Mathematical model-based catalyst process parameter optimization method

Abstract

The application relates to the technical field of catalysts and discloses a catalyst process parameter optimization method based on a mathematical model, which comprises the following steps: obtaining model data and operation process parameters of a catalyst; establishing a mathematical model of the catalyst based on the model data; calibrating the mathematical model based on the operation process parameters to obtain a calibrated model; obtaining at least two groups of operation process parameters of the catalyst; simulating particle size distribution of the catalyst based on the calibrated model to obtain particle size distribution data corresponding to each group of operation process parameters; screening optimal particle size distribution data and optimal process parameters corresponding to the optimal particle size distribution data from all the particle size distribution data; and updating the operation process parameters to the optimal process parameters. The method provided by the embodiment of the application optimizes the operation process parameters to the optimal process parameters, so that the produced catalyst has optimal particle size distribution.

Description

Technical Field

[0001] This invention relates to the field of catalyst technology, and in particular to a method for optimizing catalyst process parameters based on mathematical models. Background Technology

[0002] Catalytic cracking catalysts play a crucial role in the petroleum refining process. Under high temperature and the action of catalytic cracking catalysts, heavy petroleum can be distilled into light oil products for use in various industrial production activities.

[0003] The particle size distribution of catalytic cracking catalysts is an important indicator for evaluating their quality. Therefore, in the production process of catalytic cracking catalysts, it is necessary to strictly control the particle size distribution of the produced catalysts. If the particle size distribution of the catalytic cracking catalysts is uneven, it will directly affect the catalytic efficiency of the catalysts, thereby reducing the yield of light oil products and affecting economic benefits. Summary of the Invention

[0004] This invention provides a method for optimizing catalyst process parameters based on a mathematical model. By optimizing the operating process parameters to the optimal process parameters, the catalyst produced has the optimal particle size distribution.

[0005] In a first aspect, embodiments of the present invention provide a method for optimizing catalyst process parameters based on a mathematical model. The method includes: acquiring model data and operating process parameters of the catalyst; establishing a mathematical model of the catalyst based on the model data; calibrating the mathematical model based on the operating process parameters to obtain a calibrated model; acquiring at least two sets of operating process parameters of the catalyst; simulating the particle size distribution of the catalyst based on the calibrated model to obtain particle size distribution data corresponding to each set of operating process parameters; selecting the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data, and updating the operating process parameters to the optimal process parameters.

[0006] The catalyst process parameter optimization method based on mathematical models provided in this invention determines the particle size distribution data corresponding to each set of operating process parameters by calibrating the model, and selects the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data. The operating process parameters are then updated to the optimal process parameters to optimize the catalyst process parameters, so that the final operating process parameters are the optimal process parameters and the corresponding catalyst produced has the optimal particle size distribution, thereby ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst.

[0007] Optionally, the steps for establishing a mathematical model of the catalyst based on model data include: establishing a model framework; determining the number of input layer nodes, hidden layer nodes, output layer nodes, and output function of the model framework, wherein the output function is:

[0008] v = Σnwi×xi + b;

[0009] y = purelin(v);

[0010] q = sgn(y);

[0011] Where n is the number of iterations, wi is the weight, b is the bias value, xi is the input vector, v is the output neuron, y is the net input value of the output neuron, and q is the final output value; the model data is input into the model framework to obtain the initial model; the initial model is iteratively optimized to obtain the mathematical model.

[0012] Optionally, the steps of inputting model data into the model framework and establishing the initial model include: obtaining multiple initial constants based on the simulated annealing algorithm, model data, and output function; and inputting the multiple initial constants into the model framework to establish the initial model.

[0013] Optionally, the steps for obtaining multiple initial constants based on the simulated annealing algorithm and model data include: obtaining the following combined expression based on the simulated annealing algorithm, model data, and output function:

[0014] w(n)=[b(n),w1(n),w2(n),..,wN(n)]";

[0015] x(n)=[1,x(n),x2(n),…,xm(n)]F;

[0016] e(n)=d(n)-y(n)=d(n)-x'(n)w(n);

[0017] w(n+1)=w(n)+hx'(n)e(n);

[0018] Where n is the iteration number, b(n) is the bias value for the corresponding iteration number, w(n) is the combined vector of the bias value for the corresponding iteration number and all weights, x(n) is the input sample vector, d(n) is the expected output value, y(n) is the actual output value, h is the learning rate parameter, T is the transpose of the corresponding vector, and e(n) is the error value of d(n) and y(n) for the corresponding iteration number; multiple initial constants are obtained based on combinatorial calculation.

[0019] Optionally, the steps of iteratively optimizing the initial model to obtain the mathematical model include: obtaining the initial output value of the initial model; determining whether the initial model satisfies the algorithm convergence principle based on the tabu search algorithm; if not, using the initial output value as a candidate output value; determining whether the candidate output value satisfies the tabu principle; if so, replacing the candidate output value with the current output value that satisfies the tabu search criterion and updating the initial model; if not, determining the tabu attribute of the candidate output value, replacing the candidate output value with the optimal output value corresponding to the non-tabu object, and updating the initial model; and restarting the steps of determining whether the updated initial model satisfies the algorithm convergence principle based on the updated initial model, until the output value of the initial model satisfies the algorithm convergence principle, thus obtaining the mathematical model.

[0020] Optionally, the step of calibrating the mathematical model based on the operating process parameters to obtain the calibrated model includes: obtaining the actual particle size distribution data of the catalyst corresponding to the operating process parameters; obtaining the predicted particle size distribution data calculated by the mathematical model based on the operating process parameters; comparing whether the error value between the actual particle size distribution data and the predicted particle size distribution data exceeds a preset error value; if it exceeds the preset error value, then calibrating the mathematical model to obtain the calibrated model.

[0021] Optionally, if the error exceeds a preset error value, the mathematical model is calibrated to obtain the calibrated model. The steps include: obtaining the baseline parameters of the operating process parameters; and adjusting the size of one, two, or more of the operating process parameters based on the baseline parameters so that the error between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, thereby obtaining the calibrated model.

[0022] Optionally, the step of adjusting one, two, or more of the parameters of the operating process parameters based on the baseline parameters, so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than a preset error value, to obtain the calibrated model includes: obtaining a multinomial fitting formula; and adjusting one, two, or more of the parameters of the operating process parameters based on the multinomial fitting formula and the baseline parameters, so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than a preset error value, to obtain the calibrated model.

[0023] Optionally, the model data includes multiple operating process parameters and particle size distribution data corresponding to each operating process parameter. The operating process parameters include the number of spray guns, nozzle orifice value, spray pressure value, spray flow rate value, and colloidal solids content value.

[0024] In a second aspect, embodiments of the present invention provide a catalyst process parameter optimization device, comprising: a processor and a memory, wherein the memory stores instructions; the processor calls the instructions in the memory to cause the processor to execute the catalyst process parameter optimization method based on a mathematical model according to any of the foregoing embodiments of the first aspect of the present invention.

[0025] The processor of the catalyst process parameter optimization device provided in this embodiment of the invention executes the catalyst process parameter optimization method based on a mathematical model according to any of the foregoing embodiments of the first aspect of the invention by calling instructions in the memory. This enables the catalyst process parameter optimization device to determine the particle size distribution data corresponding to each set of operating process parameters through the calibrated model, and to select the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data. The operating process parameters are then updated to the optimal process parameters to optimize the catalyst process parameters, so that the final operating process parameters are the optimal process parameters and the corresponding produced catalyst has the optimal particle size distribution, thereby ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst.

[0026] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing instructions that, when executed by a processor, implement the catalyst process parameter optimization method based on a mathematical model according to any of the foregoing embodiments of the first aspect of the present invention.

[0027] The instructions stored in the computer-readable storage medium provided in this embodiment of the invention can be called by a processor and executed by the catalyst process parameter optimization method based on a mathematical model according to any of the foregoing embodiments of the first aspect of the invention. This method determines the particle size distribution data corresponding to each set of operating process parameters through a calibrated model, selects the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data, updates the operating process parameters to the optimal process parameters, thereby optimizing the catalyst process parameters so that the final obtained operating process parameters are the optimal process parameters and the corresponding produced catalyst has the optimal particle size distribution, thus ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0029] Figure 1This is a flowchart of an embodiment of the catalyst process parameter optimization method based on a mathematical model according to the present invention;

[0030] Figure 2 This is a flowchart of step S120 in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0031] Figure 3 This is a flowchart of step S124 in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0032] Figure 4 This is a flowchart of step S130 in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0033] Figure 5 This is a catalyst process flow diagram in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0034] Figure 6 This is an electron micrograph comparing the catalyst under different operating process parameters in one embodiment of the catalyst process parameter optimization method based on mathematical model of the present invention.

[0035] Figure 7 This is a schematic diagram showing the predicted and actual values ​​of the calibrated model in one embodiment of the catalyst process parameter optimization method based on a mathematical model according to the present invention.

[0036] Figure 8 This is a schematic diagram illustrating the error between the predicted and actual values ​​of the calibrated model in one embodiment of the catalyst process parameter optimization method based on a mathematical model according to the present invention.

[0037] Figure 9 This is a schematic diagram of simulation results under different solid contents and spray pressures in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention.

[0038] Figure 10 This is a schematic diagram of the tabu search algorithm in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0039] Figure 11 This is a schematic diagram of the initial model establishment process in one embodiment of the catalyst process parameter optimization method based on mathematical models of the present invention;

[0040] Figure 12 This is a structural block diagram of one embodiment of the catalyst process parameter optimization equipment of the present invention.

[0041] Explanation of icon numbers:

[0042] 110 - Air heater; 120 - Spray drying tower; 130 - Cyclone separator; 140 - Recycled fan; 150 - Exhaust fan;

[0043] 200-catalyst;

[0044] 301 - Processor; 302 - Memory; 303 - Communication interface; 304 - Bus. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0046] It should be noted that all directional indications in the embodiments of the present invention, such as up, down, left, right, front, back, etc., are only used to explain the relative positional relationship and movement of the components in a specific posture as shown in the attached figure. If the specific posture changes, the directional indication will also change accordingly.

[0047] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0048] For ease of understanding, the catalyst process parameter optimization method based on a mathematical model according to embodiments of the present invention will be described below, such as... Figure 1 As shown, the present invention proposes a method for optimizing catalyst process parameters based on a mathematical model, including steps S110 to S160.

[0049] In step S110, the model data and operating process parameters of the catalyst are obtained.

[0050] In this embodiment, the model data includes multiple operating process parameters and granularity distribution data corresponding to each operating process parameter.

[0051] The operating process parameters include the number of spray guns, nozzle orifice diameter, spray pressure, spray flow rate, and colloidal solids content. The spray gun model also affects the particle size distribution of the catalyst. When the spray gun model remains constant during catalyst production, the particle size distribution of the catalyst can be adjusted by changing the number of spray guns and nozzle orifice diameter. When the spray gun model changes, the parameters of the number of spray guns and nozzle orifice diameter need to be readjusted to adjust the particle size distribution of the catalyst.

[0052] In step S120, a mathematical model of the catalyst is established based on the model data.

[0053] like Figure 2 As shown, in some optional embodiments, step S120 includes steps S121 to S124.

[0054] In step S121, the model framework is established.

[0055] In step S122, the number of input layer nodes, hidden layer nodes, output layer nodes, and output function of the model framework are determined. The output function is:

[0056] v = Σnwi×xi + b;

[0057] y = purelin(v);

[0058] q = sgn(y);

[0059] Where n is the number of iterations, wi is the weight, b is the bias value, xi is the input vector, v is the output neuron, y is the net input value of the output neuron, and q is the final output value.

[0060] In step S123, the model data is input into the model framework to obtain the initial model.

[0061] Further, step S123 includes steps S1231 to S1232.

[0062] In step S1231, multiple initial constants are obtained based on the simulated annealing algorithm, model data, and output function.

[0063] Based on the simulated annealing algorithm, model data, and output function, the following combined formula is obtained:

[0064] w(n)=[b(n),wl(n),w2(n),…,wN(n)";

[0065] x(n)=[1,x(n),x(n),...,xm(n)]T;

[0066] e(n)=d(n)-y(n)=d(n)-x'(n)w(n);

[0067] w(n+1)=w(n)+hx(n)e(n);

[0068] Where n is the iteration number, b(n) is the bias value for the corresponding iteration number, w(n) is the combined vector of the bias value and all weights for the corresponding iteration number, x(n) is the input sample vector, d(n) is the expected output value, y(n) is the actual output value, h is the learning rate parameter, T is the transpose of the corresponding vector, and e(n) is the error value of d(n) and y(n) for the corresponding iteration number. After obtaining this combination formula, several initial constants are calculated based on it.

[0069] In step S1232, multiple initial constants are input into the model framework to establish the initial model.

[0070] like Figure 11 As shown, in this embodiment, the mathematical model is a neural network model. Before establishing the mathematical model, it is necessary to determine its architecture, including the number of nodes in the input layer, the number of nodes in the hidden layer, and the number of nodes in the output layer. Then, a neural network object is created using a function, setting the number of nodes in each layer and the activation function type. In this embodiment, the above-mentioned combination formula is obtained through simulated annealing algorithm, model data, and output function to establish the initial model.

[0071] In a neural network model with multiple input neurons, nonlinear inputs can be added between each pair of neurons, or this can be understood as establishing a mathematical relationship between two neurons as input. In this embodiment, an initial model is established through the above-mentioned combination formula. During the initial model establishment process, model variables and parameters are first defined, and based on the simulated annealing algorithm, the following formula is obtained:

[0072] w(n)=[b(n),w1(n),w2(1),...,wN(0)] n ;

[0073] The training samples are determined as follows:

[0074] x(n) = [1, x1(n), x2(n), ..., x m (n)] T ;

[0075] Then, initialize the vector w(n) by assigning it a small random value, at which point n = 0;

[0076] Next, input the model data, according to the formula:

[0077] e(n) = d(n) - y(n) = d(n) - x t (n)w(n);

[0078] Calculate the actual output value and error value. Calculate the output value based on the given expected value. Then adjust the weight vector. Calculate the size of w(n+1) based on the error value calculated in the previous step. Then determine whether the algorithm has converged. If the convergence condition is met, the initial model is obtained.

[0079] In step S124, the initial model is iteratively optimized to obtain a mathematical model.

[0080] like Figure 3 and Figure 10 As shown, step S124 further includes steps S1241 to S1244.

[0081] In step S1241, the initial output values ​​of the initial model are obtained.

[0082] In step S1242, based on the tabu search algorithm, it is determined whether the initial model satisfies the algorithm convergence principle. If it does not, the initial output value is used as a candidate output value.

[0083] In step S1243, it is determined whether the candidate output value satisfies the taboo principle. If it does, the candidate output value is replaced with the current output value that satisfies the taboo search criterion and the initial model is updated. If it does not, the taboo attribute of the candidate output value is determined, the candidate output value is replaced with the optimal output value corresponding to the non-taboo object and the initial model is updated.

[0084] In step S1244, based on the updated initial model, the step of judging whether the updated initial model satisfies the algorithm convergence principle is restarted until the output value of the initial model satisfies the algorithm convergence principle, and the mathematical model is obtained.

[0085] In this embodiment, the initial model is iteratively optimized based on the tabu search algorithm to obtain a mathematical model. The specific implementation steps are as follows:

[0086] Step 1: Set the initial output value X0 and record the current optimal output value Xbest = X0, T = N(Xbest), where N(Xbest) represents the neighborhood of Xbest.

[0087] Step 2: When best = empty set, or when other stopping criteria are met, output the calculation result and stop the calculation; otherwise, continue the calculation according to steps S1241 to S1244.

[0088] Step 3: Preset a set S and obtain the current output value Xnow of the set S. If F(Xnow) < F(Xbest), then Xnow = Xbest, T = N(Xbest), and the calculation is stopped to obtain the optimal output value; otherwise, T = T - S, and according to steps S1241 to step S1244, continue the search until the optimal output value is obtained. Among them, the initial output value X0 can be randomly generated.

[0089] In step S130, based on the operating process parameters, calibrate the mathematical model to obtain the calibrated model.

[0090] As Figure 4 shown, in some optional embodiments, step S130 includes steps S131 to step S133.

[0091] In step S131, obtain the actual particle size distribution data of the catalyst corresponding to the operating process parameters.

[0092] In step S132, based on the operating process parameters, obtain the predicted particle size distribution data calculated by the mathematical model.

[0093] In step S133, compare whether the error value between the actual particle size distribution data and the predicted particle size distribution data exceeds the preset error value. If it exceeds the preset error value, calibrate the mathematical model to obtain the calibrated model.

[0094] Further, step S133 includes steps S1331 to step S1332.

[0095] In step S1331, obtain the reference parameters of the operating process parameters.

[0096] In step S1332, based on the reference parameters, adjust the magnitude of one, two or more of all the parameters of the operating process parameters, so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, and obtain the calibrated model.

[0097] Further, when adjusting the operating process parameters, first obtain a multi-term fitting formula. Among them, the multi-term fitting formula is: Formula: y = p{0}x n +p{1}x n-1 +p{2}x n-2 +p{2}x n-3 +…+p{n};

[0098] Among them, x is the independent variable, y is the actual function value, p is the coefficient of the polynomial fitting formula, and n is the number of parameters.

[0099] After obtaining multiple fitting formulas, based on the multiple fitting formulas and benchmark parameters, the magnitude of one, two, or more of the parameters of the operation process is adjusted so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, thus obtaining the calibrated model.

[0100] After obtaining the mathematical model, it needs to be calibrated to ensure the accuracy of its predictions. The calibration process is as follows:

[0101] In this embodiment, after obtaining the model data and operating process parameters of the catalyst, the particle size distribution of the catalyst can be predicted using a mathematical model, and the predicted particle size distribution result can be obtained. By comparing the error value between the predicted particle size distribution result obtained by the mathematical model and the actual particle size distribution result, it can be determined whether the mathematical model needs to be calibrated. The specific calibration steps are as follows.

[0102] In step S140, at least two sets of operating process parameters for the catalyst are obtained.

[0103] In this embodiment, two, three, four or more sets of operating process parameters for the catalyst can be obtained to calibrate the mathematical model and improve its accuracy.

[0104] In step S150, based on the calibrated model, the particle size distribution of the catalyst is simulated to obtain particle size distribution data corresponding to each set of operating process parameters.

[0105] In this embodiment, the specific calibration steps and the steps for simulating the particle size distribution of the catalyst based on the calibrated model are as follows:

[0106] like Figures 5 to 11 As shown in the embodiments of this application, the operating process parameters of the catalytic cracking catalyst are optimized by the method of the above embodiments of this application. In the catalyst production process, natural gas and air react in an air heater 110 to obtain a catalyst slurry. The catalyst slurry reacts in a spray drying tower 120 to obtain catalyst 200. The remaining product is separated into fine powder by a cyclone separator 130. The separated gas is separated by a reuse fan 140 and an induced draft fan 150 to generate reuse air and discharge the waste gas.

[0107] First, the particle size of the catalyst was calculated using a mathematical model. The predicted particle size distribution of the catalyst under different solid contents was then compared with the actual distribution. As shown in Tables 1 and 2, Table 1 shows the actual particle size distribution of the catalyst under different solid contents, and Table 2 shows the predicted particle size distribution of the catalyst under different solid contents.

[0108]

[0109] Table 1

[0110]

[0111] Table 2

[0112] According to Tables 1 and 2, there is an error between the predicted distribution of catalyst particle size under different solid contents and the actual distribution of catalyst particle size under different solid contents, and the mathematical model needs to be calibrated.

[0113] In this embodiment, the baseline parameters of the operating process are obtained, and based on these baseline parameters, one, two, or more of the operating process parameters are adjusted to adjust the baseline parameters. For example, in the operating process parameters of the catalyst, if the spray pressure adjustment range is 10MPa to 13MPa, then the baseline parameter for the spray pressure can be set to 12MPa; if the nozzle orifice diameter adjustment range is 2.4μm to 3.2μm, then the baseline parameter for the nozzle orifice diameter can be set to 2.8μm. Similarly, the corresponding baseline parameters can also be adjusted according to the adjustment range of the number of spray guns, the spray flow rate, and the colloidal solids content. Each time the baseline parameters are adjusted, a mathematical model is used for simulation and prediction until the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than a preset error value, thus obtaining a calibrated model.

[0114] In this embodiment of the application, the process of adjusting the baseline parameters and performing simulation prediction through a mathematical model is as follows:

[0115] Table 3 shows the baseline parameters for the operating process of different groups of catalyst Cat1. Table 4 shows the actual particle size distribution data of catalyst Cat1 under the corresponding baseline parameters. Table 5 shows the predicted particle size distribution data of catalyst Cat1 under the corresponding baseline parameters. In Tables 3, 4, and 5, the colloidal solid content is 33% to 34%, and the colloidal viscosity is 100,000 cp to 160,000 cp.

[0116]

[0117] Table 3

[0118]

[0119] Table 4

[0120]

[0121] Table 5

[0122] As shown in the table above, using seven spray guns, increasing the spray pressure while keeping the spray flow rate constant improves the particle size distribution in the 0-40µm and 0-149µm ranges, but also increases the amount of fine powder classification. Appropriately reducing the spray flow rate results in a more reasonable particle size distribution and a decrease in fine powder classification, thus improving catalyst quality and yield, and increasing economic efficiency. The simulation accuracy of the calibrated model is within 5%.

[0123] In Tables 6, 7 and 8, the colloidal solids content is 35% to 36% and the colloidal viscosity is 100,000 cp to 160,000 cp.

[0124] Table 6 shows the baseline parameters for the operating process of different groups of catalyst Cat2, Table 7 shows the actual particle size distribution data of catalyst Cat2 under the corresponding baseline parameters, and Table 8 shows the predicted particle size distribution data of catalyst Cat2 under the corresponding baseline parameters.

[0125]

[0126] Table 6

[0127]

[0128] Table 7

[0129]

[0130] Table 8

[0131] In Tables 6, 7 and 8, because the colloidal solids content of catalyst Cat2 is higher than that of catalyst Cat1, the spray flow rate of catalyst Cat2 is also smaller under the same spray pressure, and the content of catalyst particles in the 0-149 μm range is also lower.

[0132] By comparing actual and predicted particle size distribution data, the simulation accuracy of the calibrated model can be found to be within 5%.

[0133] As can be seen from Tables 6, 7 and 8, catalyst particles with higher colloidal solid content tend to have larger particle sizes. By calibrating the model, the corresponding baseline parameters can be adjusted to significantly reduce the amount of fine powder fractionation of the catalyst, thereby improving the catalyst yield.

[0134] In Tables 9, 10 and 11, the colloidal solids content is 35% to 36% and the colloidal viscosity is 100,000 cp to 150,000 cp.

[0135] Table 9 shows the baseline parameters for the operating process of different groups of catalyst Cat3, Table 10 shows the actual particle size distribution data of catalyst Cat3 under the corresponding baseline parameters, and Table 11 shows the predicted particle size distribution data of catalyst Cat3 under the corresponding baseline parameters.

[0136]

[0137] Table 9

[0138]

[0139] Table 10

[0140]

[0141] Table 11

[0142] In Tables 9, 10 and 11, a high level of catalyst yield can still be maintained with 8 spray guns, and the particle size distribution results in the range of 0-149 μm also meet the requirements.

[0143] By comparing actual and predicted particle size distribution data, the simulation accuracy of the calibrated model can be found to be within 5%.

[0144] In Tables 12, 13 and 14, the colloidal solids content is 35% to 36% and the colloidal viscosity is 150,000 cp to 190,000 cp.

[0145] Table 12 shows the baseline parameters for the operation process of different groups of catalyst Cat4, Table 13 shows the actual particle size distribution data of catalyst Cat4 under the corresponding baseline parameters, and Table 14 shows the predicted particle size distribution data of catalyst Cat4 under the corresponding baseline parameters.

[0146]

[0147] Table 12

[0148]

[0149] Table 13

[0150]

[0151] Table 14

[0152] In Tables 12, 13, and 14, catalyst Cat4 exhibits higher colloidal viscosity and a lower spray flow rate compared to catalyst Cat3. Under these operating conditions, it helps reduce the amount of fine powder classification while still meeting particle size distribution requirements. By comparing actual and predicted particle size distribution data, the simulation accuracy of the calibrated model is found to be within 5%.

[0153] In step S160, the optimal particle size distribution data and its corresponding optimal process parameters are selected from all particle size distribution data, and the operating process parameters are updated to the optimal process parameters.

[0154] In this embodiment, after calculating multiple sets of catalyst particle size distribution data corresponding to different operating process parameters through the calibrated model, the particle size distribution data with the smallest error value to the actual particle size distribution data of the catalyst corresponding to each set of operating process parameters is selected as the optimal particle size distribution data. The operating process parameters of the catalyst are then updated to the optimal process parameters corresponding to the optimal particle size distribution data, thereby optimizing the catalyst process parameters, improving the product quality of the catalyst, ensuring a reasonable particle size distribution of the catalyst, and improving economic efficiency.

[0155] The catalyst process parameter optimization method based on a mathematical model provided in this invention includes: acquiring model data and operating process parameters of the catalyst; establishing a mathematical model of the catalyst based on the model data; calibrating the mathematical model based on the operating process parameters to obtain a calibrated model; acquiring at least two sets of operating process parameters of the catalyst; simulating the particle size distribution of the catalyst based on the calibrated model to obtain particle size distribution data corresponding to each set of operating process parameters; selecting the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data, and updating the operating process parameters to the optimal process parameters.

[0156] The method provided in this invention can determine the particle size distribution data corresponding to each set of operating process parameters through a calibrated model, and select the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data. The operating process parameters are then updated to the optimal process parameters to optimize the catalyst process parameters, so that the final operating process parameters are the optimal process parameters and the catalyst produced has the optimal particle size distribution, thereby ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst.

[0157] In addition to the above method embodiments, the present invention also provides, for example, Figure 12 The catalyst process parameter optimization device shown includes a processor 301 and a memory 302, wherein the memory 302 stores instructions; the processor 301 calls the instructions in the memory 302 so that the processor 301 executes the catalyst process parameter optimization method based on mathematical model according to any of the foregoing embodiments of the present invention.

[0158] The catalyst process parameter optimization method based on a mathematical model provided in this invention includes: acquiring model data and operating process parameters of the catalyst; establishing a mathematical model of the catalyst based on the model data; calibrating the mathematical model based on the operating process parameters to obtain a calibrated model; acquiring at least two sets of operating process parameters of the catalyst; simulating the particle size distribution of the catalyst based on the calibrated model to obtain particle size distribution data corresponding to each set of operating process parameters; selecting the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data, and updating the operating process parameters to the optimal process parameters.

[0159] The catalyst process parameter optimization device provided in this embodiment of the invention, by implementing the above method, can determine the particle size distribution data corresponding to each set of operating process parameters through a calibrated model, and select the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data. The operating process parameters are then updated to the optimal process parameters to optimize the catalyst process parameters, so that the final operating process parameters are the optimal process parameters, and the catalyst produced has the optimal particle size distribution, thereby ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst.

[0160] Furthermore, the catalyst process parameter optimization device provided in this embodiment of the invention may also include a communication interface 303 and a bus 304, with the processor 301, memory 302 and communication interface 303 electrically connected via the bus 304.

[0161] The memory 302 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network. The bus 304 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 12 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0162] Processor 301 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 301 or by instructions in software form. Processor 301 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 302. The processor 301 reads the information from memory 302 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0163] This invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the catalyst process parameter optimization method based on the mathematical model described above.

[0164] The computer-readable storage medium provided in this embodiment of the invention stores data and computer-executable instructions for the above-described method for optimizing catalyst process parameters based on a mathematical model. The method includes: acquiring model data and operating process parameters of the catalyst; establishing a mathematical model of the catalyst based on the model data; calibrating the mathematical model based on the operating process parameters to obtain a calibrated model; acquiring at least two sets of operating process parameters of the catalyst; performing particle size distribution simulation on the catalyst based on the calibrated model to obtain particle size distribution data corresponding to each set of operating process parameters; selecting the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data, and updating the operating process parameters to the optimal process parameters.

[0165] The computer-readable storage medium provided in this embodiment of the invention, by implementing the above method, can determine the particle size distribution data corresponding to each set of operating process parameters based on the calibrated model, and select the optimal particle size distribution data and its corresponding optimal process parameters from all particle size distribution data. The operating process parameters are then updated to the optimal process parameters to optimize the catalyst process parameters, so that the final operating process parameters are the optimal process parameters and the corresponding produced catalyst has the optimal particle size distribution, thereby ensuring the particle size distribution quality of the produced catalyst and improving the catalytic efficiency of the catalyst.

[0166] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0168] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing catalyst process parameters based on a mathematical model, characterized in that, The method includes: Obtain model data and operating parameters for the catalyst; Based on the model data, a mathematical model of the catalyst is established; Based on the aforementioned operating process parameters, the mathematical model is calibrated to obtain the calibrated model. Obtain at least two sets of the operating process parameters for the catalyst; Based on the calibrated model, the particle size distribution of the catalyst is simulated to obtain particle size distribution data corresponding to each set of the operating process parameters; The optimal particle size distribution data and its corresponding optimal process parameters are obtained by filtering from all the particle size distribution data, and the operating process parameters are updated to the optimal process parameters.

2. The method for optimizing catalyst process parameters based on a mathematical model according to claim 1, characterized in that, The steps for establishing a mathematical model of the catalyst based on the model data include: Establish a model framework; The number of input layer nodes, hidden layer nodes, output layer nodes, and output function of the model framework are determined, wherein the output function is: v = Σnwi×xi + b; y = purelin(v); q = sgn(y); Where n is the number of iterations, wi is the weight, b is the bias value, xi is the input vector, v is the output neuron, y is the net input value of the output neuron, and q is the final output value; The model data is input into the model framework to obtain the initial model; The initial model is iteratively optimized to obtain the mathematical model.

3. The method for optimizing catalyst process parameters based on a mathematical model according to claim 2, characterized in that, The steps for inputting the model data into the model framework to establish the initial model include: Based on the simulated annealing algorithm, the model data, and the output function, multiple initial constants are obtained; The initial constants are input into the model framework to establish the initial model.

4. The method for optimizing catalyst process parameters based on a mathematical model according to claim 3, characterized in that, The step of obtaining multiple initial constants based on the simulated annealing algorithm and the model data includes: Based on the simulated annealing algorithm, the model data, and the output function, the following combined expression is obtained: w(n)=[b(n),w1(n),w2(n),...,wN(n)] n ; x(n)=[1,x1(n),x2(n),...,x m (n)] T 4 e(n)=d(n)-y(n)=d(n)-xt(n)w(n); w(n+1)=w(n)+hx t (n)e(n); Where n is the number of iterations, b(n) is the bias value for the corresponding number of iterations, w(n) is the combined vector of the bias value for the corresponding number of iterations and all weights, x(n) is the input sample vector, d(n) is the expected output value, y(n) is the actual output value, h is the learning rate parameter, T is the transpose of the corresponding vector, and e(n) is the error value of d(n) and y(n) for the corresponding number of iterations; Multiple initial constants are obtained based on the combined calculation.

5. The method for optimizing catalyst process parameters based on a mathematical model according to claim 2, characterized in that, The steps for iteratively optimizing the initial model to obtain the mathematical model include: Obtain the initial output value of the initial model; Based on the tabu search algorithm, it is determined whether the initial model satisfies the algorithm convergence principle. If it does not, the initial output value is used as a candidate output value. Determine whether the candidate output value satisfies the taboo principle. If it does, replace the candidate output value with the current output value that satisfies the taboo search criterion and update the initial model. If it does not, determine the taboo attribute of the candidate output value, replace the candidate output value with the optimal output value corresponding to the non-taboo object, and update the initial model. Based on the updated initial model, the step of determining whether the updated initial model satisfies the algorithm convergence principle is restarted until the output value of the initial model satisfies the algorithm convergence principle, thus obtaining the mathematical model.

6. The method for optimizing catalyst process parameters based on a mathematical model according to claim 1, characterized in that, The step of calibrating the mathematical model based on the operating process parameters to obtain the calibrated model includes: Obtain the actual particle size distribution data of the catalyst corresponding to the operating process parameters; Based on the aforementioned operating process parameters, the predicted granularity distribution data calculated by the mathematical model is obtained; Compare the error values ​​between the actual granularity distribution data and the predicted granularity distribution data to see if they exceed a preset error value. If they exceed the preset error value, then calibrate the mathematical model to obtain a calibrated model.

7. The method for optimizing catalyst process parameters based on a mathematical model according to claim 6, characterized in that, If the error exceeds a preset value, the mathematical model is calibrated to obtain the calibrated model. The steps include: Obtain the reference parameters for the operation process parameters; Based on the baseline parameters, the magnitude of one, two, or more of the parameters of the operation process parameters is adjusted so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, thereby obtaining the calibrated model.

8. The method for optimizing catalyst process parameters based on a mathematical model according to claim 7, characterized in that, The step of adjusting one, two, or more of the operating process parameters based on the benchmark parameters, such that the error between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, to obtain the calibrated model includes: Obtain the multinomial fitting formula; Based on the polynomial fitting formula and the benchmark parameters, the magnitude of one, two, or more of the parameters of the operation process parameters is adjusted so that the error value between the predicted particle size distribution data calculated by the mathematical model and the actual particle size distribution data is less than the preset error value, thereby obtaining the calibrated model.

9. The method for optimizing catalyst process parameters based on a mathematical model according to claim 1, characterized in that, The model data includes multiple operating process parameters and particle size distribution data corresponding to each operating process parameter. The operating process parameters include the number of spray guns, nozzle orifice value, spray pressure value, spray flow rate value, and colloidal solids content value.

10. A catalyst process parameter optimization device, characterized in that, The catalyst process parameter optimization device includes a processor and a memory, wherein the memory stores instructions; The processor invokes the instructions in the memory to cause the catalyst process parameter optimization device to implement the catalyst process parameter optimization method based on a mathematical model as described in any one of claims 1 to 9.

11. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the catalyst process parameter optimization method based on a mathematical model as described in any one of claims 1 to 9.

Images