A method and system for determining clean coal yield

Abstract

The application discloses a method and system for determining clean coal yield, and relates to the technical field of coal preparation and floatation, which comprises the following steps: collecting historical float-and-sink data of heavy separation feed and distribution release data of floatation feed; predicting the ash content of the heavy separation feed and the floatation feed according to the ash content of raw coal; correcting the historical float-and-sink data to generate a new float-and-sink table; fitting and drawing a gravity separation actual selectability curve; correcting the yield of the historical step release data table, fitting and drawing an actual floatability curve; determining the heavy separation process parameters, the floatation process parameters, the product structure and the corresponding production parameters. The application can improve the clean coal yield.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of coal cleaning and flotation, and particularly relates to a method and system for determining clean coal yield. BACKGROUND

[0002] In the coal washing process, gravity separation refers to a mineral separation method that uses the differences in relative density, particle size, shape, movement rate and direction of particles in medium (water, air or other liquid with relatively high density) to separate the particles from each other. Flotation is a mineral separation method that separates useful minerals from useless minerals under the action of reagents according to the differences in surface properties of the minerals. The composition of the comprehensive clean coal in a coal preparation plant usually includes gravity clean coal, coarse coal slime and flotation clean coal. The combination of the ash contents of the clean coal in each link is different, and the comprehensive clean coal with ash content meeting the user requirements can still be obtained. However, different combinations of the ash contents of the clean coal will result in different comprehensive clean coal yields.

[0003] In the prior art, the washing process of most coal preparation plants is: lump coal and fine coal heavy medium-coarse slime separate recovery-coal slime flotation process. In the actual production process, in order to ensure that the ash content of the comprehensive clean coal meets the standard, each workshop formulates the ash content index of the clean coal in each link according to the artificial experience, so as to determine the separation parameters in each link. The ash content index of the clean coal in each link is usually much lower than the sales standard, so the clean coal yield is sacrificed to ensure that the ash content of the clean coal does not exceed the standard.

[0004] At present, the existing technology cannot accurately obtain the clean coal ash content that does not exceed the standard according to the artificial experience, so it is impossible to reasonably set the production parameters, and unreasonable production parameters will affect the clean coal yield. SUMMARY

[0005] The embodiments of the present application provide a method and system for determining clean coal yield, which can solve the problem in the prior art that the production parameters cannot be reasonably set through accurate clean coal ash content to improve the clean coal yield.

[0006] This invention provides a method for determining the yield of clean coal, comprising the following steps: obtaining a flotation table including the yield of the flotation table and the historical ash content of the gravity separation feed under gravity separation conditions, and a step-by-step release data table including the yield of the step-by-step release data table and the historical ash content of the flotation feed under flotation conditions; wherein the gravity separation feed ash content represents the content of non-combustible components obtained after separating mineral particles in the raw coal by gravity separation, and the flotation feed ash content represents the content of non-combustible components obtained after separating mineral particles in the raw coal by flotation; using the raw coal ash content to train a neural network model to predict the ash content of the gravity separation feed and the flotation feed, thereby obtaining an ash content prediction model; inputting the raw coal ash content to be detected into the ash content prediction model to obtain the ash content of the gravity separation feed and the flotation feed. Ash content of the feed material; based on the difference between the ash content of the gravity separation feed and the historical ash content of the gravity separation feed, the yield of the flotation table is corrected and the flotation table is updated; based on the difference between the ash content of the flotation feed and the historical flotation feed, the yield of the distribution release data table is corrected and the distribution release data table is updated; based on the updated flotation table, the actual gravity separation washability curve is fitted; based on the updated distribution release data table, the actual floatability curve is fitted; based on the boundary ash content used to distinguish clean coal, the ash content of gravity separation clean coal and flotation clean coal are obtained from the actual gravity separation washability curve and the actual floatability curve, respectively; based on the ash content of gravity separation clean coal and flotation clean coal, the total clean coal ash content is obtained using the equal boundary ash content principle, and the corresponding production parameters are set according to the total clean coal ash content to determine the clean coal yield.

[0007] Furthermore, the specific steps for correcting the yield of the float / sink table include:

[0008] The difference Δweight between the ash content of the re-selected feed and the historical ash content of the re-selected feed is obtained using the following formula:

[0009] Δrepetition = λrepetition - λrepetition

[0010] Wherein: λre-entry is the ash content of the re-selected feed; λre-origin is the ash content of the historical re-selected feed, and the ash content of the historical re-selected feed is specifically: the total ash content in the float-sink table of the historical re-selected feed.

[0011] Obtain a density greater than +1.8 g / cm³ 3 ash content at the density level Ad +1.8 The formula is:

[0012]

[0013] Where Adn represents the nth element greater than +1.8 g / cm³. 3 The density level of ash content; γn represents the nth ash content greater than +1.8 g / cm³. 3 Yield at density levels; n indicates greater than +1.8 g / cm³. 3 The number of density levels;

[0014] The ash Ad of the density level less than -1.8 g / cm 3 The density level is +1.8 g / cm -1.8 The formula is:

[0015]

[0016] Wherein, Adm represents the ash of the mth density level less than -1.8 g / cm 3 The density level is +1.8 g / cm 3 The formula is: 3 Wherein, m represents the number of the density level less than -1.8 g / cm

[0017] The calibration value X is obtained, and the formula is:

[0018] X = (100 * Δ weight) / (Ad +1.8 - Ad -1.8 )

[0019] The yield of the float-and-sink table is corrected.

[0020] If the density level is +1.8 g / cm 3 :

[0021] γ correction = γ + X

[0022] If the density level is -1.8 g / cm 3 :

[0023]

[0024] Wherein, γ correction represents the yield of the corresponding density level after correction, and γ represents the yield of the corresponding density level before correction.

[0025] Further, the yield of the distribution release data table is corrected, and the specific steps include:

[0026] The difference Δ float between the float feed ash and the historical float feed ash is obtained, and the formula is:

[0027] Δ float = λ float in - λ float original

[0028] Wherein, λ float in is the float feed ash; λ float original is the historical float feed ash, and the historical float feed ash is specifically: the weighted ash of each clean and tail coal of the historical distribution release data table.

[0029] The ash Ad 轻 of the first tail coal of the distribution release is obtained, and the formula is:

[0030]

[0031] Ad tail m represents the ash of the mth tailing in the distribution release; γ tail m represents the yield of the mth tailing in the distribution release; m represents the number of flotation in the distribution release test; Ad clean represents the ash of the clean coal in the distribution release; γ clean represents the yield of the clean coal in the distribution release; γ tail 1 represents the yield of the first tailing in the distribution release;

[0032] The calibration value X is obtained, and the formula is:

[0033] X=(100*Δ float) / (Ad 尾1 -Ad 轻 )

[0034] Ad tail 1 represents the ash of the first tailing in the distribution release; 尾1

[0035] The yield of the distribution release table is corrected;

[0036] For the first flotation tailing in the distribution release:

[0037] γ corrected =γ tail 1+X

[0038] For the mth flotation tailing in the distribution release (m>=2):

[0039] γ corrected =γ tail m-γ tail m*X / (100-γ tail 1)

[0040] For the clean coal in the distribution release:

[0041] γ corrected =γ clean-γ clean*X / (100-γ tail 1)

[0042] Wherein, γ corrected represents the yield of the corresponding flotation clean (tail) coal after correction.

[0043] Further, the ash of the gravity separation clean coal is obtained in the gravity separation actual selectivity curve, and the specific steps include: setting the boundary ash for distinguishing the clean coal according to the target ash required by the clean coal as the ash content; on the ash characteristic curve in the gravity separation actual selectivity curve, taking the boundary ash as the abscissa value, obtaining the corresponding ordinate value as the gravity separation clean coal yield; the gravity separation actual selectivity curve includes: ash characteristic curve λ, float cumulative curve β, density curve δ; on the float cumulative curve in the gravity separation actual selectivity curve, taking the gravity separation clean coal yield as the ordinate value, obtaining the corresponding abscissa value as the gravity separation clean coal ash.

[0044] ​Further, the step of obtaining the ash content of the clean coal in the actual floatability curve comprises: taking the boundary ash content as the horizontal coordinate value on the ash content characteristic curve in the actual floatability curve, and obtaining the corresponding vertical coordinate value as the clean coal yield; and taking the clean coal yield as the vertical coordinate value on the cumulative float curve in the actual floatability curve, and obtaining the corresponding horizontal coordinate value as the ash content of the clean coal.

[0045] Further, the step of obtaining the total clean coal ash content according to the equal boundary ash content principle comprises:

[0046] The total clean coal ash content A is obtained according to the weighted average of the ash content of the gravity separation clean coal and the ash content of the flotation clean coal;

[0047] According to the equal boundary ash content principle, when the total clean coal ash content is less than the set error standard value than the target clean coal ash content, the clean coal yield obtained is higher than the clean coal yield obtained when the total clean coal ash content is greater than the set error standard value than the target clean coal ash content;

[0048] The error standard value ε, the step length α and the target clean coal ash A are set;

[0049] If |A-A|>ε:

[0050] When A>A, A=A-α; and when A

[0051] If |A-A|<ε, the total clean coal ash content A meets the requirement.

[0052] Further, the step of setting the corresponding production parameters according to the total clean coal ash content comprises:

[0053] The step of setting the corresponding production parameters according to the total clean coal ash content comprises: taking the total clean coal ash content as the vertical coordinate value on the density curve in the actual gravity separation selectability curve, and obtaining the corresponding horizontal coordinate value as the separation density of the gravity separation link; and taking the total clean coal ash content as the vertical coordinate value on the cumulative float yield-distribution release test frequency curve in the actual floatability curve, and obtaining the corresponding horizontal coordinate value as the optimal flotation section number of the flotation link.

[0054] The embodiment of the present application provides a clean coal yield determination system, which comprises:

[0055] The ash content prediction module is configured to obtain a float-and-sink table containing the float-and-sink table yield and the historical gravity separation feed ash content under the gravity separation condition, and a step-by-step release data table containing the step-by-step release data table yield and the historical flotation feed ash content under the flotation condition.

[0056] The yield correction module is configured to use the neural network model trained by the raw coal ash content to predict the gravity separation feed ash content and the flotation feed ash content, to obtain an ash content prediction model; input the raw coal ash content to be detected into the ash content prediction model to obtain the gravity separation feed ash content and the flotation feed ash content; correct the sink-and-float table yield according to the difference between the gravity separation feed ash content and the historical gravity separation feed ash content, and update the sink-and-float table; correct the distribution release data table yield according to the difference between the flotation feed ash content and the historical flotation feed ash content, and update the distribution release data table; fit the gravity separation actual selectability curve according to the updated sink-and-float table; and fit the actual floatability curve according to the updated distribution release data table.

[0057] The yield improvement module is configured to obtain the gravity separation clean coal ash content and the flotation clean coal ash content in the gravity separation actual selectability curve and the actual floatability curve respectively according to the boundary ash content for distinguishing the clean coal; obtain the total clean coal ash content by using the equal boundary ash content principle according to the gravity separation clean coal ash content and the flotation clean coal ash content, and set the corresponding production parameters by using the total clean coal ash content to determine the clean coal yield.

[0058] The embodiment of the present application provides a clean coal yield determination method and system, which has the following advantages compared with the prior art.

[0059] The gravity separation feed ash content and the flotation feed ash content are obtained by using the trained neural network model, i.e., the ash content prediction model; the sink-and-float table yield is corrected and the sink-and-float table is updated according to the difference between the gravity separation feed ash content and the historical gravity separation feed ash content; the distribution release data table yield is corrected and the distribution release data table is updated according to the difference between the flotation feed ash content and the historical flotation feed ash content; the gravity separation actual selectability curve is fitted according to the updated sink-and-float table; the actual floatability curve is fitted according to the updated distribution release data table; the gravity separation clean coal ash content and the flotation clean coal ash content are obtained by using the corresponding values of the curves, so that the total clean coal ash content is obtained by using the equal boundary ash content principle, and the corresponding production parameters are finally determined according to the total clean coal ash content. While avoiding the error caused by obtaining the total clean coal ash content by using artificial experience, the production parameters can be accurately set by using the total clean coal ash content, so that the clean coal yield is improved according to the accurately set production parameters. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 The flowchart provided by the embodiment of the present application is provided;

[0061] Figure 2 The corrected sink-and-float data table provided by the embodiment of the present application is provided;

[0062] Figure 3 The gravity separation actual selectability curve diagram drawn after fitting provided by the embodiment of the present application is provided, wherein the lambda curve represents the ash content characteristic curve; the beta curve represents the float cumulative curve; and the delta curve represents the density curve;

[0063] Figure 4 a corrected stepwise release data table provided for the embodiment of the present application;

[0064] Figure 5 a fitted actual floatability graph provided for the embodiment of the present application, wherein the curve of λ represents the ash characteristic curve; the curve of β represents the float cumulative curve; the curve of v represents the float cumulative yield-distribution release test number curve; and the curve of n represents the sink cumulative curve. DETAILED DESCRIPTION

[0065] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application are described in detail below with reference to the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in a number of different manners other than those described herein, and it is contemplated that some modifications of the embodiments disclosed can be made by those skilled in the art without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0066] Referring to Figure 1 The embodiment of the present application provides a method for determining clean coal yield, comprising the following steps:

[0067] Step one: obtaining a sink-float table containing float-sink table yield and historical sink feed ash under gravity separation, and a stepwise release data table containing stepwise release data table yield and historical float feed ash under flotation.

[0068] Step two: using raw coal ash and raw coal screening data to train a neural network model to predict sink feed ash and float feed ash, to obtain an ash prediction model; inputting the raw coal ash to be detected into the ash prediction model to obtain the sink feed ash and the float feed ash; correcting and updating the float-sink table yield according to the difference between the sink feed ash and the historical sink feed ash; correcting and updating the distribution release data table yield according to the difference between the float feed ash and the historical float feed ash; fitting the gravity separation actual washability curve according to the updated float-sink table; and fitting the actual floatability curve according to the updated distribution release data table.

[0069] Step three: obtaining sink clean coal ash and float clean coal ash in the gravity separation actual washability curve and the actual floatability curve, respectively, according to the boundary ash for distinguishing clean coal; obtaining total clean coal ash using the equal boundary ash principle according to the sink clean coal ash and the float clean coal ash; and setting corresponding production parameters by the total clean coal ash to determine the clean coal yield.

[0070] The specific explanation of the above steps is as follows:

[0071] 1. Based on the ash content and screening results of raw coal, a BP neural network is used to train a model to determine the density composition of the coal, thereby predicting the ash content of gravity separation feed and flotation feed.

[0072] 2. Collect historical buoyancy data of gravity separation feed and floatability data (distributed release data) of flotation feed through the coal preparation plant's centralized control system.

[0073] 3. Historical float-sink data correction: Input the ash content of the new gravity separation feed, and calculate the difference Δweight between the feed ash content and the original float-sink data. Using Δweight, correct the original float-sink data yield, and generate a new float-sink data based on the corrected yield and ash content. Figure 2 As shown.

[0074] Specifically, the steps include the following:

[0075] 3.1 Calculate Δweight:

[0076] Δrepetition = λrepetition - λrepetition

[0077] Wherein: λre-entry is the ash content of the re-selected feed; λoriginal is the ash content of the historical re-selected feed, and the ash content of the historical re-selected feed is specifically the total ash content in the float-sink table of the historical re-selected feed.

[0078] 3.2 Calculate Ad +1.8 :

[0079]

[0080] Where Adn represents the nth element greater than +1.8 g / cm³. 3 The density level of ash content; γn represents the nth ash content greater than +1.8 g / cm³. 3 Yield at density levels; n indicates greater than +1.8 g / cm³. 3 The number of density levels.

[0081] 3.3 Calculate Ad -1.8 :

[0082]

[0083] Where: Adm represents the m-th element less than -1.8 g / cm³ 3 The density level of ash content; γm represents the m-th ash content less than -1.8 g / cm³. 3 Yield at density levels; m indicates less than -1.8 g / cm³. 3 The number of density levels.

[0084] 3.4 Calculate the calibration value X:

[0085] X = (100 * Δ weight) / (Ad) +1.8 -Ad -1.8 )

[0086] 3.5 Correcting the sink-float table yield:

[0087] If the density class is +1.8 g / cm 3 :

[0088] γcorrected = γ + X

[0089] If the density class is -1.8 g / cm 3 :

[0090]

[0091] Where γcorrected represents the yield of the corresponding density class after correction, and γ represents the yield of the corresponding density class before correction.

[0092] 4. Drawing of the actual selectivity curve: the percentage of the amount of a certain density class in the raw material that enters the light product in the raw material is called the distribution rate of the density class in the light product, denoted by the symbol e. The corresponding distribution rates of the separation density at 1.3, 1.4, 1.5, 1.6 and 1.7 are calculated: the value of the intermediate value t is calculated, the value of e is calculated according to the high-level language python, the data table of the actual selectivity curve of gravity separation is calculated, and the actual selectivity curve of gravity separation is fitted and drawn, as shown in Figure 3 .

[0093] The empirical formula for calculating the intermediate parameter t is:

[0094] t = 0.675 / E * (δ - δp)

[0095] Where δ represents the average density of each density class, and δp represents the actual separation density.

[0096] The python high-level language for calculating the value of e is:

[0097]

[0098] The fitting formula of the actual floatability curve is:

[0099] y = 100 * (b - np.arctan(c * (x - d))) * (b - a)

[0100] Where a, b, c, d, and x are undetermined parameters.

[0101] 5. Correction of historical step release data: input the ash content of the new flotation feed, calculate the difference Δfloat between the ash content of the feed and the total ash content of the original step release data table. Use Δfloat to correct the yield of the original step release data table, and generate a new distribution release data table based on the corrected yield and ash content, as shown in Figure 4 , the actual floatability curve is fitted and drawn, as shown in Figure 5As shown.

[0102] The difference Δfloat is obtained by comparing the ash content of the flotation feed with the historical ash content of the flotation feed. The formula is:

[0103] Δbuoyancy = λbuoyancy_in - λbuoyancy_origin

[0104] Wherein, λfloat represents the ash content of the flotation feed; λfloat origin represents the ash content of the historical flotation feed, specifically the weighted ash content of each tailings coal in the historical distribution release data table.

[0105] Obtain the ash content of the first tailings release. 轻 The formula is:

[0106]

[0107] Where Adtailm represents the ash content of the m-th tailings in the distributed release; γtailm represents the yield of the m-th tailings in the distributed release; m represents the number of flotation times in the distributed release test; Adclean represents the ash content of the clean coal in the distributed release; γclean represents the yield of the clean coal in the distributed release; and γtail1 represents the yield of the first tailings in the distributed release.

[0108] The calibration value X is obtained using the following formula:

[0109] X = (100 * Δbuoyancy) / (Ad) 尾1 -Ad 轻 )

[0110] Among them, Ad 尾1 This indicates the ash content of the first batch of tailings released.

[0111] Correct the yield of the distributed release table.

[0112] For the distributed release of tailings from the first flotation stage:

[0113] γ correction = γ tail 1 + X

[0114] For the distributed release of tailings from the m-th flotation (m>=2):

[0115] γ correction = γ tail m - γ tail m * X / (100 - γ tail 1)

[0116] For distributed release of refined coal:

[0117] γ correction = γ precision - γ precision * X / (100 - γ tail 1)

[0118] Wherein, γ correction represents the yield of clean (tailings) coal after the corresponding flotation number of times after correction, and γ* represents the yield of clean (tailings) coal before the corresponding flotation number of times.

[0119] 6. Determine the reselection process parameters: according to the purpose of ash A set boundary ash λ, check the ash characteristic curve (λ curve) of the actual reselection selectivity curve, so as to obtain its corresponding ordinate a2, that is, the reselection clean coal yield. Bring a2 into the cumulative float of the float curve (β curve), so as to obtain the corresponding abscissa a3, that is, the reselection clean coal ash.

[0120] 7. Determine the flotation process parameters: input the boundary ash λ, check the λ curve of the actual floatability curve, so as to obtain its corresponding ordinate b2, that is, the flotation clean coal yield. Bring b2 into the β curve to obtain the corresponding abscissa b3, that is, the flotation clean coal ash.

[0121] 8. Determine the product structure: calculate the effect of each separation operation according to the equal boundary ash principle, calculate the total clean coal ash A, so as to set the corresponding production parameters.

[0122] According to the weighted average ash of the reselection clean coal ash and the flotation clean coal ash, the total clean coal ash A is obtained.

[0123] According to the equal boundary ash principle, when the total clean coal ash and the target clean coal ash are less than the set error standard value, the clean coal yield obtained is higher than that when the total clean coal ash and the target clean coal ash are greater than the set error standard value.

[0124] Set the error standard value ε, the step size α and the target clean coal ash A.

[0125] If |A-A|>ε:

[0126] When A>A, A=A-α; when A<A, A=A+α.

[0127] If |A-A|<ε, the total clean coal ash A meets the requirements.

[0128] On the density curve in the actual selectivity curve of gravity separation, the total clean coal ash is taken as the ordinate value, and the corresponding abscissa value is obtained as the separation density of the gravity separation link.

[0129] On the cumulative yield-distribution release test number curve in the actual floatability curve, the total clean coal ash is taken as the ordinate value, and the corresponding abscissa value is obtained as the optimal flotation section number of the flotation link.

[0130] The present application designs a calculation template for maximizing the clean coal yield. When the raw coal properties or the required product structure of the user changes, only the corresponding raw coal ash or boundary ash set value in the template needs to be changed, and the template can output the theoretical ash of each link and the product structure, as well as the total clean coal yield and ash, and transmit the calculation results to the control module to realize accurate control of the product structure.

[0131] The clean coal yield maximization system based on big data comprises a knowledge base for storing a database of professional knowledge, a database for recording and storing input data of experts and technical personnel, experimental data and operation, reasoning and process data in the expert system, a reasoning machine for matching appropriate output values through preset reasoning logic according to input values, an interpreter for modifying or explaining the output values of the reasoning machine, and a man-machine interactive interface for establishing a communication connection with a user interface, transmitting instructions, displaying data and manually inputting control parameters. The database further comprises experience data, and processing of the experience data comprises: storing original float-and-sink data, distribution release data, and screening data and the proportion of entering gravity separation and floatation under corresponding coal quality; when the equipment fails or the index is abnormal, the adjustment parameters manually input by the technical personnel and the corresponding clean coal requirement will be divided and the clean coal requirement will be divided.

[0132] The present application has the following beneficial effects:

[0133] The present application adopts a clean coal yield maximization calculation method based on big data, replaces the cumbersome series of experimental steps of traditional raw coal medium analysis, predicts the properties of raw coal through big data, can accurately and quickly determine the raw coal washing proportion, and calculates the theoretical clean coal ash of each link under the condition of requiring clean coal ash to maximize the clean coal yield with the help of the equal boundary ash principle, can not only reduce the labor intensity of the operator's test, but also eliminate the interference of human factors, improve the efficiency and scientificity of the preparation of the washing scheme, and significantly improve the automation and intelligence level of the whole coal preparation process, guarantee the realization of the clean coal yield maximization, i.e., the maximization of economic benefits.

[0134] The present application provides a kind of determination system of clean coal yield, comprising:

[0135] The ash prediction module is used to obtain a float-and-sink table containing float-and-sink table yield and historical gravity separation feed ash under gravity separation, and a step-by-step release data table containing step-by-step release data table yield and historical floatation feed ash under floatation.

[0136] The yield correction module is used to train a neural network model using raw coal ash content and raw coal screening data to predict the ash content of gravity separation feed and flotation feed, thus obtaining an ash content prediction model. The raw coal ash content to be tested is input into the ash content prediction model to obtain the ash content of gravity separation feed and flotation feed. Based on the difference between the gravity separation feed ash content and historical gravity separation feed ash content, the yield of the flotation table is corrected and updated. Based on the difference between the flotation feed ash content and historical flotation feed ash content, the yield of the distribution release data table is corrected and updated. Based on the updated flotation table, the actual gravity separation selectivity curve is fitted. Based on the updated distribution release data table, the actual floatability curve is fitted.

[0137] The yield improvement module is used to obtain the ash content of gravity separation clean coal and flotation clean coal respectively from the actual washability curve and the actual floatability curve of gravity separation, based on the boundary ash content used to distinguish clean coal; based on the ash content of gravity separation clean coal and flotation clean coal, the total clean coal ash content is obtained using the equal boundary ash content principle; and the corresponding production parameters are set according to the total clean coal ash content to determine the clean coal yield.

[0138] A specific example is as follows:

[0139] like Figure 1 The flowchart shown illustrates the process for maximizing the clean coal yield in a coal preparation plant:

[0140] The calculation template for maximizing clean coal yield is used when the properties of raw coal or the required product structure changes. Only the corresponding raw coal ash content or boundary ash content setting value in the template needs to be changed. The template can then output the theoretical ash content and product structure of each stage, as well as the total clean coal yield and ash content, and transmit the calculation results to the control module to achieve precise control of the product structure. Specifically, the big data-based clean coal yield maximization system includes a knowledge base, a database, an inference engine, an interpreter, and a human-computer interaction interface. The knowledge base stores databases of professional domain knowledge, and the database records input data, experimental data, and computational, inference, and process data from experts and technicians. The inference engine matches appropriate output values ​​based on preset inference logic according to the input values. The interpreter modifies or explains the output values ​​of the inference engine. The human-computer interaction interface establishes a communication connection with the user interface for command transmission, data display, and manual control parameter input.

[0141] In this example, the PB neural network is programmed by Matlab to train the historical block float data and predict the raw coal float and sink composition, the distribution rate function is defined and the output of each density distribution rate is realized by python programming, the Access database is used as the comprehensive database of the expert system, the collected knowledge is stored in the database through sensor collection and manual input, the collected ash content data and the information provided by the field staff are analyzed, the coal flotation process working state knowledge base is designed, and the expert system database based on the historical fast float data, raw coal ash content and each product clean coal ash content is established.

[0142] In addition, the database also includes experience data, and processing of the experience data includes: storing manual control parameters and corresponding gravity separation floatation dressing ratio, gravity separation clean coal ash content and floatation clean coal ash content; when the equipment fails or the index is abnormal, the adjustment parameters manually input by the technical personnel and the corresponding gravity separation floatation dressing ratio, gravity separation clean coal ash content and floatation clean coal ash content. The detected gravity separation floatation dressing ratio, gravity separation clean coal ash content and floatation clean coal ash content are sent to the database, and the data are stored in the Access database of the industrial computer, and the rule data input by the flotation experts, technical personnel and experienced workers are also included in the database.

[0143] The present application comprises the following steps:

[0144] S1. Collecting the historical float and sink data of the gravity separation feed and the floatability data (distribution release data) of the floatation feed through the centralized control system of the coal preparation plant.

[0145] S2. It can be seen from the raw coal ash content and the raw coal screening result that when the raw coal ash content changes, the yield of the-1.5 density level and the yield of the+1.8 density level change the most compared with others, and the yield of the-1.5 density level and the yield of the+1.8 density level fluctuate the most compared with the baseline. Therefore, the change of the raw coal ash content has the greatest influence on the yield of the-1.5 density level and the yield of the+1.8 density level. In the actual production process, the separation parameters such as separation density are rarely changed, so when the raw coal quality changes, the change of the raw coal quality is also reflected in the change of the ash content of the gravity separation product clean coal, middlings and gangue, that is, there is a certain influence relationship between the yield of the-1.5 density level, the yield of the+1.8 density level and the ash content of the gravity separation product clean coal, middlings and gangue, so the raw coal ash content, the ash content of the gravity separation product clean coal, middlings and gangue can be used as independent variables, and the yield of the-1.5 density level and the yield of the+1.8 density level can be used as dependent variables to train the model by BP neural network to determine the density composition of the coal, so as to predict the ash content of the gravity separation feed and the ash content of the floatation feed.

[0146] Because the four input parameter values differ greatly, in order to avoid the influence of the difference of the values on the effect of the model, the data is scaled. The scaling processing includes data normalization and data standardization, and the data normalization is mainly used to process the data in this paper, that is, each sample data is mapped to [-1, 1], and the formula is:

[0147]

[0148] where y max and y min are parameters, and the default values are -1 and 1, x min is the minimum value of the original data to be processed, x max is the maximum value of the original data to be processed, and a is the original data after normalization processing. When the data is output, the data is denormalized.

[0149] S3. History sink-float data correction: input new re-election feed ash content, calculate the difference Δre between the feed ash content and the original table ash content, use Δre to correct the original sink-float table yield, and generate a new sink-float table based on the corrected yield and ash content, Figure 2 is the corrected sink-float data table.

[0150] S4. Actual selectability curve drawing: calculate the corresponding distribution rate of the separation density at 1.3, 1.4, 1.5, 1.6 and 1.7, calculate the actual selectability curve data table of gravity separation, and fit and draw the actual selectability curve of gravity separation, Figure 3 is the fitted and drawn actual selectability curve of gravity separation.

[0151] S5. History step release data correction: input new flotation feed ash content, calculate the difference Δf1 between the feed ash content and the total ash content of the original step release data table, use Δf1 to correct the yield of the original step release data table, and generate a new distribution release data table based on the corrected yield and ash content, and fit and draw the actual floatability curve, Figure 4 and Figure 5 are the corrected step release data table and the fitted and drawn actual floatability curve, respectively.

[0152] S6. Determine the re-election process parameters: set the boundary ash content λ according to the target ash content Atarget, find the λ curve of the actual selectability curve of re-election, and obtain the corresponding ordinate a2, which is the yield of re-election clean coal. Bring a2 into the cumulative β curve of the float, and obtain the corresponding abscissa a3, which is the ash content of the re-election clean coal; bring a2 into the density δ curve, and obtain the corresponding upper abscissa a4, which is the theoretical separation density of re-election.

[0153] S7. Determining the floatation process parameters: input the boundary ash content λ, search the λ curve of the actual floatability curve, thus obtaining its corresponding ordinate b2, which is the clean coal yield of floatation. Bring b2 into the β curve to obtain the corresponding abscissa b3, which is the clean coal ash content of floatation; bring b2 into the v curve to obtain the corresponding abscissa b4, which is the optimal floatation times.

[0154] S8. Determining the product structure: calculate the effect of each separation operation according to the equal boundary ash content principle, calculate the total clean coal ash content A, and at the same time, set the corresponding production parameters; set a4 as the theoretical separation density of gravity separation, and b4 as the optimal floatation stage number.

[0155] The basic theory of the principle of the lowest clean coal ash content and the highest clean coal yield is that, in consideration of the recovery rate of combustible matter, when two or more than two kinds of coal are separated respectively, in order to make the total clean coal ash content lowest or the total clean coal yield highest, the principle of equal elementary ash content must be followed.

[0156] The above-described embodiments only express several embodiments of the present application, and the description is relatively specific and detailed, but it cannot be understood as the limitation of the patent scope of the present application. It should be noted that, for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for determining clean coal yield, characterized in that, Includes the following steps: The data includes a flotation table showing the yield and historical gravity separation feed ash content under gravity separation conditions, and a step-by-step release data table showing the yield and historical flotation feed ash content under flotation conditions. The gravity separation feed ash content represents the content of non-combustible components obtained after separating mineral particles from raw coal by gravity separation, and the flotation feed ash content represents the content of non-combustible components obtained after separating mineral particles from raw coal by flotation. The ash content of raw coal is used to train a neural network model to predict the ash content of gravity separation feed and flotation feed, thus obtaining an ash content prediction model; the ash content of the raw coal to be detected is input into the ash content prediction model to obtain the ash content of gravity separation feed and flotation feed. Based on the difference between the ash content of the gravity separation feed and the historical gravity separation feed ash content, the flotation and sinking table yield is corrected and the flotation and sinking table is updated; based on the difference between the ash content of the flotation feed and the historical flotation feed ash content, the distribution and release data table yield is corrected and the distribution and release data table is updated; based on the updated flotation and sinking table, the actual gravity separation selectivity curve is fitted; based on the updated distribution and release data table, the actual floatability curve is fitted. Based on the boundary ash content used to distinguish clean coal, the ash content of gravity separation clean coal and flotation clean coal are obtained from the actual washability curve and actual floatability curve of gravity separation, respectively. Based on the ash content of gravity separation clean coal and flotation clean coal, the total clean coal ash content is obtained using the principle of equal boundary ash content. The corresponding production parameters are set according to the total clean coal ash content to determine the clean coal yield.

2. The method for determining clean coal yield as described in claim 1, characterized in that, The specific steps for correcting the yield of the float / sink table include: The difference Δweight between the ash content of the re-selected feed and the historical ash content of the re-selected feed is obtained using the following formula: Δrepetition = λrepetition - λrepetition Wherein: λre-entry is the ash content of the re-selected feed; λre-origin is the ash content of the historical re-selected feed, and the ash content of the historical re-selected feed is specifically: the total ash content in the float-sink table of the historical re-selected feed. Obtain a density greater than +1.8 g / cm³ 3 ash content at the density level Ad +1.8 The formula is: Where Adn represents the nth element greater than +1.8 g / cm³. 3 The density level of ash content; γn represents the nth ash content greater than +1.8 g / cm³. 3 Yield at density levels; n indicates greater than +1.8 g / cm³. 3 The number of density levels; Obtain a density of less than -1.8 g / cm³ 3 ash content at the density level Ad -1.8 The formula is: Where Adm represents the m-th element less than -1.8 g / cm³. 3 The density level of ash content; γm represents the m-th ash content less than -1.8 g / cm³. 3 Yield at density levels; m indicates less than -1.8 g / cm³. 3 The number of density levels; The calibration value X is obtained using the following formula: X = (100 * Δweight) / (Ad +1.8 -Ad -1.8 ) Correct the yield of the float / sink table; If the density level is +1.8 g / cm³ 3 : γ correction = γ + X If the density is -1.8 g / cm³ 3 : Wherein, γ correction represents the yield of the corresponding density level after correction, and γ represents the yield of the corresponding density level before correction.

3. The method for determining clean coal yield as described in claim 1, characterized in that, The specific steps for correcting the yield of the distributed release data table include: The difference Δfloat is obtained by comparing the ash content of the flotation feed with the historical ash content of the flotation feed. The formula is: Δbuoyancy = λbuoyancy_in - λbuoyancy_origin Wherein, λfloat is the ash content of the flotation feed; λfloat origin is the ash content of the historical flotation feed, and the ash content of the historical flotation feed is specifically: the weighted ash content of each tailing coal in the historical distribution release data table. Obtain the ash content of the first tailings release. 轻 The formula is: Where Adtailm represents the ash content of the m-th tailings in the distributed release; γtailm represents the yield of the m-th tailings in the distributed release; m represents the number of flotation times in the distributed release test; Adclean represents the ash content of the clean coal in the distributed release; γclean represents the yield of the clean coal in the distributed release; and γtail1 represents the yield of the first tailings in the distributed release. The calibration value X is obtained using the following formula: X = (100 * Δfloat) / (Ad 尾1 -Ad 轻 ) Among them, Ad 尾1 This indicates the ash content of the first batch of tailings released in a distributed manner; Correct the yield of the distribution release table; For the distributed release of tailings from the first flotation stage: γ correction = γ tail 1 + X For the distributed release of tailings from the m-th flotation (m>=2): γ correction = γ tail m - γ tail m * X / (100 - γ tail 1) For distributed release of refined coal: γ correction = γ precision - γ precision * X / (100 - γ tail 1) Among them, γ correction represents the yield of clean (tail) coal after correction for the corresponding flotation times.

4. The method for determining clean coal yield as described in claim 1, characterized in that, The steps for obtaining the ash content of heavy-medium clean coal in the actual washability curve of gravity separation specifically include: Setting the cut-off ash for distinguishing clean coal according to the target ash content required for clean coal; On the ash characteristic curve within the actual washability curve of gravity separation, taking the cut-off ash as the abscissa value and obtaining the corresponding ordinate value as the yield of heavy-medium clean coal; the actual washability curve of gravity separation includes: ash characteristic curve λ, float cumulative curve β, density curve δ; On the float cumulative curve within the actual washability curve of gravity separation, taking the yield of heavy-medium clean coal as the ordinate value and obtaining the corresponding abscissa value as the ash content of heavy-medium clean coal.

5. The method for determining clean coal yield as described in claim 1, characterized in that, The steps for obtaining the ash content of flotation clean coal in the actual floatability curve specifically include: On the ash characteristic curve within the actual floatability curve, taking the cut-off ash as the abscissa value and obtaining the corresponding ordinate value as the yield of flotation clean coal; the actual floatability curve includes: ash characteristic curve λ, float cumulative curve β, float cumulative yield-distribution release test times curve v, sink cumulative curve n; On the float cumulative curve within the actual floatability curve, taking the yield of flotation clean coal as the ordinate value and obtaining the corresponding abscissa value as the ash content of flotation clean coal.

6. The method for determining clean coal yield as described in claim 1, characterized in that, The steps for obtaining the total clean coal ash content using the principle of equal cut-off ash specifically include: Obtaining the total clean coal ash content A_calculated according to the weighted average ash content of the heavy-medium clean coal ash content and the flotation clean coal ash content; According to the principle of equal cut-off ash, when the difference between the total clean coal ash content and the target clean coal ash content is less than the set error standard value, the yield of clean coal obtained is higher than that when the difference between the total clean coal ash content and the target clean coal ash content is greater than the set error standard value; Setting the error standard value ε, step size α, and target clean coal ash A_target; If |A_calculated - A_target| > ε: When A_calculated > A_target, A_calculated = A_calculated - α; when A_calculated < A_target, A_calculated = A_calculated + α; If |A_calculated - A_target| < ε, the total clean coal ash content A_calculated meets the requirements.

7. The method for determining clean coal yield as described in claim 1, characterized in that, The steps for setting corresponding production parameters based on the total clean coal ash content specifically include: On the density curve within the actual washability curve of gravity separation, taking the total clean coal ash content as the ordinate value and obtaining the corresponding abscissa value as the separation density of the gravity separation stage; On the float cumulative yield-distribution release test times curve within the actual floatability curve, taking the total clean coal ash content as the ordinate value and obtaining the corresponding abscissa value as the optimal number of flotation stages in the flotation stage.

8. A system for determining clean coal yield, characterized in that, Including: An ash prediction module for obtaining a float-sink table containing the yield of the float-sink table and the historical heavy-medium feed ash content in the case of gravity separation, and a step-by-step release data table containing the yield of the step-by-step release data table and the historical flotation feed ash content in the case of flotation; The yield correction module is used to train a neural network model using raw coal ash content to predict the ash content of gravity separation feed and flotation feed, thus obtaining an ash content prediction model. The raw coal ash content to be tested is input into the ash content prediction model to obtain the ash content of gravity separation feed and flotation feed. Based on the difference between the gravity separation feed ash content and historical gravity separation feed ash content, the yield of the flotation table is corrected and the flotation table is updated. Based on the difference between the flotation feed ash content and historical flotation feed ash content, the yield of the distribution release data table is corrected and the distribution release data table is updated. Based on the updated flotation table, the actual gravity separation selectivity curve is fitted. Based on the updated distribution release data table, the actual floatability curve is fitted. The yield improvement module is used to obtain the ash content of gravity separation clean coal and flotation clean coal respectively from the actual washability curve and the actual floatability curve of gravity separation, based on the boundary ash content used to distinguish clean coal; based on the ash content of gravity separation clean coal and flotation clean coal, the total clean coal ash content is obtained using the equal boundary ash content principle; and the corresponding production parameters are set according to the total clean coal ash content to determine the clean coal yield.

Images