Calculation method and system for cement production raw material formula

Abstract

The embodiment of the invention provides a calculation method and system for a cement production raw material formula, and the method comprises the steps: obtaining the chemical components, the conveying flow and the moisture content of raw materials needed by cement production raw materials; the target chemical components of the raw materials are used as dependent variables, the chemical components, the conveying flow and the moisture content of all the raw materials are used as independent variables, a raw material formula prediction model is constructed, and the quality of the cement clinker under different raw material formulas is predicted; optimizing the raw material formula scheme by using a genetic algorithm according to the constructed constraint condition by taking the lowest formula cost as an objective function; the actual chemical components of the raw material are detected and obtained, the detection result is compared with the target chemical components, and when deviation occurs, the raw material formula scheme is adjusted in real time according to the size and direction of the deviation. According to the method, the optimal batching scheme can be quickly generated, the batching cost is reduced, the production benefit is improved, and cost reduction, efficiency improvement and quality improvement of production are realized.

Description

Technical Field

[0001] This document relates to the technical field of cement production, and in particular to a method and system for calculating raw material formula for cement production. Background Art

[0002] Raw material batching is a critical step in cement production, with its accuracy directly impacting clinker quality, production efficiency, and costs. Traditional methods for batching raw materials rely primarily on manual experience and simple ratio control. Laboratory chemical analysis is often used to test raw material composition, but this approach suffers from long testing cycles and low efficiency, failing to meet the demands of real-time monitoring and rapid adjustments during production.

[0003] With technological advancements, online detection equipment has been introduced to monitor the production process. However, most are still limited to a single detection method, such as using only neutron online analyzers or X-ray fluorescence analyzers, making it difficult to obtain comprehensive and rapid information about raw materials. When formulating batching plans, existing technologies lack effective mechanisms to address fluctuations in raw material composition. When raw material composition changes, the batching ratio cannot be adjusted promptly and accurately, resulting in unstable raw material chemical composition and affecting the quality of subsequent clinker calcination.

[0004] Furthermore, existing batch optimization methods often focus solely on raw material quality, lacking comprehensive consideration of multiple objectives such as cost and output. During production process control, monitoring and feedback adjustments of the raw material's actual chemical composition are often inaccurate and inadequate. Open-loop control is often employed, making it impossible to dynamically optimize batching based on real-time changes during production. This makes it difficult to ensure continuous and stable production, and it also hinders maximizing production efficiency. Summary of the Invention

[0005] One or more embodiments of this specification provide a method for calculating a raw material formula for cement production, including:

[0006] Obtain the chemical composition, delivery flow rate and moisture content of raw materials required for cement production;

[0007] Taking the target chemical composition of raw meal as the dependent variable and the chemical composition, delivery flow rate and moisture content of each raw material as the independent variables, a raw meal formula prediction model was constructed to predict the quality of cement clinker under different raw meal formulas.

[0008] Taking the lowest formula cost as the objective function, the genetic algorithm is used to optimize the raw material formula according to the constructed constraints.

[0009] The actual chemical composition of the raw material is detected and compared with the target chemical composition. When deviation occurs, the raw material formula is adjusted in real time according to the size and direction of the deviation.

[0010] Furthermore, the specific method for obtaining the chemical composition, delivery flow rate and moisture content of the raw materials required for cement production is as follows:

[0011] The raw materials required for cement production are scanned using a near-infrared spectrometer to obtain spectral data, which is then compared with a pre-established raw material spectral database to obtain the chemical composition of the raw materials; the raw materials include limestone, clay, iron ore, and coal gangue;

[0012] Use electronic belt scales to monitor the delivery flow of each raw material in real time;

[0013] The moisture content of each raw material was measured using a moisture meter.

[0014] Furthermore, after obtaining the chemical composition, delivery flow rate and moisture content of the raw materials required for cement production, the collected data is tested for outliers to identify and eliminate abnormal data.

[0015] Furthermore, the target chemical composition of the raw meal is used as the dependent variable, and the chemical composition, delivery flow rate and moisture content of each raw material are used as independent variables to construct a raw meal formula prediction model. The specific method is as follows:

[0016] Collect historical production data, including raw material formula and corresponding cement clinker quality data;

[0017] Based on historical production data, the target chemical composition of raw materials was used as the dependent variable, and the chemical composition, flow rate, and moisture content of each raw material were used as independent variables to determine the linear relationship between the chemical composition, flow rate, and moisture content of each raw material and the quality indicators of cement clinker.

[0018] The linear relationship results are input into the artificial neural network as initial values ​​for training, and the back propagation algorithm is used to adjust the weights and thresholds of the neural network to obtain a trained raw meal formula prediction model.

[0019] Furthermore, the constraints include the range of target chemical composition of the raw material, and the cost and output of each raw material.

[0020] Furthermore, the optimization of the raw material formula using genetic algorithms specifically includes:

[0021] During the iterative process of the genetic algorithm, each recipe in the population is decoded, the chemical composition of the raw material corresponding to each recipe is calculated, whether the preset constraints are met is determined, and the fitness value is calculated;

[0022] Through genetic operations of selection, crossover and mutation, the population is continuously evolved until the optimal raw material formula is found.

[0023] Furthermore, when using genetic algorithms to optimize the raw material formula scheme, multiple crossover and mutation operators are set, and appropriate operators are adaptively selected according to the number of iterations and the convergence of the population. When performing the genetic operation of selection, the population is evolved by combining roulette wheel selection with elite retention strategy.

[0024] One or more embodiments of this specification provide a system for calculating a raw material formula for cement production, including:

[0025] Data acquisition module: used to obtain the chemical composition, delivery flow and moisture content of raw materials required for cement production;

[0026] Recipe Prediction Module: This module is used to construct a raw meal recipe prediction model using the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate, and moisture content of each raw material as the independent variables, thereby predicting the quality of cement clinker under different raw meal recipes.

[0027] Recipe Optimization Module: It is used to optimize the raw material recipe scheme using genetic algorithms based on the established constraints, taking the lowest recipe cost as the objective function;

[0028] Recipe adjustment module: used to detect and obtain the actual chemical composition of the raw material, compare the test results with the target chemical composition, and make real-time adjustments to the raw material recipe according to the size and direction of the deviation when deviation occurs.

[0029] One or more embodiments of this specification provide an electronic device, including:

[0030] processor; and,

[0031] A memory is arranged to store computer executable instructions, which, when executed, cause the processor to implement the steps of the method for calculating the raw meal formula for cement production.

[0032] One or more embodiments of this specification provide a storage medium for storing computer-executable instructions, which, when executed, implement the steps of the method for calculating the raw material formula for cement production.

[0033] By adopting the embodiments of the present invention, the problems of traditional cement raw material batching relying on manual experience, low detection efficiency and single means are solved. By combining multiple devices such as a near-infrared spectrometer, rapid acquisition of multi-dimensional information such as raw material chemical composition, flow rate, and moisture content can be achieved in minutes. The relationship between raw material parameters and raw material chemical composition is deeply analyzed, and the optimal batching scheme is quickly generated, thereby improving the stability of the raw material chemical composition. The batching scheme is adjusted in time according to the deviation between the actual chemical composition of the raw material and the target value, thereby reducing the batching cost, improving production efficiency, and achieving cost reduction, efficiency improvement, and quality improvement in production.

[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A flow chart of a method for calculating a raw material formula for cement production provided in one or more embodiments of this specification;

[0037] Figure 2 A schematic diagram of the composition of a method system for calculating raw material formula for cement production provided in one or more embodiments of this specification;

[0038] Figure 3 A schematic diagram of the structure of an electronic device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0040] Method Example

[0041] According to an embodiment of the present invention, a method for calculating the raw material formula for cement production is provided. Figure 1 A flow chart of a method for calculating a raw material formula for cement production provided in one or more embodiments of this specification, such as Figure 1 As shown, the calculation method of the raw material formula for cement production according to an embodiment of the present invention specifically includes:

[0042] S1. Obtain the chemical composition, delivery flow rate, and moisture content of raw materials required for cement production.

[0043] Specifically, a near-infrared spectrometer was used to scan the raw materials needed for cement production. Fourier transform near-infrared spectroscopy was used to obtain spectral data by measuring the raw materials' absorption and reflection characteristics for near-infrared light in the wavelength range of 780-2500nm. A raw material spectral database was established through calibration experiments. The chemical composition of the raw materials, including limestone, clay, iron ore, and coal gangue, was determined by comparing it with a pre-established database of raw material spectra. An electronic belt scale was used to monitor the flow rate of each raw material in real time. Using a strain gauge load cell, the instantaneous flow rate was calculated by measuring the material load per unit length of the belt conveyor and the belt speed. A moisture meter was used to determine the moisture content of each raw material.

[0044] After obtaining the chemical composition, flow rate, and moisture content of the raw materials required for cement production, perform outlier detection on the collected data to identify and eliminate abnormal data. This can be done by applying the 3σ criterion, calculating the mean μ and standard deviation σ of the chemical composition data and eliminating data points outside the range of μ ± 3σ. Alternatively, a sliding window filter can be used: applying a Hampel filter to the flow data, calculating the median and absolute deviation within a time window, and eliminating outliers that deviate from the median by more than three times the absolute deviation.

[0045] S2. Using the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate, and moisture content of each raw material as the independent variables, a raw meal formulation prediction model is constructed to predict the quality of cement clinker under different raw meal formulations.

[0046] First, historical production data is collected, including raw meal formula and corresponding cement clinker quality data. The raw meal formula includes the ratio of raw materials such as limestone, clay, iron ore, and coal gangue, and the clinker quality data includes chemical composition content and physical properties.

[0047] According to the quality standard of cement clinker, the target chemical composition range of raw material is set. Based on historical production data, the target chemical composition of raw material is used as the dependent variable, and the chemical composition, flow rate and moisture content of each raw material are used as independent variables to determine the linear relationship between the chemical composition, flow rate and moisture content of each raw material and the quality indicators of cement clinker.

[0048] The linear relationship result is input as the initial value into the artificial neural network for training. The training set, validation set, and test set are divided into 7:2:1. The LM optimizer is used, combined with the mean square error (MSE) loss function, and the back propagation algorithm is used to adjust the weights and thresholds of the neural network. If the validation set loss does not decrease for 10 consecutive rounds, the training is terminated to obtain a trained raw material formula prediction model. In this embodiment, a correlation analysis is performed on the independent variables before determining the linear relationship, and variables with strong correlation are eliminated by variance inflation factor analysis.

[0049] S3. Taking the lowest formula cost as the objective function, the genetic algorithm is used to optimize the raw material formula according to the constructed constraints.

[0050] In this embodiment, the constraints include the target chemical composition range of the raw material, the cost and output of each raw material, etc.

[0051] During the iterative process of the genetic algorithm, each recipe in the population is decoded, the chemical composition of the raw material corresponding to each recipe is calculated, whether the preset constraints are met is determined, and the fitness value is calculated; through the genetic operations of selection, crossover and mutation, the population is continuously evolved until the optimal raw material recipe is found.

[0052] When using genetic algorithms to optimize raw material formula schemes, multiple crossover and mutation operators are set, and appropriate operators are adaptively selected according to the number of iterations and the convergence of the population. When performing the genetic operation of selection, the population is evolved by combining roulette wheel selection with elite retention strategy.

[0053] S4. Detect and obtain the actual chemical composition of the raw material, compare the test results with the target chemical composition, and when deviations occur, make real-time adjustments to the raw material formula based on the size and direction of the deviation.

[0054] Real-time monitoring and feedback adjustment: During the cement production process, the quality data of cement clinker and production process parameters are collected in real time. For example, a B-type platinum-rhodium thermocouple is installed in the firing zone of the rotary kiln to monitor the temperature inside the kiln, with a temperature measurement range of 0-1800°C; a capacitive pressure transmitter is used to monitor the negative pressure at the kiln tail in real time, etc. These real-time data are compared and analyzed with the results of the prediction model. If the actual production results deviate from the predicted values ​​beyond the allowable range, the real-time data will be automatically fed back to the prediction model, the model will be retrained, and the raw material formula will be adjusted to achieve dynamic optimization of the production process.

[0055] The method also includes establishing a raw material supplier evaluation system, conducting comprehensive evaluation and graded management of suppliers based on factors such as raw material quality stability, supply timeliness and price, giving priority to high-quality suppliers, and ensuring a stable supply of quality raw materials.

[0056] During the production process, the operating parameters of each production equipment are monitored in real time. Combined with the raw material batching plan and actual production conditions, the equipment operating parameters are collaboratively optimized to improve the overall operating efficiency of the production system.

[0057] The beneficial effects of the present invention are as follows:

[0058] By adopting the embodiments of the present invention, the problems of traditional cement raw material batching relying on manual experience, low detection efficiency and single means are solved. By combining multiple devices such as a near-infrared spectrometer, rapid acquisition of multi-dimensional information such as raw material chemical composition, flow rate, and moisture content can be achieved in minutes. The relationship between raw material parameters and raw material chemical composition is deeply analyzed, and the optimal batching scheme is quickly generated, thereby improving the stability of the raw material chemical composition. The batching scheme is adjusted in time according to the deviation between the actual chemical composition of the raw material and the target value, thereby reducing the batching cost, improving production efficiency, and achieving cost reduction, efficiency improvement, and quality improvement in production.

[0059] System Example

[0060] According to an embodiment of the present invention, a calculation system for raw material formula of cement production is provided. Figure 2 A schematic diagram of a system for calculating a raw material formula for cement production provided in one or more embodiments of this specification is shown in FIG. Figure 2 As shown, the calculation system for cement production raw material formula according to an embodiment of the present invention specifically includes:

[0061] Data acquisition module 20: used to obtain the chemical composition, delivery flow rate and moisture content of raw materials required for cement production;

[0062] Recipe prediction module 22: used to construct a raw meal recipe prediction model with the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate and moisture content of each raw material as the independent variables, and to predict the quality of cement clinker under different raw meal recipes;

[0063] Recipe optimization module 24: used to optimize the raw material recipe scheme using genetic algorithms based on the established constraints, taking the lowest recipe cost as the objective function;

[0064] Formula adjustment module 26: used to detect and obtain the actual chemical composition of the raw material, compare the detection results with the target chemical composition, and when deviations occur, adjust the raw material formula in real time according to the size and direction of the deviations.

[0065] It also includes a human-computer interaction interface for operators to input production targets, view raw material data, raw material formula calculation results and real-time data during the production process, and can also set and adjust the parameters of the raw material formula calculation module.

[0066] The embodiment of the present invention is a system embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0067] Device Example 1

[0068] An embodiment of the present invention provides an electronic device, such as Figure 3As shown, it includes: a memory 30, a processor 32, and a computer program stored in the memory 30 and executable on the processor 32. When the computer program is executed by the processor 32, the following method steps are implemented:

[0069] S1. Obtain the chemical composition, delivery flow rate, and moisture content of raw materials required for cement production;

[0070] S2. Using the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate, and moisture content of each raw material as the independent variables, a raw meal formulation prediction model was constructed to predict the quality of cement clinker under different raw meal formulations.

[0071] S3. Taking the lowest formula cost as the objective function, the genetic algorithm is used to optimize the raw material formula according to the established constraints;

[0072] S4. Detect and obtain the actual chemical composition of the raw material, compare the test results with the target chemical composition, and when deviations occur, make real-time adjustments to the raw material formula based on the size and direction of the deviation.

[0073] Device Example 2

[0074] An embodiment of the present invention provides a computer-readable storage medium having stored thereon a program for implementing information transmission. When the program is executed by the processor 32, the following method steps are implemented:

[0075] S1. Obtain the chemical composition, delivery flow rate, and moisture content of raw materials required for cement production;

[0076] S2. Using the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate, and moisture content of each raw material as the independent variables, a raw meal formulation prediction model was constructed to predict the quality of cement clinker under different raw meal formulations.

[0077] S3. Taking the lowest formula cost as the objective function, the genetic algorithm is used to optimize the raw material formula according to the established constraints;

[0078] S4. Detect and obtain the actual chemical composition of the raw material, compare the test results with the target chemical composition, and when deviations occur, make real-time adjustments to the raw material formula based on the size and direction of the deviation.

[0079] The computer-readable storage medium in this embodiment includes but is not limited to: ROM, RAM, magnetic disk or optical disk, etc.

[0080] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating raw material formula for cement production, characterized in that: include: Obtain the chemical composition, delivery flow rate and moisture content of raw materials required for cement production; Taking the target chemical composition of raw meal as the dependent variable and the chemical composition, delivery flow rate and moisture content of each raw material as the independent variables, a raw meal formula prediction model was constructed to predict the quality of cement clinker under different raw meal formulas. Taking the lowest formula cost as the objective function, the genetic algorithm is used to optimize the raw material formula according to the constructed constraints. The actual chemical composition of the raw material is detected and compared with the target chemical composition. When deviation occurs, the raw material formula is adjusted in real time according to the size and direction of the deviation.

2. The method for calculating the raw material formula for cement production according to claim 1, characterized in that: The specific method for obtaining the chemical composition, delivery flow rate and moisture content of raw materials required for cement production is as follows: The raw materials required for cement production are scanned using a near-infrared spectrometer to obtain spectral data, which is then compared with a pre-established raw material spectral database to obtain the chemical composition of the raw materials; the raw materials include limestone, clay, iron ore, and coal gangue; Use electronic belt scales to monitor the delivery flow of each raw material in real time; The moisture content of each raw material was measured using a moisture meter.

3. The method for calculating the raw material formula for cement production according to claim 2, characterized in that: After obtaining the chemical composition, delivery flow rate and moisture content of the raw materials required for cement production, the collected data is tested for outliers to identify and eliminate abnormal data.

4. The method for calculating the raw material formula for cement production according to claim 1, characterized in that: The target chemical composition of the raw meal is used as the dependent variable, and the chemical composition, delivery flow rate, and moisture content of each raw material are used as independent variables. The specific method for constructing the raw meal formula prediction model is as follows: Collect historical production data, including raw material formula and corresponding cement clinker quality data; Based on historical production data, the target chemical composition of raw materials was used as the dependent variable, and the chemical composition, flow rate, and moisture content of each raw material were used as independent variables to determine the linear relationship between the chemical composition, flow rate, and moisture content of each raw material and the quality indicators of cement clinker. The linear relationship results are input into the artificial neural network as initial values ​​for training, and the back propagation algorithm is used to adjust the weights and thresholds of the neural network to obtain a trained raw meal formula prediction model.

5. The method for calculating the raw material formula for cement production according to claim 1, characterized in that: The constraints include the target chemical composition range of the raw meal, the cost and yield of each raw material.

6. The method for calculating the raw material formula for cement production according to claim 1, characterized in that: The optimization of raw material formula using genetic algorithm specifically includes: During the iterative process of the genetic algorithm, each recipe in the population is decoded, the chemical composition of the raw material corresponding to each recipe is calculated, whether the preset constraints are met is determined, and the fitness value is calculated; Through genetic operations of selection, crossover and mutation, the population is continuously evolved until the optimal raw material formula is found.

7. The method for calculating the raw material formula for cement production according to claim 6, characterized in that: When using genetic algorithms to optimize raw material formula schemes, multiple crossover and mutation operators are set, and appropriate operators are adaptively selected according to the number of iterations and the convergence of the population. When performing the genetic operation of selection, the population is evolved by combining roulette wheel selection with elite retention strategy.

8. A calculation system for raw material formula of cement production, characterized in that: include: Data acquisition module: used to obtain the chemical composition, delivery flow and moisture content of raw materials required for cement production; Recipe prediction module: This module is used to construct a raw meal recipe prediction model using the target chemical composition of the raw meal as the dependent variable and the chemical composition, delivery flow rate, and moisture content of each raw material as the independent variables, thereby predicting the quality of cement clinker under different raw meal recipes. Recipe Optimization Module: It is used to optimize the raw material recipe scheme using genetic algorithms based on the established constraints, taking the lowest recipe cost as the objective function; Recipe adjustment module: used to detect and obtain the actual chemical composition of the raw material, compare the test results with the target chemical composition, and make real-time adjustments to the raw material recipe according to the size and direction of the deviation when deviation occurs.

9. An electronic device, characterized in that: include: processor; as well as, A memory arranged to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the method for calculating the raw meal formula for cement production according to any one of claims 1 to 7.

10. A storage medium, characterized in that: Used to store computer-executable instructions, which, when executed, implement the steps of the method for calculating the raw material formula for cement production as described in any one of claims 1 to 7.

Images