An electric control method and system of an electrolytic cell automatic production line

Abstract

The application provides an electric control method and system of an electrolytic cell automatic production line, and belongs to the technical field of process control. The method acquires space-time potential data in real time through the construction of a multi-point potential sensor network to accurately identify potential abnormal areas. By constructing multi-dimensional electrolytic reaction state indicators, the method accurately distinguishes three types of electrolytic reaction states, namely, low-efficiency reaction, normal reaction and abnormal reaction, and dynamically adjusts the electrolytic reaction parameters of current density and electrolyte concentration accordingly, thereby realizing the adaptive and accurate adaptation of electrolytic reaction parameters to the actual reaction state in the electrolytic cell, effectively solving the problems of local current density out of control and imbalance between flow and electrochemical reaction dynamic matching caused by uneven electrolyte flow, and significantly improving the process control accuracy of the electrolytic cell automatic production line and optimizing the production efficiency and energy efficiency.

Description

Technical Field

[0001] This application relates to the field of process control technology, specifically to an electrical control method and system for an automated production line of an electrolytic cell. Background Technology

[0002] Currently, in the field of automated process control computing in the electrolysis industry, the operation and control of the electrolytic cell is a core element determining product quality and energy efficiency. The flow state of the electrolyte within the cell is particularly critical, directly affecting the uniformity and completeness of the chemical reaction, thus influencing the purity of the final electrolytic product and the stability of the electrolysis production line. However, existing process control methods rely on adjusting the overall flow rate or pressure at the inlet and outlet of the electrolytic cell. This control method, based on a single global electrolysis parameter, struggles to accurately perceive and address the complex and variable electrolyte flow conditions within the electrolytic cell. Furthermore, due to the internal structure of the electrolytic cell, electrode arrangement, and the reaction itself, uneven fluid resistance and heat distribution occur. Inlet and outlet data alone cannot reflect the true flow details within the electrolytic cell, thus hindering precise adjustment of electrolyte parameters and reducing the quality and efficiency of the automated electrolytic cell production line.

[0003] The information provided in the background section of this application is only for enhancing the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] In view of this, this application provides an electrical control method and system for an automated production line of an electrolytic cell, which can dynamically adjust the electrolysis reaction parameters.

[0005] In a first aspect, embodiments of this application provide an electrical control method for an automated production line of an electrolytic cell. The method includes: acquiring potential distribution data within the electrolytic cell; determining a potential spatiotemporal fluctuation feature vector based on the potential distribution data, and calculating a spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and historical potential spatiotemporal fluctuation feature vectors using a Pearson correlation coefficient algorithm; if the spatiotemporal correlation coefficient does not exceed a preset correlation coefficient threshold, determining a potential distribution grid diagram based on the potential distribution data; if the gradient value of a grid cell in the potential distribution grid diagram exceeds a preset gradient threshold, marking the current grid cell as... An abnormal potential region is identified, and a distribution map of the abnormal potential region is generated based on the abnormal potential region. Electrolysis reaction status indicators are determined based on the potential distribution grid map and the distribution map of the abnormal potential region. These indicators include the proportion of abnormal potential regions, potential uniformity, and process stability. The current electrolysis reaction evaluation level is determined based on the electrolysis reaction status indicators. These evaluation levels include inefficient electrolysis, normal electrolysis, and abnormal electrolysis. Electrolysis reaction parameters, including current density and electrolyte concentration, are dynamically adjusted based on the evaluation level.

[0006] Secondly, embodiments of this application provide an electrical control system for an automated electrolytic cell production line. This system includes: an acquisition module, a first determination module, a second determination module, a generation module, a third determination module, and a fourth determination module. The acquisition module is used to acquire potential distribution data within the electrolytic cell; the first determination module is used to determine a potential spatiotemporal fluctuation feature vector based on the potential distribution data, and calculate the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and historical potential spatiotemporal fluctuation feature vectors using the Pearson correlation coefficient algorithm; the second determination module is used to determine a potential distribution grid map based on the potential distribution data if the spatiotemporal correlation coefficient does not exceed a preset correlation coefficient threshold; the generation module is used to mark the current grid cell as a potential anomaly region if the gradient value of a grid cell in the potential distribution grid map exceeds a preset gradient threshold, and then... The potential anomaly region generates a potential anomaly region distribution map; the third determining module is used to determine the electrolysis reaction status index based on the potential distribution grid map and the potential anomaly region distribution map, the electrolysis reaction status index including the proportion of potential anomaly regions, potential uniformity index, and process stability index; the fourth determining module is used to determine the current electrolysis reaction evaluation level based on the electrolysis reaction status index, the electrolysis reaction evaluation level including inefficient electrolysis reaction, normal electrolysis reaction, and abnormal electrolysis reaction, and dynamically adjust the electrolysis reaction parameters based on the electrolysis reaction evaluation level, the electrolysis reaction parameters including current density and electrolyte concentration.

[0007] This application provides an electrical control method and system for an automated electrolytic cell production line. The method acquires spatiotemporal potential data in real time by constructing a multi-point potential sensor network to accurately identify abnormal potential regions. It also constructs multi-dimensional electrolytic reaction state indicators to accurately distinguish between inefficient, normal, and abnormal electrolytic reaction states. Based on these indicators, it dynamically adjusts the electrolytic reaction parameters, including current density and electrolyte concentration, achieving adaptive and precise matching between the electrolytic reaction parameters and the actual reaction state within the electrolytic cell. This effectively solves the problems of localized current density runaway and dynamic mismatch between flow and electrochemical reaction caused by uneven electrolyte flow, significantly improving the process control accuracy of the automated electrolytic cell production line and optimizing production efficiency and energy efficiency. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology 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.

[0009] Figure 1 This is a schematic flowchart of an electrical control method for an automated electrolytic cell production line provided in an exemplary embodiment of this application.

[0010] Figure 2 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0011] Figure 3 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0012] Figure 4 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0013] Figure 5 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0014] Figure 6 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0015] Figure 7 This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application.

[0016] Figure 8This is a schematic flowchart of an electrical control method for an automated production line of an electrolytic cell provided in another exemplary embodiment of this application. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this application will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this application.

[0018] The terms “a,” “one,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended inclusion and that other elements / components / etc. may exist in addition to those listed. The terms “first” and “second” are used only as markers and are not a limitation on the number of objects.

[0019] Currently, in the field of automated process control computing in the electrolysis industry, the operation and control of the electrolytic cell is a core element determining product quality and energy efficiency. The flow state of the electrolyte within the cell is particularly critical, directly affecting the uniformity and completeness of the chemical reaction, thus influencing the purity of the final electrolytic product and the stability of the electrolysis production line. However, existing process control methods rely on adjusting the overall flow rate or pressure at the inlet and outlet of the electrolytic cell. This control method, based on a single global electrolysis parameter, struggles to accurately perceive and address the complex and variable electrolyte flow conditions within the electrolytic cell. Furthermore, due to the internal structure of the electrolytic cell, electrode arrangement, and the reaction itself, uneven fluid resistance and heat distribution occur. Inlet and outlet data alone cannot reflect the true flow details within the electrolytic cell, thus hindering precise adjustment of electrolyte parameters and reducing the quality and efficiency of the automated electrolytic cell production line.

[0020] For example, as the electrolyte flows through different areas of the electrolytic cell, its velocity and direction change due to differences in local resistance, forming unstable eddies or stagnant zones. This non-uniformity of the internal flow state leads to an imbalance in the dynamic matching between electrolyte flow and electrochemical reaction. Since the rate of the electrolytic reaction is closely related to the current density distribution, non-uniform flow directly causes uncontrolled local current density; in some areas, the electrolytic reaction may be too fast, potentially generating impurities, while in other areas, the reaction may be too slow, reducing efficiency.

[0021] Therefore, how to achieve real-time monitoring of the flow state in each region inside the electrolytic cell and accurately adjust the electrolysis reaction parameters accordingly, ensuring that the electrolyte flow can not only meet the overall chemical reaction requirements but also automatically adapt to the dynamic changes in internal resistance, thereby maintaining a uniform and stable current density, has become a technical problem that needs to be solved to improve the quality and efficiency of automated electrolytic cell production lines.

[0022] This application provides an electrical control method for an automated electrolytic cell production line, such as... Figure 1 The method for controlling the electrical system of the automated electrolytic cell production line shown herein may include the following steps: Step S110: Obtain potential distribution data within the electrolytic cell; Step S120: Determine the potential spatiotemporal fluctuation feature vector based on the potential distribution data, and use the Pearson correlation coefficient algorithm to calculate the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and the historical potential spatiotemporal fluctuation feature vector; Step S130: If the spatiotemporal correlation coefficient does not exceed the preset correlation coefficient threshold, then determine the potential distribution grid map based on the potential distribution data; Step S140: If the gradient value of a grid cell in the potential distribution grid exceeds a preset gradient threshold, the current grid cell is marked as a potential anomaly region, and a potential anomaly region distribution map is generated based on the potential anomaly region. Step S150: Determine the electrolysis reaction status indicators based on the potential distribution grid diagram and the potential anomaly region distribution diagram. The electrolysis reaction status indicators include the proportion of potential anomaly regions, potential uniformity indicators, and process stability indicators. Step S160: Determine the current electrolysis reaction evaluation level based on the electrolysis reaction status indicators. The electrolysis reaction evaluation level includes inefficient electrolysis reaction, normal electrolysis reaction, and abnormal electrolysis reaction. Adjust the electrolysis reaction parameters dynamically based on the electrolysis reaction evaluation level. The electrolysis reaction parameters include current density and electrolyte concentration.

[0023] According to the electrical control method for an automated electrolytic cell production line provided in this application, this method can accurately determine the degree of deviation between the overall operating conditions and normal state of the electrolytic cell by quantifying the spatiotemporal correlation between the potential spatiotemporal fluctuation feature vector and the historical potential spatiotemporal fluctuation feature vector, and can quickly identify abnormal fluctuation trends in the electrolysis process. After determining that the overall operating conditions deviate from the normal state, the method identifies the potential abnormal area by constructing a potential distribution grid map and based on a preset gradient threshold, solving the problem that traditional process control methods cannot distinguish between local flow abnormalities and changes in overall flow demand. By constructing multi-dimensional electrolysis reaction state indicators, the method can accurately distinguish between three types of electrolysis reaction states: inefficient reaction, normal reaction, and abnormal reaction. Based on this, the core electrolysis reaction parameters, such as current density and electrolyte concentration, can be dynamically adjusted in a targeted manner. This achieves adaptive and precise matching between the electrolysis reaction parameters and the actual reaction state in the electrolytic cell, effectively solving the problems of local current density runaway and dynamic mismatch between flow and electrochemical reaction caused by uneven electrolyte flow. This significantly improves the process control accuracy of the automated electrolytic cell production line and optimizes production efficiency and energy efficiency.

[0024] The following is a detailed description of each step of the electrical control method for the automated electrolytic cell production line provided in the embodiments of this application: In one embodiment of this application, step S110 involves acquiring potential distribution data within the electrolytic cell. Specifically, a multi-point potential sensor network can be deployed within the electrolytic cell to collect potential values ​​at various locations and form potential distribution data. For example, a conventional industrial rectangular electrolytic cell measuring 2 meters long and 1 meter wide can be used as an example. A multi-point potential sensor network is deployed within the electrolytic cell, using potential sensors resistant to electrolyte corrosion and electromagnetic interference. Three representative planes are selected along the electrolyte depth direction, with 25 sensor nodes evenly arranged at 0.2-meter intervals on each plane, for a total of 75 sensors. All sensor nodes are fixed with insulating supports to prevent contact with electrodes within the cell and interference with the normal electrolytic reaction. Subsequently, all potential sensors are set to a sampling frequency of 100 Hz to continuously collect potential time-series data from different spatial locations to form potential distribution data.

[0025] In one embodiment of this application, step S120, which involves determining the potential spatiotemporal fluctuation feature vector based on potential distribution data and calculating the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and historical potential spatiotemporal fluctuation feature vectors using the Pearson correlation coefficient algorithm, further includes the following steps: Figure 2 As shown, the specific content is as follows: Step S210: Determine the potential distribution sequence based on the potential distribution data, and based on the potential distribution sequence, use the sliding window algorithm to determine the mean of the potential spatial gradient and the mean of the potential time change rate; Step S220: Based on the potential distribution sequence, Fourier transform is used to extract the main wave frequency, and the dominant frequency energy is determined according to the main wave frequency; Step S230: Calculate the standard deviation of the potential distribution sequence and use the standard deviation of the potential distribution sequence as the mean of the potential fluctuation amplitude; Step S240: Determine the potential spatiotemporal fluctuation feature vector based on the mean of the potential spatial gradient, the mean of the potential time change rate, the dominant frequency energy, and the mean of the potential fluctuation amplitude.

[0026] Specifically, the acquired potential distribution data is grouped according to the spatial location of the potential sensors and sorted according to the acquisition time to generate a structured potential distribution sequence. Then, a sliding window algorithm is used to perform windowed analysis on the potential distribution sequence. The window parameters (window length, step size) are set according to the electrolytic cell process characteristics and the sensor sampling frequency. Within each sliding window, the ratio of the potential difference between adjacent potential sensor nodes to their spatial distance is calculated using a central difference algorithm to obtain the potential spatial gradient value within a single window. The average potential spatial gradient values ​​of all windows are then calculated to obtain the mean potential spatial gradient. Simultaneously, the first-order difference of the potential time series within the window is calculated, and then divided by the potential sensor sampling interval to obtain the potential time change rate within a single window. The average potential time change rate of all windows is then calculated to obtain the mean potential time change rate. The mean potential spatial gradient and the mean potential time change rate quantify the spatial distribution difference of the potential and the rate of change of the potential in the time dimension, respectively.

[0027] Specifically, a Fast Fourier Transform (FFT) can be performed on the structured potential distribution sequence to convert the time-domain potential change data into frequency-domain data, obtaining the frequency distribution spectrum of potential fluctuations. The frequency value with the highest proportion and energy is extracted from the frequency distribution spectrum as the dominant fluctuation frequency, which reflects the core pattern of potential fluctuations within the electrolytic cell. Subsequently, according to the frequency band division standards preset in the electrolytic cell process, the frequency band to which the dominant fluctuation frequency belongs is determined, and the energy proportion of this frequency band in the overall frequency distribution spectrum is calculated. This proportion is used as the dominant frequency energy, achieving a quantitative characterization of the potential time-varying characteristics.

[0028] It is worth noting that standard deviation is the core statistical indicator for quantifying the dispersion of data. The standard deviation is calculated for all potential data in the entire potential distribution sequence. This standard deviation can reflect the overall fluctuation range and dispersion of the potential in the electrolytic cell in the spatiotemporal dimension. It can be directly used as the mean of the potential fluctuation amplitude to achieve a simple and efficient quantification of the potential fluctuation intensity.

[0029] Specifically, the mean of the spatial gradient of potential, the mean of the rate of change of potential over time, the dominant frequency energy, and the mean of the amplitude of potential fluctuations can be numerically concatenated in a preset fixed order to form a four-dimensional potential spatiotemporal fluctuation feature vector. This vector is a standardized set of numerical features, eliminating the redundancy of the original potential distribution data while retaining key information about the potential in four core dimensions: spatial distribution, temporal variation, frequency characteristics, and fluctuation intensity.

[0030] It should be noted that the historical potential spatiotemporal fluctuation feature vector is a baseline feature vector obtained after training with a large amount of experimental and production operation data under long-term normal production conditions of the electrolyzer. This vector is stored in the electrolyzer operating condition database after process verification. Because the physical dimensions of the four-dimensional feature indices of the potential spatiotemporal fluctuation feature vector differ—for example, the mean value of the potential spatial gradient is in V / m, the dominant frequency energy is a percentage, and the dynamic fluctuation amplitude is in μV—the difference in dimensions directly affects the accuracy of the correlation calculation. Therefore, it is necessary to normalize all feature values ​​of both the potential spatiotemporal fluctuation feature vector and the historical potential spatiotemporal fluctuation feature vector, mapping each feature value uniformly to the [0,1] interval to eliminate the influence of dimensions. Finally, the two calibrated and normalized feature vectors are substituted into the Pearson correlation coefficient formula to complete the calculation.

[0031] For example, after acquiring 10 consecutive seconds of potential distribution data and forming a potential distribution sequence, this sequence is grouped by the spatial location of the potential sensors and sorted by acquisition time. A sliding window algorithm with a window length of 200ms and a step size of 50ms is used for window analysis. The spatial gradient of the potential between adjacent 0.2-meter potential sensor nodes is calculated using the central difference algorithm, and the average spatial gradient is found to be 0.075V / m. Simultaneously, the potential time series within the window is first-order differencing and divided by a sampling interval of 0.01s, yielding an average potential time change rate of 0.18V / s. Next, a fast Fourier transform is performed on the potential distribution sequence to convert the time-domain potential data into a frequency-domain frequency distribution spectrum. The dominant fluctuation frequency with the highest energy proportion is extracted from the spectrum as 18Hz. Combined with the 12Hz-30Hz core frequency band standard preset by the electrolytic cell process, the dominant frequency energy of this frequency band is calculated to be 42%. Then, the standard deviation of the potential distribution sequence containing 75,000 potential data points was calculated, yielding a standard deviation of 14 μV, which was directly used as the mean potential fluctuation amplitude. Subsequently, the values ​​were concatenated according to a preset fixed order: mean potential spatial gradient, mean potential time change rate, dominant frequency energy, and mean potential fluctuation amplitude, forming the potential spatiotemporal fluctuation feature vector under the current operating conditions of the electrolyzer: [0.075V / m, 0.18V / s, 42%, 14μV]. Finally, this feature vector, along with the historical normal operating condition benchmark feature vector [0.08V / m, 0.2V / s, 45%, 15μV] retrieved from the electrolyzer operating condition database, was input into the Pearson correlation coefficient algorithm, and the calculated spatiotemporal correlation coefficient was 0.92.

[0032] In one embodiment of this application, step S130, if the spatiotemporal correlation coefficient does not exceed a preset correlation coefficient threshold, then determining the potential distribution grid map based on the potential distribution data, further includes the following steps: Figure 3 As shown, the specific content is as follows: Step S310: Based on the potential distribution data, determine the grid potential value of each grid cell using a bilinear interpolation algorithm; Step S320: Determine the grid potential value matrix based on the grid potential value of each grid cell, and generate a potential distribution grid map based on the grid potential value matrix.

[0033] Specifically, the preset correlation coefficient threshold can be determined based on the process characteristics of the electrolytic cell, long-term historical production and operation data, and the stability requirements of the on-site electrolytic reaction. For example, different types and specifications of electrolytic cells (such as rectangular electrolytic cells for copper electrolytic refining and other metal electrolysis), as well as different ranges of electrolytic process parameters (such as the process allowable range of current density and electrolyte concentration), will directly determine the normal range of potential spatiotemporal fluctuations, and thus affect the determination of the preset correlation coefficient threshold.

[0034] Because the fixed-interval deployment of potential sensors creates spatial gaps, it's impossible to fully characterize the potential distribution across the entire electrolytic cell. Bilinear interpolation, however, is an algorithm for interpolating and completing discrete two-dimensional data, combining computational efficiency with interpolation accuracy, and is well-suited to the two-dimensional spatial characteristics of the electrolytic cell's potential distribution. Based on the actual physical dimensions of the electrolytic cell and the deployment spacing of the potential sensors, equally spaced grid cell sizes are set. The target analysis plane of the electrolyte within the electrolytic cell is then divided into a fully covered two-dimensional grid. Each grid cell is assigned a unique spatial center coordinate, ensuring that the grid cells cover the electrolyte flow area without any blind spots. Subsequently, the three-dimensional spatial coordinates of all discrete potential sensor nodes are projected onto the corresponding electrolyte analysis plane, achieving precise matching with the gridded spatial coordinates, thus clarifying the specific location of each potential sensor node within the grid cell. Finally, taking each grid cell to be interpolated as the center, the four nearest discrete potential sensor nodes around it are selected as interpolation base points. The spatial coordinates of the four base points and the corresponding real-time potential values ​​are obtained. The data is substituted into the bilinear interpolation formula to complete the potential value calculation of the grid cell. The potential value calculation of all grid cells is completed in sequence according to this rule, realizing the transformation of discrete potential data into continuous grid potential data.

[0035] Next, following the row and column spatial order of the electrolytic cell's grid division, the grid potential values ​​of all grid units are arranged sequentially according to their corresponding spatial coordinates, forming a two-dimensional grid potential value matrix. The number of rows and columns in the matrix corresponds one-to-one with the number of rows and columns in the grid, and each element in the matrix is ​​the precise potential value of the corresponding grid unit. Subsequently, the grid potential values ​​of different values ​​in the two-dimensional grid potential value matrix are mapped to corresponding gradient colors. At the same time, key information such as the actual physical dimensions of the electrolytic cell, the true location of the discrete sensor nodes, and the spatial coordinate scale of the grid units are marked in the visualization interface, generating a visualized potential distribution grid map, realizing the transformation of the potential distribution state within the electrolytic cell from abstract numerical values ​​to intuitive spatial color distribution.

[0036] For example, taking a rectangular electrolytic cell measuring 2 meters long and 1 meter wide as an application scenario, 25 potential sensor nodes are deployed at 0.2-meter intervals in the depth plane of the mainstream electrolyte zone. Discrete potential distribution data of this plane has been acquired, and the calculated spatiotemporal correlation coefficient is 0.28, which does not exceed the preset correlation coefficient threshold of 0.7. This 2-meter × 1-meter electrolyte plane can be gridded. Combining the requirements for refined potential analysis with industrial computing efficiency, a grid cell size of 0.1 meters × 0.1 meters is set, dividing the plane into 20 rows (x-axis direction, 0.05m-1.95m) × 10 columns (y-axis direction, 0.05m-0.95m), totaling 200 grid cells, and assigning a unique spatial center coordinate to each grid cell. The spatial coordinates of the 25 discrete sensor nodes are then projected onto the grid plane and coordinate matching is completed. Subsequently, for each grid cell to be interpolated, the four nearest potential sensor nodes are selected as interpolation base points. For example, for a grid cell with coordinates A: (0.15m, 0.15m), four base points (0.0m, 0.0m), (0.2m, 0.0m), (0.0m, 0.2m), and (0.2m, 0.2m) are selected, with corresponding potential values ​​of 1.20V, 1.22V, 1.21V, and 1.23V, respectively. Substituting the above data into the bilinear interpolation formula, the grid potential value of the grid cell is calculated to be 1.215V. The potential value calculation of 200 grid cells is completed in sequence according to this rule to obtain the accurate grid potential value of all grid cells. Next, following the spatial order of the grid's x-axis rows and y-axis columns, the potential values ​​of 200 grid cells are sequentially arranged to construct a 20-row × 10-column two-dimensional grid potential value matrix. Each row in the matrix corresponds to grid cells from 0.05m to 1.95m along the x-axis, and each column corresponds to grid cells from 0.05m to 0.95m along the y-axis. Each element value in the matrix corresponds one-to-one with the potential value of its corresponding grid cell. This two-dimensional grid potential value matrix can then be imported into a process control visualization system. Using a blue-green-yellow-red color gradient mapping rule, low potential values ​​are mapped to dark blue, medium potential values ​​to a green-yellow gradient, and high potential values ​​to dark red. Simultaneously, the physical dimensions of the electrolytic cell (2m × 1m), the actual spatial positions of the 25 sensor nodes, and the coordinate scale of the grid cells are marked on the visualization interface. Finally, a 0.1m × 0.1m resolution visualized potential distribution grid map is generated, clearly and intuitively presenting the spatial characteristics of the potential distribution in each region of the electrolytic cell within this depth plane.

[0037] In one embodiment of this application, in step S140, if the gradient value of a grid cell in the potential distribution grid map exceeds a preset gradient threshold, the current grid cell is marked as a potential anomaly region, and a potential anomaly region distribution map is generated based on the potential anomaly region. Specifically, the Sobel operator can be used to calculate the potential gradient value of the grid potential value matrix corresponding to the potential distribution grid map. The calculated potential gradient value amplitude directly reflects the degree of spatial abrupt change in potential at that location. The larger the gradient value amplitude, the more drastic the potential spatial change, and the more abnormal the electrolyte flow state in that region of the electrolytic cell. Secondly, the preset gradient threshold can be calibrated based on the process characteristics of the electrolytic cell, long-term historical production operation data, and the stability requirements of the on-site electrolytic reaction. In other embodiments of this application, it can be flexibly adjusted according to the actual needs of electrolytic cells of different specifications and process types. The potential gradient value amplitude of each grid cell is compared with the preset gradient threshold one by one. If the potential gradient value amplitude of a certain grid cell exceeds the preset gradient threshold, the grid cell is determined to be a potential anomaly region. At the same time, a unique abnormal space identifier can be added to the grid cell.

[0038] Optionally, a heat map and highlighting visualization commonly used in process control can be used to distinguish the potential distribution area of ​​the electrolytic cell by color. Normal grid areas are mapped to the base color, and potential abnormal areas are mapped to high-contrast highlight colors. At the same time, the core information such as the center spatial coordinates, area ratio, and maximum potential gradient value of each continuous potential abnormal area are clearly marked in the visualization map to generate a visualized potential abnormal area distribution map.

[0039] For example, taking a rectangular electrolytic cell with a length of 2 meters and a width of 1 meter as an example, the depth plane of the mainstream electrolyte zone in the middle of the electrolytic cell has been constructed with 0.1m × 0.1m grid cells, forming a potential distribution grid map of 200 grid cells in 20 rows × 10 columns. Based on the copper electrolytic refining process characteristics of this electrolytic cell, the preset gradient threshold, calibrated using historical production data, is 0.15V / m. The Sobel operator is used to calculate the potential gradient value of each grid cell in this 20 rows × 10 columns grid potential value matrix, obtaining the potential gradient amplitude of each grid cell. For example, grid cell A has coordinates of (0.5m, 0.3m), and grid cell B has coordinates of (0.8m, 0.5m), with calculated gradient values ​​of 0.08V / m and 0.12V / m respectively, both below the preset gradient threshold of 0.15V / m, and are therefore determined to be normal grid areas. The calculated potential gradient values ​​for seven consecutive grid cells—grid cell C (1.2m, 0.6m), grid cell D (1.3m, 0.6m), grid cell E (1.2m, 0.7m), grid cell F (1.3m, 0.7m), grid cell G (1.4m, 0.7m), grid cell H (1.3m, 0.8m), and grid cell I (1.4m, 0.8m)—are 0.17V / m, 0.21V / m, 0.19V / m, 0.20V / m, 0.18V / m, 0.16V / m, and 0.17V / m, respectively. All of these values ​​exceed the preset gradient threshold of 0.15V / m. Therefore, these seven grid cells are marked as potential anomaly regions. Subsequently, the seven potential anomaly grid cells were spatially integrated. Spatial neighborhood analysis confirmed that these seven grid cells were spatially adjacent and continuous regions with no isolated or invalid anomaly markers. They were aggregated into a single continuous potential anomaly region, with an actual area of ​​0.07 square meters, accounting for 3.5% of the total area of ​​the electrolyte depth plane (2 square meters). The center spatial coordinates of this continuous anomaly region were determined to be 1.3m x-axis and 0.7m x-axis, with a maximum potential gradient of 0.21V / m within the region. Finally, based on the actual physical structure information of the 2m × 1m electrolytic cell, the aggregated continuous potential anomaly region was accurately mapped onto the standardized spatial coordinate system of the electrolytic cell. A potential anomaly region distribution map was generated using visualization technology. All normal grid regions in the map were marked in green, while the continuous potential anomaly region was highlighted in red. Information about the potential anomaly region was also clearly marked at designated locations on the distribution map.

[0040] In one embodiment of this application, step S150 involves determining electrolytic reaction state indicators based on a potential distribution grid diagram and a potential anomaly region distribution diagram. These indicators include the proportion of potential anomaly regions, potential uniformity indicators, and process stability indicators. The process also includes the following steps: Figure 4As shown, the specific content is as follows: Step S410: Calculate the number of grid cells occupied by the potential anomaly region in the potential distribution grid diagram, and determine the proportion of the potential anomaly region based on the number of grid cells occupied by the potential anomaly region. Step S420: Calculate the potential standard deviation in the potential distribution grid diagram and the potential standard deviation in the potential anomaly area distribution diagram, and determine the potential uniformity index based on the potential standard deviation in the potential distribution grid diagram and the potential standard deviation in the potential anomaly area distribution diagram. Step S430: Obtain the electrolysis reaction parameters of the current electrolytic cell, calculate the volatility of the electrolysis reaction parameters, and use the volatility of the electrolysis reaction parameters as a process stability index.

[0041] Specifically, the number of all grid cells marked as having potential anomalies can be extracted from the potential anomaly distribution map, ensuring that the statistical results cover all grid cells in continuous anomaly areas without omission or duplication. Subsequently, the total number of grid cells in the potential distribution grid map is counted. This number represents the total number of grid cells after the electrolytic cell analysis plane is meshed, signifying the overall spatial extent of the analysis plane. Therefore, the proportion of potential anomaly areas = number of grid cells in potential anomaly areas / total number of grid cells in the potential distribution grid map. The obtained value of the proportion of potential anomaly areas directly reflects the spatial scale of potential anomaly areas in the electrolytic cell analysis plane and is a core spatial indicator for measuring the degree of local anomalies in the electrolysis reaction.

[0042] Optionally, the grid potential values ​​of all grid cells in the potential distribution grid diagram can be extracted, and the overall potential standard deviation can be calculated using the standard deviation calculation method. Then, the grid potential values ​​of all abnormal grid cells in the potential anomaly area distribution diagram can be extracted, and the standard deviation of the anomaly area potential can be calculated using the same formula. Finally, the potential uniformity index is determined using a weighted calculation method: Potential uniformity index = 1 - (Overall potential standard deviation × 0.4 + Abnormal area potential standard deviation × 0.6), where 0.4 and 0.6 are weighting coefficients, which can be determined according to the degree of influence of the abnormal area on the uniformity of the electrolytic reaction. Here, the weight of local anomalies can be emphasized. The value range of the potential uniformity index is 0-1; the closer the value is to 1, the more uniform the potential distribution in the electrolytic cell and the more stable the electrochemical reaction state. Electrolytic reaction parameters within the current preset time window (e.g., 5-15 minutes) can also be retrieved from the electrolytic cell process control system. Electrolytic reaction parameters include current density and electrolyte concentration. Subsequently, the volatility of each electrolysis reaction parameter was calculated: Volatility of electrolysis reaction parameter = (Maximum value of electrolysis reaction parameter - Minimum value of electrolysis reaction parameter) / Average value of electrolysis reaction parameter. Finally, a weighted average method was used (the weight corresponding to current density is 0.7, and the weight corresponding to electrolyte concentration is 0.3; each weight can be calibrated according to the degree of influence of the parameter on the electrolysis reaction) to calculate the comprehensive value of the volatility of all electrolysis reaction parameters. This comprehensive value is directly used as a process stability index. The lower the index value, the smaller the volatility of the electrolysis reaction parameters and the more stable the process operation. It is the core dynamic index for measuring the stability of the electrolysis reaction process.

[0043] For example, taking a rectangular electrolytic cell 2 meters long and 1 meter wide as an example, a potential distribution grid map with 20 rows × 10 columns (200 grid cells) has been constructed in the depth plane of the mainstream electrolyte zone in the middle of the electrolytic cell, and 7 abnormal grid cells have been generated. Therefore, the proportion of the potential abnormal area = 7 / 200 × 100% = 3.5%. Extracting all potential values ​​from the 200 grid cells in the potential distribution grid map, the overall potential standard deviation is calculated to be 0.06V, and the weight corresponding to the overall potential standard deviation is 0.4. Then, extracting the potential values ​​from the 7 abnormal grid cells, the abnormal area potential standard deviation is calculated to be 0.18V, and the weight corresponding to the abnormal area potential standard deviation is 0.6. Substituting into the weighted calculation formula, we get: Potential uniformity index = 0.06 × 0.4 + 0.18 × 0.6 = 0.132. Next, the electrolysis reaction parameters of the electrolytic cell within the current 10 minutes were obtained: current density data were 180 A / m², 182 A / m², 178 A / m², 183 A / m², and 179 A / m²; electrolyte concentration (copper sulfate) data were 60 g / L, 61 g / L, 59 g / L, 62 g / L, and 58 g / L. Subsequently, the current density fluctuation rate was calculated: average value = (180 + 182 + 178 + 183 + 179) / 5 = 180.4 A / m², fluctuation range = 183 - 178 = 5 A / m², and fluctuation rate = 5 / 180.4 × 100% ≈ 2.77%. The electrolyte concentration fluctuation rate is: average value = (60 + 61 + 59 + 62 + 58) / 5 = 60 g / L, fluctuation range = 62 - 58 = 4 g / L, fluctuation rate = 4 / 60 × 100% ≈ 6.67%. The weights for current density (0.7) and electrolyte concentration (0.3) can be used to calculate the process stability index as a weighted average: 2.77% × 0.7 + 6.67% × 0.3 = 4.77%. Therefore, the current electrolysis reaction status indicators of this electrolytic cell are: potential anomaly region percentage 3.5%, potential uniformity index -0.8, and process stability index 4.77%.

[0044] In one embodiment of this application, step S160 involves determining the current electrolysis reaction evaluation level based on electrolysis reaction status indicators. The electrolysis reaction evaluation level includes inefficient electrolysis reaction, normal electrolysis reaction, and abnormal electrolysis reaction. The step also includes the following steps: Figure 5 As shown, the specific content is as follows: Step S510: Obtain the weights corresponding to the proportion of potential abnormal regions, the potential uniformity index, and the process stability index, respectively. Step S520: Based on the weights corresponding to the proportion of potential anomaly regions, the weights corresponding to the potential uniformity index, and the weights corresponding to the process stability index, perform a weighted calculation on the proportion of potential anomaly regions, the potential uniformity index, and the process stability index, and use the result of the weighted calculation as the electrolysis reaction state score. Step S530: Obtain the first preset scoring range corresponding to the inefficient electrolysis reaction, the second preset scoring range corresponding to the normal electrolysis reaction, and the third preset scoring range corresponding to the abnormal electrolysis reaction; Step S540: Compare the current electrolysis reaction state score with the first preset score range, the second preset score range, and the third preset score range to determine the current electrolysis reaction evaluation level.

[0045] Specifically, different first, second, and third preset scoring ranges can be set according to the electrolysis process, production requirements, and quality control. For example, taking copper electrolytic refining as an example, the industry has strict standards for the purity of electrolytic copper (e.g., cathode copper above 99.99%) and current efficiency (usually required to be above 95%). Only when the proportion of abnormal potential areas is low, the potential uniformity is high, and the fluctuation of process parameters is small can these standards be met. Therefore, the scoring range for meeting the industry process standards is defined as 80-100 points (normal reaction). When the score is below 80 points, the current electrolysis reaction state can no longer reach the optimal process standard, and when it is below 60 points, it directly deviates from the allowable range of the process, which will lead to substandard product purity and a significant decrease in current efficiency.

[0046] For example, if electrolytic production has high requirements for product purity and continuous operation of the production line (such as high-precision electronic-grade electrolytic copper production), the lower limit of the normal electrolytic reaction range can be increased (e.g., from 80 minutes to 85 minutes) to identify slight inefficient reactions earlier and trigger regulation. For conventional industrial electrolytic production, the inefficient electrolytic reaction range can be set at 70-85 minutes based on production efficiency and regulation cost requirements to reduce unnecessary parameter adjustments.

[0047] For example, taking a rectangular electrolytic cell for copper electrolytic refining with a length of 2 meters and a width of 1 meter as an example, the current electrolytic reaction status indicators for this electrolytic cell have been calculated as follows: abnormal potential area ratio 3.5%, potential uniformity index 0.9785, and process stability index 2.644%. Combining the characteristics of the copper electrolytic refining process with historical production data, the weights corresponding to the abnormal potential area ratio are obtained as 0.4, the potential uniformity index as 0.3, and the process stability index as 0.3, and the sum of the three weights is 1. Subsequently, the indicators are normalized and standardized from 0 to 100 points, resulting in a standardized score of 82.5 for the abnormal potential area ratio, 97.85 for the potential uniformity index, and 86.78 for the process stability index. Then, the standardized scores are weighted and calculated to obtain the electrolytic reaction status score = 82.5 × 0.4 + 97.85 × 0.3 + 86.78 × 0.3 = 88.389. Next, based on the quality requirements of the copper electrolytic refining process, the following preset scoring ranges were obtained: 60-80 points for inefficient electrolytic reactions, 80-100 points for normal electrolytic reactions, and 0-60 points for abnormal electrolytic reactions. Comparing the current electrolytic reaction status score of 88.389 points with these three preset scoring ranges, the current electrolytic reaction evaluation level of the electrolytic cell was determined to be a normal electrolytic reaction. If subsequent detections of the electrolytic cell revealed an abnormal potential area ratio of 15%, a potential uniformity index of 0.65, and a process stability index of 12%, the electrolytic reaction status score, calculated using the same method, would be 41.5 points. Comparing this with the preset scoring range, it was determined to be an abnormal electrolytic reaction. If the detected abnormal potential area ratio was 8%, the potential uniformity index was 0.78, and the process stability index was 7%, the calculated electrolytic reaction status score would be 72.9 points, and after comparison, it was determined to be an inefficient electrolytic reaction.

[0048] In one embodiment of this application, step S160 involves dynamically adjusting the electrolysis reaction parameters based on the electrolysis reaction evaluation level. These electrolysis reaction parameters include current density and electrolyte concentration. The step also includes the following steps: Figure 6 As shown, the specific content is as follows: Step S610: If the current electrolysis reaction evaluation level is inefficient electrolysis reaction or abnormal electrolysis reaction, then obtain the current current density and the current electrolyte concentration; Step S620: Based on the current current density and the current electrolyte concentration, determine the target current density and the target electrolyte concentration using a target programming algorithm; Step S630: Adjust the current current density according to the target current density, and adjust the current electrolyte concentration according to the target electrolyte concentration.

[0049] Specifically, an objective function can be constructed based on the current electrolysis reaction status indicators (proportion of abnormal potential regions, potential uniformity indicators, and process stability indicators) and the electrolysis reaction evaluation level. The objective is to reduce the proportion of abnormal potential regions to within a safe threshold, improve the potential uniformity indicator to a normal range, and optimize the process stability indicator to a reasonable range, ultimately restoring the electrolysis reaction evaluation level to a normal electrolysis reaction. Secondly, multiple constraints can be set, including the process allowable ranges for current density and electrolyte concentration, limits on the magnitude of single parameter adjustments (e.g., a single adjustment of current density not exceeding 15%, and a single adjustment of electrolyte concentration not exceeding 10%, which can be calibrated according to general process constraints in the electrolysis industry), and equipment operating load constraints after parameter adjustments, ensuring that the target parameters are within the feasible range of the process and equipment. Finally, the current current density and current electrolyte concentration are substituted into the objective programming algorithm, and the algorithm solves for the target current density and target electrolyte concentration that satisfy all constraints and achieve the core objective. Then, based on the difference between the target current density and the current current density, and the difference between the target electrolyte concentration and the current electrolyte concentration, combined with the preset parameters of the process, the adjustment step size is determined to obtain the adjustment command. Subsequently, the adjustment command is transmitted to the corresponding electrolysis process actuator. The adjustment of current density can be executed by a current regulator, and the adjustment of electrolyte concentration can be executed in conjunction with a solution circulation pump and a precision dosing device (adding concentrated electrolyte when the concentration is too low, and adding pure water and adjusting the circulation rate when the concentration is too high).

[0050] For example, taking a rectangular electrolytic cell for copper electrolytic refining with a length of 2 meters and a width of 1 meter as an example, the preset process constraints of this electrolytic cell are: the allowable range of current density is 200-350 A / m², the allowable range of electrolyte (copper sulfate) concentration is 0.8-1.8 mol / L, the single adjustment range of current density is ≤15%, the single adjustment range of electrolyte concentration is ≤10%, the adjustment step of current density is 5 A / m², and the adjustment step of electrolyte concentration is 0.02 mol / L. If it is determined to be an inefficient electrolysis reaction, the current current density is obtained as 250 A / m² and the current electrolyte concentration is 1.2 mol / L. Based on the current electrolysis reaction parameters, an objective function was constructed with the core objectives of reducing the proportion of abnormal potential regions from 8% to below 5% and improving the potential uniformity index from 0.78 to above 0.9. A target programming algorithm was used to solve for the target current density of 270 A / m² (adjustment range of 8%) and the target electrolyte concentration of 1.28 mol / L (adjustment range of 6.67%), both of which met the process constraints. Subsequently, the current density was adjusted from 250 A / m² to 270 A / m² in four steps of 5 A / m², and the electrolyte concentration was adjusted from 1.2 mol / L to 1.28 mol / L in four steps of 0.02 mol / L. The instructions were transmitted to the current regulator and the dosing device for step-by-step execution. During the adjustment process, real-time potential data was collected, and no abnormal aggravation was observed, ultimately achieving precise adjustment.

[0051] In the above method, by employing a goal programming algorithm and combining it with the constraints of the electrolysis reaction, a target function is constructed with the restoration of the normal electrolysis reaction as its core. This achieves precise planning of the electrolysis reaction parameter adjustment target, overcoming the limitations of traditional process control methods that rely on manual experience to set adjustment values, which are prone to under- or over-adjustment. Simultaneously, the algorithm's multi-objective optimization characteristics take into account both reaction state restoration and process and equipment operational constraints, ensuring the safety of parameter adjustment. Furthermore, it simultaneously achieves precise control of current density and electrolyte concentration, specifically correcting abnormal potential distribution within the electrolytic cell, effectively improving the proportion of abnormal potential areas, enhancing potential uniformity, and realizing adaptive and precise adjustment of electrolysis reaction parameters. This effectively improves the stability of the electrolysis reaction, the purity of the electrolysis products, and the overall production efficiency of the production line.

[0052] In one embodiment of this application, step S630, which adjusts the current current density according to the target current density and the current electrolyte concentration according to the target electrolyte concentration, further includes the following steps: Figure 7 As shown, the specific content is as follows: Step S710: Calculate the first deviation between the current current density and the target current density and the second deviation between the current electrolyte concentration and the target electrolyte concentration, respectively; Step S720: Determine the first adjustment step value of the current density based on the first deviation value, and determine the second adjustment step value of the electrolyte concentration based on the second deviation value; Step S730: Adjust the current current density according to the first adjustment step value, and adjust the current electrolyte concentration according to the second adjustment step value.

[0053] Specifically, the deviation between the electrolytic reaction parameters of the electrolyzer and the target electrolytic reaction parameters can be calculated. Numerical calculations determine the deviation between the current current density, the current electrolyte concentration, and the corresponding target values. The sign of the deviation indicates the direction of parameter adjustment: a positive value indicates the current parameter is lower than the target parameter and needs upward adjustment; a negative value indicates the current parameter is higher than the target parameter and needs downward adjustment; no deviation requires no adjustment. The first deviation value = target current density - current current density; the second deviation value = target electrolyte concentration - current electrolyte concentration. Next, the maximum single adjustment threshold for the current current density and electrolyte concentration is obtained, and the initial adjustment step size is determined according to a preset fixed ratio, using this maximum adjustment threshold as the upper limit. The preset fixed ratio can be adjusted to a value within the range of 1 / 2 to 3 / 4 according to the electrolysis process requirements, preferably 2 / 3. Therefore, the initial adjustment step size for current density = maximum single adjustment threshold for current density × preset fixed ratio; the initial adjustment step size for electrolyte concentration = maximum single adjustment threshold for electrolyte concentration × preset fixed ratio. If the absolute value of the first deviation does not exceed the initial adjustment step size of the current density, then the absolute value of the first deviation is used as the current current density adjustment step size. If the absolute value of the first deviation exceeds the initial adjustment step size of the current density, then the initial adjustment step size of the current density is used as the current current density adjustment step size. If the absolute value of the second deviation does not exceed the initial adjustment step size of the electrolyte concentration, then the absolute value of the second deviation is used as the current electrolyte concentration adjustment step size. If the absolute value of the second deviation exceeds the initial adjustment step size of the electrolyte concentration, then the initial adjustment step size of the electrolyte concentration is used as the current electrolyte concentration adjustment step size.

[0054] For example, the current rectangular electrolytic cell for copper electrolysis is 2 meters long and 1 meter wide. The maximum single adjustment threshold for the current density is 15%, and the maximum single adjustment threshold for the electrolyte concentration is 10%, with a preset fixed ratio of 2 / 3. The current current density is 250 A / m², the target current density is 300 A / m², the current electrolyte concentration is 1.2 mol / L, and the target electrolyte concentration is 1.5 mol / L. The first deviation value for the current density is 300 - 250 = 50 A / m², and the second deviation value for the electrolyte concentration is 1.5 - 1.2 = 0.3 mol / L. Both are positive, indicating that both the current density and electrolyte concentration need to be adjusted upwards, with total adjustments of 50 A / m² and 0.3 mol / L, respectively. The maximum single adjustment of current density is 250 × 15% = 37.5 A / m², and the corresponding initial adjustment step size is 37.5 × 2 / 3 = 25 A / m². Since the absolute value of the deviation (50 A / m²) is greater than the initial adjustment step size (25 A / m²), the first adjustment step size for current density is determined to be 25 A / m². Simultaneously, the maximum single adjustment of electrolyte concentration is calculated as 1.2 × 10% = 0.12 mol / L, and the initial adjustment step size is 0.12 × 2 / 3 = 0.08 mol / L. Since the absolute value of the deviation (0.3 mol / L) is greater than the initial adjustment step size (0.08 mol / L), the second adjustment step size for electrolyte concentration is determined to be 0.08 mol / L. Next, the parameters were adjusted step by step according to the determined adjustment step size. The current density was adjusted in steps of 25 A / m². After the first adjustment, it was 250 + 25 × 1 = 275 A / m², and after the second adjustment, it was 275 + 25 × 1 = 300 A / m². After two adjustments, the target current density was accurately achieved. The electrolyte concentration was adjusted in steps of 0.08 mol / L. After the first adjustment, it was 1.2 + 0.08 × 1 = 1.28 mol / L, after the second adjustment, it was 1.28 + 0.08 × 1 = 1.36 mol / L, and after the third adjustment, it was 1.36 + 0.08 × 1 = 1.44 mol / L. At this point, the remaining amount to be adjusted was 0.06 mol / L, and this value was less than the second adjustment step size of 0.08 mol / L. The final fine adjustment was 0.06 mol / L, and after the adjustment, it was 1.44 + 0.06 = 1.5 mol / L. After four adjustments, the target electrolyte concentration was accurately achieved.

[0055] In one embodiment of this application, after adjusting the current electrolyte concentration according to the second adjustment step value in step S730, the following steps are also included: Figure 8 As shown, the specific content is as follows: Step S810: Update the potential distribution data based on the adjusted current density and adjusted electrolyte concentration; Step S820: Update the spatiotemporal correlation coefficient based on the updated potential distribution data; Step S830: If the updated spatiotemporal correlation coefficient does not exceed the preset correlation coefficient threshold, then update the target current density and target electrolyte concentration again.

[0056] Specifically, for example, the adjusted current density is 3.0 A / cm². 2 The current electrolyte concentration is 1.5 mol / L. At this point, 75 potential sensors deployed in a grid pattern within the electrolytic cell are activated, continuously collecting potential time-series data at various spatial locations within the adjusted electrolytic cell at a sampling frequency of 100 Hz. Random noise is eliminated using a sliding window mean filtering algorithm, and then the local potential peak value and potential uniformity index of each electrolytic cell region are calculated. The updated multi-dimensional potential data replaces the original potential distribution data. Using a fixed analysis time window of 10 seconds and a spatial range of 1 meter, the Pearson correlation coefficient formula is used to perform a full-dimensional calculation on the updated potential time-series data from the 75 sensors, yielding an updated spatiotemporal correlation coefficient of 0.65. The preset correlation coefficient threshold is 0.7. Since the updated spatiotemporal correlation coefficient of 0.65 does not exceed this threshold, a precise comparison is made between the updated potential distribution data, the current process stability index of 0.85, and the pre-established electrolysis reaction state feature library. Using a multi-objective optimization algorithm that aims for maximum potential uniformity and optimal process stability, and considering process constraints of no more than 15% adjustment in current density and no more than 10% adjustment in electrolyte concentration per cycle, a new target current density of 2.9 A / cm³ is recalculated. 2 The new target electrolyte concentration is 1.55 mol / L, and the system completely replaces the original target current density of 3.0 A / cm² with this new target parameter. 2 The target current density and target electrolyte concentration are updated again after the target electrolyte concentration is set to 1.5 mol / L.

[0057] In the above method, by re-comparing the updated spatiotemporal correlation coefficient with the preset correlation coefficient threshold, and updating the target current density and target electrolyte concentration if the spatiotemporal correlation coefficient does not reach the threshold, adaptive optimization of the target process parameters is achieved. This effectively avoids ineffective process operations caused by continuing to adjust according to the original target parameters, improves the pertinence and effectiveness of the electrolytic cell process parameter adjustment, and further enhances the adaptive control capability of the electrical control system for the electrolytic cell operating status. It can continuously promote the potential distribution in the electrolytic cell to move towards a uniform and stable state, thereby ensuring the balanced and sufficient progress of the electrochemical reaction, effectively improving the purity of the electrolytic products, and enhancing the overall operational stability and production efficiency of the automated electrolytic cell production line.

[0058] This application also provides an electrical control system for an automated electrolytic cell production line, which may include an acquisition module, a first determination module, a second determination module, a generation module, a third determination module, and a fourth determination module. The system comprises the following modules: an acquisition module for acquiring potential distribution data within the electrolytic cell; a first determination module for determining the potential spatiotemporal fluctuation feature vector based on the potential distribution data and calculating the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and historical potential spatiotemporal fluctuation feature vectors using the Pearson correlation coefficient algorithm; a second determination module for determining a potential distribution grid map based on the potential distribution data if the spatiotemporal correlation coefficient does not exceed a preset correlation coefficient threshold; a generation module for marking the current grid cell as a potential anomaly region if the gradient value of a grid cell in the potential distribution grid map exceeds a preset gradient threshold, and generating a potential anomaly region distribution map based on the potential anomaly region; a third determination module for determining electrolytic reaction status indicators based on the potential distribution grid map and the potential anomaly region distribution map, including the proportion of potential anomaly regions, potential uniformity indicators, and process stability indicators; and a fourth determination module for determining the current electrolytic reaction evaluation level based on the electrolytic reaction status indicators, including inefficient electrolytic reaction, normal electrolytic reaction, and abnormal electrolytic reaction, and dynamically adjusting the electrolytic reaction parameters based on the evaluation level, including current density and electrolyte concentration.

[0059] It should be noted that the embodiment of the electrical control system of the automated production line of the electrolytic cell provided in this application can be used to execute the processing flow of the embodiment of the electrical control method of the automated production line of the electrolytic cell in the above embodiment. Its function will not be repeated here, but can be referred to the detailed description of the above method embodiment.

[0060] This application also provides an electronic device, which includes one or more processors and memory resources represented by a memory for storing instructions executable by the processor, such as application programs. The application programs stored in the memory may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor is configured to execute instructions to perform the aforementioned electrical control method for an automated electrolytic cell production line.

[0061] The electronic device may also include a power supply component configured to perform power management of the electronic device, a wired or wireless network interface configured to connect the electronic device to a network, and an input / output (I / O) interface. The electronic device can be operated based on operating devices stored in memory, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0062] In one embodiment, a computer device, which may be a server, is also provided. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an electrical control method for an automated electrolytic cell production line.

[0063] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an electrical control method for an automated electrolytic cell production line. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0064] This application also provides a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of the electronic device, enables the electronic device to execute an electrical control method for an automated production line of an electrolytic cell.

[0065] This application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0066] It should be noted that although the steps of the electrical control method for the automated electrolytic cell production line of this application are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down one step into multiple steps, should all be considered part of this application.

[0067] It should be understood that this application is not limited to the detailed structure and arrangement of the modules of the electrical control system of the automated electrolytic cell production line proposed in this specification. This application can have other embodiments and can be implemented and executed in various ways. The foregoing variations and modifications fall within the scope of this application. It should be understood that the application and its definition in this specification extend to all alternative combinations of two or more individual features mentioned or apparent in the text and / or drawings. All these different combinations constitute multiple alternative aspects of this application. The embodiments described in this specification illustrate the best known mode for implementing this application and will enable those skilled in the art to utilize this application.

Claims

1. An electrical control method for an automated production line of an electrolytic cell, characterized in that, include: Acquire potential distribution data within the electrolytic cell; Based on the potential distribution data, the potential spatiotemporal fluctuation feature vector is determined, and the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and the historical potential spatiotemporal fluctuation feature vector is calculated using the Pearson correlation coefficient algorithm. If the spatiotemporal correlation coefficient does not exceed the preset correlation coefficient threshold, then the potential distribution grid map is determined based on the potential distribution data; If the gradient value of a grid cell in the potential distribution grid exceeds a preset gradient threshold, the current grid cell is marked as a potential anomaly region, and a potential anomaly region distribution map is generated based on the potential anomaly region. Electrolysis reaction status indicators are determined based on the potential distribution grid diagram and the potential anomaly region distribution diagram. The electrolysis reaction status indicators include the proportion of potential anomaly regions, potential uniformity indicators, and process stability indicators. The current electrolysis reaction evaluation level is determined based on the electrolysis reaction status indicators. The electrolysis reaction evaluation level includes inefficient electrolysis reaction, normal electrolysis reaction, and abnormal electrolysis reaction. The electrolysis reaction parameters, including current density and electrolyte concentration, are dynamically adjusted based on the electrolysis reaction evaluation level.

2. The electrical control method for an automated electrolytic cell production line according to claim 1, characterized in that, The step of determining the potential spatiotemporal fluctuation feature vector based on the potential distribution data includes: The potential distribution sequence is determined based on the potential distribution data, and the mean of the potential spatial gradient and the mean of the potential time change rate are determined based on the potential distribution sequence using a sliding window algorithm. Based on the potential distribution sequence, the main fluctuation frequency is extracted using Fourier transform, and the dominant frequency energy is determined according to the main fluctuation frequency. Calculate the standard deviation of the potential distribution sequence and use the standard deviation of the potential distribution sequence as the mean of the potential fluctuation amplitude; The potential spatiotemporal fluctuation feature vector is determined based on the mean of the potential spatial gradient, the mean of the potential time change rate, the dominant frequency energy, and the mean of the potential fluctuation amplitude.

3. The electrical control method for an automated electrolytic cell production line according to claim 1, characterized in that, Determining the potential distribution grid map based on the potential distribution data includes: Based on the potential distribution data, the grid potential value of each grid cell is determined using a bilinear interpolation algorithm; A grid potential value matrix is ​​determined based on the grid potential value of each grid cell, and a potential distribution grid map is generated based on the grid potential value matrix.

4. The electrical control method for an automated electrolytic cell production line according to claim 1, characterized in that, The step of determining the electrolysis reaction state indicators based on the potential distribution grid map and the potential anomaly region distribution map includes: Calculate the number of grid cells occupied by the potential anomaly region in the potential distribution grid diagram, and determine the proportion of the potential anomaly region based on the number of grid cells occupied by the potential anomaly region. Calculate the potential standard deviation in the potential distribution grid diagram and the potential standard deviation in the potential anomaly region distribution diagram, and determine the potential uniformity index based on the potential standard deviation in the potential distribution grid diagram and the potential standard deviation in the potential anomaly region distribution diagram. Obtain the electrolysis reaction parameters of the current electrolytic cell, calculate the volatility of the electrolysis reaction parameters, and use the volatility of the electrolysis reaction parameters as the process stability index.

5. The electrical control method for an automated electrolytic cell production line according to claim 1, characterized in that, Determining the current electrolysis reaction evaluation level based on the electrolysis reaction state indicators includes: The weights corresponding to the proportion of the potential anomaly region, the potential uniformity index, and the process stability index are obtained respectively. Based on the weights corresponding to the proportion of the potential anomaly region, the potential uniformity index, and the process stability index, a weighted calculation is performed on the proportion of the potential anomaly region, the potential uniformity index, and the process stability index, and the result of the weighted calculation is used as the electrolysis reaction state score. Obtain the first preset scoring range corresponding to the inefficient electrolysis reaction, the second preset scoring range corresponding to the normal electrolysis reaction, and the third preset scoring range corresponding to the abnormal electrolysis reaction; The current electrolysis reaction status score is compared with the first preset score range, the second preset score range, and the third preset score range to determine the current electrolysis reaction evaluation level.

6. The electrical control method for an automated electrolytic cell production line according to claim 1, characterized in that, The step of dynamically adjusting the electrolysis reaction parameters according to the electrolysis reaction evaluation level includes: If the current evaluation level of the electrolysis reaction is inefficient electrolysis reaction or abnormal electrolysis reaction, then obtain the current current density and the current electrolyte concentration; Based on the current current density and the current electrolyte concentration, a target programming algorithm is used to determine the target current density and the target electrolyte concentration. The current density is adjusted according to the target current density, and the current electrolyte concentration is adjusted according to the target electrolyte concentration.

7. The electrical control method for an automated electrolytic cell production line according to claim 6, characterized in that, The step of adjusting the current current density according to the target current density and adjusting the current electrolyte concentration according to the target electrolyte concentration includes: Calculate the first deviation value between the current current density and the target current density and the second deviation value between the current electrolyte concentration and the target electrolyte concentration, respectively; The first adjustment step value of the current density is determined based on the first deviation value, and the second adjustment step value of the electrolyte concentration is determined based on the second deviation value. The current density is adjusted according to the first adjustment step value, and the electrolyte concentration is adjusted according to the second adjustment step value.

8. The electrical control method for an automated electrolytic cell production line according to claim 7, characterized in that, After adjusting the current electrolyte concentration according to the second adjustment step value, the method further includes: The potential distribution data is updated based on the adjusted current density and the adjusted electrolyte concentration; The spatiotemporal correlation coefficient is updated based on the updated potential distribution data; If the updated spatiotemporal correlation coefficient does not exceed the preset correlation coefficient threshold, then the target current density and the target electrolyte concentration are updated again.

9. An electrical control system for an automated electrolytic cell production line, characterized in that, include: The acquisition module is used to acquire potential distribution data within the electrolytic cell; The first determining module is used to determine the potential spatiotemporal fluctuation feature vector based on the potential distribution data, and to calculate the spatiotemporal correlation coefficient between the potential spatiotemporal fluctuation feature vector and the historical potential spatiotemporal fluctuation feature vector using the Pearson correlation coefficient algorithm. The second determining module is used to determine a potential distribution grid map based on the potential distribution data if the spatiotemporal correlation coefficient does not exceed a preset correlation coefficient threshold. The generation module is used to mark the current grid cell as a potential anomaly region if the gradient value of the grid cell in the potential distribution grid exceeds a preset gradient threshold, and to generate a potential anomaly region distribution map based on the potential anomaly region. The third determining module is used to determine the electrolysis reaction status indicators based on the potential distribution grid map and the potential anomaly region distribution map. The electrolysis reaction status indicators include the proportion of potential anomaly regions, potential uniformity indicators, and process stability indicators. The fourth determining module is used to determine the current electrolysis reaction evaluation level based on the electrolysis reaction status index. The electrolysis reaction evaluation level includes inefficient electrolysis reaction, normal electrolysis reaction, and abnormal electrolysis reaction. The module also dynamically adjusts the electrolysis reaction parameters based on the electrolysis reaction evaluation level. The electrolysis reaction parameters include current density and electrolyte concentration.

Images