A ferrite magnet production control method and system

Abstract

The embodiments of the present specification provide a ferrite magnet production control method and system, which includes conveying raw materials in a raw material storage device to a raw material mixing device based on a conveyor belt; mixing the raw materials according to a preset ratio based on the raw material mixing device to obtain a first raw material; pre-treating the first raw material based on a pre-treatment device to obtain a second raw material, and the pre-treatment is a dry treatment or a wet treatment; grinding the second raw material based on a grinding device to obtain a third raw material, the grinding device includes a stirring mechanism and a crushing mechanism, and the crushing mechanism is connected to the stirring mechanism; molding the third raw material based on a molding device to form a blank; sintering the blank based on a sintering device to form a primary product, the sintering device is equipped with a sintering controller, and the sintering controller is used to adjust the sintering parameters during the sintering process; machining the primary product based on a machining device to form a ferrite magnet product.

Description

Technical Field

[0001] This specification relates to the technical field of ferrite magnets, and in particular to a ferrite magnet production control method and system. Background Art

[0002] Ferrite magnets are a type of permanent magnet primarily made from strontium oxide or palladium oxide and ferric oxide. Compared to other permanent magnets, ferrite magnets are harder and less brittle, have lower magnetic energy, and are less susceptible to demagnetization and corrosion. However, during the sintering process, ferrite magnets may develop defects such as cracks and bubbles.

[0003] Therefore, it is necessary to provide a ferrite magnet production control method and system to improve the product quality of the produced ferrite magnets. Summary of the Invention

[0004] One or more embodiments of the present specification provide a ferrite magnet production control method, the method comprising: conveying raw materials in a raw material storage device to a raw material mixing device based on a conveyor belt; mixing the raw materials according to a preset ratio based on the raw material mixing device to obtain a first raw material; pre-treating the first raw material based on a pre-treatment device to obtain a second raw material, wherein the pre-treatment is a dry treatment or a wet treatment; grinding the second raw material based on a grinding device to obtain a third raw material, wherein the grinding device includes a stirring mechanism and a crushing mechanism, and the crushing mechanism is connected to the stirring mechanism; molding the third raw material based on a molding device to form a blank; sintering the blank based on a sintering device to form a primary product, wherein the sintering device is equipped with a sintering controller, and the sintering controller is used to adjust the sintering parameters during the sintering process; machining the primary product based on a machining device to form a ferrite magnet product.

[0005] One or more embodiments of the present specification provide a ferrite magnet production control system, the system comprising: a conveying module for conveying raw materials in a raw material storage device to a raw material mixing device based on a conveyor belt; a mixing module for mixing the raw materials according to a preset ratio based on the raw material mixing device to obtain a first raw material; a pretreatment module for pretreatment of the first raw material based on the pretreatment device to obtain a second raw material, the pretreatment being a dry process or a wet process; a grinding module for grinding the second raw material based on the grinding device to obtain a third raw material, the grinding device comprising a stirring mechanism and a crushing mechanism, the crushing mechanism being connected to the stirring mechanism; a forming module for forming the third raw material based on the forming device to form a blank; a sintering module for sintering the blank based on the sintering device to form a primary product, the sintering device being equipped with a sintering controller, the sintering controller being used to adjust the sintering parameters during the sintering process; a processing module for mechanically processing the primary product based on the mechanical processing device to form a ferrite magnet product.

[0006] One or more embodiments of this specification provide a ferrite magnet production control device, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement the ferrite magnet production control method described in any of the above embodiments.

[0007] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the ferrite magnet production control method described in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 is an exemplary module diagram of a ferrite magnet production control system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a ferrite magnet production control method according to some embodiments of this specification;

[0011] Figure 3 is an exemplary schematic diagram of a molding process for a third raw material according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of a target billet moisture content prediction model according to some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of an intake air flow prediction model according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0016] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0017] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 1 is an exemplary module diagram of a ferrite magnet production control system according to some embodiments of this specification. In some embodiments, the ferrite magnet production control system 100 may include a conveying module 110, a mixing module 120, a pre-processing module 130, a grinding module 140, a molding module 150, a sintering module 160, and a processing module 170.

[0019] The conveying module 110 can be used to convey the raw materials in the raw material storage device to the raw material mixing device based on a conveyor belt. For more information about conveying to the raw material mixing device, please refer to step 210 and its related description.

[0020] The mixing module 120 can be used to mix the raw materials according to a preset ratio based on the raw material mixing device to obtain a first raw material. For more information about obtaining the first raw material, please refer to step 220 and its related description.

[0021] The pre-processing module 130 can be used to pre-process the first raw material using a pre-processing device to obtain a second raw material. The pre-processing can be a dry process or a wet process. For more information about obtaining the second raw material, see step 230 and its related description.

[0022] Grinding module 140 can be used to grind the second raw material using a grinding device to obtain a third raw material. The grinding device includes a stirring mechanism and a crushing mechanism, and the crushing mechanism and the stirring mechanism are electrically connected. For more information about obtaining the third raw material, please refer to step 240 and its related description.

[0023] The forming module 150 can be used to form the third raw material based on the forming device to form a blank. For more information about forming the blank, please refer to step 250 and its related description.

[0024] The sintering module 160 can be used to sinter the blank using a sintering device to form a primary product. The sintering device is equipped with a sintering controller that adjusts sintering parameters during the sintering process. For more information on forming the primary product, see step 260 and its related description.

[0025] The processing module 170 can be used to perform mechanical processing on the primary product based on a mechanical processing device to form a ferrite magnet product. For more information about forming the ferrite magnet product, please refer to step 270 and its related description.

[0026] It should be noted that the above description of the ferrite magnet production control system and its modules is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without deviating from the principles. In some embodiments, Figure 1 The conveying module 110, mixing module 120, pre-treatment module 130, grinding module 140, forming module 150, sintering module 160, and processing module 170 disclosed herein may be different modules within a single system, or a single module may implement the functions of two or more of the aforementioned modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0027] Figure 2 is an exemplary flow chart of a ferrite magnet production control method according to some embodiments of this specification. In some embodiments, process 200 can be executed by a processor. Figure 2 As shown, process 200 includes the following steps:

[0028] In step 210 , the raw materials in the raw material storage device are conveyed to the raw material mixing device via a conveyor belt.

[0029] In some embodiments, the raw materials may include ferric oxide, manganese oxide, zinc oxide, and the like.

[0030] A raw material storage device refers to a device for storing raw materials. For example, a raw material storage device may include but is not limited to a raw material storage tank.

[0031] In some embodiments, different raw material storage devices can be used to store different types of raw materials. In some embodiments, different raw materials can be placed in different storage locations to store different types of raw materials.

[0032] The raw material mixing device refers to a device for mixing raw materials. For example, the raw material mixing device may include but is not limited to a high-speed mixer.

[0033] In some embodiments, the raw material mixing device includes a stirring blade. The material and size of the stirring blade can be determined based on the raw materials. By way of example only, the material and size of the stirring blade can be determined based on the type of raw material, the weight of the raw material, the particle size of the raw material, and other factors, based on empirical experience. For example, when the raw material particles are large, a stirring blade made of a harder material and having a larger size can be selected.

[0034] In some embodiments of the present invention, the material and size of the stirring blades of the raw material mixing device are determined according to the raw materials, so as to achieve a better mixing effect.

[0035] In some embodiments, the processor can transfer the raw materials to the raw material mixing device in a variety of ways. For example, the processor can transfer the raw materials to the raw material mixing device via a conveyor belt.

[0036] Step 220 : The raw materials are mixed according to a preset ratio by a raw material mixing device to obtain a first raw material.

[0037] The preset ratio refers to the weight ratio of different types of raw materials when mixed. For example, the preset ratio can be m 三氧化二铁 :m 四氧化三锰 :m 氧化锌 =a:b:c.

[0038] In some embodiments, the processor may obtain the preset ratio in a variety of ways, such as manually preset, default value, based on experience, or any combination thereof, and may be determined based on actual needs.

[0039] The first raw material refers to a mixture of different types of raw materials mixed in a preset ratio. For example, the first raw material can be a mixture of ferric oxide, manganese oxide, zinc oxide, etc. mixed in a preset ratio.

[0040] Step 230: pre-process the first raw material using a pre-processing device to obtain a second raw material.

[0041] The pretreatment device refers to a device that pre-treats the first raw material. For example, the pretreatment device may include, but is not limited to, a heater and a cleaning water gun. The cleaning water gun can use water to clean the first raw material.

[0042] Pretreatment refers to the treatment of the first raw material before grinding. In some embodiments, pretreatment can be dry or wet. By way of example only, dry treatment can involve heating the first raw material using a heater. Wet treatment can involve washing the first raw material using a water jet.

[0043] The second raw material refers to a raw material obtained by pre-processing the first raw material. For example, the second raw material can be the first raw material obtained by dry processing the first raw material.

[0044] Step 240: Grind the second raw material using a grinding device to obtain a third raw material.

[0045] The third raw material refers to the second raw material after being ground and pulverized by the grinding device.

[0046] The grinding device refers to a device for grinding the second raw material. For example, the grinding device may include but is not limited to a ball mill, a sand mill, a strong mixer, etc.

[0047] In some embodiments, the grinding device may include a batching mechanism. The batching mechanism may be used to add additives to the second raw material. For example, the batching mechanism may add organic and / or inorganic additives to the second raw material based on preset rules. These preset rules may include the type of grinding device, a preset ratio of raw materials, and the like.

[0048] In some embodiments, the grinding device may include a metering and conveying mechanism. The metering and conveying mechanism may be connected to the batching mechanism to meter and convey the second raw material mixed with additives from the batching mechanism. For example, the metering and conveying mechanism may be equipped with a weight sensor. When the weight of the second raw material mixed with additives conveyed by the batching mechanism reaches a threshold, the metering and conveying mechanism conveys it to the stirring mechanism. The threshold weight may be manually set in advance.

[0049] In some embodiments, the grinding device may include a stirring mechanism, wherein the stirring mechanism may be connected to the metering and conveying mechanism to stir the second raw material mixed with the additive to achieve uniform mixing.

[0050] In some embodiments, the grinding device may include a crushing mechanism, wherein the crushing mechanism is connected to the stirring mechanism and is used to grind and crush the second raw material after being stirred by the stirring mechanism.

[0051] In some embodiments, a buffer tank may be provided between the stirring mechanism and the pulverizing mechanism. The buffer tank is used to buffer and pre-store the second raw material after stirring by the stirring mechanism. A high-speed agitator is provided within the buffer tank. The high-speed agitator can be used to stir the second raw material in the buffer tank at high speed to maintain a uniform mixture. For example only, the speed of the high-speed agitator can be greater than 1200 rpm.

[0052] In some embodiments, a pumping mechanism may be provided between the stirring mechanism and the pulverizing mechanism, wherein the pumping mechanism may be used to transport the stirred second raw material from the stirring mechanism to the pulverizing mechanism.

[0053] In some embodiments, the grinding device may include a screening mechanism. The screening mechanism may be connected to the pulverizing mechanism to screen the second raw material after grinding and pulverizing by the pulverizing mechanism, and obtain a third raw material based on the screening conditions. The screening conditions may include the particle diameter and / or particle surface area being less than a threshold value. As an example only, the screening mechanism may use particles with a diameter less than a diameter threshold in the second raw material after grinding by the pulverizing mechanism as the third raw material, screen them, and transfer them to the finished product storage mechanism, while screening out particles with a diameter greater than the diameter threshold.

[0054] In some embodiments, the grinding device may include a finished product storage mechanism, wherein the finished product storage mechanism may be connected to the screening mechanism for storing the third raw material.

[0055] Step 250: forming the third raw material using a forming device to form a blank.

[0056] Blanks are intermediate products that have been shaped and sized and require further processing.

[0057] The forming device refers to a device used to shape the third raw material to form a blank. For example, the forming device may include but is not limited to a dry pressing forming device, a slip casting forming device, etc.

[0058] In some embodiments, the forming apparatus may include a blank mold mechanism. The blank mold mechanism is a unit equipped with a blank template for shaping the third raw material. In some embodiments, the blank mold mechanism can be used to select different blank templates to shape the third raw material, thereby forming blanks of different shapes and / or sizes.

[0059] Figure 3 FIG. 1 is an exemplary schematic diagram of forming the third raw material according to some embodiments of this specification. Figure 3 As shown, in some embodiments, the forming device 310 may further include a mixer 312 , and the mixer 312 is provided with a water adding device 311 . The water adding device 311 may be used to add water to the third raw material 320 .

[0060] In some embodiments, the forming process may include conveying the third raw material 320 to the mixer 312, and shaping the third raw material 320 after adding water based on the blank mold mechanism 312-1 to obtain the blank 330. The amount of water added by the water adding device 311 is determined based on the weight of the blank and the target moisture content of the blank.

[0061] The weight of a blank refers to the mass of the blank. For example, the weight of a blank may be a kilogram.

[0062] The amount of water added refers to the weight of water added to the third raw material by the water adding device. For example, the amount of water added can be a kilogram of water added to the third raw material by the water adding device.

[0063] In some embodiments, the processor can determine the water addition amount of the water addition device in various ways. For example, the water addition amount of the water addition device can be manually determined based on experience, based on the weight of the billet and the target billet moisture content. By way of example only, the processor can compile a data comparison table of historical water addition amounts corresponding to historical billet weights and historical target billet moisture contents, and determine the water addition amount of the water addition device based on this data comparison table.

[0064] The target billet moisture content refers to the ratio of the weight of water in the billet to the total weight of the billet. For example, the target billet moisture content can be 2% to 3%.

[0065] In some embodiments, the processor can obtain the target billet moisture content in a variety of ways. The target billet moisture content can be a default value, based on experience, manually preset, or any combination thereof, and can be determined according to actual needs.

[0066] In some embodiments, the processor can predict the target billet moisture content based on the grinding particle size and raw material composition using a target billet moisture content prediction model. For more information on predicting the target billet moisture content, please refer to Figure 4 and its related descriptions.

[0067] In step 260 , the blank is sintered using a sintering device to form a primary product.

[0068] The primary product refers to the primary product of the ferrite magnet obtained after sintering. For example, the primary product can be the primary product of the ferrite magnet that has not been machined.

[0069] The sintering device refers to a device used to sinter the blank. For example, the sintering device may include but is not limited to a belt-type exhaust sintering machine.

[0070] In some embodiments, the sintering device may be equipped with a sintering controller, wherein the sintering controller may be used to adjust sintering parameters during the sintering process.

[0071] Sintering parameters refer to relevant parameters during the sintering process. For example, sintering parameters may include but are not limited to heating temperature, heating rate, sintering temperature, holding time, cooling temperature, cooling rate, etc.

[0072] In some embodiments, the processor can determine the sintering parameters in a variety of ways. For example, the sintering parameters can be manually preset in advance. In another example, the sintering parameters can be manually set based on experience, such as the shape, size, and moisture content of the billet.

[0073] In some embodiments, the sintering process may include sintering the blank based on target sintering parameters, wherein the target sintering parameters may be adjusted by a sintering controller.

[0074] The target sintering parameters refer to sintering parameters suitable for the blank. In some embodiments, the target sintering parameters may include but are not limited to a target heating rate, a target sintering temperature, a target holding time, and a target cooling rate during sintering.

[0075] The target heating rate is a heating rate suitable for the material. For example, the target heating rate may be b°C per hour.

[0076] In some embodiments, the target heating rate may be a step-by-step heating rate.

[0077] Step-by-step heating means that the target heating rate varies within different preset temperature ranges. The preset temperature range can be manually set in advance. For example, in the first temperature stage, the target heating rate is the first target heating rate; in the second temperature stage, the target heating rate is the second target heating rate. For example, in the first temperature stage from 25°C to 800°C, the first target heating rate is 30°C per hour; in the second temperature stage from 800°C to 1300°C, the second target heating rate is 120°C per hour.

[0078] In some embodiments of this specification, a step-by-step temperature increase method is adopted to help reduce cracking during the sintering process and improve the qualified rate of the product.

[0079] The target sintering temperature is a sintering temperature suitable for the blank. For example, the target sintering temperature may be 1350°C.

[0080] The target holding time is the holding time suitable for the blank at the target sintering temperature. For example, the target holding time may be 6 hours at the target sintering temperature.

[0081] The target cooling rate is a cooling rate suitable for the blank. For example, the target cooling rate may be 15°C per hour.

[0082] In some embodiments, the processor may determine the target sintering parameters in various ways. For example, the processor may use the sintering parameters with the best sintering effect in the past as the target sintering parameters.

[0083] In some embodiments, the processor may further determine target sintering parameters based on a preset algorithm.

[0084] The preset algorithm specifically includes the following:

[0085] In some embodiments, the processor may encode the sintering parameters in the sintering parameter scheme in a variety of ways to obtain the sintering parameter scheme code.

[0086] The sintering parameters in the sintering parameter scheme may include a target heating rate, a target sintering temperature, a target holding time, and a target cooling rate. At least some of the sintering parameters are different in different sintering parameter schemes. As an example only, the sintering parameter scheme code may be (40.5℃ / h, 125℃ / h, 1400℃, 10h, 15℃ / h). Among them, 40.5℃ / h represents the first target heating rate in the first temperature stage; 125℃ / h represents the second target heating rate in the second temperature stage. For more information about the first temperature stage, the first target heating rate, the second temperature stage, and the second target heating rate, please refer to the aforementioned related description. 1400℃ represents the target sintering temperature; 10h represents the target holding time; 15℃ / h represents the target cooling rate.

[0087] In some embodiments, the processor may generate n initial sintering parameter plans. The value of n may be determined empirically. In some embodiments, the processor may obtain the initial sintering parameter plans in a variety of ways. For example, the processor may use the sintering parameters corresponding to initial products with good sintering results over a historical period as the initial sintering parameter plans.

[0088] In some embodiments, the processor may perform multiple rounds of iterative updates on multiple initial sintering parameter solutions based on a preset algorithm until preset iteration conditions are met, thereby determining target sintering parameters.

[0089] In some embodiments, the processor can determine the rationality of the sintering parameter plan based on an evaluation parameter. The evaluation parameter refers to a relevant parameter used to evaluate the rationality of the sintering parameter plan. The evaluation parameter can be positively correlated with the rationality of the sintering parameter plan. For example, the more rational the sintering parameter plan, the larger the corresponding evaluation parameter.

[0090] In some embodiments, for each initial sintering parameter scheme, the processor can determine the product quality corresponding to the initial sintering parameter scheme based on the product quality prediction model of the sintering parameter scheme, the weight of the billet, the billet template, the target billet moisture content, the grinding particle size and the raw material composition, and determine the evaluation parameters corresponding to the initial sintering parameter scheme based on the product quality.

[0091] Product quality refers to the sum of characteristics and properties of a product that satisfy specified and potential needs. In some embodiments, product quality can be negatively correlated with the number, length, and depth of cracks in the product. Product quality can be represented by a real number between 0 and 1, with larger values ​​indicating higher product quality.

[0092] In some embodiments, the product quality prediction model may be a machine learning model for predicting product quality. For example, the product quality prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, or any combination thereof.

[0093] In some embodiments, the inputs to the product quality prediction model may include sintering parameter schemes, billet weight, billet template, target billet moisture content, grinding particle size, and raw material composition. The billet template may include the type and size of the billet template selected when the third raw material is formed. For more information on billet weight and target billet moisture content, see step 250 and its related description. For more information on grinding particle size and raw material composition, see Figure 4 The output of the product quality prediction model may include the product quality corresponding to the initial sintering parameter scheme.

[0094] In some embodiments, a product quality prediction model can be obtained by training multiple first training samples with first labels. For example, multiple first training data with first labels can be input into an initial product quality prediction model. A loss function is constructed using the first labels and the results of the initial product quality prediction model, and the parameters of the initial product quality prediction model are iteratively updated based on the loss function. When the loss function of the initial product quality prediction model meets preset conditions, model training is completed, resulting in a trained product quality prediction model. The preset conditions may include convergence of the loss function, a threshold number of iterations, etc.

[0095] In some embodiments, the first training sample for the product quality prediction model may include historical sintering parameters, the corresponding billet weight, billet template, target billet moisture content, grind size, and raw material composition; and the first label may include the quality of the initial product corresponding to the sintering parameters. The first label may be obtained through manual annotation based on the number, length, and depth of cracks in the initial product.

[0096] In some embodiments, the processor can determine the evaluation parameters corresponding to the initial sintering parameters based on product quality in various ways. For example, when the product quality is less than a quality threshold, the evaluation parameters corresponding to the initial sintering parameters are 0; when the product quality is greater than the quality threshold, the evaluation parameters corresponding to the initial sintering parameters are positively correlated with the product quality, with the greater the product quality, the greater the evaluation parameters corresponding to the initial sintering parameters. The quality threshold can be set in advance.

[0097] In some embodiments, the evaluation parameter is also related to the electricity cost of the solution. For example, the processor can use the formula Q=W1*f+W2*g to calculate the evaluation parameter corresponding to the solution. Among them, Q represents the evaluation parameter corresponding to the solution; W1 and W2 are positive numbers whose sum is 1; f is a piecewise function related to the product quality of the product obtained by the sintering parameters. For example, when the product quality is less than the quality threshold, the function value corresponding to f can be 0; when the product quality is greater than the quality threshold, the greater the product quality, the greater the function value corresponding to f. G is a function related to the electricity cost of the solution, wherein the higher the electricity cost, the smaller the function value corresponding to G.

[0098] In some embodiments, the processor can obtain the electricity cost of the solution in various ways. For example, electricity cost = heating time × heating cost per unit time × (target sintering temperature - room temperature) + holding time × holding cost per unit time + cooling cost. The heating cost per unit time, holding cost per unit time, and cooling cost per unit time can be set manually.

[0099] In some embodiments of the present disclosure, the evaluation parameters are related to the electricity cost of the solution, and a reference amount of the electricity cost is introduced, so that the evaluation parameters have reference value.

[0100] In some embodiments, for each initial sintering parameter solution, the processor may, based on the evaluation parameters corresponding to the initial sintering parameter solution, use a selection operator to select the top i initial sintering parameter solutions with the best evaluation parameters from among the multiple initial sintering parameter solutions, and perform a selection operation as the first candidate sintering parameter solution. The value of i can be predefined. In some embodiments, the selection operator may include a roulette wheel selection operator or any other selection operator.

[0101] In some embodiments, the processor may use a crossover operator to perform a crossover operation on at least two first candidate sintering parameter solutions among the plurality of first candidate sintering parameter solutions to obtain a second candidate sintering parameter solution. The crossover operator may include but is not limited to a single-point crossover operator.

[0102] For example only, when the crossover operator is a single-point crossover operator, the processor may randomly select a position on the vector corresponding to the first candidate sintering parameter solution for exchange. For example, the vectors corresponding to the first candidate sintering parameter solution are (40.5°C / h, 125°C / h, 1400°C, 10h, 15°C / h) and (42.5°C / h, 105°C / h, 1500°C, 9h, 14°C / h). After the crossover operation using the single-point crossover operator, the vectors corresponding to the second candidate sintering parameter solution may be (42.5°C / h, 125°C / h, 1400°C, 10h, 15°C / h) and (40.5°C / h, 105°C / h, 1500°C, 9h, 14°C / h). In some embodiments, the processor may randomly select a position on the vector corresponding to the first candidate sintering parameter solution for exchange using a Gaussian random or Bernoulli random method.

[0103] In some embodiments, the processor may perform a mutation operation on the plurality of second candidate sintering parameter solutions using a mutation operator, and replace the corresponding second candidate sintering parameter solutions with the sintering parameter solutions after the mutation operation. The mutation operator may include but is not limited to a basic bit mutation operator.

[0104] As an example only, when the mutation operator is a basic bit mutation operator, the processor can randomly specify a certain bit or several bits of the second candidate sintering parameter vector in the second candidate sintering parameter scheme encoding vector based on the mutation probability to perform a mutation operation. Among them, the mutation probability refers to the probability that the value in the second candidate sintering parameter encoding vector needs to be mutated. The mutation probability can be preset in advance, such as a mutation probability of 5%. For example, the vector corresponding to the second candidate sintering parameter scheme is (42.5℃ / h, 125℃ / h, 1400℃, 10h, 15℃ / h). After the basic bit mutation operator performs a mutation operation and replaces it, the vector corresponding to the new second candidate sintering parameter scheme can be (42.5℃ / h, 130℃ / h, 1460℃, 10h, 15℃ / h).

[0105] In some embodiments, the variation direction of the variation operation can be subject to preset limits. The preset limits can be manually set in advance. For example, the variation direction of the cooling rate can be intended to slow down the cooling rate, avoiding a significant increase in the cooling rate during the sintering process. This can prevent cracking in the product due to a large temperature difference between the inside and outside of the sintering process.

[0106] In some embodiments of this specification, by limiting the mutation direction of the mutation operation, the iteration speed can be accelerated, computing resources can be saved, and at the same time, the product obtained by the final determined target sintering parameters can be guaranteed to have higher product quality and product qualification rate.

[0107] In some embodiments, the processor can calculate and determine the evaluation parameters of multiple first candidate sintering parameter schemes and multiple second candidate sintering parameter schemes based on the aforementioned method, and sort the evaluation parameters of multiple first candidate sintering parameter schemes and multiple second candidate sintering parameter schemes from large to small, thereby eliminating the first candidate sintering parameter schemes and / or second candidate sintering parameter schemes whose evaluation parameters rank lower than a preset ranking threshold.

[0108] In some embodiments, the processor can determine the initial sintering parameter scheme to enter the next round from the existing first candidate sintering parameter scheme and / or multiple second candidate sintering parameter schemes based on the size of the evaluation parameters, and perform the aforementioned steps of calculating the evaluation parameters, selecting operations, crossover operations, mutation operations and determining the initial sintering parameter scheme to enter the next round, and continue to iterate and update until the preset iteration conditions are met, and the first candidate sintering parameter scheme or the second candidate sintering parameter scheme with the largest evaluation parameter is used as the target sintering parameter.

[0109] In some embodiments, the processor may determine the initial sintering parameter solution to proceed to the next round in a variety of ways. For example, the processor may determine that an existing first candidate sintering parameter solution and / or multiple second candidate sintering parameter solutions whose evaluation parameters are greater than a preset value will proceed to the next round. For another example, the processor may determine that several solutions with the highest evaluation parameters will proceed to the next round.

[0110] In some embodiments, the preset iteration conditions may include the number of iteration rounds being no less than a preset round value, the evaluation parameter of the target sintering parameter being higher than an evaluation parameter threshold, the difference in evaluation parameters for m consecutive iterations being lower than a difference threshold, or any combination thereof. The preset round value, the evaluation parameter threshold, the value of m, and the difference threshold may be manually set in advance. The evaluation parameter difference refers to the difference in evaluation parameters of the target sintering parameters output from the previous and next rounds. For example, the evaluation parameter difference can be obtained by subtracting the evaluation parameter of the target sintering parameter output from the xth round from the evaluation parameter of the target sintering parameter output from the x+1th round.

[0111] In some embodiments, the sintering process further includes adjusting, by a sintering controller, a gas discharge flow rate of the gas discharge valve and a gas intake flow rate of the gas intake valve.

[0112] The degassing rate refers to the rate at which gas is released from the sintering device. For example, the degassing rate can be a cubic meter per second.

[0113] The air flow rate refers to the speed at which gas is introduced into the sintering device. For example, the air flow rate may be b cubic meters per second. In some embodiments, the air flow rate may include the air flow rate of inert gas introduced into the sintering device.

[0114] In some embodiments, the processor may obtain the deflation flow rate and the intake flow rate in various ways. For example, the deflation flow rate and the intake flow rate may be preset, based on experience, manually set, or any combination thereof, and may be determined based on actual needs.

[0115] In some embodiments, the processor can predict the inert gas intake flow rate based on the billet weight, raw material composition, target sintering parameters, real-time temperature, and degassing flow rate using an intake flow prediction model. For more information on predicting the inert gas intake flow rate, please refer to Figure 5 and its related descriptions.

[0116] In step 270 , the primary product is machined using a machining device to form a ferrite magnet product.

[0117] Machining equipment refers to equipment used to perform mechanical processing on primary products. For example, machining equipment may include, but is not limited to, CNC machine tools.

[0118] In some embodiments, the processor can perform mechanical processing on the primary product in various ways. For example, the processor can perform cutting processing on the primary product by using a CNC machine tool.

[0119] In some embodiments of the present invention, raw materials are processed by a raw material mixing device, a pretreatment device, a grinding device, a molding device, a sintering device and a machining device to obtain ferrite magnet products, which can reduce the occurrence of defects such as cracks and bubbles in the production process and improve the quality and pass rate of the products.

[0120] It should be noted that the above description of process 200 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and variations to process 200 under the guidance of this specification. However, such modifications and variations are still within the scope of this specification.

[0121] Figure 4 is an exemplary schematic diagram of a target billet moisture content prediction model according to some embodiments of this specification.

[0122] In some embodiments, the processor may predict the target billet moisture content using a target billet moisture content prediction model based on the grinding particle size and the raw material composition.

[0123] The target billet moisture content prediction model may be a machine learning model for predicting the target billet moisture content. For example, the target billet moisture content prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, or any combination thereof.

[0124] In some embodiments, the inputs to the target billet moisture content prediction model 440 may include grind size 410 and raw material composition 420 .

[0125] The grinding particle size refers to the particle size of the third raw material. For example, the grinding particle size can be that the particle diameter of the third raw material is a millimeters.

[0126] In some embodiments, the processor can obtain the grinding particle size in various ways. For example, the processor can determine the grinding particle size based on relevant grinding parameters of the grinding device. In another example, the processor can randomly sample the third raw material processed by the grinding device and obtain the grinding particle size through experimental measurement.

[0127] The raw material composition refers to the types and proportions of the raw materials contained in the third raw material. For example, the raw material composition may be that the third raw material contains ferric oxide, manganese tetraoxide and zinc oxide, and m 三氧化二铁 :m 四氧化三锰 :m 氧化锌 =d:e:f.

[0128] In some embodiments, the processor can determine the raw material composition in a variety of ways. For example, the processor can determine the raw material composition based on the types and proportions of the raw materials input into the mixing device.

[0129] In some embodiments, the input of the target billet moisture content prediction model 440 may further include target sintering parameters 430. For more information about the target sintering parameters, please refer to step 260 and its related description.

[0130] In some embodiments of the present invention, target sintering parameters are used as inputs of a target billet moisture content prediction model, and the influence of factors such as temperature during the sintering process is taken into account, so that the target billet moisture content predicted by the target billet moisture content prediction model is more accurate.

[0131] In some embodiments, the output of the target billet moisture content prediction model 440 may include a target billet moisture content 450. For more information about the target billet moisture content, please refer to step 250 and its related description.

[0132] In some embodiments, the target billet moisture content prediction model 440 can be trained using multiple second training samples 470 with second labels. For example, multiple second training data with second labels can be input into the initial target billet moisture content prediction model 460. A loss function is constructed using the second labels and the results of the initial target billet moisture content prediction model 460. The parameters of the initial target billet moisture content prediction model 460 are iteratively updated based on the loss function. When the loss function of the initial target billet moisture content prediction model 460 meets preset conditions, model training is completed, resulting in the trained target billet moisture content prediction model 440. The preset conditions may include convergence of the loss function, a threshold number of iterations, and the like.

[0133] In some embodiments, the second training samples 470 of the target billet moisture content prediction model 440 may include the milling particle size and raw material composition corresponding to the blank molds obtained by experienced blank molders; the second label may include the actual billet moisture content corresponding to each blank mold. The actual billet moisture content corresponding to each blank mold can be calculated by dividing the actual amount of water added by the actual billet weight.

[0134] In some embodiments, the second training sample 470 may further include target sintering parameters corresponding to the blank mold.

[0135] In some embodiments of the present specification, the target billet moisture content is predicted by a target billet moisture content prediction model, thereby improving the efficiency and accuracy of determining the target billet moisture content.

[0136] Figure 5 is an exemplary schematic diagram of an intake air flow prediction model according to some embodiments of this specification.

[0137] In some embodiments, the processor can predict the real-time intake flow rate of the inert gas based on the weight of the billet, raw material composition, target sintering parameters, real-time temperature, and degassing flow rate through an intake flow prediction model, and then dynamically adjust the intake flow rate of the inert gas based on the intake valve.

[0138] The intake air flow prediction model may be a machine learning model for predicting the intake air flow of the inert gas. For example, the intake air flow prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, or any combination thereof.

[0139] In some embodiments, the inputs of the inlet flow prediction model 560 may include the weight of the billet 510, the raw material composition 520, the target sintering parameters 530, the real-time temperature 540, and the degassing flow 550. The real-time temperature refers to the actual temperature in the sintering device. For more information about the raw material composition, please refer to Figure 4 For more information about the target sintering parameters, see step 260 and its related description. For more information about the weight of the blank, see step 250 and its related description. For more information about the degassing flow rate, see step 260 and its related description.

[0140] In some embodiments, the output of the intake air flow prediction model 560 may include an intake air flow of the inert gas 570. For more information about the intake air flow of the inert gas, please refer to step 260 and its related description.

[0141] In some embodiments, the intake air flow prediction model 560 can be trained using multiple third training samples 590 with third labels. For example, multiple third training data with third labels can be input into the initial intake air flow prediction model 580. A loss function is constructed using the third labels and the results of the initial intake air flow prediction model 580. The parameters of the initial intake air flow prediction model 580 are iteratively updated based on the loss function. When the loss function of the initial intake air flow prediction model 580 meets preset conditions, model training is completed, resulting in the trained intake air flow prediction model 560. The preset conditions may include convergence of the loss function, a threshold number of iterations, etc.

[0142] In some embodiments, the third training sample 590 of the intake flow prediction model 560 may include the weight, raw material composition, target sintering parameters, real-time temperature and degassing flow of the blank corresponding to the sintering sample with better product quality; the third label may include the actual intake flow of the inert gas corresponding to the sintering sample at the real-time temperature.

[0143] In some embodiments of the present specification, the intake flow rate of the inert gas is predicted by an intake flow rate prediction model, thereby improving the efficiency and accuracy of determining the intake flow rate of the inert gas.

[0144] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0145] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0146] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0147] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0148] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0149] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0150] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A ferrite magnet production control method, the method is executed based on a processor, characterized in that: include: conveying the raw materials in the raw material storage device to the raw material mixing device based on a conveyor belt; The raw materials are mixed by the raw material mixing device according to a preset ratio to obtain a first raw material; Pre-treating the first raw material using a pre-treating device to obtain a second raw material, wherein the pre-treating is a dry process or a wet process; Grinding the second raw material with a grinding device to obtain a third raw material, wherein the grinding device includes a stirring mechanism and a crushing mechanism, and the crushing mechanism is in conduction with the stirring mechanism; Performing a forming process on the third raw material using a forming device to form a blank; The forming device comprises a mixer, and the mixer is provided with a water adding device, and the water adding device is used to add water to the third raw material, and the amount of water added by the water adding device is determined based on the weight of the blank and the target blank moisture content; the target blank moisture content is determined based on the grinding particle size and the raw material composition, and is determined by a target blank moisture content prediction model, and the target blank moisture content prediction model is a machine learning model; The blank is sintered by a sintering device to form a primary product, wherein the sintering device is provided with a sintering controller, and the sintering controller is used to adjust sintering parameters during the sintering process; The sintering process includes sintering the blank based on target sintering parameters; The target sintering parameters are adjusted by the sintering controller; The target sintering parameters at least include a target heating rate, a target sintering temperature, a target holding time and a target cooling rate during sintering, and the target sintering parameters are determined based on a genetic algorithm, and the evaluation parameters in the genetic algorithm are related to the electricity cost of the solution; The primary product is machined by a machining device to form a ferrite magnet product.

2. The method according to claim 1, characterized in that The raw material mixing device includes a stirring blade, and the material and size of the stirring blade are determined based on the raw material; A buffer tank is provided between the stirring mechanism and the pulverizing mechanism, and the buffer tank is used for pre-buffering the second raw material after being stirred by the stirring mechanism, and a high-speed stirrer is provided in the buffer tank; The forming device comprises a blank mold mechanism, and the blank mold mechanism is used to select different blank templates to shape the third raw material to form blanks of different shapes and / or different sizes.

3. The method according to claim 2, characterized in that The molding process includes conveying the third raw material to the mixer, and shaping the third raw material after adding water based on the blank mold mechanism.

4. The method according to claim 1, characterized in that: include: The sintering process also includes adjusting the exhaust flow rate of the exhaust valve and the intake flow rate of the intake valve by the sintering controller, the exhaust flow rate includes the exhaust flow rate for releasing the gas in the sintering device, and the intake flow rate includes the intake flow rate for filling the inert gas into the sintering device.

5. A ferrite magnet production control system, characterized in that: include: A conveying module, used for conveying the raw materials in the raw material storage device to the raw material mixing device based on a conveyor belt; A mixing module, used for mixing the raw materials according to a preset ratio based on the raw material mixing device to obtain a first raw material; A pretreatment module, used for pretreatment of the first raw material based on a pretreatment device to obtain a second raw material, wherein the pretreatment is a dry treatment or a wet treatment; A grinding module, used for grinding the second raw material based on a grinding device to obtain a third raw material, wherein the grinding device includes a stirring mechanism and a crushing mechanism, and the crushing mechanism is connected to the stirring mechanism; A forming module, used for forming the third raw material based on the forming device to form a blank; The forming device comprises a mixer, and the mixer is provided with a water adding device, and the water adding device is used to add water to the third raw material, and the amount of water added by the water adding device is determined based on the weight of the blank and the target blank moisture content; the target blank moisture content is determined based on the grinding particle size and the raw material composition, and is determined by a target blank moisture content prediction model, and the target blank moisture content prediction model is a machine learning model; A sintering module, used for sintering the blank based on a sintering device to form a primary product, wherein the sintering device is equipped with a sintering controller, and the sintering controller is used for adjusting sintering parameters during the sintering process; The sintering process includes sintering the blank based on target sintering parameters; The target sintering parameters are adjusted by the sintering controller; The target sintering parameters at least include a target heating rate, a target sintering temperature, a target holding time and a target cooling rate during sintering, and the target sintering parameters are determined based on a genetic algorithm, and the evaluation parameters in the genetic algorithm are related to the electricity cost of the solution; The processing module is used to perform mechanical processing on the primary product based on a mechanical processing device to form a ferrite magnet product.

6. The system according to claim 5, characterized in that The raw material mixing device includes a stirring blade, and the material and size of the stirring blade are determined based on the raw material; A buffer tank is provided between the stirring mechanism and the pulverizing mechanism, and the buffer tank is used for pre-buffering the second raw material after being stirred by the stirring mechanism, and a high-speed stirrer is provided in the buffer tank; The forming device comprises a blank mold mechanism, and the blank mold mechanism is used to select different blank templates to shape the third raw material to form blanks of different shapes and / or different sizes.

7. A ferrite magnet production control device, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 4.

Images