Extraction flow control method and device, electronic equipment, storage medium and product

Abstract

The application provides an extraction flow control method and device, electronic equipment, storage medium and product. The method is based on an extracted liquid surface image collected at a current time, performs color space conversion, and determines HSV color data at the current time. Based on a pre-constructed standard database, metal concentration standard data corresponding to the HSV color data at the current time is determined. Based on the HSV color data at the current time and historical flow data, metal concentration prediction data at a next time is predicted. Based on the metal concentration standard data and the metal concentration prediction data, flow adjustment data is determined, and flow control is performed based on the flow adjustment data. The technical solution of the application can determine the metal concentration based on the color characteristics of the extraction liquid surface, realize automatic detection of the metal concentration, improve the efficiency of metal concentration detection, and thus ensure the efficiency and accuracy of flow control and improve the extraction accuracy.

Description

Technical Field

[0001] This application relates to the field of extraction technology, and in particular to an extraction flow control method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] Extraction, also known as solvent extraction or liquid-liquid extraction, is a method that utilizes the difference in solubility or partition coefficient of a substance in two immiscible or slightly soluble solvents to transfer a solute from one solvent to another. It is widely used in chemical, metallurgical, food and other industries.

[0003] In the non-ferrous metal hydrometallurgical industry, solvent extraction is a key process for separating metals such as nickel, cobalt, and manganese. During the extraction process, the feed flow rate needs to be adjusted according to the concentration of each metal in the extract. The traditional extraction method involves manual sampling and laboratory testing to obtain the concentration of each metal. However, manual testing of samples in the laboratory takes a long time, usually more than two hours, which leads to a lag in flow rate control, thus affecting the efficiency of extraction flow rate control and the accuracy of extraction. Summary of the Invention

[0004] Based on the above requirements, this application proposes an extraction flow control method, device, electronic equipment, storage medium, and product, which can realize the automatic detection of metal concentration in the extraction solution, improve detection efficiency, ensure the efficiency and accuracy of flow control, and thus improve extraction accuracy.

[0005] To achieve the above objectives, this application proposes the following technical solution:

[0006] According to a first aspect of the embodiments of this application, an extraction flow control method is provided, comprising:

[0007] Based on the collected image of the extraction liquid surface at the current moment, color space conversion is performed to determine the HSV color data at the current moment;

[0008] Based on a pre-built standard database, the metal concentration standard data corresponding to the HSV color data at the current moment is determined; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values;

[0009] Based on the current HSV color data and historical flow data, predict the metal concentration data for the next moment;

[0010] Based on the standard metal concentration data and the predicted metal concentration data, flow adjustment data is determined, and flow control is performed based on the flow adjustment data.

[0011] Optionally, based on the acquired image of the extraction liquid surface at the current moment, a color space conversion is performed to determine the HSV color data at the current moment, including:

[0012] The ROI is cropped from the current extraction liquid surface image to obtain the region to be extracted;

[0013] Based on the pixel data of the region to be extracted, a color space conversion is performed to obtain the HSV color data at the current moment.

[0014] Optionally, based on a pre-built standard database, the metal concentration standard data corresponding to the HSV color data at the current moment is determined, including:

[0015] A predetermined number of HSV color data that are closest to the HSV color data at the current moment are retrieved from a pre-built standard database as candidate HSV color data;

[0016] The candidate metal concentration standard data corresponding to each candidate HSV color data is retrieved from the pre-built standard database, and a weighted average is calculated for all candidate metal concentration standard data to obtain the metal concentration standard data corresponding to the HSV color data at the current time.

[0017] Optionally, based on the standard metal concentration data and the predicted metal concentration data, flow adjustment data is determined, including:

[0018] Determine the concentration deviation sequence between the metal concentration standard data and the metal concentration prediction data;

[0019] Based on the pre-constructed flow influence coefficient matrix and the concentration deviation sequence, flow adjustment data is determined; wherein, the flow influence coefficient matrix stores the influence coefficients of the flow change of the flow adjustment component on the concentration of each metal.

[0020] Optionally, based on the current HSV color data and historical flow data, predict the metal concentration for the next time step, including:

[0021] Use the traffic data from historical moments prior to the current moment for a preset duration as historical traffic data;

[0022] The current HSV color data and the historical flow data are input into a pre-trained component concentration prediction model to obtain the metal concentration prediction data for the next time step.

[0023] The component concentration prediction model is obtained by predicting the metal concentration of the sample HSV color data at the first moment and the sample flow rate data for a preset time period before the first moment, and the model is trained with the goal of minimizing the difference between the sample prediction data and the sample standard data at the second moment. The second moment is the moment after the first moment, and the sample standard data at the second moment is the metal concentration obtained by manually testing the extract at the second moment.

[0024] Optionally, the extraction flow control method also includes:

[0025] Obtain laboratory data obtained through manual testing, the laboratory data including first HSV color data and first metal concentration data corresponding to the first HSV color data;

[0026] Query the standard database to see if the first metal concentration data is stored;

[0027] If the standard database stores the first metal concentration data, then the HSV color data corresponding to the first metal concentration data in the standard database is updated to the first HSV color data.

[0028] If the first metal concentration data is not stored in the standard database, then the first HSV color data and the first metal concentration data corresponding to the first HSV color data are stored in the standard database.

[0029] According to a second aspect of the embodiments of this application, an extraction flow control device is provided, comprising:

[0030] The color data determination module is used to perform color space conversion based on the extracted liquid surface image acquired at the current moment, and determine the HSV color data at the current moment.

[0031] The concentration determination module is used to determine the metal concentration standard data corresponding to the HSV color data at the current moment based on a pre-built standard database; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values;

[0032] The concentration prediction module is used to predict the metal concentration data for the next moment based on the HSV color data and historical flow data at the current moment.

[0033] The flow adjustment module is used to determine flow adjustment data based on the metal concentration standard data and the metal concentration prediction data, and to perform flow control based on the flow adjustment data.

[0034] According to a third aspect of the embodiments of this application, an electronic device is provided, including: a memory and a processor;

[0035] The memory is connected to the processor and is used to store programs;

[0036] The processor is used to implement the above-described extraction flow control method by running the program in the memory.

[0037] According to a fourth aspect of the embodiments of this application, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-described extraction flow control method is implemented.

[0038] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including computer program instructions, which, when executed by a processor, cause the processor to implement the above-described extraction flow control method.

[0039] The extraction flow control method proposed in this application involves: performing color space conversion based on the acquired image of the extraction liquid surface at the current moment to determine the HSV color data at the current moment; determining the metal concentration standard data corresponding to the HSV color data at the current moment based on a pre-constructed standard database; wherein the standard database stores at least one set of HSV color data and corresponding metal concentration standard values; predicting the metal concentration prediction data for the next moment based on the HSV color data at the current moment and historical flow data; determining the flow adjustment data based on the metal concentration standard data and the metal concentration prediction data; and performing flow control based on the flow adjustment data. By adopting the technical solution of this application, metal concentration can be determined based on the color characteristics of the extraction liquid surface, realizing automatic metal concentration detection, improving the efficiency of metal concentration detection, and thus ensuring the efficiency and accuracy of flow control, thereby improving extraction accuracy. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, 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 embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A schematic flowchart of an extraction flow control method provided in an embodiment of this application;

[0042] Figure 2 A schematic flowchart of another extraction flow control method provided in an embodiment of this application;

[0043] Figure 3This is a schematic diagram of an extraction flow control device provided in an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0045] The technical solutions of this application are applicable to metal extraction scenarios. By employing the technical solutions of this application, automatic detection of metal concentration in the extract can be achieved, improving detection efficiency, ensuring the efficiency and accuracy of flow control, and thus improving extraction accuracy.

[0046] In the non-ferrous metal hydrometallurgical industry, solvent extraction is a key process for separating metals such as nickel, cobalt, and manganese. During extraction, the feed flow rate needs to be controlled to ensure stable composition with minimal variation. Current flow control relies on traditional laboratory methods: manual sampling and analysis to determine the concentration of each metal. The feed flow rate is then adjusted based on these concentrations to maintain composition stability. However, manual analysis is time-consuming, taking more than two hours. This leads to a lag in determining metal concentrations, which in turn delays flow rate control, affecting efficiency and accuracy, and consequently, extraction accuracy.

[0047] Based on this, this application proposes an extraction flow control method. This technical solution can realize the automatic detection of metal concentration in the extract, improve the detection efficiency, and thus solve the problems of low flow control efficiency and accuracy and low extraction accuracy in the prior art.

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] Exemplary methods

[0050] See Figure 1 As shown in the embodiment of this application, an extraction flow rate control method is proposed. The method includes:

[0051] S101. Based on the collected image of the extraction liquid surface at the current moment, perform color space conversion to determine the HSV color data at the current moment.

[0052] For metal extraction processes, an extraction tank is typically used, and a corresponding light source is required. This embodiment requires capturing images of the extraction liquid surface; therefore, an image acquisition device, such as a camera or industrial camera, is also necessary. The light source is arranged in a ring, and its wavelength can be set according to the metal to be extracted. For example, for Co, a wavelength of 530 nm is preferred. In this embodiment, the image acquisition device is preferably installed approximately 1.5 m above the extraction tank, at a 30° angle, to avoid glare.

[0053] This embodiment uses color feature digitization to quickly determine metal concentration. Therefore, this embodiment needs to acquire the current moment's image of the extraction liquid surface from the image acquisition device, perform color space conversion on the extraction liquid surface image, and determine the current moment's HSV color data. HSV color data is a color representation method based on human visual perception, which decomposes color into three components: hue, saturation, and value. Hue represents the basic attribute of a color, which is what we usually call "color," such as red, green, and blue. Its value range is from 0° to 360°. For example, 0° or 360° is red, 120° is green, and 240° is blue. Saturation represents the purity or vividness of a color. The higher the saturation, the more vivid the color. The lower the saturation, the closer the color is to gray. Its value range is from 0 to 1 (or 0% to 100%). For example, 0 represents gray (no hue), and 1 represents a pure color (no white or black mixture). Value represents the lightness or darkness of a color. The higher the value, the brighter the color. The lower the value, the darker the color. Its value range is from 0 to 1 (or 0% to 100%). For example, 0 represents black, and 1 represents the brightest color (depending on hue and saturation).

[0054] In this embodiment, color space conversion is performed on the extraction liquid surface image. This involves converting the RGB values ​​of each pixel in the extraction liquid surface image to HSV values. Based on the HSV values ​​of each pixel, the HSV color data of the extraction liquid surface image is determined. Specifically, after converting the RGB values ​​of each pixel in the extraction liquid surface image to HSV values, a truncated mean method is used to remove the highest k% and lowest k% data (k is chosen empirically, preferably 5). Then, the average value of all remaining HSV values ​​is calculated, and this average value is used as the HSV color data of the extraction liquid surface image, i.e., the HSV color data at the current moment.

[0055] The specific steps are as follows:

[0056] First, the ROI is cropped from the current extraction liquid surface image to obtain the region to be extracted.

[0057] In this embodiment, after acquiring the extraction liquid surface image at the current moment, it is necessary to select the region of interest from the extraction liquid surface image and crop the region of interest as the region to be extracted. The region of interest is preferably the central region of the extraction liquid surface image. Extracting the region of interest can reduce the computational load within a limited range and also reduce potential edge artifacts.

[0058] In addition, to ensure the accuracy of HSV color data, the current extraction liquid surface image can be denoised before ROI cropping. For example, an adaptive median filtering algorithm can be used to filter out salt-and-pepper noise with a high probability and better preserve the details of the image.

[0059] Second, perform color space conversion based on the pixel data of the region to be extracted to obtain the HSV color data at the current moment.

[0060] After determining the region to be extracted in the extraction liquid surface image, this embodiment needs to obtain the pixel data of each pixel in the region to be extracted, perform color space conversion on each pixel data to obtain the HSV color value of each pixel, and use the truncated mean method to remove the highest k% data and the lowest k% data (k is selected based on experience, preferably 5). Then, calculate the average value of all remaining HSV values ​​and use this average value as the HSV color data at the current time.

[0061] S102. Based on a pre-built standard database, determine the metal concentration standard data corresponding to the HSV color data at the current moment.

[0062] In this embodiment, a standard database is pre-built, which stores at least one set of HSV color data and corresponding metal concentration standard values. In this embodiment, after determining the HSV color data at the current moment, the system directly queries the standard database for the HSV color data at the current moment, finds the HSV color data that is closest to the current HSV color data, and calculates the metal concentration standard data corresponding to the current HSV color data based on the metal concentration standard value corresponding to the closest HSV color data. For example, if one closest HSV color data is found, the metal concentration standard value corresponding to the closest HSV color data is directly used as the metal concentration standard data corresponding to the current HSV color data. If multiple closest HSV color data are found, a weighted average of the metal concentration standard values ​​corresponding to each closest HSV color data is calculated based on the degree of similarity between each closest HSV color data and the current HSV color data to obtain the metal concentration standard data corresponding to the current HSV color data. The greater the degree of similarity between the closest HSV color data and the current HSV color data, the greater the weight of the metal concentration standard value corresponding to the closest HSV color data.

[0063] In this embodiment, the standard database is constructed based on historical manual laboratory test data. That is, manual sampling is performed and the obtained samples are tested in the laboratory to determine the concentration of each metal and the HSV color data of the current liquid surface image of the sample (the HSV color data is also determined by the color space conversion method in the above steps). The HSV color data of the sample and the concentration of each metal are stored in the standard database.

[0064] This embodiment can use a multidimensional hash table to store data, with the HSV value as the key to store the corresponding metal concentration, for example:

[0065] Table 1 Standard Database

[0066]

[0067] Specifically, this embodiment determines the metal concentration standard data corresponding to the HSV color data at the current moment based on a pre-built standard database, including the following steps:

[0068] First, a predetermined number of HSV color data that are closest to the current HSV color data are retrieved from a pre-built standard database as candidate HSV color data.

[0069] This embodiment requires comparing the HSV color data in the pre-built standard database with the HSV color data at the current moment one by one. It then retrieves a preset number of nearest neighbor HSV color data from the standard database and uses these nearest neighbor HSV color data as candidate HSV color data. For example, if the current HSV color data is (10°, 20%, 30%), then (9°, 20%, 30%), (10°, 19%, 30%), and (10°, 20%, 31%) are all nearest neighbor HSV color data.

[0070] In this embodiment, it is preferable to use KD-Tree to query the nearest HSV color data in the standard database.

[0071] Second, retrieve the candidate metal concentration standard data corresponding to each candidate HSV color data from the pre-built standard database, and calculate the weighted average of all candidate metal concentration standard data to obtain the metal concentration standard data corresponding to the HSV color data at the current moment.

[0072] In this embodiment, the weight of each candidate HSV color data is determined based on its similarity to the current HSV color data; that is, the closer the candidate HSV color data is to the current HSV color data, the greater its weight. Candidate metal concentration standard data corresponding to each candidate HSV color data are retrieved from the standard database. Then, a weighted average is calculated for all candidate metal concentration standard data to obtain the metal concentration standard data corresponding to the current HSV color data.

[0073] S103. Based on the current HSV color data and historical flow data, predict the metal concentration data for the next moment.

[0074] This embodiment pre-constructs a metal concentration prediction algorithm. This algorithm can predict the metal concentration at the next moment based on the current HSV color data and historical flow data. The flow data can include the flow rate of the feed pump, the flow rate of the acid valve, etc. Since a certain reaction time is required after adjusting the valve flow rate for the metal concentration in the extract to react accordingly, determining the flow rate corresponding to the current metal concentration requires checking the flow rate of a previous period. In this embodiment, the historical flow data is the flow rate data of historical moments before the current moment for a preset duration, preferably set to 3 minutes.

[0075] In this embodiment, the metal concentration prediction algorithm requires pre-collected training samples. These training samples include HSV color data at a first time step, sample flow rate data at a first time step, and sample metal concentration data at a second time step. The sample flow rate data at the first time step is the flow rate data for a preset duration prior to the first time step, and the second time step is the time step following the first time step. Based on the HSV color data and sample flow rate data at the first time step, the metal concentration prediction algorithm predicts the metal concentration at the second time step. The algorithm is trained with the objective of minimizing the difference between the predicted metal concentration data and the sample metal concentration data at the second time step.

[0076] Furthermore, this step specifically includes the following:

[0077] First, traffic data from historical moments prior to the current moment with a preset duration is used as historical traffic data.

[0078] Second, the current HSV color data and historical flow data are input into a pre-trained component concentration prediction model to obtain the metal concentration prediction data for the next moment.

[0079] This embodiment requires pre-training a component concentration prediction model, which is used to execute the metal concentration prediction algorithm. The current HSV color data and historical flow data are input into the trained component concentration prediction model, which outputs the metal concentration prediction data for the next time step. Training this component concentration prediction model first requires inputting sample HSV color data from the first time step and sample flow data from a preset time period prior to the first time step into the model to predict metal concentration, outputting sample prediction data for the second time step. The objective is to minimize the difference between this sample prediction data and the sample standard data from the second time step. The second time step is the time following the first time step, and the sample standard data for the second time step is the metal concentration obtained by manual analysis of the extract at the second time step. In this embodiment, the component concentration prediction model preferably uses an LSTM network.

[0080] S104. Based on standard metal concentration data and predicted metal concentration data, determine flow adjustment data and perform flow control based on the flow adjustment data.

[0081] During the extraction process, it is necessary to maintain the stability of the components with minimal changes, which means maintaining the stability of the metal concentration. Therefore, ideally, the metal concentration at the next moment should be the same as the metal concentration at the current moment. If it is predicted that the metal concentration at the next moment will be different from the metal concentration at the current moment, then the feed flow rate needs to be adjusted in time to make the metal concentration at the next moment closer to the metal concentration at the current moment.

[0082] This embodiment, after determining the standard metal concentration data for the current moment and the predicted metal concentration data for the next moment through the above steps, needs to determine the feed flow rate adjustment data based on the difference between the predicted metal concentration data for the next moment and the standard metal concentration data for the current moment, so that the metal concentration for the next moment can be close to the standard metal concentration data for the current moment. The flow rate adjustment data includes the flow rate of each feed valve during the extraction process. In this embodiment, after determining the flow rate adjustment data, the flow rate of each feed valve is controlled according to this flow rate adjustment data and the current operating status of each feed valve.

[0083] Specifically, based on standard metal concentration data and predicted metal concentration data, the flow rate adjustment data is determined, including the following steps:

[0084] First, determine the concentration deviation sequence between the standard metal concentration data and the predicted metal concentration data.

[0085] This embodiment requires calculating the difference between the standard data and the predicted data of metal concentration. The difference between the two is calculated as a concentration deviation sequence, which contains the difference between the predicted data and the standard data of metal concentration for each metal.

[0086] Second, based on the pre-constructed flow influence coefficient matrix and concentration deviation sequence, flow adjustment data are determined.

[0087] This embodiment pre-constructs a flow influence coefficient matrix, which stores the influence coefficients of flow rate changes of the flow regulation component on the concentrations of various metals, representing the sensitivity of each metal concentration to flow rate changes. Based on the pre-constructed flow influence coefficients and concentration deviation sequences, this embodiment determines the flow adjustment data according to a pre-set calculation method. The preferred pre-set calculation method is the matrix equation A*ΔF=ΔC, where A represents the flow influence coefficient matrix, ΔF represents the flow adjustment data, and ΔC represents the concentration deviation sequence. The flow adjustment data can be calculated using this matrix equation.

[0088] In this embodiment, the flow rate influence coefficient matrix is ​​preferably constructed using a step response test. By artificially changing a certain flow rate variable (e.g., feed pump flow rate, acid valve opening, etc.) while keeping other variables constant, the dynamic response of the target component concentration (i.e., the concentration of each metal) is monitored. A reverse step is then applied to restore the flow rate, and cross-tests with different step amplitudes are performed, while still monitoring the dynamic response of the target component concentration. The step response test is an existing technology, and the testing process will not be described in detail in this embodiment. The flow rate influence coefficient is analyzed using data obtained from the active perturbation of the step response test, as well as historical data on flow rate adjustments and concentration changes. The final flow rate influence coefficient matrix is ​​then determined based on the least squares method. For example, the flow rate influence coefficient matrix is ​​shown in the table below:

[0089] Table 2 Flow Influence Coefficient Matrix

[0090]

[0091] As described above, the extraction flow control method proposed in this application, based on the acquired image of the extraction liquid surface at the current moment, performs color space conversion to determine the HSV color data at the current moment; based on a pre-constructed standard database, it determines the metal concentration standard data corresponding to the HSV color data at the current moment; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values; based on the HSV color data at the current moment and historical flow data, it predicts the metal concentration prediction data for the next moment; based on the metal concentration standard data and the metal concentration prediction data, it determines the flow adjustment data, and performs flow control based on the flow adjustment data. By adopting the technical solution of this embodiment, the metal concentration can be determined based on the color characteristics of the extraction liquid surface, realizing automatic metal concentration detection, improving the efficiency of metal concentration detection, and thus ensuring the efficiency and accuracy of flow control, thereby improving extraction accuracy.

[0092] As an optional implementation, this application also proposes an extraction flow control method. See [link to relevant documentation]. Figure 2 As shown, the method includes:

[0093] S201. Obtain laboratory data obtained through manual testing.

[0094] This embodiment involves manually sampling the extract during the extraction process and conducting manual analysis of the samples in a laboratory. The metal concentration data of each metal in the sample is used as the first metal concentration data. The liquid surface image of the extract at the time of sampling is then converted to a color space to determine the HSV color data at that moment, which is used as the first HSV color data. Both the first HSV color data and the first metal concentration data are used as laboratory data. The method of color space conversion for the liquid surface image is the same as the method of color space conversion for the current moment's extract liquid surface image in the previous embodiment, and will not be repeated here.

[0095] S202. Query the standard database to see if the first metal concentration data is stored.

[0096] In this embodiment, after obtaining a set of laboratory data, it is necessary to query a pre-built standard database to see if the first metal concentration data from the laboratory data is already stored.

[0097] S203. If the standard database stores the first metal concentration data, then update the HSV color data corresponding to the first metal concentration data in the standard database to the first HSV color data.

[0098] If the standard database already stores the first metal concentration data from the laboratory data, then it is necessary to determine whether the HSV color data corresponding to the first metal concentration data stored in the standard database is the same as the first HSV color data in the laboratory data. If they are different, the HSV color data corresponding to the first metal concentration data in the standard database needs to be updated to the first HSV color data to update the data in the standard database.

[0099] S204. If the first metal concentration data is not stored in the standard database, then the first HSV color data and the first metal concentration data corresponding to the first HSV color data are stored in the standard database.

[0100] If the first metal concentration data from the laboratory data is not stored in the standard database, the first HSV color data and the first metal concentration data from the laboratory data are directly stored in the standard database to add data to the standard database.

[0101] Through the above steps, the standard database is continuously updated and expanded, making the data stored in the standard database increasingly reliable.

[0102] If the first metal concentration data in a certain laboratory dataset is already stored in the standard database, compare the first HSV color data in the laboratory dataset with the corresponding HSV color data of the first metal concentration data in the standard database. If the color deviation between the two exceeds a preset threshold (e.g., ±8%), then the current laboratory dataset is considered an abnormal sample. Abnormal samples cannot be used to update the standard database or to train the component concentration prediction model.

[0103] Exemplary device

[0104] Accordingly, embodiments of this application also provide an extraction flow control device, see [link to relevant documentation]. Figure 3 As shown, the device includes:

[0105] The color data determination module 100 is used to perform color space conversion based on the extracted liquid surface image acquired at the current moment, and determine the HSV color data at the current moment.

[0106] The concentration determination module 110 is used to determine the metal concentration standard data corresponding to the HSV color data at the current moment based on a pre-built standard database; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values;

[0107] The concentration prediction module 120 is used to predict the metal concentration data for the next moment based on the current HSV color data and historical flow data.

[0108] The flow adjustment module 130 is used to determine the flow adjustment data based on the standard metal concentration data and the predicted metal concentration data, and to perform flow control based on the flow adjustment data.

[0109] As can be seen from the above description, the extraction flow control device proposed in this application can determine the metal concentration based on the color characteristics of the extraction liquid surface, realize the automatic detection of metal concentration, improve the efficiency of metal concentration detection, and thus ensure the efficiency and accuracy of flow control, thereby improving the extraction accuracy.

[0110] As an optional implementation, another embodiment of this application discloses that the color data determination module 100 is specifically used for:

[0111] The ROI is cropped from the current extraction liquid surface image to obtain the region to be extracted;

[0112] The color space is converted based on the pixel data of the region to be extracted to obtain the HSV color data at the current moment.

[0113] As an optional implementation, another embodiment of this application discloses that the concentration determination module 110 is specifically used for:

[0114] A predetermined number of HSV color data that are closest to the current HSV color data are retrieved from a pre-built standard database as candidate HSV color data.

[0115] The system retrieves the candidate metal concentration standard data corresponding to each candidate HSV color data from a pre-built standard database, and calculates a weighted average of all candidate metal concentration standard data to obtain the metal concentration standard data corresponding to the HSV color data at the current moment.

[0116] As an optional implementation, another embodiment of this application discloses that the flow adjustment module 130 is specifically used for:

[0117] Determine the concentration deviation sequence between standard metal concentration data and predicted metal concentration data;

[0118] Based on the pre-constructed flow influence coefficient matrix and concentration deviation sequence, flow adjustment data is determined; wherein, the flow influence coefficient matrix stores the influence coefficients of the flow change of the flow adjustment component on the concentration of each metal.

[0119] As an optional implementation, another embodiment of this application discloses that the concentration prediction module 120 is specifically used for:

[0120] Use the traffic data from historical moments prior to the current moment for a preset duration as historical traffic data;

[0121] The current HSV color data and historical flow data are input into a pre-trained component concentration prediction model to obtain the metal concentration prediction data for the next time step.

[0122] The component concentration prediction model is obtained by predicting the metal concentration of the sample HSV color data at the first moment and the sample flow rate data at a preset time before the first moment, and the sample prediction data at the second moment is obtained by training with the goal of minimizing the difference between the sample prediction data and the sample standard data at the second moment. The second moment is the moment after the first moment, and the sample standard data at the second moment is the metal concentration obtained by manual analysis of the extract at the second moment.

[0123] As an optional implementation, another embodiment of this application discloses that the extraction flow control device further includes: an acquisition module, a query module, an update module, and a storage module.

[0124] The acquisition module is used to acquire laboratory data obtained by manual testing. The laboratory data includes the first HSV color data and the first metal concentration data corresponding to the first HSV color data.

[0125] The query module is used to query the standard database to see if the first metal concentration data is stored.

[0126] The update module is used to update the HSV color data corresponding to the first metal concentration data in the standard database to the first HSV color data if the first metal concentration data is stored in the standard database.

[0127] The storage module is used to store the first HSV color data and the first metal concentration data corresponding to the first HSV color data in the standard database if the first metal concentration data is not stored in the standard database.

[0128] The extraction flow control device provided in this embodiment belongs to the same concept as the extraction flow control method provided in the above embodiments of this application. It can execute the extraction flow control method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the extraction flow control method. Technical details not described in detail in this embodiment can be found in the specific processing content of the extraction flow control method provided in the above embodiments of this application, and will not be repeated here.

[0129] Exemplary electronic devices

[0130] Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 4 As shown, the device includes:

[0131] Memory 200 and processor 210;

[0132] The memory 200 is connected to the processor 210 and is used to store programs;

[0133] The processor 210 is configured to implement the extraction flow control method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0134] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0135] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:

[0136] A bus can include a pathway for transmitting information between various components of a computer system.

[0137] The processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0138] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0139] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0140] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0141] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0142] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0143] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement any of the steps of the extraction flow control method provided in the above embodiments of this application.

[0144] Exemplary computer program products and storage media

[0145] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the extraction flow control methods according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.

[0146] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0147] Furthermore, embodiments of this application may also be storage media storing a computer program thereon, the computer program being executed by a processor of the steps in the extraction flow control method according to various embodiments of this application as described in the "Exemplary Methods" section above.

[0148] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0149] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0150] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0151] The modules and sub-modules in the apparatus and terminal in the various embodiments of this application can be merged, divided, and deleted according to actual needs.

[0152] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0153] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0154] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0155] Those skilled in the art will further 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, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. 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.

[0156] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0157] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0158] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling extraction flow rate, characterized in that, include: Based on the collected image of the extraction liquid surface at the current moment, color space conversion is performed to determine the HSV color data at the current moment; Based on a pre-built standard database, the metal concentration standard data corresponding to the HSV color data at the current moment is determined; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values; The flow data of historical moments with a preset duration before the current moment are used as historical flow data. The HSV color data of the current moment and the historical flow data are input into a pre-trained component concentration prediction model to obtain the metal concentration prediction data for the next moment. A concentration deviation sequence between the standard metal concentration data and the predicted metal concentration data is determined. Based on a pre-constructed flow influence coefficient matrix and the concentration deviation sequence, flow adjustment data is determined, and flow control is performed based on the flow adjustment data. The flow influence coefficient matrix stores the influence coefficients of the flow rate changes of the flow adjustment component on each metal concentration. The component concentration prediction model is obtained by predicting the metal concentration of the sample HSV color data at the first moment and the sample flow rate data for a preset time period before the first moment, and the model is trained with the goal of minimizing the difference between the sample prediction data and the sample standard data at the second moment. The second moment is the moment after the first moment, and the sample standard data at the second moment is the metal concentration obtained by manual analysis of the extract at the second moment.

2. The extraction flow rate control method according to claim 1, characterized in that, Based on the acquired image of the extraction liquid surface at the current moment, a color space conversion is performed to determine the HSV color data at the current moment, including: The ROI is cropped from the current extraction liquid surface image to obtain the region to be extracted; Based on the pixel data of the region to be extracted, a color space conversion is performed to obtain the HSV color data at the current moment.

3. The extraction flow rate control method according to claim 1, characterized in that, Based on a pre-built standard database, the metal concentration standard data corresponding to the HSV color data at the current moment is determined, including: A predetermined number of HSV color data that are closest to the HSV color data at the current moment are retrieved from a pre-built standard database as candidate HSV color data; The candidate metal concentration standard data corresponding to each candidate HSV color data is retrieved from the pre-built standard database, and a weighted average is calculated for all candidate metal concentration standard data to obtain the metal concentration standard data corresponding to the HSV color data at the current time.

4. The extraction flow rate control method according to claim 1, characterized in that, Also includes: Obtain laboratory data obtained through manual testing, the laboratory data including first HSV color data and first metal concentration data corresponding to the first HSV color data; Query the standard database to see if the first metal concentration data is stored; If the standard database stores the first metal concentration data, then the HSV color data corresponding to the first metal concentration data in the standard database is updated to the first HSV color data. If the first metal concentration data is not stored in the standard database, then the first HSV color data and the first metal concentration data corresponding to the first HSV color data are stored in the standard database.

5. An extraction flow control device, characterized in that, include: The color data determination module is used to perform color space conversion based on the extracted liquid surface image acquired at the current moment, and determine the HSV color data at the current moment. The concentration determination module is used to determine the metal concentration standard data corresponding to the HSV color data at the current moment based on a pre-built standard database; wherein, the standard database stores at least one set of HSV color data and corresponding metal concentration standard values; The concentration prediction module is used to take the flow data of historical times with a preset duration before the current time as historical flow data, input the HSV color data of the current time and the historical flow data into a pre-trained component concentration prediction model to obtain the metal concentration prediction data for the next time. A flow adjustment module is used to determine the concentration deviation sequence between the standard metal concentration data and the predicted metal concentration data, determine flow adjustment data based on a pre-constructed flow influence coefficient matrix and the concentration deviation sequence, and perform flow control based on the flow adjustment data; wherein, the flow influence coefficient matrix stores the influence coefficients of the flow change of the flow adjustment component on each metal concentration; The component concentration prediction model is obtained by predicting the metal concentration of the sample HSV color data at the first moment and the sample flow rate data for a preset time period before the first moment, and the model is trained with the goal of minimizing the difference between the sample prediction data and the sample standard data at the second moment. The second moment is the moment after the first moment, and the sample standard data at the second moment is the metal concentration obtained by manual analysis of the extract at the second moment.

6. An electronic device, characterized in that, include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the extraction flow control method as described in any one of claims 1 to 4 by running a program in the memory.

7. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the extraction flow control method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, It includes computer program instructions that, when executed by a processor, cause the processor to implement the extraction flow control method as described in any one of claims 1 to 4.

Images