An optimized control method and system for wet blank cutting applied to denitration catalysts

Abstract

The present invention relates to an optimized control method and system for wet blank cutting of denitration catalysts. The method includes: M1. On the production line for wet blank cutting of denitration catalysts, based on a solid flowmeter, the flow data information of the wet blanks of denitration catalysts is obtained in real time; based on a speed sensor, the speed data information of the conveyor belt is obtained in real time; and based on a laser counting sensor, the cutting frequency data information of the wet blank cutting knife is obtained in real time. M2. Based on the flow data information of the wet blanks of denitration catalysts, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a random forest regression model for wet blank cutting of denitration catalysts is constructed to control the flow of the wet blanks of denitration catalysts. The present invention can not only accurately control and cut the length of the catalyst, but also has low requirements for the levelness between the guide rollers and does not require manual adjustment, thus improving the production efficiency of the catalyst.

Description

Technical Field

[0001] The present invention relates to the technical field of wet blank cutting of denitration catalysts, and in particular to an optimized control method and system for wet blank cutting of denitration catalysts. Background Art

[0002] During the production process of catalysts, generally, guide rollers, belt conveyors, and cutting devices are arranged at the outlet of the SCR catalyst extruder. The existing wet blank cutting movement includes an outlet guide roller and two batch conveying operation platforms. A set of cutting encoders is configured at the outlet of the extruder. First driving devices and second driving devices are respectively arranged on the two belt conveying operation platforms. The first driving device includes a first driving belt, a first belt pulley, and a servo motor. The second driving device includes a second driving belt, a second belt pulley, and a servo motor. There is a guide roller between the encoder and the first driving belt. A cutting knife is arranged on one side of the guide roller, and the blade of the cutting knife is arranged in front of the first driving belt. During the process of the catalyst moving forward on the guide roller, the length is counted by the PIC through the encoder, and the catalyst is cut into the required length by the cutting knife. A manipulator is arranged on one side of the second driving belt, and the arm of the manipulator is located above the second driving belt. After the cut catalyst reaches the position where the manipulator is located, the cut catalyst is clamped away by the manipulator. Generally, this kind of driving device judges the length of the catalyst by the encoder at the extrusion outlet, and the length of the catalyst cannot be accurately controlled. The requirement for the levelness between the guide rollers is also high, and there are easy cutting errors, which require workers to adjust at any time, resulting in low efficiency and affecting the normal production of the catalyst. Summary of the Invention

[0003] In view of the above problems, the present invention provides an optimized control method and system for wet blank cutting of denitration catalysts, which can not only accurately control and cut the length of the catalyst, but also has low requirements for the levelness between the guide rollers, without manual adjustment, and improves the production efficiency of the catalyst.

[0004] In order to achieve the above object and other related objects, the technical solutions provided by the present invention are as follows:

[0005] An optimized control method for wet blank cutting of denitration catalysts, the method comprising:

[0006] M1. On the production line of wet blank cutting of denitration catalysts, based on a solid flowmeter, the flow data information of the wet blank of the denitration catalyst is obtained in real time, based on a speed sensor, the speed data information of the conveyor belt is obtained in real time, and based on a laser counting sensor, the cutting frequency data information of the wet blank cutting knife is obtained in real time;

[0007] M2. Based on the flow data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, construct a random forest regression model for the cutting of the wet blank of the denitration catalyst, predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the predicted flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife;

[0008] M3. Based on the predicted flow rate of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, use the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guiding mechanism to optimize the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the cutting knife;

[0009] M4. Based on the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the cutting knife, establish a feasibility evaluation function Q for the cutting of the wet blank of the denitration catalyst, evaluate the comprehensive operation data of the cutting of the wet blank of the denitration catalyst, and obtain the comprehensive evaluation data information of the cutting of the wet blank of the denitration catalyst.

[0010] Further, the method further includes:

[0011] M5. Based on the comprehensive evaluation data information of the cutting of the wet blank of the denitration catalyst, set a preset threshold. If the comprehensive evaluation of the cutting of the wet blank of the denitration catalyst is greater than the preset threshold, it operates normally. If the comprehensive evaluation of the cutting of the wet denitration blank is less than the preset threshold, it cannot operate normally, and repeat steps M3 - M4.

[0012] Further, in step M2, the constructing of the random forest regression model for the cutting of the wet blank of the denitration catalyst and predicting the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife includes:

[0013] M21. Based on the flow data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, establish a sample function G for the cutting of the wet blank of the denitration catalyst,

[0014] ,

[0015] Among them, x1 is the flow data information of the wet blank of the denitration catalyst, x2 is the speed data information of the conveyor belt, x3 is the cutting frequency data information of the wet blank cutting knife, α1 and α2 are the sample estimation factors for cutting the denitration catalyst, which characterize the sample data of cutting the wet blank of the denitration catalyst, and construct a sample data set for cutting the wet blank of the denitration catalyst to obtain the data information of the sample data set for cutting the wet blank of the denitration catalyst;

[0016] M22. Based on the data information of the sample data set for cutting the wet blank of the denitration catalyst, establish a node feature extraction function H for the decision tree of cutting the wet blank of the denitration catalyst,

[0017] ,

[0018] where g is the data information of the sample data set for cutting the wet blank of the denitration catalyst, and β1, β2, and β3 are the node feature extraction factors for cutting the wet blank of the denitration catalyst, which extract features from the sample data set for cutting the wet blank of the denitration catalyst to obtain the decision tree node feature data information for cutting the wet blank of the denitration catalyst;

[0019] M23. Based on the decision tree node feature data information for cutting the wet blank of the denitration catalyst, establish a decision tree function F for cutting the wet blank of the denitration catalyst,

[0020] ,

[0021] where h i is the i-th node feature data information of the decision tree for cutting the wet blank of the denitration catalyst, n is the sample size, h min is the minimum node feature data information of the decision tree for cutting the wet blank of the denitration catalyst, h max is the maximum node feature data information of the decision tree for cutting the wet blank of the denitration catalyst, and ρ1, ρ2, and ρ3 are the decision tree metric factors for cutting the wet blank of the denitration catalyst to obtain the decision tree data information for cutting the wet blank of the denitration catalyst;

[0022] M24. Based on the decision tree data information for cutting the wet blank of the denitration catalyst, construct a prediction function R for cutting the wet blank of the denitration catalyst,

[0023] ,

[0024] where y is the decision tree data information for cutting the wet blank of the denitration catalyst, and µ1 and µ2 are the prediction factors for cutting the wet blank of the denitration catalyst, which predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife to obtain the predicted flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife.

[0025] Furthermore, the minimum node feature data information h of the decision tree for wet blank cutting of the denitration catalyst min is

[0026] ,

[0027] The maximum node feature data information h of the decision tree for wet blank cutting of the denitration catalyst max is

[0028] ,

[0029] where h i is the i-th node feature data information of the decision tree for wet blank cutting of the denitration catalyst.

[0030] Furthermore, the constraint conditions of the decision tree metric factors ρ1, ρ2, and ρ3 for wet blank cutting of the denitration catalyst are

[0031] .

[0032] Furthermore, in step M3, the optimization of the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife by using the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guiding mechanism includes

[0033] M31. Based on the predicted flow rate of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, construct a butterfly population and initialize it, determine the population parameters, and obtain the initialized butterfly population data information;

[0034] M32. Based on the initialized butterfly population data information, establish a fitness function W for the individuals of the butterfly population based on the adaptive adjustment factor

[0035] ,

[0036] where z is the initialized butterfly population data information, γ1, γ2, and γ3 are the fitness determination factors of the individuals of the butterfly population, and the fitness values of the individuals of the butterfly population are deduced to obtain the fitness value data information of the individuals of the butterfly population;

[0037] M33. Based on the fitness value data information of the individuals of the butterfly population, establish an objective optimization function U of the golden sine guiding mechanism

[0038] ,

[0039] ,

[0040] ,

[0041] Among them, a is the fitness value data information of the individuals in the butterfly population, and ω1 and ω2 are the optimization factors of the golden sine guiding mechanism of the population individuals, which optimize the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the data information of the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife.

[0042] Furthermore, the constraint function f of the fitness determination factors γ1, γ2, and γ3 of the individuals in the butterfly population is

[0043] ,

[0044] where the value range of f is (0, 1).

[0045] Furthermore, the feasibility evaluation function Q for cutting the wet blank of the denitration catalyst is

[0046] ,

[0047] where r1 is the data information of the optimized flow rate of the wet blank of the denitration catalyst, r2 is the data information of the optimized speed of the conveyor belt, r3 is the data information of the optimized cutting frequency of the cutting knife, and θ1, θ2, and θ3 are the comprehensive evaluation factors for the feasibility of cutting the wet blank of the denitration catalyst.

[0048] To achieve the above-mentioned purposes and other related purposes, the present invention also provides a system for implementing the optimization control method for cutting the wet blank of the denitration catalyst described in any one of the above, and the system includes:

[0049] A data acquisition module for acquiring the flow rate data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife;

[0050] A prediction module for cutting the wet blank of the denitration catalyst, connected to the data acquisition module, for constructing a random forest regression model for cutting the wet blank of the denitration catalyst to predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife;

[0051] An optimization module for cutting the wet blank of the denitration catalyst, connected to the prediction module for cutting the wet blank of the denitration catalyst, for optimizing the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtaining the data information of the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife;

[0052] The evaluation module for wet blank cutting of denitration catalyst, which is connected to the optimization module for wet blank cutting of denitration catalyst, is used to establish a feasibility evaluation function Q for wet blank cutting of denitration catalyst and evaluate the comprehensive operation data of wet blank cutting of denitration catalyst.

[0053] Furthermore, the system further includes an early warning module, which is connected to the evaluation module for wet blank cutting of denitration catalyst, and is used to output early warning prompt information for the production line of wet blank cutting of denitration catalyst according to the comprehensive evaluation data information of wet blank cutting of denitration catalyst to remind the user.

[0054] The present invention has the following positive effects:

[0055] 1. By constructing a random forest regression model for wet blank cutting of denitration catalyst, the present invention predicts the flow rate of wet blanks of denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and combines the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guiding mechanism to optimize the flow rate of wet blanks of denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife. It can not only accurately control and cut the length of the catalyst, but also has low requirements for the levelness between the guide rollers and does not require manual adjustment, improving the production efficiency of the catalyst.

[0056] 2. By establishing a feasibility evaluation function Q for wet blank cutting of denitration catalyst, the present invention evaluates the comprehensive operation data of wet blank cutting of denitration catalyst, and combines the setting of a preset threshold to give an early warning prompt for the production of wet blank cutting of denitration catalyst. It can not only monitor the wet blank cutting of denitration catalyst in real time to ensure the quality of catalyst products, but also does not require manual participation throughout the process, reducing labor costs and further improving the production efficiency of the catalyst. Description of the Drawings

[0057] Figure 1 It is the schematic structural diagram (one) of the wet blank cutting device for denitration catalyst of the present invention;

[0058] Figure 2 It is the schematic flow diagram of constructing a random forest regression model for wet blank cutting of denitration catalyst of the present invention;

[0059] Figure 3 It is the schematic flow diagram of the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guiding mechanism of the present invention;

[0060] Figure 4 It is the schematic system framework diagram of the present invention;

[0061] Figure 5 It is the schematic method flow diagram of the present invention;

[0062] Figure 6Schematic diagram (II) of the wet blank cutting device for the denitration catalyst of the present invention.

[0063] Description of reference numerals in the figure: 1 - Wet blank extruder for denitration catalyst, 2 - Solid flowmeter, 3 - Speed sensor, 4 - Conveyor belt, 5 - Cutting knife, 6 - Laser counting sensor. Detailed implementation mode

[0064] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0065] Example 1: As Figure 1 or Figure 5 or Figure 6 shown, an optimized control method for wet blank cutting of denitration catalyst, the method includes:

[0066] M1. On the production line for wet blank cutting of denitration catalyst, the wet blank extruder 1 of denitration catalyst extrudes the wet blank of denitration catalyst. Based on the solid flowmeter 2, the flow data information of the wet blank of denitration catalyst is obtained in real time. Based on the speed sensor 3, the speed data information of the conveyor belt 4 is obtained in real time. Based on the laser counting sensor 6, the cutting frequency data information of the wet blank cutting knife 5 is obtained in real time;

[0067] M2. Based on the flow data information of the wet blank of denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a random forest regression model for wet blank cutting of denitration catalyst is constructed to predict the flow rate of the wet blank of denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and the flow rate of the wet blank of denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife after prediction are obtained;

[0068] M3. Based on the flow rate of the predicted denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guiding mechanism is used to optimize the flow rate of the wet blank of denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and the flow rate of the wet blank of denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the cutting knife after optimization are obtained;

[0069] M4. Based on the data information of the flow rate of the optimized wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife, establish a feasibility evaluation function Q for cutting the wet blank of the denitration catalyst, evaluate the comprehensive operation data of cutting the wet blank of the denitration catalyst, and obtain the comprehensive evaluation data information of cutting the wet blank of the denitration catalyst.

[0070] In this embodiment, the method further includes:

[0071] M5. Based on the comprehensive evaluation data information of cutting the wet blank of the denitration catalyst, set a preset threshold. If the comprehensive evaluation of cutting the wet blank of the denitration catalyst is greater than the preset threshold, it operates normally; if the comprehensive evaluation of cutting the wet blank of the denitration catalyst is less than the preset threshold, it cannot operate normally, and repeat steps M3 - M4.

[0072] In this embodiment, as Figure 2 shown, in step M2, the construction of the random forest regression model for cutting the wet blank of the denitration catalyst and the prediction of the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife include:

[0073] M21. Based on the flow rate data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, establish a sample function G for cutting the wet blank of the denitration catalyst,

[0074] ,

[0075] where x1 is the flow rate data information of the wet blank of the denitration catalyst, x2 is the speed data information of the conveyor belt, x3 is the cutting frequency data information of the wet blank cutting knife, α1 and α2 are sample estimation factors for cutting the denitration catalyst, characterize the sample data of cutting the wet blank of the denitration catalyst, and construct a sample data set for cutting the wet blank of the denitration catalyst to obtain the data information of the sample data set for cutting the wet blank of the denitration catalyst;

[0076] M22. Based on the data information of the sample data set for cutting the wet blank of the denitration catalyst, establish a node feature extraction function H for the decision tree of cutting the wet blank of the denitration catalyst,

[0077] ,

[0078] where g is the data information of the sample data set for cutting the wet blank of the denitration catalyst, β1, β2, and β3 are node feature extraction factors for cutting the wet blank of the denitration catalyst, extract the features of the sample data set for cutting the wet blank of the denitration catalyst, and obtain the decision tree node feature data information for cutting the wet blank of the denitration catalyst;

[0079] Based on the decision tree node feature data information of the wet blank cutting of the denitration catalyst, establish the decision tree function F of the wet blank cutting of the denitration catalyst,

[0080] ,

[0081] where h i is the decision tree's i-th node feature data information of the wet blank cutting of the denitration catalyst, n is the sample size, h min is the decision tree's minimum node feature data information of the wet blank cutting of the denitration catalyst, h max is the decision tree's maximum node feature data information of the wet blank cutting of the denitration catalyst, and ρ1, ρ2, and ρ3 are the decision tree measurement factors of the wet blank cutting of the denitration catalyst, to obtain the decision tree data information of the wet blank cutting of the denitration catalyst;

[0082] M24. Based on the decision tree data information of the wet blank cutting of the denitration catalyst, construct the prediction function R of the wet blank cutting of the denitration catalyst,

[0083] ,

[0084] where y is the decision tree data information of the wet blank cutting of the denitration catalyst, and µ1 and µ2 are the prediction factors of the wet blank cutting of the denitration catalyst, to predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the predicted flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife.

[0085] In this embodiment, the decision tree's minimum node feature data information h min of the wet blank cutting of the denitration catalyst is

[0086] ,

[0087] The decision tree's maximum node feature data information h max of the wet blank cutting of the denitration catalyst is

[0088] ,

[0089] where h i is the decision tree's i-th node feature data information of the wet blank cutting of the denitration catalyst.

[0090] In this embodiment, the constraint conditions of the decision tree measurement factors ρ1, ρ2, and ρ3 of the wet blank cutting of the denitration catalyst are

[0091] .

[0092] Example 2: Based on the optimized control method for wet blank cutting of denitration catalysts in Example 1, the present invention will be further described and explained below.

[0093] As Figure 1 or Figure 5 or Figure 6 shown, an optimized control method for wet blank cutting of denitration catalysts, the method comprising:

[0094] M1. On the production line for wet blank cutting of denitration catalysts, a denitration catalyst wet blank extruder 1 extrudes denitration catalyst wet blanks. Based on a solid flow meter 2, flow data information of the denitration catalyst wet blanks is obtained in real time. Based on a speed sensor 3, speed data information of a conveyor belt 4 is obtained in real time. Based on a laser counting sensor 6, cutting frequency data information of a wet blank cutting knife 5 is obtained in real time;

[0095] M2. Based on the flow data information of the denitration catalyst wet blanks, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a random forest regression model for wet blank cutting of denitration catalysts is constructed to predict the flow rate of the denitration catalyst wet blanks, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and flow rate data information, conveyor belt speed data information, and cutting frequency data information of the predicted denitration catalyst wet blanks are obtained;

[0096] M3. Based on the flow rate of the predicted denitration catalyst, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a butterfly optimization algorithm based on an adaptive adjustment factor and a golden sine guiding mechanism is used to optimize the flow rate of the denitration catalyst wet blanks, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and flow rate data information, conveyor belt speed data information, and cutting frequency data information of the optimized denitration catalyst wet blanks and the cutting knife are obtained;

[0097] M4. Based on the flow rate data information, conveyor belt speed data information, and cutting frequency data information of the optimized denitration catalyst wet blanks and the cutting knife, a feasibility evaluation function Q for wet blank cutting of denitration catalysts is established to evaluate the comprehensive operation data of wet blank cutting of denitration catalysts, and comprehensive evaluation data information of wet blank cutting of denitration catalysts is obtained.

[0098] In this embodiment, as Figure 3 shown, in step M3, the use of a butterfly optimization algorithm based on an adaptive adjustment factor and a golden sine guiding mechanism to optimize the flow rate of the denitration catalyst wet blanks, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife includes:

[0099] M31. Based on the predicted flow rate of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency data of the green blank cutting knife, construct a butterfly population, initialize it, determine the population parameters, and obtain the initialized butterfly population data information;

[0100] M32. Based on the initialized butterfly population data information, establish a fitness function W for the individuals of the butterfly population based on an adaptive adjustment factor,

[0101] ,

[0102] where z is the initialized butterfly population data information, and γ1, γ2, and γ3 are the fitness determination factors of the individuals of the butterfly population. Calculate the fitness values of the individuals of the butterfly population to obtain the fitness value data information of the individuals of the butterfly population;

[0103] M33. Based on the fitness value data information of the individuals of the butterfly population, establish an objective optimization function U for the golden sine guiding mechanism,

[0104] ,

[0105] ,

[0106] ,

[0107] where a is the fitness value data information of the individuals of the butterfly population, and ω1 and ω2 are the optimization factors of the golden sine guiding mechanism of the population individuals. Optimize the flow rate of the green blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the green blank cutting knife to obtain the optimized data information of the flow rate of the green blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife.

[0108] In this embodiment, the constraint function f of the fitness determination factors γ1, γ2, and γ3 of the individuals of the butterfly population is

[0109] ,

[0110] where the value range of f is (0, 1).

[0111] In this embodiment, the feasibility evaluation function Q for cutting the green blank of the denitration catalyst is

[0112] ,

[0113] where r1 is the data information of the optimized flow rate of the green blank of the denitration catalyst, r2 is the data information of the optimized speed of the conveyor belt, r3 is the data information of the optimized cutting frequency of the cutting knife, and θ1, θ2, and θ3 are the comprehensive evaluation factors for the feasibility of cutting the green blank of the denitration catalyst.

[0114] In this embodiment, as Figure 4 shown, the present invention provides a system for implementing an optimization control method for wet blank cutting applied to any of the denitration catalysts. The system includes:

[0115] A data acquisition module, configured to acquire the flow data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife;

[0116] A prediction module for wet blank cutting of the denitration catalyst, connected to the data acquisition module, configured to construct a random forest regression model for wet blank cutting of the denitration catalyst, and predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife;

[0117] An optimization module for wet blank cutting of the denitration catalyst, connected to the prediction module for wet blank cutting of the denitration catalyst, configured to optimize the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the data information of the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife;

[0118] An evaluation module for wet blank cutting of the denitration catalyst, connected to the optimization module for wet blank cutting of the denitration catalyst, configured to establish a feasibility evaluation function Q for wet blank cutting of the denitration catalyst, and evaluate the comprehensive operation data of wet blank cutting of the denitration catalyst.

[0119] In this embodiment, the system further includes an early warning module, connected to the evaluation module for wet blank cutting of the denitration catalyst, configured to output an early warning prompt message for the production line of wet blank cutting of the denitration catalyst according to the comprehensive evaluation data information of wet blank cutting of the denitration catalyst, and remind the user.

[0120] In this embodiment, the present invention further provides a computer-readable storage medium, on which a computer program is stored that is programmed or configured to execute the optimization control method for wet blank cutting applied to any of the denitration catalysts.

[0121] Any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0122] In summary, the present invention can not only precisely control and cut the length of the catalyst, but also has low requirements for the levelness between the guide rollers, eliminating the need for manual adjustment and improving the production efficiency of the catalyst.

[0123] The above specific embodiments do not constitute a limitation to the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present disclosure should be included within the protection scope of the present disclosure.

Claims

1. An optimized control method for wet blank cutting applied to denitration catalysts, characterized in that, The method includes: M1. On the production line for wet blank cutting of denitration catalysts, the flow data information of the wet blanks of denitration catalysts is obtained in real time based on a solid flowmeter, the speed data information of the conveyor belt is obtained in real time based on a speed sensor, and the cutting frequency data information of the wet blank cutting knife is obtained in real time based on a laser counting sensor; M2. Based on the flow data information of the wet blanks of denitration catalysts, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a random forest regression model for wet blank cutting of denitration catalysts is constructed to predict the flow of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and the flow data information of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife after prediction are obtained; M3. Based on the flow data information of the denitration catalysts, the speed of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife after prediction, a butterfly optimization algorithm based on an adaptive adjustment factor and a golden sine guiding mechanism is used to optimize the flow of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and the flow data information of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency data information of the cutting knife after optimization are obtained; M4. Based on the flow data information of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency data information of the cutting knife after optimization, a feasibility evaluation function Q for wet blank cutting of denitration catalysts is established to evaluate the comprehensive operation data of wet blank cutting of denitration catalysts, and the comprehensive evaluation data information of wet blank cutting of denitration catalysts is obtained.

2. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 1, characterized in that The method further includes: M5. Based on the comprehensive evaluation data information of wet blank cutting of denitration catalysts, a preset threshold is set. If the comprehensive evaluation of wet blank cutting of denitration catalysts is greater than the preset threshold, it operates normally; if the comprehensive evaluation of wet blank cutting of denitration catalysts is less than the preset threshold, it cannot operate normally, and steps M3 - M4 are repeated.

3. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 1, characterized in that, In step M2, the construction of the random forest regression model for wet blank cutting of denitration catalysts to predict the flow of the wet blanks of denitration catalysts, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife includes: M21. Based on the flow data information of the wet blanks of denitration catalysts, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife, a sample function G for wet blank cutting of denitration catalysts is established, ， where x1 is the flow data information of the wet blanks of denitration catalysts, x2 is the speed data information of the conveyor belt, x3 is the cutting frequency data information of the wet blank cutting knife, α1 and α2 are sample estimation factors for denitration catalyst cutting, which characterize the sample data of wet blank cutting of denitration catalysts, and a sample data set for wet blank cutting of denitration catalysts is constructed, and the data information of the sample data set for wet blank cutting of denitration catalysts is obtained; M22. Based on the data information of the sample data set for wet blank cutting of denitration catalysts, a node feature extraction function H for the decision tree of wet blank cutting of denitration catalysts is established. ， Among them, g is the data information of the sample dataset for wet blank cutting of denitration catalysts, and β1, β2, and β3 are the node feature extraction factors for wet blank cutting of denitration catalysts. Feature extraction is performed on the sample dataset for wet blank cutting of denitration catalysts to obtain the decision tree node feature data information for wet blank cutting of denitration catalysts; M23. Based on the decision tree node feature data information for wet blank cutting of denitration catalysts, establish the decision tree function F for wet blank cutting of denitration catalysts, ， Among them, h i is the feature data information of the i-th node of the decision tree for wet blank cutting of denitration catalyst, n is the sample size, and h min is the minimum node feature data information of the decision tree for wet blank cutting of denitration catalyst, and h max is the maximum node feature data information of the decision tree for wet blank cutting of denitration catalyst. ρ1, ρ2, and ρ3 are the metric factors of the decision tree for wet blank cutting of denitration catalyst, and the decision tree data information for wet blank cutting of denitration catalyst is obtained; M24. Based on the decision tree data information for wet blank cutting of denitration catalysts, construct the prediction function R for wet blank cutting of denitration catalysts, ， Among them, y is the decision tree data information for wet blank cutting of denitration catalysts, and µ1 and µ2 are the prediction factors for wet blank cutting of denitration catalysts. Predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife to obtain the data information of the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife after prediction.

4. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 3, characterized in that: The minimum node feature data information h of the decision tree for wet blank cutting of the denitration catalyst min is ， The decision tree maximum node feature data information h for wet blank cutting of the denitration catalyst max is ， Among them, h i is the characteristic data information of the i-th node of the decision tree for wet blank cutting of the denitration catalyst.

5. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 2, characterized in that: The constraint conditions of the decision tree metric factors ρ1, ρ2, and ρ3 for wet blank cutting of denitration catalysts are as follows: 。 6. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 1, characterized in that, In step M3, the optimization of the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife using the butterfly optimization algorithm based on the adaptive adjustment factor and the golden sine guidance mechanism includes: M31. Based on the data information of the flow rate of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife after prediction, construct a butterfly population and initialize it to determine the population parameters to obtain the initialized butterfly population data information; M32. Based on the initialized butterfly population data information, establish the fitness function W of the individuals in the butterfly population based on the adaptive adjustment factor, ， Among them, z is the initialized butterfly population data information, and γ1, γ2, and γ3 are the fitness determination factors of the individuals in the butterfly population. Deduce the fitness values of the individuals in the butterfly population to obtain the data information of the fitness values of the individuals in the butterfly population; M33. Based on the data information of the fitness values of the individuals in the butterfly population, establish the target optimization function U of the golden sine guidance mechanism, ， ， ， Among them, a is the data information of the fitness values of the individuals in the butterfly population, and ω1 and ω2 are the optimization factors of the golden sine guidance mechanism of the population individuals. Optimize the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife to obtain the data information of the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife.

7. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 6, characterized in that: The constraint function f of the fitness determination factors γ1, γ2, and γ3 of the individuals in the butterfly population is as follows: ， Among them, the value range of f is (0, 1).

8. The optimized control method for wet blank cutting applied to denitration catalysts according to claim 1, characterized in that: The feasibility evaluation function Q for wet blank cutting of denitration catalysts is as follows: ， Among them, r1 is the data information of the flow rate of the wet blank of the optimized denitration catalyst, r2 is the data information of the speed of the optimized conveyor belt, r3 is the data information of the cutting frequency of the optimized cutting knife, and θ1, θ2, and θ3 are the comprehensive feasibility evaluation factors for wet blank cutting of denitration catalysts.

9. A system for implementing an optimized control method for wet blank cutting applied to denitration catalysts according to any one of claims 1-8, characterized in that, The system includes: A data acquisition module, which is used to acquire the flow data information of the wet blank of the denitration catalyst, the speed data information of the conveyor belt, and the cutting frequency data information of the wet blank cutting knife; A prediction module for cutting the wet blank of the denitration catalyst, connected to the data acquisition module, which is used to construct a random forest regression model for cutting the wet blank of the denitration catalyst, and predict the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife; An optimization module for cutting the wet blank of the denitration catalyst, connected to the prediction module for cutting the wet blank of the denitration catalyst, which is used to optimize the flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the wet blank cutting knife, and obtain the data information of the optimized flow rate of the wet blank of the denitration catalyst, the speed of the conveyor belt, and the cutting frequency of the cutting knife; An evaluation module for cutting the wet blank of the denitration catalyst, connected to the optimization module for cutting the wet blank of the denitration catalyst, which is used to establish a feasibility evaluation function Q for cutting the wet blank of the denitration catalyst, and evaluate the comprehensive operation data of cutting the wet blank of the denitration catalyst.

10. The system according to claim 9, characterized in that: The system further includes an early warning module, connected to the evaluation module for cutting the wet blank of the denitration catalyst, which is used to output the early warning prompt information of the production line for cutting the wet blank of the denitration catalyst according to the comprehensive evaluation data information of cutting the wet blank of the denitration catalyst, and remind the user.

Images