Flotation process quality prediction method, flotation process system, equipment and storage medium

Abstract

The invention provides a flotation process quality prediction method, a flotation process system, equipment and a storage medium, relates to the technical field of flotation processes, and aims to solve the technical problem of poor timeliness of coal slime flotation process quality prediction. Comprising the steps that multiple sets of data sets of the tailing mine slurry in the flotation technology are obtained, each set of data set at least comprises the concentration, the scattering light intensity and the first ash content of the tailing mine slurry, and the first ash content is the real ash content of the tailing mine slurry; constructing a first initial model and a second initial model; wherein the first initial model is used for reflecting a coupling relationship among the concentration of the data set, the scattering light intensity and the first ash content; the second initial model is used for reflecting the relationship between the output result of the first initial model and the first ash content; determining a first model and a second model based on the first initial model and the second initial model; and based on the first model and the second model, determining a second ash content predicted value of the flotation process at the current moment. The method can realize intellectualization of the flotation process of the coal preparation plant.

Description

Technical Field

[0001] The present invention relates to the technical field of flotation technology, and in particular to a flotation quality prediction method, a flotation system, equipment and a storage medium. Background Art

[0002] Coal slime flotation is a key link in coal sorting. With the continuous advancement of instrumentation and computer technology, its degree of automation is gradually improving. However, achieving closed-loop control of the flotation process still faces challenges, especially in terms of the timeliness of flotation product quality prediction, which has become a major obstacle to the intelligent development of coal preparation plants. Summary of the invention

[0003] The purpose of the present invention is to provide a flotation process quality prediction method, a flotation process system, an equipment and a storage medium to solve the technical problems that the quality prediction of coal slime flotation process is poor in timeliness and difficult to realize intelligentization.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a flotation process quality prediction method, comprising:

[0006] Acquire multiple sets of data sets of tailings slurry in a flotation process, each set of the data sets at least including the concentration, scattered light intensity and first ash content of the tailings slurry, wherein the first ash content is the real ash content of the tailings slurry;

[0007] Constructing a first initial model and a second initial model; wherein the first initial model is used to reflect the coupling relationship between the concentration of the data set, the scattered light intensity and the first ash content; and the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content;

[0008] Based on the first initial model and the second initial model, determine a first model and a second model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model;

[0009] Based on the first model and the second model, a second ash content prediction value of the flotation process at the current moment is determined.

[0010] According to at least one embodiment of the present invention, when determining the first model and the second model based on the first initial model and the second initial model, the quality prediction method includes:

[0011] Taking the concentration of the tailing coal slurry and the scattered light intensity as input and the first ash content as output, the first initial model is trained to obtain the first model.

[0012] According to at least one embodiment of the present invention, when determining the first model and the second model based on the first initial model and the second initial model, the quality prediction method further includes:

[0013] The second initial model is trained with the concentration of the tailings slurry and the scattered light intensity as input and the first difference as output to obtain the second model; wherein the first difference is the difference between the first ash content prediction value of the first model and the first ash content.

[0014] According to at least one embodiment of the present invention, after obtaining multiple sets of data sets of tailings slurry in the flotation process, the quality prediction method further includes:

[0015] Normalization processing is performed on each data set in the plurality of data sets; wherein the concentration, the scattered light intensity and the first ash content at the same time after the normalization processing constitute the same set of data.

[0016] According to at least one embodiment of the present invention, the first initial model is a linear regression model; and / or,

[0017] The second initial model is a nonlinear regression model.

[0018] According to at least one embodiment of the present invention, the linear regression model includes one of ridge regression, lasso regression and weighted least squares regression; and / or,

[0019] The nonlinear regression model includes at least one of a random configuration network or a neural network.

[0020] In a second aspect, an embodiment of the present invention provides a flotation process quality prediction device, comprising:

[0021] An acquisition module, used for acquiring multiple sets of data sets of tailings slurry in a flotation process, each set of the data sets at least including the concentration, scattered light intensity and first ash content of the tailings slurry, wherein the first ash content is the real ash content of the tailings slurry;

[0022] A construction module, used to construct a first initial model and a second initial model; wherein the first initial model is used to reflect the coupling relationship between the concentration of the data set, the scattered light intensity and the first ash content; and the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content;

[0023] A processing module, configured to determine a first model and a second model based on the first initial model and the second initial model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model;

[0024] A prediction module is used to determine a second ash content prediction value of the flotation process at a current moment based on the first model and the second model.

[0025] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0026] processor; and,

[0027] A memory for storing programs;

[0028] The program includes instructions, and when the instructions are executed by a processor, the processor executes the method according to the exemplary embodiment of the present invention.

[0029] In a fourth aspect, an embodiment of the present invention provides a flotation process system, comprising a flotation machine, a pipeline, a backscattered light intensity collection device, a concentration meter, and the electronic device described in the third aspect, wherein the flotation machine, the backscattered light intensity collection device, and the concentration meter are respectively connected to the electronic device for communication;

[0030] The pipeline is used to return the tailing coal slurry of the flotation machine to the flotation machine after the backscattered light intensity is collected by the backscattered light intensity collection device.

[0031] In a fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute a method according to an exemplary embodiment of the present invention.

[0032] Among the one or more technical solutions provided in the exemplary embodiments of the present invention, at least one of the following beneficial effects can be achieved.

[0033] The flotation process quality prediction method of the exemplary embodiment of the present invention collects the concentration, scattered light intensity and first ash content of the tailing coal slurry at different times, and forms a set of data sets according to the concentration, scattered light intensity and first ash content at the same time; the first initial model and the second initial model are trained through multiple sets of data sets, thereby respectively determining the first model and the second model, wherein the first model can characterize the coupling relationship between the concentration, scattered light intensity and the first ash content of the tailing coal slurry; and the second model can correct the ash content prediction value of the first model to obtain the final second ash content prediction value. Since the first model and the second model can be stored in an electronic device, and the concentration and heat dissipation light intensity of the tailing coal slurry can be collected in real time during the flotation process, the quality (ash content) of the tailing coal slurry can be accurately predicted by the electronic device in real time, so as to adjust the parameters of the flotation equipment through the accurate quality prediction to ensure that it has the best flotation effect. Based on this, the flotation process quality prediction method of the exemplary embodiment of the present invention can meet the needs of intelligent transformation of the flotation process of the coal preparation plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings illustrate exemplary embodiments of the present invention and together with the description serve to explain the principles of the present invention, and these drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification;

[0035] Figure 1 is a schematic flow chart of a method for predicting flotation process quality according to an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of a flotation process quality model training method according to an embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of a relationship curve between a first ash content, a concentration and a backscattered light intensity according to an embodiment of the present invention;

[0038] Figure 4 is a schematic block diagram of modules of a flotation process quality prediction device according to an embodiment of the present invention;

[0039] Figure 5 is a schematic block diagram of a chip according to an embodiment of the present invention;

[0040] Figure 6 is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] The flotation process quality prediction method provided in the embodiment of the present invention can be executed by a terminal with a display function. The terminal can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a PDA, and a wearable device based on augmented reality (AR) and / or virtual reality (VR) technology.

[0043] The flotation process quality prediction method provided by the exemplary embodiment of the present invention is executed by a terminal or a chip applied in the terminal. The scheme of the present invention is described below with reference to the accompanying drawings.

[0044] Figure 1 FIG. 1 is a flow chart of a method for predicting flotation process quality according to an embodiment of the present invention. Figure 1 As shown, the flotation process quality prediction method of the exemplary embodiment of the present invention comprises the following steps:

[0045] Step 101: obtaining multiple data sets of tailings slurry in a flotation process, each data set at least including concentration, scattered light intensity and a first ash content of the tailings slurry, wherein the first ash content is a real ash content of the tailings slurry.

[0046] The flotation process can be a flotation machine to float coal, or a flotation column to float coal to separate clean coal products and remove tailings. In this flotation process, it is necessary to predict the quality of the tailings slurry online, such as predicting the ash content of the tailings slurry, to guide the adjustment of flotation control parameters and ensure flotation effect and product quality.

[0047] In the related art, the prediction accuracy of ash content detection methods is relatively poor. For example, the ash content detection method based on image processing does not have a mature theoretical model, has many image features, and has poor generalization ability. The present invention directly collects the concentration and scattered light intensity of the tailing coal slurry, and uses the different optical properties of coal and gangue, as well as the coupling relationship between ash content, concentration and scattered light intensity, to predict the ash content of the tailing coal slurry and achieve accurate measurement.

[0048] Figure 2 Schematic diagram of a flotation process quality model training method according to an embodiment of the present invention. Figure 2As shown, the tailings slurry of the flotation machine is led out through a pipeline and circulated back to the flotation machine, and a backscattered light intensity collection device is used to obtain the backscattered light intensity of the tailings slurry irradiated into the tailings slurry pipeline at the current moment, and a concentration meter is used to obtain the concentration of the tailings slurry in the pipeline at the current moment.

[0049] It should be noted that the real ash content in the data set, that is, the first ash content, can be obtained by manually collecting the tailings slurry in the pipeline at the current moment, and then filtering, drying, and manually testing the ash content of the sample to obtain the first ash content of the tailings slurry at the current moment.

[0050] The data collection in the data set can be carried out according to the following steps: the data collection time is 30s and the collection interval is 5min.

[0051] Specifically, after the tailings slurry circulation in the pipeline is stabilized, the computer controls the concentration meter to collect the concentration data of the tailings slurry within 30 seconds, and the backscattered light intensity collection equipment collects the backscattered light intensity data within the same 30 seconds. The first ash content obtained from the tailings slurry within the same 30 seconds is transmitted to the computer and collected again after 5 minutes.

[0052] After obtaining multiple sets of data sets of tailings slurry in the flotation process, it also includes: normalizing each data in the multiple sets of data sets; wherein the concentration, scattered light intensity and first ash content at the same time after normalization constitute the same set of data.

[0053] Specifically, the backscattered light intensity and concentration data in the data set are first screened to remove individual abnormal data; then the normalized data are formed into multiple groups of data, and the training set and test set are composed of a ratio of 8:2.

[0054] The training set is used for training the first initial model and the second initial model, and the test set is used for verifying the training results of the first initial model and the second initial model.

[0055] Step 102: construct a first initial model and a second initial model; wherein the first initial model is used to reflect the coupling relationship between the concentration of the data set, the scattered light intensity and the first ash content; and the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content.

[0056] Figure 3 FIG. 1 is a schematic diagram of a relationship curve between the first ash content, concentration and backscattered light intensity according to an embodiment of the present invention. Figure 3 As shown, the horizontal axis is the concentration of tailings slurry, the vertical axis is the intensity of backscattered light of tailings slurry, and each curve is a curve of different ash content. Figure 3It can be seen that at the same concentration, as the ash content increases, the backscattered light intensity also increases. At the same ash content, as the concentration increases, the backscattered light intensity also increases. Therefore, there is a significant coupling relationship between the concentration, light intensity and ash content of the tailings slurry. According to this coupling relationship, the corresponding ash value can be obtained based on the concentration and light intensity of the tailings slurry. Based on this, the working principle of the ash content of the tailings slurry can be accurately detected.

[0057] It can be seen from the above that the constructed first initial model can be used to reflect the above coupling relationship between the concentration of the data set, the backscattered light intensity and the first ash content.

[0058] In some embodiments, the first initial model is a linear regression model; and the second initial model is a nonlinear regression model.

[0059] Exemplarily, the linear regression model includes one of ridge regression, lasso regression and weighted least squares regression.

[0060] The following description takes ridge regression as an example. Ridge regression, as a linear model, can prevent linear regression from overfitting in the present invention.

[0061] The nonlinear regression model includes at least one of a random configuration network or a neural network.

[0062] Among them, the nonlinear regression model adopts a random configuration network in the present invention to avoid noise and errors generated in the data collection process.

[0063] Step 103: Determine a first model and a second model based on the first initial model and the second initial model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model.

[0064] Exemplarily, with the concentration and scattered light intensity of the tailings slurry as input and the first ash content as output, the first initial model is trained to obtain the first model.

[0065] Exemplarily, the concentration and scattered light intensity of tailings slurry are used as input, and the first difference is used as output to train the second initial model to obtain the second model; wherein the first difference Ash2 is the difference between the first ash content prediction value Ash1 of the first model and the first ash content.

[0066] The prediction effectiveness of the first model and the second model can be guaranteed by training the training set in the above data set and verifying the test set.

[0067] Step 104: Based on the first model and the second model, determine a second ash content prediction value of the flotation process at the current moment.

[0068] After the output of the second model is corrected for the output of the first model, the final prediction value of the tailing ash content can be obtained, thereby ensuring the accuracy of the final prediction model.

[0069] A specific implementation is given below to illustrate how to determine the first model and the second model.

[0070] Exemplarily, the training of the first initial model includes the following steps:

[0071] Given the first initial model training sample (X1, Y1), where X1 = [x1 Τ ,x2 Τ ,…,x N Τ ] Τ ∈R (N×2) , represents the input data backscattered light intensity and concentration, x i =[BS(i),C(i)]∈R 2 ,i=1,2,…,N;Y1=[y1 Τ ,y2 Τ ,…,y N Τ ] Τ ∈R (N×1) , represents the expected output, y i =[Ash0(i)]∈R 1 ,i=1,2,…,N。

[0072] The ridge regression model can be expressed as:

[0073] Y p =Xw+b

[0074] Among them, Y p is the predicted gray value, w is the weight vector, b is the bias term, then the loss function L(w):

[0075] L(w)=‖Y-Xw‖ 2 +α‖w‖,

[0076] Among them, α is the regularization parameter;

[0077] Step 1: Initialize weights w and bias b;

[0078] Step 2: Calculate the predicted value Y p ;

[0079] Step 3: Calculate the loss function L(w);

[0080] Step 4: Update the weight w and bias b using gradient descent;

[0081] Step 5: Repeat steps 2 to 4 until the loss drops to the set value or the maximum number of iterations is reached;

[0082] The first initial model prediction output is Ash1.

[0083] Exemplarily, the training of the second initial model includes the following steps:

[0084] Given the training sample (X2, Y2) of the second initial model,

[0085] Where X2 = [x1 Τ ,x2 Τ ,...,x N Τ ] Τ ∈R (N×2) , represents the input data backscattered light intensity and concentration, x i =[BS(i),C(i)]∈R 2 , i=1,2,...,N;

[0086] Y2=[y1 Τ ,y2 Τ ,...,y N Τ ] Τ ∈R (N×1) , represents the nonlinear expected output;

[0087] y i =[ΔAsh2(i)]∈R 1 ,i=1,2,...,N,

[0088] Among them, ΔAsh2=Ash0-Ash1, Ash0 is the true ash value, and Ash1 is the predicted value of the first model.

[0089] Step 11: Neural Network Initialization:

[0090] Let the initial residual e0 = [y1,y2,…,y N ] Τ , a sufficiently small positive real number ∈, given 1-∈<r<1, where 0<r<1, establish two empty sets W1 and W2 to store the output h of the hidden node L L and supervision mechanism L ;

[0091] Step 12: Neural network random parameter configuration:

[0092] The current number of hidden layer nodes is less than L max And ‖e (L-1) ‖ 2 >∈, a new Lth hidden layer node needs to be added, and the input weight w of the node is randomly generatedL and bias b L , calculate the output h of the hidden node according to the following formula L and supervision mechanism L .

[0093] Where γ=(h L Τ ·h L +1 / C) 2 / (h L Τ ·h L +2 / C), μ L =(1-r) / (L+1),

[0094] C is the regularization coefficient, if ξ L >0, w L and b L Stored in set W1, L Store in W2, otherwise select a larger r value and recalculate. Select the largest ξ in the set W2 L The corresponding input weight w L * and bias b L * .

[0095] h L =[g L (w L Τ x1+b L ),g L (w L Τ x2+b L ),...,g L (w L Τ x N +b L )] Τ ,

[0096]

[0097] Step 13: Calculate output weights;

[0098] Step 14: Calculate the residual;

[0099] Step 15: The result is output Ash2.

[0100] The output of the second model is used to correct the output of the first model to obtain the final predicted value of tail coal ash content Ash, where Ash = Ash1 + Ash2.

[0101] An exemplary embodiment of the present invention also provides a flotation process system, including a flotation machine, a pipeline, a backscattered light intensity collection device, a concentration meter and an electronic device, wherein the flotation machine, the backscattered light intensity collection device and the concentration meter are respectively connected to the electronic device for communication; the pipeline is used to return the tailing coal slurry of the flotation machine to the flotation machine after the backscattered light intensity is collected by the backscattered light intensity collection device.

[0102] Exemplarily, the electronic device may be a computer or a PLC, which stores a program including instructions, which, when executed by a processor, enable the processor to execute the flotation process quality prediction method in the above embodiment.

[0103] In actual applications, in the flotation process system, the tailings pulp after flotation is transferred to the pipeline as a sample for ash content detection. A part of the pipeline is made of transparent material and placed in a black box. The laser light source in the black box penetrates the pipeline to irradiate the tailings pulp. Since the tailings pulp has a certain concentration, it will cause the irradiated light to scatter. The backscattered light intensity collection device also set inside the black box will obtain the intensity of the backscattered light.

[0104] Based on this, the flotation process system is not only environmentally friendly but also produces accurate and fast ash data, and is not easily affected by the environment and moisture and impurities in the tailings slurry.

[0105] In some embodiments, the laser light source may be an 880nm infrared laser light source with a laser power of 10MW. The light emitted by the infrared laser light source is environmentally friendly and safe, and has a wide range of applicable environments and objects.

[0106] Compared with the natural gamma ray method for ash detection, the use of infrared laser light source can overcome the problem that natural gamma rays are only applicable to coal with high content of radioactive elements and are easily affected by the environment; compared with the ash detection of X-ray fluorescence detection method, which is only suitable for elements with higher atomic numbers, the use of infrared laser light source can be applicable to elements with various atomic numbers; compared with the ash detection of dual-energy gamma ray transmission method, which is affected by moisture and impurities, the use of infrared laser light source can avoid the influence of moisture and impurities.

[0107] Furthermore, the exemplary embodiment of the present invention uses an 880mm infrared laser light source to detect only the backscattered light of the tailings slurry irradiated into the transparent container, without considering the transmitted light, and can accurately detect the corresponding ash content of the tailings slurry. For the tailings slurry, since it has poor light transmittance or even no light transmittance, the detection of the light intensity of the backscattered light can avoid the problem of being unable to detect the ash content due to the difficulty of the tailings slurry to transmit light.

[0108] The pipeline of the exemplary embodiment of the present invention is connected to the outside of the black box, and the tailings slurry is continuously transported to the pipeline by a water pump, so that sampling can be performed at intervals according to actual needs to obtain the ash content of the tailings slurry at the current moment, meeting the requirements of online detection of ash content and adapting to the flotation process to adjust corresponding parameters according to the ash content to optimize the flotation effect.

[0109] The pipeline may include a circular main pipe and a branch pipe, wherein the branch pipe is connected in parallel to the main pipe, wherein the tailings slurry is transported along the main pipe by a water pump arranged on the main pipe, and at the same time, when passing through the branch pipe connected in parallel therewith, a portion of the tailings slurry flows through the branch pipe, and a black box for detection is arranged on the branch pipe to detect the ash content of the tailings slurry (collecting backscattered light intensity).

[0110] Exemplarily, there is a certain angle between the backscattered light intensity collection device and the line connecting the light spot irradiated on the tailings coal slurry, and the light emitted by the laser light source, for example, 30° to 60°, optionally 45°. Within this angle range, the intensity of the backscattered light irradiated on the tailings coal slurry is the largest, therefore, the accuracy of light intensity detection can be improved.

[0111] In one embodiment, the backscattered light intensity collection device and the laser light source are at the same position in the axial direction of the branch pipe. For example, when the axial direction of the branch pipe is in the vertical direction, the backscattered light intensity collection device and the laser light source are at the same position in the vertical direction, that is, the line connecting the backscattered light intensity collection device and the light spot irradiated on the tailing coal slurry and the plane formed by the light emitted by the laser light source are parallel to the horizontal plane. At this time, the line connecting the backscattered light intensity collection device and the light spot irradiated on the tailing coal slurry and the light emitted by the laser light source can also have an angle of 45°. This embodiment can minimize the influence of the curvature of the branch pipe on the light to accurately detect the backscattered light intensity.

[0112] Exemplarily, the backscattered light intensity collection device may be a light intensity sensor.

[0113] For example, the diameter of the branch pipe is smaller than the diameter of the main pipe, that is, the main pipe can be a thicker steel pipe than the branch pipe, and the branch pipe can be a thinner quartz glass pipe. The diameter of the branch pipe can be 20 mm to 30 mm, optionally 23 mm, 25 mm, 27 mm, 29 mm, so as to minimize the surface curvature of the circular quartz glass tube that affects the reflection of light. It should be noted that in order to reduce the blocking of light by the quartz glass tube, it should be as thin as possible on the basis of meeting the strength of bearing the pressure of the tailings slurry.

[0114] In actual application, the main pipe is connected to the tailings outlet of the flotation machine, and the tailings slurry in the tailings outlet is transported to the main pipe by a water pump. After passing through the main pipe and the branch pipe, the tailings slurry returns to the tailings outlet of the flotation machine through the main pipe, thus forming a circulation of tailings slurry. This process does not affect the operation of the flotation machine, but after testing the ash content of the tailings frame, since the ash content reflects the yield and recovery rate of the flotation product to a certain extent, it can guide the adjustment of the on-site flotation process parameters, and adjust the process parameters of the flotation machine through the control device, completing the closed-loop control of the flotation process, and overcoming the technical problem of lagging flotation product quality detection.

[0115] The above is an introduction to the scheme provided by the embodiment of the present invention. It is understandable that, in order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0116] The embodiment of the present invention can divide the terminal into functional units according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0117] In the case of dividing each functional module according to each function, an exemplary embodiment of the present invention provides a flotation process quality prediction device. Figure 4 Schematic block diagram of a flotation process quality prediction device according to an embodiment of the present invention. Figure 4 As shown, the flotation process quality prediction device 400 includes:

[0118] An acquisition module 401 is used to acquire multiple sets of data sets of tailings slurry in a flotation process, each set of data sets at least including the concentration, scattered light intensity and first ash content of the tailings slurry, wherein the first ash content is the real ash content of the tailings slurry;

[0119] A construction module 402 is used to construct a first initial model and a second initial model; wherein the first initial model is used to reflect the coupling relationship between the concentration of the data set, the scattered light intensity and the first ash content; and the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content;

[0120] Processing module 403, used to determine the first model and the second model based on the first initial model and the second initial model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model;

[0121] The prediction module 404 is used to determine a second ash content prediction value of the flotation process at the current moment based on the first model and the second model.

[0122] As a possible implementation manner, the processing module 403 is further configured to take the concentration and scattered light intensity of the tailings slurry as input and the first ash content as output, and train the first initial model to obtain the first model.

[0123] As a possible implementation method, the processing module 403 is also used to train the second initial model with the concentration and scattered light intensity of the tailings slurry as input and the first difference as output to obtain a second model; wherein the first difference is the difference between the first ash content prediction value of the first model and the first ash content.

[0124] As a possible implementation manner, the acquisition module 401 is further used to perform normalization processing on each data in the multiple data sets; wherein the concentration, scattered light intensity and first ash content at the same time after the normalization processing constitute the same set of data.

[0125] As a possible implementation, the first initial model is a linear regression model; and / or,

[0126] The second initial model is a nonlinear regression model.

[0127] As a possible implementation, the linear regression model includes one of ridge regression, Lasso regression and weighted least squares regression; and / or,

[0128] The nonlinear regression model includes at least one of a random configuration network or a neural network.

[0129] Figure 5 Schematic block diagram of a chip according to an embodiment of the present invention is shown. Figure 5 As shown, the chip 500 includes one or more (including two) processors 501 and a communication interface 502. The communication interface 502 can support the server to perform the data sending and receiving steps in the above method, and the processor 501 can support the server to perform the data processing steps in the above method.

[0130] Optional, such as Figure 5 As shown, the chip 500 also includes a memory 503, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory (NVRAM).

[0131] In some embodiments, Figure 5 As shown, the processor 501 performs corresponding operations by calling the operation instructions stored in the memory (the operation instructions may be stored in the operating system). The processor 501 controls the processing operations of any one of the terminal devices, and the processor may also be called a central processing unit (CPU). The memory 503 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A portion of the memory 503 may also include NVRAM. For example, in an application, the memory, the communication interface, and the memory are coupled together through a bus system, wherein the bus system may include a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, in Figure 5 Various buses are labeled as bus system 504 .

[0132] The method disclosed in the above embodiment of the present invention can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software.

[0133] The exemplary embodiment of the present invention further provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to enable the electronic device to perform a method according to an embodiment of the present invention when executed by the at least one processor.

[0134] Exemplary embodiments of the present invention also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method according to an embodiment of the present invention.

[0135] refer to Figure 6 , a structural block diagram of an electronic device 600 that can serve as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention.

[0136] like Figure 6As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0137] A plurality of components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, and the input unit 606 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 607 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 may include, but is not limited to, a disk, an optical disk. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0138] like Figure 6 As shown, the computing unit 601 can be various general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the method of the exemplary embodiment of the present invention may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. In some embodiments, the computing unit 601 can be configured to execute the method in any other appropriate manner (e.g., by means of firmware).

[0139] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] It should be understood by those skilled in the art that the above embodiments are only for the purpose of clearly illustrating the present invention, and are not intended to limit the scope of the present invention. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present invention.

Claims

1. A method for predicting flotation process quality, characterized in that: include: Acquire multiple sets of data sets of tailings slurry in a flotation process, each set of the data sets at least including the concentration, scattered light intensity and first ash content of the tailings slurry, wherein the first ash content is the real ash content of the tailings slurry; Constructing a first initial model and a second initial model; wherein the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content; Based on the first initial model and the second initial model, determine a first model and a second model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model; Based on the first model and the second model, a second ash content prediction value of the flotation process at the current moment is determined.

2. The quality prediction method according to claim 1, characterized in that: When the first model and the second model are determined based on the first initial model and the second initial model, the quality prediction method includes: Taking the concentration of the tailing coal slurry and the scattered light intensity as input and the first ash content as output, the first initial model is trained to obtain the first model.

3. The quality prediction method according to claim 2, characterized in that: When determining the first model and the second model based on the first initial model and the second initial model, the quality prediction method further includes: The second initial model is trained with the concentration of the tailings slurry and the scattered light intensity as input and the first difference as output to obtain the second model; wherein the first difference is the difference between the first ash content prediction value of the first model and the first ash content.

4. The quality prediction method according to any one of claims 1 to 3, characterized in that: After obtaining multiple sets of data sets of tailings slurry in the flotation process, the quality prediction method further includes: Normalization processing is performed on each data set in the plurality of data sets; wherein the concentration, the scattered light intensity and the first ash content at the same time after the normalization processing constitute the same set of data.

5. The quality prediction method according to any one of claims 1 to 3, characterized in that: The first initial model is a linear regression model; and / or, The second initial model is a nonlinear regression model.

6. The quality prediction method according to claim 5, characterized in that: The linear regression model includes one of ridge regression, Lasso regression and weighted least squares regression; and / or, The nonlinear regression model includes at least one of a random configuration network or a neural network.

7. A flotation process quality prediction device, characterized in that: include: An acquisition module, used for acquiring multiple sets of data sets of tailings slurry in a flotation process, each set of the data sets at least including the concentration, scattered light intensity and first ash content of the tailings slurry, wherein the first ash content is the real ash content of the tailings slurry; A construction module, used to construct a first initial model and a second initial model; wherein the first initial model is used to reflect the coupling relationship between the concentration of the data set, the scattered light intensity and the first ash content; and the second initial model is used to reflect the relationship between the output result of the first initial model and the first ash content; A processing module, configured to determine a first model and a second model based on the first initial model and the second initial model; wherein the first model is determined by training the first initial model; and the second model is determined by training the second initial model; A prediction module is used to determine a second ash content prediction value of the flotation process at a current moment based on the first model and the second model.

8. An electronic device, characterized in that: include: processor; as well as A memory for storing programs; The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 6.

9. A flotation process system, characterized in that: It comprises a flotation machine, a pipeline, a backscattered light intensity collection device, a concentration meter and the electronic device according to claim 8, wherein the flotation machine, the backscattered light intensity collection device and the concentration meter are respectively connected to the electronic device for communication; The pipeline is used to return the tailing coal slurry of the flotation machine to the flotation machine after the backscattered light intensity is collected by the backscattered light intensity collection device.

10. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

Images