Big data-based silicon steel magnesia production process adjustment system and method

Abstract

The application relates to the technical field of silicon steel magnesium oxide production, and provides a silicon steel magnesium oxide production process adjustment system and method based on big data. First, state data of a silicon steel magnesium oxide coating to be transported, a transportation environment vibration, a transportation vehicle body structure and the magnesium oxide coating are collected; a mechanical imbalance comprehensive index is calculated based on the mechanical and structural state data, and magnesium oxide coating wear analysis is carried out in combination with the functional state data. Secondly, a transportation damage risk prediction model is established by using historical transportation environment vibration and vehicle body structure data to evaluate the transportation damage risk of the silicon steel magnesium oxide coating to be transported. Then, the coating wear analysis result and the transportation damage risk prediction value are comprehensively combined to obtain a failure risk prediction value of the silicon steel magnesium oxide coating to be transported. Finally, the failure risk prediction value is used to realize the determination and diversion of the silicon steel magnesium oxide product, and unqualified products are returned to the factory.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of silicon steel magnesium oxide production, and in particular to a silicon steel magnesium oxide production process adjustment system and method based on big data. BACKGROUND

[0002] Silicon steel is an important soft magnetic alloy and is widely used in the electrical industry. In its production process, coating a magnesium oxide coating on the surface of the silicon steel sheet is one of the key processes. The coating mainly plays the role of isolating the silicon steel sheets, preventing sintering during high-temperature annealing, and improving the magnetic properties of the silicon steel sheets. However, the quality of the coating is easily affected by fluctuations in the production process parameters. In addition, during subsequent transportation, environmental vibrations on the transportation route and the transportation vehicle structure can also cause wear and even damage to the coating, thereby increasing the risk of failure.

[0003] Current magnesium oxide coating production process adjustment relies mainly on human experience and lacks systematic and quantitative analysis of the intrinsic properties of the magnesium oxide coating and the risk of external transportation damage. On the one hand, existing technologies cannot accurately assess the mechanical properties of the magnesium oxide coating (i.e., mechanical imbalance) and the resulting wear tendency; on the other hand, existing methods cannot effectively predict the dynamic damage risk of the magnesium oxide coating under specific transportation conditions.

[0004] Big data technology provides a new path to solve the above problems, but its application depth in the field of silicon steel magnesium oxide coating production process optimization still needs to be expanded. Currently, data applications in this field are mainly concentrated in single-link monitoring, and in multiple key links, including multi-state data fusion analysis of coating performance, quantitative prediction of transportation damage risk, and dynamic optimization of production process parameters based on risk feedback, no systematic solution has been formed. SUMMARY

[0005] To overcome the problems of relying on experience, ignoring transportation damage risk, and lagging adjustment in the existing silicon steel magnesium oxide coating production process adjustment, the present application provides a silicon steel magnesium oxide production process adjustment system and method based on big data. The method realizes accurate prediction of the failure risk of the magnesium oxide coating by constructing a magnesium oxide coating wear state prediction model and integrating a transportation damage risk prediction model, and accordingly realizes the judgment and diversion of products. The system is used to realize each step of the above method.

[0006] To achieve the above purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a silicon steel magnesium oxide production process adjustment method based on big data, comprising the following steps:

[0008] S1, obtain environmental vibration data and transportation vehicle body structure data on the transportation route of the to-be-transported silicon steel magnesium oxide coating, and simultaneously obtain mechanical state data, functional state data and structural state data of the magnesium oxide coating, and production process parameters of the magnesium oxide coating;

[0009] S2, based on the mechanical state data of the magnesium oxide coating and the structural state data of the magnesium oxide coating, obtain a mechanical imbalance comprehensive index of the magnesium oxide coating, and combine the mechanical imbalance comprehensive index of the magnesium oxide coating with the functional state data of the magnesium oxide coating to analyze the wear state of the magnesium oxide coating;

[0010] S3, based on the environmental vibration data on the corresponding historical silicon steel transportation route of the same coating process as the to-be-transported silicon steel magnesium oxide coating, and the transportation vehicle body structure data of the corresponding historical silicon steel, a transportation damage risk prediction model is constructed to predict the transportation damage risk of the to-be-transported silicon steel magnesium oxide coating;

[0011] S4, combining the wear state analysis result of the magnesium oxide coating and the transportation damage risk prediction value of the to-be-transported silicon steel magnesium oxide coating, a failure risk prediction value of the to-be-transported silicon steel magnesium oxide coating is obtained;

[0012] S5, through the failure risk prediction value of the to-be-transported silicon steel magnesium oxide coating, the to-be-transported silicon steel magnesium oxide coating is judged and divided.

[0013] According to the above technical scheme, the steps of obtaining the environmental vibration data and the transportation vehicle body structure data on the transportation route of the to-be-transported silicon steel magnesium oxide coating, and simultaneously obtaining the mechanical state data, the functional state data and the structural state data of the magnesium oxide coating, and the production process parameters of the magnesium oxide coating include:

[0014] Firstly, the transportation route environmental vibration data is obtained, including vibration time domain signal and preprocessed clean vibration data; secondly, the transportation vehicle body structure data is obtained, including the frequency response function data set obtained by experimental modal testing; thirdly, the mechanical state data of the magnesium oxide coating is obtained, including hardness, elastic modulus, material density, yield strength estimate value, critical failure stress, interface bonding strength, equivalent damping ratio, material fatigue index and fatigue strength limit; the surface insulation resistance value of the functional state data; the surface three-dimensional topography feature and cross-section topography image of the structural state data; and the planned transportation time of the production process parameter; through comprehensive collection and standardization preprocessing of the above-mentioned multi-source data, a complete and reliable data foundation is laid for subsequent coating state analysis and risk prediction.

[0015] According to the technical solution, the mechanical imbalance comprehensive index of the magnesium oxide coating is obtained based on the mechanical state data and the structural state data of the magnesium oxide coating, and the wear state analysis of the magnesium oxide coating is performed in combination with the mechanical imbalance comprehensive index and the functional state data of the magnesium oxide coating.

[0016] Based on the hardness and the elastic modulus in the mechanical state data of the magnesium oxide coating, the elastic strain limit of the magnesium oxide coating is obtained by calculating the ratio of the hardness to the elastic modulus; the elastic strain limit indicates that the elastic strain capacity of the magnesium oxide coating is proportional to the hardness and inversely proportional to the elastic modulus, and the quantitative influence law of the hardness and the elastic modulus on the elasticity of the magnesium oxide coating is determined.

[0017] In combination with the surface morphology and the cross-sectional morphology in the structural state data of the magnesium oxide coating and the elastic modulus in the mechanical state data of the magnesium oxide coating, the stress concentration coefficient of the magnesium oxide coating is obtained by simulating and analyzing the stress concentration effect caused by the microstructure non-uniformity of the magnesium oxide coating by using the finite element method; specifically, first, a finite element model reflecting the real microstructure is established according to the surface and cross-sectional morphologies, and the elastic modulus is input as a material property; then, a standard normal load is applied for finite element calculation, and the stress distribution cloud diagram of the surface and the interface region of the magnesium oxide coating is extracted; finally, the stress concentration coefficient is obtained by calculating the ratio of the maximum stress value to the average stress value in the stress distribution cloud diagram. The coefficient reveals the weak link of the coating at the microscale and quantifies the amplification law of the micro-morphology on the local stress through numerical simulation.

[0018] In combination with the stress concentration coefficient, the critical failure stress, the interface bonding strength, the elastic strain limit and the yield strength estimate value of the magnesium oxide coating, the weights of the five parameters are determined by using the analytic hierarchy process, and a comprehensive analysis is performed based on the linear weighting method to obtain the mechanical imbalance comprehensive index of the magnesium oxide coating; wherein the analytic hierarchy process is to construct a judgment matrix and calculate a characteristic vector to determine the weight coefficients of the two.

[0019] Based on the mechanical imbalance comprehensive index of the magnesium oxide coating, the elastic strain limit and the yield strength estimate value of the magnesium oxide coating, and the functional state data of the magnesium oxide coating, a non-linear mapping relationship between the essential attributes and the wear state of the magnesium oxide coating is established by using the extreme learning machine, a data-driven wear state prediction model of the magnesium oxide coating is obtained, and the wear state analysis of the magnesium oxide coating is realized; in specific implementation, the mechanical imbalance comprehensive index, the elastic strain limit, the yield strength estimate value and the functional state data of the magnesium oxide coating are taken as input features, and the experimentally measured wear state of the magnesium oxide coating is taken as output labels to train the extreme learning machine model, the optimal network structure parameters are determined through cross-validation, and finally the data-driven wear state prediction model of the magnesium oxide coating is established.

[0020] According to the technical scheme, based on the environmental vibration data on the historical silicon steel transportation route corresponding to the coating process of the silicon steel magnesium oxide coating to be transported and the transportation vehicle body structure data of the corresponding historical silicon steel, a transportation damage risk prediction model is constructed, and the step of predicting the transportation damage risk of the silicon steel magnesium oxide coating to be transported includes:

[0021] Based on the environmental vibration data on the historical silicon steel transportation route corresponding to the coating process of the silicon steel magnesium oxide coating to be transported, the vibration acceleration root mean square value and the vibration main frequency on the corresponding historical silicon steel transportation route are calculated; specifically, the vibration acceleration root mean square value is calculated by using the vibration intensity evaluation method, and the value represents the average vibration energy intensity in the transportation process; at the same time, the vibration main frequency is identified based on the frequency spectrum analysis technology of fast Fourier transform (FFT), and the frequency reflects the dominant excitation component in the transportation environment; the above two characteristic indexes jointly constitute the quantitative basis of the transportation environment vibration characteristics;

[0022] Based on the transportation vehicle body structure data of the corresponding historical silicon steel of the coating process of the silicon steel magnesium oxide coating to be transported, the dominant natural frequency of the transportation vehicle body structure of the corresponding historical silicon steel and the transportation vehicle body damping ratio are extracted; wherein the dominant natural frequency is obtained by the modal analysis method, and is used to represent the dynamic characteristics of the transportation vehicle body structure itself; the damping ratio is calculated and determined based on the half-power bandwidth method by analyzing the bandwidth of the frequency response function curve at the resonance peak;

[0023] Based on the known material parameters and structure parameters of the silicon steel magnesium oxide coating to be transported, including the elastic modulus, the material density and the magnesium oxide coating thickness, the equivalent natural frequency of the silicon steel magnesium oxide coating to be transported is calculated by using the classical dynamics formula;

[0024] By comparing the vibration main frequency of the historical transportation route with the equivalent natural frequency of the silicon steel magnesium oxide coating to be transported and the dominant natural frequency of the transportation vehicle body, and combining the equivalent damping ratio of the magnesium oxide coating with the damping ratio of the transportation vehicle body, the dynamic load amplification factor of the silicon steel magnesium oxide coating to be transported is calculated; specifically, based on the calculated data, the dynamic load amplification factor of the magnesium oxide coating itself resonance and the dynamic load amplification factor caused by the transportation vehicle body structure resonance are calculated, and the maximum value of the two is taken as the dynamic load amplification factor of the silicon steel magnesium oxide coating to be transported;

[0025] The equivalent alternating stress amplitude calculated by the stress acceleration coefficient calibrated by the finite element simulation, the vibration main frequency action time of the historical transportation route, and the mechanical imbalance index of the silicon steel magnesium oxide coating to be transported are comprehensively calculated to obtain the transportation damage risk prediction value of the silicon steel magnesium oxide coating to be transported; wherein the equivalent alternating stress amplitude is calculated based on the vibration acceleration root mean square value of the corresponding historical silicon steel transportation route, the dynamic load amplification factor of the silicon steel magnesium oxide coating to be transported, and the stress acceleration coefficient calibrated by the finite element simulation.

[0026] According to the above technical scheme, the step of obtaining the failure risk prediction value of the silicon steel magnesium oxide coating to be transported in combination with the magnesium oxide coating wear state analysis result and the transportation damage risk prediction value of the silicon steel magnesium oxide coating to be transported includes:

[0027] The weight coefficients of the magnesium oxide coating wear state analysis result and the transportation damage risk prediction value of the silicon steel magnesium oxide coating to be transported are determined by the analytic hierarchy process;

[0028] Based on the magnesium oxide coating wear state analysis result, the transportation damage risk prediction value of the silicon steel magnesium oxide coating to be transported, and the determined weight coefficients, the failure risk prediction value of the silicon steel magnesium oxide coating to be transported is calculated by the linear weighting method.

[0029] According to the above technical scheme, the silicon steel magnesium oxide coating to be transported is judged and divided according to the failure risk prediction value of the silicon steel magnesium oxide coating to be transported, including the following steps:

[0030] The silicon steel magnesium oxide coating to be transported is judged based on the set failure risk judgment threshold and the failure risk prediction value of the silicon steel magnesium oxide coating to be transported; wherein the determination of the failure risk judgment threshold specifically includes: a large number of historical samples are analyzed by backtracking to establish the corresponding relationship between the failure risk prediction value and whether the magnesium oxide coating fails after actual transportation, and a statistical distribution method is used, such as determining quantile based on the prediction value distribution of historical qualified samples, to finally set a failure risk judgment threshold that can effectively distinguish qualified products from high-risk products;

[0031] When the failure risk prediction value is less than or equal to the failure risk judgment threshold, it is determined that the silicon steel magnesium oxide coating to be transported is safe; when the failure risk prediction value is greater than the failure risk judgment threshold, it is determined that the silicon steel magnesium oxide coating to be transported has a transportation damage risk and is subjected to factory process tracing treatment.

[0032] In a second aspect, the application provides a silicon steel magnesium production process adjustment system based on big data, which comprises:

[0033] The data acquisition module is used to acquire environmental vibration data and vehicle structure data along the transportation route of the magnesium oxide coating on the silicon steel to be transported. It also acquires mechanical state data, functional state data, and structural state data of the magnesium oxide coating, as well as the production process parameters of the magnesium oxide coating. This module achieves unified acquisition and format conversion of the above-mentioned multi-source heterogeneous data through a standardized data interface, providing a reliable data foundation for subsequent analysis.

[0034] The wear analysis module is used to obtain the comprehensive mechanical imbalance index of the magnesium oxide coating based on the mechanical state data and structural state data of the magnesium oxide coating. It then combines the comprehensive mechanical imbalance index with the functional state data of the magnesium oxide coating to perform wear state analysis. This module uses finite element modeling, analytic hierarchy process (AHP) and limit learning machine model to achieve intelligent evaluation from the microstructure of the coating to the macroscopic wear state, completing multi-dimensional quantitative analysis and prediction of the coating state.

[0035] The transportation damage risk prediction module is used to construct a transportation damage risk prediction model based on environmental vibration data of the corresponding historical silicon steel transportation route with the same coating process as the magnesium oxide coating of the silicon steel to be transported, and the corresponding historical silicon steel transportation vehicle structure data, so as to predict the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported. This module achieves quantitative assessment of transportation damage risk by integrating environmental vibration characteristics, vehicle structure dynamic characteristics and coating mechanical properties.

[0036] The failure risk prediction module is used to combine the wear state analysis results of the magnesium oxide coating with the transportation damage risk prediction value of the magnesium oxide coating of the silicon steel to be transported, and obtain the failure risk prediction value of the magnesium oxide coating of the silicon steel to be transported. The module determines the weight of each risk factor through the analytic hierarchy process and adopts the linear weighted fusion technology to integrate the inherent characteristics of the coating and external risk factors, so as to achieve accurate prediction of the coating failure risk.

[0037] The quality assessment and diversion module assesses and diverts the magnesium oxide coating on silicon steel to be transported based on the predicted failure risk value. This module compares the predicted failure risk value with a preset threshold to determine the safety of the magnesium oxide coating on silicon steel: if the predicted value meets the standard, it is released; if it exceeds the standard, it is automatically intercepted and a return-to-factory traceability analysis is triggered to achieve closed-loop process optimization.

[0038] Thirdly, this application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a method for adjusting the silicon steel magnesium oxide production process based on big data by calling the computer program stored in the memory.

[0039] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method for adjusting the silicon steel magnesium oxide production process based on big data.

[0040] Compared with the prior art, this application has the following advantages and beneficial effects:

[0041] This application achieves accurate assessment of the wear tendency of magnesium oxide coatings by constructing a comprehensive mechanical imbalance index and a data-driven wear state prediction model. Secondly, it achieves quantitative prediction of external transportation damage risks by constructing a transportation damage risk prediction model. Furthermore, by integrating the wear state of the coating with transportation damage risks, it achieves accurate prediction of the overall failure risk of the coating. Finally, based on the failure risk prediction results, optimized production process parameters are derived through a systematic optimization algorithm. This method forms a complete closed loop from data acquisition, state analysis, risk prediction to process optimization, significantly improving the foresight, accuracy, and reliability of adjusting the production process of magnesium oxide coatings on silicon steel. Attached Figure Description

[0042] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0043] Figure 1 This is a schematic diagram of the overall process of the silicon steel magnesium oxide production process adjustment method based on big data provided in the embodiments of this application;

[0044] Figure 2 This is a schematic diagram of the data acquisition and preprocessing process provided in the embodiments of this application;

[0045] Figure 3 This is a schematic diagram of the wear state analysis process for magnesium oxide coatings provided in the embodiments of this application;

[0046] Figure 4 This is a schematic diagram of the construction process of the transportation damage risk prediction model provided in the embodiments of this application;

[0047] Figure 5 This is a schematic diagram of the magnesium oxide coating failure risk prediction process provided in the embodiments of this application;

[0048] Figure 6 This is a schematic diagram of the quality judgment and diversion process provided in the embodiments of this application. Detailed Implementation

[0049] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0050] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of adjusting the silicon steel magnesium oxide production process based on big data, as provided in the embodiments of this application, which specifically includes the following steps:

[0051] S1. Obtain environmental vibration data and vehicle structure data along the transportation route of the magnesium oxide coating on the silicon steel to be transported. At the same time, obtain mechanical state data, functional state data, and structural state data of the magnesium oxide coating, as well as the production process parameters of the magnesium oxide coating.

[0052] Please see Figure 2 , Figure 2 This diagram illustrates the complete technical flow of data acquisition and preprocessing in an embodiment of this application. The diagram employs a three-channel parallel processing architecture, including:

[0053] The left channel is for acquiring mechanical, functional, and structural state data of the magnesium oxide coating. The specific processing flow includes: directly measuring the hardness, elastic modulus, material density, and estimated yield strength of the magnesium oxide coating on the silicon steel substrate surface using a nanoindenter; performing a standard tensile test on the coating sample using a universal testing machine, recording the maximum load at the appearance of the first visible crack, and calculating the critical failure stress based on the cross-sectional area; applying a linearly increasing normal load to the coating surface at a constant speed using a scratch tester, monitoring the critical load signal at interface peeling using an acoustic emission sensor, and calculating the interface bonding strength based on the scratch head geometry parameters; preparing a coating sample and testing it under dynamic conditions. A small alternating load was applied to a mechanical analysis instrument, and the equivalent damping ratio was obtained by calculating the loss factor after measuring the stress-strain phase lag angle. A standard specimen prepared using the same process as the coating to be transported was subjected to axial tensile-compression cyclic loading tests on a universal fatigue testing machine. By setting different stress levels and recording the number of failure cycles of the specimens, stress-life curves were plotted, and a power function model was used for nonlinear regression fitting. The material fatigue index and fatigue strength limit were obtained from the fitting results. The surface insulation resistance value of the magnesium oxide coating was obtained using a four-probe tester. The three-dimensional morphological features of the magnesium oxide coating surface were obtained using a laser confocal microscope. The cross-sectional morphological image of the magnesium oxide coating was obtained using a scanning electron microscope.

[0054] The intermediate channel serves as the acquisition channel for environmental vibration data and vehicle body structure data along the transportation route of the magnesium oxide coating silicon steel to be transported. Specifically, this includes: continuously collecting time-domain vibration signals along the planned transportation route using triaxial accelerometers fixed to key measuring points on the transport vehicle; and sequentially performing least-squares-based detrending processing, 0.5–1000Hz fourth-order Butterworth bandpass filtering, outlier identification and linear interpolation repair based on the 3σ criterion on the raw time-domain vibration signals collected by triaxial accelerometers installed at key measuring points such as the vehicle floor and frame beams. Furthermore, the signals are segmented into 1-second segments and subjected to Hanning windows for leak prevention. The final output is a clean time-domain vibration signal. In the experimental modal test, a broadband transient excitation force signal is collected by striking the preset excitation point of the vehicle frame with a standard impact hammer. At the same time, the dynamic acceleration response signal of the structure is measured synchronously by triaxial accelerometers arranged at each modal response point. For the experimental modal test data, the transient excitation force signal collected by the standard impact hammer striking the preset excitation point of the vehicle frame and the dynamic acceleration response signal of the structure measured synchronously by the triaxial accelerometers at each modal response point are subjected to more than 10 ensemble averaging processes. And by filtering the effective frequency bands with a coherence function greater than 0.8, a reliable frequency response function dataset is output.

[0055] The right-hand channel is for obtaining magnesium oxide coating process parameters, specifically including: extracting the planned transportation time bound to the production batch from the logistics management module of the manufacturing execution system;

[0056] The data fusion module integrates the data from the three channels, using a unified timestamp and coordinate system. The final output is a standardized dataset containing environmental vibration data, transport vehicle structure data, magnesium oxide coating status data, and production process parameters, providing a complete raw data foundation for subsequent analysis.

[0057] S2. Based on the mechanical state data and structural state data of the magnesium oxide coating, the comprehensive mechanical imbalance index of the magnesium oxide coating is obtained. The wear state of the magnesium oxide coating is analyzed by combining the comprehensive mechanical imbalance index and the functional state data of the magnesium oxide coating.

[0058] Please see Figure 3 , Figure 3 This is a schematic diagram of the wear state analysis process for magnesium oxide coatings provided in this application embodiment. This embodiment demonstrates the complete analysis process from multi-source data input to wear state prediction. The specific steps are as follows:

[0059] The calculation steps for the comprehensive index of mechanical imbalance of magnesium oxide coating include:

[0060] Step S21: Based on the hardness and elastic modulus in the mechanical state data of the magnesium oxide coating, the elastic strain limit of the magnesium oxide coating is obtained by calculating the ratio of hardness to elastic modulus.

[0061] Step S22: Combining the surface morphology, cross-sectional morphology, and elastic modulus in the structural state data of the magnesium oxide coating, the stress concentration effect caused by the microstructural inhomogeneity of the magnesium oxide coating is analyzed by finite element simulation to obtain the stress concentration factor of the magnesium oxide coating. Specifically, this includes: establishing a finite element model reflecting the real microstructure by combining the surface morphology and cross-sectional morphology in the structural state data of the magnesium oxide coating; inputting the elastic modulus of the magnesium oxide coating into the finite element model and applying a standard normal load to the finite element model to calculate the stress distribution of the magnesium oxide coating; then extracting the stress distribution cloud map of the magnesium oxide coating; and obtaining the stress concentration factor of the magnesium oxide coating by calculating the ratio of the maximum stress value to the average stress value in the stress distribution cloud map of the magnesium oxide coating. The larger the stress concentration factor, the higher the risk of brittle fracture and interface peeling of the magnesium oxide coating at micro-defects.

[0062] Step S23: Combining the stress concentration factor, critical failure stress, interfacial bonding strength, elastic strain limit, and yield strength estimate of the magnesium oxide coating, the weight of each parameter is determined using the analytic hierarchy process (AHP), and a comprehensive analysis is performed based on the linear weighted method to obtain the comprehensive index of mechanical imbalance of the magnesium oxide coating; specifically including:

[0063] First, five parameters were collected from n sets of historical qualified magnesium oxide coating samples: stress concentration factor, critical failure stress, interfacial bonding strength, elastic strain limit and yield strength estimate. Based on the collected parameters, an n×5 dimensional sample matrix was constructed.

[0064] Secondly, the sample matrix is ​​Z-score standardized to eliminate the influence of dimensions. The analytic hierarchy process is used, specifically including: constructing a hierarchical structure with the comprehensive mechanical imbalance index as the target layer and five key parameters as the criterion layers; inviting domain experts to conduct pairwise comparisons based on the 1-9 scale to construct a judgment matrix; normalizing the columns and rows of the matrix to obtain the weight vector, and ensuring the rationality of the judgment logic through a consistency test (CR < 0.1).

[0065] Thus, the stress concentration factor and weighting factor of the magnesium oxide coating are obtained. Critical failure stress weighting factor for magnesium oxide coating Interfacial bonding strength weighting coefficient of magnesium oxide coating Elastic strain limit weighting coefficient of magnesium oxide coating Weighting coefficients for the estimated yield strength of magnesium oxide coatings The comprehensive index of mechanical imbalance of magnesium oxide coating was calculated using a linear weighted method.

[0066] ;

[0067] In the formula, The comprehensive index of mechanical imbalance of magnesium oxide coating indicates that the higher the comprehensive index of mechanical imbalance, the worse the mechanical stability of magnesium oxide coating and the greater the risk of wear and damage under external load. This indicates the stress concentration factor of the magnesium oxide coating; This represents the critical failure stress of the magnesium oxide coating, which characterizes the ultimate stress at which the magnesium oxide coating material fractures. It indicates the interfacial bonding strength of the magnesium oxide coating, characterizing the firmness of the bonding interface between the magnesium oxide coating and the silicon steel substrate; This indicates the elastic strain limit of the magnesium oxide coating; This represents the estimated yield strength of the magnesium oxide coating; This represents the average stress concentration factor of magnesium oxide coatings in a historical set of qualified magnesium oxide coating samples. This represents the average critical failure stress of magnesium oxide coatings in a historical set of qualified magnesium oxide coating samples. This represents the average interfacial bonding strength of magnesium oxide coatings in a historical set of qualified magnesium oxide coating samples. This represents the mean elastic strain limit of magnesium oxide coatings in a historical set of qualified magnesium oxide coating samples. This represents the mean estimated yield strength of magnesium oxide coatings in a historical set of qualified magnesium oxide coating samples.

[0068] Step S24: Based on the comprehensive mechanical imbalance index of the magnesium oxide coating, the estimated elastic strain limit and yield strength of the magnesium oxide coating, and the functional state data of the magnesium oxide coating, a nonlinear mapping relationship between the essential properties of the magnesium oxide coating and the wear state is constructed using a limit learning machine. This yields a data-driven wear state prediction model for the magnesium oxide coating and enables wear state analysis of the magnesium oxide coating. Specifically, this includes:

[0069] First, a vibration test bench was used to test the historical magnesium oxide coating sample set, and the coating thickness and insulation resistance value of the historical magnesium oxide coating sample set were measured. After weighted fusion, a magnesium oxide coating wear state sample set was obtained for model training.

[0070] Secondly, the comprehensive index of mechanical imbalance of the magnesium oxide coating, the elastic strain limit, the estimated yield strength, and the insulation resistance value of the functional state data of the magnesium oxide coating are used as the input feature set X=[ ], The input feature set X represents the insulation resistance value in the functional state of the magnesium oxide coating. This input feature set X is then Z-score standardized to eliminate the influence of dimensions, generating a dimensionless standard score feature set. This provides standardized inputs for predicting wear condition;

[0071] Finally, Using experimentally measured samples of magnesium oxide coating wear states as input features, and as output features, an extreme learning machine model is trained. The dataset is divided into training and test sets using the hold-out method. The root mean square error and coefficient of determination on the test set are used as performance evaluation metrics to establish a model for predicting the wear state of magnesium oxide coatings.

[0072] ;

[0073] In the formula, WS represents the predicted wear state of the magnesium oxide coating. The larger the value, the worse the wear state. (·) represents the nonlinear mapping function obtained by training an extreme learning machine using historical data of magnesium oxide coating, which characterizes the coupling relationship between the essential properties of magnesium oxide coating and wear state;

[0074] This magnesium oxide coating wear state analysis workflow establishes a complete technical system from basic parameters to comprehensive prediction through a four-step progressive analysis framework. Each step is interconnected, ensuring the continuity of the analysis process and the reliability of the results, and providing systematic technical support for the accurate prediction of magnesium oxide coating wear behavior.

[0075] S3. Based on the environmental vibration data of the corresponding historical silicon steel transportation route and the corresponding historical silicon steel transportation vehicle structure data, a transportation damage risk prediction model is constructed to predict the transportation damage risk of the silicon steel magnesium oxide coating to be transported.

[0076] Please see Figure 4 , Figure 4 This is a schematic diagram of the transportation damage risk prediction model construction process provided in this application embodiment. This embodiment demonstrates the complete construction process from multi-source data input to transportation risk prediction. The specific steps are as follows:

[0077] Step S31: Calculate the root mean square value of vibration acceleration and the dominant frequency of vibration on the corresponding historical silicon steel transportation route based on environmental vibration data from the same historical silicon steel transportation route as the silicon steel to be transported using the same coating process as the magnesium oxide coating; specifically including:

[0078] First, based on the preprocessed clean time-domain vibration signal from the environmental vibration data of the corresponding historical silicon steel transportation route, all discrete acceleration data points in each 1-second signal segment are extracted, the square value of each discrete acceleration data point is calculated, and the arithmetic mean of the square values ​​is obtained. The square root of the arithmetic mean is then taken to obtain the root mean square value of vibration acceleration that characterizes the average vibration energy intensity of each time period.

[0079] Secondly, based on the preprocessed complete time-domain vibration signal from the environmental vibration data of the corresponding historical silicon steel transportation route, the corresponding frequency domain spectrum is obtained by fast Fourier transform. The frequency component with the largest amplitude is extracted from the frequency domain spectrum of the complete time-domain vibration signal to obtain the vibration main frequency that reflects the main excitation characteristics of the entire transportation process.

[0080] Step S32: Based on the structural data of the corresponding historical silicon steel transport vehicle using the same coating process as the magnesium oxide coating on the silicon steel to be transported, extract the dominant natural frequency and damping ratio of the corresponding historical silicon steel transport vehicle structure; specifically including:

[0081] First, based on the reliable frequency response function dataset obtained through experimental modal testing from the corresponding historical silicon steel transport vehicle body structure data, peak identification is performed on the frequency response function curve after ensemble averaging, and the frequency position corresponding to the resonance peak with the largest amplitude is located to obtain the dominant natural frequency of the transport vehicle body structure, whose value is always greater than zero.

[0082] Secondly, based on the identified dominant natural frequency of the transport vehicle body structure and its corresponding frequency response function curve, two characteristic frequency points are determined at the resonance peak where the amplitude drops to 0.707 times the resonance peak value. The difference between these two characteristic frequency points is calculated, and the difference is divided by the dominant natural frequency value and then halved to obtain the transport vehicle body damping ratio for subsequent transport damage risk prediction.

[0083] Step S33: Based on the known material and structural parameters of the magnesium oxide coating on the silicon steel to be transported, including elastic modulus, material density and magnesium oxide coating thickness, calculate the equivalent natural frequency of the magnesium oxide coating on the silicon steel to be transported using classical dynamics formulas.

[0084] ;

[0085] In the formula: ρ is the equivalent natural frequency of the magnesium oxide coating on the silicon steel to be transported, used to characterize the dynamic properties of the magnesium oxide coating-matrix system; E is the elastic modulus of the magnesium oxide coating on the silicon steel to be transported; ρ is the material density of the magnesium oxide coating on the silicon steel to be transported. The thickness of the magnesium oxide coating on the silicon steel to be transported is a key process parameter in actual production, and its value is always greater than zero.

[0086] Step S34: By comparing the dominant vibration frequency of the historical transportation route with the equivalent natural frequency of the magnesium oxide coating on the silicon steel to be transported and the dominant natural frequency of the transport vehicle body, and combining the equivalent damping ratio of the magnesium oxide coating with the damping ratio of the transport vehicle body, the dynamic load amplification factor of the magnesium oxide coating on the silicon steel to be transported is calculated. Specifically, based on the calculated data, the dynamic load amplification factor of the magnesium oxide coating's own resonance and the dynamic load amplification factor caused by the resonance of the transport vehicle body structure are calculated separately, and the maximum value of the two is taken as the dynamic load amplification factor of the magnesium oxide coating on the silicon steel to be transported.

[0087] ;

[0088] ;

[0089] ;

[0090] In the formula, This represents the dynamic load amplification factor of the magnesium oxide coating on the silicon steel to be transported, used to quantify the stress amplification effect under resonant conditions. This indicates the amplification factor caused by the resonance of the magnesium oxide coating on the silicon steel to be transported. This indicates the amplification factor caused by the resonance of the historical silicon steel transport vehicle body structure. This indicates the dominant vibration frequency along the historical silicon steel transportation route; This indicates the dominant natural frequency of the historical silicon steel transport vehicle body; This indicates the equivalent damping ratio of the magnesium oxide coating on the silicon steel to be transported; The damping ratio of the historical silicon steel transport vehicle body is represented; as a physical quantity characterizing the energy dissipation capacity of a system, the damping ratio is always greater than zero; in addition, the frequency ratio in the formula is numerically equal to the ratio of its corresponding angular frequencies.

[0091] Step S35: Combining the equivalent alternating stress amplitude calculated from the stress acceleration coefficient calibrated by finite element simulation, the duration of the dominant vibration frequency along the historical transportation route, and the comprehensive mechanical imbalance index of the magnesium oxide coating on the silicon steel to be transported, a comprehensive calculation is performed to obtain the predicted value of the transportation damage risk of the magnesium oxide coating on the silicon steel to be transported; the specific calculation steps are as follows:

[0092] First, based on the established finite element model of the magnesium oxide coating, an amplitude of [value missing] is applied. The standard sinusoidal vibration acceleration load is used, and the load frequency is set as the equivalent natural frequency of the magnesium oxide coating of silicon steel to be transported. The maximum equivalent strain value generated in the dangerous area of ​​the magnesium oxide coating of silicon steel to be transported under this load is extracted by transient dynamics, and the stress acceleration coefficient of the magnesium oxide coating of silicon steel to be transported is obtained.

[0093] Secondly, the equivalent alternating stress amplitude of the magnesium oxide coating on the silicon steel to be transported is obtained by multiplying the root mean square value of vibration acceleration along the historical silicon steel transportation route, the dynamic load amplification factor of the magnesium oxide coating on the silicon steel to be transported, and the stress acceleration coefficient of the magnesium oxide coating on the silicon steel to be transported. In the calculation of the equivalent alternating stress amplitude, the root mean square value of vibration acceleration represents the intensity of vibration energy during transportation, and its value is a non-zero physical quantity calculated from the measured vibration signal. The dynamic load amplification factor and the stress acceleration coefficient represent the dynamic response characteristics of the system and the structure, respectively, and are both non-zero positive numbers obtained through theoretical calculation or simulation. Therefore, the calculated result of the equivalent alternating stress amplitude is always a positive number.

[0094] Finally, the equivalent alternating stress amplitude of the magnesium oxide coating on the silicon steel to be transported, the corresponding vibration dominant frequency on the historical silicon steel transportation route, and the comprehensive mechanical imbalance index of the magnesium oxide coating on the silicon steel to be transported are normalized to eliminate the influence of dimensions. The weight coefficients of the corresponding risk items are determined by the analytic hierarchy process (AHP), thereby calculating the predicted value of the transportation damage risk of the magnesium oxide coating on the silicon steel to be transported.

[0095] ;

[0096] In the formula, This indicates the predicted risk of damage to the magnesium oxide coating on the silicon steel to be transported. The higher the value, the higher the risk of damage to the magnesium oxide coating on the silicon steel to be transported during transportation. This represents the equivalent alternating stress amplitude of the magnesium oxide coating on the silicon steel to be transported. The reference benchmark value for the comprehensive mechanical imbalance index is determined by statistically analyzing the average comprehensive mechanical imbalance index of a historical set of qualified magnesium oxide coating samples. This indicates the material fatigue index of the magnesium oxide coating on the silicon steel to be transported. This represents the fatigue strength limit of the magnesium oxide coating on the silicon steel to be transported; it is a fixed physical quantity and is always a positive number. Indicates stress risk item Weighting coefficients; Indicates the risk item of vibration frequency. Weighting coefficients; Indicates the intrinsic risk item of the coating Weighting coefficients This indicates the planned transportation time. Internal, dominant vibration frequency The total number of vibration cycles; This indicates the planned transportation time for the magnesium oxide coating on the silicon steel to be transported. This represents the reference total number of vibration cycles, determined by statistical analysis of the average total number of vibration cycles along historical transportation routes.

[0097] Introducing the natural logarithm function ln into the predicted value of transportation damage risk can more accurately describe the nonlinear effect of the number of vibration cycles on coating fatigue damage. The increase in the number of vibration cycles does not linearly increase the damage risk, but rather increases significantly in the early stage and then gradually saturates. Using the logarithmic function can compress a wide range of vibration cycles into a reasonable numerical range and avoid this factor accounting for too large a proportion in the comprehensive risk calculation.

[0098] The construction process of this transportation damage risk prediction model adopts a five-step progressive analysis framework. Starting from the extraction of basic signal features, it sequentially completes the dynamic characteristic analysis of the coating and the equivalent stress calculation, and finally achieves accurate prediction of transportation risks. By combining environmental vibration characteristics, dynamic characteristics of the transport vehicle structure and mechanical properties of the coating itself, a physical prediction model that can accurately reflect the dynamic load characteristics under actual transportation conditions is constructed, providing a reliable input basis for subsequent failure risk assessment of magnesium oxide coatings.

[0099] S4. Combining the wear state analysis results of the magnesium oxide coating and the predicted risk of damage during transportation of the magnesium oxide coating on the silicon steel to be transported, the predicted failure risk of the magnesium oxide coating on the silicon steel to be transported is obtained.

[0100] Please see Figure 5 , Figure 5 This is a schematic diagram of the magnesium oxide coating failure risk prediction process provided in this application embodiment. This embodiment demonstrates the complete evaluation process from multi-source input to failure risk prediction value calculation, including the composition architecture and technical route of two core steps:

[0101] Step S41: Determine the weighting coefficients of the wear state analysis results of the magnesium oxide coating and the weighting coefficients of the predicted transport damage risk of the magnesium oxide coating on the silicon steel to be transported by using the analytic hierarchy process.

[0102] Step S42: Based on the wear state analysis results of the magnesium oxide coating, the predicted transportation damage risk of the magnesium oxide coating on the silicon steel to be transported, and the determined weighting coefficients, calculate the predicted failure risk of the magnesium oxide coating on the silicon steel to be transported using a linear weighted method.

[0103] ;

[0104] In the formula, This represents the predicted risk value of failure of the magnesium oxide coating on the silicon steel to be transported, and is used to comprehensively characterize the degree of risk of wear and peeling of the magnesium oxide coating after transportation. This represents the weighting coefficients of the wear condition analysis results for magnesium oxide coatings; The weighting coefficients represent the predicted risk of damage to the magnesium oxide coating on the silicon steel to be transported; all weighting coefficients were obtained through the analytic hierarchy process.

[0105] This magnesium oxide coating failure risk prediction process adopts a two-step analysis architecture. It uses the analytic hierarchy process to scientifically quantify the contribution of different influencing factors, and then uses linear weighting to achieve effective fusion of multi-source information. This method comprehensively considers the intrinsic properties of magnesium oxide coating and external dynamic loads, and realizes a quantitative assessment of the failure probability of magnesium oxide coating, providing clear decision input for subsequent judgment and triage.

[0106] S5. Based on the predicted failure risk value of the magnesium oxide coating on the silicon steel to be transported, determine and divert the magnesium oxide coating on the silicon steel to be transported.

[0107] Please see Figure 6 , Figure 6 This is a schematic diagram of the quality assessment and triage process provided in this application embodiment. This embodiment illustrates the complete process from failure risk prediction results to quality assessment and triage, including the composition architecture and functional division of two core optimization steps:

[0108] Step S51: Based on the set failure risk judgment threshold and the failure risk prediction value of the magnesium oxide coating of the silicon steel to be transported, the failure risk judgment threshold of the silicon steel to be transported is judged; wherein, the determination of the failure risk judgment threshold specifically includes: by retrospectively analyzing a large number of historical samples, establishing the correspondence between the failure risk prediction value and whether the magnesium oxide coating failure occurs after actual transportation, and using statistical distribution methods, such as determining the quantile based on the distribution of prediction values ​​of historical qualified samples, and finally setting a failure risk judgment threshold that can effectively distinguish between qualified products and high-risk products.

[0109] Step S52: When the predicted failure risk value is less than or equal to the failure risk judgment threshold, the magnesium oxide coating of the silicon steel to be transported is determined to be safe; when the predicted failure risk value is greater than the failure risk judgment threshold, the magnesium oxide coating of the silicon steel to be transported is determined to have a high failure risk, and the process traceability is carried out upon return to the factory.

[0110] This quality assessment and triage process, through the aforementioned assessment and triage mechanism, enables rapid identification and classification of the magnesium oxide coating condition of silicon steel to be transported, providing an effective basis for subsequent quality control and process improvement.

[0111] This application provides a big data-based process adjustment system for silicon steel magnesium oxide production, including:

[0112] The data acquisition module is used to acquire environmental vibration data and vehicle structure data along the transportation route of the magnesium oxide coating on the silicon steel to be transported. It also acquires mechanical state data, functional state data, and structural state data of the magnesium oxide coating, as well as the production process parameters of the magnesium oxide coating.

[0113] The wear analysis module is used to obtain the comprehensive mechanical imbalance index of the magnesium oxide coating based on the mechanical state data and structural state data of the magnesium oxide coating, and to perform wear state analysis of the magnesium oxide coating by combining the comprehensive mechanical imbalance index and the functional state data of the magnesium oxide coating.

[0114] The transportation damage risk prediction module is used to construct a transportation damage risk prediction model based on environmental vibration data of the corresponding historical silicon steel transportation route with the same coating process as the magnesium oxide coating of the silicon steel to be transported, and the corresponding historical silicon steel transportation vehicle structure data, so as to predict the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported.

[0115] The failure risk prediction module is used to combine the wear state analysis results of the magnesium oxide coating with the transportation damage risk prediction value of the magnesium oxide coating of the silicon steel to be transported, and obtain the failure risk prediction value of the magnesium oxide coating of the silicon steel to be transported.

[0116] The quality assessment and diversion module assesses and diverts the magnesium oxide coating on the silicon steel to be transported based on the predicted failure risk value.

[0117] The steps for implementing the corresponding functions of each parameter and unit module in the above-described silicon steel magnesium oxide production process adjustment system based on big data of the present invention can be referred to the parameters and steps in the embodiments of the above-described silicon steel magnesium oxide production process adjustment method based on big data, and will not be repeated here.

[0118] This application provides an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus; the memory stores a method for adjusting the silicon steel magnesium oxide production process based on big data, which can be loaded and executed by the processor as provided in the above embodiments.

[0119] The memory can be used to store instructions, programs, code, code sets, or instruction sets; the memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the big data-based silicon steel magnesium oxide production process adjustment method provided in the above embodiments, etc.; the data storage area may store data involved in the big data-based silicon steel magnesium oxide production process adjustment method provided in the above embodiments, etc.

[0120] The processor may include one or more processing cores; the processor executes or runs instructions, programs, code sets or instruction sets stored in memory, calls data stored in memory, and performs various functions and processes data in this application; the processor may be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller and microprocessor; it is understood that for different devices, the electronic device used to implement the above processor functions may also be other, and the embodiments of this application do not specifically limit it.

[0121] A communication bus may include a path for transmitting information between the aforementioned components; the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc.; the communication bus may be divided into address bus, data bus, control bus, etc.

[0122] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for adjusting the silicon steel magnesium oxide production process based on big data.

[0123] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device; a computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof; specifically, a computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital multifunction disc (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, or any combination thereof.

[0124] The terms include, encompass, or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0125] The above description is merely a preferred embodiment of this application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the foregoing application concept; for example, technical solutions formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions applied in this application.

Claims

1. A method for adjusting the production process of magnesium oxide silicon steel based on big data, characterized in that, Includes the following steps: S1. Obtain environmental vibration data and vehicle structure data along the transportation route of the magnesium oxide coating on the silicon steel to be transported, and at the same time obtain mechanical state data, functional state data, structural state data of the magnesium oxide coating, as well as the production process parameters of the magnesium oxide coating. S2. Based on the mechanical state data and structural state data of the magnesium oxide coating, the comprehensive mechanical imbalance index of the magnesium oxide coating is obtained. The wear state of the magnesium oxide coating is analyzed by combining the comprehensive mechanical imbalance index and the functional state data of the magnesium oxide coating. S3. Based on the environmental vibration data of the corresponding historical silicon steel transportation route with the same coating process as the magnesium oxide coating of the silicon steel to be transported, and the corresponding historical silicon steel transportation vehicle structure data, a transportation damage risk prediction model is constructed to predict the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported. The method involves constructing a transportation damage risk prediction model based on environmental vibration data from historical silicon steel transportation routes using the same coating process as the magnesium oxide coating on the silicon steel to be transported, and on the corresponding historical silicon steel vehicle body structure data. This model predicts the transportation damage risk to the magnesium oxide coating on the silicon steel to be transported, and includes the following steps: S31. Based on the environmental vibration data of the corresponding historical silicon steel transportation route with the same coating process as the magnesium oxide coating of the silicon steel to be transported, calculate the root mean square value of vibration acceleration and the dominant frequency of vibration of the corresponding historical silicon steel transportation route. S32. Based on the transportation vehicle structure data of the corresponding historical silicon steel with the same coating process as the magnesium oxide coating of the silicon steel to be transported, extract the dominant natural frequency and the damping ratio of the transportation vehicle structure of the corresponding historical silicon steel. S33. Based on the known material and structural parameters of the magnesium oxide coating on the silicon steel to be transported, calculate the equivalent natural frequency of the magnesium oxide coating on the silicon steel to be transported using classical dynamic formulas. S34. By comparing the dominant vibration frequency of the historical transportation route with the equivalent natural frequency of the magnesium oxide coating of the silicon steel to be transported and the dominant natural frequency of the transport vehicle body, and combining the equivalent damping ratio of the magnesium oxide coating with the damping ratio of the transport vehicle body, the dynamic load amplification factor of the magnesium oxide coating of the silicon steel to be transported is calculated. S35. Combining the equivalent alternating stress amplitude calculated by the stress acceleration coefficient calibrated by finite element simulation, the duration of the main frequency of vibration on the historical transportation route, and the comprehensive mechanical imbalance index of the magnesium oxide coating of silicon steel to be transported, a comprehensive calculation is performed to obtain the predicted value of transportation damage risk of the magnesium oxide coating of silicon steel to be transported. S4. Based on the analysis results of the wear state of the magnesium oxide coating and the predicted value of the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported, the predicted value of the failure risk of the magnesium oxide coating of the silicon steel to be transported is obtained. S5. Based on the predicted failure risk value of the magnesium oxide coating on the silicon steel to be transported, determine and divert the magnesium oxide coating on the silicon steel to be transported.

2. The method for adjusting the silicon steel magnesium oxide production process based on big data according to claim 1, characterized in that, The mechanical imbalance index of the magnesium oxide coating is obtained based on the mechanical state data and structural state data of the magnesium oxide coating. Wear state analysis of the magnesium oxide coating is then performed by combining the mechanical imbalance index with the functional state data of the magnesium oxide coating, including the following steps: S21. Based on the hardness and elastic modulus in the mechanical state data of the magnesium oxide coating, the elastic strain limit of the magnesium oxide coating is obtained by calculating the ratio of hardness to elastic modulus. S22. Combining the surface morphology, cross-sectional morphology in the structural state data of magnesium oxide coating and the elastic modulus in the mechanical state data of magnesium oxide coating, the stress concentration effect caused by the microstructural inhomogeneity of magnesium oxide coating is analyzed by finite element simulation to obtain the stress concentration factor of magnesium oxide coating. S23. Combining the stress concentration factor, critical failure stress, interfacial bonding strength, elastic strain limit and yield strength estimate of the magnesium oxide coating, the weight of each parameter is determined by the analytic hierarchy process (AHP), and a comprehensive analysis is performed based on the linear weighting method to obtain the comprehensive index of mechanical imbalance of the magnesium oxide coating. S24. Based on the comprehensive index of mechanical imbalance of magnesium oxide coating, the estimated elastic strain limit and yield strength of magnesium oxide coating, and the functional state data of magnesium oxide coating, a nonlinear mapping relationship between the essential properties of magnesium oxide coating and wear state is constructed through limit learning machine. This results in a data-driven wear state prediction model for magnesium oxide coating and enables wear state analysis of magnesium oxide coating.

3. The method for adjusting the magnesium oxide production process of silicon steel based on big data according to claim 2, characterized in that, The method of combining the wear state analysis results of the magnesium oxide coating and the predicted risk value of transportation damage to the magnesium oxide coating of the silicon steel to be transported to obtain the predicted failure risk value of the magnesium oxide coating of the silicon steel to be transported includes the following steps: S41. The weighting coefficients of the wear state analysis results of magnesium oxide coating and the weighting coefficients of the predicted transport damage risk of magnesium oxide coating on silicon steel to be transported are determined by the analytic hierarchy process. S42. Based on the wear state analysis results of the magnesium oxide coating, the predicted value of the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported, and the corresponding weight coefficients determined by the analytic hierarchy process, the predicted value of the failure risk of the magnesium oxide coating of the silicon steel to be transported is calculated by the linear weighted method.

4. The method for adjusting the magnesium oxide production process of silicon steel based on big data according to claim 3, characterized in that, Based on the predicted failure risk value of the magnesium oxide coating on the silicon steel to be transported, the magnesium oxide coating on the silicon steel to be transported is determined and diverted, including the following steps: S51. Based on the set failure risk judgment threshold and the predicted failure risk value of the magnesium oxide coating on the silicon steel to be transported, the magnesium oxide coating on the silicon steel to be transported is judged. S52. When the predicted failure risk value is less than or equal to the failure risk judgment threshold, the magnesium oxide coating of the silicon steel to be transported is determined to be safe; when the predicted failure risk value is greater than the failure risk judgment threshold, the magnesium oxide coating of the silicon steel to be transported is determined to have a risk of damage during transportation and is returned to the factory for process traceability.

5. A big data-based process adjustment system for silicon steel magnesium oxide production, implemented based on the big data-based process adjustment method for silicon steel magnesium oxide production as described in any one of claims 1-4, characterized in that, The system includes: The data acquisition module is used to acquire environmental vibration data and vehicle structure data along the transportation route of the magnesium oxide coating on the silicon steel to be transported, as well as mechanical state data, functional state data, structural state data of the magnesium oxide coating and production process parameters of the magnesium oxide coating. The wear analysis module obtains the comprehensive mechanical imbalance index of the magnesium oxide coating based on the mechanical state data and structural state data of the magnesium oxide coating. It then combines the comprehensive mechanical imbalance index of the magnesium oxide coating with the functional state data of the magnesium oxide coating to analyze the wear state of the magnesium oxide coating. The risk prediction module is used to construct a transportation damage risk prediction model based on environmental vibration data of the corresponding historical silicon steel transportation route with the same coating process as the magnesium oxide coating of the silicon steel to be transported, and the corresponding historical silicon steel transportation vehicle structure data, so as to predict the transportation damage risk of the magnesium oxide coating of the silicon steel to be transported. The failure risk prediction module is used to combine the wear state analysis results of the magnesium oxide coating with the transportation damage risk prediction value of the magnesium oxide coating of the silicon steel to be transported, and obtain the failure risk prediction value of the magnesium oxide coating of the silicon steel to be transported. The quality assessment and diversion module is used to assess and divert the magnesium oxide coating of silicon steel to be transported based on the predicted failure risk value of the magnesium oxide coating.

6. An electronic device, comprising: The processor and memory are characterized in that the memory stores a computer program that can be called by the processor; the processor executes the big data-based silicon steel magnesium oxide production process adjustment method as described in any one of claims 1-4 by calling the computer program stored in the memory.

7. A computer-readable storage medium storing instructions, characterized in that, When the instructions are executed on a computer, the computer performs the big data-based process adjustment method for silicon steel magnesium oxide production as described in any one of claims 1-4.

Images