Control parameter optimization method and system for purification of metallic indium

Abstract

The application relates to the field of metal indium purification control, and discloses a metal indium purification control parameter optimization method and system. First, composition detection data of a current batch of waste materials is acquired, and corresponding feed composition features and first indium purification influence degree features of each composition are extracted; then, historical composition detection data of multiple groups of historical optimal process parameters are acquired, and historical feed composition features and second indium purification influence degree features are determined. The similarity of the two types of features is calculated by preset weight weighting, the comprehensive matching degree of the current data and the historical data is obtained, the historical optimal process parameter corresponding to the maximum comprehensive matching degree is selected as a target parameter, and indium purification is performed on the current waste materials accordingly. According to the scheme, the optimal historical parameters are weighted and matched in combination with the composition features and the purification influence degree features, and scientific and reasonable optimization of indium recovery control parameters can be realized.

Description

Technical Field

[0001] This application relates to the field of indium purification control technology, and more specifically, to a method and system for optimizing control parameters for indium purification. Background Technology

[0002] The demand for high-purity indium from the new energy and electronic information industries continues to grow. Catalyst waste recycling for indium extraction has become one of the core pathways for indium resource supply. The accuracy and real-time control of process parameters directly determine the indium recovery rate, product purity, and production efficiency. Existing control technologies have gradually introduced data-driven matching logic, which can match historically optimal parameters based on the characteristics of waste composition to carry out production control, providing a mature technological foundation for further improving the control effect.

[0003] Currently, parameter control for indium recovery from pulverized catalysts lacks a scientifically sound basis. Parameter selection, setting, and adjustment rely solely on operators' past experience, without establishing a parameter optimization mechanism based on material characteristics and recovery effectiveness. Due to variations in composition, particle size distribution, indium content, and impurity types among different batches of waste catalysts, experience-based process parameters cannot accurately adapt to the recovery needs of different batches, resulting in poor parameter control for indium recovery. Specifically, this manifests as significant fluctuations in indium recovery rates, difficulty in consistently achieving product purity, and potential issues such as wasted leaching reagents, prolonged reaction times, and increased energy consumption. This not only reduces the production efficiency and economic benefits of indium recovery but also increases the risk of environmental pollution due to excessive waste liquid and residue generated by improper parameter control, failing to meet the demands of large-scale, efficient, and refined industrial indium recovery production. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for optimizing control parameters in indium metal purification, which solves the technical problem that the control parameters for indium recovery cannot be optimized scientifically and reasonably, and achieves the technical effect of scientifically and reasonably optimizing the control parameters for indium recovery.

[0005] In a first aspect, embodiments of this application provide a method for optimizing control parameters in the purification of metallic indium. The method includes: acquiring composition detection data of a current batch of waste; determining the feed composition characteristics corresponding to the composition detection data of the current batch of waste; acquiring first indium purification influence characteristics of multiple components corresponding to the composition detection data of the current batch of waste; acquiring historical composition detection data of multiple historically optimal process parameters; determining historical feed composition characteristics corresponding to the historical composition detection data of multiple historically optimal process parameters; acquiring second indium purification influence characteristics of multiple components corresponding to the historical composition detection data of multiple historically optimal process parameters; and determining the similarity between the feed composition characteristics and the historical feed composition characteristics of multiple historically optimal process parameters, using these similarities as the composition detection data of the current batch of waste and the historical feed composition characteristics of multiple historically optimal process parameters. The process involves: determining the first matching degree of historical component detection data; determining the similarity between the first indium purification influence feature and the second indium purification influence feature of multiple historical optimal process parameters, using this as the second matching degree between the current batch of waste component detection data and the historical component detection data of multiple historical optimal process parameters; obtaining the weights of the first and second matching degrees; determining the sum of the first matching degree weight and the product of the first matching degree, and the product of the second matching degree weight and the second matching degree, using this as the multiple comprehensive matching degrees between the current batch of waste component detection data and the historical component detection data of multiple historical optimal process parameters, and determining the maximum comprehensive matching degree among the multiple comprehensive matching degrees; determining the historical optimal process parameter corresponding to the maximum comprehensive matching degree, using this as the target process parameter; and performing indium purification on the current batch of waste according to the target process parameter.

[0006] In one possible implementation, the method further includes: determining cross-stage components in the composition detection data of the current batch of waste that are adapted to parameter adjustments in different purification stages; when the number of cross-stage components in the current batch of waste is equal to 0, obtaining the historical adjustment range and standard adjustment range of a single-stage process parameter corresponding to multiple historically optimal process parameters; determining the difference between the historical adjustment range and the standard adjustment range of the single-stage process parameter corresponding to multiple historically optimal process parameters as the redundancy adjustment range of the single-stage process parameter; determining multiple redundancy adjustment degrees corresponding to the multiple redundancy adjustment ranges of the multiple single-stage process parameters; and determining the sum of the multiple redundancy adjustment degrees corresponding to the multiple historically optimal process parameters as the sum of the multiple historically optimal process parameters. The comprehensive redundancy adjustment degree corresponding to the optimal process parameters is determined. Cross-process components include excessive copper and iron impurities. The larger the redundancy adjustment range, the greater the redundancy adjustment degree. The comprehensive matching degree weight and comprehensive redundancy adjustment degree weight corresponding to multiple historically optimal process parameters are obtained. The sum of the comprehensive matching degree weight and the product of the comprehensive matching degree, and the product of the comprehensive redundancy adjustment degree weight and the comprehensive redundancy adjustment degree, corresponding to multiple historically optimal process parameters, is used as the corrected matching degree for multiple historically optimal process parameters. The maximum corrected matching degree is determined. The historically optimal process parameter corresponding to the maximum corrected matching degree is determined as the target process parameter. Indium purification is performed on the current batch of waste according to the target process parameter.

[0007] In another possible implementation, determining multiple redundancy adjustment degrees corresponding to the redundancy adjustment range of the single-stage process parameters corresponding to multiple components includes: obtaining the standard redundancy adjustment range of the single-stage process parameters corresponding to multiple components; determining and normalizing the ratio of the redundancy adjustment range of the single-stage process parameters corresponding to multiple components to the standard redundancy adjustment range, as the multiple redundancy adjustment degrees corresponding to the redundancy adjustment range of the single-stage process parameters corresponding to multiple components.

[0008] In another possible implementation, the method further includes: when purifying indium from the current batch of waste according to the target process parameters, acquiring the abnormal operating conditions corresponding to the target process parameters; acquiring the target process parameter adjustment range for the abnormal operating conditions corresponding to the target process parameters; acquiring the process parameter adjustment range for the abnormal operating conditions corresponding to multiple historical optimal process parameters; determining the difference between the target process parameter adjustment range and the process parameter adjustment range for the abnormal operating conditions corresponding to the multiple historical optimal process parameters as the abnormal element adjustment range for the abnormal operating conditions corresponding to the multiple historical optimal process parameters; and determining the abnormal element adjustment degree corresponding to the abnormal element adjustment range for the multiple historical optimal process parameters; wherein, the operating conditions... Abnormal factors include excessive impurities in the leachate and abnormal electrolytic cell temperature. The larger the adjustment range of an abnormal factor, the greater its adjustment degree. The adjustment degree weights of multiple historically optimal process parameters are obtained. The sum of the comprehensive matching degree weight and its product, the comprehensive redundancy adjustment degree weight and its product, and the abnormal factor adjustment degree weight and its product are determined as the abnormal handling matching degree corresponding to multiple historically optimal process parameters. The maximum abnormal handling matching degree is then determined. The historically optimal process parameter corresponding to the maximum abnormal handling matching degree is determined as the target process parameter. Indium purification of the current batch of waste continues according to the target process parameter.

[0009] In another possible implementation, determining the abnormal element adjustment degree corresponding to the abnormal element adjustment range corresponding to multiple historical optimal process parameters includes: obtaining the standard abnormal element adjustment range corresponding to multiple historical optimal process parameters; determining and normalizing the ratio of the abnormal element adjustment degree corresponding to multiple historical optimal process parameters to the standard abnormal element adjustment range, as the abnormal element adjustment degree corresponding to the abnormal element adjustment range corresponding to multiple historical optimal process parameters.

[0010] In another possible implementation, the method further includes: obtaining historical intermediate product indices and standard intermediate product indices corresponding to abnormal operating conditions for multiple historically optimal process parameters; determining the difference between the historical intermediate product indices and standard intermediate product indices corresponding to abnormal operating conditions for multiple historically optimal process parameters, as intermediate product index deviation values; determining the intermediate product index deviation degree corresponding to the intermediate product index deviation values ​​for multiple historically optimal process parameters; obtaining the intermediate product index deviation degree weights corresponding to multiple historically optimal process parameters; determining the product of the intermediate product index deviation degree weights and the intermediate product index deviation degrees corresponding to multiple historically optimal process parameters, as the intermediate product deviation matching degree; determining the difference between the abnormal handling matching degree and the intermediate product deviation matching degree for abnormal operating conditions for multiple historically optimal process parameters, as the abnormal handling deviation matching degree, and determining the maximum abnormal handling deviation matching degree among multiple abnormal handling deviation matching degrees; determining the historically optimal process parameter corresponding to the maximum abnormal handling deviation matching degree, as the target process parameter; and continuing indium purification on the current batch of waste according to the target process parameter.

[0011] In another possible implementation, determining the intermediate product index deviation degree corresponding to the intermediate product index deviation value corresponding to multiple historical optimal process parameters includes: obtaining the standard intermediate product index deviation value corresponding to multiple historical optimal process parameters; determining and normalizing the ratio of the abnormal element adjustment degree corresponding to multiple historical optimal process parameters to the standard intermediate product index deviation value, as the intermediate product index deviation degree corresponding to the intermediate product index deviation value corresponding to multiple historical optimal process parameters.

[0012] In another possible implementation, determining the feed composition features corresponding to the composition detection data of the current batch of waste includes: determining the feed composition vector corresponding to the composition detection data of the current batch of waste according to the same composition dimension order, as the feed composition features corresponding to the composition detection data of the current batch of waste; determining the historical feed composition features corresponding to the historical composition detection data of multiple historical optimal process parameters includes: determining the historical feed composition vector corresponding to the historical composition detection data of multiple historical optimal process parameters according to the same composition dimension order, as the historical feed composition features corresponding to the historical composition detection data of multiple historical optimal process parameters.

[0013] In another possible implementation, obtaining the first indium purification influence feature of multiple components corresponding to the component detection data of the current batch of waste includes: determining the first indium purification influence vector of multiple components corresponding to the component detection data of the current batch of waste according to the same component dimension order, as the first indium purification influence feature of multiple components corresponding to the component detection data of the current batch of waste; obtaining the second indium purification influence feature of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters includes: determining the second indium purification influence vector of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters according to the same component dimension order, as the second indium purification influence feature of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters.

[0014] Secondly, embodiments of this application provide a control parameter optimization system for the purification of metallic indium, including units for implementing the above-described method.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are: This application provides a method for optimizing control parameters in indium refining. The method includes: acquiring composition detection data of the current batch of waste; determining the feed composition characteristics corresponding to the composition detection data of the current batch of waste; acquiring first indium refining influence characteristics of multiple components corresponding to the composition detection data of the current batch of waste; acquiring historical composition detection data of multiple historical optimal process parameters; determining historical feed composition characteristics corresponding to the historical composition detection data of multiple historical optimal process parameters; acquiring second indium refining influence characteristics of multiple components corresponding to the historical composition detection data of multiple historical optimal process parameters; and determining the similarity between the feed composition characteristics and the historical feed composition characteristics of multiple historical optimal process parameters, using this similarity as the historical similarity between the composition detection data of the current batch of waste and the historical optimal process parameters. The process involves: determining the first matching degree of historical component analysis data; determining the similarity between the first indium purification influence feature and the second indium purification influence feature of multiple historical optimal process parameters, using this as the second matching degree between the current batch of waste component analysis data and the historical component analysis data of multiple historical optimal process parameters; obtaining the weights of the first and second matching degrees; determining the sum of the first matching degree weight and the product of the first matching degree, and the product of the second matching degree weight and the second matching degree, using this as the multiple comprehensive matching degrees between the current batch of waste component analysis data and the historical component analysis data of multiple historical optimal process parameters, and determining the maximum comprehensive matching degree among the multiple comprehensive matching degrees; determining the historical optimal process parameter corresponding to the maximum comprehensive matching degree, using this as the target process parameter; and performing indium purification on the current batch of waste according to the target process parameter. In this embodiment, the matching degree is obtained by matching the historical feed composition characteristics corresponding to the historical optimal process parameters and the indium purification influence characteristics of the historical component detection data corresponding to the historical optimal process parameters. The comprehensive matching calculation directly retrieves the historical optimal process parameters as the target process parameters. There is no need to readjust the parameters. The current batch of waste is directly purified according to the target process parameters, which shortens the process debugging time, reduces raw material loss, ensures the indium purification yield, and reduces the overall purification operating cost. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating the first method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 2A schematic diagram illustrating the workflow of the first method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 3 A flowchart illustrating a second method for optimizing control parameters in the purification of metallic indium, provided in an embodiment of this application. Figure 4 A schematic diagram illustrating the workflow of the second method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 5 A flowchart illustrating the third method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 6 A schematic diagram illustrating the workflow of the third method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 7 A flowchart illustrating the fourth method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 8 A schematic diagram illustrating the workflow of the fourth method for optimizing control parameters in the purification of metallic indium provided in this application embodiment; Figure 9 This is a schematic diagram of the logic structure of a control parameter optimization method system for indium metal purification provided in an embodiment of this application. Detailed Implementation

[0018] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0019] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0021] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0023] Currently, the parameter control for indium recovery from pulverized catalysts lacks a scientific and reasonable basis. Parameter selection, setting, and adjustment can only be done based on the operator's past experience, without establishing a parameter optimization mechanism based on material characteristics and recovery effect.

[0024] Based on the above reasons, this application provides a method for optimizing control parameters for indium metal purification. The method includes: acquiring composition detection data of the current batch of waste; determining the feed composition characteristics corresponding to the composition detection data of the current batch of waste; acquiring first indium purification influence characteristics of multiple components corresponding to the composition detection data of the current batch of waste; acquiring historical composition detection data of multiple historical optimal process parameters; determining historical feed composition characteristics corresponding to the historical composition detection data of multiple historical optimal process parameters; acquiring second indium purification influence characteristics of multiple components corresponding to the historical composition detection data of multiple historical optimal process parameters; and determining the similarity between the feed composition characteristics and the historical feed composition characteristics of multiple historical optimal process parameters, using these similarities as the basis for comparing the composition detection data of the current batch of waste with the historical feed composition characteristics of multiple historical optimal process parameters. The process involves: determining the first matching degree of historical component detection data; determining the similarity between the first indium purification influence feature and the second indium purification influence feature of multiple historical optimal process parameters, using this as the second matching degree between the current batch of waste component detection data and the historical component detection data of multiple historical optimal process parameters; obtaining the weights of the first and second matching degrees; determining the sum of the first matching degree weight and the product of the first matching degree, and the product of the second matching degree weight and the second matching degree, using this as the multiple comprehensive matching degrees between the current batch of waste component detection data and the historical component detection data of multiple historical optimal process parameters, and determining the maximum comprehensive matching degree among the multiple comprehensive matching degrees; determining the historical optimal process parameter corresponding to the maximum comprehensive matching degree, using this as the target process parameter; and performing indium purification on the current batch of waste according to the target process parameter. In this embodiment, the matching degree is obtained by matching the historical feed composition characteristics corresponding to the historical optimal process parameters and the indium purification influence characteristics of the historical component detection data corresponding to the historical optimal process parameters. The comprehensive matching calculation directly retrieves the historical optimal process parameters as the target process parameters. There is no need to readjust the parameters. The current batch of waste is directly purified according to the target process parameters, which shortens the process debugging time, reduces raw material loss, ensures the indium purification yield, and reduces the overall purification operating cost.

[0025] In some scenarios, the control parameter optimization method for indium metal purification according to the embodiments of this application can be applied to the parameter optimization of indium metal purification and recovery through catalyst waste, which can improve the parameter optimization effect of indium metal.

[0026] The following describes in detail, with specific examples, a method for optimizing control parameters for indium purification provided in this application.

[0027] Figure 1 A flowchart illustrating the first method for optimizing control parameters in the purification of metallic indium provided in this application is shown below. Figure 1As shown in the embodiment of this application, a method for optimizing control parameters for the purification of metallic indium is provided. The method includes steps S110 to S130, which are described in detail below.

[0028] S110. Obtain the composition detection data of the current batch of waste. Determine the feed composition characteristics corresponding to the composition detection data of the current batch of waste. Obtain the first indium purification influence characteristics of multiple components corresponding to the composition detection data of the current batch of waste. Obtain historical composition detection data of multiple historical optimal process parameters. Determine the historical feed composition characteristics corresponding to the historical composition detection data of multiple historical optimal process parameters. Obtain the second indium purification influence characteristics of multiple components corresponding to the historical composition detection data of multiple historical optimal process parameters.

[0029] Figure 2 A schematic diagram of the workflow of the first control parameter optimization method for indium metal purification provided in this application embodiment is shown below. Figure 2 As shown, in this implementation, various components and their corresponding contents of the current batch of waste to be purified can be collected through detection methods such as spectral detection and component titration, so as to obtain the component detection data of the current batch of waste.

[0030] For example, the composition detection data of the current batch of waste may include multiple sets of content data such as the proportion of indium, tin, lead, zinc, and total impurities.

[0031] In this implementation, the composition detection data of the current batch of waste can be standardized, and the content parameters of various components can be converted into a feature set of a unified dimension to obtain the corresponding feed composition characteristics.

[0032] For example, the feed composition characteristics can be represented as a multi-dimensional vector, where each dimension of the vector corresponds to the standardized content values ​​of components such as indium, tin, lead, and zinc.

[0033] In this implementation, the influence coefficient of each component of the current batch of waste on the indium purification process can be calculated by combining the preset component influence analysis rules, and the first indium purification influence characteristics of multiple components can be obtained by summarizing them.

[0034] For example, the first indium purification influence feature can be represented as a multi-dimensional vector, where each dimension of the vector corresponds to the influence coefficient of different components such as tin, lead, and zinc on the indium purification efficiency and purity.

[0035] In this implementation, multiple sets of historically optimal process parameters with verified purification effects can be retrieved from a pre-built process parameter database, along with the waste component detection records corresponding to each set of historically optimal process parameters, to obtain historical component detection data for multiple historically optimal process parameters.

[0036] For example, historical component detection data corresponding to a set of historical optimal process parameters may include multiple sets of content data such as the proportion of indium, tin, lead, zinc, and total impurities in that historical batch of waste.

[0037] In this implementation, the same standardized processing logic as the current batch can be executed on each set of historical component detection data, converting the content parameters of various components into a feature set of a unified dimension to obtain the corresponding historical feed component features.

[0038] For example, each set of historical feed composition characteristics can be represented as a multi-dimensional vector, with each dimension of the vector corresponding one-to-one with the dimension of the current batch feed composition characteristics, corresponding to the standardized content values ​​of components such as indium, tin, lead, and zinc.

[0039] In this implementation, the same calculation rules as the first indium purification influence characteristic can be used to calculate the influence coefficient of each component in each group of historical component detection data on the indium purification process, and summarize them to obtain the second indium purification influence characteristic of multiple components.

[0040] For example, each group of second indium purification influence features can be represented as a multi-dimensional vector. Each dimension of the vector corresponds one-to-one with the dimension of the first indium purification influence feature of the current batch, respectively corresponding to the influence coefficient values ​​of different components such as tin, lead, and zinc on indium purification efficiency and purity.

[0041] S120. Determine the similarity between the feed composition characteristics and the historical feed composition characteristics of multiple historical optimal process parameters, and use this as the first matching degree between the current batch of waste composition detection data and the historical composition detection data of multiple historical optimal process parameters. Determine the similarity between the first indium purification influence characteristic and the second indium purification influence characteristic of multiple historical optimal process parameters, and use this as the second matching degree between the current batch of waste composition detection data and the historical composition detection data of multiple historical optimal process parameters.

[0042] In this implementation, a vector similarity calculation method can be used to calculate the similarity between the feed composition characteristics of the current batch and the historical feed composition characteristics of each group, and the calculated similarity value is used as the first matching degree of the corresponding historical optimal process parameters.

[0043] For example, a cosine similarity algorithm can be used to calculate the feature vector of the current batch of feed components and a set of historical feed component feature vectors, respectively. The cosine value of the two vectors is then calculated, which is the first matching degree corresponding to the two sets of features.

[0044] In this implementation, the same similarity calculation logic as the first matching degree can be used to calculate the similarity between the first indium purification influence feature of the current batch and the second indium purification influence feature of each group, and the calculated similarity value is used as the second matching degree of the corresponding historical optimal process parameter.

[0045] For example, a cosine similarity algorithm can be used to calculate the first indium purification influence feature vector and a certain group of second indium purification influence feature vectors in the current batch, respectively. The cosine value of the two vectors is then calculated, and this cosine value is the second matching degree corresponding to the two groups of features.

[0046] S130. Obtain the first matching degree weight and the second matching degree weight. Determine the sum of the first matching degree weight and the product of the first matching degree, and the product of the second matching degree weight and the second matching degree, as the comprehensive matching degree of the current batch of waste material's composition detection data and the historical composition detection data of multiple historical optimal process parameters, and determine the maximum comprehensive matching degree. Determine the historical optimal process parameter corresponding to the maximum comprehensive matching degree as the target process parameter. Perform indium purification on the current batch of waste material according to the target process parameter.

[0047] In this implementation, the first matching degree weight and the second matching degree weight can be retrieved from the preset weight configuration library according to the control requirements of the purification process. The two types of weights correspond to the proportion of the two types of matching degrees in the comprehensive evaluation.

[0048] For example, if the purification process prioritizes ensuring the matching degree of the feed components, the first matching degree weight can be set to a first preset value, the second matching degree weight can be set to a second preset value, and the sum of the two weights is a preset standard value.

[0049] In this implementation, the first and second matching degrees corresponding to each set of historical best process parameters can be weighted and summed to obtain the comprehensive matching degree corresponding to each set of historical best process parameters. Then, all comprehensive matching degrees are sorted by size, and the maximum comprehensive matching degree with the highest value is selected.

[0050] For example, for a set of historically optimal process parameters, the product of the first matching degree and the weight of the first matching degree can be superimposed with the product of the second matching degree and the weight of the second matching degree to obtain the comprehensive matching degree corresponding to the set of parameters.

[0051] In this implementation, the historical optimal process parameters corresponding to the maximum comprehensive matching degree can be located, and the set of historically verified optimal process parameters can be directly used as the target process parameters for the purification of the current batch of waste materials.

[0052] In this implementation, the target process parameters can be directly loaded into the control equipment of the purification process, and the equipment of each process can be controlled to operate according to the set values ​​of the target process parameters to complete the indium purification operation of the current batch of waste.

[0053] This implementation method obtains the composition detection data of the current batch of waste, determines the corresponding feed composition characteristics, matches the historical feed composition characteristics corresponding to the historical best process parameters to obtain the corresponding matching degree, and calculates the comprehensive matching degree based on the matching weight to select the optimal process parameters, thereby improving the adaptability of process parameters and current feed, reducing raw material fluctuation interference, and improving the purification stability of metallic indium.

[0054] This implementation method obtains the indium purification influence characteristics of multiple components corresponding to the component detection data of the current batch of waste, matches the indium purification influence characteristics of historical component detection data corresponding to the historical optimal process parameters to obtain the corresponding matching degree, and calculates and screens target process parameters based on the comprehensive matching degree. This fully considers the differences in the influence of different components on purification, avoids parameter deviation, and improves the rationality of purification parameters.

[0055] This implementation method directly retrieves the historically optimal process parameters as the target process parameters through comprehensive matching calculations. There is no need to readjust the parameters. The current batch of waste material is directly purified according to the target process parameters, which shortens the process debugging time, reduces raw material loss, ensures the yield of purified indium metal, and reduces the overall purification operating cost.

[0056] Figure 3 A flowchart illustrating the second method for optimizing control parameters in indium purification provided in this application is shown below. Figure 3 As shown, in some implementations, the above method also includes S140 to S150, which will be described in detail below.

[0057] S140. Determine the cross-stage components in the current batch of waste material's composition analysis data that are compatible with parameter adjustments for different purification stages. When the number of cross-stage components in the current batch of waste material is zero, obtain the historical adjustment range and standard adjustment range of the single-stage process parameter corresponding to multiple historical best process parameters. Determine the difference between the historical adjustment range and standard adjustment range of the single-stage process parameter corresponding to multiple historical best process parameters as the redundancy adjustment range of the single-stage process parameter. Determine multiple redundancy adjustment degrees corresponding to the redundancy adjustment range of the single-stage process parameter. Determine the sum of multiple redundancy adjustment degrees corresponding to multiple historical best process parameters as the comprehensive redundancy adjustment degree corresponding to multiple historical best process parameters. Among them, cross-stage components include copper impurity exceeding the standard and iron impurity exceeding the standard. The larger the redundancy adjustment range, the greater the redundancy adjustment degree.

[0058] Figure 4A schematic diagram of the workflow for optimizing control parameters in the purification of metallic indium provided in this application embodiment is shown below. Figure 4 As shown, in this implementation, the component detection data of the current batch of waste can be traversed and identified by combining the preset cross-stage component determination rules, and the components that have a constraining effect on the parameter adjustment of multiple purification stages can be screened out and classified as cross-stage components.

[0059] It should be noted that cross-process components include excessive copper and iron impurities. The content fluctuations of these components cannot be addressed by adjusting the parameters of a single purification process; multiple process parameters must be adjusted simultaneously.

[0060] For example, when the composition detection data of the current batch of waste material simultaneously meets the conditions of both copper impurity content exceeding the threshold and iron impurity content exceeding the threshold, both copper impurity exceeding the standard and iron impurity exceeding the standard are cross-stage components adapted to the parameter adjustment of different purification stages.

[0061] In this implementation, the number of cross-process components identified can be counted first. When the counted number is 0, the associated data of all historical optimal process parameters in the pre-stored historical process database can be retrieved, and the two types of adjustment ranges of single-process parameters corresponding to different components can be extracted from them.

[0062] For example, the standard adjustment range of a single process parameter can be preset according to the general specifications of the purification process, and the historical adjustment range can correspond to the adjustable parameter range when the corresponding components fluctuate slightly during actual application of the historical optimal process parameter.

[0063] In this implementation, the historical adjustment range and standard adjustment range of each extracted single-stage process parameter can be calculated separately. The calculated difference is used as the redundant adjustment range of the corresponding single-stage process parameter of the corresponding component, which represents the adjustable margin of the process parameter.

[0064] For example, the standard adjustment range of the extraction pH value of zinc impurities corresponding to a certain historical optimal process parameter is a fixed interval, and the historical adjustment range is another interval. The difference between the two intervals is the redundant adjustment range of the single-stage process parameter of the extraction pH value of zinc impurities.

[0065] In this implementation, each redundancy adjustment range can be standardized and converted according to a preset conversion rule to obtain a redundancy adjustment degree that corresponds one-to-one with the redundancy adjustment range. The redundancy adjustment degree is a standardized parameter that can be directly referenced in subsequent numerical calculations.

[0066] It should be noted that the larger the redundancy adjustment range, the greater the redundancy adjustment degree, the higher the component fluctuation range that the corresponding process parameter can handle, and the stronger the parameter adaptation flexibility.

[0067] S150. Obtain the comprehensive matching degree weight and comprehensive redundancy adjustment degree weight corresponding to multiple historical optimal process parameters. Determine the sum of the comprehensive matching degree weight and the product of the comprehensive matching degree, and the product of the comprehensive redundancy adjustment degree weight and the comprehensive redundancy adjustment degree, as the corrected matching degree corresponding to the multiple historical optimal process parameters, and determine the maximum corrected matching degree among the multiple corrected matching degrees. Determine the historical optimal process parameter corresponding to the maximum corrected matching degree as the target process parameter. Perform indium purification on the current batch of waste according to the target process parameter.

[0068] In this implementation, the redundancy adjustment degree corresponding to the same historical optimal process parameter can be summed, and the summed value can be used as the comprehensive redundancy adjustment degree of the historical optimal process parameter, which can represent the full-dimensional adjustable space of the process parameter.

[0069] For example, the redundancy adjustment degree of the three components corresponding to a certain historical optimal process parameter is three fixed values, and the sum of the three values ​​is the comprehensive redundancy adjustment degree corresponding to the historical optimal process parameter.

[0070] In this implementation, the pre-stored weight configuration data can be retrieved according to the priority requirements of the current purification process to obtain the comprehensive matching degree weight and the comprehensive redundancy adjustment degree weight. The two types of weights correspond to the importance of the two evaluation dimensions, respectively.

[0071] For example, when the purification process prioritizes parameter matching, the overall matching weight can be set to a higher value, and the overall redundancy adjustment weight can be set to a lower value, with the sum of the two weights being a fixed value.

[0072] In this implementation, the comprehensive matching degree and comprehensive redundancy adjustment degree corresponding to each historical optimal process parameter can be multiplied by their respective weights and then summed to obtain the corrected matching degree of each historical optimal process parameter. Then, all corrected matching degrees are compared to find the maximum corrected matching degree with the largest value.

[0073] For example, the overall matching degree of a certain historical optimal process parameter is a fixed value, the overall matching degree weight is a fixed value, the overall redundancy adjustment degree is a fixed value, the overall redundancy adjustment degree weight is a fixed value, and the sum of the two types of products is the corrected matching degree corresponding to the historical optimal process parameter.

[0074] In this implementation, the historical optimal process parameter corresponding to the maximum correction matching degree can be selected as the target process parameter to adapt to the current batch of waste. This parameter satisfies both the matching degree requirement and the adjustability requirement.

[0075] In this implementation, the target process parameters can be sent to each control node of the purification production line, and each piece of equipment can be controlled to operate according to the requirements of the target process parameters to complete the indium purification operation of the current batch of waste.

[0076] This implementation method identifies cross-process components in the composition detection data of the current batch of waste that are compatible with parameter adjustments in different purification stages. Only when the cross-process components in the current batch of waste are not present will the subsequent process parameter correction process be initiated. This can quickly screen out special waste conditions that require multi-stage coordinated parameter adjustments, reduce the amount of computation for invalid parameter matching, and improve the efficiency of target process parameter matching.

[0077] This implementation method obtains the historical adjustment range and standard adjustment range of the single-stage process parameters corresponding to multiple components for multiple historical optimal process parameters. The difference between the two is determined as the redundancy adjustment range of the single-stage process parameters corresponding to multiple components. After converting the corresponding redundancy adjustment degrees, the summation is obtained to obtain the comprehensive redundancy adjustment degree. This method can intuitively quantify the adjustable space of historical optimal process parameters and provide a more comprehensive reference for parameter selection.

[0078] This implementation method obtains the comprehensive matching degree weight and comprehensive redundancy adjustment degree weight corresponding to multiple historical optimal process parameters. The comprehensive matching degree and comprehensive redundancy adjustment degree are weighted and summed to obtain the corrected matching degree. The historical optimal process parameter corresponding to the maximum corrected matching degree is selected as the target process parameter. This method takes into account both parameter matching degree and adjustability, effectively improves the rationality of the final selected target process parameter in adapting to the current purification conditions, and ensures the indium purification efficiency and purification accuracy.

[0079] In some implementations, in S140 above, multiple redundancy adjustment degrees corresponding to the redundancy adjustment range of multiple single-stage process parameters are determined, including S141 to S142. S141 to S142 will be explained in detail below.

[0080] S141. Obtain the standard redundancy adjustment range of multiple single-stage process parameters.

[0081] In this implementation, standard redundancy adjustment ranges for each component can be pre-set based on the equipment operating specifications, process safety thresholds, and statistical data of long-term purification operations for each individual process parameter. This serves as a unified reference benchmark for calculating redundancy adjustment degree, eliminating benchmark differences between different parameter types.

[0082] For example, the standard redundancy adjustment range of the reducing agent dosage parameter for adjusting the copper impurities in the displacement process can be set as a fixed value range as a reference based on the rated dosage threshold of the reducing agent and the safe reaction range of the displacement reaction.

[0083] S142. Determine and normalize the ratio of the redundant adjustment range of multiple single-stage process parameters to the standard redundant adjustment range, which serves as the multiple redundancy adjustment degrees corresponding to the redundant adjustment range of multiple single-stage process parameters.

[0084] In this implementation, the ratio of the interval length of the redundant adjustment range of the single-stage process parameter corresponding to each component to the interval length of the corresponding standard redundant adjustment range can be calculated. Then, all ratios are normalized to obtain the redundancy adjustment degree of each component, thereby achieving the standardization and quantification of the adjustable space of different types of process parameters.

[0085] For example, if the length of the redundant adjustment range of a single process parameter corresponding to a certain component is 0.4 times the length of the corresponding standard redundant adjustment range, after normalization, the redundancy adjustment degree corresponding to the component can be determined to be 0.4.

[0086] This implementation method first obtains the standard redundancy adjustment range of multiple single-stage process parameters when calculating the redundancy adjustment degree. Then, it calculates the ratio of the redundancy adjustment range of the multiple single-stage process parameters to the standard redundancy adjustment range. After normalizing the ratio, the corresponding redundancy adjustment degree is obtained. This allows the quantification result of the redundancy adjustment degree to better match the actual process adjustment requirements, effectively improving the accuracy of the redundancy adjustment degree and avoiding interference from quantification deviations on subsequent parameter matching. It can also help to screen out target process parameters with stronger adaptability, reduce the difficulty of parameter adjustment in the actual indium purification process, effectively improve the indium purification efficiency and purification accuracy of different batches of waste, and reduce resource waste caused by insufficient parameter adaptability.

[0087] Figure 5 A flowchart illustrating the third method for optimizing control parameters in indium purification provided in this application is shown below. Figure 5 As shown, in some implementations, the above method also includes S210 to S220, which will be described in detail below.

[0088] S210. When purifying indium from the current batch of waste according to the target process parameters, obtain the abnormal operating conditions corresponding to the target process parameters. Obtain the target process parameter adjustment range for the abnormal operating conditions corresponding to the target process parameters. Obtain the process parameter adjustment range for the abnormal operating conditions corresponding to multiple historical best process parameters. Determine the difference between the target process parameter adjustment range and the process parameter adjustment range for the abnormal operating conditions corresponding to the multiple historical best process parameters, and use this difference as the abnormal element adjustment range for the abnormal operating conditions corresponding to the multiple historical best process parameters. Determine the abnormal element adjustment degree corresponding to the abnormal element adjustment range for the multiple historical best process parameters. The abnormal operating conditions include excessive impurities in the leaching solution and abnormal electrolytic cell temperature. The larger the abnormal element adjustment range, the greater the abnormal element adjustment degree.

[0089] Figure 6 A schematic diagram of the workflow for the third method of optimizing control parameters for indium metal purification provided in this application embodiment is shown below. Figure 6 As shown, in this implementation, during the purification operation, a set of abnormal operating conditions bound to the currently enabled target process parameters can be collected synchronously, providing a reference for parameter adaptation and adjustment under subsequent abnormal operating conditions.

[0090] For example, the abnormal operating conditions may include various unexpected operating states that may occur in the entire indium purification process, covering two typical abnormal scenarios: excessive impurities in the leaching solution during the leaching stage and abnormal temperature of the electrolytic cell during the electrolysis stage.

[0091] In this implementation, the adjustment range of the target process parameter corresponding to the abnormal operating conditions of the target process parameter can be obtained. The adjustment range of the target process parameter can be determined by empirical values ​​of indium purification.

[0092] In this implementation, the adjustable parameter range associated with abnormal operating conditions for each historical optimal process parameter can be retrieved from the preset repository and used as the adjustment range of the corresponding process parameter.

[0093] For example, the adjustment range of process parameters corresponding to abnormal operating conditions for multiple historical optimal process parameters can be reflected as the adjustable range of pH value when impurities in the leachate exceed the standard, and the adjustable range of current when the temperature of the electrolytic cell is abnormal.

[0094] In this implementation, the difference calculation can be performed on the adjustment range of the target process parameter corresponding to the abnormal operating condition element of the target process parameter and the adjustment range of the process parameter corresponding to the abnormal operating condition element of multiple historical optimal process parameters. The numerical range obtained by the calculation is used as the adjustment range of the abnormal element of the corresponding process parameter. The adjustment range of the abnormal element represents the redundancy range of the adjustment range of the abnormal element of multiple historical optimal process parameters relative to the target process parameter.

[0095] For example, if the pH adjustment range of a certain historically optimal process parameter for exceeding the standard of leaching impurities caused by copper impurities is the first interval, and the pH adjustment range of the target process parameter for exceeding the standard of leaching impurities caused by iron impurities is the second interval, the difference between the two intervals is the abnormal element adjustment range of the leaching impurity exceeding the standard element corresponding to the process parameter.

[0096] In this implementation, the adjustment range of abnormal elements corresponding to each historical optimal process parameter can be quantitatively converted to obtain the adjustment degree of abnormal elements that can be used for parameter matching calculation, which characterizes the ability of the corresponding process parameter to adjust to abnormal operating conditions.

[0097] In this implementation, the scope of abnormal operating conditions can be limited in advance, including only the two types of abnormalities that occur frequently in the indium purification process and have a significant impact on the purification effect, thereby reducing unnecessary computation.

[0098] It should be noted that abnormal operating conditions refer to unexpected operating states that occur during the indium purification process, which may affect the purification accuracy and efficiency. These abnormalities need to be eliminated by adjusting the process parameters.

[0099] In this implementation, a positive correlation mapping relationship can be set between the adjustment range and the adjustment degree of abnormal elements to ensure that the quantitative result of the adjustment degree can directly reflect the adjustment space of the corresponding process parameters in response to abnormalities.

[0100] S220. Obtain the anomaly factor adjustment weights corresponding to multiple historical optimal process parameters. Determine the sum of the comprehensive matching degree weight and its product, the comprehensive redundancy adjustment degree weight and its product, and the anomaly factor adjustment degree weight and its product for the multiple historical optimal process parameters. Use this sum as the anomaly handling matching degree corresponding to the multiple historical optimal process parameters, and determine the maximum anomaly handling matching degree among the multiple anomaly handling matching degrees. Determine the historical optimal process parameter corresponding to the maximum anomaly handling matching degree as the target process parameter. Continue indium purification of the current batch of waste according to the target process parameter.

[0101] In this implementation, pre-configured abnormal element adjustment weights adapted to the current purification scenario can be retrieved for weighted calculation of the matching degree of subsequent abnormal handling.

[0102] For example, the adjustment weight of abnormal elements can be set in conjunction with the abnormal risk level of the current purification batch. If the impurity content of the waste material in the current batch is high and the probability of abnormality is high, the value of the adjustment weight of abnormal elements can be increased accordingly.

[0103] In this implementation, the three types of indicators—comprehensive matching degree, comprehensive redundancy adjustment degree, and abnormal element adjustment degree—are multiplied by their corresponding weights and then summed to obtain the abnormal handling matching degree of each process parameter. Then, the item with the largest value is selected from multiple abnormal handling matching degrees.

[0104] For example, if the product of the overall matching degree and the corresponding weight of a certain historical optimal process parameter is the first value, the product of the overall redundancy adjustment degree and the corresponding weight is the second value, and the product of the abnormal element adjustment degree and the corresponding weight is the third value, the sum of the three values ​​is the abnormal handling matching degree corresponding to that process parameter.

[0105] In this implementation, the historical optimal process parameters associated with the highest anomaly handling matching degree obtained by screening can be updated to the target process parameters of the current purification operation to adapt to the purification needs under abnormal operating conditions.

[0106] In this implementation, the updated target process parameters can be sent to the control equipment of the corresponding purification stage to quickly complete the parameter adjustment and maintain the normal progress of the purification operation of the current batch of waste.

[0107] This implementation method, when purifying indium from the current batch of waste according to the target process parameters, obtains the abnormal operating conditions corresponding to the target process parameters, calculates the abnormal condition adjustment degree corresponding to the abnormal operating conditions of the historical best process parameters, and obtains the abnormal handling matching degree by combining the comprehensive matching degree, the comprehensive redundancy adjustment degree and the corresponding weight. The process parameters corresponding to the maximum abnormal handling matching degree are selected as the target process parameters for continued purification. This method can quickly complete parameter adjustments when conditions such as excessive impurities in the leaching solution and abnormal temperature in the electrolytic cell occur, ensuring the stability and accuracy of the purification operation.

[0108] In some implementations, in S210 above, the abnormal element adjustment degree corresponding to the abnormal element adjustment range corresponding to multiple historical optimal process parameters is determined, including S211 to S212. S211 to S212 will be explained in detail below.

[0109] S211. Obtain the adjustment range of standard abnormal elements corresponding to multiple historical optimal process parameters.

[0110] In this implementation, the long-term operating statistics of the indium metal purification process and the adjustment restrictions of abnormal elements under different operating conditions can be combined to obtain the standard abnormal element adjustment range corresponding to multiple historical optimal process parameters in advance, so as to provide a unified reference benchmark for the subsequent quantification of abnormal adjustment capabilities.

[0111] For example, the adjustment range of standard abnormal elements can be set according to the type of abnormal element. For example, the adjustment range of standard abnormal elements for excessive impurities in leachate can be set to the maximum adjustment range of the amount of leaching agent allowed by the process. For standard abnormal elements for abnormal electrolytic cell temperature, the adjustment range can be set to the maximum adjustment range of the electrolytic cell heating power allowed by the process.

[0112] S212. Determine and normalize the ratio of the abnormal element adjustment degree to the standard abnormal element adjustment range corresponding to multiple historical optimal process parameters, and use it as the abnormal element adjustment degree corresponding to the abnormal element adjustment range corresponding to multiple historical optimal process parameters.

[0113] In this implementation, for each historical optimal process parameter, the ratio of its abnormal element adjustment range to the corresponding standard abnormal element adjustment range can be calculated. After normalizing the obtained ratio, the result is used as the abnormal element adjustment degree corresponding to the abnormal element adjustment range of the historical optimal process parameter.

[0114] It should be noted that normalization can map the ratios corresponding to abnormal elements under different operating conditions to a unified numerical range, eliminating the impact of the magnitude difference in the adjustment range of different abnormal elements on the quantification results and ensuring the comparability of the adjustment degrees of each abnormal element.

[0115] For example, when the interval length of the adjustment range of the abnormal element corresponding to the excessive impurities in the leachate for a certain historical optimal process parameter is the first parameter, and the interval length of the adjustment range of the standard abnormal element is the second parameter, the ratio of the first parameter and the second parameter can be calculated, and the ratio can be mapped to the interval between 0 and 1. The result obtained is the abnormal element adjustment degree of the process parameter corresponding to the condition of excessive impurities in the leachate.

[0116] This implementation method determines the adjustment degree of abnormal elements by first obtaining the corresponding standard abnormal element adjustment range, then calculating the ratio of the abnormal element adjustment degree to the standard abnormal element adjustment range and performing normalization processing to finally obtain the corresponding abnormal element adjustment degree. This can eliminate the calculation deviation caused by the difference in the adjustment range values ​​of abnormal elements under different working conditions, improve the accuracy of assigning the abnormal element adjustment degree, and ensure the reliability of subsequent parameter matching calculations.

[0117] This implementation incorporates the precisely calculated abnormal element adjustment degree into the matching calculation dimension of the target process parameters. It combines the original comprehensive matching degree and comprehensive redundancy adjustment degree to calculate the abnormal handling matching degree. The process parameter corresponding to the maximum abnormal handling matching degree is then selected as the target process parameter. This approach can balance the adaptability of feed components with the redundancy of conventional process adjustment and the ability to cope with abnormal operating conditions, thereby improving the adaptability of the target process parameters to the actual purification scenario.

[0118] This implementation method allows for the indium purification operation to be carried out according to the target process parameters obtained through final screening. When abnormal operating conditions occur during the process, the corresponding adjustment operation is directly performed using the matched process parameters without the need for additional temporary parameter debugging. This significantly shortens the response time for parameter adjustment when abnormal operating conditions occur, reduces the negative impact of abnormal operating conditions on purification efficiency and purification accuracy, and improves the operational stability of the entire indium purification process and the quality of the final indium metal produced.

[0119] Figure 7 A flowchart illustrating the fourth method for optimizing control parameters in indium metal purification provided in this application is shown below. Figure 7As shown, in some implementations, the above method also includes S310 to S320, which will be described in detail below.

[0120] S310. Obtain historical and standard intermediate product indices for anomaly factors corresponding to multiple historical optimal process parameters. Determine the difference between the historical and standard intermediate product indices for anomaly factors corresponding to multiple historical optimal process parameters, and use this as the intermediate product index deviation value. Determine the intermediate product index deviation degree corresponding to the intermediate product index deviation values ​​for multiple historical optimal process parameters.

[0121] Figure 8 A schematic diagram of the workflow for the fourth method of optimizing control parameters for indium metal purification provided in this application embodiment is shown below. Figure 8 As shown, in this implementation, the actual intermediate product detection data under the same operating conditions when abnormal factors are triggered can be retrieved using the historical optimal process parameters. At the same time, the qualified standard data of the corresponding intermediate products set in the indium purification process can be retrieved to provide a numerical basis for subsequent deviation calculation.

[0122] It should be noted that the historical intermediate product index is the actual detection index of the intermediate product produced during the operation of the corresponding historical optimal process parameters when abnormal operating conditions occur, while the standard intermediate product index is the qualified index of the corresponding intermediate product specified in the indium purification process specification.

[0123] For example, historical intermediate product indicators can be reflected in actual test values ​​such as indium concentration in the leachate and impurity content in the replacement solution, while standard intermediate product indicators can be reflected in preset values ​​such as the lower limit of indium concentration in the leachate and the upper limit of impurity content in the replacement solution specified in the process specification.

[0124] In this implementation, the difference between historical intermediate product indicators and standard intermediate product indicators under the same abnormal operating conditions can be calculated to obtain the deviation value of each intermediate product indicator, which intuitively reflects the control effect of the corresponding process parameters on intermediate products under abnormal operating conditions.

[0125] It should be noted that the calculation logic can be adjusted according to the type of indicator when calculating the difference. For indicators where a higher value is better, the standard value is taken minus the actual value. For indicators where a lower value is better, the actual value is taken minus the standard value, thus ensuring the positive statistical logic of the deviation value.

[0126] For example, if the historical intermediate product index corresponding to the indium concentration in the leaching solution of a certain historical optimal process parameter is 8 g / L and the standard intermediate product index is 10 g / L, the difference between the two is 2 g / L, and this value is the deviation value of the corresponding intermediate product index.

[0127] In this implementation, the deviation values ​​of intermediate product indicators corresponding to multiple intermediate product indicators can be weighted and normalized to obtain the deviation degree of a single quantified intermediate product indicator, which comprehensively reflects the overall deviation level of intermediate products under abnormal operating conditions corresponding to the historical best process parameters.

[0128] In this implementation, the weight parameters of the deviation of the corresponding intermediate product index can be preset according to the degree of influence of different intermediate products on the subsequent purification process, so as to provide a weight basis for the subsequent matching degree calculation.

[0129] It should be noted that the weight of the deviation of intermediate product indicators can be dynamically configured according to the process adjustment requirements. The intermediate product with the greater impact on the purification process has a higher weight value.

[0130] For example, if the indium concentration in the leachate has a higher impact on the subsequent purification yield, the weight of the deviation of the corresponding intermediate product index can be set to a higher value, while the weight of the impurity content in the replacement solution can be set to a relatively lower value.

[0131] S320. Obtain the intermediate product index deviation weights corresponding to multiple historical best process parameters. Determine the product of the intermediate product index deviation weights and the intermediate product index deviations corresponding to multiple historical best process parameters as the intermediate product deviation matching degree. Determine the difference between the anomaly handling matching degree and the intermediate product deviation matching degree corresponding to the abnormal operating conditions for multiple historical best process parameters as the anomaly handling deviation matching degree, and determine the maximum anomaly handling deviation matching degree among multiple anomaly handling deviation matching degrees. Determine the historical best process parameter corresponding to the maximum anomaly handling deviation matching degree as the target process parameter. Continue indium purification of the current batch of waste according to the target process parameter.

[0132] In this implementation, the intermediate product index deviation weight and the intermediate product index deviation can be multiplied to obtain the weighted intermediate product deviation matching degree, which quantitatively reflects the parameter adaptation under the intermediate product deviation dimension.

[0133] For example, the deviation weight of intermediate product indicators can be set in conjunction with the abnormal risk level of the current purification batch. If the impurity content of the waste material in the current batch is high and the probability of abnormality is high, the value of the deviation weight of intermediate product indicators can be increased accordingly.

[0134] In this implementation, the abnormal handling matching degree calculated by the above method can be subtracted from the intermediate product deviation matching degree to obtain the corrected abnormal handling deviation matching degree. The correction effect of intermediate product deviation is introduced on the basis of the original matching logic, and the maximum value is obtained by screening all abnormal handling deviation matching degrees to provide a basis for the selection of target process parameters.

[0135] It should be noted that the higher the deviation matching degree value of the anomaly handling, the stronger the comprehensive adaptability of the corresponding historical best process parameters, which not only has good anomaly adjustment capabilities, but also ensures that the quality of intermediate products meets the requirements.

[0136] For example, if the anomaly handling matching degree of a certain historical optimal process parameter is 0.92 and the intermediate product deviation matching degree is 0.05, the difference between the two is 0.87, which is the corresponding anomaly handling deviation matching degree.

[0137] In this implementation, the historical process parameters corresponding to the maximum abnormal handling deviation matching degree obtained by screening can be used as the target process parameters under the current abnormal operating conditions, ensuring that the selected parameters simultaneously meet the abnormal adjustment requirements and the intermediate product quality requirements.

[0138] In this implementation, the operating configuration of the matched target process parameters can be directly retrieved, the operating parameters of the corresponding purification equipment can be controlled, and the indium purification operation of the current batch of waste can continue without additional parameter debugging.

[0139] This implementation method first calculates the difference between the historical intermediate product index and the standard intermediate product index corresponding to the abnormal operating conditions of multiple historical optimal process parameters to obtain the intermediate product index deviation value. After converting it into the corresponding deviation degree, the intermediate product deviation matching degree is calculated in combination with the weight. After correcting the original matching degree, the target process parameters are screened to improve the adaptability of the target process parameters and the current abnormal operating conditions.

[0140] This implementation adds intermediate product index dimension verification to the parameter screening logic of the original abnormal operating conditions. It introduces the actual performance data of intermediate products corresponding to the abnormal operating conditions of historical optimal process parameters to adjust the matching results, avoids parameter adaptation deviations caused by relying solely on adjustment range feature matching, and improves the pass rate of intermediate products under abnormal operating conditions.

[0141] In some implementations, in S310 above, the deviation degree of intermediate product index corresponding to the deviation value of intermediate product index corresponding to multiple historical optimal process parameters is determined, including S311 to S312. S311 to S312 will be explained in detail below.

[0142] S311. Obtain the standard intermediate product index deviation values ​​corresponding to multiple historical optimal process parameters.

[0143] In this implementation, the standard intermediate product index deviation values ​​corresponding to each historical optimal process parameter can be pre-retrieved within the indium purification process system. These values ​​are the allowable deviation thresholds for intermediate product indexes obtained from statistics of a large number of compliant purification operations during the process debugging phase, providing a unified reference benchmark for the subsequent quantitative calculation of intermediate product index deviation.

[0144] For example, for the indium content index of the leaching solution corresponding to the indium purification leaching process, the deviation value of the standard intermediate product index corresponding to a certain set of historical best process parameters is the maximum threshold value that the indium content of the leaching solution is allowed to deviate from the standard value under the corresponding abnormal operating conditions preset by the process system.

[0145] S312. Determine and normalize the ratio of the abnormal element adjustment degree and the standard intermediate product index deviation value corresponding to multiple historical optimal process parameters, and use it as the intermediate product index deviation degree corresponding to the intermediate product index deviation value corresponding to multiple historical optimal process parameters.

[0146] In this implementation, the ratio of the abnormal element adjustment degree to the corresponding standard intermediate product index deviation value can be calculated first. Then, the normalization process is performed on all the obtained ratio results to map the values ​​to a unified range. Finally, the intermediate product index deviation degree corresponding to each historical optimal process parameter is obtained. This value can intuitively reflect the degree of deviation of the intermediate product index of the corresponding process parameter under abnormal operating conditions.

[0147] For example, for a set of historically optimal process parameters, first retrieve the abnormal element adjustment degree corresponding to the process parameter and the corresponding standard intermediate product index deviation value. After completing the ratio calculation between the two, map the ratios corresponding to all historically optimal process parameters to a preset numerical range to obtain the intermediate product index deviation degree corresponding to the set of historically optimal process parameters.

[0148] This implementation method first obtains the standard intermediate product index deviation values ​​corresponding to multiple historical optimal process parameters when calculating the intermediate product index deviation. Then, it normalizes the ratio of the abnormal element adjustment degree corresponding to multiple historical optimal process parameters to the standard intermediate product index deviation value to obtain the intermediate product index deviation value corresponding to multiple historical optimal process parameters. This effectively improves the accuracy of intermediate product index deviation calculation and provides an accurate and reliable reference for subsequent process parameter matching.

[0149] This implementation method calculates the deviation degree of intermediate product indicators, combines the corresponding deviation degree weight of intermediate product indicators to obtain the deviation matching degree of intermediate product, and then subtracts the deviation matching degree of intermediate product from the deviation matching degree of abnormal handling to obtain the deviation matching degree of abnormal handling. The historical best process parameter corresponding to the maximum deviation matching degree of abnormal handling is selected as the target process parameter for subsequent purification operations, which effectively improves the adaptability of process parameter matching under abnormal operating conditions.

[0150] In some implementations, in S110 above, determining the feed component features corresponding to the component detection data of the current batch of waste includes: determining the feed component vector corresponding to the component detection data of the current batch of waste according to the same component dimension order, as the feed component features corresponding to the component detection data of the current batch of waste.

[0151] In this implementation, a fixed order of component dimensions can be preset. The detection results of each component in the current batch of waste component detection data are arranged in the preset order to generate a corresponding multi-dimensional vector. This vector is used as the feed component feature of the current batch of waste, ensuring the standardization of the dimension arrangement of feature parameters.

[0152] For example, the component dimension order is preset to indium, copper, iron, tin, and lead. The corresponding component detection values ​​of the current batch of waste are arranged in this order, and the generated multi-dimensional vector is the feed component vector corresponding to the component detection data of the current batch of waste.

[0153] In some implementations, in S110 above, determining the historical feed composition features corresponding to the historical composition detection data of multiple historical optimal process parameters includes: determining the historical feed composition vectors corresponding to the historical composition detection data of multiple historical optimal process parameters in the same composition dimension order, as the historical feed composition features corresponding to the historical composition detection data of multiple historical optimal process parameters.

[0154] In this implementation, the component dimension order used when generating the current batch of feed component features can be used. The component detection results in the historical component detection data corresponding to each historical optimal process parameter are arranged in this order to generate corresponding multi-dimensional vectors, which serve as the historical feed component features of the corresponding historical optimal process parameters. This ensures that the dimensions of the two types of features are completely aligned and avoids matching errors caused by dimension misalignment.

[0155] For example, following the pre-defined compositional order of indium, copper, iron, tin, and lead, the historical detection values ​​of each corresponding component in the historical compositional detection data corresponding to a certain historical optimal process parameter are arranged in this order, and the generated multi-dimensional vector is the historical feed composition vector corresponding to the historical compositional detection data of that historical optimal process parameter.

[0156] This implementation transforms the component detection data of the current batch of waste into feed component vectors as feed component features, following the same component dimension order. At the same time, historical feed component features are generated according to the same rules. When performing feed feature matching, the two types of feed features adopt completely consistent component dimension arrangement rules, eliminating the need for additional dimension mapping alignment. The matching result can be obtained by directly calculating the vector similarity, simplifying the matching operation steps, reducing computational resource consumption, and improving the parameter matching response speed.

[0157] In some implementations, in S110 above, obtaining the first indium purification influence feature of multiple components corresponding to the component detection data of the current batch of waste includes: determining the first indium purification influence vector of multiple components corresponding to the component detection data of the current batch of waste according to the same component dimension order, and using it as the first indium purification influence feature of multiple components corresponding to the component detection data of the current batch of waste.

[0158] In this implementation, a pre-defined composition dimension arrangement rule can be followed. Combined with the actual influence weight of each component of the current batch of waste on the indium purification process, corresponding vector data is generated as the first indium purification influence feature. This ensures that the influence feature dimension of the current batch is completely aligned with the historical data dimension, reducing the probability of error in subsequent matching operations.

[0159] For example, the actual weight of each component of the current batch of waste on the indium purification process can be determined by empirical values.

[0160] For example, the component dimension order is preset to indium, copper, iron, zinc and tin. The purification influence weight of each component is pre-calibrated. The vector obtained by arranging the influence weights of each component of the current batch of waste in this order is the first indium purification influence feature.

[0161] In some implementations, in S110 above, obtaining the second indium purification influence characteristics of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters includes: determining the second indium purification influence vector of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters in the same component dimension order, and using it as the second indium purification influence characteristics of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters.

[0162] In this implementation, the component dimension order that is completely consistent with the current batch data can be used to arrange the purification influence weights of each component of the waste corresponding to each historical optimal process parameter into vector data, which serves as the second indium purification influence feature. No additional dimension mapping and alignment operations are required, simplifying the matching calculation process.

[0163] For example, the weight of the influence of each component of the waste on purification corresponding to each historical optimal process parameter can be determined by empirical values.

[0164] For example, following the same component dimension order as the current batch data, the purification influence weights of each component of the waste corresponding to a certain historical optimal process parameter are calibrated and arranged in the same order to obtain a vector, which is the second indium purification influence feature corresponding to that historical optimal process parameter.

[0165] This implementation method determines the feed component vector corresponding to the component detection data of the current batch of waste as the feed component feature, following the same component dimension order. At the same time, it determines the historical feed component vector corresponding to the historical component detection data of multiple historical optimal process parameters as the historical feed component feature, which can ensure the uniformity of feature matching dimensions and improve the accuracy of target process parameter selection. Following the same component dimension order, it determines the indium purification influence vector of multiple components corresponding to the component detection data of the current batch of waste as the corresponding indium purification influence feature. The dimensions and historical data are completely aligned during matching, which can avoid matching errors caused by component order and improve the reliability of matching degree calculation.

[0166] By using this method, the indium purification influence vectors of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters are determined according to the same component dimension order as the corresponding indium purification influence features. This is consistent with the feature dimension order of the current batch, which can reduce matching calculation errors and improve the adaptability of target process parameters and current batch waste.

[0167] This application also provides a control parameter optimization system for indium metal purification, including units for implementing the method described above.

[0168] Figure 9 A schematic diagram of the logic structure of a control parameter optimization method system for indium metal purification provided in this application embodiment is shown below. Figure 9 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0169] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0170] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0171] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0172] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0173] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0174] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0175] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for optimizing control parameters in the purification of metallic indium, characterized in that, The method includes: Obtain the composition detection data of the current batch of waste; determine the feed composition characteristics corresponding to the composition detection data of the current batch of waste; obtain the first indium purification influence characteristics of multiple components corresponding to the composition detection data of the current batch of waste; obtain the historical composition detection data of multiple historical optimal process parameters; determine the historical feed composition characteristics corresponding to the historical composition detection data of multiple historical optimal process parameters; obtain the second indium purification influence characteristics of multiple components corresponding to the historical composition detection data of multiple historical optimal process parameters. The similarity between the feed composition characteristics and the historical feed composition characteristics of multiple historical optimal process parameters is determined as the first matching degree between the composition detection data of the current batch of waste and the historical composition detection data of multiple historical optimal process parameters; the similarity between the first indium purification influence characteristic and the second indium purification influence characteristic of multiple historical optimal process parameters is determined as the second matching degree between the composition detection data of the current batch of waste and the historical composition detection data of multiple historical optimal process parameters. Obtain the first matching degree weight and the second matching degree weight; determine the sum of the first matching degree weight and the product of the first matching degree, the second matching degree weight and the product of the second matching degree, as multiple comprehensive matching degrees of the current batch of waste material composition detection data and the historical composition detection data of multiple historical optimal process parameters, and determine the maximum comprehensive matching degree of multiple comprehensive matching degrees; determine the historical optimal process parameter corresponding to the maximum comprehensive matching degree as the target process parameter; perform indium purification on the current batch of waste material according to the target process parameter.

2. The method according to claim 1, characterized in that, The method further includes: Identify cross-stage components in the current batch of waste material's composition analysis data that are compatible with parameter adjustments for different purification stages; when the number of cross-stage components in the current batch of waste material is zero, obtain the historical adjustment range and standard adjustment range of single-stage process parameters corresponding to multiple historically optimal process parameters; determine the difference between the historical adjustment range and standard adjustment range of single-stage process parameters corresponding to multiple historically optimal process parameters as the redundancy adjustment range of single-stage process parameters; determine multiple redundancy adjustment degrees corresponding to multiple single-stage process parameters; determine the sum of multiple redundancy adjustment degrees corresponding to multiple historically optimal process parameters as the comprehensive redundancy adjustment degree corresponding to multiple historically optimal process parameters; among them, cross-stage components include copper impurity exceeding the standard and iron impurity exceeding the standard; the larger the redundancy adjustment range, the greater the redundancy adjustment degree; Obtain the comprehensive matching degree weight and comprehensive redundancy adjustment degree weight corresponding to multiple historical optimal process parameters; determine the sum of the comprehensive matching degree weight and the product of the comprehensive matching degree and the product of the comprehensive redundancy adjustment degree weight and the comprehensive redundancy adjustment degree corresponding to multiple historical optimal process parameters, and determine the maximum corrected matching degree among multiple corrected matching degrees; determine the historical optimal process parameter corresponding to the maximum corrected matching degree, and use it as the target process parameter; purify indium in the current batch of waste according to the target process parameter.

3. The method according to claim 2, characterized in that, Determine multiple redundancy adjustment degrees corresponding to the redundancy adjustment range of single-stage process parameters for multiple components, including: Obtain the standard redundancy adjustment range of process parameters for a single step corresponding to multiple components; Determine and normalize the ratio of the redundant adjustment range of the single-stage process parameters corresponding to multiple components to the standard redundant adjustment range, and use this ratio as multiple redundancy adjustment degrees corresponding to the redundant adjustment range of the single-stage process parameters corresponding to multiple components.

4. The method according to claim 3, characterized in that, The method further includes: When refining indium from the current batch of waste according to the target process parameters, the following steps are taken: 1) Obtain the abnormal operating conditions corresponding to the target process parameters; 2) Obtain the target process parameter adjustment range for the abnormal operating conditions corresponding to the target process parameters; 3) Obtain the process parameter adjustment range for the abnormal operating conditions corresponding to multiple historical optimal process parameters; 4) Determine the difference between the target process parameter adjustment range and the process parameter adjustment range for the abnormal operating conditions corresponding to the multiple historical optimal process parameters, using this difference as the abnormal element adjustment range for the multiple historical optimal process parameters; 5) Determine the abnormal element adjustment degree corresponding to the abnormal element adjustment range for the multiple historical optimal process parameters; where abnormal operating conditions include excessive impurities in the leaching solution and abnormal electrolytic cell temperature; 6) The larger the abnormal element adjustment range, the greater the abnormal element adjustment degree. Obtain the abnormal element adjustment degree weights corresponding to multiple historical optimal process parameters; determine the sum of the comprehensive matching degree weight and the product of the comprehensive matching degree, the comprehensive redundancy adjustment degree weight and the comprehensive redundancy adjustment degree, and the abnormal element adjustment degree weight and the product of the abnormal element adjustment degree, as the abnormal handling matching degree corresponding to multiple historical optimal process parameters, and determine the maximum abnormal handling matching degree among multiple abnormal handling matching degrees; determine the historical optimal process parameter corresponding to the maximum abnormal handling matching degree as the target process parameter; continue indium purification on the current batch of waste according to the target process parameter.

5. The method according to claim 4, characterized in that, Determine the degree of adjustment of abnormal elements corresponding to the adjustment range of multiple historical optimal process parameters, including: Obtain the adjustment range of standard abnormal elements corresponding to multiple historical optimal process parameters; The ratio of the abnormal element adjustment degree to the standard abnormal element adjustment range corresponding to multiple historical optimal process parameters is determined and normalized, and used as the abnormal element adjustment degree corresponding to the abnormal element adjustment range corresponding to multiple historical optimal process parameters.

6. The method according to claim 5, characterized in that, The method further includes: Obtain historical and standard intermediate product indices for abnormal operating conditions corresponding to multiple historical optimal process parameters; determine the difference between historical and standard intermediate product indices for abnormal operating conditions corresponding to multiple historical optimal process parameters as intermediate product index deviation values; determine the intermediate product index deviation degree corresponding to the intermediate product index deviation values ​​for multiple historical optimal process parameters. Obtain the deviation weights of intermediate product indicators corresponding to multiple historical optimal process parameters; determine the product of the deviation weights and deviations of intermediate product indicators corresponding to multiple historical optimal process parameters as the intermediate product deviation matching degree; determine the difference between the anomaly handling matching degree and the intermediate product deviation matching degree corresponding to the abnormal operating conditions of multiple historical optimal process parameters as the anomaly handling deviation matching degree, and determine the maximum anomaly handling deviation matching degree among multiple anomaly handling deviation matching degrees; determine the historical optimal process parameter corresponding to the maximum anomaly handling deviation matching degree as the target process parameter; continue indium purification of the current batch of waste according to the target process parameter.

7. The method according to claim 6, characterized in that, Determine the intermediate product index deviation degree corresponding to the intermediate product index deviation values ​​corresponding to multiple historical best process parameters, including: Obtain the standard intermediate product index deviation values ​​corresponding to multiple historical optimal process parameters; The ratio of the abnormal element adjustment degree to the standard intermediate product index deviation value corresponding to multiple historical optimal process parameters is determined and normalized, and used as the intermediate product index deviation degree corresponding to the intermediate product index deviation value corresponding to multiple historical optimal process parameters.

8. The method according to claim 7, characterized in that, Determine the feed composition characteristics corresponding to the composition detection data of the current batch of waste, including: Following the same component dimension order, determine the feed component vector corresponding to the component detection data of the current batch of waste, and use it as the feed component feature corresponding to the component detection data of the current batch of waste; Determine the historical feed composition characteristics corresponding to historical composition detection data for multiple historical optimal process parameters, including: Following the same component dimension order, determine the historical feed component vectors corresponding to the historical component detection data of multiple historical optimal process parameters, and use them as the historical feed component features corresponding to the historical component detection data of multiple historical optimal process parameters.

9. The method according to claim 8, characterized in that, Obtain the first indium purification influence characteristics of multiple components corresponding to the component analysis data of the current batch of waste, including: Following the same component dimension order, determine the first indium purification influence vector of multiple components corresponding to the component detection data of the current batch of waste, and use it as the first indium purification influence feature of multiple components corresponding to the component detection data of the current batch of waste. Obtain the second indium purification influence characteristics of multiple components corresponding to historical component detection data of multiple historical optimal process parameters, including: Following the same component dimension order, the second indium purification influence vector of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters is determined, and it serves as the second indium purification influence feature of multiple components corresponding to the historical component detection data of multiple historical optimal process parameters.

10. A control parameter optimization system for the purification of metallic indium, characterized in that, Includes units for implementing the method of any one of claims 1 to 9.

Images