Copper flotation froth layer thickness prediction method, device and equipment and storage medium

Abstract

The invention discloses a copper flotation froth layer thickness prediction method, device and equipment and a storage medium, and relates to the technical field of production detection in the flotation process. The method comprises the steps that historical flotation parameter data in the historical flotation process and historical data corresponding to foam layer thickness parameters are obtained; performing foam layer thickness correlation analysis on the historical flotation parameter data to obtain target parameters and historical data corresponding to the target parameters; performing regression analysis according to historical data corresponding to the foam layer thickness parameter and historical data corresponding to the target parameter to obtain a sample regression function; and predicting new data corresponding to the thickness parameter of the foam layer according to the new data corresponding to the target parameter and the sample regression function. Therefore, the target parameters related to the thickness parameters of each foam layer are determined, and the statistical relationship between the thickness parameters of the foam layer and the target parameters is fitted to obtain the sample regression function, so that the prediction precision of the thickness of the foam layer is improved based on the method of the sample regression function.

Description

Technical Field

[0001] The present invention relates to the field of flotation process production detection technology, and in particular to a method, device, equipment and storage medium for predicting the thickness of a copper flotation foam layer. Background Art

[0002] The thickness of the flotation foam layer is an important parameter in the flotation process, which directly affects the flotation recovery rate and concentrate grade. Although the existing method of using a float level meter to detect the thickness of the flotation foam layer can adapt to complex measurement environments, its measurement principle determines that there are still errors in its measurement results. Summary of the invention

[0003] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and provide a copper flotation foam layer thickness prediction method, device, equipment and storage medium, which are used to perform regression analysis on the foam layer thickness parameters and target parameters related to the foam layer thickness parameters to obtain a sample regression function, so that the foam layer thickness data can be predicted according to the sample regression function.

[0004] The present invention provides the following technical solutions: In a first aspect, the present invention provides a method for predicting the thickness of a copper flotation foam layer, comprising: Obtain historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; Performing a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter; Perform regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; The new data corresponding to the foam layer thickness parameter is predicted based on the new data corresponding to the target parameter and the sample regression function.

[0005] In one embodiment, performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function includes: Determine a training sample database according to the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter; Establishing a regression equation between the foam layer thickness parameter and the target parameter; The regression equation is subjected to regression analysis according to the distribution states of multiple foam layers and the sample database to obtain the sample regression function.

[0006] In one embodiment, determining the sample database according to the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter includes: Determine a one-dimensional parameter state matrix according to the historical data corresponding to the target parameter; The sample database is determined according to the historical data corresponding to the foam layer thickness parameter and the one-dimensional parameter state matrix.

[0007] In one embodiment, performing regression analysis on the regression equation according to the distribution states of the multiple foam layers and the sample database to obtain the sample regression function includes: Determine a training sample from the sample database according to the distribution state of each foam layer; The regression equation is subjected to regression analysis according to the training samples to obtain the sample regression function.

[0008] In one embodiment, performing regression analysis on the regression equation according to the training sample to obtain the sample regression function includes: Based on the least squares criterion, regression analysis is performed on the regression equation according to the training samples to obtain the sample regression function.

[0009] In one embodiment, after performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function, the method further includes: Based on the coefficient of determination, the accuracy of the sample regression function is checked; If the sample regression function passes the accuracy check, the step of predicting the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function is performed; If the sample regression function fails the accuracy check, the step of obtaining the historical flotation parameter data in the historical flotation process is performed again.

[0010] In one embodiment, the accuracy check of the sample regression function based on the determination coefficient includes: Obtaining a predicted value of the foam layer thickness according to the sample regression function, and obtaining an actual value of the foam layer thickness corresponding to the predicted value; Calculating a determination coefficient based on the predicted value of the foam layer thickness and the actual value of the foam layer thickness; If the determination coefficient is greater than a preset coefficient threshold, the sample regression function passes the accuracy check; If the determination coefficient is less than or equal to the preset coefficient threshold, the sample regression function fails the accuracy check.

[0011] In a second aspect, the present invention provides a copper flotation foam layer thickness prediction device, comprising: An acquisition module, used for acquiring historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; An analysis module, used for performing a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter; A regression module, used for performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; A prediction module is used to predict the new data corresponding to the foam layer thickness parameter according to the new data corresponding to the target parameter and the sample regression function.

[0012] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for predicting the thickness of the copper flotation foam layer as described in the first aspect is implemented.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for predicting the thickness of a copper flotation foam layer as described in the first aspect.

[0014] The copper flotation foam layer thickness prediction method, device, equipment and storage medium disclosed in the present invention obtain historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; perform foam layer thickness correlation analysis on the historical flotation parameter data to obtain the target parameter and the historical data corresponding to the target parameter; perform regression analysis on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; predict the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function. In this way, by performing correlation analysis on the historical flotation parameter data in the historical flotation process to determine the target parameters related to each foam layer thickness parameter, and performing regression analysis on the foam layer thickness parameter and the target parameter to fit the statistical relationship between the foam layer thickness parameter and the target parameter, a sample regression function is obtained, so that the copper flotation foam layer thickness data can be predicted in real time based on the sample regression function, and the method based on the sample regression function improves the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope of protection of the present invention. In each of the drawings, similar components are numbered similarly.

[0016] Figure 1A schematic diagram of a process of predicting the thickness of the copper flotation foam layer proposed in this embodiment is shown; Figure 2 A schematic diagram showing the float liquid level under different foam layer distribution states; Figure 3 Another schematic diagram of the process of predicting the thickness of the copper flotation foam layer proposed in this embodiment is shown; Figure 4 A schematic diagram showing the flotation foam layer thickness fitting effect; Figure 5 A schematic structural diagram of the copper flotation foam layer thickness prediction device proposed in this embodiment is shown.

[0017] Description of the accompanying drawings: 500 - copper flotation foam layer thickness prediction device; 501 - acquisition module; 502 - analysis module; 503 - regression module; 504 - prediction module. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] The components of the embodiments of the present invention generally described and shown in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present invention, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0021] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0022] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present invention belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present invention.

[0023] Example 1 The disclosed embodiment provides a copper flotation foam layer thickness prediction method for performing regression analysis on a foam layer thickness parameter and a target parameter related to the foam layer thickness parameter to obtain a sample regression function, thereby predicting the foam layer thickness data according to the sample regression function.

[0024] See also Figure 1 A method for predicting the thickness of a copper flotation foam layer includes steps S101 to S104, and each step is described in detail below.

[0025] Step S101, obtaining historical flotation parameter data and historical data corresponding to the froth layer thickness parameter in the historical flotation process.

[0026] In this embodiment, historical flotation parameter data such as the ball float level gauge measurement value, the flotation machine inflation volume and the flotation foam image analyzer data in the historical flotation process are obtained. The flotation foam image analyzer data includes flotation foam flow rate, flotation foam size matrix and other data.

[0027] Furthermore, the flotation froth layer phenomenon in the historical flotation process is marked to obtain historical data corresponding to the froth layer thickness parameter, which is used as the basis of sample data later.

[0028] It should be noted that a variety of foam layer distribution states can be determined based on production experience, and the foam layer distribution state space is defined as ,exist: ,in ( ) is the distribution state of each foam layer in the state space. Therefore, when obtaining the historical data corresponding to the foam layer thickness parameter, the foam layer distribution state space is also used. , select the historical data corresponding to the foam layer thickness parameters under each foam layer distribution state in turn.

[0029] The foam layer distribution states include a normal state, a groove state and a sink state.

[0030] Step S102, performing a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter.

[0031] In this embodiment, based on the experience of correlation analysis, it can be known that different foam layer thicknesses result in different distances between the foam and the camera, and the number of foams recognized varies greatly. The foam flow rate also varies greatly with different foam layer thicknesses. The float level meter can detect the height of the slurry level. Therefore, the main parameters related to the foam layer thickness are determined as target parameters, including: the number of large bubbles, the number of medium bubbles, the number of small bubbles, the foam flow rate matrix and the float level meter measurement value.

[0032] The thickness of the foam layer and the foam image under different foam layer distribution conditions and the schematic diagram of the float level gauge are shown in the figure. Figure 2 As shown. It can be seen that under normal foam layer distribution conditions, the foam layer level value error of the float level gauge is small, but under the two special foam layer distribution conditions of sink and groove, the foam layer level value is inaccurate due to the characteristics of the float and foam, so the foam layer thickness measurement value deviates greatly from the actual foam layer thickness. At the same time, the distance between the foam image and the foam layer surface will be different under different foam layer distribution conditions. Therefore, the foam layer thickness value can be analyzed by combining the flotation foam image analyzer data with the float level gauge measurement data.

[0033] Step S103, performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function.

[0034] In this embodiment, regression analysis is performed on historical data corresponding to the foam layer thickness parameter and historical data corresponding to the target parameter to obtain a sample regression function, so that the statistical relationship between the foam layer thickness parameter and the target parameter is described by the sample regression function, and then the foam layer thickness parameter value can be predicted based on the sample regression function according to the target parameter value to achieve real-time monitoring of the copper flotation foam layer thickness. At the same time, the foam layer thickness is predicted based on the statistical relationship between the foam layer thickness parameter and the target parameter related to the foam layer thickness parameter, and the prediction accuracy is higher.

[0035] Step S104: predicting new data corresponding to the foam layer thickness parameter according to the new data corresponding to the target parameter and the sample regression function.

[0036] In this embodiment, new data corresponding to the target parameter in the flotation process for which the foam layer thickness needs to be predicted is obtained, and the new data corresponding to the target parameter is substituted into the sample regression function for prediction to obtain new data corresponding to the foam layer thickness parameter, thereby completing real-time monitoring of the foam layer thickness.

[0037] See also Figure 3 In a specific embodiment, step S103 includes steps S1031 to S1033, and each step is described in detail below.

[0038] Step S1031 : determining a training sample database according to the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter.

[0039] In this embodiment, the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter are used as a training sample database. In the training sample database, the historical foam layer thickness parameter data needs to be associated with a corresponding set of historical target parameter data to ensure data accuracy during regression analysis, thereby improving the accuracy of the sample regression function.

[0040] In a specific embodiment, step S1031 includes: determining a one-dimensional parameter state matrix according to historical data corresponding to the target parameter; and determining the sample database according to the historical data corresponding to the foam layer thickness parameter and the one-dimensional parameter state matrix.

[0041] In this embodiment, if the target parameters include the number of large bubbles, the number of medium bubbles, the number of small bubbles, the foam flow rate, and the measurement parameters of the float level meter, it can be defined as follows: ,in, is a one-dimensional parameter state matrix, Represents the number of large bubbles, Represents the number of bubbles. Represents the number of vesicles, represents the foam flow rate, Represents the measurement parameters of the float level gauge.

[0042] Furthermore, according to the one-dimensional parameter state matrix The historical data corresponding to the foam layer thickness parameters are associated with each other to form a sample database.

[0043] Step S1032, establishing a regression equation between the foam layer thickness parameter and the target parameter.

[0044] In this example, it is assumed that the foam layer thickness parameter and target parameters There is a linear relationship between ,in, is the intercept, is the regression coefficient, The target parameter The non-random parameter factors in is a random error.

[0045] Step S1033: performing regression analysis on the regression equation according to the distribution states of multiple foam layers and the sample database to obtain the sample regression function.

[0046] In this embodiment, the regression equation is regressed using the sample database according to the multiple foam layer distribution states, which can ensure that the foam layer thickness parameters suitable for the special cases of various foam layer distribution states can be fitted. and target parameters The linear relationship between them is improved, thereby improving the prediction accuracy of the copper flotation foam layer thickness.

[0047] In a specific embodiment, step S1033 includes: determining training samples from the sample database according to the distribution states of each foam layer; and performing regression analysis on the regression equation according to the training samples to obtain the sample regression function.

[0048] In this embodiment, training samples in various foam layer states are equally selected from the sample database, and regression analysis is performed on the regression equation using the training samples to obtain a sample regression function.

[0049] Specifically, , , , …, ,get: .make: , , , , and obtain the sample regression function .

[0050] In a specific embodiment, performing regression analysis on the regression equation according to the training samples to obtain the sample regression function includes: performing regression analysis on the regression equation according to the training samples based on a least squares criterion to obtain the sample regression function.

[0051] In this embodiment, the least squares criterion is used to perform regression analysis using the principle of minimizing the estimated residual sum of squares to determine the sample regression function. The least squares method finds the optimal and , which can ensure that the sample regression function is as close to the actual data as possible as a whole, thereby improving the prediction accuracy.

[0052] In a specific embodiment, after step S103, it also includes: based on the determination coefficient, performing accuracy verification on the sample regression function; if the sample regression function passes the accuracy verification, executing the step of predicting the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function; if the sample regression function does not pass the accuracy verification, re-executing the step of obtaining the historical flotation parameter data in the historical flotation process.

[0053] In this embodiment, based on the coefficient of determination, the sample regression function is precision-checked; if the sample regression function passes the precision check, step S104 is executed; if the sample regression function fails the precision check, step S101 is re-executed to re-establish the sample regression function. Among them, the coefficient of determination R² is an important indicator for measuring the fitting effect of the regression model. It indicates that a certain proportion of the variance of the dependent variable can be explained by the independent variable. The value range of R² is between 0 and 1. The closer it is to 1, the better the regression model fits the data; the closer it is to 0, the poorer the regression model fits the data.

[0054] It should be noted that if the sample regression function passes the accuracy verification, a portion of the test data can also be selected for testing to verify the accuracy of the sample regression function.

[0055] In a specific embodiment, the sample regression function is precision-checked based on the determination coefficient, including: obtaining a predicted value of the foam layer thickness according to the sample regression function, and obtaining an actual value of the foam layer thickness corresponding to the predicted value; calculating the determination coefficient according to the predicted value of the foam layer thickness and the actual value of the foam layer thickness; if the determination coefficient is greater than a preset coefficient threshold, the sample regression function passes the precision check; if the determination coefficient is less than or equal to the preset coefficient threshold, the sample regression function fails the precision check.

[0056] In this embodiment, the predicted value of the foam layer thickness is obtained according to the sample regression function, and the actual value of the foam layer thickness corresponding to the predicted value is obtained. The determination coefficient is calculated according to the predicted value of the foam layer thickness and the actual value of the foam layer thickness. The calculation formula is: ,in, represents the predicted value of foam layer thickness, Represents the error between the predicted value of the foam layer thickness and the actual value of the foam layer thickness.

[0057] If the coefficient of determination is greater than the preset coefficient threshold , the sample regression function passes the accuracy check; if the determination coefficient is less than or equal to the preset coefficient threshold , the sample regression function fails the accuracy check.

[0058] See also Figure 4 , under different foam layer distribution conditions, there are obvious differences in the errors between the foam layer thickness measurement value measured by the float level gauge, the model prediction value of the foam layer thickness obtained by the sample regression function and the actual value of the foam layer thickness. Under normal working conditions, the foam layer thickness measurement value, the model prediction value of the foam layer thickness and the actual value of the foam layer thickness are not much different, but under the two special distribution conditions of the sinking tank working condition and the bubbling tank working condition, the foam layer thickness measurement value and the actual value of the foam layer thickness are quite different, while the model prediction value of the foam layer thickness is closer to the actual value of the foam layer thickness.

[0059] The copper flotation foam layer thickness prediction method proposed in this embodiment obtains historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; performs foam layer thickness correlation analysis on the historical flotation parameter data to obtain the target parameter and the historical data corresponding to the target parameter; performs regression analysis on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; and predicts the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function. In this way, the target parameters related to each foam layer thickness parameter are determined by performing correlation analysis on the historical flotation parameter data in the historical flotation process, and regression analysis is performed on the foam layer thickness parameter and the target parameter to fit the statistical relationship between the foam layer thickness parameter and the target parameter to obtain the sample regression function, so that the copper flotation foam layer thickness data can be predicted in real time based on the sample regression function, and the method based on the sample regression function improves the prediction accuracy.

[0060] Example 2 In addition, the present disclosure provides a copper flotation foam layer thickness prediction device 500, see Figure 5 , the device comprises: An acquisition module 501 is used to acquire historical flotation parameter data and historical data corresponding to the froth layer thickness parameter in the historical flotation process; An analysis module 502 is used to perform a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter; A regression module 503 is used to perform regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; The prediction module 504 is used to predict the new data corresponding to the foam layer thickness parameter according to the new data corresponding to the target parameter and the sample regression function.

[0061] Optionally, the regression module 503 is also used to determine a training sample database based on historical data corresponding to the foam layer thickness parameter and historical data corresponding to the target parameter; establish a regression equation between the foam layer thickness parameter and the target parameter; perform regression analysis on the regression equation based on multiple foam layer distribution states and the sample database to obtain the sample regression function.

[0062] Optionally, the regression module 503 is further used to determine a one-dimensional parameter state matrix according to historical data corresponding to the target parameter; and determine the sample database according to the historical data corresponding to the foam layer thickness parameter and the one-dimensional parameter state matrix.

[0063] Optionally, the regression module 503 is further used to determine training samples from the sample database according to the distribution state of each foam layer; and perform regression analysis on the regression equation according to the training samples to obtain the sample regression function.

[0064] Optionally, the regression module 503 is further configured to perform regression analysis on the regression equation according to the training samples based on a least squares criterion to obtain the sample regression function.

[0065] Optionally, the device also includes a verification module for performing accuracy verification on the sample regression function based on the determination coefficient; if the sample regression function passes the accuracy verification, the step of predicting the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function is executed; if the sample regression function fails the accuracy verification, the step of obtaining the historical flotation parameter data in the historical flotation process is re-executed.

[0066] Optionally, the verification module is also used to obtain a predicted value of the foam layer thickness according to the sample regression function, and obtain an actual value of the foam layer thickness corresponding to the predicted value; calculate a determination coefficient according to the predicted value of the foam layer thickness and the actual value of the foam layer thickness; if the determination coefficient is greater than a preset coefficient threshold, the sample regression function passes the accuracy verification; if the determination coefficient is less than or equal to the preset coefficient threshold, the sample regression function fails the accuracy verification.

[0067] The device provided in the embodiment of the present disclosure can execute the steps of the copper flotation foam layer thickness prediction method provided in Example 1, which will not be described again to avoid repetition.

[0068] The copper flotation foam layer thickness prediction device proposed in this embodiment obtains historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; performs foam layer thickness correlation analysis on the historical flotation parameter data to obtain the target parameter and the historical data corresponding to the target parameter; performs regression analysis on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; and predicts the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function. In this way, the target parameters related to each foam layer thickness parameter are determined by performing correlation analysis on the historical flotation parameter data in the historical flotation process, and regression analysis is performed on the foam layer thickness parameter and the target parameter to fit the statistical relationship between the foam layer thickness parameter and the target parameter to obtain the sample regression function, so that the copper flotation foam layer thickness data can be predicted in real time based on the sample regression function, and the method based on the sample regression function improves the prediction accuracy.

[0069] Example 3 In addition, an embodiment of the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for predicting the thickness of the copper flotation foam layer described in Example 1 is implemented.

[0070] The device provided in the embodiment of the present disclosure can execute the steps of the copper flotation foam layer thickness prediction method provided in Example 1, which will not be described again to avoid repetition.

[0071] Example 4 The disclosed embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for predicting the thickness of the copper flotation foam layer described in the embodiment 1 is implemented.

[0072] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0073] The computer-readable storage medium provided in this embodiment can implement the copper flotation foam layer thickness prediction method provided in Example 1, and will not be described again here to avoid repetition.

[0074] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0075] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0076] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for predicting the thickness of a copper flotation foam layer, characterized in that: include: Obtain historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; Performing a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter; Perform regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; The new data corresponding to the foam layer thickness parameter is predicted based on the new data corresponding to the target parameter and the sample regression function.

2. The method for predicting the thickness of the copper flotation foam layer according to claim 1, characterized in that: The performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function includes: Determine a training sample database according to the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter; Establishing a regression equation between the foam layer thickness parameter and the target parameter; The regression equation is subjected to regression analysis according to the distribution states of multiple foam layers and the sample database to obtain the sample regression function.

3. The method for predicting the thickness of the copper flotation foam layer according to claim 2, characterized in that: The determining of the sample database according to the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter comprises: Determine a one-dimensional parameter state matrix according to the historical data corresponding to the target parameter; The sample database is determined according to the historical data corresponding to the foam layer thickness parameter and the one-dimensional parameter state matrix.

4. The method for predicting the thickness of the copper flotation foam layer according to claim 2, characterized in that: The step of performing regression analysis on the regression equation according to the distribution states of the multiple foam layers and the sample database to obtain the sample regression function includes: Determine a training sample from the sample database according to the distribution state of each foam layer; The regression equation is subjected to regression analysis according to the training samples to obtain the sample regression function.

5. The method for predicting the thickness of the copper flotation foam layer according to claim 4, characterized in that: The performing regression analysis on the regression equation according to the training sample to obtain the sample regression function includes: Based on the least squares criterion, regression analysis is performed on the regression equation according to the training samples to obtain the sample regression function.

6. The method for predicting the thickness of the copper flotation foam layer according to claim 1, characterized in that: After performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function, the method further includes: Based on the coefficient of determination, performing accuracy verification on the sample regression function; If the sample regression function passes the accuracy check, the step of predicting the new data corresponding to the foam layer thickness parameter based on the new data corresponding to the target parameter and the sample regression function is performed; If the sample regression function fails the accuracy check, the step of obtaining the historical flotation parameter data in the historical flotation process is performed again.

7. The method for predicting the thickness of the copper flotation foam layer according to claim 6, characterized in that: The step of performing accuracy check on the sample regression function based on the determination coefficient includes: Obtaining a predicted value of the foam layer thickness according to the sample regression function, and obtaining an actual value of the foam layer thickness corresponding to the predicted value; Calculating a determination coefficient based on the predicted value of the foam layer thickness and the actual value of the foam layer thickness; If the determination coefficient is greater than a preset coefficient threshold, the sample regression function passes the accuracy check; If the determination coefficient is less than or equal to the preset coefficient threshold, the sample regression function fails the accuracy check.

8. A copper flotation foam layer thickness prediction device, characterized in that: include: An acquisition module, used for acquiring historical flotation parameter data and historical data corresponding to the foam layer thickness parameter in the historical flotation process; An analysis module, used for performing a froth layer thickness correlation analysis on the historical flotation parameter data to obtain a target parameter and historical data corresponding to the target parameter; A regression module, used for performing regression analysis based on the historical data corresponding to the foam layer thickness parameter and the historical data corresponding to the target parameter to obtain a sample regression function; A prediction module is used to predict the new data corresponding to the foam layer thickness parameter according to the new data corresponding to the target parameter and the sample regression function.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for predicting the thickness of the copper flotation foam layer according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The device stores a computer program, which, when executed by a processor, implements the method for predicting the thickness of the copper flotation foam layer as claimed in any one of claims 1 to 7.

Images