A raw material proportioning optimization control method and system for cement production

Abstract

The present application relates to the field of cement production raw material proportioning, and specifically discloses a raw material proportioning optimization control method and system for cement production, comprising: determining a three-rate value interval according to the cement variety, calculating a feasible proportioning scheme set based on the raw material oxide content; constructing a mixed type easy-to-burn prediction model to select the optimal proportioning; monitoring the kiln condition parameters through small-scale trial burning, dynamically correcting the three-rate value and adjusting the proportioning; evaluating the clinker quality after trial burning, and if the quality meets the standard, storing the proportioning scheme, otherwise, recycling optimization. Through the three-rate value quantitative control, kiln condition real-time feedback and closed-loop verification mechanism, the present application solves the problems of low proportioning accuracy, response lag and unstable clinker quality of the traditional method, significantly improves the calcination efficiency and cement performance, and is suitable for various cement production scenes such as Portland cement, slag cement, etc.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cement production raw material proportioning, and relates to a raw material proportioning optimization control method and system for cement production. BACKGROUND

[0002] In the cement production process, the optimization control of raw material proportioning directly affects the clinker quality and energy efficiency. The traditional method relies on manual experience to adjust the proportioning, which has the following shortcomings: (1) insufficient precision: existing technologies, such as the Chinese patent with publication number CN1408081A, disclose a system and method for adjusting raw material mixing proportioning controller, which uses fuzzy logic and genetic algorithm to dynamically adjust the proportioning, but lacks quantitative correlation analysis of cement three rate values, resulting in difficulty in accurately matching the calcination requirements of the proportioning scheme.

[0003] (2) poor real-time performance: existing technologies, such as the existing Chinese patent with publication number CN111552255A, disclose a cement production quality online detection system, which can monitor production data, but does not dynamically correct the proportioning in combination with the kiln condition parameters, and cannot timely respond to process fluctuations in the calcination process.

[0004] (3) closed loop missing: existing technologies are mostly limited to theoretical simulation or single detection, lacking a closed loop mechanism of "trial burning-evaluation-adjustment", resulting in long proportioning optimization period and unstable clinker quality. SUMMARY

[0005] In view of this, in order to solve the problems raised in the background art, a raw material proportioning optimization control method and system for cement production are proposed.

[0006] The technical solution adopted by the present application to solve its technical problems is as follows: in the first aspect, the present application provides a raw material proportioning optimization control method for cement production, comprising the following steps: S1: determining the three rate value interval according to the cement production requirements, the three rate values including the lime saturation coefficient, the silicon rate and the aluminum rate, calculating the feasible proportioning scheme set satisfying the three rate value interval based on the types of raw materials and the contents of main oxides in each raw material.

[0007] S2: constructing a mixed type easy burning prediction model, calculating the easy burning raw material proportioning through the model according to the expected easy burning performance, screening the proportioning scheme matching or having the minimum deviation degree with the easy burning raw material proportioning and recording it as the set raw material proportioning.

[0008] S3: performing small-scale trial burning according to the set raw material proportioning and monitoring the kiln condition parameters, correcting the three rate values and dynamically adjusting the set raw material proportioning according to the kiln condition parameter deviation, and recording the adjusted raw material proportioning.

[0009] S4: After the trial burning is finished, the clinker sample is evaluated in quality, the raw material ratio feasibility is verified based on the evaluation result, if feasible, the current raw material ratio and its associated information are bound and stored, otherwise, the raw material ratio is adjusted according to the quality deviation, and the step S3 is returned for secondary trial burning.

[0010] In the second aspect, the application further provides a raw material batching optimization control system for cement production, comprising: a feasible ratio acquisition module: determining a three rate value interval according to the cement production requirements, the three rate values including a lime saturation coefficient, a silicon rate and an aluminum rate, calculating a feasible ratio scheme set meeting the three rate value interval based on the raw material types and the content of main oxides in each raw material.

[0011] A ratio screening module: constructing a mixed type easy burning prediction model, calculating an easy burning raw material ratio through the model according to the expected easy burning performance, screening a ratio scheme matching the easy burning raw material ratio or having the minimum deviation degree and recording the ratio scheme as a set raw material ratio.

[0012] A trial burning adjustment ratio module: performing small-scale trial burning according to the set raw material ratio and monitoring kiln condition parameters, correcting the three rate values and dynamically adjusting the set raw material ratio according to the kiln condition parameter deviation, and recording the adjusted raw material ratio.

[0013] A ratio feasibility verification module: evaluating the clinker sample in quality after the trial burning is finished, verifying the raw material ratio feasibility based on the evaluation result, if feasible, binding and storing the current raw material ratio and its associated information, otherwise, returning to the trial burning adjustment ratio module for secondary trial burning after adjusting the raw material ratio according to the quality deviation.

[0014] Compared with the prior art, the application has the following beneficial effects: 1. The application generates a feasible ratio scheme set through three rate value interval constraints and oxide conservation equations, and screens the optimal ratio by combining a mixed type easy burning prediction model, thereby improving the matching accuracy of the ratio and the calcination performance.

[0015] 2. The application corrects the three rate values based on the key parameters such as the calcination temperature in the kiln, the kiln skin thickness, the kiln tail concentration and the like in real time, realizes dynamic optimization of the ratio, and solves the response lag problem of the traditional method.

[0016] 3. The application forms a closed loop feedback through small-scale trial burning and clinker quality evaluation, automatically adjusts the ratio and performs secondary trial burning when the indicators such as the clinker strength and the setting time do not meet the standards, and ensures that the indicators such as the clinker strength and the setting time meet the standards stably.

[0017] 4. The application binds and stores the optimized ratio and the process parameters, constructs a reusable production scheme library, and reduces the trial and error cost of subsequent similar production. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0019] Figure 1 The method flowchart of the present application.

[0020] Figure 2 The system module connection diagram of the present application.

[0021] Figure 3 The workflow diagram of step S3 of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present application.

[0023] Please refer to Figure 1 and Figure 3 , the first aspect of the present application provides a raw material batching optimization control method for cement production, comprising the following steps: S1: determining a three-ratio value interval according to the cement production requirements, the three-ratio values including a lime saturation coefficient, a silicon ratio and an aluminum ratio, and calculating a feasible batching scheme set meeting the three-ratio value interval based on the types of raw materials and the contents of main oxides in each raw material.

[0024] Exemplarily, the specific analysis process of the step S1 is as follows: S1.1, obtaining the variety of cement to be produced according to the cement production requirements, and calling the three-ratio value interval corresponding to the cement variety from the database, the three-ratio values including a lime saturation coefficient, a silicon ratio and an aluminum ratio.

[0025] S1.2, obtaining the types of raw materials used for production, and determining the contents of main oxides in each raw material through chemical analysis, the main oxides including , , , .

[0026] S1.3, obtaining the combined values of multiple groups of three-ratio values according to the three-ratio value interval, inputting the combined values of each group of three-ratio values and the contents of main oxides of each raw material into a preset raw material batching calculation model, and solving to obtain a feasible batching scheme set meeting the three-ratio value interval, the raw material batching calculation model being an equation set based on oxide conservation and three-ratio value definition.

[0027] It should be noted that different varieties of cement have different requirements for the mineral composition of clinker, and the tri-ratio value directly determines the mineral composition, so the tri-ratio value is divided into a basic interval according to the variety. The cement variety includes but is not limited to Portland cement, slag Portland cement, low-heat cement, etc. In a specific embodiment, the tri-ratio value range corresponding to Portland cement is: lime saturation factor: 0.88-0.96; silicon ratio: 2.0-3.0; aluminum ratio: 1.5-3.5. The tri-ratio value range corresponding to slag Portland cement is: lime saturation factor: 0.88-0.92; silicon ratio: 2.0-2.8; aluminum ratio: 1.5-2.5. The tri-ratio value range corresponding to low-heat cement is: lime saturation factor: 0.75-0.85; silicon ratio: 2.5-3.5; aluminum ratio: 1.0-1.5.

[0028] It should be noted that the tri-ratio value interval corresponding to each cement variety stored in the database is pre-set based on historical production data or industry standards, and can be dynamically updated and optimized according to actual production data.

[0029] It should be noted that the core basis of cement raw material ratio is the tri-ratio value of the raw material, i.e. the lime saturation factor, the silicon ratio and the aluminum ratio. The lime saturation factor is to ensure that calcium silicate is fully formed in the clinker and the free calcium oxide content is qualified. The silicon ratio is to balance the ratio of silicate minerals and flux minerals to ensure smooth calcination and strength performance. The aluminum ratio is to control the viscosity of the liquid phase within a suitable range to ensure stable calcination operation and qualified cement performance. Reasonable tri-ratio value combination can ensure smooth clinker calcination and stable quality, and ultimately make the cement have good strength, stability, setting time and other properties.

[0030] It should be noted that the lime saturation factor ( ) reflects the ratio between calcium oxide, silicon dioxide, aluminum trioxide and iron trioxide in the cement clinker, and embodies the saturation degree of calcium silicate in the clinker. If it is too large, the free calcium oxide content in the clinker will increase significantly, resulting in poor cement stability, at the same time, the clinker calcination difficulty increases, requiring higher firing temperature and longer holding time, which is easy to overburn, reducing clinker quality and increasing energy consumption; if it is too small, it means that the content of calcium silicate is insufficient, which will reduce the early and late strength of the cement, and cannot meet the use requirements.

[0031] It should be noted that the silicon ratio ( ) represents the proportion of the sum of , , in the clinker, and reflects the relative content of silicate minerals and flux minerals. If it is Excessively large, excessive silicate mineral content, and insufficient fluxing mineral, will result in a decrease in the liquid phase amount during clinker calcination, difficulty in burning, and easy occurrence of green burning, which reduces the grindability and strength development of clinker, and at the same time, the cement hydration speed is slow and the early strength is low; if It is too small, and the fluxing mineral is excessive, and the liquid phase amount is too large, which easily leads to clinker clumping, sticking to the kiln, and other problems during calcination, affecting the kiln operation, and the cement setting time is too fast, and the strength development is insufficient.

[0032] It should be noted that the aluminum rate represents the ratio of in the clinker , which mainly affects the relative content of and in the fluxing mineral and the viscosity of the liquid phase during calcination. If is too large, the liquid phase viscosity is high, and the material flowability is poor, which is not conducive to heat transfer and reaction, and easily leads to incomplete clinker calcination, and at the same time, the cement setting time is shortened, the hydration heat is increased, and the sulfate resistance is reduced; if is too small, the liquid phase viscosity is low, and the material is easy to flow, which may cause the kiln to ring and other faults, and the early strength development of the cement is slow and the strength is low.

[0033] In one specific embodiment, the types of raw materials used for cement production are limestone, clay, iron powder, and silica.

[0034] It should be noted that the main oxides refer to the oxides involved in the three rate values, which are determined by the definition of the three rate values.

[0035] It should be noted that the content of the main oxides, i.e., the mass fraction, is expressed in percentage form.

[0036] In this embodiment, the present application generates a feasible matching scheme set through the three rate value interval constraint and the oxide conservation equation, and combines a mixed type easy-to-burn prediction model to select the optimal matching, thereby improving the matching accuracy of the matching and calcination performance.

[0037] Exemplarily, the specific analysis process of step S1.3 is as follows: S1.3.1, determining multiple sets of three rate value combinations: based on the three rate value interval, multiple sets of combination values of the lime saturation coefficient , the silicon rate , and the aluminum rate are selected.

[0038] S1.3.2, defining the raw material composition parameters: the contents of , , , , in the first raw material are respectively denoted as , wherein .

[0039] S1.3.3, set the ratio constraint: the ratio of various raw materials meet: , .

[0040] S1.3.4, calculate the total content of oxides: calculate the total content of , , , in raw materials by the following formula , , , .

[0041] .

[0042] S1.3.5, establish equations according to the three rate value definition: .

[0043] S1.3.6, multi-solution: for each set of combination value, solve the constraint conditions and equation set of steps S1.3.3-S1.3.5 simultaneously to obtain the corresponding raw material ratio scheme.

[0044] S1.3.7, result screening: screen all raw material ratio schemes that meet the constraints in step S1.3.3 as a set of feasible ratio schemes that meet the three rate value interval.

[0045] It should be noted that the definition of lime saturation coefficient is: , the coefficient in the formula is the conversion result of oxide molar mass, 1.65 is the molar ratio coefficient of , 2.8 is the molar ratio coefficient of , and 0.35 is the molar ratio coefficient of . The definition of silicon rate is: . The definition of aluminum rate is: .

[0046] It should be noted that the number of unknowns in the equation set is consistent with the number of equations, that is, the number of raw materials is equal to the number of equations.

[0047] S2: build a mixed type easy burning prediction model, according to the expected easy burning performance, calculate the easy burning raw material ratio through the model, screen the ratio scheme matched with the easy burning raw material ratio or the minimum deviation degree and record it as the set raw material ratio.

[0048] Illustratively, the specific analysis process of step S2 is: S2.1, constructing a mixed easy burning prediction model: based on historical cement production data, a mixed easy burning prediction model is established, the input of the model includes raw material information, process parameters and raw material ratio, and the output is easy burning performance.

[0049] S2.2, obtaining easy burning raw material ratio: input the raw material information, process parameters and expected easy burning performance of the cement to be produced into the model, and calculate the corresponding easy burning raw material ratio.

[0050] S2.3, ratio matching verification: find a matching ratio scheme in the set of feasible ratio schemes.

[0051] If there is a matching scheme, mark the raw material ratio in the ratio scheme as the set raw material ratio, otherwise go to S2.4.

[0052] S2.4, ratio deviation analysis: calculate the deviation degree of each feasible ratio scheme and the easy burning raw material ratio, and select the ratio scheme with the smallest deviation degree, and mark the raw material ratio in the scheme as the set raw material ratio.

[0053] It should be noted that the expected easy burning performance is set according to actual needs.

[0054] It should be noted that the method for calculating the three rate value corresponding to the easy burning raw material ratio refers to the specific analysis process of step S1.

[0055] It should be noted that screening the ratio scheme with the smallest deviation degree from the easy burning raw material ratio can optimize the raw material ratio to adapt to the burning characteristics of the kiln, thereby improving the calcination efficiency.

[0056] Illustratively, the specific process of constructing a mixed easy burning prediction model in step S2 is: extracting historical cement production data from the database, including raw material information, process parameters, raw material ratio and easy burning performance evaluation index, the raw material information includes raw material type, chemical composition, particle size distribution and crystal morphology, the process parameters include kiln temperature, kiln speed, coal heat value and preheater outlet temperature, and the easy burning performance evaluation index includes firing temperature, free calcium content, liquid phase amount and energy consumption.

[0057] According to the preset weight, the easy burning performance evaluation index is weighted and fused to calculate the easy burning performance value.

[0058] Based on the historical data, a training data set is constructed, and a mixed easy burning prediction model is established by using a machine learning algorithm, with the input being raw material information, process parameters and raw material ratio, and the output being easy burning performance value.

[0059] It should be noted that the machine learning algorithm includes but is not limited to random forest, neural network, genetic algorithm, etc.

[0060] It should be noted that the mixed easy-burning prediction model is used to dynamically optimize the cement raw material ratio to improve the easy-burning property, and the core is to quantify the influence of different raw material combinations on the calcination process through algorithm, and find the ratio scheme with the minimum deviation degree.

[0061] It should be noted that the raw material ratio with good easy-burning property can be selected through the batching software simulation.

[0062] S3: Small-scale trial burning is carried out according to the set raw material ratio, and the kiln condition parameters are monitored, the three rate values are corrected according to the kiln condition parameter deviation, and the set raw material ratio is dynamically adjusted, and the adjusted raw material ratio is recorded.

[0063] Exemplarily, the specific analysis process of the step S3 is: S3.1, trial burning implementation: small-scale trial burning is carried out according to the set raw material ratio, and the initial three rate values are recorded.

[0064] S3.2, kiln condition parameter monitoring: the kiln calcination temperature is collected through the high-temperature infrared thermometer.

[0065] The kiln shell surface temperature is measured by the infrared thermal imager, and the kiln skin thickness is calculated based on the set kiln skin thickness-tube temperature relationship model.

[0066] The kiln tail concentration is detected by the infrared gas analyzer.

[0067] S3.3, deviation analysis: the measured value of the kiln condition parameter is compared with the corresponding set value to obtain the deviation, and if any deviation exceeds the preset threshold, S3.4 is entered.

[0068] S3.4, three rate value correction: based on the set kiln calcination temperature-lime saturation coefficient, kiln skin thickness-silicon rate, kiln tail concentration-aluminum rate correction model, the lime saturation coefficient, silicon rate and aluminum rate are respectively corrected according to the kiln calcination temperature deviation, kiln skin thickness deviation, concentration deviation.

[0069] S3.5, boundary check: if the corrected three rate value exceeds the corresponding interval, the interval boundary value is taken as the final value.

[0070] S3.6, ratio adjustment: the raw material ratio is recalculated based on the final three rate value, and is updated as the set raw material ratio and recorded.

[0071] It should be noted that the initial three rate value is the three rate value corresponding to the set raw material ratio.

[0072] It should be noted that the high-temperature infrared thermometer lens is aligned with the kiln area through the observation hole for temperature collection, and the mean value of the collected multiple groups of temperature data is calculated to obtain the kiln calcination temperature.

[0073] It should be noted that the infrared gas analyzer installed through the kiln tail smoke chamber detects the concentration of gas in the kiln tail and is recorded as the kiln tail concentration.

[0074] It should be noted that if the calcination temperature in the kiln is insufficient, the lime saturation coefficient is reduced to reduce the calcination pressure caused by excessive free calcium; if the calcination temperature in the kiln is too high, the lime saturation coefficient is increased, and the content is increased to improve the strength.

[0075] It should be noted that if the kiln skin is too thick, it indicates that the liquid phase is too much and the silicon rate is too low, and the silicon rate needs to be increased; if the kiln skin is too thin, it indicates that the liquid phase is insufficient and the silicon rate is too high, and the silicon rate needs to be reduced.

[0076] It should be noted that when the kiln tail concentration is higher than the set value, the aluminum rate correction is triggered, and the kiln tail concentration is too high, the aluminum rate is reduced to improve the combustion condition.

[0077] It should be noted that the calcination temperature in the kiln, the thickness of the kiln skin, and the kiln tail concentration are the core influencing factors of the three rate values, and through real-time monitoring, the process deviation can be accurately positioned to realize directional correction of the three rate values. These three parameters have the characteristics of process criticality, monitoring convenience and control specificity, and are the optimal solution to balance the quality control cost and effect.

[0078] In this embodiment, the present application corrects the three rate values in real time based on key parameters such as the calcination temperature in the kiln, the thickness of the kiln skin, and the kiln tail concentration, realizes dynamic optimization of the proportioning, and solves the problem of response lag in the traditional method.

[0079] Exemplarily, the specific process of obtaining the thickness of the kiln skin in the step S3.2 is as follows: fitting the thickness of the kiln skin actually measured at the historical kiln stop and the corresponding kiln cylinder temperature data to obtain a relationship model of the thickness of the kiln skin-cylinder temperature.

[0080] The surface of the kiln cylinder is scanned by an infrared thermal imager, temperature data of each measuring point is obtained, and a temperature distribution thermal map is generated.

[0081] According to the relationship model of the thickness of the kiln skin-cylinder temperature, the temperature of each measuring point is converted into the corresponding thickness of the kiln skin, and the thickness distribution of the kiln skin is obtained.

[0082] Based on the thickness distribution of the kiln skin, the thickness of the kiln skin is calculated and output according to a preset rule.

[0083] In one specific embodiment, the thickness of the kiln skin corresponding to each measuring point is calculated by mean value to obtain the final thickness of the kiln skin.

[0084] ​Exemplarily, the specific analysis process of step S3.4 is as follows: based on historical production data, the calcination temperature in the kiln and its corresponding lime saturation coefficient, the thickness of the kiln skin and its corresponding silicon rate, the concentration of the kiln tail and its corresponding aluminum rate are extracted respectively according to the single variable principle.

[0085] By using the regression analysis method, the correction model of the calcination temperature in the kiln-lime saturation coefficient, the correction model of the thickness of the kiln skin-silicon rate, and the correction model of the concentration of the kiln tail-aluminum rate are established respectively.

[0086] The real-time monitored deviation of the calcination temperature in the kiln, the deviation of the thickness of the kiln skin, and the deviation of the concentration of the kiln tail are input into the corresponding correction model, and the correction amount of the lime saturation coefficient, the silicon rate, and the aluminum rate is calculated.

[0087] The correction amount is added to the original value, and the corrected three rate value result is output.

[0088] S4: After the trial burning is completed, the quality of the clinker sample is evaluated, the feasibility of the raw material ratio is verified based on the evaluation result, if feasible, the current raw material ratio and its associated information are bound and stored, otherwise the raw material ratio is adjusted according to the quality deviation and the trial burning is returned to step S3 for the second time.

[0089] Exemplarily, the specific analysis process of step S4 is as follows: after the trial burning is completed, the clinker sample is obtained.

[0090] The quality indicators of the clinker sample are detected, including the strength, the vertical height weight, and the setting time, and the production quality of the clinker sample is evaluated according to the preset mapping relationship between the quality indicators and the production quality.

[0091] If the production quality reaches the set expected value, the current raw material ratio and its associated information are bound and stored, and the associated information includes the cement production requirements and the kiln condition parameters.

[0092] If the expected value is not reached, the raw material ratio is adjusted according to the deviation of the production quality and the expected value, and the trial burning is returned to step S3 for the second time.

[0093] It should be noted that the three rate values are corrected by analyzing the relationship between the production quality deviation and the three rate values, and the raw material ratio is recalculated based on the corrected three rate values and then fine-tuned.

[0094] It should be noted that the effectiveness of the ratio is verified by detecting the quality indicators of the clinker and comparing them with the preset standard, and if the standard is met, the optimized ratio and the associated process parameters are stored, which is beneficial to establish a reusable production scheme, and if the standard is not met, the ratio is adjusted and the trial burning is restarted. This mechanism not only guarantees the quality verification before production and avoids production risks, but also continuously improves the ratio scheme through closed-loop iteration, and at the same time accumulates valuable process knowledge base. ​​​

[0095] In the embodiment, the application forms a closed-loop feedback through small-scale trial burning and clinker quality evaluation, automatically adjusts the proportioning when it does not meet the standard and performs secondary trial burning, to ensure that the clinker strength, setting time and other indicators meet the standard.

[0096] In the embodiment, the application binds the optimized proportioning and process parameters, and constructs a reusable production scheme library to reduce the trial and error cost of subsequent similar production.

[0097] Referring to Figure 2 The second aspect of the application provides a raw material proportioning optimization control system for cement production, comprising a feasible proportioning acquisition module, a proportioning screening module, a trial burning and proportioning adjustment module and a proportioning feasibility verification module.

[0098] The proportioning screening module is connected with the feasible proportioning acquisition module and the trial burning and proportioning adjustment module, and the proportioning feasibility verification module is connected with the trial burning and proportioning adjustment module.

[0099] The feasible proportioning acquisition module determines a three rate value interval according to the cement production requirements, the three rate values include a lime saturation coefficient, a silicon rate and an aluminum rate, and calculates a feasible proportioning scheme set meeting the three rate value interval based on the types of raw materials and the contents of main oxides in each raw material.

[0100] The proportioning screening module constructs a mixed type easy burning prediction model, calculates the easy burning raw material proportioning through the model according to the expected easy burning performance, screens the proportioning scheme matching the easy burning raw material proportioning or having the minimum deviation degree and records it as the set raw material proportioning.

[0101] The trial burning and proportioning adjustment module performs small-scale trial burning according to the set raw material proportioning and monitors the kiln condition parameters, corrects the three rate values and dynamically adjusts the set raw material proportioning according to the kiln condition parameter deviation, and records the adjusted raw material proportioning.

[0102] The proportioning feasibility verification module performs quality evaluation on the clinker sample after the trial burning ends, verifies the feasibility of the raw material proportioning based on the evaluation results, if feasible, binds and stores the current raw material proportioning and its associated information, otherwise, adjusts the raw material proportioning according to the quality deviation and returns to the trial burning and proportioning adjustment module for secondary trial burning.

[0103] The above formulas are dimensionless values, the formulas are obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0104] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part.

[0105] Those skilled in the art can understand that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0106] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0107] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0108] Finally, the above is only the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing and controlling the batching of raw materials for cement production, characterized in that, include: S1: Determine the range of three ratio values ​​according to cement production requirements. The three ratio values ​​include lime saturation coefficient, silicon ratio and aluminum ratio. Based on the types of raw materials and the content of major oxides in each raw material, calculate the set of feasible mix proportion schemes that meet the range of three ratio values. S2: Construct a hybrid easy-to-burn prediction model. Based on the desired easy-to-burn performance, calculate the easy-to-burn raw material ratio through the model, and screen the ratio scheme that matches the easy-to-burn raw material ratio or has the smallest deviation and record it as the set raw material ratio. S3: Conduct small-scale trial firing according to the set raw material ratio and monitor kiln condition parameters. Correct the three ratio values ​​according to the deviation of kiln condition parameters and dynamically adjust the set raw material ratio. Record the adjusted raw material ratio. S4: After the trial firing is completed, the quality of the clinker sample is evaluated. Based on the evaluation results, the feasibility of the raw material ratio is verified. If it is feasible, the current raw material ratio and its associated information are bound and stored. Otherwise, the raw material ratio is adjusted according to the quality deviation and the process is returned to step S3 for a second trial firing. The specific analysis process of step S3 is as follows: S3.1, Trial firing implementation: Conduct small-scale trial firing according to the set raw material ratio and record the initial three ratio values; S3.2, Kiln condition parameter monitoring: Collect the calcination temperature inside the kiln through a high-temperature infrared thermometer; Measure the surface temperature of the kiln shell through an infrared thermal imager, and calculate the kiln shell thickness based on the set kiln skin thickness-shell temperature relationship model. Detecting the kiln tail using an infrared gas analyzer Concentration; S3.3, Deviation Analysis: Compare the measured values ​​of kiln condition parameters with their corresponding set values ​​to obtain the deviation. If any deviation exceeds the preset threshold, proceed to S3.4; S3.4, Three-Ratio Correction: Based on the set kiln calcination temperature-lime saturation coefficient, kiln lining thickness-silica ratio, and kiln tail... The concentration-aluminum ratio correction model is based on the kiln calcination temperature deviation, kiln lining thickness deviation, and other factors. Concentration deviations are corrected for lime saturation coefficient, silica ratio, and alumina ratio respectively; S3.5, Boundary verification: If the corrected values ​​of the three ratios exceed their corresponding intervals, the interval boundary value is taken as the final value; S3.6, Proportion adjustment: Based on the final values ​​of the three ratios, the raw material proportion is recalculated, updated to the set raw material proportion, and recorded; The specific analysis process of step S4 is as follows: After the trial firing is completed, a clinker sample is obtained; the quality indicators of the clinker sample are tested, including strength, liter weight and setting time; the production quality of the clinker sample is evaluated according to the preset mapping relationship between the quality indicators and the production quality; if the production quality reaches the set expected value, the current raw material ratio and its associated information are bound and stored, the associated information including cement production requirements and kiln condition parameters; if the expected value is not reached, the raw material ratio is adjusted according to the deviation between the production quality and the expected value, and the process returns to step S3 for a second trial firing.

2. The method for optimizing and controlling the batching of raw materials for cement production according to claim 1, characterized in that: The specific analysis process of step S1 is as follows: S1.1 Obtain the type of cement to be produced according to the cement production requirements, and retrieve the corresponding three-rate value range from the database. The three-rate values ​​include lime saturation coefficient, silicon content and aluminum content. S1.2 Obtain the types of raw materials used in production, and determine the content of major oxides in each raw material through chemical analysis. The major oxides include... , , , ; S1.

3. Based on the range of the three rates, obtain the combined values ​​of multiple sets of the three rates. Input the combined values ​​of each set of the three rates and the main oxide content of each raw material into the preset raw material ratio calculation model, and solve to obtain a set of feasible ratio schemes that satisfy the range of the three rates. The raw material ratio calculation model is a set of equations based on oxide conservation and the definition of the three rates.

3. The method for optimizing and controlling the batching of raw materials for cement production according to claim 2, characterized in that: The specific analysis process of step S1.3 is as follows: S1.3.1 Determine multiple combinations of the three-rate values: Based on the range of the three-rate values, select multiple sets of lime saturation coefficients. Silicon ratio and aluminum ratio The combined value; S1.3.2, Define raw material composition parameters: [The following text appears to be a separate, unrelated section:] ...the first... Among the raw materials , , , The contents are respectively denoted as ,in ; S1.3.3 Setting proportioning constraints: Proportions of various raw materials satisfy: , ; S1.3.4 Calculation of total oxide content: The total oxide content in the raw material is calculated using the following formula. , , , Total content , , , ; ； S1.3.

5. Establish the equation based on the definition of the three rates: ； S1.3.6, Multiple Solution Approaches: For each group Combine the values, solve the constraints and equations in steps S1.3.3-S1.3.5 simultaneously, and obtain the corresponding raw material proportioning scheme; S1.3.7 Result Screening: Screen all raw material proportioning schemes that meet the constraints in step S1.3.3, and use them as a set of feasible proportioning schemes that meet the three rate value ranges.

4. The method for optimizing and controlling the batching of raw materials for cement production according to claim 2, characterized in that: The specific analysis process of step S2 is as follows: S2.1 Constructing a hybrid easy-to-burn prediction model: Based on historical cement production data, a hybrid easy-to-burn prediction model is established. The input of the model includes raw material information, process parameters and raw material ratio, and the output is easy-to-burn performance. S2.2 Obtain the proportion of easily combustible raw materials: Input the raw material information, process parameters and desired easily combustible performance of the cement to be produced into the model, and calculate the corresponding proportion of easily combustible raw materials; S2.3, Proportion Matching Verification: Search for a proportion scheme that matches the proportion of the easily flammable raw materials in the set of feasible proportion schemes; If a matching scheme exists, the raw material ratio in that scheme is marked as the set raw material ratio; otherwise, proceed to S2.

4. S2.4, Proportion Deviation Analysis: Calculate the deviation between each feasible proportion scheme and the proportion of easily combustible raw materials, select the proportion scheme with the smallest deviation, and record the raw material proportion in this scheme as the set raw material proportion.

5. The method for optimizing and controlling the batching of raw materials for cement production according to claim 1, characterized in that: The specific process of constructing the hybrid easy-to-burn prediction model in step S2 is as follows: Historical cement production data is extracted from the database, including raw material information, process parameters, raw material proportions, and easy-to-burn performance evaluation indicators. The raw material information includes raw material type, chemical composition, particle size distribution, and crystal morphology. The process parameters include kiln temperature, kiln speed, calorific value of pulverized coal, and preheater outlet temperature. The easy-to-burn performance evaluation indicators include firing temperature, free calcium content, liquid phase quantity, and energy consumption. The easy-to-burn performance evaluation index is weighted and fused according to preset weights to calculate the easy-to-burn performance value; Based on the historical data, a training dataset is constructed, and a hybrid easy-burning prediction model is established using machine learning algorithms. The input consists of raw material information, process parameters, and raw material ratio, and the output is the easy-burning performance value.

6. The method for optimizing and controlling the batching of raw materials for cement production according to claim 5, characterized in that: The specific process for obtaining the kiln lining thickness in step S3.2 is as follows: By fitting the measured kiln lining thickness and corresponding kiln shell temperature data during historical kiln shutdowns, a relationship model between kiln lining thickness and kiln shell temperature is obtained. The surface of the kiln cylinder is scanned by an infrared thermal imager to obtain temperature data at each measuring point and generate a temperature distribution thermal map. Based on the kiln lining thickness-cylinder temperature relationship model, the temperature of each measuring point is converted into the corresponding kiln lining thickness to obtain the kiln lining thickness distribution; Based on the kiln lining thickness distribution, the kiln lining thickness monitoring results are calculated and output according to preset rules.

7. The method for optimizing and controlling the batching of raw materials for cement production according to claim 5, characterized in that: The specific analysis process of step S3.4 is as follows: Based on historical production data, the following parameters were extracted according to the principle of single variables: kiln calcination temperature and its corresponding lime saturation coefficient, kiln lining thickness and its corresponding silica ratio, and kiln tail temperature. Concentration and its corresponding aluminum ratio; Regression analysis was used to establish correction models for kiln calcination temperature versus lime saturation coefficient, kiln lining thickness versus silica content, and kiln tail. Concentration-aluminum ratio correction model; The real-time monitoring of kiln calcination temperature deviation, kiln lining thickness deviation, and kiln tail temperature deviation will be used to... The concentration deviation is input into the corresponding correction model, and the correction amounts for lime saturation coefficient, silica ratio, and aluminum ratio are calculated. Add the correction value to the original value and output the corrected three-rate values.

8. A raw material batching optimization control system for cement production, characterized in that, include: Feasible mix proportion acquisition module: Determine the range of three ratio values ​​according to cement production requirements. The three ratio values ​​include lime saturation coefficient, silicon ratio and aluminum ratio. Based on the types of raw materials and the content of major oxides in each raw material, calculate the set of feasible mix proportion schemes that meet the range of three ratio values. Proportioning and screening module: Construct a hybrid easy-to-burn prediction model, calculate the proportion of easy-to-burn raw materials based on the desired easy-to-burn performance, screen the proportion scheme that matches the proportion of easy-to-burn raw materials or has the smallest deviation and record it as the set raw material proportion; Trial firing and ratio adjustment module: Conduct small-scale trial firing according to the set raw material ratio and monitor kiln condition parameters. Correct the three ratio values ​​according to the deviation of kiln condition parameters and dynamically adjust the set raw material ratio, and record the adjusted raw material ratio. Formula Feasibility Verification Module: After the trial firing, the quality of the clinker sample is evaluated. Based on the evaluation results, the feasibility of the raw material formula is verified. If it is feasible, the current raw material formula and its associated information are bound and stored. Otherwise, the raw material formula is adjusted according to the quality deviation and the sample is returned to the formula adjustment module for a second trial firing.

Images