Method and apparatus for recipe optimization, non-transitory storage medium, electronic device

Abstract

The application discloses a formula optimization method and device, a nonvolatile storage medium and an electronic device. The method comprises the following steps: obtaining a detection result of mixed production raw materials; determining an initial production formula according to the detection result and production constraint parameters, wherein the initial production formula comprises a plurality of discharging weights, the discharging weight is used to indicate the weight of the production raw materials discharged to a discharging bin; determining a target index value corresponding to the initial production formula, wherein the target index value is used to indicate the oxidation-reduction performance of the production environment in the process of producing a target product by using the initial production formula; and in the case that the target index value does not belong to a preset numerical interval, iteratively updating the initial production formula to obtain an optimized formula. The application solves the technical problems of unstable production condition indexes and low production efficiency caused by the fact that the optimal batching ratio cannot be determined by relying on manual work in the related art, and the batching ratio cannot be optimized.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and apparatus for formula optimization, a non-volatile storage medium, and an electronic device. Background Technology

[0002] The batching methods used in related technologies are typically manually controlled. For example, when determining the required content of key components for glass fiber products, the factory first samples, prepares, and analyzes the raw materials to obtain the content of key components for each raw material. By selecting several suitable raw materials, the weight of the raw materials in the feed hopper is calculated based on the formula and manual operating experience. The batch formed after batching enters the furnace for melting. Finally, the finished product is sampled and analyzed, and the target component content after analysis is compared with the set value. Based on the deviation, it is determined whether the weight of the selected raw materials needs to be further adjusted. The above process relies on manual control, which has problems such as inaccurate detection of raw material components, difficulty in determining the optimal batching ratio, and difficulty in timely optimization of the batching ratio, resulting in unstable production conditions and low production efficiency.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method and apparatus for formula optimization, a non-volatile storage medium, and an electronic device to at least solve the technical problems of unstable production conditions and low production efficiency caused by the inability to determine the optimal ingredient ratio due to reliance on manual methods in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for formula optimization is provided, comprising: obtaining test results of mixed production raw materials, wherein the test results include: measured weights of multiple key components, the key components including production raw materials used to generate a target product in the mixed production raw materials; determining an initial production formula based on the test results and production constraint parameters, wherein the initial production formula includes: multiple feed weights, the feed weights indicating the weight of production raw materials fed to feed silos, and different types of production raw materials in the mixed production raw materials being fed to different feed silos; determining a target index value corresponding to the initial production formula, wherein the target index value indicating the redox performance of the production environment during the production of the target product using the initial production formula; and iteratively updating the initial production formula to obtain an optimized formula when the target index value does not belong to a preset value range, wherein in each iteration update, the feed weight of the target feed silo is adjusted, the target feed silo being the feed silo where the type of target production raw material fed is an alkaline type production raw material.

[0006] Optionally, the test results may also include: the number of raw material types included in the mixed production raw materials and the number of component types of the key components; production constraint parameters include: the target weight of each key component and the weight of a single batch, wherein the target weight is used to indicate the weight of the key components contained in the target product; determining the initial production formula based on the test results and production constraint parameters includes: determining the target value of the component raw material conversion index based on an objective function constructed from the measured weight of the key components, the target weight of the key components, the number of raw material types included in the mixed production raw materials, the number of component types of the key components, and the component raw material conversion index, wherein the component raw material conversion index is used to adjust the impact of raw material loss on the production of the target product, and the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key components; determining the initial production formula based on the target value of the component raw material conversion index and the weight of a single batch.

[0007] Optionally, the initial production formula is determined based on the target value of the component raw material conversion index and the single batch weight, including: analyzing the target value of the component raw material conversion index to obtain the key component raw material conversion index corresponding to each type of key component; determining the total component raw material conversion index based on the weight of each type of key component and the key component raw material conversion index corresponding to each type of key component, wherein the weight of the key component is used to indicate the proportion of the key component in the target product; for each type of key component, determining the corresponding feed weight of the key component based on the ratio of the key component raw material conversion index to the total component raw material conversion index and the single batch weight; and determining the initial production formula based on the multiple feed weights corresponding to multiple types of key components.

[0008] Optionally, the initial production formula is iteratively updated to obtain an optimized formula, including: searching for a first parameter within a first weight range of the key component using multiple preset step sizes, searching for a second parameter within a second weight range of the alkaline production raw material, and generating multiple parameter pairs based on the multiple first parameters and multiple second parameters; screening first-class parameter pairs that satisfy material conservation constraints from the multiple parameter pairs; screening second-class parameter pairs that satisfy redox performance constraints from the multiple first-class parameter pairs; determining a target parameter pair from the multiple second-class parameter pairs based on cost constraints, wherein the target parameter pair is the second-class parameter pair that minimizes production cost, and determining the production formula corresponding to the target parameter pair as the optimized formula.

[0009] Optionally, selecting a first-class parameter pair that satisfies the material conservation constraint from multiple parameter pairs includes: determining optional parameter pairs that make the objective function solvable from multiple parameter pairs, wherein the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key component; for each optional parameter pair, determining the feed weight based on the optional parameter pair, the objective function, and the single batching weight; and identifying parameter pairs with optional feed weights that are less than or equal to the upper limit of the feed weight and greater than or equal to the lower limit of the feed weight as first-class parameter pairs.

[0010] Optionally, a second type of parameter pair that satisfies the redox performance constraint is selected from multiple first type parameter pairs, including: for each first type parameter pair, determining an optional production formula generated based on the first type parameter pair, wherein the optional production formula is used to indicate the feed weight of various key components when producing the target product; for each optional production formula, determining the redox performance index of the optional production formula based on the content of oxidizing elements and reducing elements; determining the optional redox performance index whose difference from the target redox performance index value is less than a preset difference, and determining the first type parameter pair corresponding to the optional redox performance index as the second type parameter pair.

[0011] Optionally, a target parameter pair is determined among multiple second-class parameter pairs based on cost constraints, including: for each second-class parameter pair, determining the first weight of each type of key component defined by the second-class parameter pair, and determining the second weight of each type of production raw material containing the key component based on the first weight; determining the production cost based on the unit price of each type of production raw material and the second weight of each type of production raw material; and determining the second-class parameter pair corresponding to the production cost with the smallest value as the target parameter pair.

[0012] Optionally, the formulation optimization method also includes updating the objective function when there is no solution to the objective function, or when the raw materials for mixed production change.

[0013] According to another aspect of the embodiments of this application, a formula optimization apparatus is also provided, comprising: an acquisition module, configured to acquire the detection results of mixed production raw materials, wherein the detection results include: measured weights of multiple key components, the key components including production raw materials used to generate the target product in the mixed production raw materials; a first determination module, configured to determine an initial production formula based on the detection results and production constraint parameters, wherein the initial production formula includes: multiple feeding weights, the feeding weights indicating the weight of production raw materials issued to feeding silos, and different types of production raw materials in the mixed production raw materials being issued to different feeding silos; a second determination module, configured to determine a target index value corresponding to the initial production formula, wherein the target index value indicating the redox performance of the production environment during the production of the target product using the initial production formula; and a formula optimization module, configured to iteratively update the initial production formula to obtain an optimized formula when the target index value does not belong to a preset value range, wherein in each iteration update, the feeding weight of the target feeding silo is adjusted, the target feeding silo being the feeding silo where the type of target production raw material issued is an alkaline type production raw material.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, which stores a computer program, wherein the above-described method for formula optimization is executed by running the computer program in the device where the non-volatile storage medium is located.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to perform the above-described method for formula optimization through the computer program.

[0016] According to another aspect of the embodiments of this application, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the steps of the above-described recipe optimization method.

[0017] In this embodiment, the method involves obtaining the detection results of mixed production raw materials, wherein the detection results include: the measured weights of multiple key components, including the production raw materials used to generate the target product in the mixed production raw materials; determining an initial production formula based on the detection results and production constraint parameters, wherein the initial production formula includes: multiple feed weights, which indicate the weight of production raw materials issued to the feed hopper, and different types of production raw materials in the mixed production raw materials are issued to different feed hoppers; determining the target index value corresponding to the initial production formula, wherein the target index value indicates the redox performance of the production environment during the production of the target product using the initial production formula; and iteratively updating the initial production formula when the target index value does not fall within a preset value range to obtain an optimized formula, wherein the target feed weight is adjusted during each iteration update. The method for automatically determining the optimal ingredient ratio in a formula optimization system is provided. This system utilizes the detection results of key components in the raw materials obtained from online fluorescence analyzer testing and production constraint parameters to automatically calculate the ingredient ratio for the initial production formula, thereby improving the accuracy of ingredient proportioning. By comprehensively considering production performance indicators and other production constraint parameters to optimize the initial production formula, production efficiency is improved. This achieves fully automated component detection and formula optimization, enhancing the stability of production conditions. Furthermore, it solves the technical problems of unstable production conditions and low production efficiency caused by the inability to determine and optimize the optimal ingredient ratio in related technologies. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a method for formula optimization according to an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating the steps of a method for formula optimization according to an embodiment of this application;

[0021] Figure 3 This is a structural diagram of an apparatus for formula optimization according to an embodiment of this application;

[0022] Figure 4 This is a control flowchart of a batching optimization system according to an embodiment of this application. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application are explained below:

[0026] Grid search: This refers to dividing the variable region into grids, traversing all grid points, solving for the objective function value that satisfies the constraint function, and finally comparing and selecting the optimal point.

[0027] In related technologies, during the production of glass fiber, the mixture formed after batching is fed into the tank furnace for melting. The fluctuation of the mixture composition directly affects the quality stability of the finished glass fiber and the stability of the tank furnace's production conditions. During the batching process, factories often determine whether to update the raw material formula based on the test data of each mineral powder raw material component and the finished product component, referring to the process standards for the finished product components, and considering the deviation between the test data and the process standards. When the formula needs to be updated, the retested raw material component data is substituted into multiple formula calculation formulas, and the given weight of the feed hopper is recalculated in conjunction with multiple batching constraints to ensure that the mixture entering the tank furnace meets the quality requirements of glass fiber. The stability of each raw material component is a key factor affecting the quality qualification of the glass fiber product. At the same time, formula adjustments require appropriate adjustments to the weight of individual feed hoppers based on the production conditions of the glass tank furnace to ensure the stability of the tank furnace's production conditions. The above-mentioned scheme, which is manually executed, has the following problems: 1) In the raw material critical component testing stage, manual testing can only accurately detect the critical components of some raw materials. Since the raw materials may be stratified in the silo, the distribution of raw material components during feeding is uneven, resulting in inaccurate results from manual testing; 2) In the raw material critical component testing stage, the manual testing method leads to excessively long testing time, significant lag in manual adjustment of the proportions, poor control of critical components, long production time, and low production efficiency; 3) During manual adjustment, formula calculation and optimization require multiple set parameters. Relying solely on manual experience makes it difficult to find the optimal adjustment method, determine the optimal formula, adapt to the dynamic changes in the chemical composition of raw materials, and meet the needs of industrialized assembly line operations. To solve the above problems, this application provides relevant solutions, which are detailed below.

[0028] According to an embodiment of this application, a method embodiment for formula optimization is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal for implementing a method for recipe optimization is shown. Figure 1As shown, the computer terminal 10 may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0031] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the recipe optimization method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned recipe optimization method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0032] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0033] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0034] This application provides a method for formula optimization that can run under the above-described operating environment. Figure 2 This is a flowchart of the steps of the formulation optimization method provided in the embodiments of this application, as follows: Figure 2 As shown, the method includes the following steps:

[0035] Step S202: Obtain the test results of the mixed production raw materials, wherein the test results include: the measured weight of multiple key components, and the key components include the production raw materials used to generate the target product in the mixed production raw materials.

[0036] This application provides a method for fully automated component detection and proportion adjustment. The fully automated detection is based on a component detection instrument. In step S202, the detection results of the component detection instrument on the mixed production raw materials are obtained. The key components detected by the component detection instrument depend on the chemical composition requirements of the product to be produced (i.e., the target product) and the composition of the mixed production raw materials. The mixed production raw materials contain multiple materials of different types. The detection results record the following information: all types of key components (i.e., multiple key components) contained in the mixed production raw materials used to generate the target product, and the weight of each type of key component contained in the mixed production raw materials (i.e., the measured weight). The target product is one of multiple products that can be generated from the mixed production raw materials and is predefined. In this embodiment, the component detection instrument can be a fluorescence analyzer. The fluorescence analyzer includes a sample chamber for placing the sample. The fluorescence analyzer analyzes the mixed production raw materials to be tested based on the chemical composition of the sample to detect all chemical components (i.e., multiple key components) contained in the mixed production raw materials used to generate the sample. For example, in this embodiment, the target product is a glass fiber product. In this case, the key components detected by the fluorescence analyzer are chemical components contained in the glass fiber product and also contained in the mixed production raw materials. For example, the key components can be silicon dioxide (SiO2), aluminum oxide (Al2O3), calcium oxide (CaO), etc.

[0037] Step S204: Determine the initial production formula based on the test results and production constraint parameters. The initial production formula includes: multiple feed weights, which indicate the weight of production raw materials issued to the feed hopper. Different types of production raw materials in the mixed production raw materials are issued to different feed hoppers.

[0038] In step S204, based on the principle of material conservation, the feeding weight of each feeding hopper is determined according to the detection results obtained from the key component detection of the mixed production raw materials in step S202 and the production constraint parameters related to the actual production conditions. The types of production raw materials issued to each feeding hopper are different. For example, the production raw materials used to produce the target product in the mixed production raw materials include: silicon oxide (SiO2), aluminum oxide (Al2O3), and calcium oxide (CaO). In actual production, these three types of production raw materials are issued to different feeding hoppers. Therefore, after determining the weight of the corresponding production raw materials issued to multiple feeding hoppers (i.e., multiple feeding weights), the ratio of these multiple feeding weights can be determined as the initial formula for producing the target product.

[0039] According to some optional embodiments of this application, the test results further include: the number of raw material types included in the mixed production raw materials and the number of component types of the key components; production constraint parameters include: the target weight of each type of key component and the weight of a single batch, wherein the target weight is used to indicate the weight of the key components contained in the target product; determining the initial production formula based on the test results and production constraint parameters includes: determining the target value of the component raw material conversion index based on an objective function constructed from the measured weight of the key components, the target weight of the key components, the number of raw material types included in the mixed production raw materials, the number of component types of the key components, and the component raw material conversion index, wherein the component raw material conversion index is used to adjust the influence of raw material loss on the production of the target product, and the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key components; determining the initial production formula based on the target value of the component raw material conversion index and the weight of a single batch.

[0040] The principle of material conservation states that, ideally, all types of key components contained in the mixed raw materials appear in the target product, and the weight (i.e., measured weight) of each type of key component in the mixed raw materials is the same as the weight (i.e., target weight) of the corresponding key component in the target product. However, in actual production, various raw materials have a certain loss on ignition at the firing temperature, and the loss on ignition varies for raw materials with different chemical compositions. Therefore, in this embodiment, when determining the initial production formula according to the principle of material conservation, the loss on ignition of various key components is taken into account, and an objective function constructed from the detection results and production constraint parameters is used. Determine the component raw material conversion index Component raw material conversion index This is used to introduce the impact of loss on ignition on the production of the target product; in the above objective function... Let represent the target weight of the j-th critical component, m represent the number of raw material types in the mixed production raw materials (i.e., how many types of raw materials are included in the mixed production raw materials), and n represent the number of component types of the critical components (i.e., how many critical components there are). Let represent the measured weight of key component j contained in raw material i; the objective function described above is used to solve for minimizing product composition fluctuations (i.e., minimizing the difference between the measured weight and the target weight of component j, where j represents any key component). The value (i.e., the target value); to further determine the value that minimizes fluctuations in product composition. The value (i.e., the target value) and the weight of ingredients per batch ( The initial production formula is determined, where the weight of a single batch refers to the total weight of all raw materials mixed in one production batch or cycle (i.e., the total weight of a single batch). The objective function is used to determine the component raw material conversion index. During the process, and The parameters are included in the production constraint parameters and are related to the actual production situation. m and n are included in the test results obtained from the testing of mixed production raw materials.

[0041] The above uses the objective function to determine When the value of is obtained (i.e., the target value), first convert each objective function into matrix form: Further confirmation Where T represents the transpose of the matrix, yes The matrix form has dimensions ( ), ; yes The matrix form has dimensions ( ), ; It is a dimension of ( The identity matrix (all elements are 1) of . ; yes The matrix form has dimensions ( ) ;because , and Since it is known, it can be solved. .

[0042] Optionally, the initial production formula is determined based on the target value of the component raw material conversion index and the single batch weight, including: analyzing the target value of the component raw material conversion index to obtain the key component raw material conversion index corresponding to each type of key component; determining the total component raw material conversion index based on the weight of each type of key component and the key component raw material conversion index corresponding to each type of key component, wherein the weight of the key component is used to indicate the proportion of the key component in the target product; for each type of key component, determining the corresponding feed weight of the key component based on the ratio of the key component raw material conversion index to the total component raw material conversion index and the single batch weight; and determining the initial production formula based on the multiple feed weights corresponding to multiple types of key components.

[0043] In the previous embodiment, the objective function was used to solve for the product composition that minimizes fluctuations. The value (i.e., the target value) is a vector containing each element. This refers to the key component raw material conversion index corresponding to each type of key component. In this embodiment, it is based on the index that minimizes product composition fluctuations. The value (i.e., the target value) and the weight of ingredients per batch ( When further determining the initial production formula, follow the formula. The defined calculation rules are as follows: The total component raw material conversion index (TRI) is a weighted sum of the conversion indices of all components. It is used to balance the contributions of different types of raw materials in the production of the target product. At that time, for the objective function determined in the previous embodiment... Analysis was performed to obtain the key component raw material conversion index corresponding to each type of key component. And determine the weights corresponding to each type of key component. The product; after determining the multiple products corresponding to multiple key components, the sum of the multiple products is determined as The weight of each of the above key components can be determined based on the proportion of the key component in the target product. This is the feed weight of the i-th type of critical component. In this embodiment, after determining the feed weight of each type of critical component... Then, multiple feed weights corresponding to various key components can be calculated. Determine an ingredient ratio and use this ratio as the initial production formula.

[0044] Step S206: Determine the target index value corresponding to the initial production formula, wherein the target index value is used to indicate the redox performance of the production environment during the production of the target product using the initial production formula.

[0045] The relative amount of alkaline raw materials used has a certain impact on the firing of the product, mainly by affecting the redox properties during the glass melting process, which indirectly affects the quality of the target product. Therefore, redox properties are an important process indicator for the production of the target product in the tank furnace. After obtaining the initial formula in S204, in step S206, it is necessary to further determine the redox properties in the tank furnace (i.e., the production environment) when producing the target product using the initial production formula, so as to determine whether the initial formula meets the preset process standards and whether it needs to be optimized based on the value of the redox property index (i.e., the target index value).

[0046] Step S208: If the target index value does not fall within the preset value range, iteratively update the initial production formula to obtain an optimized formula. During each iteration, the feeding weight of the target feeding hopper is adjusted. The target feeding hopper is the feeding hopper where the target production raw material is of the alkaline type.

[0047] If the redox performance index value (i.e., the target value) of the initial production formula deviates from the preset value range, then in step S208, the iterative optimization process of the initial formula is entered. The initial production formula is optimized by adjusting the amount of alkaline raw materials (i.e., the feeding weight of the target feeding hopper). When the convergence condition is reached, the iteration is stopped, and the iteration result obtained from the last iteration is output as the optimized formula. In this embodiment, when the target product is produced using the optimized formula, the redox performance of the production environment meets the process requirements, while keeping the fluctuation of product composition within the allowable range.

[0048] According to some optional embodiments of this application, the initial production formula is iteratively updated to obtain an optimized formula, including: searching for a first parameter within a first weight range of the key component using multiple preset step sizes, searching for a second parameter within a second weight range of the alkaline production raw material, and generating multiple parameter pairs based on multiple first parameters and multiple second parameters; screening first-class parameter pairs that satisfy material conservation constraints from multiple parameter pairs; screening second-class parameter pairs that satisfy redox performance constraints from multiple first-class parameter pairs; determining a target parameter pair from multiple second-class parameter pairs based on cost constraints, wherein the target parameter pair is the second-class parameter pair that minimizes production cost, and determining the production formula corresponding to the target parameter pair as the optimized formula.

[0049] The method provided in this application embodiment searches for the optimal process parameters within the parameter process constraints based on an improved grid search algorithm, and uses these parameters for batching calculations to achieve dynamic optimization control of the batching process. In this embodiment, the parameter process constraints include: the weight range of key components (i.e., the first weight range) and the weight range of alkaline production raw materials (i.e., the second weight range). During iterative optimization of the formulation, the amount of major raw materials used is first searched within the above-mentioned process constraints. The parameters are (i.e., the first parameter) and the amount of alkaline raw material used, w (i.e., the second parameter), where the amount of raw material used represents the total weight of multiple key components in a single production process. When optimizing within the process constraints, different preset step sizes can be used for the search. For example, initially, if the search range is large, a larger preset step size can be used for a larger search span. After several searches, a smaller preset step size can be used. This method of using different step sizes not only improves the search accuracy but also shortens the search time. This method can be implemented by predefining the total number of searches M and N less than M, so that when the number of searches is less than N, the first preset step size is used, and when the number of searches is greater than N, the second preset step size is used. Each time, the amount of raw material used is searched within the process constraints. After combining the first parameter (i.e., the first parameter) and the amount of alkaline raw material w (i.e., the second parameter), a result is obtained from... The parameter pairs consisting of 'w' and 'w' represent nodes in a grid search. The method provided in this application uses multiple constraints to filter the parameter pairs obtained from the grid search. First, based on the material conservation constraint, parameter pairs satisfying material conservation (i.e., first-class parameter pairs) are selected from the first-class parameter pairs. Next, parameter pairs satisfying redox performance constraints (i.e., second-class parameter pairs) are selected from the first-class parameter pairs. Finally, parameter pairs satisfying cost constraints (i.e., target parameter pairs) are selected from the second-class parameter pairs. When producing the target product using the formula generated based on the above target parameter pairs, the product composition deviation is minimized (i.e., meets the requirements of...). The goal is to achieve optimal performance in both production conditions and operating parameters (i.e., redox performance) while minimizing production costs. The above target parameters specify the optimal dosage of alkaline raw materials that simultaneously meet all three constraints. And the amount of alkaline raw material w, according to By adjusting the initial formula with w, we can obtain an optimized formula corresponding to the target parameters.

[0050] Optionally, selecting a first-class parameter pair that satisfies the material conservation constraint from multiple parameter pairs includes: determining optional parameter pairs that make the objective function solvable from multiple parameter pairs, wherein the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key component; for each optional parameter pair, determining the feed weight based on the optional parameter pair, the objective function, and the single batching weight; and identifying parameter pairs with optional feed weights that are less than or equal to the upper limit of the feed weight and greater than or equal to the lower limit of the feed weight as first-class parameter pairs.

[0051] Material conservation constraints include: objective function Limited conditions and the upper limit of material weight under actual working conditions and minimum material weight Limited conditions: In this embodiment, for each parameter pair obtained by grid search, if substituting the parameter pair into the objective function yields a solution, the parameter pair is classified as an optional parameter pair for redox performance verification; otherwise, if substituting the parameter pair into the objective function yields a solution, the parameter pair is deleted. For the selected optional parameter pairs, the target value of the key component raw material conversion index calculated based on the objective function is used. Combined with the total weight of ingredients in a single batch According to the formula for calculating the weight of the material. This determines the feed weight when producing the target product using each optional parameter of the defined formula. , will satisfy Optional blanking weight The corresponding parameter pairs are determined to be the first type of parameter pairs that satisfy the material conservation constraints.

[0052] Optionally, a second type of parameter pair that satisfies the redox performance constraint is selected from multiple first type parameter pairs, including: for each first type parameter pair, determining an optional production formula generated based on the first type parameter pair, wherein the optional production formula is used to indicate the feed weight of various key components when producing the target product; for each optional production formula, determining the redox performance index of the optional production formula based on the content of oxidizing elements and reducing elements; determining the optional redox performance index whose difference from the target redox performance index value is less than a preset difference, and determining the first type parameter pair corresponding to the optional redox performance index as the second type parameter pair.

[0053] After selecting the first type of parameter pairs that satisfy the material conservation constraint using the method of the previous embodiment, this embodiment further filters the first type of parameter pairs to find those parameter pairs that can keep the redox performance index within a predetermined target range (i.e., the second type of parameter pairs). Specifically, when filtering parameter pairs that satisfy the redox performance constraint from those that satisfy the material conservation constraint, for each first type of parameter pair, based on the determined feed weight... Combining process objectives and component raw material conversion index The process generates corresponding optional production formulas, each detailing the feed weights of various key components for producing the target product. Next, for each optional production formula, its corresponding redox index is calculated based on the ratio of oxidizing to reducing element content. For example, for each optional production formula, the weight of the raw material containing sulfur is determined as the oxidizing element content, and the weight of the raw material containing carbon is determined as the reducing element content. The ratio of oxidizing to reducing element content is then determined as the redox index of the optional production formula. Finally, the difference between the redox index of the optional production formula and the target redox index value is determined. If the calculated difference is less than a preset difference, the first parameter pair of the optional production formula corresponding to this difference is the parameter pair that simultaneously satisfies both material conservation constraints and redox constraints (i.e., the second parameter pair). This method ensures that while minimizing product composition fluctuations, the redox index remains within acceptable fluctuation ranges.

[0054] According to some optional embodiments of this application, a target parameter pair is determined among multiple second-class parameter pairs based on cost constraints, including: for each second-class parameter pair, determining the first weight of each type of key component defined by the second-class parameter pair, and determining the second weight of each type of production raw material containing the key component based on the first weight; determining the production cost based on the unit price of each type of production raw material and the second weight of each type of production raw material; and determining the second-class parameter pair corresponding to the production cost with the smallest value as the target parameter pair.

[0055] In this embodiment, target parameter pairs that satisfy the cost constraint are further selected from parameter pairs that simultaneously satisfy both material conservation and redox property constraints (i.e., the second parameter pairs). In this embodiment, the lowest cost strategy is adopted as the cost constraint, and the cost constraint can be expressed as a nonlinear function: In the formula, n is the number of types of raw materials used in production. The weight of the i-th type of raw material added when producing the target product (i.e., the second weight). Let be the unit price of the i-th type of raw material; determine the appropriate value in the second type of parameter pair according to the above formula. The target parameter pair with the minimum value. The weight of the i-th type of raw material (i.e., the second weight) can be determined as follows: In the optional production formula generated based on the second type of parameters, the proportions of multiple key components are determined. The weight of each key component (i.e., the first weight) can be determined based on the proportion of each key component and the weight of the provided mixed raw materials. The weight of each key component (i.e., the first weight) is associated with the raw materials containing that key component, and the second weight (i.e., the actual weight used in production) of multiple raw materials containing the same key component is calculated. For example, if the key component is carbon, and the mixed raw materials containing carbon are quartz sand, feldspar, and limestone, then the first weight is the weight of carbon, and the second weight includes the weight of quartz sand, feldspar, and limestone.

[0056] According to some alternative embodiments of this application, the method for formula optimization further includes: updating the objective function when there is no solution to the objective function, or when the raw materials for mixed production change.

[0057] The objective function representing the material conservation constraint This is based on several assumptions. It considers that during ingredient optimization, the objective function may become unsolvable (this usually means the current formulation parameters cannot achieve the optimal solution while satisfying all constraints), and that the chemical properties of raw materials may change over time, with different suppliers, or batches, rendering the original objective function inapplicable. In this embodiment, when the above situations are detected, the objective function representing the material conservation constraints is updated. Specifically, when the objective function becomes unsolvable, it is updated by adjusting the fluctuation range of key components, the upper limit of feed weight, or the lower limit of feed weight. When the mixed production raw materials change, the key components of the mixed production raw materials are re-detected to obtain new detection results. The objective function is updated based on the new detection results and the changed production constraint parameters. For example, if a new type of production raw material is added to the mixed production raw materials, parameters related to the new type of production raw material are added to the objective function.

[0058] Through the above steps, fully automated component detection and formula optimization can be achieved. By combining the component detection results of production raw materials, production constraint parameters, and iterative algorithms, the formula used to produce the target product is automatically optimized, significantly improving the accuracy of ingredient ratios and production efficiency, and reducing errors and lags caused by manual operation. Especially in the glass fiber industry, this method can effectively control product component fluctuations, ensure the stability of tank furnace production conditions, and reduce production costs.

[0059] Figure 3 This is a structural diagram of an apparatus for optimizing a formulation according to an embodiment of this application, such as... Figure 3 As shown, the apparatus for formula optimization includes: an acquisition module 30, used to acquire the test results of mixed production raw materials, wherein the test results include: the measured weights of multiple key components, the key components including the production raw materials used to generate the target product in the mixed production raw materials; a first determination module 32, used to determine the initial production formula based on the test results and production constraint parameters, wherein the initial production formula includes: multiple feeding weights, the feeding weights indicating the weight of production raw materials issued to the feeding silos, and different types of production raw materials in the mixed production raw materials being issued to different feeding silos; a second determination module 34, used to determine the target index value corresponding to the initial production formula, wherein the target index value indicates the redox performance of the production environment during the production of the target product using the initial production formula; and a formula optimization module 36, used to iteratively update the initial production formula to obtain an optimized formula when the target index value does not belong to a preset value range, wherein in each iteration update, the feeding weight of the target feeding silo is adjusted, the target feeding silo being the feeding silo where the type of target production raw material issued is alkaline.

[0060] When generating and optimizing a formula using a formula optimization device, the acquisition module 30 collects the detection results obtained from the key component detection of the mixed production raw materials. These results can be provided by an online fluorescence analyzer and record the measured weights of various key components used to generate the target product within the mixed production raw materials. The acquisition module 30 outputs the detection results to the first determination module 32. Based on the detection results and preset production constraint parameters, the first determination module 32 determines the initial production formula, which includes the feeding weights of multiple feeding bins (each containing different types of production raw materials). When determining the initial production formula, the first determination module 32 follows the principle of material balance (i.e., material conservation constraints) to ensure that the total feeding amount of key components meets the product composition ratio requirements. The second determination module 34 evaluates the redox performance indicators of the production environment under the initial production formula. By analyzing the proportions of key components in the mixture after batching, especially the content of alkaline raw materials, it calculates the redox performance index value (i.e., the target index value) to ensure that the chemical reaction environment during the production process remains stable and unaffected by raw material fluctuations. The formula optimization module 36 is used to start the ingredient optimization program when the target index value calculated by the second determination module 34 does not fall within the preset fluctuation range of the redox index (i.e., the preset value range). The initial production formula is iteratively updated by adjusting the feeding weight of the feeding bin (i.e., the target feeding bin) where the alkaline raw materials are located until an optimized formula that simultaneously satisfies multiple constraints such as material conservation constraints and redox performance index constraints is found.

[0061] It should be noted that, Figure 3 Preferred embodiments of the shown examples can be found in [reference needed]. Figure 2 The relevant descriptions of the embodiments shown will not be repeated here.

[0062] The batching optimization method provided in this application embodiment can be executed by a batching optimization system, which consists of a component detection system, an online optimization calculation system, and a programmable logic controller (PLC). When the target product is glass, the batching optimization system combines raw material component detection data and feed hopper information, calculates the formula in real time according to the material conservation relationship, and considers glass production operating conditions and formula costs. The optimal formula is generated through the iteration of the optimization algorithm. After the new formula meets the issuance conditions, it will be written back to the programmable logic controller (PLC) used to implement batching.

[0063] The component detection system in the batching optimization system is used to detect key components of the mixed production raw materials, and the online optimization calculation system is used to execute the batching optimization method provided in the embodiments of this application and output the optimal formula (i.e., the optimized formula). The PLC batching system is used to produce the target product (such as glass fiber product) according to the above-mentioned optimal formula. Figure 4This is the control flow chart of the ingredient optimization system, such as... Figure 4 As shown, the component detection system uses an online fluorescence analyzer (fluorescence analyzer) to detect key components and outputs detection results. The detection results record the following information: the measured weights of multiple key components used to generate the target product contained in the mixed production raw materials. These detection results are input into the online optimization system to obtain the optimal formula (i.e., the optimized formula) output by the online optimization calculation system. Specifically, the online optimization calculation system calls the aforementioned online optimization device. The acquisition module 30 in the device acquires the aforementioned detection results, and the first determining module 32 determines the initial production formula based on the detection results and production constraint parameters. When the target product to be produced is glass fiber, the production constraint parameters include the target set value of the glass fiber component (i.e., the target weight of the key component), and the initial production formula records the calculated values ​​of multiple glass fiber components calculated according to the material conservation constraint (i.e., the feed weight of multiple glass fiber components). In this embodiment, in the process of calculating the multiple glass fiber component values ​​according to the material conservation constraint, an objective function is used. The system determines whether the calculation results meet the quality requirements. If they do not (i.e., the objective function has no solution), it prompts the user to update the mixed production raw materials. Based on the detection results obtained from the key component detection of the updated mixed production raw materials using an online fluorescence analyzer, the initial production formula is re-determined. If the initial production formula meets the quality requirements (i.e., the objective function has a solution), the second determination module 34 calculates the operating condition indicators of the initial production formula and evaluates them. In this embodiment, the initial production formula is evaluated for meeting the operating condition constraints by calculating the value of the indicator representing the redox performance of the initial production formula (i.e., the target indicator value). Figure 4 As shown, when the initial production formula does not meet the operating condition constraints / requirements (i.e., the target index value does not belong to the preset value range), the initial production formula is iteratively updated through the formula optimization module 36 to obtain the optimal formula. Figure 4As shown, during each iteration, a new production formula is generated based on quality relationships (i.e., a new production formula is generated using a grid search method). For multiple new production formulas, it is sequentially determined whether there is a formula that meets the quality requirements (i.e., whether the material conservation constraint is met). If not, the mixed production raw materials are updated, and the above steps are repeated. If there is, it is determined whether there is a formula that meets the operating condition constraints (i.e., whether the redox performance constraint is met) among the schemes that meet the material conservation constraints. If not, a new production formula is generated based on the quality relationships, and the evaluation starts again from the material conservation constraints. If there is, it is determined whether there is a production formula that meets both the material conservation constraints and the operating condition constraints and meets the cost constraints, i.e., whether there is a production formula with the lowest production cost. If not, iterative optimization is performed based on the operating condition constraints (i.e., optimization is performed by adjusting the feed amount of the alkaline production raw materials). If there is, the production formula corresponding to the lowest production cost is output, and it is verified whether the feed amount in the production formula meets the feed conditions (i.e., whether the feed amount in the production formula is at the preset feed amount upper limit). and preset minimum feed amount The optimal formula is obtained by updating; if it is not satisfied, no update is performed. Figure 4 In some embodiments, the material feeding conditions are applied after screening based on cost constraints. Alternatively, they can be applied to the stage of screening production formulas that meet material conservation constraints (i.e., first screening production formulas that meet material conservation constraints → screening production formulas that meet material feeding conditions from those formulas → screening production formulas that meet operating condition constraints from those formulas → screening production formulas that meet cost constraints from those formulas). The optimized formula output by the formula optimization module 36 is written to the programmable logic controller (PLC) as the optimal formula, and the PLC distributes the corresponding ingredients to each feeding bin according to the optimal formula.

[0064] This application also provides a non-volatile storage medium storing a computer program, wherein the above-mentioned method for formula optimization is executed by running the computer program on the device where the non-volatile storage medium is located.

[0065] The aforementioned non-volatile storage medium is used to store a program that performs the following functions: acquiring the test results of mixed production raw materials, wherein the test results include: measured weights of multiple key components, including production raw materials used to generate the target product in the mixed production raw materials; determining an initial production formula based on the test results and production constraint parameters, wherein the initial production formula includes: multiple feed weights, the feed weights indicating the weight of production raw materials issued to the feed hopper, and different types of production raw materials in the mixed production raw materials being issued to different feed hoppers; determining the target index value corresponding to the initial production formula, wherein the target index value indicating the redox performance of the production environment during the production of the target product using the initial production formula; and iteratively updating the initial production formula to obtain an optimized formula when the target index value does not fall within a preset value range, wherein in each iteration update, the feed weight of the target feed hopper is adjusted, and the target feed hopper is the feed hopper where the type of target production raw material issued is alkaline.

[0066] This application also provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor is configured to execute the above-described method for formula optimization through the computer program.

[0067] The processor in the aforementioned electronic device is used to run a program that performs the following functions: acquiring the detection results of the mixed production raw materials, wherein the detection results include: the measured weights of multiple key components, the key components including the production raw materials used to generate the target product in the mixed production raw materials; determining the initial production formula based on the detection results and production constraint parameters, wherein the initial production formula includes: multiple feed weights, the feed weights indicating the weight of production raw materials issued to the feed hopper, and different types of production raw materials in the mixed production raw materials being issued to different feed hoppers; determining the target index value corresponding to the initial production formula, wherein the target index value indicating the redox performance of the production environment during the production of the target product using the initial production formula; and iteratively updating the initial production formula to obtain an optimized formula when the target index value does not fall within a preset value range, wherein in each iteration update, the feed weight of the target feed hopper is adjusted, the target feed hopper being the feed hopper where the type of target production raw material issued is alkaline.

[0068] This application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the above-described recipe optimization method.

[0069] It should be noted that each module in the above-mentioned formula optimization device can be a program module (e.g., a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0070] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0071] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0076] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for formula optimization, characterized in that, include: Obtain the test results of the mixed production raw materials, wherein the test results include: the measured weight of multiple key components, the number of raw material types contained in the mixed production raw materials, and the number of component types of the key components, wherein the key components include the production raw materials used to generate the target product in the mixed production raw materials; Determining the initial production formula based on the test results and production constraint parameters includes: determining the target value of the component raw material conversion index based on an objective function constructed from the measured weight of the key component, the target weight of the key component, the number of raw material types included in the mixed production raw materials, the number of component types of the key component, and the component raw material conversion index, wherein the component raw material conversion index is used to adjust the influence of raw material loss on ignition on the production of the target product, and the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key component; determining the initial production formula based on the target value of the component raw material conversion index and the single batch weight, wherein the target weight and single batch weight of each type of key component are included in the production constraint parameters, the target weight is used to indicate the weight of the key component included in the target product, and the initial production formula includes: multiple feed weights, the feed weights are used to indicate the weight of production raw materials fed to the feed hopper, and different types of production raw materials in the mixed production raw materials are fed to different feed hoppers; Determine the target index value corresponding to the initial production formula, wherein the target index value is used to indicate the redox performance of the production environment during the production of the target product using the initial production formula; If the target index value does not fall within the preset value range, the initial production formula is iteratively updated to obtain an optimized formula. During each iteration, the feeding weight of the target feeding hopper is adjusted. The target feeding hopper is the feeding hopper where the target production raw material is of the alkaline type.

2. The method according to claim 1, characterized in that, The initial production formula is determined based on the target value of the component raw material conversion index and the weight of the single batch of ingredients, including: The target value of the component raw material conversion index is analyzed to obtain the key component raw material conversion index corresponding to each type of key component. The total component raw material conversion index is determined based on the weight of each type of key component and the key component raw material conversion index corresponding to each type of key component, wherein the weight of the key component is used to indicate the proportion of the key component in the target product; For each type of key component, the feed weight corresponding to the key component is determined based on the ratio of the raw material conversion index of the key component to the raw material conversion index of the total components and the single batch feed weight. The initial production formula is determined based on the multiple feed weights corresponding to the various key components.

3. The method according to claim 1, characterized in that, The initial production formula is iteratively updated to obtain an optimized formula, including: The system uses multiple preset step sizes to search for a first parameter within a first weight range of the key components, and searches for a second parameter within a second weight range of the alkaline production raw materials. Multiple parameter pairs are generated based on multiple first parameters and multiple second parameters. The first parameter is used to indicate the amount of raw material used, which represents the total weight of multiple key components in a single production process. The second parameter is used to indicate the amount of alkaline raw materials used. Select the first type of parameter pairs that satisfy the material conservation constraint from the plurality of parameter pairs; Select a second type of parameter pair that satisfies the redox performance constraint from multiple first type of parameter pairs; Based on cost constraints, a target parameter pair is determined from multiple second-type parameter pairs, wherein the target parameter pair is the second-type parameter pair that minimizes production costs; The production formula corresponding to the target parameters is determined as the optimized formula.

4. The method according to claim 3, characterized in that, Among the multiple parameter pairs, the first type of parameter pairs that satisfy the material conservation constraints are selected, including: Among a plurality of said parameter pairs, an optional parameter pair is determined that makes the objective function solvable, wherein the objective function indicates the target value of the component feed conversion index that minimizes the difference between the target weight and the measured weight of the key component; For each of the optional parameter pairs, the feed weight is determined based on the optional parameter pair, the objective function, and the single batch feed weight. The parameter pairs with optional cutting weights that are less than or equal to the upper limit of cutting weight and greater than or equal to the lower limit of cutting weight are defined as the first type of parameter pairs.

5. The method according to claim 3, characterized in that, Selecting second-class parameter pairs from multiple first-class parameter pairs that satisfy redox performance constraints, including: For each of the first type of parameter pairs, an optional production formula generated based on the first type of parameter pair is determined, the optional production formula being used to indicate the feed weight of each of the key components when producing the target product; For each of the optional production formulations, the redox index of the optional production formulation is determined based on the content of oxidizing elements and the content of reducing elements; Selectable redox indices whose difference from the target redox index value is less than a preset difference are determined, and the first type of parameter pair corresponding to the selectable redox index is determined as the second type of parameter pair.

6. The method according to claim 3, characterized in that, Based on cost constraints, target parameter pairs are determined from multiple pairs of second-type parameter pairs, including: For each of the second type of parameter pairs, determine the first weight of each type of key component defined by the second type of parameter pair, and determine the second weight of each type of production raw material containing the key component based on the first weight; determine the production cost based on the unit price of each type of production raw material and the second weight of each type of production raw material. The second type of parameter pair corresponding to the production cost with the smallest value is determined as the target parameter pair.

7. The method according to claim 1, characterized in that, The method further includes updating the objective function when the objective function has no solution, or when the mixed production raw materials change.

8. An apparatus for formula optimization, characterized in that, include: The acquisition module is used to acquire the detection results of the mixed production raw materials, wherein the detection results include: the measured weight of multiple key components, the number of raw material types contained in the mixed production raw materials, and the number of component types of the key components, wherein the key components include the production raw materials used to generate the target product in the mixed production raw materials; The first determining module is used to determine the initial production formula based on the detection results and production constraint parameters, wherein the initial production formula includes: multiple feeding weights, the feeding weights are used to indicate the weight of production raw materials issued from the feeding silos, and different types of production raw materials in the mixed production raw materials are issued to different feeding silos; The second determining module is used to determine the target index value corresponding to the initial production formula, including: determining the target value of the component raw material conversion index based on an objective function constructed from the measured weight of the key component, the target weight of the key component, the number of raw material types included in the mixed production raw materials, the number of component types of the key component, and the component raw material conversion index, wherein the component raw material conversion index is used to adjust the influence of raw material loss on the generation of the target product, and the objective function indicates the target value of the component raw material conversion index that minimizes the difference between the target weight and the measured weight of the key component; determining the initial production formula based on the target value of the component raw material conversion index and the single batch weight, wherein the target weight and the single batch weight of each type of key component are included in the production constraint parameters, the target weight is used to indicate the weight of the key component included in the target product, and the target index value is used to indicate the redox performance of the production environment during the production of the target product using the initial production formula; The formula optimization module is used to iteratively update the initial production formula to obtain an optimized formula when the target index value does not belong to a preset value range. In each iteration update, the feeding weight of the target feeding hopper is adjusted. The target feeding hopper is the feeding hopper where the target production raw material is an alkaline type production raw material.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a computer program, wherein the device containing the non-volatile storage medium executes the method for formula optimization according to any one of claims 1 to 7 by running the computer program.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method for formula optimization according to any one of claims 1 to 7 through the computer program.

11. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the recipe optimization method according to any one of claims 1 to 7.

Images