Cement industry-oriented quality data modeling method and device and storage medium

Abstract

The embodiment of the invention provides a cement industry-oriented quality data modeling method, which comprises the following steps of: acquiring data of each key process in cement production in real time; the key process data comprises a raw material ratio, a calcining temperature, a cooling rate and grinding fineness; based on a Pearson correlation analysis method, analyzing correlation between the key process data and the cement quality to obtain strong correlation data; and based on a Light GBM algorithm, according to the strong correlation data, obtaining a cement strength prediction value. The proportion of raw materials can be adjusted in real time, and the production quality and production efficiency of cement are improved.

Description

Technical Field

[0001] This document relates to the technical field of cement production quality control, and particularly to a quality data modeling method, device, and storage medium for the cement industry. Background Art

[0002] Cement is one of the important building materials. Whether it is large-scale infrastructure such as bridges, roads, tunnels, dams, or ports, cement is indispensable. The adhesiveness and strength of cement enable it to firmly bond these building components together and provide stable structural support.

[0003] The production of cement involves multiple links (such as raw material crushing, grinding, firing, cooling, etc.), and each link affects each other. Factors such as fluctuations in raw material composition and changes in equipment status can lead to unstable product quality. When producing cement, existing methods mainly use automated control systems (such as DCS, PLC) to monitor the production process. Statistical Process Control (SPC) and machine learning models are used to predict product quality.

[0004] However, the automated system relies on manual experience to adjust parameters and lacks intelligence. The accuracy of data modeling is limited by data quality and algorithm capabilities, and it is difficult to handle complex working conditions. There is a lack of real-time performance, unable to quickly respond to production fluctuations, and the detection results lag behind the production process, making it difficult to adjust parameters in a timely manner, thus resulting in low product quality. Summary of the Invention

[0005] In view of the above solutions, the present application aims to propose a quality data modeling method, device, and storage medium for the cement industry to solve at least one of the above technical problems.

[0006] In a first aspect, one or more embodiments of this specification provide a quality data modeling method for the cement industry, including:

[0007] Real-time collect data of each key process in cement production; the key process data includes raw material ratio, calcination temperature, cooling rate, and grinding fineness;

[0008] Based on the Pearson correlation analysis method, analyze the correlation between each key process data and cement quality to obtain strongly correlated data; and

[0009] Based on the LightGBM algorithm, obtain the predicted value of cement strength according to the strongly correlated data.

[0010] Further, each key process data includes:

[0011] Based on the min-max normalization method, perform data processing on each key process data to obtain preprocessed key process data;

[0012] The key process data for preprocessing is calculated by the following method:

[0013]

[0014] Among them, k ′ represents the key process data after preprocessing; and

[0015] k represents each of the key process data.

[0016] Furthermore, based on the Pearson correlation analysis method, analyzing the correlation between each of the key process data and the cement quality, the strongly correlated data includes:

[0017] Based on the Pearson correlation analysis method, according to each of the key process data, the Pearson correlation coefficient is obtained;

[0018] judging whether each of the Pearson correlation coefficients is greater than a preset threshold, and

[0019] if it is greater than or equal to the preset threshold, then strongly correlated data is obtained.

[0020] Furthermore, the Pearson correlation coefficient is calculated by the following method:

[0021]

[0022] r represents the correlation coefficient value;

[0023] n represents the number of samples;

[0024] i represents the i-th sample;

[0025] x represents the key process data; and

[0026] y represents the cement strength value.

[0027] Furthermore, when the key process data in cement production is collected in real time, it also includes:

[0028] Using near-infrared spectroscopy (NIR) and X-ray fluorescence analysis (XRF) for real-time data analysis.

[0029] In a second aspect, an embodiment of the present application provides a quality data modeling device for the cement industry, including,

[0030] A collection module for collecting in real time the key process data in cement production; the key process data includes raw material ratio, calcination temperature, cooling rate, and grinding fineness;

[0031] An analysis module for analyzing the correlation between each of the key process data and the cement quality based on the Pearson correlation analysis method to obtain strongly correlated data; and

[0032] A prediction module, configured to obtain a predicted value of cement strength based on the LightGBM algorithm and according to strongly correlated data.

[0033] Further, it further includes a first calculation module.

[0034] Based on the min-max normalization method, perform data processing on each of the key process data to obtain preprocessed key process data.

[0035] The preprocessed key process data is calculated by the following method:

[0036]

[0037] where k ′ represents the preprocessed key process data; and

[0038] k represents each of the key process data.

[0039] Further, the analysis module is configured to:

[0040] Based on the Pearson correlation analysis method, obtain the Pearson correlation coefficient according to each of the key process data;

[0041] Judge whether each of the Pearson correlation coefficients is greater than a preset threshold, and

[0042] If it is greater than or equal to the preset threshold, obtain strongly correlated data.

[0043] Further, it further includes a second calculation module.

[0044] The Pearson correlation coefficient is calculated by the following method:

[0045]

[0046] r represents the correlation coefficient value;

[0047] n represents the number of samples;

[0048] i represents the i-th sample;

[0049] x represents the key process data; and

[0050] y represents the cement strength value.

[0051] In a third aspect, an embodiment of the present application provides a storage medium for storing computer-executable instructions, characterized in that the computer-executable instructions, when executed, implement the steps of the quality data modeling method for the cement industry described in any item of the first aspect.

[0052] Compared with the prior art, the present application can at least achieve the following technical effects:

[0053] This application can monitor and analyze the data of each key process in the cement production process in real time, understand the production status in a timely manner, and quickly make adjustments once data anomalies are found, ensuring the stability and reliability of the production process and improving production efficiency. Then, through Pearson correlation analysis and the LightGBM algorithm, real-time and accurate prediction of cement quality can be achieved, improving product quality. Brief Description of the Drawings

[0054] In order to more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a flowchart of a quality data modeling method for the cement industry provided for one or more embodiments of this specification;

[0056] Figure 2 It is a schematic structural diagram of a quality data modeling device for the cement industry provided for one or more embodiments of this specification. Detailed Embodiments

[0057] In order to enable those skilled in the art of this technology to better understand the technical solutions in one or more embodiments of this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification 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, rather than all of them. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0058] During the production process of cement, due to various factors such as raw materials, technology, and human factors, the quality of cement will vary. Among them, raw material factors include fluctuations in raw material composition resulting in unstable chemical composition of clinker, the use of alternative raw materials leading to unstable composition and performance, and uneven particle size distribution of raw materials affecting the firing reaction of cement. Process factors include inaccurate raw meal proportioning resulting in deviation of clinker mineral composition from the target value and affecting cement performance, insufficient homogenization of raw meal leading to uneven chemical composition of clinker and affecting cement quality, too high or too low firing temperature both affecting the mineral composition and structure of clinker, and too fast or too slow cooling rate affecting the mineral composition and crystal structure of clinker. Human factors include the technical level and work attitude of operators that may affect the stability of the production process, and inadequate production management that may lead to lax control of process parameters and affect cement quality.

[0059] To address the above technical problems, this application proposes a quality data modeling method for the cement industry, as Figure 1 shown, which specifically includes:

[0060] Step S1, collect data of each key process in cement production in real time; the key process data includes raw material proportioning, calcination temperature, cooling rate, and grinding fineness.

[0061] In the embodiment of this application, sensors and analysis equipment are deployed on key equipment to monitor parameters such as vibration, temperature, and pressure in real time. First, raw material proportioning detection: Use load cells and flow meters to monitor the proportion of raw materials such as limestone, clay, and iron ore in real time. Chemical composition analysis: Introduce near-infrared spectroscopy (NIR) to analyze the raw material composition online, and deploy X-ray fluorescence analysis (XRF) equipment to detect the elemental composition of clinker and finished products in real time. Second, calcination temperature monitoring: Install high-temperature thermocouples in the calcination kiln to collect the temperature of the firing zone in real time. Cooling rate monitoring: Monitor the temperature change of clinker from the outlet of the calcination kiln to the cooler through an infrared thermometer and calculate the cooling rate. Grinding fineness monitoring: Use a laser particle size analyzer to measure the surface area of cement particles in real time. Finally, based on the monitoring and analysis of different processes of cement, key process data such as raw material proportioning, calcination temperature, cooling rate, and grinding fineness are obtained.

[0062] Further, data preprocessing is performed on the key process data. By cleaning and standardizing the data, high-quality input is provided for subsequent analysis. Among them, data cleaning is to remove duplicate data, missing data, and outliers. For example, the outlier method using box plot or Z-score method is used to eliminate outliers. By setting a reasonable threshold range, data that obviously does not conform to the production logic is filtered out (such as the calcination temperature > 1500 °C or < 1200 °C. If it is not within this range, this part of the data is excluded). Standardizing the data is to perform data processing on each of the key process data based on the min-max normalization method, scale the data with different dimensions into the interval [0, 1], ensure that each parameter is compared on the same scale, and obtain the preprocessed key process data;

[0063] The preprocessed key process data is calculated by the following method:

[0064]

[0065] Among them, k ′ represents the preprocessed key process data; and

[0066] k represents each of the key process data.

[0067] For example: normalize the calcination temperature, the original range is 1400 °C to 1500 °C, and the normalized range is 0.0 to 1.0.

[0068] Step S2, based on the Pearson correlation analysis method, analyze the correlation between each of the key process data and the cement quality to obtain strongly correlated data.

[0069] In the embodiment of the present application, based on the Pearson correlation analysis method, according to each of the key process data, the Pearson correlation coefficient is obtained; it is judged whether each of the Pearson correlation coefficients is greater than a preset threshold, and if it is greater than or equal to the preset threshold, strongly correlated data is obtained.

[0070] Specifically, through the Pearson correlation analysis method, the linear correlation between each key process data and the cement strength is quantified, and the correlation coefficient between each process data and the cement is obtained. The preset threshold of the correlation coefficient is used to screen out the key process data with strong correlation with the cement strength to obtain strongly correlated data.

[0071] The Pearson correlation coefficient is calculated by the following method:

[0072]

[0073] r represents the correlation coefficient value;

[0074] n represents the number of samples;

[0075] i represents the i-th sample;

[0076] x represents key process data (such as calcination temperature); and

[0077] y represents the cement strength value.

[0078] For example: Using the Pearson correlation analysis method, the correlation coefficient between the calcination temperature and the cement strength is 0.82, the correlation coefficient between the limestone ratio and the cement strength is 0.75, the correlation coefficient between the cooling rate and the cement strength is 0.12, and the correlation coefficient between the grinding fineness and the cement strength is 0.65. When the correlation threshold is greater than or equal to 0.5, it is a strong correlation. Therefore, the data strongly correlated with the cement quality are screened out as the calcination temperature, the limestone ratio, and the grinding fineness.

[0079] Through Pearson correlation analysis, this application scientifically identifies the strongly correlated parameters in the key process data, providing a core basis for subsequent machine learning modeling and real-time control, thereby significantly improving the accuracy and efficiency of cement production quality control.

[0080] Step S3, based on the LightGBM algorithm, obtain the predicted value of the cement strength according to the strongly correlated data.

[0081] In the embodiment of this application, use the LightGBM algorithm to train a regression model to predict the cement strength. First, collect historical data and divide the historical data into a training set and a test set. Initialize the model, set the initial parameters of LightGBM to balance the training speed and accuracy. Then construct a feature histogram. LightGBM uses the histogram algorithm to discretize continuous features to reduce the amount of calculation and memory usage; for each feature, construct a histogram and record its statistical information in different intervals. Secondly, perform iterative training on the model. Build multiple decision trees (learners) in an iterative manner. Each learner tries to correct the mistakes of the previous learner; in each iteration, optimize the model according to the gradient information to minimize the loss function. Then adopt the leaf-wise growth strategy, select the node with the largest split gain from all current leaf nodes for splitting, select the optimal feature and split point according to the split gain, and gradually generate a more complex decision tree structure. Then, prevent overfitting by setting the maximum depth limit, using L1 and L2 regularization terms, implementing the backward pruning strategy, etc.; cross-validation can be used to evaluate the generalization ability of the model and adjust the parameters to optimize the performance. Next, use the test set to evaluate the performance of the model, calculate the error between the predicted value and the true value, such as the mean square error (MSE), the mean absolute error (MAE), etc. Then adjust the model parameters according to the evaluation results to finally obtain a trained LightGBM model. Then use the trained LightGBM model to predict new cement data to obtain the predicted value of the cement strength.

[0082] Predicting the cement strength through the LightGBM model not only improves the prediction accuracy of cement quality but also realizes the real-time optimization of the production process, thus enhancing the production efficiency of cement.

[0083] In this application, online learning technology can also be introduced to update the LightGBM model online, achieving dynamic self-adaptation of the model and continuously enhancing the intelligent level of production quality.

[0084] The embodiment of this application provides a quality data modeling device for the cement industry, as Figure 2 shown, including

[0085] A collection module 101 for collecting data of each key process in cement production in real time; the key process data includes raw material ratio, calcination temperature, cooling rate, and grinding fineness.

[0086] An analysis module 102 for analyzing the correlation between each key process data and cement quality based on the Pearson correlation analysis method to obtain strongly correlated data; and

[0087] A prediction module 103 for obtaining the predicted value of cement strength based on the LightGBM algorithm according to the strongly correlated data.

[0088] Furthermore, it further includes a first calculation module

[0089] Based on the min-max normalization method, process the key process data to obtain preprocessed key process data.

[0090] The preprocessed key process data is calculated by the following method:

[0091]

[0092] where k ′ represents the preprocessed key process data; and

[0093] k represents each key process data.

[0094] Furthermore, the analysis module is configured to:

[0095] Based on the Pearson correlation analysis method, obtain the Pearson correlation coefficient according to each key process data;

[0096] Judge whether each Pearson correlation coefficient is greater than a preset threshold, and

[0097] If it is greater than or equal to the preset threshold, obtain strongly correlated data.

[0098] Furthermore, it further includes a second calculation module

[0099] The Pearson correlation coefficient is calculated by the following method:

[0100]

[0101] r represents the correlation coefficient value;

[0102] n represents the number of samples;

[0103] i represents the i-th sample;

[0104] x represents the key process data; and

[0105] y represents the cement strength value.

[0106] An embodiment of the present application provides a storage medium for storing computer-executable instructions, characterized in that the computer-executable instructions, when executed, implement the steps of the quality data modeling method for the cement industry described in any one of the above embodiments.

[0107] It should be noted that the embodiment of the storage medium in this specification and the embodiment of the blockchain-based service providing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the corresponding implementation of the blockchain-based service providing method described above, and the repeated parts will not be elaborated.

[0108] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not just one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing some logical programming on the method flow using the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0110] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0111] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0112] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0113] Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0114] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks or multiple blocks.

[0115] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks or multiple blocks.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 means for implementing the functions specified in one or more of the blocks or multiple blocks.

[0117] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0118] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0120] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0121] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0122] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0123] The above are only examples of this document and are not intended to limit this document. For those skilled in the art, this document may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document shall be included within the scope of the claims of this document.

Claims

1. A quality data modeling method for the cement industry, characterized in that including: Real-time collection of data on key processes in cement production; the key process data includes raw material ratio, calcination temperature, cooling rate, and grinding fineness; Based on the Pearson correlation analysis method, analyzing the correlation between each of the key process data and cement quality to obtain strongly correlated data; and Based on the LightGBM algorithm, obtaining a predicted value of cement strength according to the strongly correlated data.

2. The method according to claim 1, wherein Each of the key process data includes: Based on the min-max normalization method, performing data processing on each of the key process data to obtain preprocessed key process data; The preprocessed key process data is calculated by the following method: where k ′ represents the key process data after preprocessing; and k represents each of the key process data.

3. The method according to claim 1, wherein Analyzing the correlation between each of the key process data and cement quality based on the Pearson correlation analysis method to obtain strongly correlated data includes: Based on the Pearson correlation analysis method, obtaining a Pearson correlation coefficient according to each of the key process data; Judging whether each of the Pearson correlation coefficients is greater than a preset threshold, and If it is greater than or equal to the preset threshold, then strongly correlated data is obtained.

4. The method according to claim 3, wherein The Pearson correlation coefficient is calculated by the following method: r represents the correlation coefficient value; n represents the number of samples; i represents the i-th sample; x represents the key process data; and y represents the cement strength value.

5. The method according to claim 1, wherein When collecting data on key processes in cement production in real time, it further includes: Using near-infrared spectroscopy (NIR) and X-ray fluorescence analysis (XRF) for real-time data analysis.

6. A quality data modeling device for the cement industry, characterized in that including, A collection module for real-time collection of data on key processes in cement production; the key process data includes raw material ratio, calcination temperature, cooling rate, and grinding fineness; An analysis module for analyzing the correlation between each of the key process data and cement quality based on the Pearson correlation analysis method to obtain strongly correlated data; and A prediction module for obtaining a predicted value of cement strength based on the LightGBM algorithm according to the strongly correlated data.

7. The device according to claim 6, wherein The device further includes a first calculation module, Based on the min-max normalization method, performing data processing on each of the key process data to obtain preprocessed key process data; The preprocessed key process data is calculated by the following method: where k ′ represents the key process data after preprocessing; and k represents each of the key process data.

8. The device according to claim 6, characterized in that The analysis module is configured to: Based on the Pearson correlation analysis method, obtaining a Pearson correlation coefficient according to each of the key process data; Judging whether each of the Pearson correlation coefficients is greater than a preset threshold, and If it is greater than or equal to the preset threshold, then strongly correlated data is obtained.

9. The device according to claim 8, characterized in that The device further includes a second calculation module, The Pearson correlation coefficient is calculated by the following method: r represents the correlation coefficient value; n represents the number of samples; i represents the i-th sample; x represents the key process data; and y represents the cement strength value.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed, implement the steps of the quality data modeling method for the cement industry according to any one of claims 1-5.

Images