Intelligent monitoring system and method based on production line processing

Abstract

The invention discloses an intelligent monitoring system and method based on production line processing, and relates to the technical field of data processing management, and the system comprises a workpiece scanning module which uses a flatness detection device and a hardness detection device to scan the surface of a workpiece; the region division module is used for calculating the local density of each scanning point and dividing the surface of the workpiece into a plurality of independently controlled partitions through a clustering algorithm according to the local density value of each scanning point; the cutting parameter optimization module is used for establishing a tool life model by using a random forest algorithm, taking the flatness and hardness of the workpiece as input, and outputting an optimal cutting parameter combination corresponding to each flatness and hardness interval; and the subarea control module is used for calculating the flatness mean value and the hardness mean value of each subarea, determining an optimal cutting parameter combination according to the flatness mean value and the hardness mean value, and independently controlling each subarea, so that the machining precision is remarkably improved, and the service life of the cutter is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing management, and in particular to an intelligent monitoring system and method based on production line processing. Background Art

[0002] In modern manufacturing, the quality and production efficiency of workpieces are directly related to the competitiveness of enterprises. As the key link in workpiece production, the monitoring and optimization of the manufacturing and machining production lines are particularly important, especially for the processing and management of machining data. Traditional machining monitoring methods mainly rely on manual inspection and experience judgment. This method is not only inefficient, but also difficult to ensure the stability and consistency of workpiece quality.

[0003] During the workpiece machining process, due to differences in workpiece shape, size and material, as well as improper selection of cutting parameters, problems such as excessive tool wear, low machining efficiency and unstable workpiece quality often occur; traditional solutions mainly rely on the operator's experience and trial and error method, which is not only inefficient but also difficult to find the optimal combination of cutting parameters; in addition, for large or complex-shaped workpieces, there are often multiple areas of different flatness and hardness on their surfaces. Traditional machining methods often use uniform cutting parameters for machining, which can easily lead to overcutting or undercutting in certain areas, affecting the overall quality of the workpiece. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides an intelligent monitoring system and method based on production line processing. Through comprehensive flatness and hardness detection, local density clustering and partitioning, prediction of optimal cutting parameters and independent control of partitions, it achieves comprehensive control of workpiece processing quality, intelligent optimization of cutting parameters and precise control of the processing process, significantly improves processing accuracy and extends the service life of the tool.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent monitoring system based on production line processing, comprising: The workpiece scanning module uses a flatness detection device and a hardness detection device to scan the workpiece surface, obtain the flatness data and hardness data of each scanning point, and summarize and construct a scanning data set; The area division module calculates the local density of flatness and hardness of each scanning point in the surrounding neighborhood for each scanning point. The local density of the scanning point is calculated by the local density of flatness and hardness in the surrounding neighborhood. According to the local density value of each scanning point, the workpiece surface is divided into several independently controlled partitions by the K-means++ clustering algorithm. The cutting parameter optimization module obtains the historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, uses the random forest algorithm to establish a tool life model, takes the flatness and hardness of the workpiece as input, and outputs the optimal cutting parameter combination corresponding to each flatness and hardness range; The partition control module obtains the flatness data and hardness data in the scanning data set for each partition of the workpiece surface, calculates the average flatness and hardness of each partition, determines the best cutting parameter combination based on the average flatness and hardness, and independently controls each partition.

[0006] Furthermore, each scanning point is traversed, and the flatness of each scanning point is compared with a preset flatness threshold. If the flatness of the scanning point reaches the preset flatness threshold, the coordinates of the scanning point are recorded, and the workpiece surface is pre-processed according to the recorded coordinates of the scanning point until the flatness of each scanning point is lower than the preset flatness threshold. After the pre-processing, the flatness data of each scanning point is re-acquired.

[0007] Furthermore, for each scanning point, a square window with a side length of 2w+1 and the scanning point as the center is used as the surrounding neighborhood of the scanning point, where w is the window width. The local density of flatness and local density of hardness of each scanning point in the surrounding neighborhood are calculated by the flatness and hardness of each scanning point. The calculation formula is as follows: ; in, and They represent the local density of flatness and the local density of hardness, and Respectively represent the flatness of the i-th scanning point and the j-th scanning point, and Respectively represent the hardness of the i-th scanning point and the j-th scanning point, represents the set of scanning points in the surrounding neighborhood of scanning point i, and σ is the width parameter of the Gaussian kernel.

[0008] Furthermore, the local density of each scanning point is calculated by the local density of flatness and the local density of hardness in the surrounding neighborhood: , in, represents the local density, and denote the weights of flatness and hardness respectively, and ; Among them, the weight of flatness is: , the weight of hardness: ,in, , N is the number of all scanning points.

[0009] Furthermore, the workpiece surface is divided into several independently controlled partitions by using the K-means++ clustering algorithm, including: S1: Initialize cluster centers using K-means++ algorithm; S2: For each scan point, calculate the Euclidean distance from the scan point to each cluster center, and assign each scan point to the category to which the cluster center closest to the scan point belongs; S3: For each category, recalculate the cluster center of the category. The new cluster center is the average value of the local density values ​​of all scanning points in the category. S4: Repeat S2-S3 until the cluster center no longer changes (i.e. converges) or the preset number of iterations is reached; S5: According to the final clustering result, k cluster centers and the cluster category to which each scanning point belongs are obtained, and adjacent scanning points belonging to the same cluster are connected into continuous areas to form a number of independently controlled partitions.

[0010] Furthermore, the K-means++ algorithm is used to initialize the cluster centers, including: S11: Randomly select a scan point as the first cluster center; S12: For each scan point, calculate the Euclidean distance from the scan point to the nearest cluster center: ,in, represents the Euclidean distance from the i-th scan point to the k-th cluster center, represents the local density of the i-th scanning point, represents the local density of the kth cluster center; S13: for each scanning point, the square of the Euclidean distance from the scanning point to the nearest cluster center is calculated as the weight of the next cluster center selected, and the next cluster center is selected by the roulette wheel selection method according to the weight of each scanning point; S14: Repeat S12~S13 until k cluster centers are selected.

[0011] Furthermore, the optimal cutting parameter combination corresponding to each flatness and hardness range is output, including: The flatness and hardness of the workpiece are taken as characteristic variables, the tool life is taken as the target variable, and the cutting parameters are taken as the optimization variables. The tool life model is established using the random forest algorithm. The tool life model is trained using historical processing data, and the mapping relationship between flatness and hardness and tool life is established.

[0012] Furthermore, within the preset cutting parameter range, all possible cutting parameter combinations are traversed through grid search, the flatness and hardness of the workpiece are used as input, and the tool life under each cutting parameter combination is predicted using the trained tool life model. The mean square error (MSE) between the predicted tool life and the actual value under each cutting parameter combination is calculated. The error threshold is set in advance, and the cutting parameter combinations with mean square error (MSE) less than the error threshold are screened out. The screened cutting parameter combinations are sorted, and the cutting parameter combination with the longest tool life is selected as the optimal cutting parameter combination. The optimal cutting parameter combination corresponding to each flatness and hardness range is output.

[0013] Furthermore, for each partition of the workpiece surface, according to the mean flatness and mean hardness, the best cutting parameter combination corresponding to the interval is selected by finding the flatness and hardness intervals closest to the mean flatness and mean hardness of the partition in the tool life model output.

[0014] The intelligent monitoring method based on production line processing includes the following steps: Step 1: Use a flatness detection device and a hardness detection device to scan the surface of the workpiece, obtain the flatness data and hardness data of each scanning point, summarize and construct a scanning data set; Step 2: For each scanning point, calculate the local density of flatness and hardness in the surrounding neighborhood of the scanning point. Calculate the local density of the scanning point through the local density of flatness and hardness in the surrounding neighborhood of the scanning point. According to the local density value of each scanning point, divide the workpiece surface into several independently controlled partitions through the K-means++ clustering algorithm; Step 3: Obtain historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, and use the random forest algorithm to establish a tool life model. The flatness and hardness of the workpiece are used as inputs, and the optimal cutting parameter combination corresponding to each flatness and hardness range is output; Step 4: For each partition of the workpiece surface, obtain the flatness data and hardness data in the scan data set, calculate the average flatness and hardness of each partition, determine the optimal cutting parameter combination based on the average flatness and hardness, and independently control each partition.

[0015] (III) Beneficial effects The present invention provides an intelligent monitoring system and method based on production line processing, which has the following beneficial effects: (1) The flatness detection device and the hardness detection device are used to scan the workpiece surface point by point, and the flatness and hardness data of each scanning point can be accurately obtained. Through pre-processing, the high points and uneven parts of the workpiece surface can be removed, thereby reducing the tool wear during the cutting process. The flat surface helps to reduce the friction and vibration between the tool and the workpiece, further extending the service life of the tool.

[0016] (2) By calculating the local density of each scanning point and clustering it according to the local density, the workpiece surface can be divided into areas with similar characteristics, and each area can be processed differently, thereby improving the overall processing accuracy. The surface characteristics of the workpiece in different areas (such as flatness and hardness) may be different, so the required tools and processing parameters may also be different. Through partition control, the appropriate tools and processing parameters can be selected for each area, thereby extending the service life of the tool.

[0017] (3) By obtaining the historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations and establishing a tool life model, the best cutting parameter combination can be selected according to the specific characteristics of the workpiece surface, thereby optimizing the processing process and selecting the cutting parameter combination that minimizes tool wear, effectively extending the tool life.

[0018] (4) By calculating the mean flatness and hardness of each partition and determining the optimal cutting parameter combination based on these means, it can be ensured that each partition is processed using the cutting parameters that best suit its characteristics. The differences in the workpiece surface can be fully considered, thereby significantly improving the machining accuracy and reducing the errors caused by improper cutting parameters. By considering the impact of flatness and hardness on tool life, the optimal cutting parameter combination selected for each partition can maximize the tool life. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the structure of the intelligent monitoring system based on production line processing of the present invention; Figure 2 This is a schematic diagram of workpiece cutting for the production line of the present invention; Figure 3 It is a schematic diagram of the steps of the intelligent monitoring method based on production line processing of the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] See also Figure 1-Figure 2 The present invention provides an intelligent monitoring system based on production line processing, including: a workpiece scanning module, a region division module, a cutting parameter optimization module and a partition control module; wherein, The workpiece scanning module uses a flatness detection device and a hardness detection device to scan the workpiece surface, obtain the flatness data and hardness data of each scanning point, and summarize and construct a scanning data set; Place the workpiece on the inspection platform, use a fixture or other fixture to fix the workpiece at the inspection position to prevent movement or deformation during the inspection process, set the scanning mode and scanning parameters, such as scanning speed, scanning depth, and scanning interval, and use the scanning software or the device's built-in path planning function to generate the final scanning path based on the set scanning parameters and the selected scanning mode; It should be noted that according to the shape and size of the workpiece, select the appropriate scanning mode, including grid scanning, spiral scanning, linear scanning, etc. Grid scanning is suitable for workpieces with regular shapes and flat surfaces, spiral scanning is more suitable for cylindrical or conical workpieces, and linear scanning is often used for long strips or strips. Taking a rectangular workpiece as an example, when performing flatness inspection on it, the grid scanning mode is selected to divide the workpiece surface into multiple small grids, each grid as a scanning point, and the grid size and scanning speed are set according to the size of the workpiece and the expected inspection accuracy. The scanning path is generated by the scanning device, and the workpiece surface is scanned point by point according to the scanning path; When determining the scanning point spacing, it is necessary to make a reasonable choice based on the actual situation. A smaller scanning point spacing will improve the detection accuracy, but will also increase the detection time and cost, while a larger scanning point spacing will reduce the detection accuracy, but can reduce the detection time and cost; Start the flatness detection device (such as laser rangefinder, displacement sensor, etc.), move the detection probe along the workpiece surface, scan the workpiece surface point by point according to the scanning path, at each scanning point, the detection probe measures the distance from the workpiece surface to the probe, and records the flatness data of each scanning point; It should be noted that flatness is the difference between the surface of an object and the absolute level when it is processed or produced. It reflects the flatness of the surface of the object. Specifically, it is evaluated by measuring the distance between each point on the surface of the object and a reference plane. Traverse each scanning point, compare the flatness of each scanning point with the preset flatness threshold, and if the flatness of the scanning point reaches the preset flatness threshold, record the coordinates of the scanning point, and perform pre-processing on the workpiece surface according to the recorded coordinates of the scanning point, such as grinding, polishing, etc., to remove the protruding part, or perform other necessary pre-processing operations until the flatness of each scanning point is lower than the preset flatness threshold. After the pre-processing, re-acquire the flatness data of each scanning point; It should be noted that the setting of the flatness threshold includes: preliminarily setting the flatness threshold, trial processing a small batch of workpieces, monitoring the processing quality and tool life during the trial processing, and adjusting the flatness threshold if the processing quality does not meet the requirements or the tool life is too short to ensure improved processing quality and extended tool life. After multiple trial processing and adjustments, the final flatness threshold is determined; Start the hardness testing device (such as a hardness tester, indenter, etc.), move the testing probe along the surface of the workpiece, scan the surface of the workpiece point by point according to the scanning path, press the testing head into the surface of the workpiece to a predetermined depth or apply a predetermined testing force at each scanning point, and record the hardness data of each scanning point; Summarize the flatness data and hardness data and construct a scanning data set, which includes the coordinates, flatness value and hardness value of each scanning point; By scanning the workpiece surface point by point using a flatness detection device and a hardness detection device, the flatness and hardness data of each scanning point can be accurately obtained. Through pre-processing, the high points and uneven parts of the workpiece surface can be removed, thereby reducing tool wear during the cutting process. A flat surface helps reduce friction and vibration between the tool and the workpiece, further extending the service life of the tool.

[0022] The area division module calculates the local density of flatness and hardness of each scanning point in the surrounding neighborhood for each scanning point. The local density of the scanning point is calculated by the local density of flatness and hardness in the surrounding neighborhood. According to the local density value of each scanning point, the workpiece surface is divided into several independently controlled partitions by the K-means++ clustering algorithm. The flatness data and hardness data in the scanned data set are preprocessed, such as removing outliers and filling missing values, and the preprocessed flatness data and hardness data are normalized to map the flatness data and hardness data to the [0,1] interval: ,in, represents the normalized data, Represents the original data, Indicates the minimum value, Indicates the maximum value; For each scanning point, a square window with a side length of 2w+1 and the scanning point as the center is used as the surrounding neighborhood of the scanning point, where w is the window width. The flatness and hardness of each scanning point are obtained, and the local density of flatness and local density of hardness of each scanning point in the surrounding neighborhood are calculated. The calculation formula is as follows: ; in, and They represent the local density of flatness and the local density of hardness, and Respectively represent the flatness of the i-th scanning point and the j-th scanning point, and Respectively represent the hardness of the i-th scanning point and the j-th scanning point, represents the set of scanning points in the surrounding neighborhood of scanning point i, and σ is the width parameter of the Gaussian kernel.

[0023] It should be noted that the window size (i.e., the side length or radius of the square window) should be determined according to the size, shape, and expected detection accuracy of the workpiece. A larger window can capture a wider range of spatial features, but may reduce the resolution of local features. A smaller window can capture finer local features, but may be affected by noise. The local density of each scanning point is calculated by the local density of flatness and local density of hardness in the surrounding neighborhood: ,in, represents the local density, and denote the weights of flatness and hardness respectively, and ; Among them, the weight of flatness is: , the weight of hardness: ,in, , N is the number of all scanning points.

[0024] According to the local density value of each scanning point, the workpiece surface is divided into several independently controlled partitions through the K-means++ clustering algorithm, including: S1: Initialize the cluster center using the K-means++ algorithm, including: S11: Randomly select a scan point as the first cluster center; S12: For each scan point, calculate the Euclidean distance from the scan point to the nearest cluster center: , in, represents the Euclidean distance from the i-th scan point to the k-th cluster center, represents the local density of the i-th scanning point, represents the local density of the kth cluster center; S13: for each scanning point, the square of the Euclidean distance from the scanning point to the nearest cluster center is calculated as the weight of the next cluster center selected, and the next cluster center is selected by the roulette wheel selection method according to the weight of each scanning point; S14: Repeat S12-S13 until k cluster centers are selected; It should be noted that the k value (i.e., the number of cluster categories) in the K-means++ algorithm can be determined by the elbow rule. The elbow rule is to plot the sum of squared errors (SSE) curves corresponding to different k values. As the k value increases, the SSE usually decreases gradually, but after a certain k value, the decline of the SSE slows down significantly. This point is the so-called "elbow". The optimal k value is determined by observing the "elbow" position of the curve. S2: For each scan point, calculate the Euclidean distance from the scan point to each cluster center, and assign each scan point to the category to which the cluster center closest to the scan point belongs; S3: For each category, recalculate the cluster center of the category. The new cluster center is the average value of the local density values ​​of all scanning points in the category. S4: Repeat S2-S3 until the cluster center no longer changes (i.e. converges) or the preset number of iterations is reached; S5: According to the final clustering result, k cluster centers and the cluster category to which each scanning point belongs are obtained, and adjacent scanning points belonging to the same cluster are connected into continuous areas to form several independently controlled partitions; It should be noted that since the clustering algorithm is based on local density values ​​and does not directly consider the physical location of the scanning points, the partitions may not be continuous. Therefore, it is necessary to determine whether the scanning points of the same cluster are adjacent based on the physical location of the scanning points, so as to perform partitioning; By calculating the local density of each scanning point and clustering it according to the local density, the workpiece surface can be divided into areas with similar characteristics, and each area can be processed differently, thereby improving the overall processing accuracy. The surface characteristics of workpieces in different areas (such as flatness and hardness) may be different, so the required tools and processing parameters may also be different. Through partition control, suitable tools and processing parameters can be selected for each area, thereby extending the service life of the tool.

[0025] The cutting parameter optimization module obtains the historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, uses the random forest algorithm to establish a tool life model, takes the flatness and hardness of the workpiece as input, and outputs the optimal cutting parameter combination corresponding to each flatness and hardness range; Obtain historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations from the historical database. The data includes the flatness and hardness of the workpiece, cutting parameters (such as cutting speed, feed rate, cutting depth, etc.) and the corresponding tool life; The flatness and hardness of the workpiece are used as characteristic variables, the tool life is used as the target variable, and the cutting parameters are used as the optimization variables. The tool life model is established using the random forest algorithm. The tool life model is trained using historical processing data to establish the mapping relationship between flatness and hardness and tool life. Within the preset cutting parameter range, all possible cutting parameter combinations are traversed through grid search, the flatness and hardness of the workpiece are used as input, the tool life under each cutting parameter combination is predicted using the trained tool life model, and the mean square error (MSE) between the predicted tool life and the actual value under each cutting parameter combination is calculated; Preset the error threshold, filter out the cutting parameter combinations whose mean square error (MSE) is less than the error threshold, sort the filtered cutting parameter combinations, select the cutting parameter combination with the longest tool life as the optimal cutting parameter combination, and output the optimal cutting parameter combination corresponding to each flatness and hardness range; It should be noted that a suitable error threshold range is determined through experiments or experience, and further adjustments and optimizations are made within this range. For example, an error threshold is first set, and a certain number of cutting parameter combinations are screened for actual processing tests. According to the test results and feedback, the error threshold is gradually adjusted until the best combination that meets the processing requirements and prediction accuracy is found; By obtaining the historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations and establishing a tool life model, it is possible to select the best cutting parameter combination based on the specific characteristics of the workpiece surface, thereby optimizing the processing process, selecting the cutting parameter combination that causes the least tool wear, and effectively extending the tool life.

[0026] A partition control module obtains the flatness data and hardness data in the scanned data set for each partition of the workpiece surface, calculates the average flatness and hardness of each partition, determines the best cutting parameter combination based on the average flatness and hardness, and independently controls each partition; For each partition of the workpiece surface, obtain the flatness data and hardness data in the scanning data set, and calculate the average flatness value and the average hardness value of each partition; For each partition of the workpiece surface, according to the mean flatness and hardness values, the best cutting parameter combination corresponding to the interval is selected by finding the flatness and hardness interval closest to the mean flatness and hardness of the partition in the tool life model output; During the production line processing, according to the selected optimal cutting parameter combination, the cutting speed, feed rate, cutting depth and other parameters are adjusted to independently control each partition; By calculating the average flatness and hardness of each partition and determining the optimal cutting parameter combination based on these averages, it can be ensured that each partition is processed using the cutting parameters that best suit its characteristics, fully considering the differences in the workpiece surface, thereby significantly improving processing accuracy and reducing errors caused by improper cutting parameters. By considering the impact of flatness and hardness on tool life, the optimal cutting parameter combination selected for each partition can maximize the tool life.

[0027] See also Figure 3 The present invention also provides an intelligent monitoring method based on production line processing, comprising the following steps: Step 1: Use a flatness detection device and a hardness detection device to scan the surface of the workpiece, obtain the flatness data and hardness data of each scanning point, summarize and construct a scanning data set; Step 2: For each scanning point, calculate the local density of flatness and hardness in the surrounding neighborhood of the scanning point. Calculate the local density of the scanning point through the local density of flatness and hardness in the surrounding neighborhood of the scanning point. According to the local density value of each scanning point, divide the workpiece surface into several independently controlled partitions through the K-means++ clustering algorithm; Step 3: Obtain historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, and use the random forest algorithm to establish a tool life model. The flatness and hardness of the workpiece are used as inputs, and the optimal cutting parameter combination corresponding to each flatness and hardness range is output; Step 4: For each partition of the workpiece surface, obtain the flatness data and hardness data in the scan data set, calculate the average flatness and hardness of each partition, determine the optimal cutting parameter combination based on the average flatness and hardness, and independently control each partition; In the application, the several formulas involved are all calculated by removing dimensions and taking their numerical values. The formula is a formula of the most recent real situation obtained by collecting a large amount of data and performing software simulation. The coefficients in the formula are set by technicians in this field according to actual conditions.

[0028] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in combination with electronic hardware, computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0029] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. Intelligent monitoring system based on production line processing, characterized by: include: The workpiece scanning module uses a flatness detection device and a hardness detection device to scan the workpiece surface, obtain the flatness data and hardness data of each scanning point, and summarize and construct a scanning data set; The area division module calculates the local density of flatness and hardness of each scanning point in the surrounding neighborhood for each scanning point. The local density of the scanning point is calculated by the local density of flatness and hardness in the surrounding neighborhood. According to the local density value of each scanning point, the workpiece surface is divided into several independently controlled partitions by the K-means++ clustering algorithm. The cutting parameter optimization module obtains the historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, uses the random forest algorithm to establish a tool life model, takes the flatness and hardness of the workpiece as input, and outputs the optimal cutting parameter combination corresponding to each flatness and hardness range; The partition control module obtains the flatness data and hardness data in the scanning data set for each partition of the workpiece surface, calculates the average flatness and hardness of each partition, determines the best cutting parameter combination based on the average flatness and hardness, and independently controls each partition.

2. The intelligent monitoring system based on production line processing according to claim 1 is characterized in that: Traverse each scanning point and compare the flatness of each scanning point with the preset flatness threshold. If the flatness of the scanning point reaches the preset flatness threshold, record the coordinates of the scanning point. According to the recorded coordinates of the scanning point, pre-process the workpiece surface until the flatness of each scanning point is lower than the preset flatness threshold. After the pre-processing, re-acquire the flatness data of each scanning point.

3. The intelligent monitoring system based on production line processing according to claim 1 is characterized in that: For each scanning point, a square window with a side length of 2w+1 and the scanning point as the center is used as the surrounding neighborhood of the scanning point, where w is the window width. The local density of flatness and local density of hardness of each scanning point in the surrounding neighborhood are calculated by the flatness and hardness of each scanning point. The calculation formula is as follows: ； in, and They represent the local density of flatness and the local density of hardness, and Respectively represent the flatness of the i-th scanning point and the j-th scanning point, and Respectively represent the hardness of the i-th scanning point and the j-th scanning point, represents the set of scanning points in the surrounding neighborhood of scanning point i, and σ is the width parameter of the Gaussian kernel.

4. The intelligent monitoring system based on production line processing according to claim 3 is characterized in that: The local density of each scanning point is calculated by the local density of flatness and local density of hardness in the surrounding neighborhood: ,in, represents the local density, and denote the weights of flatness and hardness respectively, and ; Among them, the weight of flatness is: , the weight of hardness: ,in, , N is the number of all scanning points.

5. The intelligent monitoring system based on production line processing according to claim 1 is characterized in that: The workpiece surface is divided into several independently controlled partitions using the K-means++ clustering algorithm, including: S1: Initialize cluster centers using K-means++ algorithm; S2: For each scan point, calculate the Euclidean distance from the scan point to each cluster center, and assign each scan point to the category to which the cluster center closest to the scan point belongs; S3: For each category, recalculate the cluster center of the category. The new cluster center is the average value of the local density values ​​of all scanning points in the category. S4: Repeat S2 to S3 until the cluster center no longer changes or the preset number of iterations is reached; S5: According to the final clustering result, k cluster centers and the cluster category to which each scanning point belongs are obtained, and adjacent scanning points belonging to the same cluster are connected into continuous areas to form a number of independently controlled partitions.

6. The intelligent monitoring system based on production line processing according to claim 5 is characterized in that: Use K-means++ algorithm to initialize cluster centers, including: S11: Randomly select a scan point as the first cluster center; S12: For each scan point, calculate the Euclidean distance from the scan point to the nearest cluster center: ,in, represents the Euclidean distance from the i-th scan point to the k-th cluster center, represents the local density of the i-th scanning point, represents the local density of the kth cluster center; S13: for each scanning point, the square of the Euclidean distance from the scanning point to the nearest cluster center is calculated as the weight of the next cluster center selected, and the next cluster center is selected by the roulette wheel selection method according to the weight of each scanning point; S14: Repeat S12~S13 until k cluster centers are selected.

7. The intelligent monitoring system based on production line processing according to claim 1 is characterized in that: Output the optimal cutting parameter combination corresponding to each flatness and hardness range, including: The flatness and hardness of the workpiece are taken as characteristic variables, the tool life is taken as the target variable, and the cutting parameters are taken as the optimization variables. The tool life model is established using the random forest algorithm. The tool life model is trained using historical processing data, and the mapping relationship between flatness and hardness and tool life is established.

8. The intelligent monitoring system based on production line processing according to claim 7 is characterized in that: Within the preset cutting parameter range, all possible cutting parameter combinations are traversed through grid search, the flatness and hardness of the workpiece are used as input, the tool life under each cutting parameter combination is predicted using the trained tool life model, and the mean square error (MSE) between the predicted tool life and the actual value under each cutting parameter combination is calculated; The error threshold is set in advance, and the cutting parameter combinations with mean square error (MSE) less than the error threshold are screened out. The screened cutting parameter combinations are sorted, and the cutting parameter combination with the longest tool life is selected as the optimal cutting parameter combination. The optimal cutting parameter combination corresponding to each flatness and hardness range is output.

9. The intelligent monitoring system based on production line processing according to claim 1 is characterized in that: For each partition of the workpiece surface, according to the mean flatness and hardness values, the best cutting parameter combination corresponding to the interval is selected by finding the flatness and hardness interval closest to the mean flatness and hardness of the partition in the tool life model output.

10. An intelligent monitoring method based on production line processing, using any system described in claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use a flatness detection device and a hardness detection device to scan the surface of the workpiece, obtain the flatness data and hardness data of each scanning point, summarize and construct a scanning data set; Step 2: For each scanning point, calculate the local density of flatness and hardness in the surrounding neighborhood of the scanning point. Calculate the local density of the scanning point through the local density of flatness and hardness in the surrounding neighborhood of the scanning point. According to the local density value of each scanning point, divide the workpiece surface into several independently controlled partitions through the K-means++ clustering algorithm; Step 3: Obtain historical processing data of workpieces with different flatness and hardness under various cutting parameter combinations, and use the random forest algorithm to establish a tool life model. The flatness and hardness of the workpiece are used as inputs, and the optimal cutting parameter combination corresponding to each flatness and hardness range is output; Step 4: For each partition of the workpiece surface, obtain the flatness data and hardness data in the scan data set, calculate the average flatness and hardness of each partition, determine the optimal cutting parameter combination based on the average flatness and hardness, and independently control each partition.

Images