Zirconium oxide powder production device, method, system and medium

Abstract

The embodiments of this specification provide a zirconia powder production device, method, system, and medium. The device includes a batcher for batching raw materials based on the production raw material ratio to obtain the production raw materials of zirconia powder; a reactor including a first container and a second container, wherein the first volume of the first container meets the volume range condition and the second volume of the second container is greater than a preset volume threshold, and the reactor is used to process the production raw materials in the first container and the second container in sequence to obtain a reaction slurry; a filter press washer for performing filter press washing on the reaction slurry to obtain a slurry cake that meets the first preset condition; a calciner for calcining the slurry cake to obtain a precursor powder; a pulverizer for pulverizing the precursor powder to obtain zirconia powder; and a processor for determining the production raw material ratio of zirconia powder based on the finished product requirement parameters of the zirconia powder and sending it to the batcher.

Description

Technical Field

[0001] This specification relates to the field of intelligent production, and in particular to a zirconium oxide powder production device, method, system and medium. Background Art

[0002] Zirconia ceramics, as a new type of ceramic material, possess many excellent physical and chemical properties. For example, they exhibit high toughness, high flexural strength, high wear resistance, and excellent thermal insulation. Therefore, they are widely used in thermal barrier coatings, catalyst supports, medical and healthcare applications, refractories, textiles, and other fields. Zirconia ceramics are generally produced by forming zirconia powder. Current zirconia powder production equipment involves production parameters such as various material ratios, temperature, and time. However, controlling the inflow rate of the production raw materials during the reaction makes it difficult to ensure a sufficient reaction.

[0003] Therefore, it is necessary to provide a zirconium oxide powder production device, method, system and medium to control the flow rate of raw materials in the reaction process when the finished product requirements are different, so that the reaction in the reactor can proceed fully and the quality of the produced zirconium oxide powder can be guaranteed. Summary of the Invention

[0004] One of the embodiments of the present specification provides a zirconium oxide powder production device, which includes: a batcher for batching based on the ratio of production raw materials to obtain the production raw materials of zirconium oxide powder; a reactor including a first container and a second container, the first volume of the first container meets the volume range condition, and the second volume of the second container is greater than a preset volume threshold, and is used to process the production raw materials in the first container and the second container in sequence to obtain a reaction slurry; a filter press washer for filter pressing and washing the reaction slurry to obtain a slurry cake that meets the first preset condition; a calciner for calcining the slurry cake to obtain a precursor powder; a pulverizer for pulverizing the precursor powder to obtain the zirconium oxide powder; and a processor for determining the production raw material ratio of the zirconium oxide powder based on the finished product requirement parameters of the zirconium oxide powder and sending it to the batcher.

[0005] One of the embodiments of this specification provides a method for producing zirconium oxide powder, which is applied to the processor in the zirconium oxide powder production device described in the above embodiment. The method includes: determining the production raw material ratio of the zirconium oxide powder based on the finished product requirement parameters of the zirconium oxide powder and sending it to the batcher; controlling the batcher to batch based on the production raw material ratio to obtain the production raw material of the zirconium oxide powder; controlling the first container and the second container in the reactor to process the production raw material in sequence to obtain a reaction slurry; controlling the filter press washer to filter press wash the reaction slurry to obtain a slurry cake that meets the first preset condition; controlling the calciner to calcine the slurry cake to obtain a precursor powder; controlling the pulverizer to pulverize the precursor powder to obtain the zirconium oxide powder.

[0006] One of the embodiments of the present specification provides a zirconium oxide powder production system, which includes: a determination module, which is used to determine the production raw material ratio of the zirconium oxide powder based on the finished product requirement parameters of the zirconium oxide powder and send it to a batcher; a first control module, which is used to control the batcher to batch the raw materials based on the production raw material ratio to obtain the production raw materials of the zirconium oxide powder; a second control module, which is used to control the first container and the second container in the reactor to process the production raw materials in sequence to obtain a reaction slurry; a third control module, which is used to control the filter press washer to filter press wash the reaction slurry to obtain a slurry cake that meets the first preset condition; a fourth control module, which is used to control the calciner to calcine the slurry cake to obtain a precursor powder; and a fifth control module, which is used to control the crusher to crush the precursor powder to obtain the zirconium oxide powder.

[0007] One of the embodiments of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the zirconium oxide powder production method as 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 a schematic diagram of a zirconium oxide powder production device according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for producing zirconium oxide powder according to some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of a second prediction model according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart of another method for producing zirconium oxide powder according to some embodiments of this specification;

[0013] Figure 5 is an exemplary flow chart for determining a target flow rate according to some embodiments of this specification;

[0014] Figure 6 is another exemplary flow chart for determining a target flow rate according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] Figure 1 It is a schematic diagram of a zirconium oxide powder production device according to some embodiments of this specification.

[0020] like Figure 1As shown, the zirconium oxide powder production apparatus 100 may include a processor 110 , a batcher 120 , a reactor 130 , a filter press washer 140 , a calciner 150 , and a pulverizer 160 .

[0021] The processor 110 can be used to obtain information and analyze and process the collected information to perform one or more functions described in this specification. In some embodiments, the processor 110 can also be used to determine the raw material ratio of the zirconium oxide powder based on the finished product parameters of the zirconium oxide powder and send it to the batcher. For detailed description, see Figure 2 In some embodiments, the processor 110 may also control the batcher 120, the reactor 130, the filter press washer 140, the calciner 150, and the pulverizer 160 to execute the corresponding zirconium oxide powder production process. For example, the processor 110 may control the batcher 120 to batch the raw materials based on the production ratio. For another example, the processor 110 may control the filter press washer 140 to perform filter press washing on the reaction slurry. For more information on the processor controlling the relevant devices to execute the zirconium oxide powder production process, see Figure 2 The relevant part of .

[0022] The batcher 120 may be a device used to prepare the raw materials needed to produce zirconium oxide powder. In some embodiments, the batcher 120 may prepare the raw materials based on a raw material ratio to produce the raw materials for zirconium oxide powder. For example, the batcher 120 may obtain the raw materials from a raw material bin based on the raw material ratio and add the raw materials to the reactor for processing.

[0023] The reactor 130 may refer to a device for processing production raw materials to obtain reaction slurry. In some embodiments, the reactor 130 may be connected to the batcher 120 and process the production raw materials obtained from the batcher 120 to obtain reaction slurry. For example, the reactor may mix and react zirconium oxychloride solution and yttrium trioxide solution obtained from the batcher at a certain concentration ratio to obtain reaction slurry. Figure 1 As shown, the reactor 130 may include a first container 134 and a second container 136 .

[0024] The first container 134 can be used to stir the production raw materials in batches, so that after the raw materials are fully reacted, the initial reaction slurry is flowed into the second container 136. For example, the production raw materials, i.e., zirconium oxychloride solution, yttrium trioxide solution, and other additives, can be obtained in five batches. The first container 134 can stir the zirconium oxychloride solution, yttrium trioxide solution, and other additives, and after the raw materials are evenly mixed, the initial reaction slurry is flowed into the second container 136.

[0025] The second container 136 can be used to stir the initial reaction slurry obtained in each batch in the first container again to mix them evenly to generate reaction slurry, which flows into the filter press washer 140 for filter press washing.

[0026] In some embodiments, the volume of the first container may be a first volume that satisfies a volume range condition. In some embodiments, the volume of the second container may be a second volume that is greater than a preset volume threshold. For more information on the first volume, the second volume, the volume range condition, and the preset volume threshold, see Figure 2 It should be understood that the smaller volume of the first container facilitates stirring of this portion of the production materials, obtaining a fully reacted initial reaction slurry that then flows into the larger second container for uniform mixing. This ensures that the production materials are fully reacted in the first container, saving production resources while improving production efficiency.

[0027] In some embodiments, the reactor 130 may further include a flow control valve 132. The flow control valve 132 may be used to control the flow rate at which the feedstock is added from the batcher 120 to the reactor 130. For example, the flow control valve 132 may control the flow rate at which the feedstock is added to the first container 134 to be 0.7 cubic meters per second.

[0028] The process of processing the production raw materials to obtain the reaction slurry in the reactor 130 can be controlled by the processor 110. For example, the processor 110 can control parameters such as the temperature and pressure of the reaction in the reactor 130. For another example, the processor 110 can control the volume of the first container in the reactor 130.

[0029] The filter press washer 140 may refer to a device for filter press washing the reaction slurry. In some embodiments, the filter press washer 140 may be connected to the reactor 130 and filter press wash the reaction slurry obtained in the reactor 130 to obtain a slurry cake. For example, the filter press washer may filter press wash the solution containing substances such as hydroxide, water, and chloride ions obtained by the reaction in the reactor to obtain a zirconium oxide slurry cake. The process of filter press washing the reaction slurry by the filter press washer 140 may be controlled by the processor 110. For example, the processor 110 may control the pressure, number of filter presses, etc. of the filter press washer 140.

[0030] The calciner 150 may be a device for drying and calcining the slurry cake. In some embodiments, the calciner 150 may be connected to the filter press washer 140 and dry and calcine the slurry cake obtained in the filter press washer 140 to produce a precursor powder. For example, the calciner 150 may calcine the zirconium oxide slurry cake obtained in the filter press washer 140 into zirconium oxide powder of a certain dryness. The calcination process of the slurry cake in the calciner 150 may be controlled by the processor 110. For example, the processor 110 may control the temperature of the calciner 150, the calcination time, and other aspects.

[0031] The pulverizer 160 may refer to a device for pulverizing precursor powder. In some embodiments, the pulverizer 160 may be connected to the calciner 150 and pulverize the precursor powder obtained in the calciner 150. For example, the pulverizer 160 may pulverize the zirconia powder obtained by the calciner 150 into particles of a predetermined size. The pulverization of the precursor powder by the pulverizer 160 may be controlled by the processor 110. For example, the processor 110 may control the pulverization pressure, operating time, and other parameters of the pulverizer 160.

[0032] It should be noted that the schematic diagram of the zirconia powder production apparatus 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art will readily appreciate that various modifications and variations can be made based on the description of this specification. For example, the zirconia powder production apparatus 100 may further include a network. For another example, the zirconia powder production apparatus 100 may be implemented on other devices to achieve similar or different functions. However, such modifications and variations do not deviate from the scope of this specification.

[0033] Figure 2 is an exemplary flow chart of a method for producing zirconium oxide powder 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:

[0034] Step 210: Based on the parameters required for the finished product of the zirconium oxide powder, the raw material ratio for producing the zirconium oxide powder is determined and sent to a batcher.

[0035] Finished product requirement parameters refer to the quality requirements for the finished zirconia powder. For example, finished product requirement parameters for zirconia powder may include at least one of the required finished product quantity, chemical composition, particle size, particle size distribution, specific surface area, residual water content, and the transmittance of the zirconia powder product. The transmittance of the zirconia powder product refers to the transmittance of the product (e.g., etching material) made from the zirconia powder, and the finished product quantity requirement refers to the quantity of finished zirconia powder to be produced (e.g., one ton). The finished product requirement parameters may be based on the actual application of the zirconia powder product, with different application requirements resulting in different finished product parameters. For example, zirconia powder used as structural ceramics has high particle size requirements, while zirconia powder used as etching material requires the resulting product to have good transmittance. In some embodiments, the finished product requirement parameters can be determined in a variety of ways. For example, they can be pre-set by the user. In another example, the actual application of the zirconia powder product required for production can be input by the user, and the corresponding finished product requirement parameters can be determined using a preset correspondence table.

[0036] Raw materials refer to the raw materials and additives used to produce zirconium oxide powder. For example, these materials may include, but are not limited to, zirconium oxychloride solution, yttrium trichloride solution, organic acids, aqueous ammonia solution, colorants, and adhesives. The raw material ratio refers to the proportion of the various raw materials used to produce zirconium oxide powder. For example, the raw material ratio might be a 3:2 ratio of zirconium oxychloride solution to yttrium trichloride solution. Another example might be the ratio of zirconium oxychloride solution to yttrium trioxide solution and other additives.

[0037] In some embodiments, the raw material ratio also includes the required amount of each raw material, such as the required amount of zirconium oxychloride solution or yttrium trichloride solution. The required amount refers to the amount of raw material required to produce a certain amount of finished zirconium oxide powder. In some embodiments, the required amount of raw materials can be determined based on the finished product required amount in the zirconium oxide powder finished product requirement parameters. In some embodiments, the raw material ratio can also include the concentration of the raw material solution, such as the concentration of the zirconium oxychloride solution, the concentration of the yttrium trioxide solution, the concentration of the organic acid, the concentration of the ammonia solution, etc.

[0038] In some embodiments, the processor can determine the raw material ratio for zirconia powder production based on the finished product parameters required by the zirconia powder through various methods. In some embodiments, the processor can identify historical production data with finished product test parameters that are identical or similar to the finished product test parameters, and determine the raw material ratio corresponding to the historical production data as the raw material ratio corresponding to the finished product test parameters. The historical production data can be publicly available production data from multiple companies, research institutions, etc. The finished product test parameters can include at least one of the actual chemical composition, particle size, particle size distribution, specific surface area, residual water content, and transmittance of the zirconia powder produced.

[0039] In some embodiments, the processor may send the determined production raw material ratio to the batcher in a variety of ways. For example, the processor may send the determined production raw material ratio to the batcher via one or more ways such as a network, Bluetooth, or a serial interface.

[0040] Step 220: Control the batcher to batch the raw materials based on the raw material ratio to obtain the raw materials for the production of zirconium oxide powder.

[0041] In some embodiments, the processor can control the batcher to obtain raw materials, additives, etc. of corresponding proportions and volumes (contents) from the corresponding raw material bin based on the production raw material ratio to obtain the production raw materials of zirconium oxide powder.

[0042] Step 230: Control the first container and the second container in the reactor to process the production raw materials in sequence to obtain reaction slurry.

[0043] Reaction slurry refers to the initial reaction slurry formed after the production raw materials react and mix. For example, the reaction slurry can be a solution containing hydroxide, water, chloride ions, etc., formed after the zirconium oxychloride solution and yttrium trioxide solution are fully reacted and mixed.

[0044] In some embodiments, the processor can also control the production raw materials prepared by the batcher to flow into the reaction vessel at a target flow rate for processing to obtain a reaction slurry. In some embodiments, the processor can also be used to determine the target flow rate of the production raw materials entering the reactor and send them to the reactor. For more information about the above embodiments, please refer to Figure 3 and its related descriptions.

[0045] In some embodiments, the processor can control the first container to process the production raw materials so that the production raw materials can be mixed and fully reacted to generate an initial reaction slurry. The first container can have a first volume, and the first volume satisfies a volume range condition. The volume range condition can be a pre-set volume range of the first container. For example, the volume range condition can be 0.05 to 0.2 cubic meters. In some embodiments, the processor can determine the volume range condition based on historical production data. For example, the volume range condition is determined based on the first volume in historical production data with the same finished product requirement parameters.

[0046] In some embodiments, the processor can control the operating parameters of the first container based on the raw material ratio. These operating parameters may include, but are not limited to, heating temperature and reaction time. In some embodiments, the processor can retrieve corresponding reaction parameters from a memory or other database based on the raw materials and their ratios, and use them as the operating parameters of the first container.

[0047] In some embodiments, the processor may determine the volume of the production raw material added to the first container at each time based on the first volume of the first container. For example, the volume of the production raw material added to the first container at each time is the first volume. The processor may sequentially stir each of the multiple portions of production raw material to ensure that the production raw material in the first container fully reacts, generating multiple portions of initial reaction slurry, which are then flowed into the second container.

[0048] In some embodiments, the processor may further adjust the first volume of the first container to obtain an adjusted first container. The volume of the adjusted first container may be a target first volume, which also satisfies the volume range condition. The target first volume refers to the first volume that can fully react with each portion of the current production raw material. For example, if the first volume of the first container before adjustment is 0.05 square meters, the target first volume of the first container after adjustment may be 0.1 cubic meter, both of which satisfy the volume range condition of 0.05 to 0.2 cubic meters.

[0049] Before producing zirconium oxide powder, the processor can adjust the first volume of the first container to ensure both the production quality and production efficiency of the raw materials after the adjustment. If the first volume is too small, the first container can only process a small amount of raw materials at a time, resulting in slow production speed. If the first volume is too large, the first container can only process a large amount of raw materials at a time, which may lead to insufficient stirring, incomplete reaction, and reduced production quality.

[0050] The processor can process the finished product requirement parameters and the production raw material ratio through the second prediction model to determine the target first volume and the target flow rate. The second prediction model is a machine learning model.

[0051] like Figure 3 As shown, the processor may use the target first volume 310 and the target flow rate 320 as inputs to the second prediction model, and the finished product requirement parameters 340 and the production raw material ratio 350 as outputs of the second prediction model. The second prediction model 330 may include any one or a combination of deep neural network models (DNN), recurrent neural network models (RNN), convolutional neural network models (CNN), or other custom model structures.

[0052] It is worth noting that, in actual production, the flow rate of raw materials flowing into the reactor is difficult to obtain. Therefore, using flow rate as a label to train the second prediction model is not feasible. Furthermore, the required parameters for the finished product and the raw material ratio can be manually controlled. Therefore, by constructing the second prediction model 330, the target first volume and target flow rate can be determined through reverse solution.

[0053] In some embodiments, the second prediction model 330 can be acquired based on training. The training of the second prediction model 330 can be performed by a processor. In some embodiments, when training the second prediction model 330, a plurality of labeled training samples can be used, and training can be performed by a variety of methods (e.g., gradient descent method) so that the parameters of the model can be learned. When the trained model meets the preset conditions, the training ends and the trained second prediction model 330 is obtained. In some embodiments, the finished product inspection parameters and the production raw material ratio in the historical production data can be used as training labels, and the flow rate and the first volume of the production raw materials flowing into the first container in the historical production data can be used as training data to train the initial second prediction model 330. The training labels can be obtained by manual measurement.

[0054] Based on the trained second prediction model, a correspondence between the flow rate, the first volume, and the finished product test parameters and the raw material ratio can be obtained. In some embodiments, when the zirconia powder production apparatus is actually used, after the required finished product parameters and the raw material ratio are determined, the target first volume and target flow rate for zirconia powder production that meet the current finished product parameters can be determined based on the aforementioned correspondence.

[0055] Some embodiments of this specification employ a reverse-engineering model construction approach, utilizing readily available finished product parameters and raw material ratios as labels. The model is trained using the first volume and the flow rate of the raw materials flowing into the first container as training samples, enabling the model to learn the corresponding relationship between the data. During model application, the corresponding target flow rate and target first volume are determined based on this correspondence and the readily available finished product parameters and raw material ratios. This addresses the difficulty in obtaining training labels when using flow rates as training labels for training a second prediction model.

[0056] In some embodiments of this specification, by adjusting the volume of the first container, an appropriate first volume corresponding to the current finished product parameters and raw material ratio can be obtained, ensuring that the raw materials can fully react within the first container at a faster rate, thereby improving the quality and efficiency of zirconia powder production. Furthermore, by determining the target first volume and target flow rate through a machine learning model, the self-learning capabilities of the machine learning model can be leveraged to identify patterns within large amounts of historical production data and process the current finished product parameters and raw material ratios, thereby improving processing efficiency and accuracy.

[0057] In some embodiments, the processor can control the initial reaction slurry generated by multiple treatments in the first container to flow into the second container for full reaction to generate a reaction slurry. In some embodiments, the processor can control the operating parameters of the second container based on the concentration, viscosity, etc. of the initial reaction slurry. The concentration and viscosity of the initial reaction slurry can be detected by a concentration detector, viscosity detector, etc. and sent to the processor. In some embodiments, the processor can determine the operating parameters of the second container based on the concentration, viscosity, etc. of the initial reaction slurry using a preset correspondence table.

[0058] Step 240: Control the filter press washer to repeatedly filter and wash the reaction slurry until the first preset condition is met to obtain a slurry cake.

[0059] The first preset condition may refer to a pre-set condition for the filter press washer to stop filtering and washing. In some embodiments, the first preset condition may be any one or a combination of the following: the chloride ion concentration in the filtrate after filter press washing reaches a preset standard (e.g., the chloride ion content in the filtrate is less than 0.005%), the filter press washing times of the filter press washer reaches a target filter press washing times, etc. For more information on the target filter press washing times, see Figure 6 and its related descriptions.

[0060] The slurry cake refers to the filter cake obtained after the reaction slurry is subjected to filter pressing and washing. For example, the slurry cake can be the filter cake obtained after the reaction slurry is subjected to at least one round of washing and filter pressing to remove a certain amount of water.

[0061] In some embodiments, the processor can control the filter press washer to repeatedly filter-wash the reaction slurry, and test the chloride ion concentration of the filtrate from each round of filter pressing until the detected chloride ion concentration meets a first preset condition, thereby obtaining a slurry cake. When the chloride ion content in the filtrate meets the first preset condition, the processor controls the filter press washer to stop operating.

[0062] Step 250: Control the calciner to calcine the slurry cake to obtain a precursor powder.

[0063] Precursor powder refers to a slurry cake that has been calcined to a specified dryness. This dryness refers to the moisture content of the slurry cake being below a certain range, which can be industry standards or determined empirically. For example, a precursor powder can be a slurry cake with a moisture content below 3% after calcination.

[0064] In some embodiments, the processor may determine operating parameters of a calciner based on the dryness standard of the precursor powder, the moisture content of the slurry cake, etc., to calcine the slurry cake to obtain the precursor powder. For example, the processor may determine the calcination temperature and duration of the calciner based on the dryness standard of the precursor powder and the moisture content of the slurry cake.

[0065] Step 260: Control the pulverizer to pulverize the precursor powder to obtain zirconium oxide powder.

[0066] In some embodiments, the processor can control a pulverizer to pulverize the precursor powder based on the required parameters of the finished product to obtain the desired zirconium oxide powder. For example, based on the particle size and particle size distribution in the required parameters of the finished product, the processor can control the pulverizer to stop when the pulverized particle size reaches the required size, thereby obtaining the desired zirconium oxide powder. For another example, the processor can determine the type and amount of chemical substances (such as manganese dioxide, iron oxide, etc. and the corresponding amount) that need to be added during pulverization based on the particle size and particle size distribution in the required parameters of the finished product.

[0067] In some embodiments of this specification, based on the finished product requirements and the ratio of production raw materials, the production raw material flow rate, first volume and other parameters of zirconia powder production are accurately determined, which can achieve precise control of each link of zirconia powder production, so that the produced zirconia powder meets the finished product requirements, while improving production efficiency and production quality.

[0068] Figure 4 FIG4 is an exemplary flow chart of another method for producing zirconium oxide powder according to some embodiments of this specification. In some embodiments, process 400 may be executed by processor 110. Figure 4 As shown, process 400 includes the following steps:

[0069] Step 410: determine the target flow rate of the production raw materials into the reactor and send them to the reactor.

[0070] The target flow rate may refer to the speed at which the raw materials flow into the reactor during the current zirconium oxide powder production. Further, the target flow rate may refer to the speed at which the raw materials flow into the first container of the reactor during the current zirconium oxide powder production.

[0071] In some embodiments, the target flow rate can be determined in a variety of ways. For example, the target flow rate can be manually set to 0.7 cubic meters per second.

[0072] In some embodiments, the processor may further process the finished product requirement parameters, the production raw material ratio, and the first volume based on the first prediction model to determine the target flow rate.

[0073] The first prediction model input includes the flow rate of the production raw materials into the reactor, and the output is the first volume, the production raw materials ratio, and the required parameters of the finished product. The first prediction model can include any one or a combination of a deep neural network model, a convolutional neural network model, or other custom model structures.

[0074] In some embodiments, the first prediction model can be trained and acquired based on reverse solution. The training sample can be the flow rate of the production raw materials flowing into the first container in the historical production data, and the training label can be the volume of the first container, the production raw material ratio, and the finished product requirement parameters in the historical production data. The training of the first prediction model can be performed by a processor. In some embodiments, when training the first prediction model, multiple labeled training samples can be used, and training can be performed through multiple methods (for example, gradient descent method) to learn the parameters of the model. When the trained model meets the preset conditions, the training ends and the trained first prediction model is obtained.

[0075] Based on the trained first prediction model, a correspondence between the target flow rate and the finished product's required parameters, the first volume, and the raw material ratio can be obtained. In some embodiments, the target flow rate can be determined based on the finished product's required parameters, the first volume, the raw material ratio, and the aforementioned correspondence. For example, after obtaining the raw material ratio, the finished product's required parameters, and the first volume, the required target flow rate can be determined based on the aforementioned correspondence.

[0076] It should be understood that there is a corresponding relationship between the flow rate of the production raw materials flowing into the first container and the finished product required parameters, the production raw material ratio and the first volume. Among them, the finished product required parameters can be manually pre-set based on production needs, so that the production raw material ratio and the first volume can be determined. However, the flow rate of the production raw materials flowing into the reactor is difficult to accurately control. Therefore, some embodiments of the present invention can use a first prediction model to determine the corresponding relationship between the target flow rate and the finished product required parameters, the first volume, and the production raw material ratio. Using the finished product required parameters, the production raw material ratio and the first volume as labels can avoid the problem that when the flow rate of the production raw materials flowing into the reactor is used as a label, the label is not easy to obtain and the model is difficult to train.

[0077] Some embodiments of the present specification can determine the target flow rate into the first container through a first prediction model, and can use the self-learning ability of the machine learning model to find patterns in a large amount of historical production data, process the current finished product requirement parameters and production raw material ratios, and improve processing efficiency and accuracy.

[0078] In some embodiments, the processor may further adjust the volume of the first container to obtain a first container with a target first volume. For more information about the target first volume, see Figure 2 When the volume of the first container changes, the target flow rate may also change accordingly. In some embodiments, the processor may also determine the target first volume and the corresponding target flow rate in a variety of ways.

[0079] In some embodiments, the processor can also process the finished product requirement parameters and the production raw material ratio through a second prediction model to determine the target first volume and the target flow rate. The second prediction model is a machine learning model. For more information about the above embodiments, see Figure 2 and its related descriptions.

[0080] In some embodiments, the processor may further obtain multiple initial production plans, each of which includes an initial first volume, an initial flow rate, and an initial number of filter press washes; perform at least one round of iterative updates on the multiple initial production plans based on a preset algorithm until preset conditions are met, thereby obtaining a target production plan, which includes a target first volume, a target flow rate, and a target number of filter press washes. For more information on the above embodiments, see Figure 6 and its related descriptions.

[0081] In step 420 , the production raw materials are controlled to enter the first container at a target flow rate through the flow control valve in the reactor.

[0082] The processor can control the flow control valve in the reactor so that the production raw materials can enter the first container at a target flow rate.

[0083] In some embodiments of this specification, a flow control valve is used to control the production raw materials to flow into the reactor at an appropriate speed, so that the zirconium oxide powder production device can adapt to different finished product requirements, improve production efficiency, and ensure production quality.

[0084] Figure 5 FIG. 5 is an exemplary flow chart of determining a target flow rate according to some embodiments of the present specification. In some embodiments, process 500 may be executed by a processor. Figure 5 As shown, process 500 includes the following steps:

[0085] Step 510: construct an initial feature vector based on the finished product requirement parameters and the production raw material ratio.

[0086] An initial feature vector is a vector that reflects the current required parameters for the finished product and the raw material ratio. For example, the initial feature vector can reflect information such as the chemical composition, particle size, particle size distribution, specific surface area, residual water content, and the transmittance of the zirconia product. It can also reflect information such as the type, required amount, concentration, and ratio of the various raw materials in the production process.

[0087] In some embodiments, the processor may preset a value for each of the multiple pieces of information and / or data in the current finished product requirement parameters and the production raw material ratio, and construct the initial feature vector based on the preset values. In some embodiments, the processor may construct the initial feature vector based on the actual values ​​of the multiple pieces of information and / or data in the current finished product requirement parameters and the production raw material ratio. For example, the initial eigenvector can be expressed as (((a1,a2,a3,……),b,c,d,e,f),((A1,A2,A3,),(B1,B2,B3,B4),(C1,C2,C3,C4),……)), where ((a1,a2,a3,……),b,c,d,e,f) represent the required parameters of the current finished product, (a1,a2,a3,……) represent the content of each component in the chemical composition, b,c,d,e,f represent the particle size, particle size distribution, specific surface area, residual water content, and transmittance of the zirconia powder product, respectively; ((A1,A2,A3,A4),(B1,B2,B3,B4),(C1,C2,C3,C4),……) represent the type, demand, concentration, and proportion information corresponding to Class A production raw materials, Class B production raw materials, and Class C production raw materials, respectively.

[0088] Step 520, determine the vector distance between the initial feature vector and each of the candidate reference feature vectors in the vector database, where the vector database includes multiple candidate reference feature vectors, each of the multiple candidate reference feature vectors is constructed based on a set of historical finished product detection parameters in historical zirconia powder production data and its corresponding historical production raw material ratio.

[0089] A candidate reference feature vector is a vector that reflects the finished product test parameters and raw material ratio information corresponding to historical production data. For example, a candidate feature vector can reflect information such as the chemical composition, particle size, particle size distribution, specific surface area, residual water content, and transmittance of the finished zirconia powder corresponding to a set of historical zirconia powder production data, as well as information such as the type, required quantity, concentration, and ratio of the raw materials used to produce the zirconia powder.

[0090] A vector database refers to a database consisting of multiple candidate reference feature vectors.

[0091] In some embodiments, the processor may determine the vector distance between the initial feature vector and each of the candidate reference feature vectors using various methods, such as Euclidean distance, Manhattan distance, Chebyshev distance, angle cosine distance, etc.

[0092] Step 530: Determine the candidate reference feature vector whose vector distance meets the second preset condition as the reference feature vector.

[0093] The second preset condition refers to a condition that the vector distance between the preset initial feature vector and the candidate reference feature vector must meet. For example, the second preset condition may be one or a combination of the following: the Euclidean distance between the vectors is less than 0.02, the angle cosine distance is greater than 0.98, etc.

[0094] The reference feature vector refers to a vector in the candidate reference feature vectors that is similar to the initial feature vector.

[0095] In some embodiments, the processor may compare the vector distance between the initial feature vector and each candidate feature vector with a second preset condition, and determine the candidate reference feature vector whose vector distance satisfies the second preset condition as the reference feature vector. When the vector distance between the reference feature vector and the initial feature vector satisfies the second preset condition, it is characterized that the reference feature vector is similar to the initial feature vector, that is, the finished product inspection parameters of the zirconia powder product corresponding to the reference feature vector are similar to the finished product requirement parameters of the zirconia powder corresponding to the initial feature vector. For example, the vector database contains a total of 1,000 candidate reference feature vectors, of which 50 candidate reference feature vectors have vector distances with the initial feature vector that meet the second preset condition, then these 50 candidate reference feature vectors are determined as reference feature vectors.

[0096] Step 540: Determine a target flow rate for the production raw material to enter the first container based on each reference flow rate corresponding to the reference feature vector.

[0097] The reference flow rate refers to the flow rate in the historical production data of the zirconia powder corresponding to the reference feature vector. For example, if the flow rate in the historical production data of the zirconia powder corresponding to the reference feature vector is 0.1 cubic meter per second, then the reference flow rate is 0.1 cubic meter per second.

[0098] In some embodiments, the processor may determine a target flow rate for the production raw material entering the first container based on the reference flow rate corresponding to each reference feature vector using various methods. For example, when there is only one reference feature vector, the flow rate corresponding to that reference feature vector may be directly determined as the target flow rate. For another example, when there are multiple reference feature vectors, the target flow rate may be obtained by averaging the multiple reference flow rates corresponding to the multiple reference feature vectors.

[0099] In some embodiments of this specification, an initial feature vector is constructed, and based on the vector distance between the initial feature vector and a candidate reference feature vector, a reference feature vector that meets a first preset condition is determined. A target flow rate is then determined based on the reference flow rate corresponding to the reference feature vector. This approach allows parameters from historical zirconium oxide powder production data to be referenced to determine the target flow rate under conditions with equivalent finished product parameter requirements. This approach better meets actual production needs, makes the determined target flow rate more accurate, and improves production quality.

[0100] In some embodiments, the processor may determine the target first volume, the target flow rate, and the target number of filter press washes based on a preset algorithm.

[0101] Figure 6 FIG6 is another exemplary flow chart for determining a target flow rate according to some embodiments of the present specification. In some embodiments, process 600 may be executed by a processor. Figure 6 As shown, process 600 includes the following steps:

[0102] Step 610: Acquire multiple initial production plans, each of which includes an initial first volume, an initial flow rate, and an initial number of filter press washes.

[0103] The initial production plan refers to a pre-set preliminary plan for zirconium oxide powder production. The initial production plan may include initial parameters corresponding to each production process, such as the initial first volume of the first container, the initial flow rate, and the initial number of filter press washes. For example, the initial production plan may include an initial first volume of 0.05 cubic meters, an initial flow rate of 0.1 cubic meters per second, and an initial number of filter press washes of 10.

[0104] In some embodiments, the processor may obtain multiple initial production plans in various ways. For example, multiple initial production plans may be obtained based on historical production experience or a standard production parameter table. For example, parameters of various production processes may be obtained based on historical production experience or a standard production parameter table, and multiple initial production plans may be determined based on the aforementioned parameters. For example, multiple initial production plans may be manually set.

[0105] Step 620, based on the preset algorithm, perform at least one round of iterative update on the multiple initial production plans until the third preset condition is met, and obtain the target production plan, which includes the target first volume, the target flow rate and the target number of filter press washing times.

[0106] A preset algorithm is a preset algorithm used to iteratively update multiple initial production plans to obtain a target production plan. In some embodiments, the preset algorithm can be manually designed based on computational requirements. For example, the preset algorithm can be set based on the initial first volume, initial flow rate, and initial filter press wash times in the zirconium oxide powder production plan. In some embodiments, the preset algorithm can be implemented by the following method:

[0107] Step 1: The processor can construct a particle swarm containing N particles, and the dimension of each particle is D. Each particle can represent an initial production plan, and the size of N can be determined based on the number of initial production plans. For example, if there are 200 initial production plans, the value of N is 200. The particle dimension D represents the spatial dimension of the particle search, that is, the number of variables included in the initial production plan. In some embodiments, each initial production plan can be represented in the form of a vector, and the particle dimension D is the dimension of the vector, that is, the number of parameters in the initial production plan. For example, the initial production plan can be represented in the form of a vector, and the aforementioned vector can contain three elements, corresponding to the initial first volume, the initial flow rate, and the initial number of filter press washes, that is, the dimension of the vector is 3, and the corresponding particle dimension D is also 3.

[0108] In some embodiments, the processor may set the candidate production plan corresponding to the i-th particle to X id , X id =(X i1 , X i2 , X i3 ), X id Includes a candidate flow rate, a candidate first volume, and a candidate number of filter press washes. For example, X i1 represents the candidate flow rate, that is, the possible solution of the target flow rate, X i2 represents the candidate first volume, i.e., the possible solution of the target first volume, X i3 represents the candidate filter press washing times, that is, the possible solutions for the target filter press washing times.

[0109] In some embodiments, the processor may set the rate of change of the i-th particle to V id , V id =(V i1 ,,V i2 , V i3 ), represents the direction and size of particle movement. In some embodiments, the particle change rate V id represents the candidate production plan X of the i-th particle id The adjustment range is as follows: id and X id is a one-to-one correspondence. For example, V i1 Represents X i1 Adjustment range, V i2 Represents X i2 Adjustment range, V i3 Represents X i3 The adjustment range can refer to the magnitude of the update adjustment of each parameter in the candidate target solution, for example, V i1 The adjustment amplitude for each update can be +0.001 cubic meters per second.

[0110] Step 2: The processor can design an iterative formula based on preset algorithm parameters such as particle swarm size, particle dimension, number of iterations, inertia weight, learning factor, etc. In some embodiments, the iterative formula can be based on the particle change rate V id and the candidate production plan X of the i-th particle id Design the particle swarm change rate update formula and the candidate production plan update formula.

[0111] In some embodiments, the particle swarm change rate update formula can be designed as follows:

[0112]

[0113] Wherein, the particle dimension is N, i represents the serial number of the initial production plan, i = 1, 2, 3, ..., N; the particle dimension is D, d represents the serial number of the parameter in the initial production plan, d = 1, 2, 3, ..., D; k is the number of iterations; ω is the inertia weight; c1 is the individual learning factor; c2 is the group learning factor; r1 and r2 are random numbers in the interval [0, 1], which are used to increase the randomness of the search; represents the change magnitude vector of the dth dimension of the initial production plan i in the kth iteration, for example, It can represent the change amplitude vector of the first dimension of the initial production plan 2 in the kth iteration, i.e. the initial flow rate; represents the candidate production plan vector of dimension d for the initial production plan i in the kth iteration, for example, It can represent the first dimension of the initial production plan 2 in the kth iteration, that is, the vector of the initial flow rate; It represents the historical optimal position of the dth dimension of the initial production plan i in the kth iteration, that is, the optimal solution obtained by searching the i-th initial production plan after the kth iteration; It represents the historical optimal position of the swarm in the dth dimension in the kth iteration, that is, the optimal solution searched by the swarm after the kth iteration.

[0114] In some embodiments, the processor may determine an update formula for a candidate production solution as follows:

[0115]

[0116] Wherein, formula (2) indicates that the candidate production plan for the next iterative update can be determined by the current candidate production plan and the particle change rate for the next iterative update.

[0117] In some embodiments, the processor may perform at least one round of iterative updates on multiple initial production plans based on a preset algorithm until a third preset condition is satisfied, thereby obtaining a target production plan. For example, multiple initial production plans may be iteratively updated based on formula (2) to obtain a target production plan. The target production plan refers to a zirconium oxide powder production plan corresponding to the current finished product requirement parameters and production raw material ratio. The target production plan may include target production parameters corresponding to each production process, such as a target first volume, a target flow rate, and a target number of filter press washes.

[0118] The third preset condition refers to a condition that the particle fitness must meet during the iterative update process based on the preset algorithm. For example, the third preset condition may be that the particle fitness is less than a set value or reaches a maximum number of iterative updates. In some embodiments, the third preset condition can be manually set. For example, the third preset condition can be set based on computing experience, production experience, etc.

[0119] The particle fitness refers to the difference between the predicted parameters of the finished product, which are influenced by the flow rate, the first volume, and the number of filter presses, and the required parameters of the finished product. The predicted parameters are the predicted values ​​of the parameters of the finished product produced by zirconia powder. The predicted parameters may include at least one of the following: chemical composition, particle size, particle size distribution, specific surface area, residual water content, and transmittance of the zirconia product. In some embodiments, the particle fitness is also related to the power consumption during the filter press: the greater the power consumption during the filter press, the greater the particle fitness.

[0120] In some embodiments, the processor may evaluate the fitness of the particle by constructing a fitness function. For example, the fitness function may be expressed as:

[0121] G(x)=|AB|+C (3)

[0122] Among them, A represents the required parameters of the finished product, B represents the predicted parameters of the finished product, and C represents the power consumption of the filter press.

[0123] In some embodiments, the finished product prediction parameters can be determined based on a finished product parameter prediction model, which is a machine learning model. In some embodiments, the finished product parameter prediction model can process the candidate target flow rate, candidate first volume, and candidate filter press wash times in each round of iteratively updated candidate production plans to determine the finished product prediction parameters corresponding to each iteratively updated candidate production plan.

[0124] In some embodiments, the finished product parameter estimation model can be obtained through training. The training of the finished product parameter estimation model can be performed by a processor. In some embodiments, the processor can use multiple sets of historical zirconium oxide powder production data as training samples and the finished product detection parameters corresponding to the historical production data as labels to train the finished product parameter estimation model to obtain a trained finished product parameter estimation model. In some embodiments, the processor can train the finished product parameter estimation model using various methods (such as gradient descent).

[0125] In some embodiments, performing at least one round of iterative updates on the initial production plan may include updating the adjustment amplitude, and then updating the production plan based on the updated adjustment amplitude. For example, when the processor performs the second round of iteration, it first updates the production plan based on the adjustment amplitude obtained in the first round of iteration. The amplitude change vector is calculated by formula (1) Perform iterative updates to obtain the adjustment amplitude Based on the adjustment range And the candidate production plan obtained in the first round of iteration For candidate production plan vector Update to obtain candidate production solutions In this way, after at least one round of iterative updates, the third preset condition is met and the target production plan is obtained.

[0126] In some embodiments, after each round of iterative updates, the fitness of the particles can be evaluated based on a fitness function, and the particle with the lowest fitness can be selected as the current optimal solution for the next round of iterative updates. For example, the processor can iteratively update multiple initial production plans based on a preset algorithm, calculate the fitness of the particles after each round of iterative updates, and select the candidate production plan with the lowest fitness as the current optimal production plan for the next round of iterative updates.

[0127] In some embodiments, when the particle fitness satisfies a third preset condition, iteration is stopped, and the candidate production solution with the smallest fitness is determined as the target production solution. For example, when the third preset condition is reaching a maximum number of iterative updates, iteration is stopped when the maximum number of iterations is reached, and the candidate production solution with the smallest particle fitness is selected as the target production solution.

[0128] In some embodiments of this specification, a preset algorithm is used to iteratively update multiple initial production plans. A fitness function is then constructed to evaluate the fitness of the particles until a third preset condition is met. The particles with the lowest fitness are then selected as the target production plan. This approach allows for the rapid and accurate determination of a zirconia powder production plan that meets the desired parameters for the final product, improving the accuracy and feasibility of the production plan, reducing production power consumption, and increasing production efficiency.

[0129] It should be noted that the above descriptions of the various processes are for illustrative purposes only and do not limit the scope of application of this specification. Those skilled in the art may make various modifications and alterations to the various processes under the guidance of this specification. However, such modifications and alterations remain within the scope of this specification. For example, step 620 may include steps such as iteratively updating candidate production plans and determining a target production plan based on fitness.

[0130] Some embodiments of the present specification also provide a zirconium oxide powder production system, which includes: a determination module, used to determine the production raw material ratio of the zirconium oxide powder based on the finished product requirement parameters of the zirconium oxide powder and send it to a batcher; a first control module, used to control the batcher to batch the raw materials based on the production raw material ratio to obtain the production raw materials of the zirconium oxide powder; a second control module, used to control the first container and the second container in the reactor to process the production raw materials in sequence to obtain a reaction slurry; a third control module, used to control the filter press washer to filter press wash the reaction slurry to obtain a slurry cake that meets the first preset condition; a fourth control module, used to control the calciner to calcine the slurry cake to obtain a precursor powder; and a fifth control module, used to control the crusher to crush the precursor powder to obtain the zirconium oxide powder.

[0131] Some embodiments of this specification also provide a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the zirconium oxide powder production method described in any embodiment of this specification is implemented.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 zirconium oxide powder production device, characterized in that: The device comprises: A batcher, used to batch raw materials based on the production raw material ratio to obtain the production raw materials of zirconium oxide powder; A reactor comprising a first container and a second container, wherein a first volume of the first container satisfies a volume range condition and a second volume of the second container is greater than a preset volume threshold, and is configured to sequentially process the production raw materials in the first container and the second container to obtain a reaction slurry; A filter press washer, used for performing filter press washing on the reaction slurry to obtain a slurry cake that meets a first preset condition; a calciner, used to calcine the slurry cake to obtain a precursor powder; A pulverizer, used to pulverize the precursor powder to obtain the zirconium oxide powder; Processor for: Based on the finished product parameters of the zirconium oxide powder, determining the production raw material ratio of the zirconium oxide powder and sending it to the batcher; Determining a target flow rate of the production raw material into the reactor and sending the raw material to the reactor; Adjusting the first volume of the first container to obtain an adjusted first container, where the volume of the adjusted first container is a target first volume; The processor is further configured to: Obtaining a plurality of initial production plans, each of the plurality of initial production plans comprising an initial first volume, an initial flow rate, and an initial number of filter press washes; Based on a preset algorithm, the multiple initial production plans are iteratively updated for at least one round until a third preset condition is met to obtain a target production plan, wherein the target production plan includes the target first volume, the target flow rate, and the target number of filter press washes. The third preset condition includes that the particle fitness is less than a set value or reaches a maximum number of iterative updates, and the particle fitness is the difference between the predicted parameters of the finished product and the required parameters of the finished product.

2. The device according to claim 1, characterized in that The reactor further comprises a flow control valve, which is used to: The production raw material is controlled to enter the first container at the target flow rate.

3. The device according to claim 2, characterized in that The processor is further configured to: Constructing an initial feature vector based on the finished product requirement parameters and the production raw material ratio; determining a vector distance between the initial feature vector and each of candidate reference feature vectors in a vector database, the vector database including a plurality of candidate reference feature vectors, each of the plurality of candidate reference feature vectors being constructed based on a set of historical finished product detection parameters and corresponding historical production raw material ratios in historical zirconia powder production data; Determine the candidate reference feature vector whose vector distance satisfies a second preset condition as a reference feature vector; The target flow rate of the production raw material entering the reactor is determined based on each reference flow rate corresponding to the reference feature vector.

4. A control method for a zirconium oxide powder production device, characterized in that: The method is applied to a processor in a zirconium oxide powder production device according to any one of claims 1 to 3, and the method comprises: Based on the finished product parameters of the zirconium oxide powder, the raw material ratio of the zirconium oxide powder is determined and sent to the batcher; Controlling the batcher to batch the raw materials based on the raw material ratio to obtain the raw materials for the zirconium oxide powder; Determine the target flow rate of the production raw material into the reactor and send it to the reactor; Adjusting a first volume of a first container in the reactor to obtain an adjusted first container, wherein the volume of the adjusted first container is a target first volume; Controlling the first container and the second container to process the production raw materials in sequence to obtain reaction slurry; Controlling the filter press washer to perform filter press washing on the reaction slurry to obtain a slurry cake that meets a first preset condition; controlling a calciner to calcine the slurry cake to obtain a precursor powder; controlling a pulverizer to pulverize the precursor powder to obtain the zirconium oxide powder; The method further comprises: Obtaining a plurality of initial production plans, each of the plurality of initial production plans comprising an initial first volume, an initial flow rate, and an initial number of filter press washes; Based on a preset algorithm, the multiple initial production plans are iteratively updated for at least one round until a third preset condition is met to obtain a target production plan, wherein the target production plan includes the target first volume, the target flow rate, and the target number of filter press washes. The third preset condition includes that the particle fitness is less than a set value or reaches a maximum number of iterative updates, and the particle fitness is the difference between the predicted parameters of the finished product and the required parameters of the finished product.

5. The method according to claim 4, characterized in that The reactor further comprises a flow control valve, and the method further comprises: The flow control valve in the reactor controls the production raw material to enter the first container at the target flow rate.

6. The method according to claim 5, characterized in that The method further comprises: Constructing an initial feature vector based on the finished product requirement parameters and the production raw material ratio; determining a vector distance between the initial feature vector and each of candidate reference feature vectors in a vector database, wherein the vector database includes a plurality of candidate reference feature vectors, each of the plurality of candidate reference feature vectors being constructed based on a set of historical finished product detection parameters and corresponding historical production raw material ratios in historical zirconia powder production data; Determine the candidate reference feature vector whose vector distance satisfies a second preset condition as a reference feature vector; The target flow rate of the production raw material entering the reactor is determined based on each reference flow rate corresponding to the reference feature vector.

7. A zirconium oxide powder production system, characterized in that: The system comprises: a determination module, configured to determine, based on the finished product requirement parameters of the zirconium oxide powder, a ratio of raw materials for producing the zirconium oxide powder and send the ratio to a batcher; determine a target flow rate of the raw materials entering a reactor and send the ratio to the reactor; adjust a first volume of a first container of the reactor to obtain an adjusted first container, wherein the volume of the adjusted first container is a target first volume; obtain multiple initial production plans, each of the multiple initial production plans including an initial first volume, an initial flow rate, and an initial number of filter press washes; perform at least one round of iterative updates on the multiple initial production plans based on a preset algorithm until a third preset condition is met, thereby obtaining a target production plan, the target production plan including the target first volume, the target flow rate, and the target number of filter press washes, the third preset condition including a particle fitness being less than a set value or reaching a maximum number of iterative updates, the particle fitness being the difference between the finished product prediction parameter and the finished product requirement parameter; A first control module is used to control the batcher to batch the raw materials based on the raw material ratio to obtain the raw materials for the production of zirconium oxide powder; a second control module, configured to control the first container and the second container in the reactor to process the production raw materials in sequence to obtain reaction slurry; a third control module, configured to control the filter press washer to perform filter press washing on the reaction slurry to obtain a slurry cake that meets a first preset condition; a fourth control module, configured to control a calciner to calcine the slurry cake to obtain a precursor powder; The fifth control module is used to control the pulverizer to pulverize the precursor powder to obtain the zirconium oxide powder.

8. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the zirconium oxide powder production method according to any one of claims 4 to 6.

Images