution Figure 3 The whale optimization algorithm with enhanced exploration mechanism shown can obtain a set of values ​​that satisfy the constraints of the cleavage depth optimization system. This set of values This refers to the pyrolysis depth value of the pyrolysis furnace group determined by the deep optimization model based on the objective function within the constraint conditions of the optimization variables.

[0142] The following is a specific, non-limiting preferred embodiment, which will be used to further illustrate the cracking depth optimization system for ethylene cracking furnace groups proposed in this invention.

[0143] In this embodiment, the cracking depth optimization system selects the propylene-to-ethylene ratio (propylene yield to ethylene) as the cracking depth index to be optimized by the depth optimization model. Based on the optimized cracking depth value determined by the cracking depth optimization system, the system provides the cracking depth setpoint for the cracking depth controller of each cracking furnace in the cracking furnace group.

[0144] First, the cracking depth optimization system determines the objective function based on the selected optimization index to improve the flexibility of the depth optimization model. In this embodiment, the optimization index is the propylene-to-ethylene ratio. The objective functions include maximizing ethylene yield, maximizing propylene yield, and maximizing diene yield.

[0145] Here, the mathematical expression for optimizing the objective function can be expressed as follows:

[0146]

[0147] Where f1(x), f2(x), and f3(x) represent maximizing ethylene yield, maximizing propylene yield, and maximizing diene yield, respectively; X0 is the current feed rate to the cracking furnace; and W... C2H4 W represents the product yield of C2H4. C3H6 The product yield of C3H6 is given by mass.

[0148] The current whale position X(t) represents the pyrolysis depth value of each pyrolysis furnace. Here, the pyrolysis depth X of pyrolysis furnaces F1 to F18 is... i The upper limit is The lower limit is The minimum ethylene production limit for the cracking furnace group is MIN. C2H4 The actual ethylene production situation is REAL C2H4By using the cracking furnace mechanism model, the ethylene production rate can be predicted to be MODEL. C2H4 During the optimization process of the deep optimization model, the ethylene production rate can be predicted as MODEL' using the cracking furnace mechanism model. C2H4 .

[0149] In this embodiment, the pyrolysis depth optimization system can select to optimize the j-th pyrolysis furnace, so that the upper and lower limits of the pyrolysis depth of this pyrolysis furnace can be maintained as follows: j = 0, 1, 2, ..., 18; The pyrolysis depth optimization system can also choose not to optimize the j-th pyrolysis furnace, and the upper and lower limits of the pyrolysis depth optimization range for that pyrolysis furnace are the current pyrolysis depth. Right now This indicates that the cracking furnace does not require optimization.

[0150] Therefore, when the actual ethylene production situation REAL C2H4 The minimum ethylene production limit (MIN) of the cracking furnace group is greater than the minimum limit. C2H4 At that time, the ethylene production MODEL′ calculated by the cracking furnace mechanism model during the optimization process is satisfied. C2H4 Compared to the ethylene production model before optimization C2H4 The decrease is smaller than the actual ethylene production. C2H4 Compared to the minimum ethylene production constraint value (MINC) of the cracking furnace group 2H4 When constrained by the surplus value, the fracturing depth optimization system optimizes in the direction of maximizing the user-defined objective function:

[0151]

[0152] in, and These are f1(x) and f2(x) in the above optimization objective function.

[0153] In addition, when the actual ethylene production situation REAL C2H4 Less than the minimum constraint value MIN for ethylene production of the cracking furnace group C2H4 At that time, the cracking depth optimization system uses maximizing the ethylene yield f1(x) as the optimization objective function, and during the optimization process, the ethylene production MODEL′ calculated by the cracking furnace mechanism model is... C2H4 Compared to the ethylene production model before optimization C2H4 The increase cannot exceed the actual ethylene production situation. C2H4 Compared to the minimum ethylene production constraint value MIN of the cracking furnace group C2H4 The missing value multiplied by a certain empirical coefficient α:

[0154]

[0155] Subsequently, based on the operating variables of each cracking furnace, the cracking depth optimization system can construct input elements for multidimensional optimization variables. The number of rows in the matrix of input elements for multidimensional optimization variables is the number of cracking furnaces in the cracking furnace group, and the number of columns is the number of selected operating variables. Here, the input element a for each cracking furnace consists of outlet temperature cot, dilution steam ratio dor, feed flow rate feeded, outlet pressure pout, cross-section feed temperature tlec, and cross-section feed pressure pin. j :

[0156] a j =[cot j ,dor j feed j pout j tlec j pin j j = 1, 2, ..., 18.

[0157] According to the input element a of each cracking furnace j Multidimensional optimization variables can be constructed for pyrolysis furnace groups:

[0158] X = [a1, a2, ... a N ],

[0159] Where N is the number of cracking furnaces (in this embodiment, N = 18), and the optimization variable is the COT of each cracking furnace.

[0160] In the application scenario of ethylene cracking furnace clusters, whale populations often number in the hundreds. Furthermore, when calculating the position vector and objective function value of a single whale, the number of times the model is invoked matches the number of cracking furnaces. Therefore, during continuous optimization, a single iteration may require calling the mechanistic model thousands of times, and exiting the iteration may require calling the mechanistic model tens of thousands of times. Consequently, the time and computational resources required for continuous optimization algorithms in the continuously feasible region are excessively high.

[0161] Preferably, in order to reduce the number of calls to the pyrolysis furnace mechanism model and improve the timeliness of the whale optimization algorithm in the deep optimization model, the pyrolysis deep optimization system discretizes the original continuous optimization problem into a combinatorial optimization problem, that is, it sets the upper and lower limits of the COT of the j-th pyrolysis furnace [m j h j ]m j h j Discretize ∈Z into feasible set {m j m j +1, ..., h j -1,h jThe algorithm searches for the pyrolysis depth value of the pyrolysis furnace group within the constraint space of this feasible set. Here, the constraint space of this feasible set is the constraint condition of the optimization variable COT.

[0162] Thus, based on the aforementioned multidimensional optimization variables, the determined optimization objective function, and the constraints of the optimization variables, the optimization depth value of the pyrolysis furnace group is determined within the range of constraints using a deep optimization model.

[0163] Specifically, when determining the optimal pyrolysis depth value for a group of pyrolysis furnaces, the pyrolysis depth optimization system first initializes control parameters and a whale population. Here, the pyrolysis depth optimization system can set the maximum number of population iterations (Max_iters) to 100, the population size (population_size) to 150, and the logarithmic spiral shape constant (b) to 1.0, and set the current best individual whale X... best The number of times the iteration remains unchanged during the iteration process, unchange_iters, is set to 50, as a convergence condition for the deep optimization model.

[0164] The initial whale population is {X1(0), X2(0), X3(0), ..., X}. population_size-1 (0)}, the whale population is a uniformly distributed set of randomly generated integers. In an initialized set of whale populations, the position vector of the i-th whale individual is:

[0165] X i (0)=[x 0，i (0), x 1，i (0), ..., x N-1，i (0)],

[0166] Each dimension corresponds to the pyrolysis depth of a single pyrolysis furnace in the pyrolysis furnace group. Therefore, each dimension is constrained by the upper and lower limits of the pyrolysis depth of its corresponding furnace. Here, the upper and lower limits of the pyrolysis depth of the corresponding furnace can be:

[0167] x j，min ≤x j，i (0)≤x j，max j = 0, 1, 2, ..., N-1,

[0168] Wherein, the subscript j represents the dimension number, that is, the j-th pyrolysis furnace; the subscript i represents the i-th individual in the whale population; and N is the number of pyrolysis furnaces.

[0169] Then, initialize (i.e., the current iteration number t is 0) the first coefficient vector A, the second coefficient vector C, the first variable p that controls the way of updating the position, the second variable h that controls the range of the coefficient vector A, and the random number l in the control parameters.

[0170] The cleavage depth optimization system first updates the second variable h within the range of the control coefficient vector A:

[0171]

[0172] Then, based on the updated second variable h, the first coefficient vector A is updated, and the second coefficient vector C, the first variable p controlling the update position, and the random number l are continued to be updated:

[0173] A = 2h·rand-h,

[0174] C = 2·rand,

[0175] p = rand(0, 1),

[0176]

[0177] Subsequently, based on the first variable p and the first coefficient vector A in the updated control parameters, the cleavage depth optimization system can determine the method of updating the position and determine the first position vector of each individual whale based on the determined method of updating the position.

[0178] Specifically, when the first variable p is less than 0.5, the first coefficient vector A is evaluated. When the first coefficient vector A is less than 1, the fragmentation depth optimization system can determine the first position vector X according to the shrinking encirclement mechanism with a convergent adaptive weighting strategy. local (t+1).

[0179] The update formula for the shrinking encirclement mechanism with convergent adaptive weighting strategy is as follows:

[0180] X local (t+1)=r×X best (t)-A·B,

[0181] The formula for calculating the weight r is as follows:

[0182]

[0183] The formula for calculating B is:

[0184] B = |C·X best (t)-X local (t)|,

[0185] Among them, X local (t) is the position vector X(t) of the whale individual selected to update its position in the current population.

[0186] When the first variable p is less than 0.5 and the first coefficient vector A is greater than or equal to 1, the cleavage depth optimization system can determine the first position vector X according to the stochastic update mechanism with a convergent adaptive weighting strategy. local (t+1).

[0187] The update formula for the stochastic update mechanism with convergent adaptive weighting strategy is as follows:

[0188] X local (t+1)=r×X best (t)-A·B,

[0189] The formula for calculating the weight r is the same as that for the shrinking encirclement mechanism with convergent adaptive weighting strategy:

[0190]

[0191] The formula for calculating B is:

[0192] B = |C·X rand (t)-X local (t)|,

[0193] Among them, X rand (t) is the position vector of a randomly selected whale individual in the current population.

[0194] Furthermore, when the first variable p is greater than or equal to 0.5, the cleavage depth optimization system can determine the first position vector X according to the spiral update position mechanism. local (t+1).

[0195] The spiral update position mechanism first calculates the position of the whale located at (X, Y) and the position of the whale located at (X). * Y * The distance between the whale and its prey is calculated, and then a spiral equation is created between the positions of the whale and its prey to simulate the whale's spiral movement.

[0196] The equation for this spiral is as follows:

[0197] X local (t+1)=X best (t)+B p ·e bl cos(2πl),

[0198] Among them, B p The calculation formula is as follows:

[0199] B p =|X best (t)-X local (t)|.

[0200] Thus, based on the control parameters, the first position vector of each individual whale in the whale population is updated to complete the update of the first position vector of all individual whales in the whale population.

[0201] Furthermore, the dimensions of the determined first position vector of the individual whale are within the upper and lower bounds of their respective dimensions. When a dimension of the first position vector violates the upper and lower bounds of its corresponding dimension, the value of that dimension needs to be updated to ensure that each dimension remains within the upper and lower bounds. Specifically, the values ​​of the dimensions can be updated using the following formula:

[0202]

[0203]

[0204] Where, x j，i (t) represents the j-th dimension of the i-th whale individual in the whale population during the t-th iteration, x j，i `new` represents the j-th dimension of the position vector to be updated for the i-th whale individual. Here, this position vector is the first position vector X. local (t+1).

[0205] Preferably, to ensure that the updated position vector values ​​are within a discrete set of feasible integers, the following encoding conversion function is used to convert the real number vector into an integer vector:

[0206]

[0207] Where, N j For the j-th cracking furnace at the upper and lower limits [m] j n j The number of feasible integer sets within [m, n ∈ Z], where w is [1, N]. j -2] integer, y j，i The value of the j-th dimension of the i-th individual whale is obtained by converting the real number into an integer using an encoding conversion function.

[0208] After converting the first position vectors of all whale individuals within the whale population using the aforementioned encoding conversion function, their fitness function values ​​are calculated.

[0209] Subsequently, the split depth optimization system uses reverse learning, random candidate selection, and random assignment methods to determine the second, third, and fourth position vectors of each whale individual and their corresponding fitness function values.

[0210] Backward learning is used for each individual whale in the whale population to form a second position vector X for each individual whale. iop :

[0211] X iop=Lb+Ub-X i ,

[0212] Where [Lb, Ub] represents the search range of the solution space. Then, the second position vector X of all individual whales... iop Form a new reverse solution set X op .

[0213] Preferably, the cleavage depth optimization system can optimize the resulting inverse solution set X. op The second position vector X of each individual whale in the data iop After conversion using the above encoding conversion function, calculate its fitness function value.

[0214] Similarly, a random candidate method is used for each individual whale in the whale population. When the position vector of an individual whale satisfies the following probability condition, its position is updated to the position of the current best individual whale, i.e., the third position vector of that individual whale, forming a new solution set X. rs :

[0215]

[0216] The rift depth optimization system can also use a random assignment method to redistribute the position of each individual whale in the whale population. According to the following formula, the rift depth optimization system randomly redistributes the position of each individual whale within a radius k region to form a new fourth position vector X. ird :

[0217] X ird =X i +k×rand×sgin(rand-0.5),

[0218]

[0219] Then, the pyrolysis depth optimization system uses the above-mentioned encoding conversion function to transform the fourth position vector X. ird After converting to an integer vector, calculate its fitness function value.

[0220] Therefore, after each whale individual has determined its first, second, third, and fourth position vectors, the first, second, third, and fourth position vectors of all determined whale individuals are sorted in ascending order according to the fitness function value. The whale individuals with the first population_size position vectors are selected as the whale individuals of the next generation whale population, and the position vector of the whale individual with the highest fitness function value is updated as the best whale individual.

[0221] Furthermore, when updating the best whale individual, if a whale individual with a better position vector than the current best whale individual exists, the best whale individual and its corresponding best fitness function value are updated, and the number of times the best whale individual remains unchanged (unchange_iters) is set to 0. Conversely, if no whale individual with a better position vector than the current best whale individual exists, the best whale individual and its corresponding best fitness function value are not updated, and the number of times the best whale individual remains unchanged (unchange_iters) is incremented by 1.

[0222] Then, increment the iteration count (iters) by 1 and start the next iteration. This continues until the deep optimization model meets the convergence condition (in this example, convergence is considered met when the number of unchanged iterations (unchange_iters) reaches 50) or reaches the maximum population iteration count (Max_iters).

[0223] Therefore, the cleavage depth optimization system yields a set of values ​​that satisfy the constraints: This refers to the pyrolysis depth value of the pyrolysis furnace group determined by the deep optimization model based on the objective function within the constraint conditions of the optimization variables.

[0224] Please refer to Figure 5 and Figure 6 , Figure 5 and Figure 6 The diagram shows the effect of the method for optimizing the cracking depth for ethylene cracking furnace groups.

[0225] like Figure 5 , Figure 6 As shown, after the cracking depth optimization system was put into operation, two optimization indicators were successively determined. The cracking depth optimization system first selected maximizing the diene yield as the optimization objective function to optimize the cracking depth value of the cracking furnace group. Figure 5 As shown in the figure, the right ordinate represents the COT value, and the left ordinate represents the cracking depth (SEV) value. The figure shows that when maximizing the yield of both rare earth elements is selected as the optimization objective function, line 501 decreases, indicating a decrease in the cracking depth; while line 502 increases, indicating an increase in the COT temperature. Based on these changes in operating conditions—a decrease in cracking depth and an increase in COT temperature—the yield of both rare earth elements increases. Therefore, the cracking depth optimization system selects maximizing the propylene yield as the optimization objective function to optimize the cracking depth value of the cracking furnace group. Figure 6 As shown, when maximizing propylene yield is selected as the objective function, line 601 increases, indicating an increase in the cracking depth value; line 602 decreases, indicating a decrease in the COT temperature. Thus, increasing the cracking depth value and decreasing the COT temperature leads to an increase in propylene yield. These results demonstrate that the cracking depth optimization method for ethylene cracking furnace groups provided by this invention can effectively improve the operational efficiency of the cracking furnaces.

[0226] In summary, the cracking depth optimization technology for ethylene cracking furnace groups provided by the present invention has a faster convergence speed and better accuracy. It can determine the optimal cracking depth in real time based on the current real-time operation of the cracking furnace, thereby significantly improving the product yield while meeting overall constraints.

[0227] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0228] Those skilled in the art will understand that information, signals, and data can be represented using any of a variety of different techniques and arts. For example, the data, instructions, commands, information, signals, bits, symbols, and chips described throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0229] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0230] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or performed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but in alternatives, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0231] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0232] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or through a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

[0233] The prior description of this disclosure is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not intended to be limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing the cracking depth of an ethylene cracking furnace group, characterized in that, Including the following steps: Multidimensional optimization variables are determined based on the operating variables of each cracking furnace. The constraints of the optimization variables are determined according to the upper and lower limits of the optimization variables. The optimization objective function is determined based on the minimum constraint value of ethylene production of the cracking furnace group. as well as The multidimensional optimization variables are input into the deep optimization model, which determines the optimized pyrolysis depth value of the pyrolysis furnace group within the constraint conditions of the optimization variables according to the optimization objective function. The deep optimization model is constructed by the whale optimization algorithm with enhanced exploration mechanism. The step of determining the optimized pyrolysis depth value of the pyrolysis furnace group includes: within the constraints, using the enhanced exploration mechanism whale optimization algorithm, determining the optimized pyrolysis depth value of the pyrolysis furnace group by iteratively calculating and adjusting the multidimensional optimization variables; Within the constraints, the step of determining the optimized pyrolysis depth value of the pyrolysis furnace group by iteratively calculating and adjusting the multidimensional optimization variables using the enhanced exploration mechanism whale optimization algorithm includes: S1: Initialize control parameters and a whale population, and determine the optimal individual whale based on a fitness function, wherein the whale population includes... Individual whale; S2: Update the control parameters, and determine the first position vector and its fitness function value for each individual whale based on the control parameters, wherein the dimension of the first position vector is within the upper and lower limits of the dimension; S3: Use reverse learning to determine the second position vector and its fitness function value for each individual whale, wherein the dimension of the second position vector is within the upper and lower limits of the dimension; S4: Use a random candidate method to determine the third position vector and its fitness function value for each individual whale, wherein the dimension of the third position vector is within the upper and lower limits of the dimension; S5: Use a random assignment method to determine the fourth position vector and its fitness function value for each individual whale, wherein the dimension of the fourth position vector is within the upper and lower limits of the dimension; S6: Based on the fitness function value, sort the first position vector, second position vector, third position vector, and fourth position vector of all determined whale individuals in ascending order, and select the first... Each position vector represents the position of an individual whale in the next generation whale population, and the position vector of the whale with the highest fitness function value is updated as the optimal whale individual; and S7: Repeat steps S2 to S6 until the number of iterations reaches the maximum number of population iterations or the convergence condition of the deep optimization model is met.

2. The cleavage depth optimization method as described in claim 1, characterized in that, The control parameters include the maximum number of population iterations, population size, target prey location, current whale location, current iteration number, first coefficient vector, second coefficient vector, first variable controlling the update position method, second variable controlling the coefficient vector, logarithmic spiral shape constant, and random number.

3. The cleavage depth optimization method as described in claim 1, characterized in that, The step of determining the first position vector of each individual whale based on the control parameters includes: In response to the first variable of the control update position method being less than 0.5 and the first coefficient vector being less than 1, the first position vector is determined according to the shrinking encirclement mechanism with convergent adaptive weighting strategy; In response to the first variable being less than 0.5 and the first coefficient vector being greater than or equal to 1, the first position vector is determined according to a random update mechanism with a convergent adaptive weighting strategy; and In response to the first variable being greater than or equal to 0.5, the first position vector is determined according to the spiral position update mechanism.

4. The cleavage depth optimization method as described in claim 1, characterized in that, Steps S2 to S5 include: When the dimension of the first position vector and / or the second position vector and / or the third position vector and / or the fourth position vector violates the upper and lower bound constraints of the dimension, the value of the dimension is updated.

5. The cleavage depth optimization method as described in claim 4, characterized in that, Steps S2 to S5 also include: According to the encoding conversion function, the first position vector and / or the second position vector and / or the third position vector and / or the fourth position vector are converted into integer vectors.

6. The cleavage depth optimization method as described in claim 1, characterized in that, The optimization objective function includes maximizing ethylene yield and / or maximizing propylene yield and / or maximizing diene yield.

7. The method for optimizing cleavage depth as described in claim 1, characterized in that, The step of determining the constraint conditions of the optimization variable based on the upper and lower bound constraints of the optimization variable includes: The upper and lower limits of the optimization variables are discretized to determine the constraints of the optimization variables.

8. A cracking depth optimization system for ethylene cracking furnace groups, characterized in that, include: Memory, on which computer instructions are stored; as well as A processor, connected to the memory, is configured to execute computer instructions stored in the memory to implement the cracking depth optimization method for an ethylene cracking furnace group as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, the method for optimizing the cracking depth of an ethylene cracking furnace group as described in any one of claims 1 to 7 is implemented.

Images