Method and device for adjusting process parameters of a cement kiln based on the strength of the kiln discharge clinker
By constructing a calibrated prediction model based on X-ray diffraction data and deep learning, the problem of low accuracy in predicting the strength of clinker leaving the kiln was solved, enabling real-time optimization of cement kiln process parameters and improving production efficiency and product quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ANHUI SHUZHI BUILDING MATERIALS RES INST CO LTD
- Filing Date
- 2026-03-31
- Publication Date
- 2026-05-29
AI Technical Summary
The accuracy of the predicted clinker strength data in the existing technology is low, which makes it impossible to adjust the process parameters in a timely manner during production, resulting in raw material waste and production efficiency loss.
By acquiring the raw material batching ratio and cement kiln process parameters, a calibrated prediction model based on X-ray diffraction data and deep learning is constructed, and the cement kiln process parameters are adjusted in real time to improve the accuracy of clinker strength prediction.
It enables rapid and accurate prediction of clinker strength after kiln firing, reduces prediction errors, and improves production efficiency and product quality while reducing production costs by optimizing the configuration through real-time adjustment of process parameters.
Smart Images
Figure CN122107797A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of production data processing technology, and in particular to a method and apparatus for adjusting cement kiln process parameters based on the prediction of clinker strength at the kiln outlet. Background Technology
[0002] Currently, in the cement production process, clinker performance is a core indicator determining the quality of the final cement product, directly affecting the structural safety and service life of building projects. Its stability control has always been a key focus of production management in the cement industry. Clinker performance is easily affected by multiple factors, including external variables such as fluctuations in raw material composition, changes in coal calorific value and ash content, as well as differences in the regulation of internal production parameters such as cement kiln calcination temperature, rotation speed, and feed rate. However, the accuracy of current clinker strength prediction data is relatively low. Summary of the Invention
[0003] The purpose of this invention is to provide a method and apparatus for adjusting cement kiln process parameters based on the prediction of clinker strength at the kiln outlet, so as to solve the technical problem of low accuracy of current clinker strength prediction data.
[0004] In a first aspect, this application provides a method for adjusting cement kiln process parameters based on the predicted strength of the clinker discharged from the kiln, the method comprising: Obtain the raw material batching ratio and the process parameters of the cement kiln; Based on the raw material proportioning ratio and the process parameters of the cement kiln, the strength of clinker at a specified time is predicted to obtain the initial clinker strength prediction value at a specified time. The initial clinker strength prediction value over a specified time is determined as the initial benchmark value for the strength prediction of the clinker after a specified time. A calibrated prediction model for the intensity of kiln clinker at a specified time is constructed based on the initial benchmark value, historical clinker strength data, and corresponding batches of clinker X-ray diffraction data. Based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportioning ratio and the corresponding chemical analysis data of the raw materials, the calibrated prediction model is used to predict the intensity of the final clinker at a specified time after exiting the kiln. Based on the predicted intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal, process adjustment parameters for the cement kiln are generated.
[0005] In one possible implementation, the raw meal proportioning and cement kiln process parameters include the raw meal proportioning and key cement kiln process parameters; the step of predicting the clinker strength at a specified time based on the raw meal proportioning and cement kiln process parameters, to obtain the predicted clinker strength at a specified time, includes: A basic clinker strength prediction model was obtained through model training based on historical clinker data from kilns. Abnormal data in the raw material batching ratio and key process parameters of cement kiln are eliminated by preprocessing the raw material batching ratio and key process parameters of cement kiln to obtain preprocessed data. The preprocessed data is used as the input features of the basic clinker strength prediction model. Based on the input features, the basic clinker strength prediction model is used to calculate the basic clinker strength prediction value for a specified time.
[0006] In one possible implementation, the calibration prediction model for the intensity of kiln clinker at a specified time, constructed based on the initial reference value, historical clinker intensity data, and corresponding batches of clinker X-ray diffraction data, includes: Obtain historical clinker intensity measurement data for a specified duration and corresponding batches of clinker X-ray diffraction data; The measured intensity data of the historical clinker over a specified time and the X-ray diffraction data of the corresponding batch of clinker are correlated and matched with the initial reference value to obtain the feature matching result; Based on the feature matching results, a calibrated prediction model for the intensity of kiln clinker over a specified time is constructed using deep learning to complete the model calibration.
[0007] In one possible implementation, the clinker X-ray diffraction data are the measured X-ray diffraction data of the clinker exiting the kiln; The step of predicting the intensity of the clinker at a specified time after discharge from the kiln using the calibrated prediction model, based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportioning, and the chemical analysis data of the raw materials, includes: The measured X-ray diffraction data of the clinker exiting the kiln, the current process parameters of the cement kiln, the raw material proportion, and the chemical analysis data of the raw materials are used as dynamic feedback features and continuously input into the calibrated prediction model for prediction. This allows the calibrated prediction model to adapt to the fluctuations in the operating conditions during the production process. Through real-time feedback iteration, the predicted data of the intensity of the clinker exiting the kiln for a specified time is obtained as the output result.
[0008] In one possible implementation, generating process adjustment parameters for the cement kiln based on predicted data of the final clinker intensity over a specified time, clinker X-ray diffraction data, raw meal proportions, and chemical analysis data of the raw meal raw materials includes: Based on the predicted intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw material proportioning, and the chemical analysis data of the raw material, the optimal adjustment range of the process parameters for the cement kiln is obtained by calculation through the process parameter optimization model within the algorithm.
[0009] In one possible implementation, before calculating the optimal adjustment range of the process parameters for the cement kiln based on the predicted data of the intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal, using the process parameter optimization model within the algorithm, the following is also included: A function set M is constructed to represent the process parameter optimization model through functions. The function set M contains sub-functions [M1, M2, M3...Mn] covering the entire process. M1 is an index function, which is an implicit function containing all control variables and external variables, used to calculate the output optimization function through machine learning algorithms.
[0010] In one possible implementation, the optimization function computed by the machine learning algorithm includes: The optimization function is calculated by advancing the algorithm according to different granularities to complete the global optimization, and / or by calculating the optimization function through an approximation algorithm. The system uses iterative self-learning to predict the strength of clinker exiting the cement kiln and continuously outputs data for adjusting cement kiln process parameters.
[0011] Secondly, this application provides a cement kiln process parameter adjustment device based on the prediction of clinker strength, comprising: The acquisition module is used to acquire the raw material batching ratio and the process parameters of the cement kiln; The first prediction module is used to predict the strength of clinker at a specified time based on the raw material proportion and the process parameters of the cement kiln, and to obtain the initial clinker strength prediction value at a specified time. The determination module is used to determine the initial clinker strength prediction value over a specified time as the initial benchmark value for the strength prediction of the clinker exiting the kiln over a specified time. The construction module is used to construct a calibrated prediction model of the intensity of kiln clinker for a specified time based on the initial benchmark value, historical clinker strength data and corresponding batches of clinker X-ray diffraction data; The second prediction module is used to make predictions based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material batching ratio and the corresponding chemical analysis data of the raw materials, through the calibrated prediction model, to obtain the predicted data of the final clinker intensity at a specified time after exiting the kiln. The generation module is used to generate process adjustment parameters for the cement kiln based on the predicted data of the intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw material proportion, and the chemical analysis data of the raw material.
[0012] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described in the first aspect above.
[0013] Fourthly, this application also provides a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method described in the first aspect above.
[0014] This application brings the following beneficial effects: This application provides a method and apparatus for adjusting cement kiln process parameters based on clinker strength prediction. The method can obtain the raw meal ratio and the cement kiln process parameters; predict the clinker strength at a specified time based on the raw meal ratio and the cement kiln process parameters to obtain an initial clinker strength prediction value for a specified time; determine the initial clinker strength prediction value for a specified time as the initial reference value for predicting the clinker strength at a specified time; construct a calibrated prediction model for the clinker strength at a specified time based on the initial reference value, historical clinker strength data, and X-ray diffraction data of the corresponding batches of clinker; and predict the final clinker strength at a specified time based on the clinker X-ray diffraction data, the cement kiln process parameters, the raw meal ratio, and the corresponding chemical analysis data of the raw meal materials using the calibrated prediction model to obtain the final clinker strength at a specified time. The method involves predicting the intensity of clinker at a specified duration based on the predicted intensity of the final clinker exiting the kiln, the clinker X-ray diffraction data, the raw material proportioning, and the chemical analysis data of the raw material. This method uses X-ray diffraction data of the cement clinker to predict the intensity of the clinker exiting the kiln. This leverages the diffraction data and deep learning technology to enhance the accuracy of the clinker intensity prediction, reduce prediction errors, and achieve rapid and accurate prediction of the intensity of the clinker at a specified duration. This solves the technical problem of low accuracy in predicting clinker intensity. Furthermore, it allows for real-time adjustment and optimization of the cement kiln process parameters, enabling timely adjustment of the kiln calcination process parameters based on the logical relationship between the diffraction data of the cement clinker, the predicted clinker intensity, and the kiln process parameters.
[0015] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 A flowchart illustrating the cement kiln process parameter adjustment method based on clinker strength prediction provided in this application embodiment; Figure 2 This is another flowchart illustrating the cement kiln process parameter adjustment method based on clinker strength prediction provided in this application embodiment. Figure 3 A schematic diagram of a cement kiln process parameter adjustment device based on clinker strength prediction provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0019] The terms "comprising" and "having," and any variations thereof, used in the embodiments of this application, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.
[0020] Currently, under the traditional production model, it takes 28 days to obtain the measured value of clinker strength. This method has a significant time lag. If the test results are substandard, the produced clinker will face quality defects, and the results cannot be fed back to the production stage in a timely manner to adjust process parameters, easily leading to a large amount of raw material waste and production efficiency loss. Moreover, the accuracy of the current predicted clinker strength data is relatively low.
[0021] Based on this, the present application provides a method and apparatus for adjusting cement kiln process parameters based on the prediction of clinker strength at the kiln outlet. This method can solve the technical problem of low accuracy of clinker strength prediction data at the kiln outlet.
[0022] The embodiments of the present invention will be further described below with reference to the accompanying drawings.
[0023] Figure 1 This is a flowchart illustrating a method for adjusting cement kiln process parameters based on the prediction of clinker strength, provided as an embodiment of this application. Figure 1 As shown, the method includes: Step S110: Obtain the raw material batching ratio and the process parameters of the cement kiln.
[0024] In one possible implementation, this step involves obtaining the raw material batching and the process parameters of the cement kiln, i.e., obtaining the raw material ratio and the process parameters of the cement kiln.
[0025] Step S120: Based on the raw material proportion and the process parameters of the cement kiln, predict the strength of the clinker at a specified time to obtain the initial clinker strength prediction value at a specified time.
[0026] In this step, such as Figure 2 As shown, based on the raw meal proportioning and the process parameters of the cement kiln, the strength of clinker at a specified time (e.g., 28 days) is predicted. For example, the raw meal proportioning and the process parameters of the cement kiln include the raw meal proportioning ratio and key process parameters of the cement kiln. Predicting the clinker strength at a specified time based on these parameters yields the predicted clinker strength value, which may specifically include the following steps: A basic clinker strength prediction model is obtained through model training based on historical clinker data from the kiln. Abnormal data in the raw meal proportion and key process parameters of the cement kiln are eliminated by preprocessing to obtain preprocessed data. The preprocessed data is used as the input features of the basic clinker strength prediction model. Based on the input features, the basic clinker strength prediction model is used to calculate the basic clinker strength prediction value for a specified time.
[0027] For example, such as Figure 2 As shown, a basic clinker strength prediction model is constructed. The raw material proportion and key process parameters of the cement kiln are used as input features. After preprocessing to eliminate abnormal data, the model is substituted into the basic prediction model trained with historical clinker data to calculate the basic clinker strength prediction value for a specified time (e.g., 28 days).
[0028] Step S130: Determine the initial clinker strength prediction value for a specified time as the initial benchmark value for the strength prediction of the clinker after a specified time.
[0029] In one possible implementation, this value is set as the initial baseline value for predicting the 28-day strength of the clinker after kiln exit, such as... Figure 2 As shown, the predicted strength of clinker at 28 days is used as the initial value for the strength prediction of clinker at a specified time (such as 28 days) after leaving the kiln, providing a basic reference for subsequent accurate prediction.
[0030] Step S140: Based on the initial benchmark value, historical clinker strength data and corresponding batches of clinker X-ray diffraction data, a calibrated prediction model for the strength of kiln clinker over a specified time period is constructed.
[0031] In one alternative implementation, such as Figure 2 As shown, based on the initial value of the clinker strength prediction at a specified time (e.g., 28 days) after exiting the kiln, historical clinker performance data, and clinker diffraction data, a prediction model for the 28-day strength of clinker after exiting the kiln is established, namely, the calibrated prediction model for the 28-day strength of clinker after exiting the kiln.
[0032] As an example, a calibrated prediction model for the intensity of kiln clinker over a specified time can be constructed based on an initial baseline value, historical clinker strength data, and X-ray diffraction data of the corresponding batches of clinker. This can specifically include the following steps: Acquire historical clinker intensity measured data for a specified duration and corresponding batches of clinker X-ray diffraction data; perform data association and feature matching between the historical clinker intensity measured data for a specified duration and corresponding batches of clinker X-ray diffraction data and the initial benchmark value to obtain feature matching results; based on the feature matching results, construct a calibrated prediction model of the kiln clinker intensity for a specified duration using deep learning to complete model calibration.
[0033] For example, such as Figure 2 As shown, by combining historical clinker strength measured data for a specified period (e.g., 28 days) and corresponding batches of clinker X-ray diffraction data, data association and feature matching are performed with the above initial prediction values. A 28-day clinker strength prediction model is constructed using deep learning technology, and model calibration is completed to improve the model prediction accuracy.
[0034] Step S150: Based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportion and the corresponding chemical analysis data of the raw materials, the predicted data of the final clinker strength at a specified time after exiting the kiln is obtained by using a calibrated prediction model.
[0035] In one possible implementation, such as Figure 2 As shown, based on the raw material proportioning data, chemical analysis data of raw materials, clinker diffraction data, and process parameters of the cement kiln as feedback values, the predicted data of the clinker strength at a specified time (e.g., 28 days) is output in real time.
[0036] For example, the clinker X-ray diffraction data is the measured X-ray diffraction data of the clinker exiting the kiln; the above-mentioned prediction data of the intensity of the clinker at a specified time after exiting the kiln is obtained by using a calibrated prediction model based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportion, and the chemical analysis data of the raw materials, which may specifically include the following steps: The measured X-ray diffraction data of the clinker exiting the kiln, the current process parameters of the cement kiln, the raw material proportion, and the chemical analysis data of the raw materials are used as dynamic feedback features and continuously input into the calibrated prediction model for prediction. This allows the calibrated prediction model to adapt to the fluctuations in the operating conditions during the production process. Through real-time feedback iteration, the predicted data of the intensity of the clinker exiting the kiln for a specified time period are obtained as the output results.
[0037] By establishing a real-time feedback and iteration mechanism, such as Figure 2 As shown, raw material proportioning data, raw material chemical analysis results, measured X-ray diffraction data of clinker leaving the kiln, and current process parameters of the cement kiln are used as dynamic feedback features and continuously input into the calibrated prediction model to ensure that the model can adapt to the fluctuations in operating conditions during the production process, and finally output a highly accurate intensity prediction output of clinker leaving the kiln for a specified time (such as 28 days).
[0038] Step S160: Based on the predicted data of the intensity of the final clinker at a specified time after discharge, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal, process adjustment parameters for the cement kiln are generated.
[0039] As an optional implementation method, such as Figure 2 As shown, based on the predicted data of clinker intensity at a specified time (e.g., 28 days), clinker diffraction data, raw meal ratio and test data, the process adjustment parameters of the cement kiln are output.
[0040] For example, generating process adjustment parameters for a cement kiln based on predicted data of the final clinker intensity at a specified time, clinker X-ray diffraction data, raw meal proportions, and chemical analysis data of raw meal can specifically include the following steps: Based on the predicted intensity of the final clinker at a specified time, clinker X-ray diffraction data, raw meal proportions, and chemical analysis data of raw meal, the optimal adjustment range of process parameters for the cement kiln is obtained through calculation using the process parameter optimization model within the algorithm.
[0041] like Figure 2 As shown, the optimal adjustment range of cement kiln process parameters is calculated through the process parameter optimization model within the algorithm, so as to achieve the goal of improving production efficiency and reducing production costs while ensuring clinker performance.
[0042] In this embodiment, the strength of clinker exiting the cement kiln is predicted using X-ray diffraction data of cement clinker. This method utilizes the diffraction data of cement clinker and deep learning technology to enhance the accuracy of clinker strength prediction, reduce prediction errors, and achieve rapid and accurate prediction of the strength of clinker exiting the kiln at a specified time. Based on this, the process parameters of the cement kiln are adjusted and optimized in real time. This enables timely adjustment of the kiln calcination process parameters by utilizing the logical relationship between the diffraction data of cement clinker, the predicted clinker strength data, and the kiln process parameters. This achieves continuous improvement in the strength performance of cement clinker, thereby increasing production efficiency, ensuring product quality, and reducing production costs.
[0043] In some embodiments, before the optimal adjustment range of the process parameters for the cement kiln is obtained by calculating using the process parameter optimization model within the algorithm based on the predicted data of the final clinker intensity at a specified time after discharge, clinker X-ray diffraction data, raw meal proportions, and chemical analysis data of the raw meal, the method may further include the following steps: Construct a function set M to represent the process parameter optimization model through functions. The function set M contains sub-functions [M1, M2, M3...Mn] covering the entire process. M1 is the index function, which is an implicit function containing all control variables and external variables, used to calculate the output optimization function through machine learning algorithms.
[0044] For example, clinker strength prediction and process parameter optimization models can both be represented by functions. Assume that the constructed model is a set of functions M, which contains sub-functions [M1, M2, M3...Mn] covering the entire process. The index function M1 is an implicit function containing all control variables and external variables, and the output optimization function can be calculated by machine learning algorithms.
[0045] In some embodiments, the optimization function calculated by the machine learning algorithm may specifically include the following steps: advancing the optimization function according to different granularities using a progressive optimization algorithm to complete global optimization, and / or calculating the optimization function using an approximation algorithm; completing the prediction of the clinker strength at the cement kiln outlet through iterative self-learning and continuously outputting the cement kiln process parameter adjustment data.
[0046] By comprehensively optimizing algorithms such as progressive optimization, advancing according to different granularities, and performing global optimization, or by using approximate algorithms, including binary methods, the output of the optimization function can be completed. Through iterative self-learning, the strength of the clinker exiting the cement kiln can be predicted and the continuous output guiding the adjustment of cement kiln process parameters can be completed.
[0047] Figure 3 A schematic diagram of a cement kiln process parameter adjustment device based on clinker strength prediction is provided. (See diagram below.) Figure 3As shown, the cement kiln process parameter adjustment device 300 based on the predicted clinker strength includes: The acquisition module 301 is used to acquire the raw material batching ratio and the process parameters of the cement kiln; The first prediction module 302 is used to predict the strength of clinker at a specified time based on the raw material batching ratio and the process parameters of the cement kiln, and obtain the initial clinker strength prediction value at a specified time. The determination module 303 is used to determine the initial clinker strength prediction value over a specified time as the initial reference value for the strength prediction of the clinker after a specified time. The construction module 304 is used to construct a calibrated prediction model of the intensity of kiln clinker for a specified time based on the initial benchmark value, historical clinker strength data and corresponding batches of clinker X-ray diffraction data; The second prediction module 305 is used to make predictions based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material batching ratio and the corresponding chemical analysis data of the raw material, through the calibrated prediction model, to obtain the predicted data of the intensity of the final clinker at a specified time after exiting the kiln. The generation module 306 is used to generate process adjustment parameters for the cement kiln based on the predicted data of the intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw material proportion, and the chemical analysis data of the raw material.
[0048] The cement kiln process parameter adjustment device based on clinker strength prediction provided in this application embodiment has the same technical features as the cement kiln process parameter adjustment method based on clinker strength prediction provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.
[0049] An electronic device provided in this application embodiment, such as Figure 4 As shown, the electronic device 400 includes a processor 402 and a memory 401. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method provided in the above embodiments.
[0050] See Figure 4 The electronic device also includes a bus 403 and a communication interface 404. The processor 402, the communication interface 404 and the memory 401 are connected via the bus 403. The processor 402 is used to execute executable modules, such as computer programs, stored in the memory 401.
[0051] The memory 401 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 404 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.
[0052] Bus 403 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.
[0053] The memory 401 is used to store programs. After receiving an execution instruction, the processor 402 executes the program. The method executed by the apparatus defined by the process disclosed in any of the preceding embodiments of this application can be applied to the processor 402 or implemented by the processor 402.
[0054] Processor 402 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 402 or by instructions in software form. The processor 402 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 401, and processor 402 reads the information from memory 401 and, in conjunction with its hardware, completes the steps of the above method.
[0055] Corresponding to the above-mentioned method for adjusting cement kiln process parameters based on the prediction of clinker strength at the kiln outlet, this application embodiment also provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are called and run by a processor, the computer-executable instructions cause the processor to perform the steps of the above-mentioned method for adjusting cement kiln process parameters based on the prediction of clinker strength at the kiln outlet.
[0056] The cement kiln process parameter adjustment device based on clinker strength prediction provided in this application embodiment can be specific hardware on the equipment or software or firmware installed on the equipment. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the aforementioned method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.
[0057] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0058] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0060] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0061] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the cement kiln process parameter adjustment method based on clinker strength prediction described in various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0062] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0063] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.
Claims
1. A method for adjusting cement kiln process parameters based on the predicted strength of clinker discharged from the kiln, characterized in that, The method includes: Obtain the raw material batching ratio and the process parameters of the cement kiln; Based on the raw material proportioning ratio and the process parameters of the cement kiln, the strength of clinker at a specified time is predicted to obtain the initial clinker strength prediction value at a specified time. The initial clinker strength prediction value over a specified time is determined as the initial benchmark value for the strength prediction of the clinker after a specified time. A calibrated prediction model for the intensity of kiln clinker at a specified time is constructed based on the initial benchmark value, historical clinker strength data, and corresponding batches of clinker X-ray diffraction data. Based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportioning ratio and the corresponding chemical analysis data of the raw materials, the calibrated prediction model is used to predict the intensity of the final clinker at a specified time after exiting the kiln. Based on the predicted intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal, process adjustment parameters for the cement kiln are generated.
2. The method according to claim 1, characterized in that, The raw material proportioning ratio and cement kiln process parameters include the raw material proportioning ratio and key process parameters of the cement kiln. The step of predicting the clinker strength at a specified time based on the raw material batching and cement kiln process parameters, and obtaining the predicted clinker strength at a specified time, includes: A basic clinker strength prediction model was obtained through model training based on historical clinker data from kilns. Abnormal data in the raw material batching ratio and key process parameters of cement kiln are eliminated by preprocessing the raw material batching ratio and key process parameters of cement kiln to obtain preprocessed data. The preprocessed data is used as the input features of the basic clinker strength prediction model. Based on the input features, the basic clinker strength prediction model is used to calculate the basic clinker strength prediction value for a specified time.
3. The method according to claim 1, characterized in that, The calibrated prediction model for the intensity of kiln clinker at a specified time, constructed based on the initial benchmark value, historical clinker strength data, and corresponding batches of clinker X-ray diffraction data, includes: Obtain historical clinker intensity measurement data for a specified duration and corresponding batches of clinker X-ray diffraction data; The measured intensity data of the historical clinker over a specified time and the X-ray diffraction data of the corresponding batch of clinker are correlated and matched with the initial reference value to obtain the feature matching result; Based on the feature matching results, a calibrated prediction model for the intensity of kiln clinker over a specified time is constructed using deep learning to complete the model calibration.
4. The method according to claim 1, characterized in that, The clinker X-ray diffraction data are the actual measured data of clinker exiting the kiln; The step of predicting the intensity of the clinker at a specified time after discharge from the kiln using the calibrated prediction model, based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material proportioning, and the chemical analysis data of the raw materials, includes: The measured X-ray diffraction data of the clinker exiting the kiln, the current process parameters of the cement kiln, the raw material proportion, and the chemical analysis data of the raw materials are used as dynamic feedback features and continuously input into the calibrated prediction model for prediction. This allows the calibrated prediction model to adapt to the fluctuations in the operating conditions during the production process. Through real-time feedback iteration, the predicted data of the intensity of the clinker exiting the kiln for a specified time is obtained as the output result.
5. The method according to claim 4, characterized in that, The process adjustment parameters for the cement kiln are generated based on the predicted intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal. Based on the predicted intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw material proportioning, and the chemical analysis data of the raw material, the optimal adjustment range of the process parameters for the cement kiln is obtained by calculation through the process parameter optimization model within the algorithm.
6. The method according to claim 5, characterized in that, Before calculating the optimal adjustment range of the process parameters for the cement kiln based on the predicted data of the final clinker intensity at a specified time, the clinker X-ray diffraction data, the raw meal proportion, and the chemical analysis data of the raw meal, using the process parameter optimization model within the algorithm, the following steps are also included: A function set M is constructed to represent the process parameter optimization model through functions. The function set M contains sub-functions [M1, M2, M3...Mn] covering the entire process. M1 is an index function, which is an implicit function containing all control variables and external variables, used to calculate the output optimization function through machine learning algorithms.
7. The method according to claim 6, characterized in that, The optimized function calculated and output by the machine learning algorithm includes: The optimization function is calculated by advancing the algorithm according to different granularities to complete the global optimization, and / or by calculating the optimization function through an approximation algorithm. The system uses iterative self-learning to predict the strength of clinker exiting the cement kiln and continuously outputs data for adjusting cement kiln process parameters.
8. A cement kiln process parameter adjustment device based on clinker strength prediction, characterized in that, include: The acquisition module is used to acquire the raw material batching ratio and the process parameters of the cement kiln; The first prediction module is used to predict the strength of clinker at a specified time based on the raw material proportion and the process parameters of the cement kiln, and to obtain the initial clinker strength prediction value at a specified time. The determination module is used to determine the initial clinker strength prediction value over a specified time as the initial benchmark value for the strength prediction of the clinker exiting the kiln over a specified time. The construction module is used to construct a calibrated prediction model of the intensity of kiln clinker for a specified time based on the initial benchmark value, historical clinker strength data and corresponding batches of clinker X-ray diffraction data; The second prediction module is used to make predictions based on the clinker X-ray diffraction data, the process parameters of the cement kiln, the raw material batching ratio and the corresponding chemical analysis data of the raw materials, through the calibrated prediction model, to obtain the predicted data of the final clinker intensity at a specified time after exiting the kiln. The generation module is used to generate process adjustment parameters for the cement kiln based on the predicted data of the intensity of the final clinker at a specified time, the clinker X-ray diffraction data, the raw material proportion, and the chemical analysis data of the raw material.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.