Advanced process control system and method for alumina ore pulp mill

Abstract

The invention relates to the technical field of advanced process control of an aluminum oxide ore pulp mill, in particular to an advanced process control system and method for the aluminum oxide ore pulp mill. The method comprises the following steps: firstly, classifying aluminum oxide raw ores needing to be ground through an aluminum oxide raw ore classification unit to obtain an aluminum oxide raw ore set with a qualified size and an aluminum oxide raw ore set with an unqualified size; secondly, the aluminum oxide raw ore in the aluminum oxide raw ore set with the unqualified size is smashed through a smashing unit; thirdly, a blending liquid control unit is used for obtaining the proportion of blending liquid according to the aluminum oxide raw ore parameters corresponding to the aluminum oxide raw ore set with the qualified size; then, pulp grinding parameters are obtained through a pulp grinding parameter obtaining unit, and the aluminum oxide raw ore set with the qualified size is subjected to pulp grinding through a pulp grinding unit; and after the pulp grinding time is up, the generated aluminum oxide raw ore pulp is detected through the pulp grinding result detection unit. By means of the system, the pulp grinding effect of aluminum oxide raw ore can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of advanced process control for alumina slurry mills, and in particular to an advanced process control system and method for alumina slurry mills. Background Art

[0002] Alumina ore is an important ore mainly used in alumina production. Its chemical composition is mainly composed of alumina, silicate and other impurities. Alumina slurry grinding is the process of refining the coarsely ground alumina ore to the required particle size range by mechanical grinding to produce alumina ore slurry suitable for dissolution and dilution.

[0003] There are many control methods for the alumina slurry grinding process in the prior art. For example, the document ("Improvement of the central transmission double-bin overflow ball mill", "Nonferrous Metal Design", Li Xing, 2015-03-15) combines the fault phenomena that occur in production to improve the ball mill, which can eliminate the main problems that occur in the production process of the ball mill in the alumina plant, ore dressing plant and other industries. The above document only improves the hardware of the ball mill, and cannot optimize the grinding parameters of the ball mill according to the alumina ore, which is not smart enough. For another example, the Chinese patent with publication number CN117138933A proposes an advanced process control system and method for alumina slurry grinding. The method adopts soft instrument technology, calculates the specific gravity of the ore slurry through the soft instrument algorithm of auxiliary variables, and combines the model predictive control algorithm to adjust the input parameters of the mill in real time according to the liquid-solid ratio parameters and optimization targets set by the quality controller. In addition, the Chinese patent with publication number CN111196715B proposes a method for preparing inert alumina chemical fillers using activated alumina ball industrial solid waste and hazardous waste. In this method, the raw materials are placed in a ball mill respectively, and wet ultrafine grinding and other treatments are performed to obtain aluminum sol; zirconium sol is added to the aluminum sol and then dried to obtain the inert alumina chemical filler. The above method does not optimize the amount of regulator added and the slurry grinding parameters in the slurry grinding process in combination with the characteristics of the alumina ore itself, resulting in poor slurry grinding effect.

[0004] Therefore, an advanced process control system and method for alumina slurry grinding is proposed. Summary of the invention

[0005] The object of the present invention is to provide an advanced process control system and method for alumina slurry grinding. First, the present invention classifies the alumina raw ore to be slurried through an alumina raw ore classification unit to obtain a set of alumina raw ore with qualified size and a set of alumina raw ore with unqualified size; secondly, the present invention crushes the alumina raw ore in the set of alumina raw ore with unqualified size through a crushing unit; thirdly, the present invention obtains the ratio of the blending liquid according to the alumina raw ore parameters corresponding to the set of alumina raw ore with qualified size through a blending liquid control unit; then, the present invention obtains the slurry grinding parameters through a slurry grinding parameter obtaining unit and grinds the set of alumina raw ore with qualified size through a slurry grinding unit; after reaching the slurry grinding time, the present invention detects the generated alumina raw ore slurry through a slurry grinding result detection unit.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An advanced process control system for alumina slurry grinding, comprising:

[0008] An alumina raw ore classification unit: used to classify the alumina raw ore to be slurried, and obtain a set of alumina raw ore with qualified size and a set of alumina raw ore with unqualified size.

[0009] Further, the classification of the alumina raw ore to be slurried includes:

[0010] Set the sieve holes of the vibrating screen according to the maximum feed particle size of the ball mill, and the size of the sieve holes is not greater than the maximum feed particle size of the ball mill; screen the alumina raw ore to be slurried through the vibrating screen; divide the alumina raw ore remaining on the vibrating screen into a set of alumina raw ore with unqualified size; divide the alumina raw ore sieved out by the vibrating screen into a set of alumina raw ore with qualified size.

[0011] A crushing unit: used to crush the alumina raw ore in the set of alumina raw ore with unqualified size.

[0012] Further, the crushing process includes:

[0013] Step 1: When the number of alumina raw ore contained in the set of alumina raw ore with unqualified size is less than the set value W, jump to step 5; otherwise, execute step 2;

[0014] Step 2: Select S alumina raw ore from the set of alumina raw ore with unqualified size for hardness detection, S < W, and obtain the surface hardness values of the S alumina raw ore;

[0015] Step 3: Obtain the crushing parameters according to the maximum value of the S surface hardness values and the set maximum feed particle size of the ball mill;

[0016] Step 4: The crushing unit crushes according to the crushing parameters. When the crushing time is reached, the alumina ore that cannot be discharged through the discharge port is divided into a set of alumina ore with unqualified size, and the process goes to step 1;

[0017] Step 5: The crushing unit does not perform crushing.

[0018] Furthermore, the calculation process of the surface hardness value includes:

[0019] A plurality of detection points are uniformly selected on each of the alumina ore; a hardness tester is used to detect the hardness value of each of the detection points; and the hardness values ​​corresponding to the plurality of detection points are averaged to obtain the surface hardness value of each of the alumina ore.

[0020] A mixing liquid control unit is used to obtain the mixing liquid ratio according to the alumina ore parameters corresponding to the set of qualified alumina ores.

[0021] Furthermore, the step of obtaining the proportion of the blending solution according to the alumina ore parameters corresponding to the set of alumina ore with qualified sizes includes:

[0022] The alumina ore parameters include alumina ore size, alumina ore hardness, alumina ore density, alumina ore pH value and alumina ore humidity; the process of obtaining the alumina ore size includes: randomly selecting N alumina ore samples from the set of alumina ore with qualified size; calculating the minimum circumscribed sphere diameters of the N alumina ores, averaging the N minimum circumscribed sphere diameters, and using the calculated result as the alumina ore size;

[0023] The process of obtaining the hardness of the alumina ore is as follows: calculating the hardness of N alumina ores, averaging the hardness of the N alumina ores, and using the calculation result as the hardness of the alumina ore;

[0024] The process of obtaining the density, pH value and humidity of the alumina ore can refer to the process of obtaining the hardness of the alumina ore;

[0025] The alumina ore parameters are input into a mixing liquid proportioning model to obtain the proportion of the mixing liquid.

[0026] Furthermore, the mixing liquid ratio model is constructed based on a deep belief network, and the mixing liquid ratio model adaptively adjusts the learning rate according to the model loss during the training process; the training process of the mixing liquid ratio model includes:

[0027] Collecting a historical alumina raw ore blending liquid ratio data set; the historical alumina raw ore blending liquid ratio data set includes a plurality of historical alumina blending liquid ratio data; the historical alumina blending liquid ratio data includes alumina raw ore parameters and their corresponding standard blending liquid ratios;

[0028] The historical alumina ore blending liquid ratio data set is divided into a training set and a test set; the learning rate in the blending liquid ratio model is initialized; the alumina ore parameters in the training set are used as input, and the blending liquid ratio prediction result is used as output; the blending loss function value of the blending liquid ratio model is calculated, and the expression of the blending loss function is:

[0029]

[0030] Among them, ss t is represented by the value of the blending loss function at the tth iteration; M is represented by the number of historical alumina blending liquid ratio data in the training set; N is represented by the number of additive types contained in the blending liquid; pb (i,j,t) It is expressed as the proportion of the jth additive in the predicted result of the mixing liquid ratio corresponding to the i-th historical alumina mixing liquid ratio data output by the model after the t-th iteration; and bzb (i,j) It is expressed as the proportion of the jth additive in the standard mixing solution ratio corresponding to the i-th historical alumina mixing solution ratio data; and exp() represents an exponential function with a natural constant as the base;

[0031] When the value of the mixing loss function converges, the training ends and the learning rate in the mixing liquid ratio model is output; otherwise, the learning rate is adjusted according to the mixing loss function and the training continues until the value of the mixing loss function converges; the formula for adjusting the learning rate according to the mixing loss function is:

[0032]

[0033] Among them, xxl t It represents the learning rate after the tth iteration; β1 represents the set increment value, β1>0; β2 represents the set decrement value, β2>0; ss t Expressed as the allocation loss function value of the tth iteration; It is represented by the set loss reduction threshold; the test set is used to test the mixing liquid ratio model.

[0034] Slurry grinding parameter acquisition unit: used to obtain slurry grinding parameters according to the characteristic parameters of alumina.

[0035] Further, obtaining the pulp grinding parameters according to the characteristic parameters of alumina includes:

[0036] The alumina characteristic parameters include the alumina ore parameters, the target particle diameter of the alumina ore and the addition rate of the alumina ore; the slurry milling parameters include the ball mill parameters and the mixing liquid addition rate; the ball mill parameters include the speed of the ball mill, the motor power and the slurry milling time; the mixing liquid addition rate is obtained according to the alumina ore addition rate; the process of obtaining the ball mill parameters includes:

[0037] Collecting a historical alumina slurry grinding data set, wherein the historical alumina slurry grinding data set includes Q historical alumina characteristic parameters and corresponding historical ball mill parameter standard values;

[0038] The historical alumina characteristic parameters include historical alumina ore parameters, historical alumina ore target particle diameter and historical alumina ore addition rate;

[0039] Clustering the Q historical alumina characteristic parameters to obtain P clusters; using the data in the P clusters to train a ball mill slurry grinding parameter prediction model to obtain P trained ball mill slurry grinding parameter prediction models;

[0040] Calculate the distance between the characteristic parameters of aluminum oxide and the centers of P clusters, and select the cluster with the closest distance as the prediction cluster; input the characteristic parameters of aluminum oxide into the trained ball mill slurry grinding parameter prediction model corresponding to the prediction cluster to obtain the ball mill parameters corresponding to the characteristic parameters of aluminum oxide;

[0041] The training process of the ball mill slurry grinding parameter prediction model includes: randomly initializing the weight and bias of the ball mill slurry grinding parameter prediction model;

[0042] The historical alumina characteristic parameters in the cluster are input into the ball mill slurry grinding parameter prediction model to obtain the historical ball mill parameter prediction value; the ball mill loss function value in the ball mill slurry grinding parameter prediction model is calculated, and the calculation formula is:

[0043]

[0044] Among them, csyc t It is represented by the ball mill loss function value after the tth iteration in the ball mill grinding parameter prediction model training process; m is represented by the number of data items contained in the cluster; qmcs (e,d,t) It is represented by the dth historical ball mill parameter prediction value corresponding to the eth historical alumina characteristic parameter output by the ball mill slurry grinding parameter prediction model at the tth iteration; bzcs (e,d)It is represented by the dth historical ball mill parameter standard value corresponding to the eth historical alumina characteristic parameter; d=1 corresponds to the speed of the ball mill; d=2 corresponds to the motor power of the ball mill; d=3 corresponds to the slurry grinding time of the ball mill;

[0045] When the ball mill loss function value converges, the training ends and the weight and bias of the ball mill slurry grinding parameter prediction model are output; otherwise, the training continues until the ball mill loss function value converges.

[0046] Pulp grinding unit: used for pulp grinding the alumina ore set of qualified size according to the pulp grinding parameters.

[0047] Pulp grinding result detection unit: used to detect the generated alumina raw ore slurry after reaching the pulp grinding time.

[0048] Furthermore, the pulping result detection unit comprises:

[0049] Randomly select M liters of the alumina raw slurry as the raw slurry test sample;

[0050] Obtaining a first weight of solid particles in the raw ore slurry whose particle diameter is greater than the set target particle diameter of the alumina raw ore; and simultaneously obtaining a second weight of all solid particles in the raw ore slurry;

[0051] Calculate the ratio of the first weight to the second weight; when the ratio is greater than the set ratio, output an unqualified pulp grinding warning; otherwise, obtain the alumina ore slurry and corresponding parameters, and re-train the mixing liquid proportioning model and the ball mill pulp grinding parameter prediction model.

[0052] Furthermore, the retraining of the mixing liquid ratio model and the ball mill slurry grinding parameter prediction model includes: obtaining corresponding parameters in the slurry grinding process; the corresponding parameters include alumina ore parameters, alumina characteristic parameters, mixing liquid ratio and slurry grinding parameters;

[0053] The proportion of the prepared liquid is used as the standard prepared liquid proportion corresponding to the parameters of the alumina ore;

[0054] The alumina ore parameters and the corresponding standard blending solution ratio are added to the historical alumina ore blending solution ratio data set, and the blending solution ratio model is trained again;

[0055] The alumina characteristic parameters and the ball mill parameters in the slurry grinding parameters are added to the historical alumina slurry grinding data set, and the ball mill slurry grinding parameter prediction model is trained again.

[0056] An advanced process control method for alumina slurry grinding, characterized by comprising:

[0057] Classify the alumina raw ore to be ground by slurry, and obtain a set of alumina raw ore with qualified size and a set of alumina raw ore with unqualified size; crush the alumina raw ore in the set of alumina raw ore with unqualified size. The specific process includes:

[0058] Step 1: When the number of alumina raw ore contained in the set of alumina raw ore with unqualified size is less than the set value W, jump to Step 5; otherwise, execute Step 2;

[0059] Step 2: Select S alumina raw ore from the set of alumina raw ore with unqualified size for hardness detection, S < W, and obtain the surface hardness values of the S alumina raw ore;

[0060] Step 3: Obtain the crushing parameters according to the maximum value of the S surface hardness values and the maximum feed particle size of the set ball mill;

[0061] Step 4: The crushing unit crushes according to the crushing parameters. When the crushing time is reached, the alumina raw ore that fails to be discharged through the discharge port is classified into the set of alumina raw ore with unqualified size, and jump to Step 1;

[0062] Step 5: The crushing unit does not perform crushing;

[0063] Obtain the ratio of the blending liquid according to the alumina raw ore parameters corresponding to the set of alumina raw ore with qualified size;

[0064] Obtain the slurry grinding parameters according to the alumina characteristic parameters; the alumina characteristic parameters include the alumina raw ore parameters, the target particle diameter of the alumina raw ore, and the addition rate of the alumina raw ore; perform slurry grinding on the set of alumina raw ore with qualified size according to the slurry grinding parameters; detect the generated alumina raw ore slurry after the slurry grinding time is reached.

[0065] Compared with the prior art, the beneficial effects of the present invention are:

[0066] 1. During the crushing process of the alumina raw ore in the present invention, first, the hardness values at multiple points on the surface of the alumina raw ore are averaged to obtain the surface hardness value of the alumina raw ore. The present invention sets different crushing parameters according to the surface hardness value to crush the alumina raw ore. This method can better represent the hardness level of the overall sample by measuring the hardness at multiple points and taking the average value, reducing errors caused by local non-uniformity; at the same time, obtaining the crushing parameters of the crusher according to the maximum value of the surface hardness value and the maximum feed particle size of the set ball mill can enable the crusher to accurately crush the large-sized alumina raw ore, thereby improving the slurry grinding effect in the subsequent slurry grinding process.

[0067] 2. The present invention constructs a mixing liquid ratio model, which uses historical alumina ore mixing liquid ratio data for training, takes alumina ore parameters as input, and mixing liquid ratio as output, and uses the error between the mixing liquid ratio output in each iteration and the standard mixing liquid ratio as the loss function value of the mixing liquid ratio model, and dynamically adjusts the learning rate according to the change of the loss function. This model can avoid rapid overfitting caused by too large a learning rate or slow training speed caused by too small a learning rate. The present invention uses a trained mixing liquid ratio model to obtain the mixing liquid ratio. This method can combine the various characteristics of the alumina ore to accurately obtain the mixing liquid ratio, thereby improving the slurry grinding effect of the alumina ore.

[0068] 3. The present invention obtains a historical alumina slurry grinding data set, clusters the historical alumina characteristic parameters in the historical alumina slurry grinding data set, and obtains multiple clustering clusters. The present invention constructs a ball mill slurry grinding parameter prediction model, and uses the historical alumina slurry grinding data in different clusters to obtain multiple trained ball mill slurry grinding parameter prediction models. During the training process, the error between the historical ball mill parameter prediction value output in each iteration and the corresponding historical slurry grinding parameter standard value is used as the loss function value to optimize the weight and bias of the model. The present invention selects the corresponding trained ball mill slurry grinding parameter prediction model according to the distance between the alumina characteristic parameters and different clusters to obtain the ball mill parameters corresponding to the alumina characteristic parameters. This method can train specific models for different clusters, and can more accurately capture the alumina slurry grinding data patterns and changes in these specific clusters. Therefore, targeted prediction of the ball mill slurry grinding parameters of each cluster can significantly improve the prediction accuracy of the ball mill parameters, thereby improving the slurry grinding effect of the alumina ore. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the structure of an advanced process control system for an alumina slurry mill provided by an embodiment of the present invention;

[0070] Figure 2 A schematic flow chart of an advanced process control method for alumina slurry grinding provided by an embodiment of the present invention;

[0071] Figure 3 A schematic diagram of a crushing process of a crushing unit provided in an embodiment of the present invention;

[0072] Figure 4 A schematic diagram of a pulping parameter acquisition process provided by an embodiment of the present invention;

[0073] Figure 5 A schematic flow chart of a pulp mill advanced process control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] Alumina ore is an important ore mainly used for alumina production. Its chemical composition is mainly composed of alumina, silicate and other impurities. Alumina ore needs to undergo a series of processing to obtain alumina. Alumina slurry grinding is the process of refining the coarsely ground alumina ore to the required particle size range by mechanical grinding. This process is usually used in the aluminum smelting industry to produce alumina ore slurry suitable for dissolution and dilution.

[0076] The present invention provides an advanced process control system for an alumina slurry mill. The system is applied to an advanced process control method for an alumina slurry mill. For specific system structure diagrams and method flow charts, refer to Figure 1 and Figure 2 .

[0077] Embodiment 1

[0078] Reference Figure 1 The alumina ore classification unit is applied to S10 of an alumina slurry mill advanced process control method.

[0079] Furthermore, the classification of the alumina ore that needs to be slurry-milled in the alumina processing plant A includes:

[0080] The mesh holes of the vibrating screen are set according to the maximum feed particle size of the ball mill, and the size of the mesh holes is not larger than the maximum feed particle size of the ball mill; in this embodiment, the maximum feed particle size of the ball mill is 40 mm, and the size of the mesh holes is set to 40 mm; the alumina ore to be slurry-milled is screened through the vibrating screen; the alumina ore remaining on the vibrating screen is divided into a set of alumina ores with unqualified sizes; the alumina ore screened out by the vibrating screen is divided into a set of alumina ores with qualified sizes.

[0081] Since the ball mill cannot perform pulp grinding on oversized alumina ore, it is necessary to screen the alumina ore according to size. In this embodiment, this step screens the alumina ore according to its size, and divides the large-sized alumina ore into a set of unqualified alumina. This method can facilitate the subsequent processing of alumina ores of different sizes.

[0082] Reference Figure 1The crushing unit is applied to S20 of an advanced process control method for alumina ore pulp grinding.

[0083] Further, referring to Figure 3 , the crushing process includes:

[0084] Step 1: When the number of alumina raw ores contained in the set of alumina raw ores with unqualified size is less than the set value W, jump to Step 5; otherwise, execute Step 2;

[0085] Step 2: Select S alumina raw ores from the set of alumina raw ores with unqualified size for hardness detection, where S < W, and obtain the surface hardness values of the S alumina raw ores;

[0086] The calculation process of the surface hardness value includes:

[0087] Uniformly select multiple detection points on each alumina raw ore; use a hardness tester to detect the hardness values of each detection point; average the hardness values corresponding to the multiple detection points to obtain the surface hardness value of each alumina raw ore.

[0088] In this embodiment, during the crushing process of the alumina raw ore, first average the hardness values of multiple points on the surface of the alumina raw ore to obtain the surface hardness value of the alumina raw ore. This method can better represent the hardness level of the overall sample and reduce errors caused by local non-uniformity by measuring the hardness at multiple points and taking the average.

[0089] Step 3: Obtain the crushing parameters of the crusher according to the maximum value of the S surface hardness values and the maximum feed particle size of the ball mill set; the crushing parameters include the discharge port size, motor power, and crushing time of the crusher; the discharge port size is equal to the maximum feed particle size of the ball mill;

[0090] Step 4: The crushing unit crushes according to the crushing parameters. When the crushing time is reached, divide the alumina raw ores that fail to be discharged through the discharge port into the set of alumina raw ores with unqualified size, and jump to Step 1;

[0091] Step 5: The crushing unit does not perform crushing.

[0092] Further, Step 4 also includes: dividing the alumina raw ores discharged through the discharge port into the set of alumina raw ores with qualified size.

[0093] In this step of the present embodiment, different crushing parameters are set according to the surface hardness value to crush the alumina ore. At the same time, the crushing parameters of the crusher are obtained according to the maximum value of the surface hardness value and the set maximum feed particle size of the ball mill, and the alumina ore whose size is still unqualified after crushing is repeatedly crushed. This method enables the crusher to accurately crush the alumina ore of large size, thereby improving the slurry grinding effect in the subsequent slurry grinding process.

[0094] Reference Figure 1 The mixing liquid control unit is applied to S30 of an advanced process control method for alumina slurry mill.

[0095] Furthermore, after the pulverizing unit stops pulverizing, the mixing liquid control unit obtains the mixing liquid ratio according to the alumina ore parameters corresponding to the set of alumina ore with qualified sizes, and the specific steps include:

[0096] The alumina ore parameters include alumina ore size, alumina ore hardness, alumina ore density, alumina ore pH value and alumina ore humidity;

[0097] The process of obtaining the size of the alumina ore comprises: randomly selecting N alumina ore samples from the set of alumina ore with qualified size; calculating the minimum circumscribed sphere diameters of the N alumina ores, averaging the N minimum circumscribed sphere diameters, and using the calculated result as the size of the alumina ore;

[0098] The process of obtaining the hardness of the alumina ore is as follows: calculating the hardness of N alumina ores, averaging the hardness of the N alumina ores, and using the calculation result as the hardness of the alumina ore;

[0099] The process of obtaining the density, pH value and humidity of the alumina ore can refer to the process of obtaining the hardness of the alumina ore; the alumina ore parameters are input into the mixing liquid proportioning model to obtain the proportion of the mixing liquid.

[0100] In this step of the present embodiment, various parameters of the alumina ore are obtained by random sampling, including the size of the alumina ore, the hardness of the alumina ore, the density of the alumina ore, the pH value of the alumina ore, and the humidity of the alumina ore. This method can ensure that the extracted alumina ore is consistent with the overall statistical characteristics, and this method obtains various parameters of the alumina ore, providing a data basis for the subsequent prediction of the mixing liquid ratio and the prediction of the pulp mill parameters.

[0101] Furthermore, in the process of alumina ore slurry grinding, the mixing liquid (also called grinding agent) plays a vital role, which can affect the effect of ore grinding and the efficiency of the process. The mixing liquid is a mixture of water, lime and caustic soda. The mixing liquid ratio model is constructed based on a deep belief network, and the mixing liquid ratio model adaptively adjusts the learning rate according to the model loss during the training process; the training process of the mixing liquid ratio model includes: collecting the historical alumina ore mixing liquid ratio data set of alumina processing plant A, and the historical alumina ore mixing liquid ratio data set includes 450 historical alumina mixing liquid ratio data; the historical alumina mixing liquid ratio data includes alumina ore parameters and its corresponding standard mixing liquid ratio;

[0102] The historical alumina raw ore blending liquid ratio data set is divided into a training set and a test set; the number of data items contained in the training set is 315, and the number of data items contained in the test set is 135;

[0103] Initializing parameters in the mixing liquid ratio model; the parameters include learning rate, batch size, number of hidden layers and number of neurons in each hidden layer;

[0104] The parameters of the alumina ore in the training set are used as input, and the predicted result of the mixing liquid ratio is used as output; the mixing loss function value of the mixing liquid ratio model is calculated, and the expression of the mixing loss function is:

[0105]

[0106] Among them, ss t is represented by the value of the blending loss function at the tth iteration; M is represented by the number of historical alumina blending liquid ratio data in the training set; N is represented by the number of additive types contained in the blending liquid; pb (i,j,t) It is expressed as the proportion of the jth additive in the predicted result of the mixing liquid ratio corresponding to the i-th historical alumina mixing liquid ratio data output by the model after the t-th iteration; and bzb (i,j) It is expressed as the proportion of the jth additive in the standard mixing solution ratio corresponding to the i-th historical alumina mixing solution ratio data; and exp() is expressed as an exponential function with a natural constant as the base; when the ratio of the prepared liquid output by the model is exactly the same as the ratio of the standard prepared liquid, ss t =1;ss t The larger it is, the worse the prediction effect of the model.

[0107] In this embodiment, the step obtains the mixing loss function value of each iteration according to the difference between the mixing liquid ratio output by the mixing liquid ratio model and the standard mixing liquid ratio. The mixing loss function value can measure the prediction effect of the mixing liquid ratio model and provide a data basis for the subsequent learning rate adjustment of the mixing liquid ratio model.

[0108] Further, when the value of the mixing loss function converges, the training ends and the learning rate in the mixing liquid ratio model is output; otherwise, the learning rate is adjusted according to the mixing loss function, and the training continues until the value of the mixing loss function converges; the formula for adjusting the learning rate according to the mixing loss function is:

[0109]

[0110] Among them, xxl t It represents the learning rate after the tth iteration; β1 represents the set increment value, β1>0; β2 represents the set decrement value, β2>0; ss t Expressed as the allocation loss function value of the tth iteration; It is represented by the set loss reduction threshold; the test set is used to test the mixing liquid ratio model.

[0111] Furthermore, in order to verify the effectiveness of the mixing liquid ratio model in this embodiment, this embodiment also adopts four other models for comparison. The comparison results are shown in Table 1.

[0112] Table 1 Comparison of the predicted effects of the mixing ratio model of Example 1

[0113] Model Model 1 Model 2 Model 3 Model 4 Mean square error 0.021 0.043 0.064 0.069 Mean absolute error 0.046 0.096 0.106 0.132 Root mean square error 0.032 0.084 0.095 0.121 Mean absolute percentage error 0.072％ 0.167％ 0.194％ 0.249％

[0114] Furthermore, model 1 in Table 1 is the mixing liquid ratio model proposed by the present invention, model 2 is trained with a fixed learning rate based on model 1, model 3 is trained with an absolute value loss function based on model 1, and model 4 is trained with a traditional deep belief network. It can be seen from Table 1 that the mixing liquid ratio model proposed in this embodiment is superior to the other three models in all indicators.

[0115] This step of the present embodiment constructs a mixing liquid ratio model, which uses historical alumina ore mixing liquid ratio data for training, takes alumina ore parameters as input, and mixing liquid ratio as output, and uses the error between the mixing liquid ratio output in each iteration and the standard mixing liquid ratio as the loss function value of the mixing liquid ratio model, and dynamically adjusts the learning rate according to the change of the mixing loss function. This model can avoid rapid overfitting caused by too large a learning rate or slow training speed caused by too small a learning rate. The present invention uses a trained mixing liquid ratio model to obtain the mixing liquid ratio. This method can combine the various characteristics of the alumina ore to accurately obtain the mixing liquid ratio, thereby improving the slurry grinding effect of the alumina ore.

[0116] Reference Figure 1 A pulp mill parameter acquisition unit is provided, wherein the pulp mill parameter acquisition unit is applied to S40 of an advanced process control method for alumina pulp mill.

[0117] Further, refer to Figure 4 , the obtaining of pulp grinding parameters according to the characteristic parameters of alumina includes:

[0118] The alumina characteristic parameters include the alumina ore parameters, the target particle diameter of the alumina ore and the alumina ore addition rate; the slurry grinding parameters include the ball mill parameters and the formulation liquid addition rate; the ball mill parameters include the speed of the ball mill, the motor power and the slurry grinding time; the formulation liquid addition rate is obtained according to the alumina ore addition rate; the ball mill model and size data selected by the alumina processing factory A in this embodiment refer to Table 2.

[0119] Table 2 Ball mill models and dimensions selected by Alumina Processing Plant A

[0120] model Cylinder diameter Cylinder length Motor Model Effective volume Processing power Maximum feed size YQg2436 2400mm 3600mm JR137-6 <![CDATA[13.8m 3 ]]> 8~110t / h 40mm

[0121] Furthermore, the process of obtaining the parameters of the ball mill includes:

[0122] Collecting a historical alumina slurry grinding data set, wherein the historical alumina slurry grinding data set includes 450 historical alumina characteristic parameters and corresponding historical ball mill parameter standard values;

[0123] Cluster the 450 historical alumina characteristic parameters to obtain P clusters, each cluster containing at least k historical alumina characteristic parameters, k is a set value to ensure that the model training data is sufficient; in this embodiment, k is set to 50; construct a ball mill slurry grinding parameter prediction model based on a multi-layer perceptron; use the data in the P clusters to train the ball mill slurry grinding parameter prediction model to obtain P trained ball mill slurry grinding parameter prediction models; calculate the distance between the alumina characteristic parameters and the centers of the P clusters, and select the cluster with the closest distance as the prediction cluster; input the alumina characteristic parameters into the trained ball mill slurry grinding parameter prediction model corresponding to the prediction cluster to obtain the ball mill parameters corresponding to the alumina characteristic parameters.

[0124] The training process of the ball mill slurry grinding parameter prediction model includes:

[0125] Randomly initializing the weights and biases of the ball mill slurry grinding parameter prediction model;

[0126] The historical alumina characteristic parameters in the cluster are input into the ball mill slurry grinding parameter prediction model to obtain the historical ball mill parameter prediction value; the ball mill loss function value in the ball mill slurry grinding parameter prediction model is calculated, and the calculation formula is:

[0127]

[0128] Among them, csyc t It is represented by the ball mill loss function value after the tth iteration in the ball mill grinding parameter prediction model training process; m is represented by the number of data items contained in the cluster; qmcs (e,d,t) It is represented by the dth historical ball mill parameter prediction value corresponding to the eth historical alumina characteristic parameter output by the ball mill slurry grinding parameter prediction model at the tth iteration; bzcs (e,d) It is expressed as the dth historical ball mill parameter standard value corresponding to the eth historical alumina characteristic parameter; d=1 corresponds to the rotation speed of the ball mill; d=2 corresponds to the motor power of the ball mill; d=3 corresponds to the slurry grinding time of the ball mill.

[0129] In this embodiment, the step obtains the ball mill loss function value of each iteration based on the difference between the various ball mill parameters output by the model and the historical ball mill parameter standard values. The ball mill loss function value can measure the prediction effect of the ball mill slurry grinding parameter prediction model and provide a data basis for the parameter adjustment of the subsequent ball mill slurry grinding parameter prediction model.

[0130] Furthermore, when the ball mill loss function value converges, the training ends and the weight and bias of the ball mill slurry grinding parameter prediction model are output; otherwise, the training continues until the ball mill loss function value converges.

[0131] Furthermore, this embodiment selects 10 different aluminum oxide characteristic parameters, obtains the prediction cluster corresponding to each aluminum oxide characteristic parameter, and obtains the ball mill parameters according to the corresponding trained ball mill slurry grinding parameter prediction model. In order to verify the effectiveness of this method in this embodiment, this embodiment also selects three other methods to predict the ball mill parameters, and selects the ball mill loss function value in this embodiment as the error index to verify the effectiveness of the ball mill parameter prediction method proposed in this embodiment. For specific results, refer to Table 3.

[0132] Table 3 Example 1 Ball mill parameter prediction results

[0133] Alumina characteristic parameter serial number Method 1 Method 2 Method 3 Method 4 1 0.046 0.086 0.116 0.119 2 0.057 0.089 0.114 0.121 3 0.048 0.082 0.107 0.116 4 0.051 0.094 0.108 0.117 5 0.049 0.090 0.110 0.118 6 0.055 0.086 0.112 0.116 7 0.037 0.090 0.114 0.118 8 0.042 0.085 0.113 0.120 9 0.038 0.093 0.109 0.123 10 0.047 0.091 0.112 0.119

[0134] Furthermore, the method 1 in Table 3 is the method proposed in this embodiment, including clustering the characteristic parameters of aluminum oxide first and then selecting the corresponding trained ball mill slurry grinding parameter prediction model for prediction; the method 2 is based on the method 1, using the mean absolute error as the loss function to train the ball mill slurry grinding parameter prediction model; the prediction process of the method 3 includes not clustering the characteristic parameters of aluminum oxide, but directly using the historical aluminum oxide slurry grinding data set to train a ball mill slurry grinding parameter prediction model, and inputting the ball mill slurry grinding parameters into the same ball mill slurry grinding parameter prediction model for prediction; the method 4 is based on the method 3, replacing the ball mill slurry grinding parameter prediction model with a traditional multi-layer perceptron for prediction. It can be seen from Table 3 that the method proposed in this embodiment can effectively improve the accuracy of slurry grinding parameter prediction.

[0135] This step of the present embodiment obtains a historical alumina slurry grinding data set, clusters the historical alumina characteristic parameters in the historical alumina slurry grinding data set, and obtains multiple clustering clusters. The present invention constructs a ball mill slurry grinding parameter prediction model based on a multi-layer perceptron, and uses historical alumina slurry grinding data in different clusters to obtain multiple trained ball mill slurry grinding parameter prediction models. During the training process, the error between the historical ball mill parameter prediction value obtained in each iteration and the corresponding historical slurry grinding parameter standard value is used as the ball mill loss function value to optimize the weight and bias of the model. The present invention selects the corresponding trained ball mill slurry grinding parameter prediction model according to the distance between the alumina characteristic parameters and different clusters to obtain the ball mill parameters corresponding to the alumina characteristic parameters. This method can train specific models for different clusters, and can more accurately capture the data patterns and changes of these specific clusters. Therefore, targeted prediction of the ball mill slurry grinding parameters of each cluster can significantly improve the prediction accuracy of the ball mill parameters, thereby improving the slurry grinding effect of the alumina ore.

[0136] Reference Figure 1The pulp grinding unit and the pulp grinding result detection unit are applied to S50 and S60 of an advanced process control method for alumina pulp grinding.

[0137] Furthermore, the pulping result detection unit comprises:

[0138] Randomly select M liters of the alumina ore pulp as the ore pulp test sample; obtain the first weight of solid particles in the ore pulp whose particle diameter is greater than the set alumina ore target particle diameter; simultaneously obtain the second weight of all solid particles in the ore pulp; calculate the proportion of the first weight in the second weight; when the proportion is greater than the set ratio, output a slurry grinding failure warning; otherwise, obtain the alumina ore pulp and corresponding parameters, and retrain the mixing liquid ratio model and the ball mill slurry grinding parameter prediction model. The alumina ore pulp is then graded, and solid particles with a particle diameter greater than the set alumina ore target particle diameter are screened out to obtain an alumina ore pulp suitable for dissolution and dilution operations.

[0139] In this embodiment, the step detects the alumina ore slurry generated after slurry grinding, calculates the weight ratio of particles whose diameters do not reach the target particle diameter, and issues an early warning when the ratio is too large. This method can reflect abnormal conditions in the alumina ore slurry process in real time, helping production managers to discover and solve potential problems in a timely manner.

[0140] Furthermore, the retraining of the mixing liquid ratio model and the ball mill slurry grinding parameter prediction model includes: obtaining corresponding parameters in the slurry grinding process; the corresponding parameters include alumina ore parameters, alumina characteristic parameters, mixing liquid ratio and slurry grinding parameters;

[0141] The proportion of the prepared liquid is used as the standard prepared liquid proportion corresponding to the parameters of the alumina ore;

[0142] The alumina ore parameters and the corresponding standard blending solution ratio are added to the historical alumina ore blending solution ratio data set, and the blending solution ratio model is trained again;

[0143] The alumina characteristic parameters and the ball mill parameters in the slurry grinding parameters are added to the data corresponding to the prediction cluster in the historical alumina slurry grinding data set, and the ball mill slurry grinding parameter prediction model corresponding to the prediction cluster is trained again.

[0144] After the output of the pulp mill is qualified, the corresponding parameters in the pulp milling process are obtained, and the mixing liquid ratio model and the ball mill pulp mill parameter prediction model are retrained. This method can expand the training data of the two models, thereby helping the models to better learn features, thereby improving the accuracy of model prediction.

[0145] This embodiment obtains a pulp mill advanced process control system flow chart of an alumina slurry mill advanced process control system according to the above steps. Figure 5 . In this embodiment, the alumina ore is input into the alumina ore control unit for classification, and a set of alumina ore with qualified size and a set of alumina ore with unqualified size are obtained; the set of alumina ore with unqualified size is input into the crushing unit for crushing, and the alumina ore with qualified size is classified into the set of alumina ore with qualified size; then, the alumina ore parameters are obtained according to the set of alumina ore with qualified size, and the mixing liquid control unit is controlled according to the alumina ore parameters to obtain the ratio of the mixing liquid and generate the mixing liquid; at the same time, the alumina characteristic parameters are obtained, and the slurry grinding parameters of the ball mill are obtained through the slurry grinding parameter acquisition unit; then, the mixing liquid and the alumina ore in the set of alumina ore with qualified size are input into the slurry grinding unit, and the ball mill is controlled by the slurry grinding parameters for slurry grinding; and the alumina ore slurry output from the ball mill is input into the slurry grinding result detection unit for detection.

[0146] Embodiment 2

[0147] Reference Figure 1 The alumina ore classification unit is applied to S10 of an alumina slurry mill advanced process control method.

[0148] Furthermore, the classification of the alumina ore that needs to be slurry-milled in the alumina processing plant B includes:

[0149] The mesh holes of the vibrating screen are set according to the maximum feed particle size of the ball mill, and the size of the mesh holes is not larger than the maximum feed particle size of the ball mill; in this embodiment, the maximum feed particle size of the ball mill is 35 mm, and the size of the mesh holes is set to 35 mm; the alumina ore that needs to be slurry-milled is screened through the vibrating screen; the alumina ore remaining on the vibrating screen is divided into a set of alumina ores with unqualified sizes; the alumina ore screened out by the vibrating screen is divided into a set of alumina ores with qualified sizes.

[0150] Reference Figure 1 A pulverizing unit is used in an S20 of an advanced process control method for an alumina slurry mill.

[0151] Further, the crushing process includes:

[0152] Step 1: When the number of alumina ores contained in the set of unqualified alumina ores is less than the set value W, jump to step 5; otherwise, execute step 2.

[0153] Step 2: Select S alumina raw ores from the set of alumina raw ores with unqualified size, where S < W, and perform hardness testing on these S alumina raw ores to obtain the surface hardness values of the S alumina raw ores;

[0154] The calculation process of the surface hardness value includes:

[0155] Uniformly select multiple detection points on each of the alumina raw ores; use a hardness tester to detect the hardness values of each of the detection points; average the hardness values corresponding to the multiple detection points to obtain the surface hardness value of each alumina raw ore.

[0156] Step 3: Obtain the crushing parameters according to the maximum value of the S surface hardness values and the set maximum feed particle size of the ball mill. The crushing parameters include the discharge port size, motor power, and crushing time;

[0157] Step 4: The crushing unit performs crushing according to the crushing parameters. When the crushing time is reached, classify the alumina raw ores that fail to be discharged through the discharge port into the set of alumina raw ores with unqualified size, and jump to Step 1;

[0158] Step 5: The crushing unit does not perform crushing.

[0159] Refer to Figure 1 the dispensing liquid control unit in, and the dispensing liquid control unit is applied to S30 of an advanced process control method for an alumina ore mill.

[0160] Further, the obtaining of the ratio of the dispensing liquid according to the alumina raw ore parameters corresponding to the set of alumina raw ores with qualified size includes: the alumina raw ore parameters include the alumina raw ore size, alumina raw ore hardness, alumina raw ore density, alumina raw ore pH value, and alumina raw ore humidity; the obtaining process of the alumina raw ore size includes: randomly select N alumina raw ore samples from the set of alumina raw ores with qualified size;

[0161] Calculate the minimum circumscribed sphere diameter of the N alumina raw ores, average the N minimum circumscribed sphere diameters, and use the calculation result as the alumina raw ore size;

[0162] The obtaining process of the alumina raw ore hardness is:

[0163] Calculate the hardness of the N alumina raw ores, average the hardness of the N alumina raw ores, and use the calculation result as the alumina raw ore hardness; the obtaining processes of the alumina raw ore density, alumina raw ore pH value, and alumina raw ore humidity can refer to the obtaining process of the alumina raw ore hardness; input the alumina raw ore parameters into the dispensing liquid ratio model to obtain the ratio of the dispensing liquid.

[0164] Furthermore, the mixing liquid ratio model is constructed based on a deep belief network, and the mixing liquid ratio model adaptively adjusts the learning rate according to the model loss during the training process; the training process of the mixing liquid ratio model includes:

[0165] Collecting a historical alumina raw ore mixing solution ratio data set of alumina processing plant B, wherein the historical alumina raw ore mixing solution ratio data set includes 500 pieces of historical alumina mixing solution ratio data; the historical alumina mixing solution ratio data includes alumina raw ore parameters and their corresponding standard mixing solution ratios;

[0166] The historical alumina raw ore blending liquid ratio data set is divided into a training set and a test set; the number of data items contained in the training set is 350, and the number of data items contained in the test set is 150;

[0167] Initializing parameters in the mixing liquid ratio model; the parameters include learning rate, batch size, number of hidden layers and number of neurons in each hidden layer;

[0168] The parameters of the alumina ore in the training set are used as input, and the predicted result of the mixing liquid ratio is used as output; the mixing loss function value of the mixing liquid ratio model is calculated, and the expression of the mixing loss function is:

[0169]

[0170] Among them, ss t is represented by the value of the blending loss function at the tth iteration; M is represented by the number of historical alumina blending liquid ratio data in the training set; N is represented by the number of additive types contained in the blending liquid; pb (i,j,t) It is expressed as the proportion of the jth additive in the predicted result of the mixing liquid ratio corresponding to the i-th historical alumina mixing liquid ratio data output by the model after the t-th iteration; and bzb (i,j) It is expressed as the proportion of the jth additive in the standard mixing solution ratio corresponding to the i-th historical alumina mixing solution ratio data; and exp() is expressed as an exponential function with a natural constant as the base; when the ratio of the prepared liquid output by the model is exactly the same as the ratio of the standard prepared liquid, ss t =1;ss t The larger the value, the worse the prediction effect of the model; when the value of the mixing loss function converges, the training ends and the learning rate in the mixing liquid ratio model is output; otherwise, the learning rate is adjusted according to the mixing loss function and the training continues until the value of the mixing loss function converges; the formula for adjusting the learning rate according to the mixing loss function is:

[0171]

[0172] Among them, xxl t It represents the learning rate after the tth iteration; β1 represents the set increment value, β1>0; β2 represents the set decrement value, β2>0; ss t Expressed as the deployment loss function of the tth iteration; It is represented by the set loss reduction threshold; the test set is used to test the mixing liquid ratio model.

[0173] Furthermore, in order to verify the effectiveness of the mixing liquid ratio model in this embodiment, this embodiment also adopts four other models for comparison. The comparison results are shown in Table 4.

[0174] Table 4 Comparison of the predicted effects of the mixing ratio model of Example 2

[0175] Model Model 1 Model 2 Model 3 Model 4 Mean square error 0.018 0.040 0.059 0.064 Mean absolute error 0.037 0.086 0.124 0.142 Root mean square error 0.027 0.073 0.094 0.126 Mean absolute percentage error 0.071％ 0.157％ 0.206％ 0.237％

[0176] Furthermore, model 1 in Table 4 is the mixing liquid ratio model proposed by the present invention, model 2 is trained with a fixed learning rate based on model 1, model 3 is trained with an absolute value loss function based on model 1, and model 4 is trained with a traditional deep belief network. It can be seen from Table 4 that the mixing liquid ratio model proposed in this embodiment is superior to the other three models in all indicators.

[0177] Reference Figure 1 A pulp mill parameter acquisition unit is provided, wherein the pulp mill parameter acquisition unit is applied to S40 of an advanced process control method for alumina pulp mill.

[0178] Further, obtaining the pulp grinding parameters according to the characteristic parameters of alumina includes:

[0179] The alumina characteristic parameters include the alumina ore parameters, the target particle diameter of the alumina ore and the alumina ore addition rate; the slurry grinding parameters include the ball mill parameters and the formulation liquid addition rate; the ball mill parameters include the speed of the ball mill, the motor power and the slurry grinding time; the formulation liquid addition rate is obtained according to the alumina ore addition rate; the ball mill model and size data selected by the alumina processing factory B in this embodiment refer to Table 5.

[0180] Table 5 Ball mill models and dimensions selected by Alumina Processing Plant B

[0181] model Cylinder diameter Cylinder length Motor Model Effective volume Processing power Maximum feed size QUR 1800mm 3620mm JR136-8 <![CDATA[8.2m 3 ]]> 4.5~29t / h 35mm

[0182] Furthermore, the process of obtaining the parameters of the ball mill includes:

[0183] Collecting a historical alumina slurry grinding data set, wherein the historical alumina slurry grinding data set includes 500 historical alumina characteristic parameters and corresponding historical ball mill parameter standard values;

[0184] Clustering the 500 historical alumina characteristic parameters to obtain P clusters, each cluster containing at least k historical alumina characteristic parameters, where k is a set value to ensure that the model training data is sufficient;

[0185] In this embodiment, k is set to 50; a ball mill slurry grinding parameter prediction model is constructed based on a multi-layer perceptron; the ball mill slurry grinding parameter prediction model is trained using the data in the P clusters to obtain P trained ball mill slurry grinding parameter prediction models; the distance between the alumina characteristic parameters and the centers of the P clusters is calculated, and the cluster with the closest distance is selected as the prediction cluster; the alumina characteristic parameters are input into the trained ball mill slurry grinding parameter prediction model corresponding to the prediction cluster to obtain the ball mill parameters corresponding to the alumina characteristic parameters.

[0186] The training process of the ball mill slurry grinding parameter prediction model includes: randomly initializing the weight and bias of the ball mill slurry grinding parameter prediction model; inputting the historical alumina characteristic parameters in the cluster into the ball mill slurry grinding parameter prediction model to obtain the historical ball mill parameter prediction value; calculating the ball mill loss function value in the ball mill slurry grinding parameter prediction model, and the calculation formula is:

[0187]

[0188] Among them, csyc t It is represented by the ball mill loss function value after the tth iteration in the ball mill grinding parameter prediction model training process; m is represented by the number of data items contained in the cluster; qmcs (e,d,t) It is represented by the dth historical ball mill parameter prediction value corresponding to the eth historical alumina characteristic parameter output by the ball mill slurry grinding parameter prediction model at the tth iteration; bzcs (e,d) It is represented by the dth historical ball mill parameter standard value corresponding to the eth historical alumina characteristic parameter; d=1 corresponds to the speed of the ball mill; d=2 corresponds to the motor power of the ball mill; d=3 corresponds to the slurry grinding time of the ball mill;

[0189] When the ball mill loss function value converges, the training ends and the weight and bias of the ball mill slurry grinding parameter prediction model are output; otherwise, the training continues until the ball mill loss function value converges.

[0190] Furthermore, this embodiment selects 5 different aluminum oxide characteristic parameters, obtains the prediction cluster corresponding to each aluminum oxide characteristic parameter, and obtains the ball mill parameters according to the corresponding trained ball mill slurry grinding parameter prediction model. In order to verify the effectiveness of this method in this embodiment, this embodiment also selects other three methods to predict the ball mill parameters, and selects the ball mill loss function value in this embodiment as the error index to verify the effectiveness of the ball mill parameter prediction method proposed in this embodiment. For specific results, refer to Table 6.

[0191] Table 6 Example 2 Ball Mill Parameter Prediction Results

[0192] Alumina characteristic parameter serial number Method 1 Method 2 Method 3 Method 4 1 0.041 0.084 0.096 0.112 2 0.039 0.083 0.102 0.111 3 0.043 0.079 0.098 0.108 4 0.040 0.082 0.101 0.112 5 0.038 0.080 0.094 0.110

[0193] Furthermore, the method 1 in Table 6 is the method proposed in this embodiment, including clustering the characteristic parameters of aluminum oxide first and then selecting the corresponding trained ball mill slurry grinding parameter prediction model for prediction; the method 2 is based on the method 1, using the mean absolute error as the loss function to train the ball mill slurry grinding parameter prediction model; the prediction process of the method 3 includes not clustering the characteristic parameters of aluminum oxide, but directly using the historical aluminum oxide slurry grinding data set to train a ball mill slurry grinding parameter prediction model, and inputting the ball mill slurry grinding parameters into the same ball mill slurry grinding parameter prediction model for prediction; the method 4 is based on the method 3, replacing the ball mill slurry grinding parameter prediction model with a traditional multi-layer perceptron for prediction. It can be seen from Table 6 that the method proposed in this embodiment can effectively improve the accuracy of slurry grinding parameter prediction.

[0194] Reference Figure 1 The pulp grinding unit and the pulp grinding result detection unit are applied to S50 and S60 of an advanced process control method for alumina pulp grinding.

[0195] Furthermore, the pulping result detection unit comprises:

[0196] Randomly select M liters of the alumina slurry as the slurry test sample; obtain the first weight of solid particles in the slurry whose particle diameter is greater than the set target particle diameter of the alumina ore; simultaneously obtain the second weight of all solid particles in the slurry; calculate the proportion of the first weight in the second weight; when the proportion is greater than the set ratio, output an unqualified slurry grinding warning; otherwise, obtain the alumina slurry and corresponding parameters, and re-train the formulation liquid ratio model and the ball mill slurry grinding parameter prediction model.

[0197] Furthermore, the retraining of the mixing liquid ratio model and the ball mill slurry grinding parameter prediction model includes: obtaining corresponding parameters in the slurry grinding process; the corresponding parameters include alumina ore parameters, alumina characteristic parameters, mixing liquid ratio and slurry grinding parameters;

[0198] The proportion of the prepared liquid is used as the standard prepared liquid proportion corresponding to the parameters of the alumina ore;

[0199] The alumina ore parameters and the corresponding standard blending solution ratio are added to the historical alumina ore blending solution ratio data set, and the blending solution ratio model is trained again;

[0200] The alumina characteristic parameters and the ball mill parameters in the slurry grinding parameters are added to the data corresponding to the prediction cluster in the historical alumina slurry grinding data set, and the ball mill slurry grinding parameter prediction model corresponding to the prediction cluster is trained again.

[0201] In the process of crushing the alumina ore in this embodiment, the hardness values ​​of multiple points on the surface of the alumina ore are averaged to obtain the surface hardness value of the alumina ore. In this embodiment, different crushing parameters are set according to the surface hardness value to crush the alumina ore. This method can better represent the hardness level of the overall sample and reduce the error caused by local heterogeneity by measuring the hardness at multiple points and taking the average value; at the same time, obtaining the crushing parameters of the crusher according to the maximum value of the surface hardness value and the set maximum feed particle size of the ball mill can enable the crusher to accurately crush the large-sized alumina ore, thereby improving the slurry milling effect in the subsequent slurry milling process. In this embodiment, a mixing liquid ratio model is constructed, which uses historical alumina ore mixing liquid ratio data for training, takes the alumina ore parameters as input, and the mixing liquid ratio as output, and takes the error between the mixing liquid ratio output in each iteration and the standard mixing liquid ratio as the loss function value of the mixing liquid ratio model, and dynamically adjusts the learning rate according to the change of the loss function. This model can avoid rapid overfitting caused by too large a learning rate or slow training speed caused by too small a learning rate. This embodiment uses a trained mixing liquid ratio model to obtain the ratio of the mixing liquid. This method can combine the various characteristics of the alumina ore to accurately obtain the ratio of the mixing liquid, thereby improving the slurry grinding effect of the alumina ore. This embodiment obtains a historical alumina slurry grinding data set, clusters the historical alumina characteristic parameters in the historical alumina slurry grinding data set, and obtains multiple clustering clusters. This embodiment constructs a ball mill slurry grinding parameter prediction model based on a multi-layer perceptron, and uses historical alumina slurry grinding data in different clusters to obtain multiple trained ball mill slurry grinding parameter prediction models. During the training process, the error between the historical ball mill parameter prediction value and the corresponding historical slurry grinding parameter standard value is used as a loss function to optimize the weight and bias of the model. This embodiment selects the corresponding trained ball mill slurry grinding parameter prediction model according to the distance between the alumina characteristic parameters and different clusters to obtain the ball mill parameters corresponding to the alumina characteristic parameters. This method can train specific models for different clusters, and can more accurately capture the data patterns and changes of these specific clusters. Therefore, targeted prediction of the ball mill slurry grinding parameters of each cluster can significantly improve the prediction accuracy of the ball mill parameters, thereby improving the slurry grinding effect of alumina ore.

[0202] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An advanced process control system for alumina slurry mill, characterized in that: Including: Aluminum oxide raw ore classification unit: used to classify aluminum oxide raw ore that needs to be pulp-ground, and obtain a set of aluminum oxide raw ore with qualified size and a set of aluminum oxide raw ore with unqualified size; Crushing unit: used to crush the aluminum oxide raw ore in the set of aluminum oxide raw ore with unqualified size. The specific process includes: Step 1: When the number of aluminum oxide raw ore contained in the set of aluminum oxide raw ore with unqualified size is less than the set value W, jump to Step 5; otherwise, execute Step 2; Step 2: Select S aluminum oxide raw ore from the set of aluminum oxide raw ore with unqualified size for hardness detection, S < W, and obtain the surface hardness values of the S aluminum oxide raw ore; Step 3: Obtain crushing parameters according to the maximum value of the S surface hardness values and the maximum feed particle size of the set ball mill; Step 4: The crushing unit crushes according to the crushing parameters. When the crushing time is reached, the aluminum oxide raw ore that fails to be discharged through the discharge port is classified into the set of aluminum oxide raw ore with unqualified size, and then jump to Step 1; Step 5: The crushing unit does not perform crushing; Blending liquid control unit: used to obtain the blending ratio of the blending liquid according to the aluminum oxide raw ore parameters corresponding to the set of aluminum oxide raw ore with qualified size; Pulp grinding parameter acquisition unit: used to obtain pulp grinding parameters according to aluminum oxide characteristic parameters; Pulp grinding unit: used to pulp grind the set of aluminum oxide raw ore with qualified size according to the pulp grinding parameters; Pulp grinding result detection unit: used to detect the generated aluminum oxide raw ore pulp after the pulp grinding time is reached.

2. The alumina slurry mill advanced process control system according to claim 1, characterized in that: The aluminum oxide raw ore classification unit includes: setting the sieve holes of the vibrating screen according to the maximum feed particle size of the ball mill, and the size of the sieve holes is not greater than the maximum feed particle size of the ball mill; screening the aluminum oxide raw ore that needs to be pulp-ground through the vibrating screen; classifying the aluminum oxide raw ore remaining on the vibrating screen into the set of aluminum oxide raw ore with unqualified size; classifying the aluminum oxide raw ore screened out by the vibrating screen into the set of aluminum oxide raw ore with qualified size.

3. The alumina slurry mill advanced process control system according to claim 1, characterized in that: The said Step 2 includes: Uniformly select multiple detection points on each of the aluminum oxide raw ore; use a hardness tester to detect the hardness value of each detection point; average the hardness values corresponding to the multiple detection points to obtain the surface hardness value of each aluminum oxide raw ore.

4. The alumina slurry mill advanced process control system according to claim 1, characterized in that: The blending liquid control unit includes: the aluminum oxide raw ore parameters include aluminum oxide raw ore size, aluminum oxide raw ore hardness, aluminum oxide raw ore density, aluminum oxide raw ore pH value, and aluminum oxide raw ore humidity; the process of obtaining the aluminum oxide raw ore size includes: randomly selecting N aluminum oxide raw ore samples from the set of aluminum oxide raw ore with qualified size; calculating the minimum circumscribed sphere diameter of the N aluminum oxide raw ore, averaging the N minimum circumscribed sphere diameters, and taking the calculation result as the aluminum oxide raw ore size; The process of obtaining the aluminum oxide raw ore hardness is: calculating the hardness of the N aluminum oxide raw ore, averaging the hardness of the N aluminum oxide raw ore, and taking the calculation result as the aluminum oxide raw ore hardness; The process of obtaining the density, pH value and humidity of the alumina ore can refer to the process of obtaining the hardness of the alumina ore; the alumina ore parameters are input into the mixing liquid proportioning model to obtain the proportion of the mixing liquid.

5. The alumina slurry mill advanced process control system according to claim 4, characterized in that: The mixing liquid ratio model adaptively adjusts the learning rate according to the mixing loss function value of the model during the training process; The training process of the mixing solution ratio model includes: collecting a historical alumina raw ore mixing solution ratio data set; the historical alumina raw ore mixing solution ratio data set includes a plurality of historical alumina mixing solution ratio data; the historical alumina mixing solution ratio data includes alumina raw ore parameters and their corresponding standard mixing solution ratios; Dividing the historical alumina ore blending liquid ratio data set into a training set and a test set; initializing the learning rate in the blending liquid ratio model; taking the alumina ore parameters in the training set as input and the blending liquid ratio prediction result as output; calculating the blending loss function value of the blending liquid ratio model; When the value of the mixing loss function converges, the training ends and the learning rate in the mixing liquid ratio model is output; otherwise, the learning rate is adjusted according to the mixing loss function and the training continues until the value of the mixing loss function converges; The mixing liquid ratio model is tested using a test set.

6. The alumina slurry mill advanced process control system according to claim 5, characterized in that: The formulation loss function includes: obtaining the formulation loss function corresponding to each iteration according to the formulation liquid ratio prediction result corresponding to each historical alumina formulation liquid ratio data output by the formulation liquid ratio model in each iteration and the standard formulation liquid ratio corresponding to each historical alumina formulation liquid ratio data.

7. The alumina slurry mill advanced process control system according to claim 1, characterized in that: The slurry milling parameter acquisition unit includes: the alumina characteristic parameters include the alumina ore parameters, the target particle diameter of the alumina ore and the alumina ore addition rate; the slurry milling parameters include ball mill parameters and the mixing liquid addition rate; the ball mill parameters include the speed of the ball mill, the motor power and the slurry milling time; the mixing liquid addition rate is obtained according to the alumina ore addition rate; the ball mill parameter acquisition process includes: A historical alumina slurry grinding data set is collected, wherein the historical alumina slurry grinding data set includes Q historical alumina characteristic parameters and corresponding historical ball mill parameter standard values; the historical alumina characteristic parameters include historical alumina ore parameters, historical alumina ore target particle diameter and historical alumina ore addition rate; the Q historical alumina characteristic parameters are clustered to obtain P clustering clusters; a ball mill slurry grinding parameter prediction model is trained using the data in the P clustering clusters to obtain P trained ball mill slurry grinding parameter prediction models; the distance between the alumina characteristic parameters and the centers of the P clusters is calculated, and the cluster with the closest distance is selected as the prediction cluster; the alumina characteristic parameters are input into the trained ball mill slurry grinding parameter prediction model corresponding to the prediction cluster to obtain the ball mill parameters corresponding to the alumina characteristic parameters.

8. The alumina slurry mill advanced process control system according to claim 1, characterized in that: The pulp grinding result detection unit includes: randomly selecting M liters of the original alumina ore pulp as the original ore pulp detection sample; obtaining the first weight of the solid particles with a particle diameter greater than the set target particle diameter of the original alumina ore in the original ore pulp; simultaneously obtaining the second weight of all solid particles in the original ore pulp; calculating the proportion of the first weight in the second weight; when the proportion is greater than the set ratio, outputting a warning of unqualified pulp grinding; otherwise, obtaining the original alumina ore pulp and corresponding parameters, and retraining the blending liquid ratio model and the ball mill pulp grinding parameter prediction model.

9. The alumina slurry mill advanced process control system according to claim 8, characterized in that: The retraining of the blending liquid ratio model and the ball mill pulp grinding parameter prediction model includes: obtaining the corresponding parameters in this pulp grinding process; the corresponding parameters include the original alumina ore parameters, alumina characteristic parameters, the ratio of the blending liquid, and the pulp grinding parameters. Taking the ratio of the blending liquid as the standard blending liquid ratio corresponding to the original alumina ore parameters. Adding the original alumina ore parameters and the corresponding standard blending liquid ratio to the historical original alumina ore blending liquid ratio dataset, and retraining the blending liquid ratio model. Adding the alumina characteristic parameters and the ball mill parameters in the pulp grinding parameters to the historical alumina pulp grinding dataset, and retraining the ball mill pulp grinding parameter prediction model.

10. An advanced process control method for alumina slurry mill, characterized in that: Including: Classifying the original alumina ore to be pulp ground, and obtaining a set of qualified-size original alumina ore and a set of unqualified-size original alumina ore. Crushing the original alumina ore in the set of unqualified-size original alumina ore. The specific process includes: Step 1: When the number of original alumina ore contained in the set of unqualified-size original alumina ore is less than the set value W, jump to Step 5; otherwise, execute Step 2. Step 2: Selecting S original alumina ore from the set of unqualified-size original alumina ore for hardness detection, S < W, and obtaining the surface hardness values of the S original alumina ore. Step 3: Obtaining the crushing parameters according to the maximum value of the S surface hardness values and the set maximum feed particle size of the ball mill. Step 4: The crushing unit crushes according to the crushing parameters. When the crushing time is reached, the original alumina ore that fails to be discharged through the discharge port is classified into the set of unqualified-size original alumina ore, and jump to Step 1. Step 5: The crushing unit does not perform crushing. Obtaining the ratio of the blending liquid according to the original alumina ore parameters corresponding to the set of qualified-size original alumina ore. Obtaining the pulp grinding parameters according to the alumina characteristic parameters; the alumina characteristic parameters include the original alumina ore parameters, the target particle diameter of the original alumina ore, and the addition rate of the original alumina ore; performing pulp grinding on the set of qualified-size original alumina ore according to the pulp grinding parameters; and detecting the generated original alumina ore pulp after the pulp grinding time is reached.

Images