Automatic flotation reagent adding control method, device and equipment and storage medium

Abstract

The invention relates to the technical field of mineral processing, and discloses an automatic flotation reagent adding control method, device and equipment and a storage medium. The method comprises the following steps: acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data; constructing a random forest model according to the preprocessed historical grinding and floating data in combination with a process mineralogy theory; and generating a plurality of dosing schemes based on the random forest model, matching the real-time grinding and floating data with the historical grinding and floating data, and determining an optimal dosing scheme of the real-time grinding and floating data. According to the method, modeling is conducted by integrating the historical grinding and floating data of the whole process, multiple dosing schemes are formulated, the real-time grinding and floating data are matched with the historical grinding and floating data, the optimal dosing scheme is determined, automatic and precise dosing of chemicals is achieved, manual intervention is reduced, and the stability of the flotation process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral processing, and in particular to a method, device, equipment and storage medium for automatically dosing a flotation reagent. Background Art

[0002] In flotation production, reagent addition is the main operation that affects the flotation production process. The control of reagent addition directly affects the concentrate grade, recovery rate and other indicators of the flotation process.

[0003] In the prior art, the common reagent control scheme is a control method based on a single parameter (such as pH value). This method cannot fully characterize the complexity of the flotation process, lacks full-process data and key data for grade analysis, is difficult to adapt to complex and changing situations, and has high labor and maintenance costs. Summary of the invention

[0004] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and to provide a flotation reagent automatic dosing control method, device, equipment and storage medium.

[0005] The present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present disclosure provides a method for controlling automatic dosing of a flotation reagent, the method comprising:

[0007] Acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data;

[0008] Constructing a random forest model based on the pre-processed historical grinding and flotation data and combining it with process mineralogy theory;

[0009] A plurality of dosing schemes are generated based on the random forest model, and the real-time grinding and floating data are matched with the historical grinding and floating data to determine the optimal dosing scheme for the real-time grinding and floating data.

[0010] Optionally, the historical grinding and flotation data include at least one of flotation raw concentrate tailings grade, foam image analyzer data, flotation feed flow rate, flotation feed concentration, flotation feed particle size, concentrate flow rate, concentrate concentration, tailings flow rate, tailings flow rate, grinding processing volume, aeration volume, dosage and pH value.

[0011] Optionally, preprocessing the historical friction and floating data to obtain the preprocessed historical friction and floating data includes:

[0012] removing abnormal data from the historical grinding and floating data, and performing time alignment on the historical grinding and floating data after the removal;

[0013] Retain the useful data at the preset time in the aligned historical grinding and floating data, and fill in the missing data in the retained historical grinding and floating data;

[0014] The filled historical friction and floating data are numerically converted to obtain the pre-processed historical friction and floating data.

[0015] Optionally, before constructing the random forest model based on the pre-processed historical grinding and flotation data and combining process mineralogy theory, the method further includes:

[0016] Using data analysis theory and the process mineralogy theory, extracting key features from the pre-processed historical grinding and flotation data;

[0017] Based on the key features, multiple single-feature decision trees are designed.

[0018] Optionally, constructing a random forest model based on the pre-processed historical grinding and flotation data in combination with process mineralogy theory includes:

[0019] Setting training parameters of the random forest model, wherein the training parameters include at least one of the number of the single-feature decision trees, the maximum depth of the single-feature decision trees, and the maximum number of features;

[0020] The training parameters of the random forest model are optimized using a K-fold cross validation method based on the preprocessed historical grinding and floating data to obtain a random forest model under an optimal training parameter combination.

[0021] Optionally, generating multiple dosing schemes based on the random forest model includes:

[0022] Generate multiple initial solutions corresponding to each of the historical friction and floating data based on the random forest model, and send each of the initial solutions to the user terminal;

[0023] Receive multiple medication dosing plans adjusted by the user terminal according to the initial plans.

[0024] Optionally, matching the real-time grinding float data with the historical grinding float data to determine the optimal dosing scheme for the real-time grinding float data includes:

[0025] Matching the real-time friction and floating data with the historical friction and floating data;

[0026] If the match is successful, the dosing scheme of the historical grinding float data that matches the real-time grinding float data is used as the optimal dosing scheme of the real-time grinding float data;

[0027] If the match fails, an exception prompt is generated and sent to the user terminal.

[0028] In a second aspect, an automatic dosing control device for flotation reagent is provided in an embodiment of the present disclosure, and the device comprises:

[0029] A preprocessing module, used for acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data;

[0030] A construction module is used to construct a random forest model based on the pre-processed historical grinding and flotation data and in combination with process mineralogy theory;

[0031] A determination module is used to generate multiple dosing schemes based on the random forest model, match the real-time grinding and floating data with the historical grinding and floating data, and determine the optimal dosing scheme for the real-time grinding and floating data.

[0032] In a third aspect, a computer device is provided in an embodiment of the present disclosure, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the automatic flotation agent dosing control method described in the first aspect when executing the computer program.

[0033] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present disclosure, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the automatic flotation agent dosing control method described in the first aspect are implemented.

[0034] Beneficial effects of this application:

[0035] The embodiment of the present application provides a method for controlling the automatic dosing of flotation reagents, the method comprising: obtaining historical grinding and flotation data, and preprocessing the historical grinding and flotation data to obtain preprocessed historical grinding and flotation data; constructing a random forest model based on the preprocessed historical grinding and flotation data and in combination with process mineralogy theory; generating multiple dosing schemes based on the random forest model, matching the real-time grinding and flotation data with the historical grinding and flotation data, and determining the optimal dosing scheme for the real-time grinding and flotation data. The present application builds a model based on the historical grinding and flotation data of the entire process, formulates multiple dosing schemes, matches the real-time grinding and flotation data with the historical grinding and flotation data, determines the optimal dosing scheme, realizes the automated and precise dosing of reagents, reduces manual intervention, and improves the stability of the flotation process.

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces 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. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work. In each drawing, similar components are numbered similarly.

[0038] Figure 1 A flow chart of an automatic flotation reagent dosing control method provided in an embodiment of the present application is shown;

[0039] Figure 2 One of the single-feature decision trees provided in the embodiment of the present application is shown;

[0040] Figure 3 The second single-feature decision tree provided in the embodiment of the present application is shown;

[0041] Figure 4 The third single-feature decision tree provided in the embodiment of the present application is shown;

[0042] Figure 5 A schematic diagram of the structure of an automatic flotation reagent dosing control device provided in an embodiment of the present application is shown;

[0043] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0045] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may also be a centered element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a centered element at the same time. In contrast, when an element is referred to as being "directly on" another element, there is no intermediate element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0046] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of the template are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0049] Example 1

[0050] like Figure 1 FIG. 1 is a flow chart of a method for controlling the automatic dosing of a flotation reagent in an embodiment of the present application. The method for controlling the automatic dosing of a flotation reagent provided in an embodiment of the present application includes the following steps:

[0051] Step S110, acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data.

[0052] In this embodiment, historical grinding and flotation data of the whole process of grinding and flotation are comprehensively obtained, including but not limited to the following data: flotation tailings grade, foam image analyzer data (including yield, mineralization rate, etc.), flotation feed flow, flotation feed concentration, flotation feed particle size, concentrate flow, concentrate concentration, tailings flow, tailings flow, grinding processing volume, aeration volume, dosage and pH value, etc.

[0053] It should be noted that the sources of the above data may include: sensors on the flotation equipment (such as flow sensors, concentration sensors, particle size analyzers, etc.), foam image analyzers (used to analyze the shape and color of the foam, etc., so as to infer the flotation effect), historical data records in the control system, etc., and the embodiments of the present application are not limited to this.

[0054] In order to ensure high-quality model training in the future, it is necessary to preprocess the historical grinding and floating data, which includes the following steps:

[0055] (1) Identify and remove abnormal data caused by abnormal operating conditions such as equipment failure and shutdown through statistical methods or expert judgment, and obtain the historical friction and floating data after removal;

[0056] (2) Data collection points are distributed throughout the process and have time differences in their mutual influence. Therefore, the approximate delay time should be determined based on the mutual influence of each data collection point in the process, and the removed historical friction and floating data should be time aligned to ensure that the causal relationship is clear and the aligned historical friction and floating data is obtained;

[0057] (3) Retain useful data at preset moments in the aligned historical grinding and flotation data, such as data when key instruments feedback results and data when processes change, to obtain retained historical grinding and flotation data. Changes in processes can be divided into active changes (manual intervention such as changes in processing volume) and passive changes (such as deviations from normal ranges in flotation feed size);

[0058] (4) Filling the missing data in the retained historical grinding and floating data using the average value or other statistical methods to obtain the filled historical grinding and floating data;

[0059] (5) Use methods such as zero-mean normalization to perform numerical conversion on the filled historical grinding and floating data, convert the data into a format suitable for model training, and obtain the preprocessed historical grinding and floating data.

[0060] The above method covers a wide range of grinding and flotation process indicators, from grade, foam image to processing volume and other online parameters, forming a multi-dimensional data view. Abnormal data removal and missing data filling ensure data integrity, and numerical standardization, time alignment and useful data screening are conducive to model digestion and absorption.

[0061] Step S120: constructing a random forest model based on the pre-processed historical grinding and flotation data and in combination with process mineralogy theory.

[0062] Understandably, by using data analysis theory and process mineralogy theory, key features such as grade, froth image, ore processing volume, reagent dosage, etc. are extracted from the pre-processed historical grinding and flotation data.

[0063] Then, based on the key features, multiple single-feature decision trees are designed. The construction of the decision trees is based on the size or range of the key features and the corresponding drug dosage adjustment rules. For example, Figure 2As shown in , it is known that the dosage of reagents is proportional to the ore processing volume. If the ore processing volume increases, the dosage of reagents will increase; if the ore processing volume decreases, the dosage of reagents will decrease; if the ore processing volume remains unchanged, the dosage of reagents will remain unchanged. Figure 3 As shown in the figure, it is known that some copper concentrate grades are sensitive to lime milk. If the copper concentrate grade is qualified, no operation is performed. If the copper concentrate grade is unqualified, it is determined whether the copper concentrate grade is too high. If the copper concentrate grade is too high, the lime milk is reduced. If the copper concentrate grade is too low, the lime milk is increased. Figure 4 As shown, it is known that some concentrate grades are sensitive to collectors. If the concentrate grade is qualified, no operation is performed. If the concentrate grade is unqualified, it is determined whether the copper concentrate grade is too high. If the copper concentrate grade is too high, the collector is reduced. If the concentrate grade is too low, the collector is increased.

[0064] Furthermore, because the random forest in the artificial intelligence algorithm is suitable for various classification and regression tasks, which is similar to the process of on-site process personnel viewing data to make decisions, this model is selected. First, the data set consisting of the complete pre-processed historical grinding and floating data is divided into a training set and a test set. The K-fold Cross Validation method is selected, that is, the data is evenly divided into K parts, one of which is used as a test set in turn, and the rest is used as a training set, and K training and testing are performed. Then, the training parameters of the random forest model are set, and the training parameters include at least one of the number of single-feature decision trees, the maximum depth of the single-feature decision tree, and the maximum number of features.

[0065] It should be noted that in this embodiment, all parameter combination sets will not be traversed for trial, because the number of online instruments is limited and the importance is relatively clear. Therefore, the importance levels are divided according to the importance and number of online instruments, and limited combination calculations are performed, which can effectively reduce the computing power requirements.

[0066] Use the training set to train the random forest model. After each test, record the model's performance indicators, such as accuracy, AUC-ROC, F1 score, etc. Determine the best training parameter combination by comparing the performance indicators under different parameter combinations. Use the test set to evaluate the trained model. The evaluation indicators include accuracy, recall, F1 value, etc. to measure the performance of the model on unseen data. According to the evaluation results, tune the model, including adjusting hyperparameters and optimizing model structure. Repeat the training, evaluation, and optimization process until the model performance meets the requirements, and finally obtain the random forest model under the best training parameter combination.

[0067] Through the above method, a flotation reagent automatic dosing control model based on random forest can be trained. The model can dynamically adjust the dosing plan according to real-time data to improve the flotation effect and reagent utilization rate.

[0068] Step S130, generating multiple dosing schemes based on the random forest model, matching the real-time grinding float data with the historical grinding float data, and determining the optimal dosing scheme for the real-time grinding float data.

[0069] Understandably, based on the random forest model constructed in step S120, multiple initial solutions corresponding to each historical grinding and floating data are generated. In order to ensure that the dosing solution meets both the model prediction results and the actual process requirements, each initial solution is sent to the process personnel at the user end, and the single feature decision tree corresponding to each initial solution is pruned and optimized based on their experience and judgment to determine the final adjusted dosing solution.

[0070] The above method was determined after communication and pruning with process personnel to determine the final dosing plan, rather than completely applying the random forest algorithm. This is also to strengthen the participation of process personnel and to provide communication and confirmation for the implementation of the algorithm.

[0071] Finally, the real-time grinding float data is matched with the historical grinding float data. If the match is successful, the dosing scheme of the historical grinding float data matched with the real-time grinding float data is used as the optimal dosing scheme for the real-time grinding float data. If the match fails, or the execution effect is not good, an abnormal prompt is generated and the abnormality is recorded. The abnormal prompt and abnormal record are sent to the process personnel at the user end to remind the on-site process personnel to intervene manually. If the number of abnormalities exceeds the upper limit threshold, the process personnel are reminded to further analyze the cause.

[0072] Understandably, if the real-time grinding and flotation data can be distinguished, iterative optimization and refinement of the dosing plan are carried out. If the real-time grinding and flotation data cannot be distinguished, the process personnel are required to conduct further offline process mineralogical analysis and make temporary adjustments or even major process modifications based on the results.

[0073] The above method realizes the fully automated and intelligent addition of flotation reagents, reduces manual intervention, and improves the stability of the flotation process. Based on the precise dosing scheme, it reduces reagent waste and reduces production costs.

[0074] In a preferred embodiment, a human-computer interaction interface can also be set up, including a control interface and a monitoring panel. The control interface is used to create a friendly interactive experience and present core data to facilitate quick understanding and action. The monitoring panel is used to display real-time trends to assist in immediate judgment and intervention.

[0075] The automatic dosing control method for flotation reagents provided in the embodiment of the present application obtains historical grinding and flotation data and preprocesses the historical grinding and flotation data to obtain preprocessed historical grinding and flotation data; constructs a random forest model based on the preprocessed historical grinding and flotation data and in combination with process mineralogy theory; generates multiple dosing schemes based on the random forest model, matches the real-time grinding and flotation data with the historical grinding and flotation data, and determines the optimal dosing scheme for the real-time grinding and flotation data. The present application builds a model based on the historical grinding and flotation data of the entire process, formulates multiple dosing schemes, matches the real-time grinding and flotation data with the historical grinding and flotation data, determines the optimal dosing scheme, realizes the automated and precise dosing of reagents, reduces manual intervention, and improves the stability of the flotation process.

[0076] Example 2

[0077] like Figure 5 FIG. 5 is a schematic diagram of a flotation reagent automatic dosing control device 500 in an embodiment of the present application, and the device includes:

[0078] A preprocessing module 510 is used to obtain historical grinding and floating data, and preprocess the historical grinding and floating data to obtain preprocessed historical grinding and floating data;

[0079] A construction module 520 is used to construct a random forest model based on the pre-processed historical grinding and flotation data and in combination with process mineralogy theory;

[0080] The determination module 530 is used to generate multiple dosing schemes based on the random forest model, match the real-time grinding and floating data with the historical grinding and floating data, and determine the optimal dosing scheme for the real-time grinding and floating data.

[0081] The automatic flotation reagent dosing control device provided in the embodiment of the present application is used to build a model based on the historical grinding and flotation data of the entire process, formulate multiple dosing plans, match the real-time grinding and flotation data with the historical grinding and flotation data, determine the optimal dosing plan, realize the automatic and precise dosing of reagents, reduce manual intervention, and improve the stability of the flotation process.

[0082] Example 3

[0083] The present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0084] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 with a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0085] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0086] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D slot compatibility test memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the slot compatibility test method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0087] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other flotation reagent automatic dosing control chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions or process data stored in the memory 61, such as computer-readable instructions for running the slot compatibility test method.

[0088] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0089] The computer device provided in this embodiment can execute the above-mentioned automatic dosing control method for flotation reagents. The automatic dosing control method for flotation reagents here can be the automatic dosing control method for flotation reagents of each of the above-mentioned embodiments.

[0090] Example 4

[0091] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the automatic flotation reagent dosing control method in the embodiment are implemented.

[0092] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, referred to as SMC), a secure digital (Secure Digital, referred to as SD) card, a flash card, etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0093] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow chart, and the combination of boxes in the structure diagram and / or the flow chart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0094] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0095] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0096] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A flotation reagent automatic dosing control method, characterized in that: The method comprises: Acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data; Constructing a random forest model based on the pre-processed historical grinding and flotation data and combining it with process mineralogy theory; A plurality of dosing schemes are generated based on the random forest model, and the real-time grinding and floating data are matched with the historical grinding and floating data to determine the optimal dosing scheme for the real-time grinding and floating data.

2. The automatic dosing control method for flotation reagent according to claim 1 is characterized in that: The historical grinding and flotation data include at least one of the flotation raw concentrate tailings grade, foam image analyzer data, flotation feed flow, flotation feed concentration, flotation feed particle size, concentrate flow, concentrate concentration, tailings flow, tailings flow, grinding processing volume, aeration volume, dosage and pH value.

3. The automatic dosing control method for flotation reagent according to claim 1, characterized in that: The preprocessing of the historical grinding and floating data to obtain the preprocessed historical grinding and floating data includes: removing abnormal data from the historical grinding and floating data, and performing time alignment on the historical grinding and floating data after the removal; Retain the useful data at the preset time in the aligned historical grinding and floating data, and fill in the missing data in the retained historical grinding and floating data; The filled historical friction and floating data are numerically converted to obtain the pre-processed historical friction and floating data.

4. The automatic dosing control method for flotation reagent according to claim 1, characterized in that: Before constructing the random forest model based on the pre-processed historical grinding and flotation data and combining process mineralogy theory, the method further includes: Using data analysis theory and the process mineralogy theory, extracting key features from the pre-processed historical grinding and flotation data; Based on the key features, multiple single-feature decision trees are designed.

5. The automatic dosing control method for flotation reagent according to claim 4, characterized in that: The random forest model is constructed based on the pre-processed historical grinding and flotation data and combined with process mineralogy theory, including: Setting training parameters of the random forest model, wherein the training parameters include at least one of the number of the single-feature decision trees, the maximum depth of the single-feature decision trees, and the maximum number of features; The training parameters of the random forest model are optimized using a K-fold cross validation method based on the preprocessed historical grinding and floating data to obtain a random forest model under an optimal training parameter combination.

6. The automatic flotation reagent dosing control method according to claim 1 is characterized in that: The generating multiple dosing schemes based on the random forest model includes: Generate multiple initial solutions corresponding to each of the historical friction and floating data based on the random forest model, and send each of the initial solutions to the user terminal; Receive multiple medication dosing plans adjusted by the user terminal according to the initial plans.

7. The automatic flotation reagent dosing control method according to claim 6, characterized in that: The matching of the real-time grinding and floating data with the historical grinding and floating data to determine the optimal dosing scheme for the real-time grinding and floating data includes: Matching the real-time friction and floating data with the historical friction and floating data; If the match is successful, the dosing scheme of the historical grinding float data that matches the real-time grinding float data is used as the optimal dosing scheme of the real-time grinding float data; If the match fails, an exception prompt is generated and sent to the user terminal.

8. A flotation reagent automatic dosing control device, characterized in that: The device comprises: A preprocessing module, used for acquiring historical grinding and floating data, and preprocessing the historical grinding and floating data to obtain preprocessed historical grinding and floating data; A construction module is used to construct a random forest model based on the pre-processed historical grinding and flotation data and in combination with process mineralogy theory; A determination module is used to generate multiple dosing schemes based on the random forest model, match the real-time grinding and floating data with the historical grinding and floating data, and determine the optimal dosing scheme for the real-time grinding and floating data.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the automatic dosing control method for flotation reagents according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the automatic flotation reagent dosing control method according to any one of claims 1 to 7 are implemented.

Images