CN113987847B - Method and device for calculating degree of mineralization of flotation foam and electronic equipment - Google Patents
Method and device for calculating degree of mineralization of flotation foam and electronic equipment Download PDFInfo
- Publication number
- CN113987847B CN113987847B CN202111615444.2A CN202111615444A CN113987847B CN 113987847 B CN113987847 B CN 113987847B CN 202111615444 A CN202111615444 A CN 202111615444A CN 113987847 B CN113987847 B CN 113987847B
- Authority
- CN
- China
- Prior art keywords
- foam
- mineralization
- degree
- flotation
- relative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000006260 foam Substances 0.000 title claims abstract description 523
- 230000033558 biomineral tissue development Effects 0.000 title claims abstract description 284
- 238000005188 flotation Methods 0.000 title claims abstract description 192
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims description 141
- 238000003860 storage Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000012512 characterization method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000003491 array Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 16
- 238000010219 correlation analysis Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013178 mathematical model Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009291 froth flotation Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Geometry (AREA)
- Mathematical Analysis (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method and a device for calculating the mineralization degree of flotation froth and electronic equipment, wherein the method comprises the following steps: acquiring a flotation froth image in the flotation process, and determining a froth characteristic parameter based on the flotation froth image; wherein, the foam characteristic parameters at least comprise: foam size, foam area, foam stability, and foam color; inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model, and determining a foam relative mineralization degree value; wherein, the foam relative mineralization degree value is used for representing the flotation foam mineralization degree; and determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval. The method can quantitatively characterize the relative mineralization degree of the foam, reduce the influence of subjective factors of operators and improve the accuracy of results.
Description
Technical Field
The invention relates to the technical field of collaborative calculation of process data, in particular to a method and a device for calculating the degree of mineralization of flotation froth and electronic equipment.
Background
In the process of froth flotation production, one of the skills widely accepted and used is to observe the froth and judge the flotation effect according to the variation of the froth. The state expressed by the foam is usually called as "foam mineralization degree" by the miners, and the foam mineralization degree is defined as the adhesion degree of the mineral particles on the surface of the bubbles, which reflects the quality of the flotation. Currently, the flotation process is usually performed under the optimal condition by experienced flotation operators, and the reasons for the changes are judged by manually observing various changes of the apparent phenomena of the foams, and the flotation process is timely adjusted. Therefore, the existing mode of manual observation is easily influenced by subjective factors of operators, and the accuracy is influenced.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, and an electronic device for calculating a mineralization degree of flotation froth, so as to quantitatively characterize a relative mineralization degree of froth, reduce the influence of subjective factors of operators, and improve accuracy of results.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a method for calculating a degree of mineralization of flotation froth, including: acquiring a flotation froth image in the flotation process, and determining a froth characteristic parameter based on the flotation froth image; wherein, the foam characteristic parameters at least comprise: foam size, foam area, foam stability, and foam color; inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model, and determining a foam relative mineralization degree value; wherein, the foam relative mineralization degree value is used for representing the flotation foam mineralization degree; and determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval.
In one embodiment, the step of inputting the characteristic parameters of the foam into a predetermined model of the relative degree of mineralization of the foam and determining the relative mineralization value of the foam comprises: determining the relative mineralization of the foam according to the following relative mineralization degree modelRMD：
Wherein,Ra matrix of the total coefficients is represented,Wa matrix of foam size coefficients is represented,Sa matrix of the foam size is shown,Ka matrix of foam area coefficients is represented,Aa matrix representing the area of the foam is shown,Qa matrix of foam stability coefficients is represented,Fa foam stability matrix is represented that represents,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant.
In one embodiment, the step of determining the degree of flotation froth mineralization based on the value of the relative degree of froth mineralization and a predetermined evaluation interval for the degree of flotation froth mineralization includes: when the relative degree of mineralization of the foam isRMD 
Determining that the degree of mineralization of flotation froth is very good; when the relative degree of mineralization of the foam isRMD 
Determining that the degree of mineralization of flotation foam is good; when the relative degree of mineralization of the foam isRMD 
Determining that the flotation froth mineralization degree is poor; wherein,
indicates the maximum value of the relative degree of mineralization of the foam,
represents the minimum value of the relative degree of mineralization of the foam,
and
an indicator factor representing the relative degree of mineralization of the foam.
In one embodiment, the step of constructing the model of the relative degree of mineralization of the foam comprises: determining a standard image sample library and a standard characteristic parameter sample library based on a preset historical database; the foam characteristic parameters in the standard characteristic parameter sample library correspond to the standard foam images in the standard image sample library; standardizing the foam characteristic parameters based on the standard characteristic parameters; the standard characteristic parameters are foam characteristic parameters corresponding to samples with a foam relative mineralization degree value of 1 in a standard characteristic parameter sample library; determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by adopting a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library; and determining a foam relative mineralization degree model based on the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix.
In one embodiment, the step of determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by using a boundary constraint algorithm based on the normalized foam characteristic parameters and a standard foam image in a standard image sample library includes: determining the standard foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree in the standard image sample library as a target foam image; determining a target foam characteristic parameter corresponding to the target foam image based on the standard characteristic parameter sample library; and determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter based on the normalized foam characteristic parameters and the target foam characteristic parameters.
In one embodiment, before the step of normalizing the foam characteristic parameter based on the standard characteristic parameter, the method further includes: and denoising the standard foam characteristic parameters in the standard characteristic parameter sample library.
In one embodiment, the construction of the model of the relative degree of mineralization of the foam further comprises: and verifying the accuracy of the foam relative mineralization degree model based on the standard foam characteristic parameters in the standard characteristic parameter sample library.
In a second aspect, an embodiment of the present invention provides a device for calculating a degree of mineralization of flotation froth, including: the parameter acquisition module is used for acquiring a flotation froth image in the flotation process and determining a froth characteristic parameter based on the flotation froth image; wherein, the foam characteristic parameters at least comprise: foam size, foam area, foam stability, and foam color; the foam relative mineralization value determining module is used for inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model and determining a foam relative mineralization degree value; wherein the foam relative mineralization value is used for representing the flotation foam mineralization degree; and the flotation foam mineralization degree determining module is used for determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores computer-executable instructions capable of being executed by the processor, and the processor executes the computer-executable instructions to implement the steps of any one of the methods provided in the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of any one of the methods provided in the first aspect.
The embodiment of the invention has the following beneficial effects:
according to the method, the device and the electronic equipment for calculating the flotation froth mineralization degree, provided by the embodiment of the invention, the flotation froth image in the flotation process can be obtained firstly, and the froth characteristic parameters (froth size, froth area, froth stability and froth color) are determined based on the flotation froth image; then inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model, and determining a foam relative mineralization degree value (used for representing the flotation foam mineralization degree); and finally, determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval. According to the method, the relative mineralization degree of the foam is quantitatively processed, the relative mineralization degree value of the foam is calculated through the relative mineralization degree model of the foam, and the relative mineralization degree model of the foam has good accuracy and generalization capability and strong robustness, so that the relative mineralization degree of the foam can be accurately represented, the influence of subjective factors of operators is reduced, and the accuracy of results is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for calculating a degree of flotation froth mineralization according to an embodiment of the present invention;
FIG. 2 is a block diagram of an embodiment of the present inventionRMDA model test effect graph;
FIG. 3 is a block diagram of an embodiment of the present inventionRMDThe effect graph is used for model online application;
fig. 4 is a schematic structural diagram of a device for calculating the degree of mineralization of flotation froth according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the process of froth flotation production, one of the skills widely accepted and used is to observe the froth and judge the flotation effect according to the variation of the froth. The state expressed by the foam is usually called as "foam mineralization degree" by the miners, and the foam mineralization degree is defined as the adhesion degree of the mineral particles on the surface of the bubbles, which reflects the quality of the flotation. In the flotation process flow, technicians obtain the capability of observing and judging the degree of foam mineralization through operation practice experience. Generally, the raw ore grade is stable, the flotation froth mineralization degree is better, the flotation froth concentrate grade is better, and more reasonable concentrate grade and recovery rate can be obtained by controlling the froth scraping amount, namely the froth flow rate; and when the mineralization degree is poor, the flotation production is represented to be abnormal, and the production stability needs to be realized by adjusting operations such as a medicament and the like.
At present, in the process of flow investigation, technicians in the flotation production field mainly observe the state of foam mineralization through manual naked eyes, judge the flotation production working condition and adjust the production control strategy. However, the degree of foam mineralization is a qualitative concept, an accurate quantitative characterization method is not available, and meanwhile, the degree of mineralization through manual experience is poor in interpretability, so that the control effect of the flotation process is limited, and therefore, the online detection of the degree of foam mineralization needs to be realized.
Based on this, the method, the device and the electronic equipment for calculating the mineralization degree of the flotation froth provided by the embodiment of the invention can quantitatively represent the relative mineralization degree of the froth, reduce the influence of subjective factors of operators and improve the accuracy of results.
To facilitate understanding of the present embodiment, a detailed description is first provided for a method for calculating a degree of flotation froth mineralization, which may be executed by an electronic device, such as a smart phone, a computer, an iPad, etc., and referring to a flowchart of the method for calculating a degree of flotation froth mineralization shown in fig. 1, it is illustrated that the method mainly includes the following steps S101 to S103:
step S101: and acquiring a flotation froth image in the flotation process, and determining a froth characteristic parameter based on the flotation froth image.
Wherein, the foam characteristic parameters at least comprise: foam size, foam area, foam stability, foam color, and foam flow rate. In one embodiment, by carrying out flotation field tracking, observing flotation foam mineralization and carrying out correlation analysis on the extracted foam characteristic parameters, the main correlation variables of the relative mineralization degree of the foam are determined as follows: foam size, foam area, foam stability, foam color, and foam flow rate. Based on the method, a flotation froth image analyzer can be installed on a flotation site, and a flotation froth image and froth characteristic parameters are obtained through the flotation froth image analyzer.
Step S102: inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model, and determining a foam relative mineralization degree value; wherein the foam relative mineralization degree value is used for representing the flotation foam mineralization degree.
In one possible embodiment, the theory of mineralization degree of the flotation process, and the relativity between good and bad mineralization can be used to analyze and narrowly define the relative mineralization degree of foam (degree of foam mineralization) ((C))RMD) "this evaluation index is used for quantitative evaluation of the degree of foam mineralization. Further, according to the correlation analysis of the extracted foam characteristic parameters, the mapping relation between the relative mineralization degree of the foam and the foam characteristic parameters can be determinedfNamely a model of the relative mineralization degree of the foam, specifically:
wherein,Sa matrix of the foam size is shown,Aa matrix representing the area of the foam is shown,Fa foam stability matrix is represented that represents,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant. Therefore, in the embodiment of the invention, the acquired foam characteristic parameters can be input into the foam relative mineralization degree model to obtain the foam relative mineralization degree value.
Step S103: and determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval.
In a possible implementation mode, the relative mineralization degree of the foam can be quantified and normalized to be in a [0,1] interval for the flotation process flow with observable flotation foam by combining the operation experience of field technicians, and specifically, an evaluation interval can be further divided according to the mineralization degree. Based on this, after the foam relative mineralization degree value is obtained through the foam relative mineralization degree model, the foam relative mineralization degree value can be compared with the divided evaluation interval of the flotation foam mineralization degree, that is, the evaluation interval in which the foam relative mineralization degree value falls is determined, so that the flotation foam mineralization degree corresponding to the evaluation interval is determined.
According to the method for calculating the flotation foam mineralization degree, provided by the embodiment of the invention, the relative mineralization degree of foam is subjected to quantitative treatment, and the relative mineralization degree value of foam is calculated through the relative mineralization degree model of foam, so that the relative mineralization degree model of foam has good accuracy and generalization capability and strong robustness, and therefore, the flotation foam mineralization degree can be accurately represented, the influence of subjective factors of operators is reduced, and the accuracy of results is improved.
In one embodiment, when the foam characteristic parameter is input into the predetermined foam relative mineralization degree model to determine the foam relative mineralization value, the following methods can be adopted, but are not limited to: determining the relative mineralization of the foam according to the following relative mineralization degree modelRMD：
Wherein,Ra matrix of the total coefficients is represented,Wa matrix of foam size coefficients is represented,Sa matrix of the foam size is shown,Ka matrix of foam area coefficients is represented,Aa matrix representing the area of the foam is shown,Qa matrix of foam stability coefficients is represented,Fa foam stability matrix is represented that represents,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant.
Further, for flotation process flows where the flotation froth is visually measurable, the relative degree of mineralization of froth can be quantified and normalized to [0, 1%]Interval, however, considering the actual production, the relative degree of mineralization of foam is not 0, so the minimum value of the relative degree of mineralization of foam is defined as
（
) At the same time, the relative mineralization degree of the foam is more than 1,so that the maximum value of the relative degree of mineralization of the foam is defined as
（
). In the flotation process flow, when the relative mineralization degree of the foam reaches a certain state, the flotation process flow needs to be controlled to realize stable production, so that the relative mineralization degree of the foam has a state control limit
And
i.e., an indicator of the relative degree of mineralization of the foam, wherein,
，
. Based on this, the evaluation interval of the flotation foam mineralization degree can be obtained, and specifically comprises the following steps:
i.e. as value of relative degree of mineralization of the foamRMD 
Determining that the degree of mineralization of flotation froth is very good; when the relative degree of mineralization of the foam isRMD 
Determining that the degree of mineralization of flotation foam is good; when the relative degree of mineralization of the foam isRMD 
And determining that the flotation froth mineralization degree is poor.
The embodiment of the invention also provides a construction method of the foam relative mineralization degree model, which mainly comprises the following steps (1) to (4):
step (1): determining a standard image sample library and a standard characteristic parameter sample library based on a preset historical database; and the foam characteristic parameters in the standard characteristic parameter sample library correspond to the standard foam images in the standard image sample library.
Before a model of relative mineralization degree of foam is constructed, the meaning and feasibility of real-time measurement of the flotation foam mineralization degree can be firstly determined by carrying out field tracking and observing the flotation foam mineralization phenomenon, and meanwhile, an evaluation interval of the flotation foam mineralization degree can be analyzed and determined.
Furthermore, a flotation froth image analyzer can be installed on site to obtain a flotation froth image and froth characteristic parameters thereof, including a froth size matrixSFoam area matrixAFoam stability matrixFFoam color feature matrixCMFoam flow rate matrixVAnd the like, establishing a parameter historical database. Furthermore, according to the theoretical knowledge of the mineralization degree of the flotation process, the flotation froth with process representativeness (such as flotation froth with "very good mineralization degree", "poor mineralization degree" and "very poor mineralization degree" determined by skilled technicians) is tracked and generated, and is used as an evaluation standard sample library, the state of each froth characteristic parameter corresponding to the standard sample is recorded, that is, a representative froth image is selected from a historical database to establish a standard image sample library, and the froth characteristic parameter corresponding to the standard froth image is recorded to establish a standard characteristic parameter sample library.
Step (2): and standardizing the foam characteristic parameters based on the standard characteristic parameters.
Considering that the flotation froth is moving at any moment, a great amount of noise exists in the froth characteristic parameters extracted by the flotation froth analyzer, and the data of the froth characteristic parameters need to be preprocessed, namely, the standard froth characteristic parameters in the standard characteristic parameter sample library are denoised. Specifically, the time scale of one minute may be used as a reference, an average value of all data may be obtained as minute data, and noise may be filtered out in the process of obtaining the average value data.
When the foam characteristic parameters are standardized, firstly, a sample with process representativeness in mineralization degree is selected from a standard image sample library, and the relative mineralization degree value of the foam corresponding to the sample is defined as 1 to be used as a standard sample, namelyRMD=1, and obtaining the foam characteristic parameter corresponding to the standard sample from the standard characteristic parameter sample library, using the foam characteristic parameter as the standard characteristic parameter, and then performing relative standardization processing based on the standard characteristic parameter, specifically, for the foam size matrixS：
Wherein,Sis a foam size matrix;S 1the number of the big bubbles;S 2the number of the medium bubbles;S 3the number of the small bubbles;
the number of the standard large bubbles;
the number of bubbles in the standard is shown;
is the standard number of vesicles. Specifically, the large bubbles, the medium bubbles and the small bubbles can be specifically determined according to the pixel size of the bubbles in the bubble image, and the specific division standard can be determined based on the actual flotation process.
For area matrix of foamA：
Wherein,Ais a foam area matrix;A 1the number of the big bubbles;A 2the number of the medium bubbles;A 3the number of the small bubbles;
is the standard large bubble area;
is the standard middle bubble area;
is the standard small bubble area.
For foam stability matrixF：
Wherein,Fis a foam stability matrix;F 1the stability of the large bubbles is achieved;F 2medium bubble stability;F 3for vesicle stability;
standard macrofoam stability;
is standard medium bubble stability;
standard vesicle stability.
For foam color feature matrixCM：
Wherein,CMis a foam color feature matrix;CM His the HSV color space H component;CM Sis the HSV color space S component;CM Vis the HSV color space V component;
HSV color space H component, which is a standard sample;
HSV color space S component, which is a standard sample;
is the HSV color space V component of the standard sample.
And (3): and determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by adopting a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library.
In specific implementation, based on correlation analysis and on-site production tracking, it can be determinedRMDThe mathematical expression of (a) is:
wherein,Rrepresenting a total coefficient matrix;Wa matrix of foam size coefficients is represented,
is the weight coefficient of the number of the big bubbles,
is the weight coefficient of the number of the medium bubbles,
is the weight coefficient of the number of the small bubbles;Ka matrix of foam area coefficients is represented,
is the weight coefficient of the area of the large bubble,
is the mid-bubble area weight coefficient,
is the vesicle area weight coefficient;Qa matrix of foam stability coefficients is represented,
is a large bubble stability weight coefficient,
for the mid-bubble stability weighting factor,
is the vesicle stability weight coefficient;Pa matrix of foam color coefficients is represented,
weighting the H component of HSV color spaceThe coefficients of which are such that,
is the weight coefficient of the S component in the HSV color space,
is the weight coefficient of the V component in the HSV color space.
The coefficient matrix corresponding to each characteristic parameter meets the following expression:
further, when the boundary constraint algorithm is used to determine the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix, the following methods may be used, including but not limited to:
firstly, determining a standard foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree in a standard image sample library as a target foam image; then, determining target foam characteristic parameters corresponding to the target foam images based on the standard characteristic parameter sample library; and finally, determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter based on the standardized foam characteristic parameters and the target foam characteristic parameters.
In a possible implementation mode, a foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree can be selected as a sample, and a coefficient matrix corresponding to each foam characteristic parameter and a total coefficient matrix are determined by adopting a boundary constraint algorithm according to a preset boundary. In particular, for the foam size matrixSCorresponding foam size coefficient matrixWExpanding the foregoing formula yields:
determination by boundary constraints
、
、
. Combining the historical database and the sample database to analyzeWSThe distribution interval of (A) is:
wherein,α、βare respectively asWSThe lower and upper bounds are statistically distributed.
Selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting a foam size matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam size matrix as the foam size matrixT S1Defining correspondence of the bubble imageWSIs composed ofαAnd then:
selecting a foam image with the best flotation foam mineralization degree from a standard image sample library, extracting a foam size matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam size matrix as the foam size matrixT S2Defining correspondence of the bubble imageWSIs composed ofβAnd then:
the following equations are solved:
to obtain
、
、
The respective weight matrices.
For area matrix of foamACorresponding foam area coefficient matrixKExpanding the foregoing formula yields:
determination by boundary constraints
、
、
. Combining historical databases andthe analysis of the sample database can obtainKAThe distribution interval of (A) is:
wherein,ρ、σare respectively asKAThe lower and upper bounds are statistically distributed.
Selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting a foam area matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam area matrix asT A1Defining correspondence of the bubble imageKAIs composed ofρAnd then:
selecting a foam image with the best flotation foam mineralization degree from a standard image sample library, extracting a foam area matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam area matrix asT A2Defining correspondence of the bubble imageKAIs composed ofσAnd then:
the following equations are solved:
to obtain
、
、
The respective weight matrices.
For foam stability matrixFCorresponding foam stability coefficient matrixQExpanding the foregoing formula yields:
determination by boundary constraints
、
、
. Combining the historical database and the sample database to analyzeFQThe distribution interval of (A) is:
wherein,θ、τare respectively asFQThe lower and upper bounds are statistically distributed.
Selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting a foam stability matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam stability matrix asT F1Defining correspondence of the bubble imageFQIs composed ofθAnd then:
selecting a foam image with the best flotation foam mineralization degree from a standard image sample library, extracting a foam stability matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam stability matrix asT F2Define the foamImage correspondenceFQIs composed ofτAnd then:
the following equations are solved:
to obtain
、
、
The respective weight matrices.
For foam color matrixCMCorresponding foam color coefficient matrixPExpanding the foregoing formula yields:
determination by boundary constraints
、
、
. Combining the historical database and the sample database to analyzePCMThe distribution interval of (A) is:
wherein,φ min 、φ max are respectively asPCMThe lower and upper bounds are statistically distributed.
Selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting a foam color matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam color matrix asT CM1Defining correspondence of the bubble imagePCMIs composed ofφ min And then:
selecting a foam image with the best flotation foam mineralization degree from a standard image sample library, extracting a foam color matrix corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam color matrix asT CM2Defining correspondence of the bubble imagePCMIs composed ofφ max And then:
the following equations are solved:
to obtain
、
、
The respective weight matrices.
Further, for the total coefficient matrixRWill beThe RMD formula expansion yields:
further unfolding can result in:
determination by boundary constraints
、
、
、
. Combining the historical database and the sample database to analyzeRMDThe distribution interval of (A) is:
selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting foam characteristic parameters corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam characteristic parameters as foam characteristic parametersT 1Defining correspondence of the bubble imageRMDIs composed of
And then:
selecting a foam image with the worst flotation foam mineralization degree from a standard image sample library, extracting foam characteristic parameters corresponding to the foam image from a standard characteristic parameter sample library, and recording the foam characteristic parameters as foam characteristic parametersT 2Defining correspondence of the bubble imageRMDIs composed of
And then:
selecting the flotation froth mineralization degree from a standard image sample library as a control lower limit
Extracting the foam characteristic parameters corresponding to the foam image from the standard characteristic parameter sample library and recording the foam characteristic parameters as the foam imageT 3Defining correspondence of the bubble imageRMDIs composed of
And then:
the following equations are solved:
to obtain
、
、
、
The respective weight coefficients.
And (4): and determining a foam relative mineralization degree model based on the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix.
In concrete implementation, each coefficient matrix obtained by calculation is substituted intoRMDIn the expression, thereby determiningRMDThe mathematical model expresses the form.
In one embodiment, after obtaining the RMD mathematical model, the exact determination of the model may need to be verified, and in particular implementations, the following may be used, including but not limited to: and verifying the accuracy of the foam relative mineralization degree model based on the standard foam characteristic parameters in the standard characteristic parameter sample library. Specifically, other foam images and corresponding foam characteristic parameters can be selected from the standard image sample library for testing, and the test results are obtainedRMDThe output result of the model is compared with the result determined by the technical personnel based on experience, and the result is verifiedRMDAccuracy of the model, theRMDThe model can well represent the mineralization degree of the flotation froth and has strong robustness.
The method for calculating the flotation foam mineralization degree provided by the embodiment of the invention combines the definition of the foam mineralization degree and the field production experience, and provides a specific quantitative characterization form of important flotation production characteristic parameters, namely the relative mineralization degree of foam, for the first time by using the foam characteristics extracted by machine vision from the perspective of soft measurement, wherein the characteristic parameters have the characteristics of high robustness and strong interpretability, and can be used in the fields of flotation process control, flotation production quality detection and the like. Specifically, firstly, the flotation froth phenomenon is tracked on site, and a relative evaluation interval between good mineralization degree and bad mineralization degree is analyzed and determined; meanwhile, a flotation froth analyzer is used for extracting froth characteristics and is combined with a flotation processThe theory knowledge related to mineralized foam analyzes and determines the parameter related to the mineralized degree of the flotation foam; then, combining the definition of mineralization degree and the relativity between ' good ' and ' bad ', the narrow definition of flotation ' relative mineralization degree of froth (1)RMD) "a quantified characterized form; finally, through evaluation of relative mineralization of the foam and analysis of foam characteristic data, fitting determinesRMDThe mathematical model realizes the soft measurement of the mineralization degree of the key state parameter in the flotation process.
For convenience of understanding, taking copper flotation as an example, the embodiment of the present invention further provides an example of construction and application of a specific model of relative mineralization of froth, which mainly includes the following steps 1 to 8:
step 1: and carrying out field tracking, observing the flotation foam mineralization phenomenon, determining the significance and feasibility of the real-time measurement of the flotation foam mineralization degree, and analyzing and determining the evaluation interval of the flotation foam mineralization degree.
Step 2: and installing a flotation froth image analyzer in a first flotation cell in the roughing operation, acquiring a flotation froth image and froth characteristic parameters thereof, and establishing a parameter historical database.
Specifically, the foam characteristic parameter comprises a foam size matrixSFoam area matrixAFoam stability matrixFFoam color feature matrixCMFoam flow rate matrixVAnd the foam characteristic parameter historical database is shown in table 1.
TABLE 1 foam characteristic parameter History database
And step 3: according to the theoretical knowledge of the mineralization degree of the flotation process and the relativity between good and bad mineralization, the relative mineralization degree of foam is analyzed and narrowly defined (RMD) "this evaluation index is used for quantitative evaluation of the degree of foam mineralization.
Wherein, for the flotation process flow with observable flotation foam, the relative mineralization degree of the foam can be quantified and normalizedTo [0,1]Interval, however, considering the actual production, the relative degree of mineralization of foam is not 0, so the minimum value of the relative degree of mineralization of foam is defined as
（
) At the same time, the relative degree of mineralization of the foam may also exceed 1, so that the maximum value of the relative degree of mineralization of the foam is defined as
（
). In the flotation process flow, when the relative mineralization degree of the foam reaches a certain state, the flotation process flow needs to be controlled to realize stable production, so that the relative mineralization degree of the foam has a state control limit
And
i.e., an indicator of the relative degree of mineralization of the foam, wherein,
，
. Based on this, the evaluation interval of the flotation foam mineralization degree can be obtained, and specifically comprises the following steps:
in the present embodiment, the first and second electrodes are,
，
，
，
。
and 4, step 4: according to the theoretical knowledge of the mineralization degree of the flotation process, tracking and generating, searching flotation foam with process representativeness as an evaluation standard sample library, and recording the states of all foam characteristic parameters corresponding to the standard sample.
In this embodiment, foam images produced continuously for one week may be collected, and then screened, and 4 types of standard samples are selected, which are "worst mineralized", "poor mineralized", "good mineralized", and "very good mineralized", respectively.
And 5: determining a foam characteristic parameter andRMDand determining the corresponding relationship ofRMDIn a characterized form.
The method specifically comprises the following steps 5.1 to 5.3:
step 5.1: and (4) analyzing and preprocessing data.
Because flotation froth is moved at any moment, a great deal of noise exists in froth characteristic parameters extracted by a flotation froth analyzer, and therefore, the data of the froth characteristic parameters need to be preprocessed. Specifically, the minute data may be obtained by averaging all the data on the one-minute time scale. The noise is filtered out during the averaging process.
Step 5.2: and (5) carrying out correlation analysis.
The degree of the existing flotation foam mineralization is only qualitatively expressed, and the embodiment of the invention firstly proposesRMDIn order to realize good quantitative characterization, correlation analysis needs to be carried out on the extracted foam characteristic parameters, and the main correlation variables are determined to be a foam size matrixSArea matrix of foamAFoam color feature matrixCMFoam stability matrixFAnd other constantsX. Specifically, the results of the correlation analysis are shown in table 2.
TABLE 2 correlation analysis
Step 5.3: determiningRMDCharacterizing the form.
Specifically, a mapping relation between the relative mineralization degree of the foam and the characteristic parameters of the foam can be determined according to correlation analysisfAnd satisfies the following conditions:
wherein,Sa matrix of the foam size is shown,Aa matrix representing the area of the foam is shown,Fa foam stability matrix is represented that represents,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant.
Step 6: determiningRMDA mathematical model.
When implemented specifically, can be according toRMDCharacterization format, and data analysis, summary fittingRMDThe mathematical model is obtained by first performing relative normalization processing on the characteristic parameters, and then calculating the coefficient matrix and the total coefficient matrix of each foam characteristic parameter by using a boundary constraint algorithm, which is specifically referred to the construction process of the foam relative mineralization degree model and is not described herein again.
And 7: authenticationRMDThe accuracy of the model.
In specific implementation, other foam images in the standard sample library and corresponding foam characteristic parameters thereof can be selected for testing. In this embodiment, first, a sample library is selected
Finding the corresponding foam characteristic parameter in the foam characteristic database, and recording the parameter as the foam imageT 4Then, then：
Then, willT 4Substitution into𝑅𝑀𝐷Model, calculation result𝑅𝑀𝐷=0.89, andδ 𝑚𝑎𝑥is within the tolerance of the error.
Then, randomly selecting foam images under four working conditions, recording foam characteristic parameters of the foam images, and passing throughRMDThe model was calculated and the results are shown in figure 2 and compared to similar images in the standard library and verified with expert experience. Through comparison of multiple sets of data, verifyRMDThe model has good accuracy and generalization capability, can well represent the mineralization degree of the flotation froth, and has strong robustness.
And 8: will be provided withRMDThe model is packaged and integrated into a computer for online real-time calculation of the flotation foam mineralization degree, when the online verification working condition is linearly changed,RMDwhether the calculation result is accurate or not.
By on-line trackingRMDThe effect of the model on-line application is further determined as shown in FIG. 3RMDThe process effectiveness of the model can provide accurate process guidance when the production working condition changes.
According to the method for calculating the mineralization degree of the flotation froth, provided by the embodiment of the invention, the phenomenon of the flotation froth is tracked on site, and a relative evaluation interval between good and bad mineralization degrees is analyzed and determined; meanwhile, extracting foam characteristics by using a flotation foam analyzer, and analyzing and determining parameters related to the mineralization degree of flotation foam by combining with the theory knowledge related to the mineralization foam in the flotation process; then, combining the definition of mineralization degree and the relativity of 'good' and 'bad', narrowly defining the quantitative characterization form of flotation 'relative mineralization degree of foam'; finally, through evaluation of relative mineralization of the foam and analysis of foam characteristic data, fitting determinesRMDThe mathematical model realizes the soft measurement of the mineralization degree of the key state parameter in the flotation process.
It should be noted that any particular value in all examples shown and described herein should be construed as merely exemplary and not limiting, and thus other examples of exemplary embodiments may have different values.
For the method for calculating the degree of flotation froth mineralization provided in the foregoing embodiment, an embodiment of the present invention further provides a device for calculating the degree of flotation froth mineralization, referring to a schematic structural diagram of a device for calculating the degree of flotation froth mineralization shown in fig. 4, where the device may include the following parts:
the parameter obtaining module 401 is configured to obtain a flotation froth image in a flotation process, and determine a froth characteristic parameter based on the flotation froth image; wherein, the foam characteristic parameters at least comprise: foam size, foam area, foam stability, foam color, and foam flow rate.
The foam relative mineralization value determining module 402 is used for inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model and determining a foam relative mineralization degree value; wherein the foam relative mineralization value is used for characterizing the flotation foam mineralization degree.
And a flotation froth mineralization degree determining module 403, configured to determine the flotation froth mineralization degree based on the relative mineralization degree value of the froth and a predetermined evaluation interval of the flotation froth mineralization degree.
According to the device for calculating the flotation foam mineralization degree, provided by the embodiment of the invention, the relative mineralization degree of foam is subjected to quantitative treatment, and the relative mineralization degree value of foam is calculated through the relative mineralization degree model of foam, so that the relative mineralization degree model of foam has good accuracy and generalization capability and strong robustness, and therefore, the flotation foam mineralization degree can be accurately represented, the influence of subjective factors of operators is reduced, and the accuracy of results is improved.
In one embodiment, the foam relative salinity value determination module 402 is specifically configured to: determining the relative mineralization of the foam according to the following relative mineralization degree modelRMD：
Wherein,Ra matrix of the total coefficients is represented,Wa matrix of foam size coefficients is represented,Sa matrix of the foam size is shown,Ka matrix of foam area coefficients is represented,Aa matrix representing the area of the foam is shown,Qa matrix of foam stability coefficients is represented,Fa foam stability matrix is represented that represents,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant.
In one embodiment, the flotation froth mineralization degree determination module 403 is specifically configured to: when the relative degree of mineralization of the foam isRMD 
Determining that the degree of mineralization of flotation froth is very good; when the relative degree of mineralization of the foam isRMD 
Determining that the degree of mineralization of flotation foam is good; when the relative degree of mineralization of the foam isRMD 
Determining that the flotation froth mineralization degree is poor; wherein,
indicates the maximum value of the relative degree of mineralization of the foam,
represents the minimum value of the relative degree of mineralization of the foam,
and
an indicator factor representing the relative degree of mineralization of the foam.
In one embodiment, the apparatus further comprises a model building module configured to: determining a standard image sample library and a standard characteristic parameter sample library based on a preset historical database; the standard foam characteristic parameters in the standard characteristic parameter sample library correspond to the standard foam images in the standard image sample library; standardizing the foam characteristic parameters based on the standard characteristic parameters; the standard characteristic parameters are foam characteristic parameters corresponding to samples with a foam relative mineralization degree value of 1 in a standard characteristic parameter sample library; determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by adopting a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library; and determining a foam relative mineralization degree model based on the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix.
In an embodiment, the model building module is further specifically configured to: determining the standard foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree in the standard image sample library as a target foam image; determining a target foam characteristic parameter corresponding to the target foam image based on the standard characteristic parameter sample library; and determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter based on the normalized foam characteristic parameters and the target foam characteristic parameters.
In an embodiment, the model building module is further specifically configured to: and denoising the standard foam characteristic parameters in the standard characteristic parameter sample library.
In an embodiment, the model building module is further specifically configured to: and verifying the accuracy of the foam relative mineralization degree model based on the standard foam characteristic parameters in the standard characteristic parameter sample library.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
The embodiment of the invention also provides electronic equipment, which specifically comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the above embodiments.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: the device comprises a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is arranged to execute executable modules, such as computer programs, stored in the memory 51.
The Memory 51 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 52 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The memory 51 is used for storing a program, the processor 50 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 50, or implemented by the processor 50.
The processor 50 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 50. The Processor 50 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the method in combination with the hardware thereof.
The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the foregoing method embodiment, which is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method for calculating the degree of mineralization of flotation froth, comprising:
acquiring a flotation froth image in a flotation process, and determining a froth characteristic parameter based on the flotation froth image; wherein the foam characteristic parameters at least comprise: foam size, foam area, foam stability, and foam color;
inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model, and determining a foam relative mineralization degree value; wherein the relative degree of foam mineralization value is used for characterizing the degree of flotation foam mineralization;
determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval;
the construction step of the foam relative mineralization degree model comprises the following steps: determining a standard image sample library and a standard characteristic parameter sample library based on a preset historical database; wherein the foam characteristic parameters in the standard characteristic parameter sample library correspond to standard foam images in the standard image sample library; standardizing the foam characteristic parameters based on standard characteristic parameters; the standard characteristic parameter is a foam characteristic parameter corresponding to a sample with a foam relative mineralization degree value of 1 in the standard characteristic parameter sample library; determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by adopting a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library; determining the relative mineralization degree model of the foam based on the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix;
the step of determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by using a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library comprises the following steps: determining the standard foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree in the standard image sample library as a target foam image; determining a target foam characteristic parameter corresponding to the target foam image based on the standard characteristic parameter sample library; and determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter based on the normalized foam characteristic parameters and the target foam characteristic parameters.
2. The method of claim 1, wherein the step of inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model to determine a foam relative mineralization degree value comprises:
determining the relative degree of mineralization of the foam according to the following relative degree of mineralization modelRMD：
Wherein,Ra matrix of the total coefficients is represented,Wa matrix of foam size coefficients is represented,Sa matrix of the foam size is shown,Ka matrix of foam area coefficients is represented,Aa matrix representing the area of the foam is shown,Qa matrix of foam stability coefficients is represented,Findicating the moment of foam stabilityThe number of the arrays is determined,Pa matrix of foam color coefficients is represented,CMa matrix of characteristics representing the color of the foam,Xrepresenting a constant.
3. The method of claim 1, wherein the step of determining a degree of flotation froth mineralization based on the value of the degree of froth relative mineralization and a predetermined evaluation interval for the degree of flotation froth mineralization comprises:
when the relative degree of mineralization of the foam is evaluated
Determining that the degree of mineralization of flotation froth is very good;
when the relative degree of mineralization of the foam is evaluated
Determining that the degree of mineralization of flotation foam is good;
when the relative degree of mineralization of the foam is evaluated
Determining that the flotation froth mineralization degree is poor;
wherein,
indicates the maximum value of the relative degree of mineralization of the foam,
represents the minimum value of the relative degree of mineralization of the foam,
and
an indicator factor representing the relative degree of mineralization of the foam.
4. The method of claim 1, wherein the step of normalizing the foam characterization parameter based on the standard characterization parameter is preceded by the step of:
and denoising the standard foam characteristic parameters in the standard characteristic parameter sample library.
5. The method of claim 1, wherein the constructing of the model of the relative degree of mineralization of the foam further comprises:
and verifying the accuracy of the foam relative mineralization degree model based on the standard foam characteristic parameters in the standard characteristic parameter sample library.
6. A flotation froth mineralization degree calculation apparatus, comprising:
the parameter acquisition module is used for acquiring a flotation froth image in the flotation process and determining a froth characteristic parameter based on the flotation froth image; wherein the foam characteristic parameters at least comprise: foam size, foam area, foam stability, and foam color;
the foam relative mineralization degree value determining module is used for inputting the foam characteristic parameters into a predetermined foam relative mineralization degree model and determining a foam relative mineralization degree value; wherein the relative degree of foam mineralization value is used for characterizing the degree of flotation foam mineralization;
the flotation foam mineralization degree determining module is used for determining the flotation foam mineralization degree based on the foam relative mineralization degree value and a predetermined flotation foam mineralization degree evaluation interval;
the apparatus further comprises a model building module configured to: determining a standard image sample library and a standard characteristic parameter sample library based on a preset historical database; wherein the foam characteristic parameters in the standard characteristic parameter sample library correspond to standard foam images in the standard image sample library; standardizing the foam characteristic parameters based on standard characteristic parameters; the standard characteristic parameter is a foam characteristic parameter corresponding to a sample with a foam relative mineralization degree value of 1 in the standard characteristic parameter sample library; determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter by adopting a boundary constraint algorithm based on the standardized foam characteristic parameters and the standard foam images in the standard image sample library; determining the relative mineralization degree model of the foam based on the coefficient matrix corresponding to each foam characteristic parameter and the total coefficient matrix;
the model building module is further specifically configured to: determining the standard foam image with the best flotation foam mineralization degree and the worst flotation foam mineralization degree in the standard image sample library as a target foam image; determining a target foam characteristic parameter corresponding to the target foam image based on the standard characteristic parameter sample library; and determining a coefficient matrix and a total coefficient matrix corresponding to each foam characteristic parameter based on the normalized foam characteristic parameters and the target foam characteristic parameters.
7. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to perform the steps of the method of any of claims 1 to 5.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111615444.2A CN113987847B (en) | 2021-12-28 | 2021-12-28 | Method and device for calculating degree of mineralization of flotation foam and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111615444.2A CN113987847B (en) | 2021-12-28 | 2021-12-28 | Method and device for calculating degree of mineralization of flotation foam and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113987847A CN113987847A (en) | 2022-01-28 |
| CN113987847B true CN113987847B (en) | 2022-04-01 |
Family
ID=79734599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111615444.2A Active CN113987847B (en) | 2021-12-28 | 2021-12-28 | Method and device for calculating degree of mineralization of flotation foam and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113987847B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104634265A (en) * | 2015-02-15 | 2015-05-20 | 中南大学 | Soft measurement method for thickness of mineral floating foam layer based on multivariate image feature fusion |
| CN107377228A (en) * | 2017-08-02 | 2017-11-24 | 太原理工大学 | The method of testing of bubble particles adhesion collision behavior in coal slime flotation |
| CN107817190A (en) * | 2017-10-23 | 2018-03-20 | 中国石油大学(北京) | A kind of foam comprehensive performance evaluation method |
| CN110082375A (en) * | 2019-05-31 | 2019-08-02 | 常州工学院 | A kind of method of quantitatively characterizing plant fiber mineralization degree |
| CN113643298A (en) * | 2021-10-18 | 2021-11-12 | 矿冶科技集团有限公司 | Working condition diagnosis method and device, electronic equipment and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2491134A (en) * | 2011-05-23 | 2012-11-28 | Imp Innovations Ltd | Method and apparatus for froth flotation control for optimising gas recovery |
-
2021
- 2021-12-28 CN CN202111615444.2A patent/CN113987847B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104634265A (en) * | 2015-02-15 | 2015-05-20 | 中南大学 | Soft measurement method for thickness of mineral floating foam layer based on multivariate image feature fusion |
| CN107377228A (en) * | 2017-08-02 | 2017-11-24 | 太原理工大学 | The method of testing of bubble particles adhesion collision behavior in coal slime flotation |
| CN107817190A (en) * | 2017-10-23 | 2018-03-20 | 中国石油大学(北京) | A kind of foam comprehensive performance evaluation method |
| CN110082375A (en) * | 2019-05-31 | 2019-08-02 | 常州工学院 | A kind of method of quantitatively characterizing plant fiber mineralization degree |
| CN113643298A (en) * | 2021-10-18 | 2021-11-12 | 矿冶科技集团有限公司 | Working condition diagnosis method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (6)
| Title |
|---|
| Online monitoring and control of froth flotation systems with machine vision：A review;C. Aldrich等;《International Journal of Mineral Processing》;20100915;第96卷(第1-4期);第1-13页 * |
| Process working condition recognition based on the fusion of morphological and pixel set features of froth for froth flotation;Xiaoli Wang等;《Minerals Engineering》;20181130;第128卷;第17-26页 * |
| Slime coatings in froth flotation：A review;Yuexian Yu等;《Minerals Engineering》;20171231;第114卷;第26-36页 * |
| 基于机器视觉的矿物浮选过程监控技术研究进展;桂卫华等;《自动化学报》;20131130;第39卷(第11期);第1879-1888页 * |
| 基于泡沫图像特征和物元可拓模型的锑浮选工况识别;唐朝晖等;《控制与决策》;20150831;第30卷(第8期);第1485-1490页 * |
| 泡沫图像处理技术在矿物浮选作业中的应用;刘小波;《计算技术与自动化》;20120930;第31卷(第3期);第138-141页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113987847A (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829878B (en) | Method and device for detecting abnormal points of industrial experimental data | |
| CN114861120B (en) | Flotation froth grade calculation method, device, electronic equipment and medium | |
| CN113838480B (en) | Washing machine abnormal sound detection method and device and electronic equipment | |
| CN111177655A (en) | Data processing method and device and electronic equipment | |
| CN117540826A (en) | Optimization method and device of machine learning model, electronic equipment and storage medium | |
| CN111368837B (en) | Image quality evaluation method and device, electronic equipment and storage medium | |
| CN113987847B (en) | Method and device for calculating degree of mineralization of flotation foam and electronic equipment | |
| CN117370871B (en) | Quality analysis method and system for special steel | |
| CN114090556A (en) | Electric power marketing data acquisition method and system | |
| US10846605B2 (en) | Detecting a transient error in a body fluid sample | |
| CN113033639A (en) | Training method of abnormal data detection model, electronic device and storage medium | |
| CN112184415A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110895719A (en) | Authentication device | |
| CN115293735A (en) | Unmanned factory industrial internet platform monitoring management method and system | |
| CN109685458A (en) | A kind of method of quality control and device for environment supervision instrument | |
| Iwata et al. | AI-aided Hammering Test System to Automatically Generate Anomaly Maps. | |
| CN112231194B (en) | Index abnormity root analysis method and device and computer readable storage medium | |
| CN114155412A (en) | Deep learning model iteration method, device, equipment and storage medium | |
| CN112505337B (en) | Data processing method for assisting analysis of sample | |
| CN113239075A (en) | Construction data self-checking method and system | |
| CN112685610A (en) | False registration account identification method and related device | |
| CN117607019B (en) | Intelligent detection method and detection system for electric power fitting surface | |
| CN117078423A (en) | Quantitative transaction strategy testing method and device | |
| CN114971408A (en) | Real-time quality control deviation rectifying method, device, equipment and program product | |
| PATOUILLARD et al. | How to select the life cycle steps to be spatialized? |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |