Prediction system for coal blending proportion of coal bunker

Abstract

The invention provides a coal blending proportion prediction system for a coal bunker, and relates to the technical field of coal blending combustion. A coal data acquisition module is used for acquiring the current coal sample storage condition in the coal bunker; the working condition data acquisition module is used for acquiring working condition data of the boiler; the historical scheme recording module is used for recording a historical coal blending scheme; the emission acquisition module is used for recording historical flue gas emission data; the model building module is used for building a plurality of coal blending models according to the coal storage condition and regularly updating the coal blending models; and the prediction module is used for performing adjustment based on the coal blending model according to actual production requirements to obtain a predicted coal blending scheme. According to the coal sample storage type, a plurality of different coal blending models are established and updated regularly, a reliable basic template is provided for the coal blending process, the stability of the coal blending effect is ensured, the requirement for personnel experience is reduced, and the coal blending scheme making speed and the scheme feasibility are improved. Through the intelligent prediction model, accurate prediction of the coal blending proportion is realized, and personal errors are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of coal blending and combustion, and in particular to a coal bunker coal blending ratio prediction system. Background Art

[0002] With the continuous growth of energy demand, coal-consuming industries such as thermal power generation have higher and higher requirements for coal utilization efficiency and environmental protection. The traditional coal blending method often uses a fixed ratio for mixing. Although this method is simple and easy to implement, it is difficult to adapt to the needs of different coal types and load changes, resulting in low energy utilization efficiency and large pollutant emissions. In order to solve these problems, modern coal-consuming industries such as thermal power generation have begun to adopt separate grinding and coal blending technology. Separate grinding and coal blending technology refers to grinding different types of coal separately in different coal mills, and then mixing them in a certain proportion according to needs to achieve the purpose of improving combustion efficiency and reducing pollutant emissions.

[0003] Traditional methods of calculating coal blending ratios mostly rely on manual experience, which has the problems of high experience requirements for staff, insufficient accuracy, slow response speed, etc., and it is difficult to meet the requirements of modern coal blending technology. Summary of the invention

[0004] The present invention provides a coal bunker coal blending ratio prediction system to solve the defects of the prior art that coal blending is performed by manual experience, has high requirements on the experience of the staff, insufficient accuracy, slow response speed, etc., and is difficult to meet the requirements of modern coal blending technology.

[0005] In one aspect, the present invention provides a coal bunker coal blending ratio prediction system, comprising:

[0006] The coal data acquisition module is used to obtain the current storage status of coal samples in the coal bunker;

[0007] The operating data collection module is used to collect the operating data of the boiler;

[0008] Historical plan recording module, used to record historical coal blending plans;

[0009] Emission collection module, used to record historical flue gas emission data;

[0010] Model building module, used to build several coal blending models according to coal storage conditions and update them regularly;

[0011] The prediction module is used to adjust the coal blending model according to actual production needs to obtain a predicted coal blending plan.

[0012] Preferably, the model building module includes:

[0013] Type determination unit, used to retrieve coal sample storage conditions;

[0014] A property determination unit, used to retrieve the coal sample characteristics of each coal sample;

[0015] A demand setting unit is used to generate an allowable range of production demand according to boiler conditions, and divide the allowable range of production demand into several production demand ranges, and generate a benchmark production demand within each production demand range;

[0016] A model generation unit generates a coal blending model based on benchmark production requirements;

[0017] Periodic update unit for periodic regeneration of coal blending model.

[0018] Preferably, the prediction module includes:

[0019] Demand analysis unit, used to determine actual coal blending requirements based on analysis of actual production needs;

[0020] A model calling unit is used to call the corresponding coal blending model according to the actual coal blending requirements;

[0021] A preliminary adjustment unit is used to make preliminary adjustments to the coal blending model according to actual coal blending requirements, historical coal blending plans and historical flue gas emission data, and obtain a basic coal blending ratio plan and corresponding predicted flue gas emission data;

[0022] The fine adjustment unit is used to adjust the basic coal blending ratio plan according to the boiler operating data to obtain a predicted coal blending plan.

[0023] Preferably, the model calling unit includes:

[0024] A range matching subunit is used to match the actual coal blending requirement with the production demand range of the coal blending model and determine the matched coal blending model;

[0025] The alarm sub-unit verifies the actual coal blending requirements when the coal blending model cannot be determined. When the actual coal blending requirements are within the allowable range of production requirements, a model missing alarm is issued. When the actual coal blending requirements are not within the allowable range of production requirements, an over-limit alarm is issued.

[0026] Preferably, the preliminary adjustment unit comprises:

[0027] Data calling subunit, used to call historical coal blending schemes and historical flue gas emission data;

[0028] The first adjustment subunit is used to adjust the coal blending model according to the historical coal blending plan and the actual coal blending requirements to obtain a basic coal blending ratio plan;

[0029] A data screening subunit is used to screen historical coal blending schemes based on the same coal blending model and historical flue gas emission data when the coal blending scheme is used according to the called coal blending model;

[0030] The emission prediction subunit is used to predict and calculate the predicted flue gas emission data of the basic coal blending ratio scheme based on the historical coal blending scheme and the historical flue gas emission data when the coal blending scheme is used.

[0031] Preferably, the fine adjustment unit comprises:

[0032] The emission correction subunit is used to correct the predicted flue gas emission data according to the boiler operating data to obtain the verified flue gas emission data;

[0033] The emission verification subunit, when the verified flue gas emission data meets the emission requirements, the basic coal blending ratio scheme is used as the predicted coal blending scheme; when the verified flue gas emission data does not meet the emission requirements, the predicted coal blending scheme is obtained after modifying the basic coal blending ratio;

[0034] The proportion adjustment subunit is used to modify the basic coal blending proportion plan according to the emission requirements to obtain the predicted coal blending plan.

[0035] Preferably, the model generation unit includes:

[0036] The coal type selection subunit is used to select the type of coal sample for establishing the coal blending model;

[0037] The proportion setting subunit is used to set the coal blending proportion corresponding to each selected coal sample type;

[0038] The verification subunit is used to verify whether the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements. If the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements, a coal blending model is generated based on the selected coal sample type and the corresponding proposed coal blending ratio. If the selected coal sample type and the corresponding proposed coal blending ratio do not meet the benchmark production requirements, the proposed coal blending ratio corresponding to each coal sample type is adjusted to generate a coal blending model.

[0039] Preferably, the coal type selection subunit includes:

[0040] Coal type classification block, used to classify each type of coal sample according to the coal type;

[0041] The priority sorting block is used to calculate the priority evaluation value of each type of coal sample and sort the coal samples in descending order according to the priority evaluation value;

[0042]

[0043] Among them, D i is the priority evaluation value of the i-th coal sample type; α iis the importance coefficient of coal cohesiveness corresponding to the type of coal sample of the i-th type; β i is the importance coefficient of coal volatile matter corresponding to the coal type of the i-th coal sample; i is the calculation reference value of the coal cohesiveness deviation corresponding to the type of coal sample of the i-th type; U i is the calculation reference value of the coal volatile matter deviation corresponding to the coal type of the i-th coal sample; N i is the actual value of the coal cohesiveness of the i-th coal sample; N0 is the calculated reference value of the coal cohesiveness of the i-th coal sample; H i is the actual value of the volatile matter of the i-th coal sample; H0 is the calculated reference value of the volatile matter of the i-th coal sample; h i is the actual value of coal ash content of the i-th coal sample type; h0 is the calculated reference value of coal ash content of the i-th coal sample type; S i is the actual value of the sulfur content of the coal of the i-th coal sample type; S0 is the calculated reference value of the sulfur content of the coal of the i-th coal sample type; ε i is the importance coefficient of the storage cost proportion corresponding to the type of coal of the i-th coal sample; μ i is the importance coefficient of the purchase cost corresponding to the type of coal of the i-th coal sample; C i1 is the storage cost proportion of the i-th coal sample type; C i2 is the purchase cost assessment value of the i-th coal sample type; k i is the daily storage cost of the i-th coal sample type per unit mass; T i is the storage time of the i-th coal sample type; θ i is the daily natural loss rate of the i-th coal sample type; C Mi is the price per unit mass of the i-th coal sample type when purchased; C Xi is the current price per unit mass of the i-th coal sample type; C Yi is the transportation cost per unit mass of the i-th coal sample; M i is the storage capacity of the i-th coal sample type; M i0 is the calculation benchmark value of the storage volume corresponding to the type of coal of the i-th coal sample; T0 is the unit storage duration; C0 is the calculation benchmark value of the coal purchase cost determined according to the market coal price;

[0044] The coal type selection block selects coal sample types in the required coal type in the order from the front to the back according to the order of the coal sample types within the coal type as the coal sample types for establishing the coal blending model.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] Several different coal blending models are established according to the types of coal sample storage and updated regularly, providing a reliable basic template for the coal blending process, ensuring the stability of the coal blending effect, reducing the requirements for personnel experience, and improving the speed of formulating coal blending plans and the feasibility of plans. Through intelligent prediction models, accurate prediction of coal blending ratios can be achieved to reduce human errors. The automated and intelligent coal blending process saves human resources and time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] In addition, in the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes, and do not specifically refer to the order or sequence, nor are they used to limit the present invention. They are only used to distinguish components or operations described with the same technical terms, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions and technical features between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0051] Example 1

[0052] The embodiment of the present invention provides a coal bunker coal blending ratio prediction system, comprising:

[0053] The coal data acquisition module is used to obtain the current storage status of coal samples in the coal bunker;

[0054] The operating data collection module is used to collect the operating data of the boiler;

[0055] Historical plan recording module, used to record historical coal blending plans;

[0056] Emission collection module, used to record historical flue gas emission data;

[0057] Model building module, used to build several coal blending models according to coal storage conditions and update them regularly;

[0058] The prediction module is used to adjust the coal blending model according to actual production needs to obtain a predicted coal blending plan.

[0059] In this embodiment, the coal sample storage status includes the types of stored coal samples and the storage quantity of each type of coal sample.

[0060] In this embodiment, the operating data of the boiler include: furnace temperature, exhaust gas temperature, excess air coefficient, and fly ash carbon content.

[0061] In this embodiment, the flue gas emission data includes: particulate matter content, sulfur dioxide content, and nitrogen oxide content.

[0062] The beneficial effects of the above technical solution are:

[0063] Several different coal blending models are established according to the types of coal sample storage, providing a reliable basic template for the coal blending process and updating it regularly, ensuring the stability of the coal blending effect, reducing the requirements for personnel experience, and improving the speed of formulating coal blending plans and the feasibility of plans. Through intelligent prediction models, accurate prediction of coal blending ratios can be achieved to reduce human errors. The automated and intelligent coal blending process saves human resources and time costs.

[0064] Example 2

[0065] Based on Example 1, the model building module includes:

[0066] Type determination unit, used to retrieve coal sample storage conditions;

[0067] A property determination unit, used to retrieve the coal sample characteristics of each coal sample;

[0068] A demand setting unit is used to generate an allowable range of production demand according to boiler conditions, and divide the allowable range of production demand into several production demand ranges, and generate a benchmark production demand within each production demand range;

[0069] A model generation unit generates a coal blending model based on benchmark production requirements;

[0070] Periodic update unit for periodic regeneration of coal blending model.

[0071] In this embodiment, the coal sample characteristics include: standard combustion value of each coal sample, purchase cost of each coal sample, standard volatile matter of each coal sample, standard adhesiveness of each coal sample, standard sulfur content of each coal sample and standard ash content of each coal sample.

[0072] In this embodiment, the benchmark production demand is a representative production demand within the corresponding production demand range, for example, the production demand with the highest frequency of use within the production demand range.

[0073] The beneficial effects of the above technical solution are:

[0074] By dividing the allowable range of production demand into several production demand ranges and generating a coal blending model based on the production demand range, the amount of coal blending models generated is greatly reduced, thereby reducing the system's hardware requirements, reducing configuration costs, and avoiding the waste of computing power caused by too many coal blending models. By regularly updating the coal blending model, it is ensured that the coal blending model matches the existing coal storage situation, thereby improving the practicability of the coal blending model.

[0075] Example 3

[0076] Based on embodiment 1 or 2, the prediction module includes:

[0077] Demand analysis unit, used to determine actual coal blending requirements based on analysis of actual production needs;

[0078] A model calling unit is used to call the corresponding coal blending model according to the actual coal blending requirements;

[0079] A preliminary adjustment unit is used to make preliminary adjustments to the coal blending model according to actual coal blending requirements, historical coal blending plans and historical flue gas emission data, and obtain a basic coal blending ratio plan and corresponding predicted flue gas emission data;

[0080] The fine adjustment unit is used to adjust the basic coal blending ratio plan according to the boiler operating data to obtain a predicted coal blending plan.

[0081] In this embodiment, the actual coal blending requirements include: the required combustion value per unit time, the allowable range of adhesiveness per unit mass of coal sample, the allowable range of volatile matter per unit mass of coal sample, the maximum allowable average sulfur content per unit mass of coal sample, and the maximum allowable average ash content per unit mass of coal sample.

[0082] The beneficial effects of the above technical solution are:

[0083] When predicting the coal blending ratio, the actual coal blending requirements are first determined based on production demand, which facilitates the matching of the coal blending model. The corresponding coal blending model is matched with the actual coal blending requirements to ensure the unique matching of the coal blending model. After that, the coal blending model is preliminarily and finely adjusted to ensure the reliability of the final output predicted coal blending plan.

[0084] Example 4

[0085] Based on any one of Embodiments 1-3, the model calling unit includes:

[0086] A range matching subunit is used to match the actual coal blending requirement with the production demand range of the coal blending model and determine the matched coal blending model;

[0087] The alarm sub-unit verifies the actual coal blending requirements when the coal blending model cannot be determined. When the actual coal blending requirements are within the allowable range of production requirements, a model missing alarm is issued. When the actual coal blending requirements are not within the allowable range of production requirements, an over-limit alarm is issued.

[0088] The beneficial effects of the above technical solution are:

[0089] When a suitable coal blending model cannot be matched during the matching process, the over-limit alarm and model missing alarm are executed respectively according to the reasons for the failure to match, so as to quickly determine the cause of the matching failure, thereby providing reliable data support for troubleshooting, improving the efficiency of troubleshooting, and avoiding the generation of coal blending ratio plans that exceed the working range of the boiler, ensuring the feasibility of the coal blending ratio plan.

[0090] Example 5

[0091] Based on any one of embodiments 1-4, the preliminary adjustment unit includes:

[0092] Data calling subunit, used to call historical coal blending schemes and historical flue gas emission data;

[0093] The first adjustment subunit is used to adjust the coal blending model according to the historical coal blending plan and the actual coal blending requirements to obtain a basic coal blending ratio plan;

[0094] A data screening subunit is used to screen historical coal blending schemes based on the same coal blending model and historical flue gas emission data when the coal blending scheme is used according to the called coal blending model;

[0095] The emission prediction subunit is used to predict and calculate the predicted flue gas emission data of the basic coal blending ratio scheme based on the historical coal blending scheme and the historical flue gas emission data when the coal blending scheme is used.

[0096] The beneficial effects of the above technical solution are:

[0097] When making preliminary adjustments to the coal blending model, by taking the historical coal blending scheme as a reference, the impact caused by the difference between the actual properties and theoretical properties of the coal sample is eliminated, thereby improving the accuracy of the coal blending ratio scheme. By using the historical flue gas emission data corresponding to the historical coal blending scheme to predict the flue gas emission data, the accuracy of the predicted flue gas emission data is ensured, thereby ensuring that the properties of the flue gas meet the emission requirements (or are within the exhaust gas treatment capacity), thereby improving the feasibility of the coal blending ratio scheme.

[0098] Example 6

[0099] Based on any one of embodiments 1-5, the fine adjustment unit includes:

[0100] The emission correction subunit is used to correct the predicted flue gas emission data according to the boiler operating data to obtain the verified flue gas emission data;

[0101] The emission verification subunit, when the verified flue gas emission data meets the emission requirements, the basic coal blending ratio scheme is used as the predicted coal blending scheme; when the verified flue gas emission data does not meet the emission requirements, the predicted coal blending scheme is obtained after modifying the basic coal blending ratio;

[0102] The proportion adjustment subunit is used to modify the basic coal blending proportion plan according to the emission requirements to obtain the predicted coal blending plan.

[0103] The beneficial effects of the above technical solution are:

[0104] By correcting the predicted flue gas emission data according to the operating data of the boiler to obtain the verified flue gas emission data, the accuracy of the verified flue gas emission data is further improved, thereby further improving the feasibility of the generated predicted coal blending plan.

[0105] Example 7

[0106] Based on any one of Embodiments 1-6, the model generation unit includes:

[0107] The coal type selection subunit is used to select the type of coal sample for establishing the coal blending model;

[0108] The proportion setting subunit is used to set the coal blending proportion corresponding to each selected coal sample type;

[0109] The verification subunit is used to verify whether the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements. If the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements, a coal blending model is generated based on the selected coal sample type and the corresponding proposed coal blending ratio. If the selected coal sample type and the corresponding proposed coal blending ratio do not meet the benchmark production requirements, the proposed coal blending ratio corresponding to each coal sample type is adjusted to generate a coal blending model.

[0110] Preferably, the coal type selection subunit includes:

[0111] Coal type classification block, used to classify each type of coal sample according to the coal type;

[0112] The priority sorting block is used to calculate the priority evaluation value of each type of coal sample and sort the coal samples in descending order according to the priority evaluation value;

[0113]

[0114] Among them, D i is the priority evaluation value of the i-th coal sample type; α i is the importance coefficient of coal cohesiveness corresponding to the type of coal sample of the i-th type; β i is the importance coefficient of coal volatile matter corresponding to the coal type of the i-th coal sample; i is the calculation reference value of the coal cohesiveness deviation corresponding to the type of coal sample of the i-th type; U i is the calculation reference value of the coal volatile matter deviation corresponding to the coal type of the i-th coal sample; N i is the actual value of the coal cohesiveness of the i-th coal sample; N0 is the calculated reference value of the coal cohesiveness of the i-th coal sample; H i is the actual value of the volatile matter of the i-th coal sample; H0 is the calculated reference value of the volatile matter of the i-th coal sample; h i is the actual value of coal ash content of the i-th coal sample type; h0 is the calculated reference value of coal ash content of the i-th coal sample type; S i is the actual value of the sulfur content of the coal of the i-th coal sample type; S0 is the calculated reference value of the sulfur content of the coal of the i-th coal sample type; ε i is the importance coefficient of the storage cost proportion corresponding to the type of coal of the i-th coal sample; μ i is the importance coefficient of the purchase cost corresponding to the type of coal of the i-th coal sample; C i1 is the storage cost proportion of the i-th coal sample type; C i2 is the purchase cost assessment value of the i-th coal sample type; k iis the daily storage cost of the i-th coal sample type per unit mass; T i is the storage time of the i-th coal sample type; θ i is the daily natural loss rate of the i-th coal sample type; C Mi is the price per unit mass of the i-th coal sample type when purchased; C Xi is the current price per unit mass of the i-th coal sample type; C Yi is the transportation cost per unit mass of the i-th coal sample; M i is the storage capacity of the i-th coal sample type; M i0 is the calculation benchmark value of the storage volume corresponding to the type of coal of the i-th coal sample; T0 is the unit storage duration; C0 is the calculation benchmark value of the coal purchase cost determined according to the market coal price;

[0115] The coal type selection block selects coal sample types in the required coal type in the order from the front to the back according to the order of the coal sample types within the coal type as the coal sample types for establishing the coal blending model.

[0116] In this embodiment, the types of coal include: coking coal, fat coal, gas coal, lean coal, lean coal and lean and lean coal.

[0117] The beneficial effects of the above technical solution are:

[0118] When generating a coal blending model, the type of coal sample to be used is determined first, and then the proportion of each type of coal sample is determined to ensure that the type of coal sample used matches the existing coal storage situation, thereby improving the practicality of the coal blending model. After the proposed coal blending ratio is generated, it is verified through forward calculation to improve the reliability of the coal blending model.

[0119] When selecting the type of coal samples, the priority of each type of coal sample is calculated to ensure that the selected coal sample type has excellent properties and excellent economy, thereby improving the economy of the predicted coal blending plan. When calculating the priority of each type of coal sample, the characteristics of the coal samples are ranked by considering the adhesion, volatile matter, ash and sulfur content of the coal samples, thereby ensuring that the properties of the coal samples ranked first are excellent. At the same time, the storage cost ratio and purchase cost of the corresponding coal samples are considered to ensure the economy of the coal samples. As the storage time of the coal sample increases, the priority of the coal sample will also increase accordingly, avoiding the performance degradation, excessive storage cost and increased risk caused by long-term storage of some coal samples.

[0120] By calculating the priority evaluation value for the coal sample types and then sorting them according to the coal types, an intuitive selection basis is provided for the selection of coal samples when establishing the coal blending model, which improves the efficiency and accuracy of coal sample selection and reduces the dependence of coal sample selection on personnel experience.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A coal bunker coal proportion prediction system, characterized in that: include: The coal data acquisition module is used to obtain the current storage status of coal samples in the coal bunker; The operating data collection module is used to collect the operating data of the boiler; Historical plan recording module, used to record historical coal blending plans; Emission collection module, used to record historical flue gas emission data; Model building module, used to build several coal blending models according to coal storage conditions and update them regularly; The prediction module is used to adjust the coal blending model according to actual production needs to obtain a predicted coal blending plan.

2. A coal bunker coal proportion prediction system according to claim 1, characterized in that: The model building module includes: Type determination unit, used to retrieve coal sample storage conditions; A property determination unit, used to retrieve the coal sample characteristics of each coal sample; A demand setting unit is used to generate an allowable range of production demand according to boiler conditions, and divide the allowable range of production demand into several production demand ranges, and generate a benchmark production demand within each production demand range; A model generation unit generates a coal blending model based on benchmark production requirements; Periodic update unit for periodic regeneration of coal blending model.

3. A coal bunker coal proportion prediction system according to claim 1, characterized in that: The prediction module includes: Demand analysis unit, used to determine actual coal blending requirements based on analysis of actual production needs; A model calling unit is used to call the corresponding coal blending model according to actual coal blending requirements; A preliminary adjustment unit is used to make preliminary adjustments to the coal blending model according to actual coal blending requirements, historical coal blending plans and historical flue gas emission data, and obtain a basic coal blending ratio plan and corresponding predicted flue gas emission data; The fine adjustment unit is used to adjust the basic coal blending ratio plan according to the boiler operating data to obtain a predicted coal blending plan.

4. A coal bunker coal proportion prediction system according to claim 3, characterized in that: The model calling unit includes: The range matching subunit is used to match the actual coal blending requirement with the production demand range of the coal blending model and determine the matched coal blending model; The alarm sub-unit verifies the actual coal blending requirements when the coal blending model cannot be determined. When the actual coal blending requirements are within the allowable range of production requirements, a model missing alarm is issued. When the actual coal blending requirements are not within the allowable range of production requirements, an over-limit alarm is issued.

5. A coal bunker coal proportion prediction system according to claim 3, characterized in that: The preliminary adjustment unit includes: Data calling subunit, used to call historical coal blending schemes and historical flue gas emission data; The first adjustment subunit is used to adjust the coal blending model according to the historical coal blending plan and the actual coal blending requirements to obtain a basic coal blending ratio plan; A data screening subunit is used to screen historical coal blending schemes based on the same coal blending model and historical flue gas emission data when the coal blending scheme is used according to the called coal blending model; The emission prediction subunit is used to predict and calculate the predicted flue gas emission data of the basic coal blending ratio scheme based on the historical coal blending scheme and the historical flue gas emission data when the coal blending scheme is used.

6. A coal bunker coal proportion prediction system according to claim 3, characterized in that: The fine adjustment unit includes: The emission correction subunit is used to correct the predicted flue gas emission data according to the boiler operating data to obtain the verified flue gas emission data; The emission verification subunit, when the verified flue gas emission data meets the emission requirements, the basic coal blending ratio scheme is used as the predicted coal blending scheme; when the verified flue gas emission data does not meet the emission requirements, the predicted coal blending scheme is obtained after modifying the basic coal blending ratio; The proportion adjustment subunit is used to modify the basic coal blending proportion plan according to the emission requirements to obtain the predicted coal blending plan.

7. A coal bunker coal proportion prediction system according to claim 2, characterized in that: The model generation unit includes: The coal type selection subunit is used to select the type of coal sample for establishing the coal blending model; The proportion setting subunit is used to set the coal blending proportion corresponding to each selected coal sample type; The verification subunit is used to verify whether the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements. If the selected coal sample type and the corresponding proposed coal blending ratio meet the benchmark production requirements, a coal blending model is generated based on the selected coal sample type and the corresponding proposed coal blending ratio. If the selected coal sample type and the corresponding proposed coal blending ratio do not meet the benchmark production requirements, the proposed coal blending ratio corresponding to each coal sample type is adjusted to generate a coal blending model.

8. A coal bunker coal proportion prediction system according to claim 7, characterized in that: The coal type selection subunit includes: Coal type classification block, used to classify each type of coal sample according to the coal type; The priority sorting block is used to calculate the priority evaluation value of each type of coal sample and sort the coal samples in descending order according to the priority evaluation value; Among them, D i is the priority evaluation value of the i-th coal sample type; α i is the importance coefficient of coal cohesiveness corresponding to the type of coal sample of the i-th type; β i is the importance coefficient of coal volatile matter corresponding to the coal type of the i-th coal sample; i is the calculation reference value of the coal cohesiveness deviation corresponding to the type of coal sample of the i-th type; U i is the calculation reference value of the coal volatile matter deviation corresponding to the coal type of the i-th coal sample; N i is the actual value of the coal cohesiveness of the i-th coal sample; N0 is the calculated reference value of the coal cohesiveness of the i-th coal sample; H i is the actual value of the volatile matter of the i-th coal sample; H0 is the calculated reference value of the volatile matter of the i-th coal sample; h i is the actual value of coal ash content of the i-th coal sample type; h0 is the calculated reference value of coal ash content of the i-th coal sample type; S i is the actual value of the sulfur content of the coal of the i-th coal sample type; S0 is the calculated reference value of the sulfur content of the coal of the i-th coal sample type; ε i is the importance coefficient of the storage cost proportion corresponding to the type of coal of the i-th coal sample; μ i is the importance coefficient of the purchase cost corresponding to the type of coal of the i-th coal sample; C i1 is the storage cost proportion of the i-th coal sample type; C i2 is the purchase cost assessment value of the i-th coal sample type; k i is the daily storage cost of the i-th coal sample type per unit mass; T i is the storage time of the i-th coal sample type; θ i is the daily natural loss rate of the i-th coal sample type; C Mi is the price per unit mass of the i-th coal sample type when purchased; C Xi is the current price per unit mass of the i-th coal sample type; C Yi is the transportation cost per unit mass of the i-th coal sample; M i is the storage capacity of the i-th coal sample type; M i0 is the calculation benchmark value of the storage volume corresponding to the type of coal of the i-th coal sample; T0 is the unit storage duration; C0 is the calculation benchmark value of the coal purchase cost determined according to the market coal price; The coal type selection block selects coal sample types in the required coal type in the order from the front to the back according to the order of the coal sample types within the coal type as the coal sample types for establishing the coal blending model.

Images