AI-based intelligent prediction method and system for production quality in electrolytic manganese process

Abstract

This invention relates to the field of intelligent process control technology in industrial production, specifically to an AI-based intelligent prediction method and system for electrolytic manganese production quality, comprising: a drift calibration module, a structure matching module, a process parameter inversion module, a path correction module, and a deviation verification module. In this invention, by utilizing the response relationship between inputs and outputs at each stage, dynamic compensation is achieved for the drift of input parameters and the deviation between output parameters. Based on the correlation and matching between the cyclical changes in the production process and the fluctuation frequency between target control parameters, the actual impact of fluctuations in each parameter on target control parameters and product quality is effectively identified. Potential interference from key process parameters on the stability of each process step is promptly identified. By determining the path between residual liquid concentration trends and raw material addition locations, the spatial and temporal origin of impurity diffusion is clearly traced. Furthermore, migration path parameters are adjusted based on the ion retention behavior at boundary detection points.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent process control of industrial production, in particular to an AI-based electrolytic manganese process production quality intelligent prediction method and system BACKGROUND

[0002] AI intelligent process control technology includes a complete set of intelligent methods for real-time monitoring, data analysis, control decision and automatic adjustment of key process parameters in industrial production processes. The technology aims to collect process data through sensors, combine historical operation information and real-time state, use model prediction and feedback control means, and realize accurate regulation and control of process variables such as flow, temperature, concentration, current density, etc. to improve the automation degree, control precision and operation stability of industrial processes. The technology is applied to continuous or complex coupled production processes such as metallurgy, chemical industry, power and pharmaceutical industry, and has important technical support significance for improving product quality and ensuring production safety. The traditional manganese smelting process, such as leaching purification, is still intermittent operation, which has problems such as low operation efficiency, high labor intensity of personnel, poor operation environment, etc. In addition, the key process control still relies on personnel experience for regulation and control, which has information lag, extensive regulation and control, etc. leading to large fluctuations in actual control parameters, unstable product quality, high production cost, etc. SUMMARY

[0003] In order to solve the problems existing in the control of the current manganese smelting process, the application embodiment provides an AI-based electrolytic manganese process production quality intelligent prediction method and system. The technical solution is as follows:

[0004] On the one hand, an AI-based electrolytic manganese process production quality intelligent prediction system is provided, which comprises:

[0005] The drift calibration module uses a temperature sensor to analyze the change trajectory between the temperature fluctuation trend of the sample introduction cavity and the environment, evaluates the corresponding relationship between the temperature synchronization deviation and the ion response difference, corrects the current cycle concentration reading, and generates a concentration calibration value;

[0006] The structure matching module uses the concentration calibration value to compare the periodical change of the spacing of the crystal lattice in the deposition process and the time frequency of the concentration fluctuation of each impurity ion, judges the structure period synchronization correlation, identifies the influence relationship of the ion concentration fluctuation on the stable configuration formation of the crystal, and generates impurity response information;

[0007] The process parameter inversion module calls the impurity response information, analyzes the positional relationship between the residual liquid element concentration trend and the raw material feeding behavior, calls the raw material feeding period, the current change direction and the temperature change region, judges the path of the initial concentration change behavior of the impurities, and generates a diffusion starting concentration;

[0008] The path correction module utilizes the diffusion starting concentration to judge the ion migration delay phenomenon by calculating the retention change direction among multiple detection points in the boundary region, corrects the behavior offset parameter of the path segment, adjusts the flow rate rhythm in the current path prediction, and generates a path delay coefficient.

[0009] As a further scheme of the present application, the concentration calibration value includes a temperature difference change direction, a response delay amplitude, and a concentration correction ratio, the impurity response information specifically includes a period frequency matching factor, a structure correlation strength, and an impurity influence degree, and the diffusion starting concentration specifically includes a concentration fluctuation interval, a starting behavior characteristic, and a diffusion trend direction.

[0010] As a further scheme of the present application, the drift calibration module includes:

[0011] The temperature difference detection submodule utilizes a temperature sensor to obtain fluctuation trend data of the sample cavity temperature and the ambient temperature, analyzes the change trajectories of the two, and calculates the change direction of the temperature difference, and combines the change amplitude and direction of the temperature difference in each detection period to establish a temperature difference change interval;

[0012] The synchronization judgment submodule evaluates the temperature synchronization deviation trend in the continuous sampling period based on the temperature difference change interval, combines the deviation duration and the change direction to judge the delay response behavior of the sample cavity, analyzes the continuous consistency of the synchronization deviation, and generates a synchronization deviation parameter;

[0013] The response correction submodule calculates the corresponding relationship between the deviation degree and the ion response difference in the concentration curve according to the synchronization deviation parameter, corrects the current period concentration reading through the matching relationship between the temperature difference fluctuation and the concentration fluctuation, and generates a concentration calibration value.

[0014] As a further scheme of the present application, the specific formula for judging the delay response behavior of the sample cavity is:

[0015] ;

[0016] The synchronization deviation trend index is calculated;

[0017] wherein, the synchronization deviation trend index is the sample cavity temperature normalized value collected in the i-th period, the ambient temperature normalized value collected in the i-th period, the sample cavity temperature normalized value collected in the i-1-th period, the ambient temperature normalized value collected in the i-1-th period, the temperature normalization stability constant is the sign function is a direction weight corresponding to a direction of temperature change in the i-th period, a total number of sampling periods, a current sampling period index number, a previous sampling period index number.

[0018] As a further scheme of the present application, the structure matching module comprises:

[0019] The period comparison sub-module acquires the concentration calibration value, collects the lattice spacing variation period in the deposition process, acquires the time frequency of the impurity ion concentration fluctuation, compares the frequency difference between the lattice spacing period and the concentration fluctuation of each impurity ion, analyzes the consistency of the period variation, and generates a period matching difference;

[0020] The synchronization analysis sub-module judges the synchronization correlation of the structure period and the impurity ion concentration fluctuation in time sequence according to the period matching difference, screens the period section with consistent variation trend, combines the structure period synchronization parameter, establishes the correlation between the structure period and the ion concentration fluctuation, generates a structure synchronization parameter;

[0021] The influence recognition sub-module analyzes the action trend of the impurity ion concentration fluctuation on the crystal deposition configuration variation based on the structure synchronization parameter, recognizes the influence relationship of the concentration fluctuation of each impurity ion on the deposition structure, and generates impurity response information.

[0022] As a further scheme of the present application, the specific formula for recognizing the influence relationship of the concentration fluctuation of each impurity ion on the deposition structure is:

[0023] ;

[0024] Calculate the influence intensity value;

[0025] wherein, the influence intensity value of the k-th impurity ion on the crystal deposition configuration, the normalized value of the concentration variation amplitude of the k-th impurity ion in the j-th lattice period, the difference value of the concentration fluctuation frequency of the k-th impurity ion in the j-th lattice period relative to the structure spacing fluctuation frequency, the normalized value of the spacing offset amount of the structure stable interval caused by the k-th impurity in the j-th lattice period, the normalized value of the grain arrangement disturbance value in the lattice distortion region caused by the k-th impurity in the j-th lattice period, a lattice period serial number, an impurity type number, a total number of periods.

[0026] As a further scheme of the present application, the process parameter inversion module comprises:

[0027] The period analysis submodule calls the impurity response information, analyzes the element concentration trend in the residual liquid at the end of each period, obtains the time position of each raw material addition, statistically analyzes the concentration change range of the impurities in the period span, calculates the fluctuation interval of the concentration in each period, and generates a period concentration interval;

[0028] The interval screening submodule screens the concentration segments with consistent fluctuation direction according to the period concentration interval, identifies the concentration change segments consistent with the period fluctuation in combination with the impurity concentration change trend parameter, extracts the fluctuation consistency mark, and generates a consistent concentration segment;

[0029] The path determination submodule calls the consistent concentration segment, combines the raw material addition period, the current change direction, and the temperature change region, judges the starting concentration behavior of the impurities in the concentration change segment, analyzes the matching and trend of each parameter, establishes the concentration value corresponding to the diffusion starting point, and generates a diffusion starting point concentration.

[0030] As a further scheme of the present application, the path correction module comprises:

[0031] The retention judgment submodule calls the diffusion starting point concentration, calculates the ion retention time change direction of each detection point in the boundary region, detects the retention data of the ions at multiple detection points, judges the migration delay phenomenon of the ions, generates a migration delay parameter in combination with the retention time trend;

[0032] The distribution comparison submodule compares the distribution difference of the retention behaviors of multiple regions according to the migration delay parameter, analyzes the distribution trend of the retention phenomenon in space, and generates a retention distribution coefficient;

[0033] The behavior correction submodule calls the retention distribution coefficient, analyzes the retention behavior of the boundary path and the migration trend of the ion continuous sampling segment, corrects the behavior offset parameter of the path line segment, adjusts the flow rate rhythm in the current path prediction, and generates a path delay coefficient.

[0034] As a further scheme of the present application, the system further comprises:

[0035] The deviation checking module calls the path delay coefficient, analyzes the deviation degree of the target feeding flow rate and the actual execution flow rate in the feeding instruction, calls the current flow characteristics and the standard flow state of the feeding medium for comparison, adjusts the flow rate control parameter range of the control signal, establishes the feedback relationship between the viscosity and the execution response deviation, and generates a feeding compensation configuration;

[0036] The feeding compensation configuration comprises a flow rate control parameter, a viscosity response relationship, and an execution compensation coefficient.

[0037] As a further scheme of the present application, the deviation checking module comprises:

[0038] The flow rate deviation module calls the path retardation coefficient, analyzes the target feeding flow rate in the feeding instruction and the actual execution flow rate, calculates the difference degree, judges the deviation interval, combines the periodic flow rate data, and generates the flow rate deviation interval;

[0039] The viscosity analysis submodule generates a viscosity influence coefficient by analyzing the influence of viscosity change on the execution stage flow rate according to the flow rate deviation interval and the current flow characteristics and standard flow state of the feeding medium;

[0040] The signal adjustment submodule generates a feeding compensation configuration by adjusting the flow rate control parameter range of the control signal, establishing a feedback relationship between viscosity and execution response deviation, and calling the viscosity influence coefficient.

[0041] On the other hand, an AI-based electrolytic manganese process production quality intelligent prediction method is provided, which is applied to an AI-based electrolytic manganese process production quality intelligent prediction system, and the method comprises:

[0042] S1: Use a temperature sensor to analyze the change trajectory between the sample chamber temperature and the environmental temperature fluctuation trend, evaluate the corresponding relationship between the temperature synchronization deviation and the ion response difference, correct the current cycle concentration reading, and generate a concentration calibration value;

[0043] S2: Use the concentration calibration value to judge the structure cycle synchronization correlation by comparing the period of the lattice spacing change in the deposition process and the time frequency of the concentration fluctuation of each impurity ion, identify the influence relationship of ion concentration fluctuation on the formation of crystal stable configuration, and generate impurity response information;

[0044] S3: Call the impurity response information to analyze the positional relationship between the residual liquid element concentration trend and the raw material feeding behavior, call the raw material feeding period, current change direction and temperature change area, judge the path of the initial concentration change behavior of the impurities, and generate the diffusion starting concentration;

[0045] S4: Use the diffusion starting concentration to judge the ion migration delay phenomenon by calculating the retention change direction between multiple detection points in the boundary area, correct the behavior deviation parameters of the path segment, adjust the flow rate rhythm in the current path prediction, and generate a path retardation coefficient;

[0046] S5: Call the path retardation coefficient to analyze the deviation degree of the target feeding flow rate in the feeding instruction and the actual execution flow rate, compare the current flow characteristics and standard flow state of the feeding medium, adjust the flow rate control parameter range of the control signal, establish a feedback relationship between viscosity and execution response deviation, and generate a feeding compensation configuration.

[0047] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0048] By utilizing the temperature difference fluctuation and the concentration response relationship, dynamic compensation of the deviation between the temperature drift and the ion concentration reading is realized, signal deviation caused by temperature anomalies is reduced, the actual influence degree of element fluctuation on the crystal structure is effectively identified according to the correlation matching of the lattice period change and the impurity fluctuation frequency, the potential interference of impurities on the stability of the crystal structure is locked in time, the starting point of impurity diffusion is accurately determined through the residual liquid concentration trend and the path judgment of the raw material adding position, the diffusion starting time and space of the impurities are clearly traced, the migration path parameters are further adjusted based on the ion retention behavior of the boundary detection point, the control parameter range of the feeding execution process is dynamically optimized according to the actual flow rate and the medium viscosity change, and the element monitoring and concentration control accuracy are improved. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0050] Fig. 1 The system flowchart of the present application;

[0051] Fig. 2 The system framework schematic diagram of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the present application will be described below with reference to the drawings.

[0053] In the embodiments of the present application, the words such as "example", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0054] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. "Of", "corresponding" and "corresponding" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0055] In the embodiments of the present application, sometimes the subscript such as W1 may be written in the form of non-subscript such as W1, and the meanings expressed thereby are consistent when the difference is not emphasized.

[0056] To make the technical problems, technical solutions and advantages to be solved by the present application clearer, specific embodiments will be described in detail below with reference to the drawings.

[0057] The AI-based electrolytic manganese process production quality intelligent prediction system provided by the embodiments of the present application is described below with reference to Figs. 1-2 The present application provides a technical solution, an AI-based electrolytic manganese process production quality intelligent prediction system, which comprises:

[0058] The drift calibration module uses a temperature sensor to analyze the change trajectory between the temperature fluctuation trend of the sample introduction cavity and the environment, evaluate the corresponding relationship between the temperature synchronization deviation and the ion response difference, correct the current cycle concentration reading, and generate a concentration calibration value;

[0059] The structure matching module uses the concentration calibration value to compare the periodical change in the spacing of the lattice during the deposition process and the time frequency of the concentration fluctuation of each impurity ion, judge the structure period synchronization correlation, identify the influence of the ion concentration fluctuation on the formation of the stable crystal structure, and generate impurity response information;

[0060] The process parameter inversion module calls the impurity response information, analyzes the positional relationship between the residual element concentration trend and the raw material feeding behavior, calls the raw material feeding period, the current change direction and the temperature change region, judges the path of the initial concentration change behavior of the impurities, and generates a diffusion starting concentration;

[0061] The path correction module uses the diffusion starting concentration to calculate the retention change direction between multiple detection points in the boundary region, judges the migration delay phenomenon of the ions, corrects the behavior offset parameter of the path segment, adjusts the flow rate rhythm in the current path prediction, generates a path delay coefficient, and generates a path delay coefficient.

[0062] The deviation checking module calls the path delay coefficient, analyzes the deviation degree of the target feeding flow rate and the actual execution flow rate in the feeding instruction, compares the current flow characteristics of the feeding medium with the standard flow state, adjusts the flow rate control parameter range of the control signal, establishes the feedback relationship between the viscosity and the execution response offset, and generates a feeding compensation configuration.

[0063] The concentration calibration value includes the temperature difference change direction, the response delay amplitude and the concentration correction proportion, the impurity response information specifically includes the period frequency matching factor, the structure correlation strength and the impurity influence degree, the diffusion starting concentration includes the concentration fluctuation interval, the initial behavior characteristics and the diffusion trend direction, the path delay coefficient specifically refers to the retention distribution difference, the flow rate rhythm adjustment amount and the path offset parameter, and the feeding compensation configuration includes the flow rate control parameter, the viscosity response relationship and the execution compensation coefficient.

[0064] The drift calibration module includes:

[0065] The temperature difference detection submodule uses a temperature sensor to acquire data on the fluctuation trends of the sample injection chamber temperature and the ambient temperature, analyzes the trajectory of their changes, calculates the direction of temperature difference change, and establishes the temperature difference change range by combining the amplitude and direction of temperature difference change within each detection cycle.

[0066] The temperature difference detection submodule uses a temperature sensor to collect the temperature values ​​inside the sample injection chamber and the external environment during the electrolysis process. The collection interval is set to once every 10 seconds, and 6 sets of data are collected continuously in each cycle, denoted as . ( (Representing the acquisition time), for example, the injection chamber temperature during the first acquisition cycle is recorded as follows: , , , , , The ambient temperatures were recorded as follows: , , , , , Based on the above data, trend analysis was performed on the temperature change trajectory. Using the acquisition time as the x-axis and temperature as the y-axis, temperature change curves for the injection chamber and the environment were plotted. By observing the trend of these curves and comparing the temperature change trajectories of the two, it was determined that the overall temperature trajectory of the injection chamber showed an upward trend. For example... If similar calculated values ​​are continuously positive, then the trend is upward. Simultaneously, analyze the ambient temperature curve to identify the upward trend of the ambient temperature trajectory, such as... The continuous value is positive. Further calculations are performed to determine the direction of temperature difference change between the injection chamber and the ambient temperature. Calculation, for example If the continuous temperature difference value changes All are positive values, for example Multiple consecutive positive values ​​indicate a continuously widening temperature difference trend. Continuous calculations determine the trend of change, and combine each The range of temperature difference variation is established as described above. If the temperature range within this collection period is 1.8℃-2.1℃, then 1.8℃ and 2.1℃ are used as the endpoints of the interval to generate the temperature difference range.

[0067] The synchronization determination submodule evaluates the trend of temperature synchronization deviation within a continuous sampling period based on the temperature difference change range. Combining the duration and direction of deviation, it judges the delayed response behavior of the injection chamber, analyzes the continuity and consistency of the synchronization deviation, and generates synchronization deviation parameters.

[0068] The specific formula for determining the delay response behavior of the sample cavity is:

[0069] ;

[0070] Calculate the synchronization deviation trend index;

[0071] wherein, is the synchronization deviation trend index, is the sample cavity temperature normalized value collected in the ith cycle, is the ambient temperature normalized value collected in the ith cycle, is the sample cavity temperature normalized value collected in the i-1th cycle, is the ambient temperature normalized value collected in the i-1th cycle, is the temperature normalization stability constant, is the sign function, is the direction weight corresponding to the temperature change direction in the ith cycle, is the total number of sampling cycles, is the current sampling cycle index number, is the previous sampling cycle index number.

[0072] Formula:

[0073] ;

[0074] Formula details and formula calculation derivation process:

[0075] The formula is used to calculate the continuous consistency trend of temperature synchronization deviation, and the result is used to determine the continuity and significance of the influence of temperature drift trend on manganese electrolysis concentration measurement;

[0076] Parameter meaning and setting value:

[0077] is the sample cavity temperature normalized value collected in the ith cycle, after real-time collection of actual sample cavity temperature data, normalization processing is adopted, the monitoring temperature of the second cycle is set to 35.6 degrees Celsius, the normalization interval is set to the actual monitoring minimum value of 20 degrees Celsius and the maximum value of 40 degrees Celsius, and after normalization ;

[0078] is the ambient temperature normalized value collected in the ith cycle, by monitoring the actual ambient temperature, the same cycle monitoring value is 30.4 degrees Celsius, and after normalization ;

[0079] is the normalized value of the temperature stability constant, which prevents the denominator from being zero, and is set to 0.01;

[0080] This is a sign function used to determine whether the direction of the temperature difference in the current cycle is consistent with that in the previous cycle;

[0081] The weight is the direction of temperature change in the i-th period. The weight standard is graded according to the magnitude of the absolute value of the temperature difference change. The weight value is set by the fluctuation range detected on site. The weight is 0.8 for below 0.2, 1.0 for 0.2-0.5, and 1.2 for above 0.5. Here, the absolute value of the temperature difference in the second period is |0.78-0.52|=0.26, corresponding to a weight of 1.0.

[0082] To represent the total number of sampling periods, we set n=4;

[0083] The monitoring sampling data is set as follows (all are normalized values): Period 1: , Weight 0.8; Second period: , Weight 1.0; 3rd period: , Weight 1.0; 4th period: , Weight 1.2;

[0084] Substitute the parameters into the formula to calculate:

[0085] Cycle 2:

[0086] ;

[0087] ;

[0088] ;

[0089] 3rd cycle:

[0090] ;

[0091] ;

[0092] ;

[0093] 4th cycle:

[0094] ;

[0095] ;

[0096] ;

[0097] Formula average:

[0098]

[0099] The result 0.1820 indicates that the temperature synchronization deviation of the current period is consistent and continuous, and the value greater than 0 represents that the temperature drift direction of most periods is consistent, and the change amplitude is within the normal monitoring interval range. The trend value is used for the generation of the synchronization deviation parameter, and can provide a quantitative reference for the subsequent automatic compensation or warning logic.

[0100] The response correction submodule calculates the corresponding relationship between the deviation degree and the ion response difference in the concentration curve according to the synchronization deviation parameter, corrects the current period concentration reading through the matching relationship between the temperature difference change and the concentration fluctuation, and generates a concentration calibration value;

[0101] The response correction submodule analyzes the corresponding relationship between the deviation parameter and the ion concentration curve according to the synchronization deviation parameter, and takes the actually measured ion concentration data as the analysis object, for example, takes the concentration data points of the nickel ion concentration continuously measured in the sampling process represent the first detection time) as analysis data, assuming that the concentrations measured at the 5 sampling points are , , , , , , the concentration points and the synchronization deviation parameters of the temperature difference change at the corresponding time are calculated, for example, the temperature difference corresponding to time is 2.1℃, the concentration correction reference value set in advance is called, when the temperature difference is located in the interval 2.0℃ to 2.2℃, the corresponding concentration correction coefficient is set to 0.95, this coefficient is pre-set according to the actual production process experience, and the measured concentration point is multiplied by the correction coefficient, for example, the corrected concentration , similar calculations are performed on all concentration points to obtain the corrected concentration values of each point, a corrected concentration curve is established, the corrected concentration curve data of the current period is called, and the average correction amplitude of the concentration points is calculated, for example , the average correction amplitude is the concentration calibration value of the current period.

[0102] The structure matching module comprises:

[0103] The period comparison submodule acquires the concentration calibration value, collects the lattice spacing change period in the deposition process, acquires the time frequency of the impurity ion concentration fluctuation, compares the frequency difference of the lattice spacing period and each kind of impurity ion concentration fluctuation, analyzes the consistency of the period change, and generates a period matching difference.

[0104] ​​The period contrast sub-module obtains a concentration calibration value, which is specifically a corrected concentration data of multiple impurity ions in the electrolysis process, continuously collects real-time data of the lattice spacing of the crystal during the deposition process by an X-ray diffractometer, for example, the lattice spacings of 6 continuous measurements are 、 、 、 、 、 , the change amount of the lattice spacing between each two continuous measurement points is calculated, for example, the change amount from the first to the second is , each change amount is calculated in turn, the period data of the change of the lattice spacing is established, the concentration fluctuation frequency of the impurity ions such as nickel ions is measured simultaneously by a mass spectrometer, the interval time of the highest point concentration in the period is taken as a fluctuation period, for example, the interval times of the concentration peaks are 3 minutes, 3.2 minutes and 3.1 minutes, the lattice period and the nickel ion fluctuation period are compared and calculated one by one, the period matching ratio is obtained by dividing the lattice period by the impurity ion period, when the matching ratio is between 0.95-1.05, it is determined that the periods match, for example, the matching ratio calculated by the lattice period of 3.05 minutes and the nickel ion period of 3 minutes is 3.05÷3=1.017, which satisfies the period matching condition, a plurality of matching ratios are summarized and analyzed to calculate the matching difference degree, if the matching difference degree is between 0.95 and 1.05, it is determined that the period matching difference is small, and if it exceeds this range, the difference is large, and the period matching difference is generated.

[0105] The synchronous analysis sub-module determines the synchronous correlation of the structure period and the impurity ion concentration fluctuation in the time sequence according to the period matching difference, selects the period sections with consistent change trend, establishes the correlation between the structure period and the ion concentration fluctuation combined with the structure period synchronization parameter, and generates the structure synchronization parameter;

[0106] The synchronous analysis submodule analyzes data based on period matching differences, using period groups with matching differences close to 1 as the base data. For example, it selects three data groups with period matching differences of 1.017, 0.998, and 1.004, and sequentially calls up the period data of lattice spacing and the fluctuation frequency of impurity ion concentration within the corresponding period group. Using the time coordinates corresponding to the start and end points of lattice changes within the period data as a benchmark, it determines whether the peak occurrence time of impurity ion concentration fluctuation falls within the start and end time range of the lattice period data. If the start and end time of the lattice period is 0 to 3.05 minutes, and the peak occurrence time of impurity ion concentration is 2.95 minutes, then it is judged... If the fluctuation time of impurity ion concentration is within the lattice period range, repeat the above steps to judge each set of data one by one, record the results of each set of judgments, and screen out the period groups in which the occurrence time of all impurity ion peaks falls within the lattice period range. For example, in a group with a period difference of 1.004, the lattice period range is 0 to 3.10 minutes, and the impurity ion peak is at 3.05 minutes, which falls completely within the lattice period range. Determine the structural period synchronization parameter by the proportion of the number of screened period groups to the total number of period groups. When this proportion exceeds 80%, it is confirmed that the structural period and impurity ion fluctuations have strong synchronization, and the structural synchronization parameter is established.

[0107] The influence identification submodule analyzes the trend of impurity ion concentration fluctuations on crystal deposition configuration changes based on structural synchronization parameters, identifies the influence relationship of each impurity ion concentration fluctuation on the deposition structure, and generates impurity response information.

[0108] The specific formula for identifying the influence of concentration fluctuations of each impurity ion on the deposition structure is as follows:

[0109] ;

[0110] Calculate the impact intensity value;

[0111] in, Let be the intensity value of the influence of the k-th impurity ion on the crystal deposition configuration. This is the normalized value of the concentration variation of the k-th impurity ion in the j-th lattice period. Let be the difference between the frequency of the concentration fluctuation of the k-th impurity ion and the frequency of the spacing fluctuation in the j-th lattice period. This is the normalized value of the spacing offset of the structurally stable region caused by the k-th impurity within the j-th lattice period. This is the normalized value of the grain arrangement perturbation value in the lattice distortion region caused by the k-th impurity within the j-th lattice period. The lattice period number, Number the impurity types. This represents the total number of cycles.

[0112] formula:

[0113] ;

[0114] Formula details and formula calculation derivation process:

[0115] The formula is used to calculate the influence intensity value of each impurity ion on the crystal deposition configuration, and the obtained result is used to determine the influence effect of impurity fluctuation on the deposition structure;

[0116] Parameter meaning and set value:

[0117] is the influence intensity value of the kth impurity ion on the crystal deposition configuration,

[0118] is the normalized value of the concentration variation amplitude of the kth impurity ion in the jth lattice period, the numerical value is derived from the original value of the impurity concentration collected by the ion concentration monitor, and is obtained by normalization with the maximum concentration variation interval of the same period;

[0119] is the difference between the fluctuation frequency of the kth impurity ion and the fluctuation frequency of the structure spacing in the jth lattice period, and the impurity fluctuation frequency is obtained by extracting the main peak from the high-frequency sampled concentration time sequence signal;

[0120] is the normalized value of the spacing offset of the structure stable interval caused by the kth impurity in the jth lattice period, and the data is obtained by quantitatively measuring the lattice spacing change by an X-ray diffractometer;

[0121] is the normalized value of the grain arrangement disturbance value in the lattice distortion region caused by the kth impurity in the jth lattice period, which is obtained by using a high-resolution electron microscope to statistically arrange the grains in the distortion region;

[0122] is the total number of periods, and the lattice structure sampling monitoring record is set to collect 5 periods, is the lattice period number, which is 1 to 5 in turn, is the impurity type number, and the copper impurity number is 1; wherein, the first period is set to: , , , , the second period is: , , , , the third period is: , , , , the fourth period is: , , , , Period 5: , , , ;

[0123] Substitute the parameters into the formula for calculation:

[0124] ;

[0125] ;

[0126] ;

[0127] The results show that the influence strength value of copper impurities in the lattice structure deposition process of this batch is 0.0436, representing the comprehensive normalized influence of copper impurity fluctuation and structure disturbance, corresponding to the impurity response information, which can be used for subsequent evaluation of the risk contribution of copper impurities to the deposition structure in the quality prediction system.

[0128] The process parameter inversion module includes:

[0129] The period analysis submodule calls the impurity response information, analyzes the element concentration trend in the residual liquid at the end of each period, obtains the time position of each raw material addition, and statistically analyzes the concentration change range of impurities within the period span. The concentration fluctuation interval in each period is calculated to generate the period concentration interval.

[0130] The period analysis submodule calls impurity response information, which is the action strength data of the influence of different impurity ions on the lattice established in the foregoing steps, selects the concentrations of multiple impurity ions such as nickel ions and copper ions as the analysis objects, and collects the concentration data of nickel ions and copper ions in the residual liquid at the end of each electrolysis period, for example, the nickel ion concentration is 3.8 mg / L and the copper ion concentration is 2.4 mg / L at the end of a certain period, and the same ion concentration values of the previous period are recorded, which are nickel ion 3.2 mg / L and copper ion 1.9 mg / L, respectively. The change trend of the concentration of each impurity ion is calculated one by one, specifically, the current period concentration is subtracted from the previous period concentration, such as nickel ion 3.8 mg / L-3.2 mg / L = 0.6 mg / L and copper ion 2.4 mg / L-1.9 mg / L = 0.5 mg / L. The raw material feeding control system is called to obtain the feeding time of the raw material, and the time position of the start of the raw material feeding in the electrolytic cell is recorded, for example, the start time of the raw material feeding in this period is the 10th minute and the end time is the 15th minute. The time sequence range of the period span is determined in this way, the concentration fluctuation amplitude of each ion in the period is counted one by one according to the impurity concentration data of two consecutive periods, specifically, the difference between the maximum and minimum values measured in each period is calculated, such as nickel ion concentration maximum 4.0 mg / L and minimum 3.0 mg / L, fluctuation amplitude 4.0 mg / L-3.0 mg / L = 1.0 mg / L. The fluctuation amplitude of copper ions is calculated as 0.8 mg / L. The fluctuation amplitude of each ion is recorded, and the concentration fluctuation interval of each ion in the period is determined according to the data record of the concentration fluctuation amplitude in multiple periods, for example, the nickel ion fluctuation interval is 3.0 mg / L-4.0 mg / L and the copper ion fluctuation interval is 1.9 mg / L-2.7 mg / L. The period concentration interval is generated.

[0131] The interval screening submodule screens the concentration segments with consistent fluctuation direction according to the period concentration interval, identifies the concentration change segments consistent with the period fluctuation in combination with the impurity concentration change trend parameter, extracts the fluctuation consistency marker, and generates the consistent concentration segment.

[0132] The interval screening submodule calls the periodic concentration interval data of impurity ions such as nickel ions and copper ions based on the recorded concentration data of multiple periods according to the periodic concentration interval, and determines the concentration fluctuation direction of the impurity ions period by period. Taking the time sequence of the maximum and minimum concentration values as the basis, for example, the maximum concentration value of nickel ions in period 1 appears at the end of the period, and the minimum concentration value appears at the beginning of the period. Therefore, it is determined that the fluctuation trend of nickel ions in the period is an upward trend. The similar judgment of fluctuation trend is performed for each ion in multiple periods. By comparing the fluctuation trend of ion concentration whether it remains consistent in multiple consecutive periods, the complete consistency of impurity ion fluctuation direction in three consecutive periods is taken as the standard of consistent fluctuation direction. For example, nickel ions in consecutive periods 1, 2 and 3 all show an upward trend in concentration, and copper ions in periods 1 and 2 show an upward trend but in period 3 show a downward trend. Therefore, nickel ions meet the consistent fluctuation direction standard, and copper ions do not. The concentration fluctuation data segments of all impurities that meet the consistent fluctuation direction standard are screened, and the concentration values in each segment are marked, such as the concentration segments of nickel ions in periods 1 to 3 are marked as consistent concentration segments. The marked segments are associated with the impurity concentration change trend parameters and recorded to generate consistent concentration segments.

[0133] The path determination submodule calls the consistent concentration segment, combines the raw material adding period, the current change direction and the temperature change region, determines the starting concentration behavior of the impurity in the concentration change segment, analyzes the matching and trend of each parameter, establishes the concentration value corresponding to the starting point of the diffusion path, and generates the starting concentration of the diffusion starting point.

[0134] The path determination sub-module calls the consistency concentration section, and compares the initial concentration behavior of impurity ions in the consistency concentration section one by one based on the recorded raw material adding period, current change direction and temperature change region. First, the raw material adding period is taken as a reference, and the corresponding relationship between the concentration data at the beginning of each concentration section and the starting time of raw material addition is recorded. For example, the time when the initial concentration of nickel ions in the consistency concentration section is 3.0 mg / L is the 10th minute, which is consistent with the starting time of raw material addition. Further analysis of the current change direction corresponding to this time is performed, for example, the current is in an upward trend at this time. Based on the actual electrolytic tank measured current data, for example, the current is 550 A at the 10th minute and 560 A at the 11th minute, and the current rising rate is 560 A-550 A=10 A / minute, confirming that the current trend is rising. Then, the temperature change data recorded by the temperature sensor is called to determine the temperature change trend in the electrolysis region at this starting time, for example, the temperature rises from 28°C to 29°C at this time, and the temperature change is in an upward trend. The above parameters are compared respectively, and the starting concentration data is called as the concentration value corresponding to the diffusion path starting point, for example, the initial concentration of nickel ions is 3.0 mg / L, and the diffusion starting point concentration is generated.

[0135] The path correction module includes:

[0136] The retention judgment sub-module calls the diffusion starting point concentration, calculates the ion retention time change direction of each detection point in the boundary region, detects the retention data of ions at multiple detection points, judges the migration delay phenomenon of ions, and generates a migration delay parameter in combination with the retention time trend.

[0137] The residence judgment submodule calls the diffusion starting point concentration, and sets multiple detection points at the boundary region of the electrolytic cell as the implementation object, such as detection points A, B, and C. The time data of nickel ion concentration from the diffusion starting point to each detection point is recorded, for example, the time of nickel ion from the diffusion starting point to detection point A is 8 minutes, to B is 10 minutes, and to C is 13 minutes. The residence time of nickel ion between each two adjacent detection points is calculated, such as the residence time of nickel ion between A and B is 10 minutes minus 8 minutes, that is, 2 minutes; the residence time between B and C is 13 minutes minus 10 minutes, that is, 3 minutes. The residence times of each section are compared one by one, and the change direction of each section of residence time is calculated, such as the residence time from A-B section to B-C section increases from 2 minutes to 3 minutes, that is, the change direction is the lengthening trend. The change trend of multiple similar sampling data is counted, and if the residence time trend is lengthened for 3 consecutive measurements, it is judged as the migration delay phenomenon. The residence data of multiple detection points are integrated, the residence trend of each sampling is recorded, and the lengthening trend or shortening trend is marked respectively. The frequency of the trend between each detection point is counted, and the lengthening trend accounts for more than 70% of the total trend number as the standard for judging the migration delay. The proportion of the lengthening trend of ion residence time is calculated combined with multiple measurement results, the degree of migration delay is determined, and the migration delay parameter is generated.

[0138] The distribution comparison submodule compares the distribution difference of the residence behavior of multiple regions according to the migration delay parameter, analyzes the distribution trend of the residence phenomenon in space, and generates a residence distribution coefficient.

[0139] The distribution comparison submodule calls the detection point data at different positions in the boundary region of the electrolytic cell according to the migration delay parameter, for example, regions I, II, and III each contain multiple detection points, such as detection points A1 and A2 in region I, B1 and B2 in region II, and C1 and C2 in region III; the average residence time of the detection points in each region is calculated, for example, the average residence time of region I is (2+2.5) / 2=2.25 minutes, and the average residence time of region II and III is calculated in the same way; the average residence time of each region is compared one by one, for example, the average residence time of region I is 2.25 minutes, the average residence time of region II is 3 minutes, and the average residence time of region III is 3.5 minutes; by direct comparison, the difference in residence behavior of each region is confirmed, and it is determined that the average residence time of region III is the longest; the average residence time data of different regions is statistically calculated, and the difference between the maximum average residence time and the minimum average residence time between regions is obtained, for example, 3.5 minutes of region III minus 2.25 minutes of region I is 1.25 minutes; the time difference is taken as the basis for evaluating the difference in residence distribution of different regions, and divided by the average value of the region to determine the residence distribution coefficient, that is, 1.25 minutes divided by (2.25+3+3.5) / 3, and the residence distribution coefficient is calculated to be about 0.43; the residence distribution coefficient value is used to confirm the distribution trend of the residence phenomenon in the electrolytic cell space, and the residence distribution coefficient is generated.

[0140] The behavior correction submodule calls the residence distribution coefficient, analyzes the residence behavior of the boundary path and the migration trend of the ion continuous sampling section, corrects the behavior offset parameter of the path line segment, adjusts the flow rate rhythm in the current path prediction, and generates the path delay coefficient;

[0141] The behavior correction sub-module calls the retention distribution coefficient, respectively records the ion continuous sampling migration path data in the electrolytic cell boundary area, such as the sampling path starting point is the position corresponding to the diffusion starting point concentration, the path continuous sampling points are detection points X, Y and Z; the ion migration speed between adjacent two sampling points is calculated, for example, the ion migration speed from X to Y is (the time difference of the position Y concentration peak value appearance time minus the position X concentration peak value appearance time) corresponding to the spatial distance divided by the time difference; such as the spatial distance from X to Y is 20 cm, the concentration peak time difference is 2 minutes, then the migration speed is 20 cm / 2 minutes=10 cm / minute; similarly, the migration speed from Y to Z is calculated, if the speed decreases gradually, such as from X-Y 10 cm / minute to Y-Z 7 cm / minute, then it is judged that the migration trend is deceleration; the influence of the retention distribution coefficient of the retention behavior in the boundary path on the ion migration trend in the path is analyzed, the retention distribution coefficient is multiplied by the actual measured migration speed, such as the retention distribution coefficient is 0.43, the actual migration speed of X-Y section is 10 cm / minute, then the corrected speed is 10 cm / minute x (1-0.43)=5.7 cm / minute; the original flow rate rhythm in the path prediction is adjusted correspondingly, such as the original set prediction path speed is 8 cm / minute, the adjusted speed is 5.7 cm / minute; all path segments are corrected one by one through the above operation, and finally the path retention coefficient is generated.

[0142] The deviation check module includes:

[0143] The flow rate deviation sub-module calls the path retention coefficient, analyzes the target feeding flow rate and the actual execution flow rate in the feeding instruction, calculates the difference degree, judges the deviation interval, combines the periodic flow rate data, and generates the flow rate deviation interval;

[0144] The flow rate deviation module calls the path delay coefficient based on the target feeding flow rate given by the electrolytic cell feeding instruction. For example, if the target feeding flow rate is 20 liters per minute, the actual feeding flow rate is measured in real time by a flow sensor, for example, the measured actual flow rates are 18 liters per minute in the first minute, 17 liters per minute in the second minute, and 19 liters per minute in the third minute. The difference between the target feeding flow rate and the actual flow rate is calculated one by one, for example, the flow rate deviation in the first minute is 20 liters (target flow rate) minus 18 liters (actual flow rate), which is 2 liters. The deviations at multiple measurement times are counted, and the average flow rate deviation in each period is recorded, for example, the average deviation in the period is calculated by averaging the deviations of 2 liters, 3 liters, and 1 liter at the three measurement times, which is (2+3+1) ÷ 3 = 2 liters. Further, the aforementioned path delay coefficient is called, for example, the path delay coefficient is 0.3, and the product of the coefficient and the average deviation in the period is calculated, which is 2 liters × 0.3 = 0.6 liters. The product value 0.6 liters is used as the correction amount of the flow rate deviation degree, and the percentage relationship between the correction amount and the target flow rate is analyzed, for example, the proportion of 0.6 liters to the target flow rate of 20 liters is 0.6 ÷ 20 = 3%. According to this proportion, it is determined that the flow rate deviation degree exceeding 5% is in the high deviation interval, and the flow rate deviation degree less than or equal to 5% is in the normal deviation interval. The 3% calculated in the current period is classified into the normal deviation interval, and the deviation interval data of multiple periods is determined by this method. The statistical data of the deviation interval of each period is summarized to generate the flow rate deviation interval.

[0145] The viscosity analysis submodule analyzes the influence of viscosity change on the flow rate in the execution stage according to the flow rate deviation interval, calls the current flow characteristics and standard flow state of the feeding medium, and generates a viscosity influence coefficient.

[0146] The viscosity analysis submodule calls the flow characteristic data of the current state of the feeding medium according to the flow rate deviation interval, such as the electrolyte, the real-time viscosity is measured as 5.5 mPa·s under the current state using the viscometer, and the viscosity value of the standard flow state of the electrolyte set by the standard process is called, for example, the standard viscosity value is set as 5.0 mPa·s, and the viscosity values of the current state and the standard state are recorded respectively; the difference between the viscosity of the current state and the standard viscosity is calculated, specifically by subtracting the standard viscosity value from the current viscosity value, for example, the calculation result is 5.5 mPa·s-5.0 mPa·s=0.5 mPa·s; the influence direction of the viscosity difference on the feeding flow rate in the actual execution stage is analyzed, the measurement data of the actual feeding flow rate in multiple cycles is called, and the deviation amount of the actual flow rate and the target flow rate in each cycle is calculated, such as the first cycle deviation in the foregoing actual flow rate measurement data is 2 liters, the cycle deviation data is recorded as 2 liters, 3 liters and 1 liter respectively, the viscosity difference 0.5 mPa·s is associated with the actual flow rate deviation data, specifically by calculating the average value of the flow rate deviation amount in multiple cycles, for example, the average value is (2+3+1)÷3=2 liters, the viscosity difference is divided by the average flow rate deviation amount, that is, 0.5 mPa·s÷2 liters=0.25 mPa·s / liter, and the value is defined as the viscosity influence coefficient, which quantifies the influence degree of viscosity change on the actual flow rate in the feeding execution stage, and generates the viscosity influence coefficient.

[0147] The signal adjustment submodule calls the viscosity influence coefficient to adjust the flow rate control parameter range of the control signal, establishes the feedback relationship between the viscosity and the execution response deviation, and generates the feeding compensation configuration;

[0148] The signal adjustment submodule calls the viscosity influence coefficient, using the original feed flow rate control parameter range in the control signal as the adjustment basis. For example, if the original flow rate control parameter range was set to 18 to 22 liters per minute, the viscosity influence coefficient of 0.25 mPa·s / L is used to calculate the flow rate parameter adjustment corresponding to the viscosity change. Specifically, this is the product of the viscosity influence coefficient and the viscosity change, i.e., 0.25 mPa·s / L × 0.5 mPa·s = 0.125 liters. This adjustment amount is used to adjust the upper and lower limits of the original flow rate control parameter range separately. For example, the upper limit flow rate of 22 liters minus the adjustment amount of 0.125 liters results in an adjusted flow rate of 21.875 liters, and the lower limit flow rate of 18 liters minus the adjustment amount of 0.125 liters results in an adjusted flow rate of 21.875 liters. The flow rate was then adjusted to 17.875 liters, completing the adjustment of the flow rate control parameter range. Further, based on the adjusted flow rate control parameter range, the actual measured viscosity and flow rate data were retrieved, and the data correlation between the measured viscosity change and the actual executed flow rate deviation was compared one by one. For example, a viscosity deviation of 0.5 mPa·s corresponds to an actual flow rate deviation of 2 liters. This establishes a feedback data relationship between viscosity and the executed response deviation. Specifically, a viscosity change of 0.1 mPa·s corresponds to an actual flow rate deviation of 0.4 liters. Multiple similar viscosity-flow rate data records were recorded and summarized to form a corresponding relationship dataset. Finally, the adjusted flow rate control parameter range and the corresponding relationship dataset were used to generate the feeding compensation configuration.

[0149] An AI-based intelligent prediction method for the production quality of electrolytic manganese processes is proposed. This method is applied to an AI-based intelligent prediction system for the production quality of electrolytic manganese processes. The method includes:

[0150] S1: Using a temperature sensor, analyze the change trajectory between the temperature fluctuation trends of the injection chamber and the ambient temperature, evaluate the correspondence between temperature synchronization deviation and ion response difference, correct the current cycle concentration reading, and generate a concentration calibration value.

[0151] S2: Using the concentration calibration value, by comparing the period of lattice spacing change during the deposition process with the time frequency of each impurity ion concentration fluctuation, the synchronous correlation of the structural period is determined, the influence of ion concentration fluctuation on the formation of a stable crystal configuration is identified, and impurity response information is generated.

[0152] S3: Call the impurity response information, analyze the positional relationship between the residual liquid element concentration trend and the raw material addition behavior, call the raw material addition time period, current change direction and temperature change area, make path judgment on the impurity initial concentration change behavior, and generate diffusion start concentration;

[0153] S4: Using the diffusion initiation concentration, by calculating the retention change direction between multiple detection points in the boundary region, the migration delay phenomenon of ions is determined, the behavior offset parameter of the path segment is corrected, the flow rate rhythm in the current path prediction is adjusted, and the path delay coefficient is generated.

[0154] S5: Call the path delay coefficient to analyze the deviation between the target feed flow rate and the actual execution flow rate in the feed instruction, call the current flow characteristics of the feed medium and the standard flow state for comparison, adjust the flow rate control parameter range of the control signal, establish the feedback relationship between viscosity and execution response offset, and generate feed compensation configuration.

[0155] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0156] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0157] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0158] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0159] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0160] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0161] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An AI-based intelligent prediction system for production quality of an electrolytic manganese process, characterized in that, The system comprises: The drift calibration module uses a temperature sensor to analyze the change trajectory between the sample chamber temperature and the ambient temperature fluctuation trend, assesses the corresponding relationship between the temperature synchronization deviation and the ion response difference, corrects the current cycle concentration reading, and generates a concentration calibration value; The structure matching module uses the concentration calibration value to judge the structure cycle synchronization correlation by comparing the period of the lattice spacing change during the deposition process and the time frequency of the concentration fluctuation of each impurity ion, identifies the influence of the ion concentration fluctuation on the stable configuration of the crystal, and generates impurity response information; The process parameter inversion module calls the impurity response information, analyzes the positional relationship between the residual element concentration trend and the raw material feeding behavior, calls the raw material feeding period, current change direction, and temperature change area, judges the path of the initial concentration change behavior of the impurity, and generates a diffusion starting concentration; The path correction module uses the diffusion starting concentration to judge the ion migration delay phenomenon by calculating the retention change direction between multiple detection points in the boundary area, corrects the behavior deviation parameter of the path segment, adjusts the flow rate rhythm in the current path prediction, and generates a path delay coefficient. 2.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 1, wherein, The concentration calibration value includes temperature difference change direction, response delay amplitude, and concentration correction ratio. The impurity response information specifically includes period frequency matching factor, structure correlation strength, and impurity influence degree. The diffusion starting concentration includes concentration fluctuation interval, initial behavior characteristics, and diffusion trend direction. The path delay coefficient specifically refers to the retention distribution difference, flow rate rhythm adjustment amount, and path deviation parameter. 3.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 1, characterized in that, The drift calibration module comprises: The temperature difference detection submodule uses a temperature sensor to obtain the fluctuation trend data of the sample chamber temperature and the ambient temperature, analyzes the change trajectory of the two, and calculates the change direction of the temperature difference. Combined with the change amplitude and direction of the temperature difference in each detection cycle, the temperature difference change interval is established; The synchronization judgment submodule assesses the trend of the temperature synchronization deviation in the continuous sampling period based on the temperature difference change interval, judges the delay response behavior of the sample chamber by combining the deviation duration and change direction, analyzes the continuous consistency of the synchronization deviation, and generates a synchronization deviation parameter; The response correction submodule calculates the corresponding relationship between the deviation degree and the ion response difference in the concentration curve according to the synchronization deviation parameter, corrects the current cycle concentration reading through the matching relationship between the temperature difference fluctuation and the concentration fluctuation, and generates a concentration calibration value. 4.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 3, wherein, The specific formula for judging the delay response behavior of the sample chamber is: ； Calculate the synchronization deviation trend index; wherein, is a synchronization deviation tendency index, is a sample chamber temperature normalized value collected in the i-th cycle, is an ambient temperature normalized value collected in the i-th cycle, is a sample chamber temperature normalized value collected in the i-1-th cycle, is an ambient temperature normalized value collected in the i-1-th cycle, is a temperature normalization stability constant, is a sign function, is a direction weight corresponding to the temperature change direction in the i-th cycle, is a total number of sampling cycles, is a current sampling cycle index number, is a previous sampling cycle index number. 5.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 3, wherein, The structure matching module comprises: The period comparison submodule obtains the concentration calibration value, collects the period of the lattice spacing change during the deposition process, obtains the time frequency of the impurity ion concentration fluctuation, compares the frequency difference between the lattice spacing period and the concentration fluctuation of each impurity ion, analyzes the consistency of the period change, and generates a period matching difference; The synchronization analysis submodule judges the synchronization correlation of the structure period and the impurity ion concentration fluctuation in time sequence according to the period matching difference, selects the period section with consistent change trend, establishes the correlation between the structure period and the ion concentration fluctuation by combining the structure period synchronization parameter, and generates a structure synchronization parameter; The influence identification submodule analyzes the action trend of the impurity ion concentration fluctuation on the crystal deposition configuration change based on the structure synchronization parameter, identifies the influence relationship of the concentration fluctuation of each impurity ion on the deposition structure, and generates impurity response information. 6.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 5, wherein, The specific formula of the influence relationship of the concentration fluctuation of each impurity ion on the deposition structure is: ； The influence intensity value is calculated; wherein, is the influence strength value of the kth impurity ion on the crystal deposition configuration, is the normalized value of the concentration variation amplitude of the kth impurity ion in the jth lattice period, is the difference value of the kth impurity ion concentration fluctuation frequency relative to the structure spacing fluctuation frequency in the jth lattice period, is the normalized value of the spacing offset of the structure stable interval caused by the kth impurity in the jth lattice period, is the normalized value of the grain arrangement disturbance value in the lattice distortion region caused by the kth impurity in the jth lattice period, is the lattice period number, is the impurity type number, is the total number of periods. 7.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 5, wherein, The process parameter inversion module comprises: The period analysis submodule calls the impurity response information, analyzes the element concentration trend in the residual liquid at the end of each period, obtains the time position of each raw material addition, statistically analyzes the concentration change amplitude of the impurities in the period span, calculates the fluctuation interval of the concentration in each period, and generates a period concentration interval; The interval screening submodule screens the concentration segments with consistent fluctuation directions according to the period concentration interval, identifies the concentration change segments consistent with the period fluctuation by combining the impurity concentration change trend parameter, extracts the fluctuation consistency markers, and generates consistent concentration segments; The path determination submodule calls the consistent concentration segments, combines the raw material addition period, the current change direction, and the temperature change region, determines the path of the initial concentration behavior of the impurities in the concentration change segment, analyzes the matching and trend of each parameter, establishes the concentration value corresponding to the diffusion path starting point, and generates a diffusion starting point concentration. 8.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 7, wherein, The path correction module comprises: The retention judgment submodule calls the diffusion starting point concentration, calculates the ion retention time change direction of each detection point in the boundary region, detects the retention data of the ions at multiple detection points, judges the migration delay phenomenon of the ions, combines the retention time trend, and generates a migration delay parameter; The distribution comparison submodule compares the distribution difference of the retention behaviors of multiple regions according to the migration delay parameter, analyzes the distribution trend of the retention phenomenon in space, and generates a retention distribution coefficient; The behavior correction submodule calls the retention distribution coefficient, analyzes the retention behavior of the boundary path and the migration trend of the ion continuous sampling segment, corrects the behavior offset parameter of the path line segment, adjusts the flow rate rhythm in the current path prediction, and generates a path delay coefficient. 9.The AI-based intelligent prediction system for production quality of an electrolytic manganese process, according to claim 1, wherein, The system further comprises: The deviation checking module calls the path delay coefficient, analyzes the deviation degree of the target feeding flow rate and the actual execution flow rate in the feeding instruction, calls the current flow characteristics and the standard flow state of the feeding medium for comparison, adjusts the flow rate control parameter range of the control signal, establishes the feedback relationship between the viscosity and the execution response deviation, and generates a feeding compensation configuration; The feeding compensation configuration comprises a flow rate control parameter, a viscosity response relationship, and an execution compensation coefficient. The deviation checking module comprises: The flow rate deviation submodule calls the path delay coefficient, analyzes the target feeding flow rate and the actual execution flow rate in the feeding instruction, calculates the difference degree, judges the deviation interval, and generates a flow rate deviation interval by combining the period flow rate data; The viscosity analysis submodule calls the current flow characteristics and the standard flow state of the feeding medium according to the flow rate deviation interval, analyzes the influence of the viscosity change on the execution stage flow rate, and generates a viscosity influence coefficient; The signal adjusting sub-module calls the viscosity influence coefficient, adjusts the flow rate control parameter range of the control signal, establishes a feedback relationship between viscosity and execution response deviation, and generates a feed compensation configuration.

10. An AI-based intelligent prediction method for production quality of an electrolytic manganese process, characterized in that, The method is used to realize the AI-based electrolytic manganese process production quality intelligent prediction system according to any one of claims 1-9, and the method comprises: S1: using a temperature sensor, analyzing the change trajectory between the temperature fluctuation trend of the sample cavity and the environment, evaluating the corresponding relationship between the temperature synchronization deviation and the ion response difference, correcting the current cycle concentration reading, and generating a concentration calibration value; S2: using the concentration calibration value, comparing the periodical change of the lattice spacing during the deposition process and the time frequency of the concentration fluctuation of each impurity ion, judging the structure period synchronization correlation, identifying the influence of ion concentration fluctuation on the formation of crystal stable configuration, and generating impurity response information; S3: calling the impurity response information, analyzing the positional relationship between the residual liquid element concentration trend and the raw material feeding behavior, calling the raw material feeding period, current change direction and temperature change area, judging the path of the initial concentration change behavior of the impurity, and generating the diffusion starting concentration; S4: using the diffusion starting concentration, calculating the retention change direction between multiple detection points in the boundary area, judging the ion migration delay phenomenon, correcting the behavior deviation parameter of the path segment, adjusting the flow rate rhythm in the current path prediction, and generating a path delay coefficient; S5: calling the path delay coefficient, analyzing the deviation degree of the target feed flow rate and the actual execution flow rate in the feed instruction, calling the current flow characteristics and standard flow state of the feed medium for comparison, adjusting the flow rate control parameter range of the control signal, establishing a feedback relationship between viscosity and execution response deviation, and generating a feed compensation configuration.

Images