Coking coal optimization method based on coupling of coal quality characteristics and process requirements

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a coking coal optimization method based on coupling of coal quality characteristics and process requirements, and the method comprises the steps: obtaining coal quality characteristic data and process requirement data of coking coal; performing relevance comparison on the coal quality characteristic data and the process demand data to obtain relevance data of the coal quality characteristic data and the process demand data; based on the relevance data, performing sensitivity analysis on the coal quality characteristic data to obtain sensitivity data of the coal quality characteristic data; performing matching adjustment on alternative coal types based on the relevance data and the sensitivity data to obtain an optimized coal type combination of the coking coal; determining the coal blending proportion based on the relevance data, the sensitivity data and the optimized coal type combination; reliable support is provided for stabilizing the coke quality and improving the coking production efficiency, and the utilization efficiency of coking coal resources is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a coking coal optimization method based on coupling of coal quality characteristics and process requirements. BACKGROUND

[0002] In the field of coking coal optimization, the existing technology is difficult to effectively utilize the coal quality characteristic data and the process requirement data in cooperation. Most methods only analyze the coal quality characteristics in a single dimension, or only adjust the independent parameters around the process requirements, and fail to fully exploit the internal correlation between the two, resulting in a lack of precise matching basis between the coal selection and the process requirements. This makes the determined coal combination often unable to fully adapt to the actual requirements of the target process, not only easily causing fluctuations in coke quality, but also reducing the overall efficiency of coking production, and is difficult to meet the requirements of efficient allocation of coal resources for industrial production.

[0003] At the same time, the existing coking coal optimization technology has significant defects in key indicator analysis and scheme landing. On the one hand, there is a lack of in-depth evaluation of the influence of coal quality characteristic indicators on process parameters, which cannot accurately identify the coal quality factors that play a key role in the process effect, resulting in a low precision and poor stability of the coal blending ratio determination and washing and selection process parameter adjustment; on the other hand, the optimized coal blending scheme and washing and selection process lack a strict effect verification mechanism, which cannot judge the feasibility and reliability of the scheme in advance, which may lead to poor process adaptability, resource waste and other problems in actual production, further increasing the cost and quality risk of coking production. SUMMARY

[0004] The present application provides a coking coal optimization method based on coupling of coal quality characteristics and process requirements to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides a coking coal optimization method based on coupling of coal quality characteristics and process requirements, which comprises:

[0006] S1, obtaining coal quality characteristic data and process requirement data of coking coal;

[0007] S2, comparing the correlation of the coal quality characteristic data and the process requirement data to obtain correlation data of the coal quality characteristic data and the process requirement data;

[0008] S3, based on the correlation data, performing sensitivity analysis on the coal quality characteristic data to obtain sensitivity data of the coal quality characteristic data;

[0009] S4, based on the correlation data and the sensitivity data, adjusting the matching of the alternative coal types to obtain an optimized coal combination of the coking coal;

[0010] S5, determining the coal blending ratio based on the correlation data, the sensitivity data and the optimized coal combination, and optimizing the parameters of the washing and separation process to obtain the optimized coal blending ratio of the coking coal and the optimized washing and separation process;

[0011] S6, verifying the optimized coal combination, the optimized coal blending ratio and the optimized washing and separation process to obtain the optimization effect data of the coking coal.

[0012] In a preferred embodiment, the analysis of the coal quality characteristics and the coking process requirements of the coking coal comprises:

[0013] performing proximate analysis on the coking coal to obtain proximate analysis data of the coking coal;

[0014] performing elemental analysis on the coking coal to obtain elemental analysis data of the coking coal;

[0015] performing coal petrography analysis on the coking coal to obtain coal petrography analysis data of the coking coal;

[0016] performing process parameter analysis on the target coking process to obtain process parameter data of the coking process requirements;

[0017] performing coke quality analysis based on the target coke quality requirements to obtain quality index data of the coking coal.

[0018] In a preferred embodiment, the correlation comparison of the coal quality characteristic data and the process requirement data to obtain the correlation data of the coal quality characteristic data and the process requirement data comprises:

[0019] performing data alignment processing on the coal quality characteristic data and the process requirement data to obtain aligned coal quality characteristic data and aligned process requirement data;

[0020] performing correlation strength evaluation on the aligned coal quality characteristic data and the aligned process requirement data to obtain a correlation strength index;

[0021] performing data summarization on the correlation strength index to obtain the correlation data.

[0022] In a preferred embodiment, the sensitivity analysis of the coal quality characteristic data based on the correlation data to obtain the sensitivity data of the coal quality characteristic data comprises:

[0023] performing index sorting on the coal quality characteristic data based on the correlation data to obtain key coal quality characteristic indexes with a correlation strength higher than a preset threshold;

[0024] Based on the correlation data, process parameter sorting is performed on the process requirement data to obtain key process parameters with a correlation strength higher than a preset threshold value;

[0025] The change range of the key coal quality characteristic index is set to obtain a coal quality characteristic index with a set change range;

[0026] The coal quality characteristic index with a set change range is sorted based on the correlation data to obtain key coal quality characteristic indexes with a correlation strength higher than a preset threshold value;

[0027] Based on the correlation data, process parameter sorting is performed on the process requirement data to obtain key process parameters with a correlation strength higher than a preset threshold value;

[0028] The change range of the key coal quality characteristic index is set to obtain a coal quality characteristic index with a set change range;

[0029] The coal quality characteristic index with a set change range is sorted based on the correlation data to obtain key coal quality characteristic indexes with a correlation strength higher than a preset threshold value;

[0030] In a preferred embodiment, the influence degree evaluation of the coal quality characteristic index with a set change range and the key process parameter to obtain the sensitivity data of the coal quality characteristic data includes:

[0031] The reference value and the change range of the coal quality characteristic index with a set change range are obtained;

[0032] The reference value of the key process parameter is obtained;

[0033] Based on historical data or experimental data, a mathematical relationship model between the coal quality characteristic index and the process parameter is established by multiple regression analysis, and the mathematical relationship model is represented as:

[0034]

[0035] In the formula, is the serial number of the coal quality characteristic index, is a constant term, is the regression coefficient of the th coal quality characteristic index;

[0036] Based on the mathematical relationship model, the change amount of the key process parameter when the coal quality characteristic index changes is calculated;

[0037] ​a sensitivity coefficient of the coal quality characteristic index to the key process parameter is calculated based on a sensitivity coefficient formula, the sensitivity coefficient formula being:

[0038]

[0039] wherein, denotes a reference value of the i-th coal quality characteristic index, denotes a variation range of the i-th coal quality characteristic index, denotes a reference value of the i-th key process parameter, denotes a variation range of the i-th key process parameter, denotes a sensitivity coefficient of the i-th coal quality characteristic index to the i-th key process parameter. all the sensitivity coefficients are summarized, and the summarized sensitivity coefficients are taken as sensitivity data of the coal quality characteristic data.

[0040] In one preferred embodiment, the matching adjustment of the alternative coal types based on the correlation data and the sensitivity data obtains the optimized coal type combination of the coking coal, including:

[0041] Based on the correlation data, candidate coal types with high correlation strength to the target process requirement are screened out from the alternative coal types, to obtain a candidate coal type set;

[0042] Based on the sensitivity data, core coal quality indexes with high sensitivity to the key process parameters are identified from the candidate coal type set;

[0043] According to the reference level of the core coal quality indexes, the coal types in the candidate coal type set are evaluated for matching degree, to obtain a matching priority list of the coal types;

[0044] Based on the matching priority list, a preset number of coal types with high matching degree are selected for combination, to obtain the optimized coal type combination of the coking coal.

[0045] In one preferred embodiment, the matching adjustment of the alternative coal types based on the correlation data and the sensitivity data obtains the optimized coal type combination of the coking coal, including,

[0046] The reference coal quality characteristic data of the coal types in the optimized coal type combination are extracted;

[0047] Core control indexes are extracted from the key coal quality characteristic indexes;

[0048] Core control indexes are extracted from the key coal quality characteristic indexes;

[0049] ​​​​​comparing the benchmark values of the core control indicators of each coal type with each other, and assigning a quality proportion of each coal type in the optimized coal type combination according to the comparison result;

[0050] forming the optimized coal blending ratio based on the quality proportions.

[0051] In one preferred embodiment, the parameter optimization of the washing and separation process includes:

[0052] comparing the expected values of the core control indicators under the optimized coal blending ratio with the process requirement target values to obtain indicator difference values;

[0053] setting a coal quality improvement target value that needs to be achieved by the washing and separation process according to the indicator difference values;

[0054] adjusting the separation density and washing water flow parameters of the washing and separation equipment according to the coal quality improvement target value to obtain the optimized washing and separation process.

[0055] In one preferred embodiment, the contribution degree model established based on historical data is used to calculate the contribution degree weight of each coal type in the optimized coal type combination to the core control indicators, which includes:

[0056] sorting the benchmark values of the core control indicators of each coal type according to the numerical values;

[0057] dividing each coal type into three levels of high benchmark value coal type, medium benchmark value coal type and low benchmark value coal type according to the sorting result;

[0058] determining the preliminary quality proportion of each coal type according to the principle that the high benchmark value coal type is assigned a higher quality proportion, the medium benchmark value coal type is assigned a medium quality proportion, and the low benchmark value coal type is assigned a lower quality proportion;

[0059] fine-tuning the preliminary quality proportion based on the sensitivity coefficients of each coal type in the sensitivity data to obtain the final quality proportion of each coal type.

[0060] In one preferred embodiment, the verification of the optimized coal type combination, the optimized coal blending ratio and the optimized washing and separation process to obtain the optimization effect data of the coking coal includes:

[0061] preparing test coal according to the optimized coal type combination and the optimized coal blending ratio;

[0062] washing and separating the test coal by using the optimized washing and separation process to obtain a test coke sample of the coking coal;

[0063] conducting a coking test on the test coke sample to obtain a test coke;

[0064] Detect the mechanical strength and post-reaction strength index of the test coke, and compare the detection results with the target value of process requirement to obtain the optimization effect data.

[0065] Advantages

[0066] Compared with the prior art, the present application has the following advantages:

[0067] 1. By systematically obtaining the coal quality characteristic data and process requirement data of coking coal, and after correlation comparison and sensitivity analysis, the selected coal species are matched and adjusted, and then the optimized coal blending ratio and the optimized washing and separation process are determined, and finally the optimization effect data is obtained through verification. This process can realize the deep coupling of coal quality characteristics and process requirements, effectively improve the precision and efficiency of coking coal optimization, and ensure that the optimized coal combination, coal blending ratio and washing process can better adapt to the coking production demand, providing reliable support for stable coke quality and improving coking production efficiency.

[0068] 2. By correlating the coal quality characteristic data and process requirement data and sensitivity analysis, the key influencing factors can be accurately identified, which provides a scientific basis for coal matching adjustment, coal blending ratio determination and washing process parameter optimization, and avoids the blindness in the optimization process. At the same time, through the verification link of the optimization results, the effectiveness of the optimization scheme can be confirmed in advance, which ensures that the optimized coking coal can achieve the expected effect in actual application, not only helps to improve the utilization efficiency of coking coal resources, but also reduces the production risk caused by unreasonable scheme, further ensures the stability and efficiency of coking production. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 A flowchart of a coking coal optimization method based on the coupling of coal quality characteristics and process requirements provided by an embodiment of the present application.

[0070] The implementation, functional characteristics and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0071] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0072] The embodiment of the present application provides a coking coal optimization method based on coupling of coal quality characteristics and process requirements. The execution subject of the coking coal optimization method based on coupling of coal quality characteristics and process requirements includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the coking coal optimization method based on coupling of coal quality characteristics and process requirements can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0073] Referring to Figure 1 Fig. 1 is a flowchart of a coking coal optimization method based on coupling of coal quality characteristics and process requirements provided by an embodiment of the present application. In the embodiment, the coking coal optimization method based on coupling of coal quality characteristics and process requirements includes the following steps.

[0074] S1, obtaining coal quality characteristic data and process requirement data of coking coal.

[0075] In the embodiment of the present application, the analysis of the coal quality characteristics and the coking process requirements of the coking coal includes the following steps.

[0076] performing proximate analysis on the coking coal to obtain proximate analysis data of the coking coal;

[0077] performing ultimate analysis on the coking coal to obtain ultimate analysis data of the coking coal;

[0078] performing coal petrography analysis on the coking coal to obtain coal petrography analysis data of the coking coal;

[0079] performing process parameter analysis on a target coking process to obtain process parameter data of the coking process requirement;

[0080] performing coke quality analysis based on a target coke quality requirement to obtain quality index data of the coking coal.

[0081] Specifically, when the industrial analysis of the coking coal is performed, a representative part is first selected from the coking coal sample, crushed to a specified particle size and mixed uniformly, then the sample is placed into a drying box and dried to a constant weight at a specific temperature, and the moisture content is calculated by weighing; the dried sample is then placed into a muffle furnace, burned in an air atmosphere at a set temperature and time, and after cooling, the ash content is calculated by weighing; another dried sample is placed into a porcelain crucible with a cover, heated under air isolation conditions at a specified temperature and time, and after cooling, the volatile matter content is calculated by weighing; the fixed carbon content is obtained by subtracting the mass of moisture, ash and volatile matter from the total mass of the coal sample, and finally the industrial analysis data of the coking coal is obtained by integrating these data.

[0082] Further, when the elemental analysis of the coking coal is performed, the prepared coking coal sample is placed into a combustion furnace of an elemental analyzer, completely burned at a set temperature under sufficient oxygen, so that carbon in the sample is converted into carbon dioxide and hydrogen is converted into water, and the two substances are respectively absorbed by a specific absorbent, and the content of carbon and hydrogen is calculated by weighing the weight gain of the absorbent; for nitrogen element, Kjeldahl method is used, the sample is mixed with catalyst and sulfuric acid and heated to digest, so that nitrogen is converted into ammonium salt, and then alkali distillation is performed, ammonia distilled out is absorbed by boric acid solution, and finally the nitrogen content is calculated by titration with an acid standard solution; for sulfur element, the sample is burned in oxygen flow to convert sulfur into sulfur dioxide, which is absorbed by a specific solution, and the sulfur content is calculated by titration; the oxygen content is calculated by subtracting the mass of carbon, hydrogen, nitrogen, sulfur and ash from the total mass of the coal sample, and finally the elemental analysis data of the coking coal is obtained by integrating these data.

[0083] Further, when the coal petrography analysis of the coking coal is performed, the coking coal sample is cut into small pieces, inlaid and fixed with resin, and after rough grinding, fine grinding and polishing, a coal rock polished section with smooth surface is prepared; the polished section is placed on the stage of a microscope, and under reflected light conditions, the area proportions of vitrinite group, inertinite group, exinite group and other coal macerals in the polished section are observed and counted one by one according to the classification standard of coal petrology, and the optical characteristics of each component are recorded, and finally the coal petrography analysis data of the coking coal is obtained according to the statistical results.

[0084] Further, when the process parameter analysis of the target coking process is performed, the type of the target coking process is determined, and during the normal operation of the process, the charging amount and charging speed during the charging process, the combustion chamber temperature variation curve and flue gas suction force during the heating process, the coking time and coke pushing time during the coking process and other parameters are continuously recorded by manual observation or special measuring equipment, the recorded parameters are arranged and verified to ensure that the data accurately reflect the actual situation of the process, and finally the process parameter data required by the coking process is obtained.

[0085] Further, based on the target coke quality requirements, representative samples are selected from the coke produced by the target coking process according to the quality requirements of the target coke. For cold strength, the coke samples are put into a rotating drum, the drum is rotated at a specified speed and time, and then the mass of coke of different particle sizes is sieved and weighed to calculate the crushing strength and abrasion resistance. For thermal properties, the coke samples are placed in a reaction furnace and reacted at a set temperature and carbon dioxide atmosphere, and the mass change and reaction rate of the coke before and after reaction are recorded to calculate the coke reactivity and post-reaction strength. The detection results are compared and analyzed with the target quality requirements, and finally the quality index data of the coking coal are obtained.

[0086] In summary, obtaining the coal quality characteristic data and process requirement data of the coking coal is the core basis for subsequent optimization of the coking coal, can solve the problem of insufficient coordination of single analysis of coal quality or independent adjustment of process in the prior art, provide complete data support for subsequent correlation comparison and sensitivity analysis, avoid optimization blindness, and can accurately anchor the core properties of the coal quality and the key requirements of the process, provide reliable data basis for subsequent screening of high-correlation candidate coal, identification of high-sensitivity indicators, determination of scientific coal blending ratio and optimization of washing and separation parameters, reduce experience decision deviation, avoid coke quality fluctuations caused by mismatch of coal and process from the source, and lay a solid data foundation for improving the precision of coking coal optimization, stabilizing coke quality and improving production efficiency.

[0087] S2, correlation comparison of the coal quality characteristic data and the process requirement data is performed to obtain correlation data of the coal quality characteristic data and the process requirement data.

[0088] In the embodiment of the present application, the correlation comparison of the coal quality characteristic data and the process requirement data is performed to obtain correlation data of the coal quality characteristic data and the process requirement data, which includes:

[0089] The coal quality characteristic data and the process requirement data are subjected to data alignment processing to obtain aligned coal quality characteristic data and aligned process requirement data.

[0090] The aligned coal quality characteristic data and the aligned process requirement data are subjected to correlation strength evaluation to obtain a correlation strength index.

[0091] The correlation strength index is subjected to data summarization to obtain the correlation data.

[0092] Specifically, a unified dimension for data alignment is determined, such as using coking production batches as the dimension. The coal quality characteristic data of each batch is matched one by one with the corresponding process requirement data of the batch. The number of entries of the two types of data in each batch is checked. If there are missing entries in the coal quality characteristic data, they are supplemented by querying the original coal quality test records of that batch. If there are redundant entries in the process requirement data, entries that are not related to that batch are removed. After processing, the aligned coal quality characteristic data and aligned process requirement data are obtained.

[0093] Furthermore, the data matching degree comparison method is used to evaluate the correlation strength. For each set of aligned data, it is checked whether the coal quality characteristic data meets the corresponding indicators in the process requirement data. If they meet, they are marked as high correlation; if they partially meet, they are marked as medium correlation; and if they do not meet, they are marked as low correlation. All the marking results are then converted into the corresponding correlation strength indicators to obtain the correlation strength indicators.

[0094] Furthermore, all the obtained correlation strength indicators are classified and organized according to the categories of coal quality characteristic data. The number of high, medium and low correlation strength indicators in each category is counted. The classification and statistical results are then integrated into a table containing data categories, correlation strength levels and corresponding quantities. This table is the correlation data, and the data summary is completed.

[0095] In general, this approach addresses the shortcomings of existing methods that only analyze coal quality or adjust processes independently without exploring the inherent relationship between the two. Through data alignment processing, it ensures that coal quality characteristic data and process requirement data (such as coal quality industrial analysis data and coking process parameter data) accurately correspond, avoiding correlation analysis bias caused by data misalignment. This provides a reliable data correlation basis for subsequent optimization and reduces the problem of mismatch between coal type selection and process requirements.

[0096] In general, the correlation strength assessment results in correlation strength indices that can screen out coal quality characteristics and process parameters that are highly correlated with the target process requirements. This provides a direct basis for subsequent sensitivity analysis (identifying key coal quality indicators and key process parameters) and candidate coal matching (screening highly correlated candidate coal types), avoiding blind optimization due to a lack of correlation basis.

[0097] In general, the correlation data formed by data aggregation objectively quantifies the degree of correlation between coal quality and process, replacing traditional experience-based decision-making, reducing subjective judgment errors, and making the subsequent determination of coal blending ratios and optimization of washing and beneficiation process parameters more in line with actual needs. This helps reduce the risk of coke quality fluctuations and lays a solid foundation for improving coking production efficiency and resource allocation efficiency.

[0098] S3. Based on the correlation data, perform sensitivity analysis on the coal quality characteristic data to obtain the sensitivity data of the coal quality characteristic data.

[0099] In the embodiment of the present application, the sensitivity analysis is performed on the coal quality characteristic data based on the correlation data, and sensitivity data of the coal quality characteristic data is obtained, which comprises:

[0100] Based on the correlation data, the indicators in the coal quality characteristic data are sorted, and key coal quality characteristic indicators with correlation strength higher than a preset threshold are obtained.

[0101] Based on the correlation data, the process parameters of the process requirement data are sorted, and key process parameters with correlation strength higher than a preset threshold are obtained.

[0102] The change amplitude of the key coal quality characteristic indicators is set, and the coal quality characteristic indicators with set change amplitudes are obtained.

[0103] The set change amplitudes of the coal quality characteristic indicators are set, and the key coal quality characteristic indicators with correlation strength higher than a preset threshold are obtained.

[0104] Based on the correlation data, the process parameters of the process requirement data are sorted, and key process parameters with correlation strength higher than a preset threshold are obtained.

[0105] The change amplitude of the key coal quality characteristic indicators is set, and the coal quality characteristic indicators with set change amplitudes are obtained.

[0106] The influence degree of the set change amplitudes of the coal quality characteristic indicators and the key process parameters is evaluated, and the sensitivity data of the coal quality characteristic data is obtained.

[0107] Specifically, the correlation strength indicators corresponding to each coal quality characteristic indicator are extracted from the correlation data, and the correlation strength indicators of each coal quality characteristic indicator are compared with the preset threshold one by one, and the coal quality characteristic indicators with correlation strength indicators higher than the preset threshold are screened out, and these screened indicators are classified and arranged, and the key coal quality characteristic indicators with correlation strength higher than the preset threshold are obtained.

[0108] Further, the correlation strength indicators corresponding to each process parameter are extracted from the correlation data, and the correlation strength indicators of each process parameter are compared with the preset threshold one by one, and the process parameters with correlation strength indicators higher than the preset threshold are screened out, and these screened parameters are arranged according to the process link, and the key process parameters with correlation strength higher than the preset threshold are obtained.

[0109] Further, the actual fluctuation of the key coal quality characteristic indicators in coking production is referred to, and specific change amplitudes are set for each key coal quality characteristic indicator, and the key coal quality characteristic indicators with set change amplitudes are recorded one by one, and the coal quality characteristic indicators with set change amplitudes are obtained.

[0110] Furthermore, the coal quality characteristic indicators with set variation ranges are respectively associated with key process parameters. The changes in the corresponding key process parameters are observed when the coal quality characteristic indicators with set variation ranges change. The degree of influence is determined according to the magnitude of the change in the key process parameters. All the results of the degree of influence are sorted out to obtain the sensitivity data of the coal quality characteristic data.

[0111] In this embodiment of the invention, the step of assessing the influence of the coal quality characteristic index with the set variation range on the key process parameters to obtain sensitivity data of the coal quality characteristic data includes:

[0112] Obtain the baseline value and variation range of the coal quality characteristic index with the set variation range;

[0113] Obtain the baseline values ​​of the key process parameters;

[0114] Based on historical or experimental data, a mathematical relationship model between the coal quality characteristics and the process parameters is established through multiple regression analysis. The mathematical relationship model is expressed as follows:

[0115]

[0116] In the formula, This refers to the serial number of the coal quality characteristic index. For constant terms, For the first Coal quality characteristic indicators The regression coefficients;

[0117] Based on the mathematical relationship model, the change in the key process parameters is calculated when the coal quality characteristics change;

[0118] The sensitivity coefficient of the coal quality characteristics to the key process parameters is calculated based on the sensitivity coefficient formula, which is:

[0119]

[0120] In the formula, Indicates the first The benchmark values ​​for each coal quality characteristic index, Indicates the first The variation range of individual coal quality characteristic indicators Indicates the first The baseline values ​​for key process parameters, Indicates the first The change in key process parameters Indicates the first The first coal quality characteristic index is related to the first The sensitivity coefficient of a key process parameter.

[0121] The sensitivity coefficients are aggregated to obtain the sensitivity data of the coal quality characteristic data.

[0122] Specifically, the initial standard value of each index is found as the reference value from the coal quality characteristic index related record with the set variation range, and the specific fluctuation range previously set for each index is extracted as the variation range, the corresponding relationship between the reference value and the variation range of each index is checked one by one to ensure no error or omission, and finally the reference value and the variation range in the coal quality characteristic index with the set variation range are obtained.

[0123] Further, the production or experimental batch corresponding to the coal quality characteristic index with the set variation range is found by consulting the historical operation record or process design file of the key process parameter, and the standard value of the key process parameter in the stable operation state is extracted from the batch record, and the validity of the value source is checked to ensure accuracy, and finally the reference value of the key process parameter is obtained.

[0124] Further, the historical data of coking production or experimental data obtained by carrying out experiments are collected, classified according to the coal quality characteristic index and the process parameter, and after excluding abnormal data, the mathematical relationship model between the coal quality characteristic index and the process parameter reflecting the corresponding law of the two is established by comparing the change relationship of the two groups.

[0125] Further, the specific value of each index in the coal quality characteristic index with the set variation range is substituted into the mathematical relationship model respectively, the corresponding process parameter value is calculated, and the difference between the calculated value and the reference value of the key process parameter is obtained, which is the change amount of the key process parameter when the coal quality characteristic index changes.

[0126] Further, the change amount of the key process parameter is divided by the reference value of the key process parameter to obtain the relative change proportion of the process parameter, the variation range of the coal quality characteristic index is divided by the reference value of the coal quality characteristic index to obtain the relative change proportion of the coal quality characteristic index, and the relative change proportion of the process parameter is divided by the relative change proportion of the coal quality characteristic index to obtain the sensitivity coefficient of the coal quality characteristic index to the key process parameter.

[0127] Specifically, in the mathematical relationship model, The source of is the key process parameter previously obtained with the correlation strength higher than the preset threshold, and the corresponding parameter is selected from the reference value of the key process parameter as ; The source of is the key coal quality characteristic index with the correlation strength higher than the preset threshold, and the corresponding index is selected from the key coal quality characteristic index as ; and The source is obtained by collecting coking production history data or experimental data, and through multiple regression analysis, specifically, by comparing each group of key coal quality characteristic indexes with corresponding key process parameters in the sorted historical or experimental data, analyzing the change law of both, and determining the constant term that can accurately reflect the relationship between the two and the regression coefficient .

[0128] Further, the significance of the relationship model is to quantitatively describe the linear correlation between the key coal quality characteristic indexes and the key process parameters, that is, when the key coal quality characteristic indexes change, the corresponding changes of the key process parameters can be determined through the model, wherein the constant term represents the basic value of the key process parameter without considering the influence of the key coal quality characteristic indexes, and the regression coefficient represents the degree of influence of each key coal quality characteristic index on the key process parameter.

[0129] Further, the trend of the mathematical relationship model is that when a certain key coal quality characteristic index increases within a set change range, if the corresponding regression coefficient is positive, the key process parameter will increase with the increase of the key coal quality characteristic index; if the corresponding regression coefficient is negative, the key process parameter will decrease with the increase of the key coal quality characteristic index; when all key coal quality characteristic indexes remain unchanged, the key process parameter remains unchanged at the value of the constant term.

[0130] Specifically, in the sensitivity coefficient formula, The source is the difference between the value of the key process parameter calculated after substituting the coal quality characteristic index with a set change range into the mathematical relationship model and the benchmark value of the key process parameter; The source is the benchmark value of the key process parameter obtained previously with a correlation strength higher than a preset threshold; The source is the specific fluctuation range set for the key coal quality characteristic index; The source is the initial standard value of the key coal quality characteristic index with a correlation strength higher than a preset threshold.

[0131] Further, the significance of the sensitivity coefficient formula is to measure the sensitivity of the th key coal quality characteristic index to the th key process parameter, and by calculating the ratio of the relative change proportion of the key process parameter to the relative change proportion of the key coal quality characteristic index, the sensitivity coefficient obtained can directly reflect the relative change amplitude of the key process parameter when the key coal quality characteristic index changes by one unit.

[0132] Further, the trend of the sensitivity coefficient formula is that if the sensitivity coefficient is positive, it means that the The key coal quality characteristic indicators and the first The changes in the key process parameters are consistent, meaning that when the key coal quality characteristic increases, the key process parameter also increases; if the sensitivity coefficient is negative, it indicates that the changes are in opposite directions, meaning that when the key coal quality characteristic increases, the key process parameter decreases; the larger the absolute value of the sensitivity coefficient, the stronger the change in the key process parameter. The first key coal quality characteristic index is related to the first The higher the sensitivity of a key process parameter, the lower the sensitivity.

[0133] In summary, this approach addresses the shortcomings of existing methods, which lack in-depth assessment of the impact of coal quality characteristics on process parameters and rely heavily on experience-based decision-making. By screening key coal quality characteristics and critical process parameters with correlation strength exceeding thresholds based on correlation data, and combining multiple regression models and sensitivity coefficient formulas, it quantitatively assesses the impact of changes in coal quality indicators on process parameters. This accurately identifies highly sensitive core coal quality indicators, avoids blind optimization due to the inability to pinpoint key influencing factors, replaces subjective experience-based judgment, and reduces errors.

[0134] In summary, when matching candidate coal types, sensitive data can be used to identify core indicators that are highly sensitive to key process parameters for coal type matching evaluation. When determining the coal blending ratio, the initial quality ratio can be fine-tuned based on the sensitivity coefficient to ensure that the coal blending is more in line with the process requirements. Sensitive indicators can also be referenced for the optimization of washing and beneficiation process parameters, and parameters such as separation density can be adjusted in a targeted manner to improve the accuracy of subsequent optimization steps.

[0135] In summary, by quantifying the sensitive relationship between coal quality indicators and process parameters, we can ensure that key coal quality indicators are under key control, avoid problems such as poor process adaptability and unstable coke quality caused by fluctuations in key indicators, reduce production risks caused by unreasonable plans, and lay the foundation for improving the utilization efficiency of coking coal resources and stabilizing coking production efficiency.

[0136] S4. Based on the correlation data and the sensitivity data, the candidate coal types are matched and adjusted to obtain the optimized coal type combination for coking coal.

[0137] In this embodiment of the invention, the step of matching and adjusting the candidate coal types based on the correlation data and the sensitivity data to obtain the optimized coal type combination for coking coal includes:

[0138] Based on the correlation data, candidate coal types with a high correlation strength with the target process requirements are selected from the candidate coal types to obtain a set of candidate coal types;

[0139] Based on the sensitivity data, core coal quality indicators that are highly sensitive to the key process parameters are identified from the candidate coal type set.

[0140] According to the benchmark level of the core coal quality index, a matching priority list of the coal types in the candidate coal type set is obtained by performing matching degree evaluation on the coal types in the candidate coal type set;

[0141] The preset number of coal types with high matching degrees are selected based on the matching priority list to obtain the optimized coal type combination of the coking coal.

[0142] Specifically, the correlation strength index of each candidate coal type with the target process requirement is extracted from the correlation data, and the correlation strength index of each candidate coal type is compared with a preset high correlation standard one by one, and candidate coal types with the correlation strength index reaching the high correlation standard are screened out. The screened coal types are uniformly arranged and recorded to obtain the candidate coal type set.

[0143] Further, the sensitivity coefficient of the coal quality index of each coal type in the candidate coal type set to the key process parameter is extracted from the sensitivity data, and the sensitivity coefficient of each coal quality index is compared with a preset high sensitivity standard, and the coal quality index with the sensitivity coefficient reaching the high sensitivity standard is screened out. The screened coal quality index is the core coal quality index with high sensitivity to the key process parameter.

[0144] Further, the benchmark level of the core coal quality index is determined first, and then the difference between the actual value of the core coal quality index of each coal type in the candidate coal type set and the benchmark level is checked one by one. The smaller the difference is, the higher the matching degree of the coal type is. The candidate coal types are sorted according to the matching degree from high to low to form a matching priority list of the coal types.

[0145] Further, the preset number of coal types to be combined is determined, and the corresponding number of coal types are selected from the matching priority list according to the priority from high to low. The selected coal types are matched and combined to obtain the optimized coal type combination of the coking coal.

[0146] In summary, the present method makes up for the defects of the existing method that only considers coal quality or process and lacks collaborative matching of the two. The candidate coal types with high correlation with the target process requirement are screened out based on the correlation data to avoid selecting coal types with poor process adaptability. The core coal quality index with high sensitivity to the key process parameter is identified based on the sensitivity data to ensure that the selected coal types can accurately respond to the process requirement and reduce the coke quality fluctuation problem caused by the mismatch between the coal type combination and the process requirement.

[0147] In summary, the present method discards the traditional method of selecting coal types relying on experience, forms a priority list through correlation strength screening, core index identification, and matching degree evaluation, selects coal types with high matching degree according to scientific standards, reduces subjective judgment errors, and makes the determination of the coal type combination have clear data support, thereby improving the reliability and rationality of the optimized coal type combination.

[0148] In general, the optimization of the coal type combination is the basis for subsequent determination of the coal blending ratio and optimization of the washing and separation process. The optimization of the coal type combination is formed based on the correlation and sensitivity data, can provide a strong adaptability of the coal type basis for the subsequent link, avoid the invalidation of the subsequent coal blending ratio calculation and washing and separation parameter adjustment due to the poor adaptability of the coal type itself, guarantee the coherence and effectiveness of the whole coking coal optimization process, and lay a coal type basis for improving the coking production efficiency.

[0149] S5, based on the correlation data, the sensitivity data and the optimized coal type combination, a coal blending ratio is determined, and a parameter optimization is performed on a washing and separation process, so as to obtain an optimized coal blending ratio and an optimized washing and separation process of the coking coal.

[0150] In the embodiment of the present application, the determination of the coal blending ratio based on the correlation data and the sensitivity data for the optimized coal type combination comprises,

[0151] The reference coal quality characteristic data of the coal types in the optimized coal type combination is extracted.

[0152] The core control index is extracted from the key coal quality characteristic indexes.

[0153] The reference values of the core control indexes of the coal types are compared with each other, and the quality proportion of each coal type in the optimized coal type combination is distributed according to the comparison result.

[0154] The optimized coal blending ratio is formed based on the quality proportion.

[0155] Specifically, the original reference data corresponding to each coal type in the optimized coal type combination is found out from the coal quality characteristic data obtained by the industrial analysis, the element analysis and the coal petrography analysis of the coking coal, including the reference values of the indexes such as the moisture, the ash content, the carbon content and the vitrinite group proportion of each coal type, and each reference data of each coal type is checked one by one to ensure that there is no omission, and finally the reference coal quality characteristic data of the coal types in the optimized coal type combination is extracted.

[0156] Further, the key coal quality characteristic indexes with the correlation strength higher than the preset threshold value obtained previously are reviewed, the indexes with high sensitivity to the key process parameters in the sensitivity data are combined, and the indexes with high sensitivity and belonging to the key coal quality characteristic indexes are screened out. These indexes are the core control indexes that need to be controlled, so that the core control indexes are extracted from the key coal quality characteristic indexes.

[0157] Further, the ideal value of the core control index is determined first, and then the benchmark value of each coal type in the optimized coal type combination is compared with the ideal value. The closer the benchmark value of a coal type to the ideal value, the higher the quality proportion of the coal type. For example, the difference between the benchmark value and the ideal value of a coal type is only 1%, and the difference between the benchmark value and the ideal value of another coal type is 5%. The quality proportion of the former is higher than that of the latter. The quality proportions of all coal types in the optimized coal type combination are obtained by completing the proportion allocation of all coal types.

[0158] Further, the quality proportion values of all coal types are counted, and the sum of the quality proportions of all coal types is calculated. If the sum is not 100%, the quality proportions of all coal types are fine-tuned while keeping the relative relationship between the quality proportions unchanged until the sum of the quality proportions of all coal types is 100%. The specific proportion values formed at this time are the optimized coal blending ratio. The optimized coal blending ratio is formed based on the quality proportions.

[0159] In the embodiment of the present application, the parameter optimization of the washing and sorting process comprises:

[0160] The expected value of the core control index under the optimized coal blending ratio is compared with the process requirement target value to obtain an index difference value.

[0161] The coal quality improvement target value to be achieved by the washing and sorting process is set according to the index difference value.

[0162] The separation density and the washing water flow parameter of the washing and sorting equipment are adjusted according to the coal quality improvement target value to obtain the optimized washing and sorting process.

[0163] Specifically, the expected values of the core control index are extracted from the coal quality analysis record corresponding to the optimized coal blending ratio, and the process requirement target value corresponding to the core control index is retrieved from the target coking process file. The expected value of each core control index is compared with the corresponding process requirement target value one by one. The specific value obtained by subtracting the process requirement target value of a single core control index from the expected value of the core control index is the index difference value.

[0164] Further, the improvement direction of the index difference value corresponding to each core control index is determined. If the index difference value is positive, it means that the expected value of the core control index is higher than the process requirement target value, and the coal quality improvement target value is set to reduce the index to the process requirement target value. If the index difference value is negative, it means that the expected value of the core control index is lower than the process requirement target value, and the coal quality improvement target value is set to increase the index to the process requirement target value. The improvement standards of all core control indexes are integrated to obtain the coal quality improvement target value to be achieved by the washing and sorting process.

[0165] Further, if the coal quality improvement target value requires more high-density impurities to be removed, the separation density of the washing and separating equipment is increased, and if more target coal quality particles need to be retained, the separation density is reduced; after the separation density is adjusted, if there are more impurities remaining, the flushing water flow is increased to enhance the flushing effect, and if the target coal quality is lost with the water flow, the flushing water flow is reduced; after adjustment, the core control indicators are detected by manual sampling to confirm that the coal quality improvement target value is achieved, and at this time, the process corresponding to the separation density and the flushing water flow parameters constitutes the optimized washing and separating process.

[0166] In the embodiment of the present application, the contribution degree model established based on historical data is used to calculate the contribution degree weight of each coal type in the optimized coal type combination to the core control indicator, which includes:

[0167] The reference values of the core control indicators of each coal type are sorted according to the numerical value;

[0168] According to the sorting result, each coal type is divided into three levels of high reference value coal type, medium reference value coal type and low reference value coal type;

[0169] According to the principle of allocating a higher quality proportion to the high reference value coal type, a medium quality proportion to the medium reference value coal type, and a lower quality proportion to the low reference value coal type, the preliminary quality proportion of each coal type is determined;

[0170] Based on the sensitivity coefficient of each coal type in the sensitivity data, the preliminary quality proportion is fine-tuned to obtain the final quality proportion of each coal type.

[0171] Specifically, from the reference coal quality characteristic data of each coal type in the previously extracted optimized coal type combination, the core control indicator reference value corresponding to each coal type is found, and all the reference values of the coal types are arranged in order from large to small in numerical value, and during the arrangement process, each coal type is ensured to correspond to its corresponding core control indicator reference value one by one without misplacement, and the reference values of the core control indicators of each coal type are sorted according to the numerical value.

[0172] Further, according to the above sorting result, all the coal types are divided into three segments, the first segment of the coal types in the front of the sorting is defined as the high reference value coal type, the second segment of the coal types in the middle of the sorting is defined as the medium reference value coal type, and the third segment of the coal types in the back of the sorting is defined as the low reference value coal type; if the total number of coal types cannot be divided by 3, the remaining coal types are classified into adjacent higher levels, for example, when the total number of coal types is 4, the first 2 are high reference value coal types, the middle 1 is a medium reference value coal type, and the last 1 is a low reference value coal type, and according to the sorting result, each coal type is divided into three levels.

[0173] Further, the preliminary quality proportion of the high reference value coal is set to 50%, the preliminary quality proportion of the medium reference value coal is set to 30%, and the preliminary quality proportion of the low reference value coal is set to 20%. If there are multiple coal types in the same grade, the preliminary quality proportion of the grade is evenly distributed to each coal type. For example, if there are two high reference value coals, the preliminary quality proportion of each coal is 25%; if there are three medium reference value coals, the preliminary quality proportion of each coal is 10%; and the preliminary quality proportion of each coal is determined according to the above principle.

[0174] Further, the sensitivity coefficient of each coal type to the key process parameter is extracted from the sensitivity data. For the coal type with a sensitivity coefficient higher than the average sensitivity coefficient of the group, the preliminary quality proportion is increased by 2%-5%. For the coal type with a sensitivity coefficient lower than the average level, the preliminary quality proportion is reduced by 2%-5%. After adjustment, the total of the quality proportions of all coal types is ensured to be 100%, and the final quality proportion of each coal type is obtained.

[0175] In summary, the problems of relying on experience and low precision in determining the coal blending ratio and adjusting the washing and separation parameters in the prior art are solved. By extracting the reference coal quality data of the optimized coal type combination, combining the core control indicators screened from the correlation data, comparing and distributing the quality proportion according to the index reference value, and fine-tuning the proportion by using the sensitivity data, the coal blending ratio is supported by data. At the same time, the difference between the expected value and the target value of the core control indicator is used to set the washing and separation improvement target, and the separation density and other parameters are adjusted accordingly, replacing subjective experience and reducing decision errors.

[0176] In summary, based on the previous correlation, sensitivity data and optimized coal type combination, the coal blending ratio can meet the requirements of the process on the core indicators, the washing and separation process can accurately improve the short board of coal quality, avoid the disconnection between coal blending or washing and separation and process requirements, reduce the coke quality fluctuations caused by substandard coal quality, and ensure the stable operation of the coking process.

[0177] In summary, the optimized coal blending ratio and washing and separation process output by this step provide a reliable scheme for subsequent effect verification, which can confirm the feasibility of the scheme in advance, avoid the risk of process adaptation difference and resource waste in actual production, improve the utilization efficiency of coking coal resources, and lay a foundation for efficient and low-cost operation of coking production.

[0178] S6, verifying the optimized coal type combination, the optimized coal blending ratio and the optimized washing and separation process to obtain the optimization effect data of the coking coal.

[0179] In the embodiment of the present application, the verification of the optimized coal type combination, the optimized coal blending ratio and the optimized washing and separation process to obtain the optimization effect data of the coking coal comprises:

[0180] The test coal is prepared according to the optimized coal type combination and the optimized coal blending ratio;

[0181] The test coal is prepared by using the optimized washing and separation process, and the test coke sample of the coking coal is obtained.

[0182] The test coke is obtained by coking test of the test coal sample.

[0183] The mechanical strength and post-reaction strength indexes of the test coke are detected, and the detection results are compared with the process requirement target value to obtain the optimization effect data.

[0184] Specifically, the corresponding coal type is selected from the optimized coal type combination, and the mass of each coal is weighed by a weighing device with precision up to standard according to the optimized blending ratio. The weighed coal types are poured into a mixing device and stirred until all the coal types are uniformly mixed. The test coal is obtained after the mixing is completed.

[0185] Further, the test coal is sent to a washing and separation device, the separation density and washing water flow rate are adjusted according to the optimized washing and separation process, and the device is started to allow the test coal to be separated and impurities to be removed and washed and purified. After the washing and separation is completed, the qualified coal material is collected to obtain the test coke sample of the coking coal.

[0186] Further, the test coke sample is loaded into a small-scale coking furnace, the temperature is controlled according to the heating curve of the target coking process, the furnace pressure is kept stable, the temperature is stopped after the set coking time is reached, and the coke is pushed out after cooling to room temperature to obtain the test coke.

[0187] Further, the test coke is taken to prepare a detection sample. In the mechanical strength detection, the sample is put into a rotating drum, screened and weighed after a specified rotation to calculate the crushing and wear resistance. In the post-reaction strength detection, the sample is put into a reaction furnace, and the strength is measured after reaction under the set conditions. The detection results are compared with the process requirement target value, the differences are recorded, and the optimization effect data are obtained by integration.

[0188] In general, the problem of lack of strict effect verification mechanism in the existing optimization technology is solved, avoiding the problems of poor process adaptation and resource waste in actual production due to the failure to judge the feasibility of the scheme in advance, reducing the cost and quality risk of coking production, and clearing the hidden dangers for the implementation of the scheme.

[0189] In general, by preparing the test coal, washing and separation treatment, coking test, detecting the mechanical strength and post-reaction strength indexes of the coke, and comparing with the process requirement target value, the optimization effect is presented in the form of data, replacing the traditional experience judgment, making the optimization effect more objective and measurable, and improving the credibility of the scheme.

[0190] In general, if the verification finds that the optimization effect does not meet the expectation, the deficiencies of the optimized coal type combination, blending ratio or washing and separation process can be traced back based on the detection data to provide a basis for subsequent precise adjustment, and to ensure that the optimization scheme continuously meets the coking production requirements.

[0191] In general, the optimization effect data verified finally can ensure that the optimized coking coal can stably produce coke meeting the process requirements, avoid coke quality fluctuation, and finally provide stability and high efficiency for coking production, and meet the needs of industrialization for efficient allocation of coal resources.

[0192] In several embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways.

[0193] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0194] Embodiments of the present application can acquire and process related data based on artificial intelligence technology. Artificial intelligence is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for optimizing coking coal based on the coupling of coal quality characteristics and process requirements, characterized in that, The method includes: S1. Obtain coal quality characteristics data and process requirements data for coking coal; S2. Perform a correlation comparison between the coal quality characteristic data and the process requirement data to obtain correlation data between the coal quality characteristic data and the process requirement data; S3. Based on the correlation data, perform sensitivity analysis on the coal quality characteristic data to obtain the sensitivity data of the coal quality characteristic data; S4. Based on the correlation data and the sensitivity data, the candidate coal types are matched and adjusted to obtain the optimized coal type combination for coking coal; S5. Based on the correlation data, the sensitivity data, and the optimized coal type combination, the coal blending ratio is determined, and the washing and beneficiation process parameters are optimized to obtain the optimized coal blending ratio and optimized washing and beneficiation process for the coking coal. S6. Verify the optimized coal type combination, the optimized coal blending ratio, and the optimized washing and beneficiation process to obtain the optimization effect data of the coking coal.

2. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The analysis of coking coal quality characteristics and coking process requirements includes: The coking coal was subjected to industrial analysis to obtain industrial analysis data of the coking coal; Elemental analysis was performed on the coking coal to obtain elemental analysis data of the coking coal; The coking coal was subjected to petrographic analysis to obtain the petrographic analysis data of the coking coal; The process parameters of the target coking process are analyzed to obtain the process parameter data required by the coking process. Based on the target coke quality requirements, coke quality analysis was conducted to obtain the quality index data of the coking coal.

3. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The step of comparing the correlation between the coal quality characteristic data and the process requirement data to obtain correlation data between the coal quality characteristic data and the process requirement data includes: The coal quality characteristic data and the process requirement data are aligned to obtain aligned coal quality characteristic data and aligned process requirement data. The correlation strength is evaluated between the aligned coal quality characteristic data and the aligned process requirement data to obtain a correlation strength index. The correlation strength index is aggregated to obtain the correlation data.

4. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The sensitivity analysis of the coal quality characteristic data based on the correlation data, to obtain the sensitivity data of the coal quality characteristic data, includes: Based on the correlation data, the indicators in the coal quality characteristic data are sorted to obtain key coal quality characteristic indicators with a correlation strength higher than a preset threshold. Based on the correlation data, the process parameters of the process requirement data are sorted to obtain key process parameters with a correlation strength higher than a preset threshold. The variation range of the key coal quality characteristic index is set to obtain the coal quality characteristic index with the set variation range. The coal quality characteristic indicators with the set change range are sorted with the correlation data to obtain key coal quality characteristic indicators with a correlation strength higher than a preset threshold. Based on the correlation data, the process parameters of the process requirement data are sorted to obtain key process parameters with a correlation strength higher than a preset threshold. The variation range of the key coal quality characteristic indicators is set to obtain coal quality characteristic indicators with set variation ranges. The influence of the coal quality characteristic index with the set variation range on the key process parameters is evaluated to obtain the sensitivity data of the coal quality characteristic data.

5. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 4, characterized in that, The assessment of the impact of the coal quality characteristic indicators with the set variation range on the key process parameters, to obtain sensitivity data of the coal quality characteristic data, includes: Obtain the baseline value and variation range of the coal quality characteristic index with the set variation range; Obtain the baseline values ​​of the key process parameters; Based on historical or experimental data, a mathematical relationship model between the coal quality characteristics and the process parameters is established through multiple regression analysis. The mathematical relationship model is expressed as follows: In the formula, This refers to the serial number of the coal quality characteristic index. For constant terms, For the first Coal quality characteristic indicators The regression coefficients; Based on the mathematical relationship model, the change in the key process parameters is calculated when the coal quality characteristics change; The sensitivity coefficient of the coal quality characteristics to the key process parameters is calculated based on the sensitivity coefficient formula, which is as follows: In the formula, Indicates the first The benchmark values ​​for each coal quality characteristic index, Indicates the first The variation range of individual coal quality characteristic indicators Indicates the first The baseline values ​​for key process parameters, Indicates the first The change in key process parameters Indicates the first The first coal quality characteristic index is related to the first Sensitivity coefficients of key process parameters; All sensitivity coefficients are summarized, and the summarized sensitivity coefficients are used as the sensitivity data of the coal quality characteristic data.

6. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The process of matching and adjusting candidate coal types based on the correlation data and the sensitivity data to obtain an optimized coal type combination for coking coal includes: Based on the correlation data, candidate coal types with a high correlation strength with the target process requirements are selected from the candidate coal types to obtain a set of candidate coal types; Based on the sensitivity data, core coal quality indicators that are highly sensitive to the key process parameters are identified from the candidate coal type set. Based on the benchmark level of the core coal quality indicators, the matching degree of the coal types in the candidate coal type set is evaluated to obtain a matching priority list of the coal types. Based on the matching priority list, a preset number of coal types with high matching degree are selected and combined to obtain the optimized coal type combination of the coking coal.

7. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The determination of the coal blending ratio for the optimized coal type combination based on the correlation data and the sensitivity data includes, Extract the baseline coal quality characteristic data of the coal types in the optimized coal type combination; Extract core control indicators from the key coal quality characteristic indicators; The benchmark values ​​of the core control indicators of each coal type are compared with each other, and the quality proportion of each coal type in the optimized coal type combination is allocated according to the comparison results. The optimized coal blending ratio is formed based on the aforementioned mass percentage.

8. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 7, characterized in that, The optimization of parameters for the washing and screening process includes: By comparing the expected values ​​of the core control indicators under the optimized coal blending ratio with the target values ​​of the process requirements, the difference values ​​of the indicators are obtained. Based on the differences in the aforementioned indicators, the target values ​​for coal quality improvement that the washing and processing technology needs to achieve are set. The separation density and flushing water flow rate parameters of the washing and beneficiation equipment are adjusted according to the coal quality improvement target value to obtain the optimized washing and beneficiation process.

9. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 8, characterized in that, The contribution weight of each coal type in the optimized coal type combination to the core control indicator is calculated based on the contribution model established using historical data, including: The benchmark values ​​of the core control indicators for each type of coal are sorted by numerical value. Based on the sorting results, each coal type is divided into three levels: high benchmark value coal type, medium benchmark value coal type, and low benchmark value coal type. The preliminary quality proportions for each coal type are determined according to the principle of allocating a higher quality proportion for coal types with high benchmark values, a medium quality proportion for coal types with medium benchmark values, and a lower quality proportion for coal types with low benchmark values. Based on the sensitivity coefficients of each coal type in the aforementioned sensitivity data, the preliminary quality proportions are fine-tuned to obtain the final quality proportions of each coal type.

10. The coking coal optimization method based on the coupling of coal quality characteristics and process requirements as described in claim 1, characterized in that, The process of verifying the optimized coal type combination, the optimized coal blending ratio, and the optimized washing and beneficiation process to obtain the optimization effect data of the coking coal includes: Test coal was prepared according to the optimized coal type combination and the optimized coal blending ratio; The optimized washing and beneficiation process was used to wash and beneficiate the test coal to obtain the test coal sample of the coking coal; The test coal sample was subjected to a coking test to obtain test coke; The mechanical strength and post-reaction strength of the test coke were tested, and the test results were compared with the target values ​​required by the process to obtain the optimization effect data.

Images