A parameter generation method, a coke quality prediction method and a device

Abstract

The present application discloses a parameter generation method, a coke quality prediction method and a device, relating to the technical fields of artificial intelligence and coking industry technology, including: obtaining the minimum value and the maximum value of the in-furnace coal index data as input data in all training samples of the coke quality prediction model, calculating a coke index contribution parameter based on the numerical interval represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, where the coke index contribution parameter represents the influence of the unit change of the in-furnace coal index data on the coke index data, determining a low-region coke index adjustment parameter and a high-region coke index adjustment parameter based on the coke index contribution parameter, and the low-region coke index adjustment parameter and the high-region coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical interval. By adopting this solution, the accuracy of the prediction result obtained by using the coke quality prediction model can be improved.

Description

Technical Field

[0001] The present application relates to the technical fields of artificial intelligence and coking industry, and in particular, to a parameter generation method, a coke quality prediction method, and an apparatus therefor. Background Art

[0002] The coal blending coking process directly determines the coke quality. If the coke quality can be accurately predicted based on parameters such as single coal information and coking furnace process before coking, the single coal ratio can be adjusted, and more suitable single coal can be used for coking as much as possible to achieve better coke indexes, thereby reducing the raw material cost and improving the coke quality.

[0003] With the development of artificial intelligence technology and machine learning technology, a coke quality prediction model for predicting coke quality has emerged, which can predict the coke quality of coking using a certain charging coal before starting the actual coking operation.

[0004] However, in practical applications, due to the characteristics of the coking industry itself, such as complex processes, long time, and high costs, it is difficult to accumulate sufficient historical coking data as sample data for model training. For example, if coking is carried out once a week, only about 40 or more data can be accumulated in a year, which cannot meet the requirements of conventional model training.

[0005] Moreover, due to the small amount of sample data, when actually predicting the coke quality, the value of the charging coal index data as the input may exceed the numerical range of the sample data for model training, resulting in inaccurate coke quality prediction values output by the model.

[0006] Therefore, there is a problem in the prior art that the prediction result obtained by using the coke quality prediction model has low accuracy. Summary of the Invention

[0007] Embodiments of the present application provide a parameter generation method, a coke quality prediction method, and an apparatus therefor, so as to solve the problem in the prior art that the prediction result obtained by using the coke quality prediction model has low accuracy.

[0008] Embodiments of the present application provide a parameter generation method for coke quality prediction, including:

[0009] Obtaining the minimum value and the maximum value of the charging coal index data as input data in all training samples of the coke quality prediction model;

[0010] Calculate the coke index contribution parameter based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model. The coke index contribution parameter represents the influence of the unit change of the in-furnace coal index data on the coke index data. The input of the model function is the in-furnace coal index data, and the output of the model function is the coke index data;

[0011] Based on the coke index contribution parameter, determine the low-region coke index adjustment parameter and the high-region coke index adjustment parameter. The low-region coke index adjustment parameter and the high-region coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range.

[0012] Further, calculating the coke index contribution parameter based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, includes:

[0013] Based on multiple preselected positions in the numerical range represented by the minimum value and the maximum value, calculate the derivative of the model function of the coke quality prediction model at each preselected position respectively, and obtain multiple coke index contribution parameters corresponding one-to-one to the multiple preselected positions respectively;

[0014] The determining the low-region coke index adjustment parameter and the high-region coke index adjustment parameter based on the coke index contribution parameter includes:

[0015] According to the low-region weighting method, perform weighted summation on the multiple coke index contribution parameters to obtain the low-region coke index adjustment parameter. In the low-region weighting method, the weight values corresponding to the multiple preselected positions decrease as the preselected positions increase from small to large;

[0016] According to the high-region weighting method, perform weighted summation on the multiple coke index contribution parameters to obtain the high-region coke index adjustment parameter. In the high-region weighting method, the weight values corresponding to the multiple preselected positions increase as the preselected positions increase from small to large.

[0017] Further, the in-furnace coal index data includes multiple in-furnace coal test index data, and the coke index data includes multiple coke test index data representing the coke quality;

[0018] The obtaining the minimum value and the maximum value of the in-furnace coal index data as the input data in all training samples of the coke quality prediction model includes:

[0019] Obtain the minimum value vector and the maximum value vector of the in-furnace coal index data that serves as input data in all training samples of the coke quality prediction model. The minimum value vector includes the minimum value of each in-furnace coal test index data in all training samples, and the maximum value vector includes the maximum value of each in-furnace coal test index data in all training samples;

[0020] Based on multiple preselected positions in the numerical range represented by the minimum value and the maximum value, calculate the derivative of the model function of the coke quality prediction model at each of the preselected positions respectively, and obtain multiple coke index contribution parameters that correspond one-to-one with the multiple preselected positions respectively, including:

[0021] Based on multiple preselected positions in the numerical range represented by the minimum value vector and the maximum value vector, calculate the derivative of the model function of the coke quality prediction model at each of the preselected positions respectively, and obtain multiple coke index contribution matrices that correspond one-to-one with the multiple preselected positions respectively. The elements in the coke index contribution matrix represent the influence of the unit change of each in-furnace coal test index data on each coke test index data.

[0022] Further, the multiple preselected positions are evenly distributed in the numerical range.

[0023] Further, the low-region coke index adjustment parameter and the high-region coke index adjustment parameter are used to adjust the calculation formula of the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range as follows:

[0024] Y = Y X +△X l M l +△X h M h where M l is the low-region coke index adjustment parameter, M h is the high-region coke index adjustment parameter, and Y is the adjusted coke quality prediction value;

[0025] Y X = f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the in-furnace coal test index data X of the to-be-predicted in-furnace coal. Those less than the minimum value of this kind of in-furnace coal test index data are changed to the corresponding minimum value, those greater than the maximum value of this kind of in-furnace coal test index data are changed to the corresponding maximum value, and other in-furnace coal test index data remain unchanged;

[0026] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged. X minis the minimum value vector;

[0027] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, and X max is the maximum value vector.

[0028] An embodiment of the present application also provides a coke quality prediction method, including:

[0029] Obtaining the index data of the coal to be charged for the coke to be predicted;

[0030] When the index data of the coal to be charged for the coke to be predicted exceeds the numerical range represented by the minimum value and the maximum value, based on the coke quality prediction model, and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in any of the above parameter generation methods for coke quality prediction, predicting the coke quality of coking using the coal to be charged for the coke to be predicted;

[0031] Wherein, the minimum value and the maximum value are the minimum value and the maximum value of the index data of the coal to be charged as input data in all training samples of the coke quality prediction model.

[0032] Further, the predicting the coke quality of coking using the coal to be charged for the coke to be predicted based on the index data of the coal to be charged for the coke to be predicted, using the coke quality prediction model, and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in any of the above parameter generation methods for coke quality prediction, includes:

[0033] Based on the index data of the coal to be charged for the coke to be predicted, predicting the coke quality of coking using the coal to be charged for the coke to be predicted by using the following formula:

[0034] Y = Y X + △X l M l + △X h M h , where M l is the low-zone coke index adjustment parameter, M h is the high-zone coke index adjustment parameter, and Y is the adjusted coke quality prediction value;

[0035] Y X= f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the values of multiple in-furnace coal test index data X of the in-furnace coal to be predicted: the values less than the minimum value of the in-furnace coal test index data are changed to the corresponding minimum value, the values greater than the maximum value of the in-furnace coal test index data are changed to the corresponding maximum value, and the other in-furnace coal test index data remain unchanged;

[0036] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, and X min is the minimum value vector;

[0037] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, and X max is the maximum value vector.

[0038] The present application further provides a parameter generation device for coke quality prediction, including:

[0039] A numerical value acquisition module, configured to acquire the minimum value and the maximum value of the in-furnace coal index data used as input data in all training samples of the coke quality prediction model;

[0040] A contribution parameter calculation module, configured to calculate coke index contribution parameters based on the numerical value range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, where the coke index contribution parameters represent the influence of the unit change of the in-furnace coal index data on the coke index data, the input of the model function is the in-furnace coal index data, and the output of the model function is the coke index data;

[0041] An adjustment parameter determination module, configured to determine a low-region coke index adjustment parameter and a high-region coke index adjustment parameter based on the coke index contribution parameters, where the low-region coke index adjustment parameter and the high-region coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical value range.

[0042] Further, the contribution parameter calculation module is specifically configured to calculate the derivatives of the model function of the coke quality prediction model at each of multiple preselected positions in the numerical value range represented by the minimum value and the maximum value, respectively, to obtain multiple coke index contribution parameters corresponding one-to-one to the multiple preselected positions;

[0043] The adjustment parameter determination module is specifically configured to perform weighted summation on the multiple coke index contribution parameters according to the low - area weighting method to obtain the low - area coke index adjustment parameter. In the low - area weighting method, the weight values corresponding to the multiple pre - selected positions decrease as the pre - selected positions increase from small to large;

[0044] Perform weighted summation on the multiple coke index contribution parameters according to the high - area weighting method to obtain the high - area coke index adjustment parameter. In the high - area weighting method, the weight values corresponding to the multiple pre - selected positions increase as the pre - selected positions increase from small to large.

[0045] Further, the in - furnace coal index data includes multiple in - furnace coal test index data, and the coke index data includes multiple coke test index data representing the coke quality;

[0046] The value acquisition module is specifically configured to obtain the minimum value vector and the maximum value vector of the in - furnace coal index data used as input data in all training samples of the coke quality prediction model. The minimum value vector includes the minimum value of each in - furnace coal test index data in all training samples, and the maximum value vector includes the maximum value of each in - furnace coal test index data in all training samples;

[0047] The contribution parameter calculation module is specifically configured to calculate the derivatives of the model function of the coke quality prediction model at multiple pre - selected positions in the numerical interval represented by the minimum value vector and the maximum value vector, respectively, to obtain multiple coke index contribution matrices corresponding one - to - one with the multiple pre - selected positions. The elements in the coke index contribution matrix represent the influence of the unit change of each in - furnace coal test index data on each coke test index data.

[0048] Further, the multiple pre - selected positions are evenly distributed in the numerical interval.

[0049] Further, the low - area coke index adjustment parameter and the high - area coke index adjustment parameter are used to adjust the calculation formula of the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical interval as follows:

[0050] Y = Y X +△X l M l +△X h M h where M l is the low - area coke index adjustment parameter, M h is the high - area coke index adjustment parameter, and Y is the adjusted coke quality prediction value;

[0051] Y X= f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the values of multiple coal quality test indexes X of the coal to be predicted into the corresponding minimum values when they are less than the minimum value of the coal quality test indexes of this type of coal to be predicted into the furnace, changing the values greater than the maximum value of the coal quality test indexes of this type of coal to be predicted into the furnace into the corresponding maximum values, and keeping the other coal quality test index data unchanged;

[0052] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, where X min is the minimum value vector;

[0053] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, where X max is the maximum value vector.

[0054] The embodiment of the present application further provides a coke quality prediction device, including:

[0055] A data acquisition module, configured to acquire the coal quality indexes data of the coal to be predicted into the furnace;

[0056] A quality prediction module, configured to, when the coal quality indexes data of the coal to be predicted into the furnace exceeds the numerical range represented by the minimum value and the maximum value, predict the coke quality of coking using the coal to be predicted into the furnace based on the coke quality prediction model and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in any of the above-mentioned parameter generation methods for coke quality prediction;

[0057] Wherein, the minimum value and the maximum value are the minimum value and the maximum value of the coal quality indexes data as input data in all training samples of the coke quality prediction model.

[0058] Further, the quality prediction module is specifically configured to predict the coke quality of coking using the coal to be predicted into the furnace based on the coal quality indexes data of the coal to be predicted into the furnace by using the following formula:

[0059] Y = Y X + △X l M l + △X h M h , where M l is the low-zone coke index adjustment parameter, M h is the high-zone coke index adjustment parameter, and Y is the adjusted coke quality prediction value;

[0060] YX = f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing, in the multiple in-furnace coal test index data X of the to-be-predicted in-furnace coal, the values less than the minimum value of this type of in-furnace coal test index data to the corresponding minimum value, the values greater than the maximum value of this type of in-furnace coal test index data to the corresponding maximum value, and keeping other in-furnace coal test index data unchanged;

[0061] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, where X min is the minimum value vector;

[0062] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, where X max is the maximum value vector.

[0063] The embodiment of the present application also provides an electronic device, including a processor and a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions that can be executed by the processor. The processor is prompted by the machine-executable instructions to: implement any of the above parameter generation methods for coke quality prediction, or implement any of the above coke quality prediction methods.

[0064] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements any of the above parameter generation methods for coke quality prediction, or implements any of the above coke quality prediction methods.

[0065] The embodiment of the present application also provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute any of the above parameter generation methods for coke quality prediction, or execute any of the above coke quality prediction methods.

[0066] The beneficial effects of the present application include:

[0067] In the method provided by the embodiment of the present application, the minimum value and the maximum value of the index data of the coal charged into the furnace, which serve as input data in all the training samples of the coke quality prediction model, are obtained. Based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, a coke index contribution parameter is calculated. The coke index contribution parameter represents the influence of the unit change of the index data of the coal charged into the furnace on the index data of the coke. The input of the model function is the index data of the coal charged into the furnace, and the output of the model function is the index data of the coke. Based on the coke index contribution parameter, a low-region coke index adjustment parameter and a high-region coke index adjustment parameter are determined. The low-region coke index adjustment parameter and the high-region coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range. In this method, since the calculated coke index contribution parameter can represent the influence of the unit change of the index data of the coal charged into the furnace on the index data of the coke, the low-region coke index adjustment parameter and the high-region coke index adjustment parameter determined based on the coke index contribution parameter can effectively adjust the coke quality prediction value output when the actual input of the prediction model exceeds the numerical range, thereby improving the accuracy of the prediction result.

[0068] Other features and advantages of the present application will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present application. The objectives and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings. Description of the Drawings

[0069] The drawings are used to provide a further understanding of the present application, and constitute a part of the specification. They are used together with the embodiments of the present application to explain the present application, but do not constitute a limitation to the present application. In the drawings:

[0070] Figure 1 is a flowchart of a parameter generation method for coke quality prediction provided by an embodiment of the present application;

[0071] Figure 2 is a flowchart of a coke quality prediction method provided by an embodiment of the present application;

[0072] Figure 3 is a schematic structural diagram of a parameter generation device for coke quality prediction provided by an embodiment of the present application;

[0073] Figure 4 is a schematic structural diagram of a coke quality prediction device provided by an embodiment of the present application;

[0074] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0075] To provide an implementation solution for improving the accuracy of prediction results obtained by using a coke quality prediction model, an embodiment of the present application provides a parameter generation method, a coke quality prediction method, and a device. The preferred embodiments of the present application are described below with reference to the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0076] An embodiment of the present application provides a parameter generation method for coke quality prediction, as Figure 1 shown, including:

[0077] Step 11: Obtain the minimum value and the maximum value of the in-furnace coal index data as input data in all training samples of the coke quality prediction model;

[0078] Step 12: Based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, calculate the coke index contribution parameter, which represents the influence of the unit change of the in-furnace coal index data on the coke index data. The input of the model function is the in-furnace coal index data, and the output of the model function is the coke index data;

[0079] Step 13: Based on the coke index contribution parameter, determine the low-region coke index adjustment parameter and the high-region coke index adjustment parameter, which are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range.

[0080] By using the above parameter generation method for coke quality prediction provided by the embodiment of the present application, since the calculated coke index contribution parameter can represent the influence of the unit change of the in-furnace coal index data on the coke index data, the low-region coke index adjustment parameter and the high-region coke index adjustment parameter determined based on the coke index contribution parameter can effectively adjust the coke quality prediction value output when the actual input of the prediction model exceeds the numerical range, thereby improving the accuracy of the prediction result.

[0081] Correspondingly, the present application also provides a coke quality prediction method, as Figure 2 shown, including:

[0082] Step 21: Obtain the in-furnace coal index data of the to-be-predicted in-furnace coal;

[0083] Step 22: When the raw coal index data of the raw coal to be predicted exceeds the numerical range represented by the minimum value and the maximum value, based on the raw coal index data of the raw coal to be predicted, adopt the coke quality prediction model and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in the above parameter generation method for coke quality prediction to predict the coke quality of coking using the raw coal to be predicted;

[0084] Among them, the minimum value and the maximum value are the minimum value and the maximum value of the raw coal index data used as input data in all training samples of the coke quality prediction model.

[0085] Adopting the above coke quality prediction method provided by the embodiment of the present application, for the situation where the raw coal index data input to the coke quality prediction model exceeds the numerical range input to the model during training, the situations of being less than the minimum value and greater than the maximum value are distinguished, and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter are used to adjust the coke quality prediction value output by the model, thereby improving the accuracy of the prediction result.

[0086] The following uses specific embodiments to describe in detail the method and device provided by the present application.

[0087] In an embodiment of the present application, for the above step 12, based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, calculate the coke index contribution parameter. Multiple preselected positions can be determined in advance in the numerical range represented by the minimum value and the maximum value. Each preselected position corresponds to the corresponding numerical value in the numerical range, and then calculate the derivative of the model function of the coke quality prediction model at each preselected position respectively, and obtain multiple coke index contribution parameters corresponding to the multiple preselected positions one by one. Each coke index contribution parameter can represent the influence of the unit change of the raw coal index data at the preselected position on the coke index data.

[0088] Correspondingly, for the above step 13, based on the coke index contribution parameter, determine the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter, which may specifically include:

[0089] According to the low-zone weighting method, perform weighted summation on the multiple coke index contribution parameters to obtain the low-zone coke index adjustment parameter. In the low-zone weighting method, the weight values corresponding to the multiple preselected positions decrease as the preselected positions increase from small to large;

[0090] According to the high-zone weighting method, perform weighted summation on the multiple coke index contribution parameters to obtain the high-zone coke index adjustment parameter. In the high-zone weighting method, the weight values corresponding to the multiple preselected positions increase as the preselected positions increase from small to large.

[0091] In this embodiment, the number of the multiple preselected positions can be determined based on the number of actual applications. For example, it can be 8, 16, including the minimum value and the maximum value, and the multiple preselected positions can be evenly distributed in the numerical range; further, in order to reduce the calculation amount, it can be two preselected positions, one corresponding to the minimum value and the other corresponding to the maximum value;

[0092] The weight value corresponding to each preselected position is also the weight value of the coke index contribution parameter corresponding to the preselected position. The specific setting of the weight value can be set based on the needs of actual applications, or can be generated by using the normalized exponential function softmax function, as long as it satisfies that the weight values corresponding to the multiple preselected positions in the low-region weighting method show a decreasing trend as the preselected positions increase from small to large, and the weight values corresponding to the multiple preselected positions in the high-region weighting method show an increasing trend as the preselected positions increase from small to large.

[0093] In the embodiment of the present application, the input data of the coke quality prediction model is the index data of the coal charged into the furnace, and the output data is the coke index data. The coke index data, as the coke quality prediction value, can represent the coke quality.

[0094] In actual applications, the index data of the coal charged into the furnace can be obtained by actual detection of the coal charged into the furnace, or the index prediction model of the coal charged into the furnace can be used to predict the index data of the blended coal used as the coal charged into the furnace. The blended coal is obtained by mixing multiple single coals according to a certain proportion. The input of the index prediction model of the coal charged into the furnace is the index data of multiple single coals and the proportion of each single coal, and the output is the index data of each index of the coal charged into the furnace (i.e., the blended coal).

[0095] In an embodiment of the present application, the index data of the coal charged into the furnace can include multiple index data of the coal charged into the furnace for testing, and the coke index data can include multiple coke testing index data representing the coke quality.

[0096] Further, the multiple index data of the coal charged into the furnace for testing can at least include two of the following testing index data:

[0097] Dry basis ash content Ad;

[0098] Dry basis volatile matter Vd;

[0099] Volatile matter on dry ash-free basis Vdaf;

[0100] Dry ash-free basis sulfur content Std;

[0101] Caking index G;

[0102] Final contraction degree x of coal;

[0103] Maximum thickness of plastic layer y;

[0104] The data of multiple coke test indexes can at least include two of the following test index data:

[0105] Ash content on dry basis Ad;

[0106] Volatile matter on dry combustible basis Vdaf;

[0107] Crushing strength M40;

[0108] Abrasion resistance M10;

[0109] Reactivity CRI;

[0110] Strength after reaction CSR.

[0111] Correspondingly, for step 11 above, obtain the minimum value and the maximum value of the index data of the coal charged into the furnace as the input data in all the training samples of the coke quality prediction model. Specifically, the minimum value vector and the maximum value vector of the index data of the coal charged into the furnace as the input data in all the training samples of the coke quality prediction model can be obtained, where the minimum value vector includes the minimum value of each type of index data of the coal charged into the furnace in all the training samples, and the maximum value vector includes the maximum value of each type of index data of the coal charged into the furnace in all the training samples;

[0112] Xmin = [X1 min , X2 min , X3 min , X4 min , X5 min , X6 min , X7 min = [Ad min , Vd min , Vdaf min , Std min , G min , x min , y min , representing the minimum value vector, and each element in the vector represents the minimum value of this type of index data of the coal charged into the furnace;

[0113] Xmax = [X1 max , X2 max , X3 max , X4 max , X5 max , X6 max , X7 max = [Ad max , Vd max , Vdaf max , Std max , G max , x max , y max, representing the maximum value vector, where each element in the vector represents the maximum value of the test index data of this type of coal charged into the furnace.

[0114] Since it includes multiple test index data of the coal charged into the furnace and multiple test index data of the coke, the coke index contribution parameter is the coke index contribution matrix, where the elements in the coke index contribution matrix represent the influence of the unit change of each test index data of the coal charged into the furnace on each test index data of the coke. The following is an example:

[0116] [R ad-ad ,R ad-Vd ,R ad-Vdaf ,R ad-Std ,R ad-G ,R ad-x ,R ad-y ,

[0117] [R Vdaf-ad ,R Vdaf-Vd ,R Vdaf-Vdaf ,R Vdaf-Std ,R Vdaf-G ,R Vdaf-x ,R Vdaf-y ,

[0118] [R M40-ad ,R M40-Vd ,R M40-Vdaf ,R M40-Std ,R M40-G ,R M40-x ,R M40-y ,

[0119] [R M10-ad ,R M10-Vd ,R M10-Vdaf ,R M10-Std ,R M10-G ,R M10-x ,R M10-y ,

[0120] [R CRI-ad ,R CRI-Vd ,R CRI-Vdaf ,R CRI-Std ,R CRI-G ,R CRI-x ,R CRI-y ,

[0121] [R CSR-ad ,R CSR-Vd ,R CSR-Vdaf ,R CSR-Std ,R CSR-G ,R CSR-x ,R CSR-y ​​​

[0123] Among them, R j-i means the change amount of the coke test index data j caused by a unit change in the in-furnace coal test index data i.

[0124] Correspondingly, for step 12 above, based on the numerical interval represented by the minimum value and the maximum value, and the model function of the coke quality prediction model, calculate the coke index contribution parameter, which may specifically include:

[0125] Based on multiple preselected positions in the numerical interval represented by the minimum value vector and the maximum value vector, calculate the derivative of the model function of the coke quality prediction model at each preselected position respectively, and obtain a plurality of coke index contribution matrices corresponding one-to-one to the multiple preselected positions respectively. For example, obtain n coke index contribution matrices, M = [M 1 , M 2 ... M n , where n is the number of multiple preselected positions.

[0126] Correspondingly, use the following formula to calculate the low-zone coke index adjustment parameter:

[0127] M l = W l ·M = Wl1 * M1 + Wl2 * M2 +.... Wln * Mn;

[0128] Among them, W l is the weight vector corresponding to the low-zone weighting method, and M l is the low-zone coke index adjustment parameter.

[0129] Use the following formula to calculate the low-zone coke index adjustment parameter:

[0130] M h = W h ·M = Wh1 * M1 + Wh2 * M2 +.... Whn * Mn;

[0131] Among them, W h is the weight vector corresponding to the high-zone weighting method, and Mh is the high-zone coke index adjustment parameter.

[0132] In the embodiments of the present application, the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical interval. Specifically, the following formula can be used to adjust the coke quality prediction value:

[0133] For step 22 in the above coke quality prediction method, when there is only one in-furnace coal index data of the to-be-predicted in-furnace coal, it may specifically include:

[0134] When the index data of the coal charged into the furnace is less than the minimum value, the following formula is used to adjust the predicted coke quality value by using the coke index adjustment parameter in the low zone to obtain the adjusted predicted coke quality value:

[0135] Y l =Y min + (X l -X min )·M l ;

[0136] Wherein, X min is the minimum value, X l is the input of the coke quality prediction model, and this input is less than the minimum value, Y min is the output of the coke quality prediction model when the input is X min , M l is the coke index adjustment parameter in the low zone, and Y l is the adjusted predicted coke quality value;

[0137] When the index data of the coal charged into the furnace is greater than the maximum value, the coke index adjustment parameter in the high zone is used to adjust the predicted coke quality value to obtain the adjusted predicted coke quality value:

[0138] Y h =Y max + (X h -X max )·M h ;

[0139] Wherein, X max is the maximum value, X h is the input of the coke quality prediction model, and this input is greater than the maximum value, Y max is the output of the coke quality prediction model when the input is X max , M h is the coke index adjustment parameter in the high zone, and Y h is the adjusted predicted coke quality value.

[0140] Regarding step 22 in the above coke quality prediction method, when there are multiple index data of the coal charged into the furnace to be predicted, it may specifically include:

[0141] Y=Y X +△X l M l +△X h M h , wherein, M l is the coke index adjustment parameter in the low zone, M h is the coke index adjustment parameter in the high zone, and Y is the adjusted predicted coke quality value;

[0142] YX = f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the values of multiple in-furnace coal test index data X of the in-furnace coal to be predicted that are less than the minimum value of this type of in-furnace coal test index data to the corresponding minimum value, changing the values that are greater than the maximum value of this type of in-furnace coal test index data to the corresponding maximum value, and keeping other in-furnace coal test index data unchanged;

[0143] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, where X min is the minimum value vector;

[0144] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, where X max is the maximum value vector;

[0145] For example, assume that the multiple in-furnace coal test index data X of the in-furnace coal to be predicted are as follows:

[0146] X = [X1, X2, X3, X4, X5, X6, X7], where X1, X3, and X7 are respectively less than X1 min , X3 min and X7 min , and X2, X4, and X6 are respectively greater than X2 max , X4 max and X6 max , then:

[0147] X` = [X1 min , X2 max , X3 min , X4 max , X5, X6 max , X7 min ;

[0148] X - X min = [X1 - X1 min , X2 - X2 min , X3 - X3 min , X4 - X4 min , X5 - X5 min , X6 - X6 min , X7 - X7 min , where X2 - X2 min , X4 - X4 min , X5 - X5 min and X6 - X6 min are all greater than 0, so they are all changed to 0, △Xl =[X1 - X1 min , 0, X3 - X3 min , 0, 0, 0, X7 - X7 min ;

[0149] X - X max =[X1 - X1 max , X2 - X2 max , X3 - X3 max , X4 - X4 max , X5 - X5 max , X6 - X6 max , X7 - X7 max , where X1 - X1 max , X3 - X3 max , X5 - X5 max and X7 - X7 max are all less than 0. Therefore, they are all changed to 0, and △X h =[0, X2 - X2 max , 0, X4 - X4 max , 0, X6 - X6 max , 0].

[0150] Based on the above formula for the case where there are multiple indices of the coal charged into the furnace, it can be seen that when there is only one index of the coal charged into the furnace to be detected, this formula is essentially also applicable.

[0151] Based on the same inventive concept, according to the method for generating parameters for coke quality prediction provided in the above embodiments of the present application, correspondingly, another embodiment of the present application further provides a device for generating parameters for coke quality prediction, and its structural schematic diagram is as Figure 3 shown, and specifically includes:

[0152] A numerical value acquisition module 31, configured to acquire the minimum value and the maximum value of the indices of the coal charged into the furnace as input data in all training samples of the coke quality prediction model;

[0153] A contribution parameter calculation module 32, configured to calculate a coke index contribution parameter based on the numerical range represented by the minimum value and the maximum value, and the model function of the coke quality prediction model. The coke index contribution parameter represents the influence of the unit change of the indices of the coal charged into the furnace on the coke index data. The input of the model function is the indices of the coal charged into the furnace, and the output of the model function is the coke index data;

[0154] An adjustment parameter determination module 33, configured to determine a low-zone coke index adjustment parameter and a high-zone coke index adjustment parameter based on the coke index contribution parameter, where the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range.

[0155] Further, the contribution parameter calculation module 32 is specifically configured to calculate the derivatives of the model function of the coke quality prediction model at each of the multiple preselected positions in the numerical range represented by the minimum value and the maximum value, to obtain a plurality of coke index contribution parameters respectively corresponding one by one to the multiple preselected positions;

[0156] The adjustment parameter determination module 33 is specifically configured to perform weighted summation on the plurality of coke index contribution parameters according to a low-zone weighting method, to obtain a low-zone coke index adjustment parameter, where in the low-zone weighting method, the weight values corresponding to the multiple preselected positions decrease as the preselected positions increase from small to large;

[0157] Perform weighted summation on the plurality of coke index contribution parameters according to a high-zone weighting method, to obtain a high-zone coke index adjustment parameter, where in the high-zone weighting method, the weight values corresponding to the multiple preselected positions increase as the preselected positions increase from small to large.

[0158] Further, the in-furnace coal index data includes a plurality of in-furnace coal test index data, and the coke index data includes a plurality of coke test index data representing coke quality;

[0159] The numerical value acquisition module 31 is specifically configured to acquire a minimum value vector and a maximum value vector of the in-furnace coal index data used as input data in all training samples of the coke quality prediction model, where the minimum value vector includes the minimum value of each in-furnace coal test index data in all training samples, and the maximum value vector includes the maximum value of each in-furnace coal test index data in all training samples;

[0160] The contribution parameter calculation module 32 is specifically configured to calculate the derivatives of the model function of the coke quality prediction model at each of the multiple preselected positions in the numerical range represented by the minimum value vector and the maximum value vector, to obtain a plurality of coke index contribution matrices respectively corresponding one by one to the multiple preselected positions, where the elements in the coke index contribution matrix represent the influence of the unit change of each in-furnace coal test index data on each coke test index data.

[0161] Further, the multiple preselected positions are evenly distributed in the numerical range.

[0162] Further, when the input of the coke quality prediction model exceeds the numerical range, the calculation formula for adjusting the coke quality prediction value output by the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter is as follows:

[0163] Y = Y X + △X l M l + △X h M h , where M l is the low-zone coke index adjustment parameter, M h is the high-zone coke index adjustment parameter, and Y is the adjusted coke quality prediction value;

[0164] Y X = f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the values of the multiple in-furnace coal assay index data X of the to-be-predicted in-furnace coal that are less than the minimum value of this type of in-furnace coal assay index data to the corresponding minimum value, and changing the values that are greater than the maximum value of this type of in-furnace coal assay index data to the corresponding maximum value, while keeping other in-furnace coal assay index data unchanged;

[0165] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, and X min is the minimum value vector;

[0166] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, and X max is the maximum value vector.

[0167] Based on the same inventive concept, according to the coke quality prediction method provided in the above embodiments of the present application, correspondingly, another embodiment of the present application further provides a coke quality prediction device, the structural schematic diagram of which is as shown in Figure 4 and specifically includes:

[0168] A data acquisition module 41, configured to acquire the in-furnace coal index data of the to-be-predicted in-furnace coal;

[0169] A quality prediction module 42, configured to, when the in-furnace coal index data of the to-be-predicted in-furnace coal exceeds the numerical range represented by the minimum value and the maximum value, predict the coke quality of coking using the to-be-predicted in-furnace coal based on the coke quality prediction model and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in any of the above parameter generation methods for coke quality prediction;

[0170] Among them, the minimum value and the maximum value are the minimum value and the maximum value of the indices data of the coal charged into the furnace as input data in all the training samples of the coke quality prediction model.

[0171] Further, the quality prediction module 42 is specifically configured to predict the coke quality of coking using the coal charged into the furnace to be predicted based on the indices data of the coal charged into the furnace to be predicted, by using the following formula:

[0172] Y = Y X +△X l M l +△X h M h , where M l is the adjustment parameter of the coke index in the low zone, M h is the adjustment parameter of the coke index in the high zone, and Y is the predicted value of the adjusted coke quality;

[0173] Y X = f(X`), where f() is the model function of the coke quality prediction model, and X` is obtained by changing the indices data X of the coal charged into the furnace to be predicted that is less than the minimum value of the indices data of this kind of coal charged into the furnace to the corresponding minimum value, changing the indices data X of the coal charged into the furnace to be predicted that is greater than the maximum value of the indices data of this kind of coal charged into the furnace to the corresponding maximum value, and keeping other indices data of the coal charged into the furnace unchanged;

[0174] △X l is obtained by changing the elements greater than 0 in the result of X - X min to 0 and keeping the elements less than or equal to 0 unchanged, and X min is the minimum value vector;

[0175] △X h is obtained by changing the elements less than 0 in the result of X - X max to 0 and keeping the elements greater than or equal to 0 unchanged, and X max is the maximum value vector.

[0176] The functions of the above modules can correspond to Figure 1 and Figure 2 the corresponding processing steps in the shown processes, which will not be elaborated here.

[0177] The parameter generation device and the coke quality prediction device for coke quality prediction provided by the embodiments of the present application can be implemented by a computer program. Those skilled in the art should be able to understand that the above module division method is only one of many module division methods. If divided into other modules or not divided into modules, as long as the parameter generation device and the coke quality prediction device for coke quality prediction have the above functions, they should all be within the protection scope of the present application.

[0178] The embodiments of the present application further provide an electronic device, such as Figure 5 shown, including a processor 51 and a machine-readable storage medium 52. The machine-readable storage medium 52 stores machine-executable instructions that can be executed by the processor 51. The processor 51 is prompted by the machine-executable instructions to: implement any of the above parameter generation methods for coke quality prediction, or implement any of the above coke quality prediction methods.

[0179] The embodiments of the present application further provide a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, it implements any of the above parameter generation methods for coke quality prediction, or implements any of the above coke quality prediction methods.

[0180] The embodiments of the present application further provide a computer program product containing instructions. When it runs on a computer, it causes the computer to execute any of the above parameter generation methods for coke quality prediction, or execute any of the above coke quality prediction methods.

[0181] The machine-readable storage medium in the above electronic device may include a random access memory (Random Access Memory, RAM), or may also include a non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0182] The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it may also be a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field-Programmable Gate Array, FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0183] Each embodiment in this specification is described in a related manner. The same or similar parts among the embodiments can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the embodiments of the device, electronic device, computer-readable storage medium, and computer program product, since they are basically similar to the method embodiments, the description is relatively simple, and the related parts can be referred to the description of the method embodiments.

[0184] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0185] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce a means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0186] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0187] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0188] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

1. A parameter generation method for coke quality prediction, characterized in that: include: Obtain the minimum and maximum values ​​of the coal index data used as input data in all training samples of the coke quality prediction model; Based on a plurality of preselected positions in the numerical interval represented by the minimum value and the maximum value, respectively calculate the derivative of the model function of the coke quality prediction model at each of the preselected positions, and obtain a plurality of coke index contribution parameters corresponding to the plurality of preselected positions, the coke index contribution parameters representing the influence of a unit change of the feed coal index data on the coke index data, the input of the model function being the feed coal index data, and the output of the model function being the coke index data; According to the low-zone weighted method, the multiple coke index contribution parameters are weighted and summed to obtain the low-zone coke index adjustment parameter, wherein the weight values ​​corresponding to the multiple preselected positions in the low-zone weighted method show a downward trend as the preselected positions increase from small to large; According to the high zone weighted method, the multiple coke index contribution parameters are weighted and summed to obtain the high zone coke index adjustment parameter, the weight values ​​corresponding to the multiple pre-selected positions in the high zone weighted method show an upward trend with the pre-selected position from small to large, and the low zone coke index adjustment parameter and the high zone coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range.

2. The method according to claim 1, characterized in that The feed coal index data includes a plurality of feed coal test index data, and the coke index data includes a plurality of coke test index data indicating the quality of the coke; The method of obtaining the minimum and maximum values ​​of the coal index data used as input data in all training samples of the coke quality prediction model includes: Obtaining a minimum value vector and a maximum value vector of the coal index data used as input data in all training samples of the coke quality prediction model, wherein the minimum value vector includes the minimum value of each type of coal test index data in all training samples, and the maximum value vector includes the maximum value of each type of coal test index data in all training samples; The method of calculating the derivative of the model function of the coke quality prediction model at each of the preselected positions in the numerical range represented by the minimum value and the maximum value, respectively, and obtaining a plurality of coke index contribution parameters corresponding to the preselected positions, respectively, comprises: Based on multiple preselected positions in the numerical interval represented by the minimum value vector and the maximum value vector, the derivatives of the model function of the coke quality prediction model at each of the preselected positions are calculated respectively, and multiple coke index contribution matrices corresponding to the multiple preselected positions are obtained. The elements in the coke index contribution matrix represent the influence of a unit change in the test index data of each type of coal entering the furnace on each type of coke test index data.

3. The method according to claim 1, characterized in that The plurality of preselected positions are evenly distributed in the numerical interval.

4. The method according to claim 2, characterized in that The calculation formula of the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter for adjusting the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range is as follows: Y=Y X +△X l M l +△X h M h , where M l The parameter for adjusting the coke index in the low zone, M h is the high-zone coke index adjustment parameter, and Y is the adjusted coke quality prediction value; Y X =f(X`), wherein f() is the model function of the coke quality prediction model, and X` is obtained by changing the value of the multiple test index data X of the feed coal to be predicted that is less than the minimum test index data of the feed coal to the corresponding minimum value, and changing the value of the multiple test index data X of the feed coal to be predicted that is greater than the maximum test index data of the feed coal to the corresponding maximum value, while keeping the other test index data of the feed coal unchanged; △X l To XX min The result is that the elements greater than 0 are changed to 0, and the elements less than or equal to 0 remain unchanged, X min is the minimum value vector; △X h To XX max The result is that the elements less than 0 are changed to 0, and the elements greater than or equal to 0 remain unchanged. max is the maximum value vector.

5. A method for predicting coke quality, characterized in that: include: Obtaining the coal index data of the coal to be predicted; When the feed coal index data of the feed coal to be predicted exceeds the numerical range represented by the minimum value and the maximum value, based on the feed coal index data of the feed coal to be predicted, the coke quality prediction model is adopted, as well as the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in the method described in any one of claims 1 to 4, to predict the coke quality of coking using the feed coal to be predicted; The minimum value and the maximum value are the minimum value and the maximum value of the coal index data used as input data in all training samples of the coke quality prediction model.

6. A parameter generation device for coke quality prediction, characterized in that: include: A numerical acquisition module is used to obtain the minimum and maximum values ​​of the coal index data used as input data in all training samples of the coke quality prediction model; a contribution parameter calculation module, for respectively calculating the derivative of the model function of the coke quality prediction model at each of the preselected positions based on the preselected positions in the numerical interval represented by the minimum value and the maximum value, and obtaining a plurality of coke index contribution parameters corresponding to the preselected positions, wherein the coke index contribution parameters represent the influence of a unit change of the feed coal index data on the coke index data, the input of the model function is the feed coal index data, and the output of the model function is the coke index data; An adjustment parameter determination module is used to perform weighted summation on the multiple coke index contribution parameters according to a low-zone weighted method to obtain a low-zone coke index adjustment parameter, wherein the weight values ​​corresponding to the multiple preselected positions in the low-zone weighted method show a downward trend as the preselected position increases from small to large; and perform weighted summation on the multiple coke index contribution parameters according to a high-zone weighted method to obtain a high-zone coke index adjustment parameter, wherein the weight values ​​corresponding to the multiple preselected positions in the high-zone weighted method show an upward trend as the preselected position increases from small to large. The low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter are used to adjust the coke quality prediction value output when the input of the coke quality prediction model exceeds the numerical range.

7. A coke quality prediction device, characterized in that: include: A data acquisition module is used to acquire the coal index data of the coal to be predicted; A quality prediction module, used for predicting the quality of coke produced by coking using the to-be-predicted coal for coaling, based on the coke quality prediction model and the low-zone coke index adjustment parameter and the high-zone coke index adjustment parameter in the method described in any one of claims 1 to 4, when the coal index data of the to-be-predicted coal for coaling exceeds the numerical range represented by the minimum value and the maximum value; The minimum value and the maximum value are the minimum value and the maximum value of the coal index data used as input data in all training samples of the coke quality prediction model.

8. An electronic device, characterized in that: The invention comprises a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement any one of the methods described in claims 1 to 4, or to implement the method described in claim 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented, or the method according to claim 5 is implemented.

Images