Seamless steel tube grinding process detection method and system based on machine vision

Abstract

The invention relates to the technical field of quality detection, and discloses a seamless steel tube grinding process detection method and system based on machine vision. The method comprises the following steps: acquiring detection data in a steel pipe grinding process under different abrasive particle sizes, inputting the detection data into a neural network model, extracting a process variable and a result variable of a grinding process, constructing a data relation scatter diagram according to the extracted variables, and performing trend analysis to calculate a discrete degree, and calculating a dispersion degree coefficient and an adjustment coefficient based on the dispersion degree, generating an overall deviation distribution scatter value, comparing the overall deviation distribution scatter value with a preset threshold value, and judging whether the grinding process is qualified or not. The method has the advantages that through multi-level analysis of data and capture of the incidence relation, the accuracy and precision of detection are effectively improved, the reliability of grinding process evaluation is improved, and the requirement for high-precision process control is met.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for detecting a grinding process of a seamless steel pipe based on machine vision. Background Art

[0002] At present, in the production and processing of seamless steel pipes, the grinding process is a key step to remove the oxide scale on the surface of the steel pipe and improve the surface quality. In this process, it is necessary to adjust the process according to the grinding conditions of the steel pipe surface, and the abrasive size in the grinding process is the main control parameter affecting the effect. Different abrasive sizes will cause different stress distribution and oxide scale distribution on the surface of the steel pipe, thus affecting the final grinding effect. Therefore, it has become an important link in process control to obtain and analyze the test data corresponding to different abrasive sizes, generate corresponding stress distribution maps and oxide scale distribution maps, and determine the optimal abrasive size.

[0003] The existing technology usually determines the consistency of data by calculating the variance of the discrete degree of different abrasive size detection data, and uses this as an evaluation index. However, this method only focuses on the discrete degree of data, ignores the correlation between different abrasive size detection data, and is difficult to reflect the overall distribution characteristics of the data, resulting in low detection accuracy and precision, which is difficult to meet the needs of high-precision process control. Summary of the invention

[0004] The present invention provides a method and system for detecting the grinding process of a seamless steel pipe based on machine vision, which solves the problem in the prior art of low detection accuracy and precision caused by only focusing on the discreteness of detection data and ignoring the correlation between detection data of different abrasive grain sizes.

[0005] In the first aspect, in order to solve the above technical problems, the present invention provides a method for detecting a grinding process of a seamless steel pipe based on machine vision, comprising:

[0006] Acquire detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed;

[0007] Inputting the detection data into a neural network model to analyze and extract process variables and result variables of the grinding process;

[0008] Constructing a data relationship scatter plot of the grinding process according to the process variables and the result variables;

[0009] Performing trend analysis on the data points in the data relationship scatter plot, calculating the degree of dispersion under each trend, and obtaining a degree of dispersion value of the data relationship;

[0010] Calculate a dispersion coefficient based on the dispersion value, and obtain an adjustment coefficient corresponding to the dispersion degree of the data relationship by combining the dispersion coefficient with the distribution density of points in the data relationship scatter plot;

[0011] Generate an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient;

[0012] The overall deviation distribution scatter value is compared with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified. If the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

[0013] Preferably, the detection data is input into a neural network model to analyze and extract process variables and result variables of the grinding process, including:

[0014] Performing data preprocessing on the detection data to obtain preprocessed detection data, wherein the data preprocessing includes removing noise and abnormal values ​​in the detection data;

[0015] Based on the pre-processed test data, the grinding process characteristics under different abrasive grain sizes are analyzed to obtain the key parameters related to the grinding effect in the pre-processed test data;

[0016] According to the key parameters related to the grinding effect in the pre-processed inspection data, the process noise and post-noise features are extracted and combined to obtain the overall inspection data;

[0017] The overall detection data is used as input data and input into a pre-trained neural network model to obtain process variables and result variables of the grinding process.

[0018] Preferably, constructing a data relationship scatter plot of the grinding process according to the process variables and the result variables includes:

[0019] Analyzing the relationship between the process variables and the result variables to obtain a correlation pattern related to the grinding process effect;

[0020] Based on the association pattern, data pairing is performed on the process variables and the result variables to generate a plurality of data pairs, wherein the data pairs can reflect the grinding process characteristics under conditions of different abrasive grain sizes;

[0021] A data relationship scatter plot of the grinding process is constructed using the data pairs as coordinate points.

[0022] Preferably, trend analysis is performed on the data points in the data relationship scatter plot, and the degree of dispersion under each trend is calculated to obtain the degree of dispersion of the data relationship, including:

[0023] According to the change trend of the data points in the data relationship scatter plot, the data points are divided into a gentle trend and a wavy trend, wherein the gentle trend indicates an area with a small change, and the wavy trend indicates an area with a large change;

[0024] According to different trends, calculate the change amount of the overall trend and the corresponding number of changes, and quantify the fluctuations under different trends;

[0025] Based on the change amount of the overall change trend and the corresponding change times, the discrete degree values ​​under different trends are calculated by the following formula:

[0026]

[0027] Among them, D r is the discrete degree value, T represents different trends, including gentle trends and undulating trends, ΔV T Indicates the change in the overall trend under the corresponding trend T, N T Indicates the number of changes in the corresponding trend T, f(ΔV T ) and g(N T ) represent two linear normalized functions under the corresponding trend T, which are calculated by the following formula:

[0028]

[0029] Among them, min(ΔV T ) is ΔV T The minimum value, max(ΔV T ) is ΔV T The maximum value of min(N T ) is N T The minimum value, max(N T ) is N T The maximum value of .

[0030] Preferably, the dispersion degree coefficient is calculated based on the dispersion degree value, and the adjustment coefficient corresponding to the dispersion degree of the data relationship is obtained by combining the dispersion degree coefficient with the distribution density of the points in the data relationship scatter plot, including:

[0031] Based on the dispersion value, the dispersion coefficient is calculated by the following formula:

[0032] D c =f(D r )

[0033] Among them, D c Denotes the dispersion coefficient, D r is the discrete degree value, f is the linear normalization function;

[0034] Based on the discrete degree coefficient, set the sliding window parameters, and calculate the discrete degree in different sliding windows in sections, wherein the sliding window parameters include window width and sliding step length;

[0035] Based on the discrete degree coefficient, the discrete situation value in each sliding window is calculated by the following formula:

[0036]

[0037] Among them, D s Indicates the discrete case value, max(D c ) and min(D c ) are the maximum and minimum values ​​of the discrete degree coefficient in the sliding window, respectively, and N is the number of discrete degree coefficients in the sliding window;

[0038] Based on the discrete case value, the normalized discrete case value is calculated by the following formula:

[0039]

[0040] Among them, D sn Represents the normalized discrete case value, max(D s ) and min(D s ) are the maximum and minimum values ​​of the discrete case values ​​in all sliding windows respectively;

[0041] Based on the dispersion degree coefficient and the normalized dispersion value, the dispersion degree adjustment coefficient is calculated by the following formula:

[0042]

[0043] Among them, D adj Represents the adjustment coefficient, N max The maximum number of scatter points in the data relationship scatter plot.

[0044] Preferably, generating the overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient includes:

[0045] Using the dispersion degree value and the dispersion degree coefficient as input parameters of the overall deviation distribution scatter point value to represent the overall dispersion degree and local characteristics of the data distribution;

[0046] Based on the dispersion degree value, the dispersion degree coefficient and the adjustment coefficient, the overall deviation distribution scatter value is calculated by the following formula:

[0047] D total =D r ×D c ×D adj

[0048] Among them, D total Indicates the overall deviation from the distribution scatter value, D r is the discrete degree value, D c Denotes the dispersion coefficient, D adj is the adjustment coefficient.

[0049] Preferably, the overall deviation distribution scatter value is compared with a preset threshold value, if the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified, if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified, including:

[0050] Collect historical data from multiple grinding processes, and count the overall deviation distribution scatter points of each grinding process to form a distribution data set;

[0051] Calculate the mean and standard deviation of the deviation distribution scatter point values ​​according to the distribution data set to obtain a preliminary threshold range;

[0052] According to the preliminary threshold range, weighted adjustment is performed on the mean value to obtain a final preset threshold value of the deviation distribution scatter point value;

[0053] The overall deviation distribution scatter value is compared with the preset threshold. If the deviation distribution scatter value is lower than or equal to the preset threshold, the grinding process is judged to be qualified. If the deviation distribution scatter value is higher than the preset threshold, the grinding process is judged to be unqualified.

[0054] In a second aspect, the present invention provides a machine vision-based seamless steel pipe grinding process detection system, which is used to implement any one of the machine vision-based seamless steel pipe grinding process detection methods described above, including:

[0055] A data acquisition module is used to acquire detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed;

[0056] A feature extraction module, used for inputting the detection data into a neural network model, analyzing and extracting process variables and result variables of the grinding process;

[0057] A data relationship building module, used for building a data relationship scatter diagram of the grinding process according to the process variables and the result variables;

[0058] A trend analysis module, used to perform trend analysis on the data points in the data relationship scatter plot, calculate the degree of dispersion under each trend, and obtain the degree of dispersion value of the data relationship;

[0059] A discrete degree adjustment module, used to calculate a discrete degree coefficient based on the discrete degree value, and to obtain an adjustment coefficient corresponding to the discrete degree of the data relationship by combining the discrete degree coefficient with the distribution density of the points in the data relationship scatter plot;

[0060] An overall deviation calculation module, used to generate an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient;

[0061] The process evaluation module is used to compare the overall deviation distribution scatter value with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified; if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

[0062] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for detecting the grinding process of a seamless steel pipe based on machine vision.

[0063] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned machine vision-based seamless steel pipe grinding process detection methods.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention provides a method for detecting the grinding process of seamless steel pipes based on machine vision, which includes the steps of real-time collection of detection data, analysis and training of neural network models, construction of data relationship scatter plots, trend analysis and calculation of discreteness, and finally generates deviation distribution scatter values ​​and performs qualification evaluation. Through this technical solution, it is possible to comprehensively analyze the data characteristics under different abrasive particle sizes, capture the correlation relationship and overall distribution characteristics between data, and thus improve the accuracy of detection.

[0066] Compared with the prior art, the present invention not only focuses on the discreteness of the data, but also considers the correlation and overall distribution characteristics between the data of different abrasive grain sizes, which significantly improves the accuracy and precision of the detection. In addition, when evaluating the grinding process effect, the present invention can not only detect the quality parameters after grinding, but also predict potential quality problems in the grinding process through real-time data analysis. Therefore, the present invention effectively solves the shortcomings of the existing methods in detection accuracy, reliability and adaptability, and meets the needs of high-precision grinding process control. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic flow chart of a method for detecting a grinding process of a seamless steel pipe based on machine vision provided by a first embodiment of the present invention;

[0068] Figure 2 It is a structural schematic diagram of a seamless steel pipe grinding process detection method based on machine vision provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Reference Figure 1 The first embodiment of the present invention provides a method for detecting a grinding process of a seamless steel pipe based on machine vision, comprising the following steps:

[0071] S11, acquiring detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed;

[0072] S12, inputting the detection data into a neural network model to analyze and extract process variables and result variables of the grinding process;

[0073] S13, constructing a data relationship scatter plot of the grinding process according to the process variables and the result variables;

[0074] S14, performing trend analysis on the data points in the data relationship scatter plot, calculating the degree of dispersion under each trend, and obtaining a degree of dispersion value of the data relationship;

[0075] S15, calculating a dispersion coefficient based on the dispersion value, and combining the dispersion coefficient with the distribution density of points in the data relationship scatter plot to obtain an adjustment coefficient corresponding to the dispersion degree of the data relationship;

[0076] S16, generating an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, the discrete degree coefficient and the adjustment coefficient;

[0077] S17, comparing the overall deviation distribution scatter value with a preset threshold value, if the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified, if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

[0078] In step S11, the detection data of the steel pipe grinding process under different abrasive grain sizes is obtained, and the detection data includes noise data generated during the grinding process and data after the grinding is completed, including:

[0079] Using multiple detection devices to collect real-time noise data during the grinding operation to obtain dynamic information of the grinding process under different abrasive grain size conditions, wherein the real-time noise data collection process during the grinding operation can capture instantaneous changes in the grinding process and reflect characteristic information generated during the grinding process;

[0080] After the grinding operation is completed, the detection equipment is continued to collect the noise data after grinding to obtain the stable state information after the grinding process is completed. The noise data after grinding can reflect the characteristics of the grinding results and provide a comparison basis for subsequent analysis;

[0081] The collected noise data are marked and classified according to the grinding process and the post-grinding state, and are sorted according to different abrasive particle size conditions to ensure that the noise characteristic data corresponding to each abrasive particle size can be accurately distinguished in subsequent analysis.

[0082] In step S12, the detection data is input into the neural network model to analyze and extract the process variables and result variables of the grinding process, including:

[0083] S121, performing data preprocessing on the detection data to obtain preprocessed detection data, wherein the data preprocessing includes removing noise and abnormal values ​​in the detection data;

[0084] S122, analyzing grinding process characteristics under different abrasive grain sizes based on the preprocessed detection data, and obtaining key parameters related to the grinding effect in the preprocessed detection data;

[0085] S123, extracting process noise and post-noise features according to key parameters related to grinding effect in the preprocessed detection data, combining them, and obtaining overall detection data;

[0086] S124, taking the overall detection data as input data, inputting it into a pre-trained neural network model to obtain process variables and result variables of the grinding process.

[0087] In step S121, the detection data is preprocessed to obtain preprocessed detection data, wherein the data preprocessing includes removing noise and abnormal values ​​in the detection data, including:

[0088] For the noise signals in the detection data, multi-level filtering processing technology is used, including high-pass filtering, low-pass filtering and band-pass filtering, to remove irrelevant background noise and high-frequency or low-frequency interference signals layer by layer;

[0089] After noise filtering, in order to further reduce the random fluctuation of data, the sliding average method is used for processing, that is, the data is smoothed by taking the average value of data within a certain range, making the data fluctuation more continuous and reducing the impact of mutation points on the analysis;

[0090] In order to ensure the accuracy and consistency of the data, a variety of algorithms are used to detect and remove outliers in the data;

[0091] After removing noise and outliers, in order to maintain the integrity of the data, an interpolation algorithm is used to compensate for missing data points;

[0092] After noise removal and outlier elimination, the data is standardized to ensure consistency among different batches of data or data collected by different testing equipment.

[0093] In steps S122 and S123, based on the pre-processed detection data, the grinding process characteristics under different abrasive grain sizes are analyzed to obtain the key parameters related to the grinding effect in the data; according to the key parameters related to the grinding effect in the data, the process noise and the later noise characteristics are extracted and combined to obtain the overall detection data. In the grinding process, the key parameters include grinding force, grinding temperature, grinding speed, and abrasive grain size, which have a direct impact on the grinding effect. Exemplarily, statistical analysis methods are used to identify these key parameters. For example, the change trend and distribution of the parameters can be understood by calculating the mean, standard deviation, maximum and minimum values ​​of each parameter. Assuming there is a set of grinding force data, the stability of the grinding force during the grinding process can be evaluated by calculating the standard deviation of this set of data. If the standard deviation is small, it means that the grinding force is relatively stable and the grinding quality is high.

[0094] Furthermore, process noise refers to the noise caused by changes in grinding parameters during the grinding process, while post-noise is related to cooling, measurement and other processes after grinding. Combining the process noise and post-noise features to obtain the noise characteristics of the overall detection data can be achieved by weighted summing the intensities of different noise features, and the weight can be determined according to the degree of influence of the noise on the grinding effect. For example, if the process noise has a greater impact on the grinding effect than the post-noise, then when combining the noise features, the process noise can be given a greater weight. In this way, the overall detection data will better reflect the main noise sources in the grinding process.

[0095] In step S124, pre-training the neural network model includes:

[0096] The overall test data is divided into a ratio of 7:2:1, where 70% of the data is used for model training, 20% for model verification, and 10% for final testing to ensure the stability and generalization ability of model training;

[0097] According to the complexity of the grinding process feature data, the neural network model architecture is designed, in which the input layer is used to receive the preprocessed overall detection data, the feature dimension matches the number of features of the detection data, and the output layer sets the number of nodes in the output layer according to the number of target output variables. The output layer uses a linear or nonlinear activation function to adapt to different types of prediction tasks.

[0098] Choose a suitable loss function to measure the error between the model's predicted value and the actual output;

[0099] Use Adam optimizer or stochastic gradient descent optimizer for model training;

[0100] The predicted value of the model is calculated through forward propagation, and the model parameters are adjusted through the back-propagation algorithm to minimize the loss function;

[0101] After the training is completed, the model is evaluated using the test set to calculate the prediction error and various evaluation indicators.

[0102] In step S13, constructing a data relationship scatter plot of the grinding process according to the process variables and the result variables includes:

[0103] S131, analyzing the relationship between the process variables and the result variables to obtain a correlation pattern related to the grinding process effect;

[0104] S132, based on the association pattern, performing data pairing on the process variable and the result variable to generate a plurality of data pairs, wherein the data pairs can reflect the grinding process characteristics under conditions of different abrasive grain sizes;

[0105] S133, constructing a data relationship scatter plot of the grinding process using the data pairs as coordinate points.

[0106] In step S131, the association pattern is a mathematical or visual structure that describes the internal association and mutual influence between variables, and is used to reveal the influence and trend of different parameters in the grinding process on the final process effect, including:

[0107] Correlation strength between variables: Through data analysis, the correlation strength between process variables and result variables under different abrasive size conditions is quantified. The correlation strength can help identify the control parameters that have the greatest impact on process quality, so that the above key variables can be adjusted in the process optimization;

[0108] Trend type and distribution characteristics: The correlation mode divides the data points into gentle trends and wavy trends through trend analysis. The gentle trend represents a relatively stable process, and the wavy trend represents fluctuations in the process. Different trends reflect how the change in abrasive size affects the uniformity and consistency of surface roughness and stress distribution. For example, a smaller abrasive size will produce a more stable and continuous surface effect, while a larger abrasive size will lead to fluctuations in surface roughness and stress distribution.

[0109] Discreteness and distribution density: The correlation model can further describe the distribution of data in the scatter plot by calculating the discreteness value and the discrete coefficient. The distribution of the data in the scatter plot indicates the uniformity of the grinding effect under different abrasive grain size conditions. Among them, dense and regularly distributed data points indicate good process consistency, while discrete and sparse points indicate the non-uniformity of the process results. Through the statistics of the discreteness, the correlation model can intuitively reveal the stability and controllability of the process conditions;

[0110] Quantitative basis for process optimization: The resulting correlation model not only intuitively demonstrates the relationship between process parameters and quality results, but also provides a quantitative basis for further process optimization. The correlation model can be used as a criterion to help identify and adjust the optimal abrasive size to ensure the stability and consistency of the process effect.

[0111] In step S133, a data relationship scatter diagram of the grinding process is constructed with the data pairs as coordinate points, including:

[0112] Two key variables closely related to the grinding effect are selected as the horizontal axis and vertical axis respectively. The horizontal axis selects variables representing process control, such as grinding speed, abrasive size, and feed rate. The above variables representing process control have a direct impact on the grinding process and can better reflect the dynamic process of grinding. The vertical axis selects variables reflecting the results, such as surface roughness, stress distribution, and oxide scale removal effect. The variables reflecting the results represent the final effect of the grinding process and are important indicators for evaluating process quality.

[0113] It should be noted that the density of data points in the scatter plot reflects the data distribution under different abrasive size conditions, and the display of density is crucial to understanding the uniformity of grinding process characteristics and effects:

[0114] Data density changes under different abrasive size conditions: In actual operation, different abrasive size conditions will produce different numbers of data points. For example, smaller abrasive sizes will generate more concentrated and dense data points, reflecting the uniformity of the grinding process; while larger abrasive sizes will result in sparser or fluctuating distribution of data points, reflecting the non-uniformity of the grinding process;

[0115] Density display method: The data density is reflected by the color or transparency of the data points on the scatter plot. The higher density areas can be represented by dark or opaque points, while the lower density areas are represented by light or translucent points. In this way, the process personnel can intuitively understand the uniformity and stability of the grinding process under different abrasive size conditions by observing the changes in color depth or transparency in the scatter plot;

[0116] Statistics of density information: Further, in order to ensure the readability of the graph and the accuracy of the information, it is necessary to count the point density under each abrasive size condition, such as calculating the number of data points per unit area and presenting the density distribution in the scatter plot by color scale or point size. The above design can more accurately reflect the concentration and dispersion of data under different grinding conditions, thereby more effectively assisting process optimization.

[0117] In step S14, trend analysis is performed on the data points in the data relationship scatter plot, and the degree of dispersion under each trend is calculated to obtain the degree of dispersion of the data relationship, including:

[0118] According to the change trend of the data points in the data relationship scatter plot, the data points are divided into a gentle trend and a wavy trend, wherein the gentle trend indicates an area with a small change, and the wavy trend indicates an area with a large change;

[0119] According to different trends, calculate the change amount of the overall trend and the corresponding number of changes, and quantify the fluctuations under different trends;

[0120] Based on the change amount of the overall change trend and the corresponding change times, the discrete degree values ​​under different trends are calculated by the following formula:

[0121]

[0122] Among them, D r is the discrete degree value, T represents different trends, including gentle trends and undulating trends, ΔV T Indicates the change in the overall trend under the corresponding trend T, N T Indicates the number of changes in the corresponding trend T, f(ΔV T ) and g(N T ) represent two linear normalized functions under the corresponding trend T, which are calculated by the following formula:

[0123]

[0124] Among them, min(ΔV T ) is ΔV T The minimum value, max(ΔV T ) is ΔV TThe maximum value of min(N T ) is N T The minimum value, max(N T ) is N T The maximum value of .

[0125] In this embodiment, the division of a flat trend and a wavy trend can be achieved by calculating the slope between data points. For each pair of consecutive data points in the scatter plot, the slope between them is calculated (i.e., the amount of change divided by the time interval or position interval). A threshold is set. When the absolute value of the slope is lower than the threshold, the data point is considered to belong to a flat trend; when the absolute value of the slope is higher than the threshold, it is considered to belong to a wavy trend. For example, if the slope between data points (1,2) and (2,3) is 0.5, and the slope between data points (3,3) and (4,6) is 2.5, then the change in the latter is greater than the preset threshold 2, which belongs to a wavy trend.

[0126] In step S15, the discrete degree coefficient is calculated based on the discrete degree value, and the adjustment coefficient corresponding to the discrete degree of the data relationship is obtained by combining the discrete degree coefficient with the distribution density of the points in the data relationship scatter plot, including:

[0127] Based on the dispersion value, the dispersion coefficient is calculated by the following formula:

[0128] D c =f(D r )

[0129] Among them, D c Denotes the dispersion coefficient, D r is the discrete degree value, f is the linear normalization function;

[0130] Based on the discrete degree coefficient, set the sliding window parameters, and calculate the discrete degree in different sliding windows in sections, wherein the sliding window parameters include window width and sliding step length;

[0131] Based on the discrete degree coefficient, the discrete situation value in each sliding window is calculated by the following formula:

[0132]

[0133] Among them, D s Indicates the discrete case value, max(D c ) and min(D c ) are the maximum and minimum values ​​of the discrete degree coefficient in the sliding window, respectively, and N is the number of discrete degree coefficients in the sliding window;

[0134] Based on the discrete case value, the normalized discrete case value is calculated by the following formula:

[0135]

[0136] Among them, D sn Represents the normalized discrete case value, max(D s ) and min(D s ) are the maximum and minimum values ​​of the discrete case values ​​in all sliding windows respectively;

[0137] Based on the dispersion degree coefficient and the normalized dispersion value, the dispersion degree adjustment coefficient is calculated by the following formula:

[0138]

[0139] Among them, D adj Represents the adjustment coefficient, N max The maximum number of scatter points in the data relationship scatter plot.

[0140] In step S16, generating the overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient includes:

[0141] Using the dispersion degree value and the dispersion degree coefficient as input parameters of the overall deviation distribution scatter point value to represent the overall dispersion degree and local characteristics of the data distribution;

[0142] Based on the dispersion degree value, the dispersion degree coefficient and the adjustment coefficient, the overall deviation distribution scatter value is calculated by the following formula:

[0143] D total =D r ×D c ×D adj

[0144] Among them, D total Indicates the overall deviation from the distribution scatter value, D r is the discrete degree value, D c Denotes the dispersion coefficient, D adj is the adjustment coefficient.

[0145] It should be noted that the discrete degree value D r It represents the degree of dispersion of data points in the grinding process, that is, the degree of dispersion of data points relative to the average or expected value. The higher the dispersion value, the more dispersed the distribution of data points and the worse the consistency of the grinding process. c Used to adjust the discreteness value to reflect the discreteness under different grinding processes or different conditions. For example, different grinding speeds or grinding tools may affect the discreteness, and the discreteness coefficient can be adjusted according to different conditions to more accurately reflect the actual discreteness. Adjustment coefficient Dadj Used to further fine-tune the overall deviation distribution scatter value. Therefore, by multiplying the discrete degree value, discrete degree coefficient and adjustment coefficient, a comprehensive indicator can be obtained to evaluate the overall deviation of the grinding process. The higher this value is, the greater the deviation of the grinding process is, and the process adjustment is needed to improve product quality.

[0146] In step S17, the overall deviation distribution scatter value is compared with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified. If the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified, including:

[0147] S171, collecting historical data from multiple grinding processes, and counting the overall deviation distribution scatter point value of each grinding process to form a distribution data set;

[0148] S172, calculating the mean and standard deviation of the deviation distribution scatter point values ​​according to the distribution data set to obtain a preliminary threshold range;

[0149] S173, performing weighted adjustment on the mean value according to the preliminary threshold range to obtain a final preset threshold value of the deviation distribution scatter point value;

[0150] S174, comparing the overall deviation distribution scatter value with the preset threshold value, if the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified, if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

[0151] In the above steps, the mean of the deviation distribution scatter value is used to represent the average level of the overall deviation; the standard deviation of the deviation distribution scatter value is used to measure the degree of fluctuation of the deviation distribution scatter value. Then, the threshold can be tightened to the sum of the mean and the standard deviation of the preset adjustment coefficient multiple to obtain a preliminary threshold range, where the preset adjustment coefficient represents the tolerance range of the deviation scatter value, for example, it is set to 1, 2, 3, etc. according to the accuracy requirement, and the present invention does not limit this.

[0152] Exemplarily, data from the past 100 grinding processes are collected. These data include the deviation between the actual size of the product after each grinding and the target size. For these 100 grindings, the deviation value of each grinding is calculated, and these deviation values ​​are recorded to form a distribution data set. For example, the deviation value set [0.02, -0.01, 0.03, -0.02, 0.00, ..., 0.01]. Calculate the mean (average deviation) and standard deviation of this data set. Assume that the calculation results are as follows: mean (average deviation): 0.005mm; standard deviation: 0.01mm. Next, a preliminary threshold range can be determined using the mean ± 3 times the standard deviation. The preliminary threshold range is:

[0153] Lower limit: 0.005mm-3*0.01mm=-0.025mm

[0154] Upper limit: 0.005mm+3*0.01mm=0.035mm

[0155] It should be noted that this embodiment determines a weighting factor to adjust the mean, so as to obtain the preset threshold of the final deviation distribution scatter value. For example, considering the uncertainty and potential risks of the process, a weighting factor less than 1 is selected to lower the threshold to ensure higher product quality. For example, a safety factor of 0.8 (i.e., 80% of 3 times the standard deviation) is used, then the final threshold is:

[0156] Lower limit: 0.005mm-0.8*3*0.01mm=-0.019mm

[0157] Upper limit: 0.005mm+0.8*3*0.01mm=0.029mm

[0158] Therefore, the final preset threshold range is [-0.019, 0.029].

[0159] In one implementation, the machine vision-based seamless steel pipe grinding process detection method of the present invention is suitable for real-time quality detection in seamless steel pipe production lines. The surface grinding process of seamless steel pipes directly affects the quality of the final product, such as the surface finish, the removal effect of oxide scale, and the uniformity of stress distribution. Therefore, high-precision real-time monitoring during the grinding process is crucial. The present invention arranges multiple noise detection devices on the production line, and uses a non-contact method to collect the grinding process noise data under different abrasive sizes in real time, including the dynamic noise data generated during the grinding process and the static noise data after the grinding is completed. These data truly reflect the dynamic change state and final result state of the grinding process, and provide a reliable data basis for the comprehensive evaluation of process quality.

[0160] After data collection is completed, the acquired grinding process noise data will enter the data preprocessing stage. Through filtering, denoising and outlier elimination data preprocessing technology, the environmental interference and accidental abnormal noise in the original grinding process noise data can be removed, thereby ensuring that the data more truly reflects the characteristics of the grinding process. This preprocessing step can improve the quality and consistency of the data and lay a solid foundation for subsequent data analysis. The preprocessed data reduces noise interference to a certain extent and more concentratedly reflects the influence of abrasive size on the grinding effect.

[0161] Next, the processed test data is input into a fully trained neural network model. The neural network model has been trained based on data of different abrasive grain sizes and multiple grinding conditions, and can accurately identify and extract key process variables and result variables in the grinding process. The key process variables and result variables in the grinding process not only characterize the current state of the grinding process, but also provide important data support for subsequent trend analysis and scatter plot construction, ensuring the accuracy and reliability of the analysis results.

[0162] After extracting the key process variables and result variables in the grinding process, the present invention visualizes these variables through a data relationship scatter plot. The data relationship scatter plot is used to show the correlation between different variables. In the present invention, the process variables and result variables are used as coordinate axes, and the grinding effects under different abrasive sizes are intuitively displayed in the form of coordinate points. The data relationship scatter plot can clearly present the data distribution characteristics under different abrasive size conditions. For example, a smaller abrasive size will correspond to a smoother surface effect and uniform stress distribution, while a larger abrasive size will lead to increased surface roughness and uneven stress distribution. Through the data relationship scatter plot, production operators can intuitively observe the relationship between different variables, providing a basis for the optimization of process parameters.

[0163] Subsequently, the system performs trend analysis on the data points in the data relationship scatter plot to calculate the degree of dispersion under each trend. The process of trend analysis includes identifying flat trends and wavy trends and performing quantitative calculations on these trends. The flat trend represents an area with small changes, and the wavy trend represents an area with large changes. The division of flat trends and wavy trends helps to reveal the fluctuation characteristics and consistency of data under different abrasive size conditions, and reflects the stability and controllability of the process under different conditions. By calculating the change amount of the overall change trend and the corresponding number of changes, the system can quantify the data fluctuations under different trends.

[0164] Based on the results of the trend analysis, the system will calculate the dispersion value. The dispersion value not only indicates the volatility of the data, but also reflects the stability and consistency of the process. Next, the dispersion values ​​under different trends are normalized by calculating the dispersion coefficient, so that the data under different abrasive size conditions can be compared within a standard range. The calculation of the dispersion coefficient also comprehensively considers the distribution density of data points in the data relationship scatter plot to ensure that data under different process conditions can be compared fairly and accurately.

[0165] After obtaining the dispersion coefficient, the system will calculate the adjustment coefficient. The adjustment coefficient is based on the data distribution density and is calculated in combination with the dispersion value and the dispersion coefficient to ensure that the overall deviation distribution scatter value can fully reflect the overall deviation of the current grinding process. By calculating the adjustment coefficient, the system can effectively adjust the deviation between the data, making the final deviation distribution scatter value more representative.

[0166] Finally, the generated overall deviation distribution scatter value is compared with the preset threshold to evaluate the qualification of the grinding process. The preset threshold is set based on process requirements, historical data and quality control standards. The overall deviation distribution scatter value is compared with the threshold. If the overall deviation distribution scatter value is lower than or equal to the threshold, it indicates that the grinding process is within the allowable quality range and is judged to be qualified; conversely, if the deviation value exceeds the threshold, the process quality is judged to be substandard and is judged to be unqualified. This quality assessment method combines multi-level data analysis with variable relationship calculation, which significantly improves the accuracy and reliability of process quality judgment.

[0167] In another implementation, the detection method of the present invention is not only applicable to the grinding process of seamless steel pipes, but can also be extended to the quality control of other metal surface processing processes, such as the grinding and polishing of castings or the surface treatment of plates. By adjusting the parameters of the data acquisition module and the feature extraction module, the system of the present invention can adapt to different metal surface processing conditions, thereby providing a widely applicable quality control solution. In other application scenarios, the present invention can achieve high-precision process evaluation through similar noise detection equipment and neural network models, effectively identify potential quality problems in the production process, and reduce the defective rate of later products.

[0168] To better illustrate the working principle of the present invention, the implementation process of the present invention is described below in conjunction with a specific application scenario. Assume that in a typical seamless steel pipe grinding workshop, by installing the detection system of the present invention, real-time data is collected at different stages of the grinding process. During the grinding process, the detection equipment collects noise data in real time and analyzes the current grinding state; after the grinding is completed, the system further collects noise data after grinding to compare the changes before and after the process. All data are transmitted to the data processing center through the network, input into the neural network model for analysis, and the key process variables and result variables of the current process are extracted. Subsequently, the system generates a data relationship scatter plot, performs trend analysis and discrete degree calculation, and finally obtains the overall deviation distribution scatter value. The system promptly feeds back the process quality judgment result to the operator based on the comparison result of the deviation distribution scatter value and the threshold. If the process is judged to be unqualified, the system will issue an alarm so that the operator can make process adjustments immediately.

[0169] In summary, refer to Figure 2The second embodiment of the present invention provides a seamless steel pipe grinding process detection system based on machine vision, comprising:

[0170] A data acquisition module is used to acquire detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed;

[0171] A feature extraction module, used for inputting the detection data into a neural network model, analyzing and extracting process variables and result variables of the grinding process;

[0172] A data relationship building module, used for building a data relationship scatter diagram of the grinding process according to the process variables and the result variables;

[0173] A trend analysis module, used to perform trend analysis on the data points in the data relationship scatter plot, calculate the degree of dispersion under each trend, and obtain the degree of dispersion value of the data relationship;

[0174] A discrete degree adjustment module, used to calculate a discrete degree coefficient based on the discrete degree value, and to obtain an adjustment coefficient corresponding to the discrete degree of the data relationship by combining the discrete degree coefficient with the distribution density of the points in the data relationship scatter plot;

[0175] An overall deviation calculation module, used to generate an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient;

[0176] The process evaluation module is used to compare the overall deviation distribution scatter value with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified; if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

[0177] Preferably, the data acquisition module includes multiple detection devices arranged at different stations of the grinding process, which are used to collect noise data in real time during the grinding process and collect noise data after grinding. The module can perform comprehensive noise monitoring of the grinding process and results under different abrasive grain sizes, providing sufficient input information for subsequent data analysis.

[0178] Preferably, the feature extraction module includes a data preprocessing unit and a neural network model processing unit. The data preprocessing unit is used to remove noise interference and abnormal values ​​in the detection data to improve the reliability of the data; the neural network model processing unit is used to extract key process variables and result variables of the grinding process from the preprocessed data to provide basic data for the construction of data relationships.

[0179] Preferably, the trend analysis module further comprises a trend identification unit and a discrete calculation unit. The trend identification unit is used to identify the smooth and wavy trend areas in the data relationship scatter plot, and the discrete calculation unit is used to calculate the degree of discreteness under different trends, thereby quantifying the volatility and consistency of the data.

[0180] Preferably, the discrete degree adjustment module includes a sliding window setting unit and a normalization calculation unit. The sliding window setting unit is used to set the window width and sliding step size for calculating the discrete degree in different windows; the normalization calculation unit is used to normalize the discrete situation values ​​in each window, so as to obtain a discrete degree coefficient with a unified scale, laying the foundation for the final adjustment coefficient calculation.

[0181] Preferably, the process evaluation module includes a threshold setting unit and a comparison and judgment unit. The threshold setting unit presets the threshold of the deviation distribution scatter point according to the process requirements, historical data and quality control standards, and the comparison and judgment unit is used to compare the overall deviation distribution scatter point value with the preset threshold to judge the qualification of the grinding process and output the evaluation result.

[0182] It should be noted that a seamless steel pipe grinding process detection device based on machine vision provided in an embodiment of the present invention is used to execute all process steps of a seamless steel pipe grinding process detection method based on machine vision in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0183] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a grinding process detection program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the seamless steel pipe grinding process detection method based on machine vision are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as the data acquisition module.

[0184] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0185] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0186] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0187] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0188] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0189] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0190] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting the grinding process of a seamless steel pipe based on machine vision, characterized in that: The following steps are involved: Acquire detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed; Inputting the detection data into a neural network model to analyze and extract process variables and result variables of the grinding process; Constructing a data relationship scatter plot of the grinding process according to the process variables and the result variables; Performing trend analysis on the data points in the data relationship scatter plot, calculating the degree of dispersion under each trend, and obtaining a degree of dispersion value of the data relationship; Calculate a dispersion coefficient based on the dispersion value, and obtain an adjustment coefficient corresponding to the dispersion degree of the data relationship by combining the dispersion coefficient with the distribution density of points in the data relationship scatter plot; Generate an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient; The overall deviation distribution scatter value is compared with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified. If the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

2. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1 is characterized in that: The detection data is input into the neural network model to analyze and extract the process variables and result variables of the grinding process, including: Performing data preprocessing on the detection data to obtain preprocessed detection data, wherein the data preprocessing includes removing noise and abnormal values ​​in the detection data; Based on the pre-processed test data, the grinding process characteristics under different abrasive grain sizes are analyzed to obtain the key parameters related to the grinding effect in the pre-processed test data; According to the key parameters related to the grinding effect in the pre-processed inspection data, the process noise and post-noise features are extracted and combined to obtain the overall inspection data; The overall detection data is used as input data and input into a pre-trained neural network model to obtain process variables and result variables of the grinding process.

3. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1, characterized in that: According to the process variables and result variables, a data relationship scatter plot of the grinding process is constructed, including: Analyzing the relationship between the process variables and the result variables to obtain a correlation pattern related to the grinding process effect; Based on the association pattern, data pairing is performed on the process variables and the result variables to generate a plurality of data pairs, wherein the data pairs can reflect the grinding process characteristics under conditions of different abrasive grain sizes; A data relationship scatter plot of the grinding process is constructed using the data pairs as coordinate points.

4. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1, characterized in that: Performing trend analysis on the data points in the data relationship scatter plot, calculating the degree of dispersion under each trend, and obtaining the degree of dispersion value of the data relationship, including: According to the change trend of the data points in the data relationship scatter plot, the data points are divided into a gentle trend and a wavy trend, wherein the gentle trend indicates an area with a small change, and the wavy trend indicates an area with a large change; According to different trends, calculate the change amount of the overall trend and the corresponding number of changes, and quantify the fluctuations under different trends; Based on the change amount of the overall change trend and the corresponding change times, the discrete degree values ​​under different trends are calculated by the following formula: Among them, D r is the discrete degree value, T represents different trends, including gentle trends and undulating trends, ΔV T Indicates the change in the overall trend under the corresponding trend T, N T Indicates the number of changes in the corresponding trend T, f(ΔV T ) and g(N T ) represent two linear normalized functions under the corresponding trend T, which are calculated by the following formula: Among them, min(ΔV T ) is ΔV T The minimum value, max(ΔV T ) is ΔV T The maximum value of min(N T ) is N T The minimum value, max(N T ) is N T The maximum value of .

5. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1, characterized in that: Calculating a dispersion coefficient based on the dispersion value, and combining the dispersion coefficient with the distribution density of points in the data relationship scatter plot to obtain an adjustment coefficient corresponding to the dispersion degree of the data relationship, including: Based on the dispersion value, the dispersion coefficient is calculated by the following formula: D c =f(D r ) Among them, D c Denotes the dispersion coefficient, D r is the discrete degree value, f is the linear normalization function; Based on the discrete degree coefficient, set the sliding window parameters, and calculate the discrete degree in different sliding windows in sections, wherein the sliding window parameters include window width and sliding step length; Based on the discrete degree coefficient, the discrete situation value within each sliding window is calculated by the following formula: Among them, D s Indicates the discrete case value, max(D c ) and min(D c ) are the maximum and minimum values ​​of the discrete degree coefficient in the sliding window, respectively, and N is the number of discrete degree coefficients in the sliding window; Based on the discrete case value, the normalized discrete case value is calculated by the following formula: Among them, D sn Represents the normalized discrete case value, max(D s ) and min(D s ) are the maximum and minimum values ​​of the discrete case values ​​in all sliding windows respectively; Based on the dispersion degree coefficient and the normalized dispersion value, the dispersion degree adjustment coefficient is calculated by the following formula: Among them, D adj Represents the adjustment coefficient, N max The maximum number of scatter points in the data relationship scatter plot.

6. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1, characterized in that: According to the discrete degree value, discrete degree coefficient and adjustment coefficient, the overall deviation distribution scatter value of the grinding process is generated, including: Using the dispersion degree value and the dispersion degree coefficient as input parameters of the overall deviation distribution scatter point value to represent the overall dispersion degree and local characteristics of the data distribution; Based on the dispersion degree value, the dispersion degree coefficient and the adjustment coefficient, the overall deviation distribution scatter value is calculated by the following formula: D total =D r ×D c ×D adj Among them, D total Indicates the overall deviation from the distribution scatter value, D r is the discrete degree value, D c Denotes the dispersion coefficient, D adj is the adjustment coefficient.

7. The method for detecting the grinding process of a seamless steel pipe based on machine vision according to claim 1, characterized in that: The overall deviation distribution scatter point value is compared with a preset threshold value, and if the deviation distribution scatter point value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified, and if the deviation distribution scatter point value is higher than the preset threshold value, the grinding process is judged to be unqualified, including: Collect historical data from multiple grinding processes, and count the overall deviation distribution scatter points of each grinding process to form a distribution data set; Calculate the mean and standard deviation of the deviation distribution scatter point values ​​according to the distribution data set to obtain a preliminary threshold range; According to the preliminary threshold range, weighted adjustment is performed on the mean value to obtain a final preset threshold value of the deviation distribution scatter point value; The overall deviation distribution scatter value is compared with the preset threshold. If the deviation distribution scatter value is lower than or equal to the preset threshold, the grinding process is judged to be qualified. If the deviation distribution scatter value is higher than the preset threshold, the grinding process is judged to be unqualified.

8. A seamless steel pipe grinding process detection system based on machine vision, characterized in that: The method for detecting the grinding process of a seamless steel pipe based on machine vision according to any one of claims 1 to 7 comprises: A data acquisition module is used to acquire detection data during the steel pipe grinding process under different abrasive grain sizes, wherein the detection data includes noise data generated during the grinding process and data after the grinding is completed; A feature extraction module, used for inputting the detection data into a neural network model, analyzing and extracting process variables and result variables of the grinding process; A data relationship building module, used for building a data relationship scatter diagram of the grinding process according to the process variables and the result variables; A trend analysis module, used to perform trend analysis on the data points in the data relationship scatter plot, calculate the degree of dispersion under each trend, and obtain the degree of dispersion value of the data relationship; A discrete degree adjustment module, used to calculate a discrete degree coefficient based on the discrete degree value, and to obtain an adjustment coefficient corresponding to the discrete degree of the data relationship by combining the discrete degree coefficient with the distribution density of the points in the data relationship scatter plot; An overall deviation calculation module, used to generate an overall deviation distribution scatter point value of the grinding process according to the discrete degree value, discrete degree coefficient and adjustment coefficient; The process evaluation module is used to compare the overall deviation distribution scatter value with a preset threshold value. If the deviation distribution scatter value is lower than or equal to the preset threshold value, the grinding process is judged to be qualified; if the deviation distribution scatter value is higher than the preset threshold value, the grinding process is judged to be unqualified.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the machine vision-based seamless steel pipe grinding process detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the machine vision-based seamless steel pipe grinding process detection method as described in any one of claims 1 to 7.

Images