A method, system and device for detecting the deviation of the roll gap of a rolling mill

Abstract

The present invention relates to the technical field of rolling process and equipment detection, and particularly relates to a method, system and equipment for detecting the deviation of the roll gap of a rolling mill. The method includes: constructing a vibration detection center line parallel to the roll axis of the working roll based on the copper material to be processed, collecting the roll vibration characteristics for each working roll according to the vibration detection center line, generating a vibration characteristic matrix according to the processing time of the corresponding working roll, and obtaining the roll gap deviation detection result by establishing a reference vibration deviation model and comparing the vibration characteristic matrices corresponding to each working roll for vibration deviation. Through the present invention, the problem that it is difficult to capture the weak vibration changes under high-speed and high-load working conditions in the roll gap deviation is effectively solved. By dynamically monitoring and analyzing based on vibration signals, a reference vibration deviation model is established, realizing efficient and accurate roll gap deviation detection and ensuring the stability of the production process.

Description

Technical Field

[0001] The present invention relates to the technical field of rolling processes and equipment detection, and particularly to a method, system, and device for detecting the deviation of the roll gap of a rolling mill. Background Art

[0002] With the continuous improvement of the automation of the rolling industry and production efficiency, the operational stability and performance optimization of rolling mill equipment are of great significance to production quality, cost control, and equipment maintenance. Roll gap deviation refers to the change in the distance or position between the rolls, which leads to problems such as uneven material thickness, surface defects, or mechanical wear during the production process, directly affecting the quality of the final product and production efficiency. Currently, the detection methods for roll gap deviation mainly rely on traditional physical quantity measurements, such as the monitoring of parameters like displacement and pressure.

[0003] Although these monitoring means can capture the macroscopic characteristics of roll gap changes to a certain extent, they have some limitations. Traditional methods often rely on manually set thresholds for judgment, and it is difficult to reflect the minute changes in roll gap deviation under complex working conditions in real-time and comprehensively. At the same time, these methods lack in-depth analysis of vibration signals, especially under high-speed or high-load working conditions, it is difficult to accurately detect the weak changes in roll gap deviation, resulting in a lag in response when deviations occur, affecting production quality and the equipment maintenance cycle.

[0004] The information disclosed in this background art section is only intended to deepen the understanding of the overall background art of the present disclosure, and should not be regarded as an admission or any form of implication that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides a method, system, and device for detecting the deviation of the roll gap of a rolling mill, which can effectively solve the problems in the background art.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] A method for detecting the deviation of the roll gap of a rolling mill, the method comprising:

[0008] Establishing a vibration detection center line based on the copper material to be processed, and the vibration detection center line is parallel to the roll axis of the work roll;

[0009] Collecting and obtaining the roll vibration characteristics for each work roll according to the vibration detection center line, and generating a vibration characteristic matrix corresponding to the processing time axis of the work roll;

[0010] Establishing a reference vibration deviation model, comparing the vibration characteristic matrices corresponding to each work roll for vibration deviation, and obtaining the roll gap deviation detection result according to the vibration deviation result mapping.

[0011] Further, perform vibration deviation comparison on the vibration characteristic matrix corresponding to each of the working rolls, including:

[0012] Set a number of vibration monitoring points at the corresponding positions of the vibration detection center line and the working roll respectively, and obtain the roll vibration characteristics of the working roll at the corresponding positions of the vibration detection center line respectively;

[0013] Determine the time length of the processing time, and divide the time length into equal-length time slices;

[0014] Perform vibration deviation comparison on the roll vibration characteristics of each working roll with the same position coordinates and in the same time slice according to the vibration monitoring points and the time slice length, and obtain a number of deviation comparison parameters;

[0015] Obtain the vibration deviation result according to a number of the deviation comparison parameters.

[0016] Further, collect and obtain roll vibration characteristics, including:

[0017] Capture roll vibration signals, perform correlation evaluation on the roll vibration signals, and obtain roll vibration characteristics;

[0018] Collect roll vibration signals in real time, update the vibration characteristic matrix, and load the reference vibration deviation model to output the roll gap deviation detection result.

[0019] Further, perform correlation evaluation on the roll vibration signals, including:

[0020] Perform preprocessing on the roll vibration signals, perform signal splitting on the preprocessed roll vibration signals, and obtain a number of intrinsic mode functions, and each of the intrinsic mode functions represents a specific frequency band of the roll vibration signals;

[0021] Screen a number of the intrinsic mode functions to obtain a number of relevant frequency bands, and the relevant frequency bands represent the intrinsic mode functions associated with the roll gap deviation;

[0022] Perform splicing and reconstruction on the roll vibration signals according to a number of the relevant frequency bands to obtain roll vibration characteristics, and the splicing and reconstruction means splicing and reorganizing a number of the relevant frequency bands.

[0023] Further, perform signal splitting on the preprocessed roll vibration signals, including:

[0024] Pre-decompose the roll vibration signals based on frequency to obtain a number of initial mode functions;

[0025] Perform time-frequency analysis on a number of the initial mode functions, estimate the frequency components of the initial mode functions, and set the initial center frequency according to the frequency components;

[0026] Collect historical rolling mill working condition information, set a minimization objective function according to the historical rolling mill working condition signal, iteratively optimize the frequency range of the initial mode functions according to the minimization objective function, and constrain the center frequency to obtain a number of intrinsic mode functions, which represent different frequency components in the roll vibration signal.

[0027] Further, establish a reference vibration deviation model, and map the vibration deviation result to obtain a roll gap deviation detection result, including:

[0028] Construct a roll vibration database, which includes historical roll vibration characteristic information and historical roll gap deviation information;

[0029] The roll vibration database classifies the historical roll vibration characteristic information and historical roll gap deviation information according to the processing equipment and the copper material to be processed;

[0030] Perform deep learning on the roll vibration database, and obtain the historical mapping relationship between the historical roll vibration characteristic information and the historical roll gap deviation information of the same processing equipment and copper material to be processed;

[0031] Match the vibration deviation result with the roll vibration database, and obtain the roll gap deviation detection result according to the historical mapping relationship.

[0032] Further, construct a roll vibration database, including:

[0033] Collect the historical roll vibration characteristic information and historical roll gap deviation information;

[0034] Cluster and manage the historical roll vibration characteristic information according to the monitoring position of the vibration detection center line and the processing time axis, and each data item of the vibration characteristic matrix corresponds to the historical roll gap deviation information;

[0035] Use the monitoring position, processing time axis, and the historical roll gap deviation information as database indexes respectively for the reference vibration deviation model to call the data chain.

[0036] Further, obtain the vibration deviation result according to a number of deviation comparison parameters, including:

[0037] Set a deviation warning value, traverse the number of deviation comparison parameters according to the deviation warning value to obtain a number of vibration parameter deviations;

[0038] Obtain the time slices corresponding to the deviations of the several vibration parameters and the position coordinates of the vibration monitoring points, and obtain the vibration deviation results.

[0039] A deviation detection system for the roll gap of a rolling mill, the system comprising:

[0040] A reference vibration center line construction module, which establishes a vibration detection center line based on the copper material to be processed, and the vibration detection center line is parallel to the roll axis of the work roll;

[0041] A working vibration acquisition module, which acquires the roll vibration characteristics in units of each work roll according to the vibration detection center line, and generates a vibration characteristic matrix corresponding to the processing time axis of the work roll;

[0042] A vibration deviation model comparison module, which establishes a reference vibration deviation model, compares the vibration characteristic matrices corresponding to each work roll for vibration deviation, and maps the roll gap deviation detection results according to the vibration deviation results.

[0043] A deviation detection device for the roll gap of a rolling mill, and the device applies any of the deviation detection methods for the roll gap of a rolling mill.

[0044] Through the technical solution of the present invention, the following technical effects can be achieved:

[0045] Effectively solve the problem that it is difficult to capture the weak vibration changes under high-speed and high-load working conditions in the roll gap deviation. Through the dynamic monitoring and analysis based on vibration signals, the weak vibration changes under high-speed and high-load working conditions can be captured, effectively improving the sensitivity and detection accuracy of the roll gap deviation. By combining with the deep learning model for data comparison, the deviation problem of the roll gap can be found in time, avoiding the problem of lag in response in the traditional method, and significantly improving the quality control ability in the production process.

[0046] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific embodiments of this application. Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1It is a schematic flow chart of a method for detecting the deviation of the roll gap of a rolling mill;

[0049] Figure 2 It is a schematic flow chart of vibration deviation comparison;

[0050] Figure 3 It is a schematic flow chart for obtaining the vibration characteristics of the roll;

[0051] Figure 4 It is a relational diagram for evaluating the correlation degree of the roll vibration signal;

[0052] Figure 5 It is a signal splitting relational diagram. Specific implementation mode

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0055] Embodiment 1;

[0056] As Figure 1 shown, the present application provides a method for detecting the deviation of the roll gap of a rolling mill, and the method includes:

[0057] S100: Establish a vibration detection center line based on the copper material to be processed, and the vibration detection center line is parallel to the roll axis of the work roll;

[0058] S200: Acquire the vibration characteristics of the roll for each work roll according to the vibration detection center line, and generate a vibration characteristic matrix corresponding to the processing time axis of the work roll;

[0059] S300: Establish a reference vibration deviation model, compare the vibration characteristic matrix corresponding to each work roll for vibration deviation, and map the roll gap deviation detection result according to the vibration deviation result.

[0060] Specifically, first, a vibration detection center line is established as a reference. The establishment of the vibration detection center line is usually determined in combination with the processing characteristics of copper materials and the type of work rolls of the rolling mill. Specifically, in the implementation process, the precise position of the detection center line can be determined by measuring or calculating the position of the roll axis and combining the geometric characteristics of the copper material to be processed. In some embodiments, the selection of the vibration detection center line should ensure that it is parallel to the roll axis and consistent with the processing path of the copper material; after the vibration detection center line is determined, vibration characteristics are determined according to the vibration detection center line. All vibration characteristics are combined into a matrix in time series. Each column represents the vibration characteristics at a specific time, and each row represents the vibration characteristics at all vibration monitoring points at that moment. To avoid the problem of excessive data dimensions or unevenness, the generated feature matrix is usually standardized. The standardization methods can include normalization, z-score normalization, etc., so that each eigenvalue in the matrix can be compared on the same scale. In addition, the feature matrix can be dimensionally reduced as needed (such as principal component analysis) to reduce redundant information and improve the efficiency of subsequent calculations. After the feature matrix is generated, it will be used as the basis for deviation detection and compared with the reference vibration deviation model. By comparing the vibration characteristics in the matrix with the ideal vibration characteristics in the standard model, the deviation value can be calculated, thus realizing the detection of roll gap deviation.

[0061] Through the technical solution of the present invention, the problem that it is difficult to capture the weak vibration changes under high-speed and high-load working conditions in roll gap deviation is effectively solved. Through the dynamic monitoring and analysis based on vibration signals, the weak vibration changes under high-speed and high-load working conditions can be captured, effectively improving the sensitivity and detection accuracy of roll gap deviation. By combining with the deep learning model for data comparison, the deviation problem of the roll gap can be found in time, avoiding the problem of lag in traditional methods, and significantly improving the quality control ability in the production process.

[0062] Furthermore, as Figure 2 shown, the vibration deviation comparison of the vibration feature matrix corresponding to each work roll includes:

[0063] S310: Set a number of vibration monitoring points at the corresponding positions of the vibration detection center line and the work roll respectively, and obtain the roll vibration characteristics of the work roll at the corresponding positions of the vibration detection center line respectively;

[0064] S320: Determine the time length of the processing time and divide the time length into equal-length time slices;

[0065] S330: Perform vibration deviation comparison on the roll vibration characteristics of each work roll with the same position coordinates and in the same time slice according to the vibration monitoring points and the time slice length, and obtain a number of deviation comparison parameters;

[0066] S340: Obtain the vibration deviation result according to a number of deviation comparison parameters.

[0067] As an optimization of the above embodiment, during the implementation process, first set the vibration monitoring points according to the vibration detection center line. The setting of the vibration monitoring points depends on the working state of the roll and the change law of the vibration characteristics. Usually, a plurality of vibration sensors are arranged at the key positions of each working roll (such as the contact surface and the support point). These sensors can be accelerometers, displacement sensors, piezoelectric sensors, etc., and are used to obtain the vibration characteristics of the roll in real time. Each vibration monitoring point will collect the roll vibration signal at a specific position. In order to comprehensively capture the vibration changes of the roll, different monitoring point densities can be selected according to different working conditions of the rolling mill. The number and position of the monitoring points should be adjusted according to the actual process requirements. For example, high-frequency sampling is used to capture high-frequency vibrations, and low-frequency sampling is used to capture low-frequency vibrations; Next, according to the processing time of the rolling mill, the time length is divided into equal-length time slices. The length of the processing time can be set according to the production cycle of the rolling mill. The length of the time slice should be adapted to the rhythm of the production process. Generally, the length of each time slice can be set from a few seconds to dozens of seconds. The specific length selection needs to be determined according to the running speed of the rolling mill, process requirements, and the characteristics of signal changes. By dividing the time length into equal-length time slices, it can be ensured that the vibration characteristics within each time slice can fully reflect the working state of the working roll during that time period, and the vibration signals within each time slice are analyzed in detail. When the vibration characteristic matrix of each time slice is generated, the next step is to perform vibration deviation comparison. During the comparison process, first compare the data in the vibration characteristic matrix with the historical data model to calculate the deviation value. The deviation value of each monitoring point will reflect the difference between the vibration state of the roll at that position and the ideal state. Through the above vibration deviation comparison process, the obtained deviation comparison parameters will be used to calculate the final vibration deviation result, and these deviation results will be directly used for the deviation detection and adjustment of the roll gap of the rolling mill.

[0068] Furthermore, as Figure 3 shown, collecting and obtaining the roll vibration characteristics includes:

[0069] S311: Capture the roll vibration signal, evaluate the correlation degree of the roll vibration signal, and obtain the roll vibration characteristics;

[0070] S312: Collect the roll vibration signal in real time, update the vibration characteristic matrix, and load the reference vibration deviation model to output the roll gap deviation detection result.

[0071] In this embodiment, first, to ensure high-precision capture of the vibration characteristics of the roll, this implementation preferably uses high-precision multi-axis accelerometers or displacement sensors. These sensors can simultaneously collect vibration information of the roll in multiple directions, especially capable of capturing subtle vibration changes. At the same time, to comprehensively collect the vibration information of the roll, the sensors are usually arranged at key positions of the roll, such as contact points, support points and other areas. The sensors can also be arranged on both sides or at multi-angle positions of the roll to capture multi-dimensional vibration signals. In the normal working state of the rolling mill, the vibration sensors continuously and real-time collect the vibration signals of the roll. These signals include low-frequency and high-frequency vibration components generated by the roll during the processing. The frequency setting of the signal acquisition process should be adjusted according to the working characteristics of the rolling mill and the minute changes in the roll gap to ensure that all vibration characteristics of the roll can be covered. Then, based on the collected vibration signals, the correlation degree of the vibration signals is evaluated to obtain the vibration characteristics of the roll. The vibration signals collected in real-time are organized according to the time axis, and the vibration characteristic matrix is updated in real-time. Whenever new vibration signals are collected, the system will update the characteristic matrix according to the time axis. With the acquisition and processing of the signal data of each time slice, the matrix will be gradually accumulated and updated to reflect the real-time vibration state of the current roll. After the update of the vibration characteristic matrix is completed, the system will load the reference vibration deviation model. The reference model is based on the normal roll vibration characteristics under different working conditions and provides a standard reference for comparison with the real-time data.

[0072] Furthermore, as Figure 4 shown, the correlation degree evaluation of the roll vibration signal includes:

[0073] Preprocess the roll vibration signal, split the preprocessed roll vibration signal to obtain a number of intrinsic mode functions, and each intrinsic mode function represents a specific frequency band of the roll vibration signal;

[0074] Screen a number of intrinsic mode functions to obtain a number of relevant frequency bands, and the relevant frequency bands represent the intrinsic mode functions associated with the roll gap deviation;

[0075] Reconstruct the roll vibration signal by splicing according to a number of relevant frequency bands to obtain the roll vibration characteristics, and splicing reconstruction means splicing and reorganizing a number of relevant frequency bands.

[0076] Specifically, first, denoise and filter the vibration signals of the rolling mill rolls collected in real time. To remove high-frequency noise and low-frequency drift, a band-pass filter is used for signal preprocessing. The bandwidth of the filter needs to be selected according to the frequency range of the roll vibration signals. Generally speaking, the band-pass filter will select a frequency range to cover the main frequency bands of the roll vibration and remove irrelevant noise frequency bands. Through standardization (such as Z-score standardization) or normalization (such as mapping the vibration amplitude to between 0 and 1), the data from different signal sources are made to have the same dimension, which is convenient for subsequent analysis and comparison. Then, by splitting the preprocessed roll vibration signals, intrinsic mode functions are obtained. Through spectral analysis of each intrinsic mode function, the vibration amplitude and frequency components of each frequency band can be obtained. The following spectral analysis methods can be used: Use the fast Fourier transform to perform spectral analysis on each intrinsic mode function to obtain a frequency-amplitude spectrogram. The purpose of spectral analysis is to quantify the energy distribution of the signal in each frequency range, especially paying attention to the parts where the energy is concentrated or the frequency bands change significantly. In the spectrogram, the frequency bands with more concentrated energy are often related to the main sources of vibration. Therefore, when screening, those frequency bands with higher energy peaks can be selected as the key analysis objects. Subsequently, by collecting data on the operation of the rolling mill multiple times, including normal working conditions and working conditions with roll gap deviations, through comparative analysis, the change rules of each frequency band under different working conditions are determined. Statistical methods such as correlation coefficients or regression analysis are used to evaluate the correlation between different frequency bands and roll gap deviations, and those parts where the frequency band changes are significantly correlated with roll gap deviations are selected. Usually, the low-frequency part represents large-scale mechanical changes, while the medium-high frequency part may be related to small roll gap deviations. Subsequently, the intrinsic mode functions of the selected relevant frequency bands are spliced together to obtain the roll vibration characteristics. The process of splicing and reconstruction is to combine the intrinsic mode functions of the selected frequency bands. During the splicing process, operations such as frequency translation and amplitude adjustment may be required for the intrinsic mode functions to ensure the time-domain continuity and frequency-domain consistency of the vibration characteristics after splicing. The reconstructed vibration characteristics usually appear as a smoother and more distinguishable signal.

[0077] Furthermore, as Figure 5 shown, the signal splitting of the preprocessed roll vibration signals includes:

[0078] Pre-decompose the roll vibration signals based on frequency to obtain several initial mode functions;

[0079] Perform time-frequency analysis on several initial mode functions, estimate the frequency components of the initial mode functions, and set the initial center frequencies according to the frequency components;

[0080] Collect historical rolling mill working condition information, set a minimization objective function according to the historical rolling mill working condition signals, iteratively optimize the frequency range of the initial mode functions according to the minimization objective function, and constrain the central frequency to obtain a number of intrinsic mode functions, which represent different frequency components in the roll vibration signal.

[0081] As an optimization of the above embodiment, first perform frequency pre-decomposition on the preprocessed roll vibration signal. The pre-decomposition process can decompose the signal into several frequency components through methods such as wavelet transform, empirical mode decomposition, or Fourier transform. Each frequency component represents different frequency band information of the signal, and these frequency bands cover various characteristics of roll vibration, including low-frequency mechanical vibration and high-frequency minute roll gap deviation information. Through these methods, the original vibration signal will be disassembled into several initial mode functions, and each initial mode function represents the frequency band information of the signal, effectively separating the roll vibration signal within a certain frequency range. Subsequently, perform time-frequency analysis on the decomposed initial mode functions. The time-frequency analysis can be carried out in the following manner: Apply a time-frequency analysis method to the decomposed mode functions. Commonly used ones include short-time Fourier transform or wavelet transform, etc. Divide the signal into small time windows, and the signal within each window can be assumed to be stable, which can ensure high resolution in both the time domain and the frequency domain. Subsequently, perform Fourier transform or wavelet transform on the signal within each time window to calculate its spectrum, which can obtain the frequency components corresponding to each time point, reflecting the frequency distribution existing at different time points of the signal. By analyzing the spectrum, estimate the main frequency components contained in the mode function. The spectrum of each mode function will show the energy distribution within different frequency intervals. Finally, display the time-frequency analysis results as a time-frequency diagram, with the horizontal axis being time and the vertical axis being frequency. After time-frequency analysis, estimate the frequency components of the initial mode functions according to the frequency distribution in the spectrogram. The frequency components reflect the main energy positions of the roll vibration signal in each frequency band. By observing the peak positions of the spectrum in the time-frequency diagram, the frequency band where the signal energy is most concentrated can be determined, and the frequency point corresponding to this frequency band is the central frequency. Then, by collecting historical working condition information, set a minimization objective function. The role of the objective function is to find the best frequency window by adjusting the frequency range and the central frequency, so that the mode function can accurately reflect the vibration characteristics of the roll gap deviation. According to the result of the minimization objective function, perform iterative optimization. By adjusting the frequency range and the central frequency of the initial mode functions, gradually approach the optimal frequency band to ensure that the frequency range can accurately reflect the characteristics of the roll gap deviation. In each optimization process, the frequency components will be re-estimated and fine-tuned according to the historical working condition information. Finally, obtain the optimized intrinsic mode functions. After the iterative optimization is completed, the finally generated intrinsic mode functions can accurately represent different frequency components in the roll vibration signal.

[0082] Furthermore, a benchmark vibration deviation model is established, and the roll gap deviation detection result is obtained by mapping according to the vibration deviation result, including:

[0083] Construct a roll vibration database, which includes historical roll vibration characteristic information and historical roll gap deviation information;

[0084] The roll vibration database classifies the historical roll vibration characteristic information and historical roll gap deviation information according to the processing equipment and the copper material to be processed;

[0085] Perform deep learning on the roll vibration database, and obtain the historical mapping relationship between the historical roll vibration characteristic information and the historical roll gap deviation information of the same processing equipment and copper material to be processed;

[0086] Match the vibration deviation result with the roll vibration database, and obtain the roll gap deviation detection result according to the historical mapping relationship.

[0087] In this embodiment, first, the historical vibration characteristic information and historical roll gap deviation information of the roll are collected and integrated to construct a roll vibration database. The historical roll vibration characteristic information includes vibration signal data, vibration amplitude, frequency components, etc. of the roll under different working conditions. The roll vibration database is classified according to the processing equipment and the copper material to be processed. Different equipment (such as different models of rolling mills, different types of work rolls) and different copper materials (such as copper materials with different thicknesses or surface treatments) will cause differences in vibration characteristics. Therefore, clustering analysis (such as K-means clustering algorithm) or multi-dimensional data analysis methods are used to classify the roll vibration characteristic information and roll gap deviation information. Each type of data corresponds to a specific combination of working conditions (such as equipment type and copper material characteristics), so as to optimize for different working conditions when training the deep learning model later. By using a neural network (such as a convolutional neural network or a long short-term memory network) to train the roll vibration database, the training data includes historical roll vibration characteristics and corresponding roll gap deviation information. Through training, the deep learning model can learn the mapping relationship between the roll vibration characteristics and the roll gap deviation, and extract the relationship between the roll vibration characteristics and the roll gap deviation. Subsequently, through the real-time collected vibration signal, the vibration deviation result is calculated, and the real-time obtained vibration deviation result is input into the trained deep learning model. The model will output the corresponding roll gap deviation detection result according to the historical mapping relationship.

[0088] Furthermore, constructing a roll vibration database includes:

[0089] Collect historical roll vibration characteristic information and historical roll gap deviation information;

[0090] Cluster and manage the historical roll vibration characteristic information according to the monitoring position of the vibration detection center line and the processing time axis, and each data item of the vibration characteristic matrix corresponds to the historical roll gap deviation information;

[0091] Take the monitoring location, the processing time axis, and the historical roll gap deviation information as database indexes respectively for the reference vibration deviation model to call the data chain.

[0092] Specifically, vibration monitoring of the roll is carried out through high-precision sensors (such as accelerometers and displacement sensors) to collect vibration characteristic information under different production conditions. These characteristics include vibration amplitude, frequency, phase, etc., which represent the overall vibration state of the roll. The roll gap deviation is usually obtained through special deviation detection equipment or directly from the control system of the rolling mill. These information record the change of the roll gap width, the deviation magnitude and its change over time. According to the obtained vibration detection center line and the monitoring location, the vibration characteristic information and the roll gap deviation information are divided according to the time axis. The vibration characteristics and deviation information within each time period will be classified into the category corresponding to that time period. And according to factors such as processing equipment and copper material type, the vibration characteristic data is clustered. By using the K-means clustering or other clustering algorithms, the data items of each vibration characteristic matrix are classified with the corresponding historical roll gap deviation information, which is convenient for subsequent data analysis and model training. Subsequently, by assigning a unique identifier to each monitoring point, the monitoring location, the processing time axis, and the roll gap deviation information are respectively used as an index field, which is convenient for quickly searching and processing the vibration data of a specific location in subsequent analysis.

[0093] Furthermore, obtain the vibration deviation result according to several deviation comparison parameters, including:

[0094] Set the deviation warning value, traverse several deviation comparison parameters according to the deviation warning value to obtain several vibration parameter deviations;

[0095] Obtain the time slice corresponding to several vibration parameter deviations and the position coordinates of the vibration monitoring points, and obtain the vibration deviation result.

[0096] As a preference of the above embodiments, first, it is necessary to set a deviation warning value based on historical data analysis, production conditions, and experience. The deviation warning value is a threshold used to determine whether there is an abnormality in the vibration signal. The deviation warning value can be a fixed value or can be dynamically adjusted according to production conditions and different working conditions. For example, a deviation warning value can be set such that the change in vibration amplitude in each frequency band exceeds 5%. For a specific production state (such as high-load rolling or high-speed operation), the warning value can be appropriately increased to avoid frequent triggering of unnecessary alarms. Subsequently, deviation comparison parameters are obtained to compare with the deviation warning value to check whether the deviation warning value is exceeded. If a certain data item exceeds the warning value, the vibration deviation of this item is recorded. Each vibration parameter deviation corresponds to a specific time slice and monitoring point. When performing deviation comparison, the system will record the time stamp when the deviation occurs and the position coordinates of the vibration monitoring point. Through the time stamp, the specific time when the deviation occurs can be determined, and through the position coordinates, the position where the deviation occurs can be determined. During the deviation comparison process, if the deviation of some vibration parameters exceeds the warning value, the system will calculate the vibration deviation results for each monitoring point and time slice.

[0097] Embodiment 2;

[0098] Based on the same inventive concept as the deviation detection method for a rolling mill roll gap in the foregoing embodiments, the present invention further provides a deviation detection system for a rolling mill roll gap. The system includes:

[0099] A reference vibration center line construction module that establishes a vibration detection center line based on the copper material to be processed as a reference. The vibration detection center line is parallel to the roll axis of the work roll;

[0100] A working vibration acquisition module that acquires the roll vibration characteristics for each work roll based on the vibration detection center line and generates a vibration characteristic matrix corresponding to the processing time axis of the work roll;

[0101] A vibration deviation model comparison module that establishes a reference vibration deviation model, performs vibration deviation comparison on the vibration characteristic matrix corresponding to each work roll, and obtains the roll gap deviation detection result according to the vibration deviation result mapping.

[0102] The above adjustment system in the present invention can effectively implement a deviation detection method for a rolling mill roll gap, and the technical effects that can be achieved are as described in the above embodiments and will not be elaborated here.

[0103] Embodiment 3;

[0104] Based on the same inventive concept as the deviation detection method for a rolling mill roll gap in the foregoing embodiments, the present invention further provides a deviation detection device for a rolling mill roll gap. The device applies any deviation detection method for a rolling mill roll gap.

[0105] Although the present application has been described in connection with specific features and their embodiments, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined by the appended claims and are considered to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for detecting the deviation of the roll gap of a rolling mill, characterized in that, The method includes: Establishing a vibration detection center line based on the copper material to be processed, and the vibration detection center line is parallel to the roll axis of the working roll; Collecting and obtaining the roll vibration characteristics for each working roll according to the vibration detection center line, and generating a vibration characteristic matrix corresponding to the processing time axis of the working roll; Collecting and obtaining the roll vibration characteristics includes: Capturing the roll vibration signal, evaluating the correlation degree of the roll vibration signal, and obtaining the roll vibration characteristics; Evaluating the correlation degree of the roll vibration signal includes: Preprocessing the roll vibration signal, splitting the preprocessed roll vibration signal, and obtaining a number of intrinsic mode functions, and each intrinsic mode function represents a specific frequency band of the roll vibration signal; Screening a number of the intrinsic mode functions to obtain a number of relevant frequency bands, where the relevant frequency bands represent the intrinsic mode functions associated with the roll gap deviation, determining the variation law of each frequency band under different working conditions, and evaluating the correlation between different frequency bands and the roll gap deviation; Performing splicing and reconstruction on the roll vibration signal according to a number of the relevant frequency bands, combining the intrinsic mode functions of the selected frequency bands to obtain the roll vibration characteristics, and the splicing and reconstruction means splicing and reorganizing a number of the relevant frequency bands; Collecting the roll vibration signal in real time, and the roll vibration signal collected in real time will be organized according to the time axis to update the vibration characteristic matrix. Whenever a new roll vibration signal is collected, the system will update the vibration characteristic matrix according to the time axis. With the collection and processing of the signal data of each time slice, the vibration characteristic matrix is gradually accumulated and updated, and a reference vibration deviation model is loaded to output the roll gap deviation detection result; Establishing a reference vibration deviation model, comparing the vibration deviation of the vibration characteristic matrix corresponding to each working roll, and obtaining the roll gap deviation detection result according to the vibration deviation result mapping; Comparing the vibration deviation of the vibration characteristic matrix corresponding to each working roll includes: Setting a number of vibration monitoring points at the corresponding positions of the vibration detection center line and the working roll respectively, and respectively obtaining the roll vibration characteristics of the working roll at the corresponding positions of the vibration detection center line; Determining the time length of the processing time and dividing the time length into equal-length time slices; Performing vibration deviation comparison on the roll vibration characteristics of each working roll with the same position coordinates and the same time slice according to the vibration monitoring points and the time slice length to obtain a number of deviation comparison parameters; Obtaining the vibration deviation result according to a number of the deviation comparison parameters.

2. The deviation detection method of the rolling mill roll gap according to claim 1, characterized in that Splitting the preprocessed roll vibration signal includes: Pre-decomposing the roll vibration signal based on frequency to obtain a number of initial mode functions; Performing time-frequency analysis on a number of the initial mode functions, estimating the frequency components of the initial mode functions, and setting the initial center frequency according to the frequency components; Collect historical rolling mill working condition information, set a minimization objective function according to the historical rolling mill working condition signal, iteratively optimize the frequency range of the initial mode function according to the minimization objective function, and constrain the central frequency to obtain a number of intrinsic mode functions, where the intrinsic mode functions represent different frequency components in the roll vibration signal.

3. The deviation detection method of the rolling mill roll gap according to claim 1, wherein Establish a reference vibration deviation model, and obtain a roll gap deviation detection result according to the mapping of the vibration deviation result, including: Construct a roll vibration database, where the roll vibration database includes historical roll vibration characteristic information and historical roll gap deviation information; The roll vibration database classifies the historical roll vibration characteristic information and historical roll gap deviation information according to the processing equipment and the copper material to be processed; Perform deep learning on the roll vibration database, and obtain a historical mapping relationship between the historical roll vibration characteristic information and the historical roll gap deviation information of the same processing equipment and copper material to be processed; Match the vibration deviation result with the roll vibration database, and obtain the roll gap deviation detection result according to the historical mapping relationship.

4. The deviation detection method of the rolling mill roll gap according to claim 3, characterized in that, Construct a roll vibration database, including: Collect the historical roll vibration characteristic information and historical roll gap deviation information; Cluster and manage the historical roll vibration characteristic information according to the monitoring position of the vibration detection center line and the processing time axis, and each data item of the vibration characteristic matrix corresponds to the historical roll gap deviation information; Use the monitoring position, processing time axis, and the historical roll gap deviation information as database indexes respectively for the reference vibration deviation model to call the data link.

5. The deviation detection method of the rolling mill roll gap according to claim 1, characterized in that, Obtain the vibration deviation result according to a number of deviation comparison parameters, including: Set a deviation warning value, traverse the number of deviation comparison parameters according to the deviation warning value to obtain a number of vibration parameter deviations; Obtain the time slice and the position coordinates of the vibration monitoring points corresponding to the number of vibration parameter deviations, and obtain the vibration deviation result.

6. A deviation detection system for the roll gap of a rolling mill, characterized in that, Adopt the deviation detection method for the roll gap of the rolling mill as described in claim 1, and the system includes: A reference vibration center line construction module, which establishes a vibration detection center line based on the copper material to be processed, and the vibration detection center line is parallel to the roll axis of the work roll; A working vibration acquisition module, which acquires roll vibration characteristics for each work roll according to the vibration detection center line, and generates a vibration characteristic matrix corresponding to the processing time axis of the work roll; A vibration deviation model comparison module, which establishes a reference vibration deviation model, performs vibration deviation comparison on the vibration characteristic matrix corresponding to each work roll, and obtains a roll gap deviation detection result according to the mapping of the vibration deviation result.

7. A deviation detection device for the roll gap of a rolling mill, characterized in that, The device applies the deviation detection method for the roll gap of the rolling mill as described in any one of claims 1-5.

Images