A cutting and forming processing analysis method for automobile control unit

Abstract

The invention discloses a method for analyzing cutting and forming processing of automobile control units, which relates to the field of cutting processing technology, including: obtaining design drawing data and raw material appearance data, determining the cutting processing path; determining the cutting tool and control parameters according to the material information and appearance data of the raw materials, and obtaining the cutting process parameters; cutting the raw materials, recording the tool vibration signal and cutting force changes, and extracting data features; identifying the local hardness deviation of the raw materials and its position information, and forming the local hardness deviation information; clustering the deviation information to determine the deviation distribution; adjusting the cutting path and process parameters according to the clustering results, and proposing a cutting and forming processing optimization plan. The method improves the processing accuracy and efficiency.

Description

Technical Field

[0001] The invention relates to the technical field of cutting processing, and in particular to a cutting forming processing analysis method for an automobile control unit. Background Art

[0002] The automotive control unit is a key mechanical component that controls the operation of the car. With the continuous development of the automotive industry, the dimensional accuracy requirements of the automotive control unit are getting higher and higher, and higher requirements are also placed on its processing technology. Cutting and forming processing is an important link in the manufacture of automotive control units. The stability and accuracy of its process directly affect the quality and performance of the product.

[0003] In the traditional cutting process, experience or simple geometric models are usually relied on to plan the processing path and select the cutting parameters. This method is prone to unstable processing quality, increased wear of cutting tools and low processing efficiency when dealing with complex and changeable materials. In addition, due to the uneven hardness distribution inside the raw materials, local hardness deviations may occur during the cutting process, thereby affecting the processing accuracy and tool life. Therefore, how to optimize the process through advanced processing analysis methods for these problems that arise during the cutting and forming process of automotive control units has become a key technical problem that needs to be solved urgently in the industry.

[0004] By real-time monitoring and analysis of vibration signals, cutting force and other data during the processing, it is possible to identify potential quality problems during the processing and dynamically adjust the processing path and cutting parameters to improve processing efficiency and quality. At the same time, using data analysis technologies such as cluster analysis and machine learning, it is possible to better identify and process local hardness deviations of raw materials, providing technical support for the realization of intelligent processing.

[0005] Therefore, a cutting and forming processing analysis method for automobile control units based on data analysis is proposed. The purpose is to optimize the cutting path and processing parameters through real-time monitoring and analysis of various data in the processing process, thereby improving the processing quality and efficiency, extending the tool life, reducing material waste, and further promoting the intelligent and automated development of automobile manufacturing. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a cutting and forming processing analysis method for an automobile control unit.

[0007] A first aspect of the present invention provides a method for analyzing cutting and forming processing of an automobile control unit, comprising:

[0008] Acquire design drawing data of the automobile control unit and appearance data of the raw materials of the automobile control unit to be processed, and determine a cutting process path of the automobile control unit according to the design drawing data and the appearance data;

[0009] Acquire material information of the raw material, determine the cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and material information, and obtain the cutting process parameters of the vehicle control unit;

[0010] Cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data;

[0011] Identifying local hardness deviation of the raw material based on the data feature, and determining location information where the local hardness deviation occurs, to obtain local hardness deviation information;

[0012] Performing clustering operation on the local hardness deviation information to obtain a clustering result;

[0013] The location distribution of local hardness deviations in the current batch of raw materials is determined according to the clustering results, and the cutting path and cutting process parameters of the automobile control unit are adjusted according to the location distribution to obtain an optimization plan for cutting and forming of the automobile control unit.

[0014] In this solution, the design drawing data of the automobile control unit and the appearance data of the raw materials of the automobile control unit to be processed are obtained, and the cutting processing path of the automobile control unit is determined according to the design drawing data and the appearance data, specifically:

[0015] Acquire design drawing data of the vehicle control unit, convert the design drawing data into an electronic image format, and obtain electronic design drawing data;

[0016] Converting the electronic design drawing data into a grayscale image, and calculating the gradient and gradient amplitude of each pixel in the grayscale image in the x direction and the y direction based on the Sobel operator;

[0017] Find the pixel with the largest gradient amplitude in the grayscale image, compare the pixel with the adjacent pixel values ​​in the gradient direction of the pixel along the gradient direction of the pixel, retain the pixels with local maximum values, and suppress the pixel values ​​that do not constitute the maximum value to 0, so as to obtain a non-maximum suppression image;

[0018] Setting a high threshold and a low threshold of the non-maximum suppression image, classifying pixels of the non-maximum suppression image according to the high threshold and the low threshold, marking pixels exceeding the high threshold as strong edges, marking pixels between the high and low thresholds as weak edges, and marking pixels below the low threshold as non-edge areas, connecting weak edges and strong edges, and obtaining contour data of the vehicle control unit;

[0019] Constructing a three-dimensional model of the appearance contour of the vehicle control unit according to the contour data;

[0020] Acquire the raw material appearance data of the automobile control unit to be processed, construct a raw material three-dimensional model according to the raw material appearance data, compare the appearance contour three-dimensional model of the automobile control unit with the raw material three-dimensional model, mark the cutting area of ​​the raw material, and obtain a three-dimensional model of the area to be cut;

[0021] The three-dimensional model of the area to be cut is analyzed based on the Voronoi path algorithm to determine the cutting path of the automobile control unit.

[0022] In this solution, the material information of the raw material is obtained, and the cutting tool and cutting control parameters of the automobile control unit are determined according to the raw material appearance data and material information to obtain the cutting process parameters of the automobile control unit, specifically:

[0023] Acquire material information of the raw material, acquire hardness information of the raw material through the Internet according to the material information, determine the material of the cutting tool according to the hardness information, and determine the type of the cutting tool according to the appearance data of the raw material;

[0024] Analyzing the wear resistance of the cutting tool according to the hardness information of the raw material and the material of the cutting tool, and obtaining data on the influence of the cutting speed on the wear resistance of the cutting tool;

[0025] Determine the cutting speed and cutting depth of the cutting tool according to the influencing data, determine the plasticity and toughness of the raw material according to the material information of the raw material, determine the feed rate of the cutting tool according to the plasticity and toughness, and obtain the cutting control parameters of the automobile control unit processing according to the cutting speed, cutting depth and feed rate;

[0026] The cutting tool material, cutting tool type and cutting control parameters are integrated to obtain the cutting process parameters of the automobile control unit.

[0027] In this solution, the preset amount of raw materials are cut according to the cutting process path and cutting process parameters, the tool vibration signal data and cutting force change data during the cutting process of the raw materials are recorded in real time, and the data features of the tool vibration signal data and cutting force change data are extracted, specifically:

[0028] Cutting a preset number of current batches of raw materials according to the cutting process path and cutting process parameters, and acquiring tool vibration signal data and cutting force change data during the cutting process of the raw materials in real time according to the vibration sensor and the force sensor;

[0029] The tool vibration signal data and cutting force change data are segmented according to a preset time window size, and the standard deviation of the data in each time window is calculated to obtain the vibration signal window standard deviation data and the cutting force window standard deviation data;

[0030] According to the vibration signal window standard deviation data and the cutting force window standard deviation data, the standard deviation distribution of each window data is counted;

[0031] By comparing the relative changes of the standard deviation data of each vibration signal window and the standard deviation data of the cutting force window, and evaluating the data fluctuation uniformity of the tool vibration signal data and the cutting force change data according to the standard deviation distribution of each window data, the data fluctuation uniformity evaluation result of the tool vibration signal data and the cutting force change data in each time window is obtained;

[0032] The data fluctuation uniformity evaluation results of the tool vibration signal data and the cutting force change data in each time window are time-labeled to obtain the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period.

[0033] In this solution, the local hardness deviation of the raw material is identified based on the data feature, and the location information where the local hardness deviation occurs is determined to obtain the local hardness deviation information, specifically:

[0034] The tool vibration signal data and cutting force variation data are used to construct a feature matrix based on the data fluctuation uniformity characteristics in each time period to obtain a vibration signal feature matrix and a cutting force feature matrix;

[0035] An isolation forest algorithm is introduced, and outlier analysis is performed on the vibration signal feature matrix and the cutting force feature matrix respectively according to the isolation forest algorithm, and the feature matrix entering the outlier analysis is calibrated as an outlier analysis state matrix;

[0036] A data cutting point is randomly selected in the value range of the outlier analysis state matrix, the outlier analysis state matrix is ​​divided into two parts according to the data cutting point, and the data cutting is repeated on the two parts of the outlier analysis state matrix after the cutting, until each outlier analysis state matrix after the cutting has only one data point, thereby obtaining an isolation forest of the outlier analysis state matrix;

[0037] Calculate the number of divisions of each data point in the outlier analysis state matrix from the root node to the leaf node according to the isolation forest, obtain the path length of each data point, and calculate the average path length of each data point in the isolation forest according to the path length;

[0038] An abnormality score is given to each data point according to the average path length, and a data point with an abnormality score greater than a preset value is marked as an abnormal data point. When the abnormal value analysis of the vibration signal feature matrix and the cutting force feature matrix is ​​completed, the abnormal data point is mapped to the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period to obtain the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data;

[0039] Align the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data in time series, and when the tool vibration signal data and the cutting force change data simultaneously show fluctuation uniformity abnormality, mark the time period as the cutting time point where the raw material shows local hardness deviation;

[0040] Determine the local hardness deviation position of the raw material according to the local hardness deviation cutting time point and the cutting process path;

[0041] The abnormal fluctuation degree of the tool vibration signal data and the cutting force change data is determined according to the fluctuation uniformity abnormal data of the tool vibration signal data and the cutting force change data, the local hardness change of the raw material is determined according to the abnormal fluctuation degree, and the local hardness deviation information of a preset number of raw materials is obtained according to the local hardness deviation position and the local hardness change.

[0042] In this solution, the local hardness deviation information is clustered to obtain a clustering result, which is specifically:

[0043] Integrate the local hardness deviation information of a preset number of raw materials, and convert the local hardness deviation information into a binary coding method to obtain a local hardness deviation data set;

[0044] Construct K clusters, randomly select K data points from the local hardness deviation dataset as the initial centroids, and use them as the cluster centers of the K clusters;

[0045] Calculate the Euclidean distance between each data point and each cluster center in the local hardness deviation dataset, and assign each data point to the cluster with the closest Euclidean distance;

[0046] For each cluster, the mean of all data points in the cluster is calculated, and the mean is used as the new cluster center. The Euclidean distance of each data point to the new cluster center is calculated repeatedly and iteratively, and clusters are assigned and cluster centers are updated until the change in the cluster center is less than the preset value. The clustering operation is stopped, and the clustering results of the local hardness deviation information of a preset number of raw materials are obtained.

[0047] In this solution, the location distribution of the local hardness deviation of the current batch of raw materials is determined according to the clustering results, and the cutting processing path and cutting process parameters of the automobile control unit are adjusted according to the location distribution to obtain the cutting and forming optimization solution of the automobile control unit, which is specifically:

[0048] Determine the position distribution of local hardness deviations in the current batch of raw materials according to the clustering results, and determine the position distribution of local hardening and local softening of the raw materials according to the position distribution, and mark them as local hardness increase distribution areas and local hardness decrease distribution areas;

[0049] If the local hardness decreases in the current batch of raw materials, the probability of the local hardness decrease in the current batch of raw materials is determined according to the local hardness deviation information, and the local hardness decrease distribution area of ​​the vehicle control unit is predicted according to the local hardness decrease distribution area and the spatial interpolation method;

[0050] Obtain the stress distribution of the automobile control unit in the working state, determine the impact of the local hardness reduction distribution area of ​​the automobile control unit on the quality of the automobile control unit according to the stress distribution, if the quality impact is greater than the preset quality impact value and the occurrence probability is less than the preset occurrence probability value, determine the quality sampling frequency of the automobile control unit after production according to the occurrence probability, if the occurrence probability of the local hardness reduction of the current batch of raw materials is greater than or equal to the preset value, cancel the processing of the batch of raw materials;

[0051] If the local hardness increase occurs in the current batch of raw materials, the hardness increase of the local hardness increase distribution area in the current batch of raw materials is determined according to the local hardness deviation information. If the hardness increase is greater than the preset increase, a Voronoi diagram is constructed, and the area where the local hardness increase is greater than the preset increase is regarded as an obstacle. The path is reconstructed based on the Voronoi path planning algorithm to determine whether the cutting path can avoid the obstacle.

[0052] If possible, the cutting path of the automobile control unit is replanned according to the Voronoi diagram to obtain the optimized cutting path. If not, the cutting control parameters of the local hardness increase distribution area are adjusted according to the hardness increase adjustment of the local hardness increase distribution area to obtain the optimized cutting and forming processing plan for the automobile control unit.

[0053] The second aspect of the present invention further provides a cutting and forming processing analysis system for an automobile control unit, the system comprising: a memory and a processor, the memory comprising an automobile control unit cutting and forming processing analysis method program, and when the automobile control unit cutting and forming processing analysis method program is executed by the processor, the following steps are implemented:

[0054] Acquire design drawing data of the automobile control unit and appearance data of the raw materials of the automobile control unit to be processed, and determine a cutting process path of the automobile control unit according to the design drawing data and the appearance data;

[0055] Acquire material information of the raw material, determine the cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and material information, and obtain the cutting process parameters of the vehicle control unit;

[0056] Cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data;

[0057] Identifying local hardness deviation of the raw material based on the data feature, and determining location information where the local hardness deviation occurs, to obtain local hardness deviation information;

[0058] Performing clustering operation on the local hardness deviation information to obtain a clustering result;

[0059] The location distribution of local hardness deviations in the current batch of raw materials is determined according to the clustering results, and the cutting path and cutting process parameters of the automobile control unit are adjusted according to the location distribution to obtain an optimization plan for cutting and forming of the automobile control unit.

[0060] The present invention discloses a method for analyzing the cutting and forming of an automobile control unit, including: obtaining design drawing data and raw material appearance data, determining the cutting path; determining the cutting tool and control parameters according to the material information and appearance data of the raw material, and obtaining the cutting process parameters; cutting the raw material, recording the tool vibration signal and cutting force change, and extracting data features; identifying the local hardness deviation of the raw material and its position information, and forming the local hardness deviation information; clustering the deviation information to determine the deviation distribution; adjusting the cutting path and process parameters according to the clustering results, and proposing a cutting and forming optimization plan. The method improves the processing accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A flow chart showing a method for analyzing cutting and forming processing of an automobile control unit according to the present invention is shown;

[0062] Figure 2 A flow chart showing the cutting process parameters for obtaining an automobile control unit according to the present invention is shown;

[0063] Figure 3 A flow chart showing the data features of the tool vibration signal data and cutting force variation data extracted according to the present invention;

[0064] Figure 4 A block diagram of a cutting and forming processing analysis system for an automobile control unit of the present invention is shown. DETAILED DESCRIPTION

[0065] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0067] Figure 1 A flow chart of a cutting and forming processing analysis method for an automobile control unit of the present invention is shown.

[0068] like Figure 1 As shown, the first aspect of the present invention provides a method for analyzing cutting and forming processing of an automobile control unit, comprising:

[0069] S102, obtaining design drawing data of the automobile control unit and appearance data of the raw material of the automobile control unit to be processed, and determining a cutting process path of the automobile control unit according to the design drawing data and the appearance data;

[0070] S104, obtaining material information of the raw material, determining a cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and the material information, and obtaining cutting process parameters of the vehicle control unit;

[0071] S106, cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data;

[0072] S108, identifying the local hardness deviation of the raw material based on the data feature, and determining the location information where the local hardness deviation occurs, to obtain the local hardness deviation information;

[0073] S110, performing a clustering operation on the local hardness deviation information to obtain a clustering result;

[0074] S112, determining the position distribution of local hardness deviations in the current batch of raw materials according to the clustering results, adjusting the cutting path and cutting process parameters of the automobile control unit according to the position distribution, and obtaining an optimization plan for cutting and forming of the automobile control unit.

[0075] It should be noted that by obtaining the design drawing data of the automobile control unit and the appearance data of the raw materials, combined with the optimization calculation of the cutting process path, the area to be processed can be accurately determined, ensuring that the cutting path is more in line with the design requirements, reducing processing errors, and improving the processing accuracy and appearance quality of the product; according to the material information of the raw materials, combined with its hardness, plasticity and toughness and other parameters, the cutting tool and its control parameters, such as cutting speed, cutting depth and feed rate, can be reasonably selected. This can not only ensure the stability and efficiency of the cutting process, but also reduce tool wear, extend tool life, and reduce production costs; during the smelting, casting or processing of raw materials, they are affected by factors such as cooling rate, component distribution, and heat treatment process, and are prone to uneven hardness in different areas. These unevenness will lead to inconsistent cutting resistance in subsequent cutting processing, which will in turn cause differences in processing surface quality and dimensional accuracy problems. Therefore, by real-time recording of tool vibration signals and cutting force changes during processing, identifying local hardness deviations of raw materials, it is possible to provide early warnings and adjustments to areas that may affect processing quality. By analyzing the location distribution of local hardness deviations based on the clustering results, the cutting path and cutting process parameters can be adjusted in a targeted manner to reduce quality problems caused by local hardness changes in the material and improve the stability of the machining process.

[0076] According to an embodiment of the present invention, the acquisition of design drawing data of the automobile control unit and appearance data of the raw material of the automobile control unit to be processed, and the determination of the cutting processing path of the automobile control unit according to the design drawing data and the appearance data, is specifically as follows:

[0077] Acquire design drawing data of the vehicle control unit, convert the design drawing data into an electronic image format, and obtain electronic design drawing data;

[0078] Converting the electronic design drawing data into a grayscale image, and calculating the gradient and gradient amplitude of each pixel in the grayscale image in the x direction and the y direction based on the Sobel operator;

[0079] Find the pixel with the largest gradient amplitude in the grayscale image, compare the pixel with the adjacent pixel values ​​in the gradient direction of the pixel along the gradient direction of the pixel, retain the pixels with local maximum values, and suppress the pixel values ​​that do not constitute the maximum value to 0, so as to obtain a non-maximum suppression image;

[0080] Setting a high threshold and a low threshold of the non-maximum suppression image, classifying pixels of the non-maximum suppression image according to the high threshold and the low threshold, marking pixels exceeding the high threshold as strong edges, marking pixels between the high and low thresholds as weak edges, and marking pixels below the low threshold as non-edge areas, connecting weak edges and strong edges, and obtaining contour data of the vehicle control unit;

[0081] Constructing a three-dimensional model of the appearance contour of the vehicle control unit according to the contour data;

[0082] Acquire the raw material appearance data of the automobile control unit to be processed, construct a raw material three-dimensional model according to the raw material appearance data, compare the appearance contour three-dimensional model of the automobile control unit with the raw material three-dimensional model, mark the cutting area of ​​the raw material, and obtain a three-dimensional model of the area to be cut;

[0083] The three-dimensional model of the area to be cut is analyzed based on the Voronoi path algorithm to determine the cutting path of the automobile control unit.

[0084] It should be noted that by acquiring the design drawing data and converting it into an electronic image format, combined with the Sobel operator to calculate the gradient and contour extraction technology, the appearance contour data of the automotive control unit can be accurately identified. This ensures the accuracy of the cutting process path, makes the processing path highly consistent with the design intent, and avoids the path deviation problem that may occur in traditional processing methods; based on the Voronoi path algorithm, the cutting area is analyzed to achieve optimal planning of the cutting path. The Voronoi algorithm can plan a more reasonable and optimized cutting path based on the shape and characteristics of the material, thereby reducing unnecessary tool movement, improving processing efficiency and reducing processing time; the Voronoi path algorithm is a path planning method based on the Voronoi diagram; the maximum value is a preset value, and pixels greater than the preset value are calibrated as maximum values.

[0085] Figure 2 The flowchart of the present invention for obtaining cutting process parameters of an automobile control unit is shown.

[0086] According to an embodiment of the present invention, the material information of the raw material is obtained, and the cutting tool and cutting control parameters of the automobile control unit are determined according to the raw material appearance data and the material information, so as to obtain the cutting process parameters of the automobile control unit, specifically:

[0087] S202, obtaining material information of the raw material, obtaining hardness information of the raw material through the Internet according to the material information, determining the material of the cutting tool according to the hardness information, and determining the type of the cutting tool according to the appearance data of the raw material;

[0088] S204, analyzing the wear resistance of the cutting tool according to the hardness information of the raw material and the material of the cutting tool, and obtaining data on the influence of the cutting speed on the wear resistance of the cutting tool;

[0089] S206, determining a cutting speed and a cutting depth of a cutting tool according to the influencing data, determining the plasticity and toughness of the raw material according to the material information of the raw material, determining a feed rate of the cutting tool according to the plasticity and toughness, and obtaining a cutting control parameter for machining the automobile control unit according to the cutting speed, cutting depth and feed rate;

[0090] S208, integrating the cutting tool material, cutting tool type, and cutting control parameters to obtain cutting process parameters of the automobile control unit.

[0091] It should be noted that by accurately determining the type, material, cutting speed, cutting depth and feed rate of the cutting tool according to the hardness information, plasticity and toughness of the raw materials, it is possible to ensure the matching of the tool and the raw material during the processing, thereby improving the processing accuracy, reducing the processing error and ensuring the quality of the finished product. For high-plasticity materials, since these materials can withstand large deformations, the contact area between the tool and the workpiece during the cutting process is large, allowing a higher feed rate. For example, in aluminum alloy processing, the feed rate can usually be increased to improve production efficiency; for low-plasticity materials, because these materials may experience brittle fracture or increased tool wear during the cutting process, it is recommended to reduce the feed rate to ensure processing stability.

[0092] Figure 3 A flow chart of extracting data features of tool vibration signal data and cutting force variation data according to the present invention is shown.

[0093] According to an embodiment of the present invention, the cutting process is performed on a preset amount of raw materials according to the cutting process path and the cutting process parameters, and the tool vibration signal data and cutting force change data during the cutting process of the raw materials are recorded in real time, and the data features of the tool vibration signal data and the cutting force change data are extracted, specifically:

[0094] S302, cutting a preset number of the current batch of raw materials according to the cutting process path and cutting process parameters, and acquiring tool vibration signal data and cutting force change data in real time during the cutting process of the raw materials according to the vibration sensor and the force sensor;

[0095] S304, segmenting the tool vibration signal data and cutting force change data according to a preset time window size, calculating the standard deviation of the data in each time window, and obtaining vibration signal window standard deviation data and cutting force window standard deviation data;

[0096] S306, counting the standard deviation distribution of each window data according to the vibration signal window standard deviation data and the cutting force window standard deviation data;

[0097] S308, by comparing the relative changes of the standard deviation data of each vibration signal window and the standard deviation data of the cutting force window, and evaluating the data fluctuation uniformity of the tool vibration signal data and the cutting force change data according to the standard deviation distribution of each window data, the data fluctuation uniformity evaluation result of the tool vibration signal data and the cutting force change data in each time window is obtained;

[0098] S310, time-marking the data fluctuation uniformity evaluation results of the tool vibration signal data and the cutting force change data in each time window to obtain the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period.

[0099] It should be noted that during the cutting process of the automotive control unit, the local hardness deviation of the raw material will cause changes in the originally regular vibration signal and cutting force of the cutting tool; therefore, a preset number of current batches of raw materials are cut according to the cutting path and cutting process parameters, and the tool vibration signal data and cutting force change data during the processing are obtained in real time, and the data fluctuation uniformity characteristics of the tool vibration signal data and cutting force change data in each time period of a preset time length are extracted, providing a data basis for the subsequent indirect identification of the local hardness deviation of the raw material based on the characteristics of the tool vibration signal data and the cutting force change data.

[0100] According to an embodiment of the present invention, the local hardness deviation of the raw material is identified based on the data feature, and the location information where the local hardness deviation occurs is determined to obtain the local hardness deviation information, specifically:

[0101] The tool vibration signal data and cutting force variation data are used to construct a feature matrix based on the data fluctuation uniformity characteristics in each time period to obtain a vibration signal feature matrix and a cutting force feature matrix;

[0102] An isolation forest algorithm is introduced, and outlier analysis is performed on the vibration signal feature matrix and the cutting force feature matrix respectively according to the isolation forest algorithm, and the feature matrix entering the outlier analysis is calibrated as an outlier analysis state matrix;

[0103] A data cutting point is randomly selected in the value range of the outlier analysis state matrix, the outlier analysis state matrix is ​​divided into two parts according to the data cutting point, and the data cutting is repeated on the two parts of the outlier analysis state matrix after the cutting, until each outlier analysis state matrix after the cutting has only one data point, thereby obtaining an isolation forest of the outlier analysis state matrix;

[0104] Calculate the number of divisions of each data point in the outlier analysis state matrix from the root node to the leaf node according to the isolation forest, obtain the path length of each data point, and calculate the average path length of each data point in the isolation forest according to the path length;

[0105] An abnormality score is given to each data point according to the average path length, and a data point with an abnormality score greater than a preset value is marked as an abnormal data point. When the abnormal value analysis of the vibration signal feature matrix and the cutting force feature matrix is ​​completed, the abnormal data point is mapped to the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period to obtain the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data;

[0106] Align the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data in time series, and when the tool vibration signal data and the cutting force change data simultaneously show fluctuation uniformity abnormality, mark the time period as the cutting time point where the raw material shows local hardness deviation;

[0107] Determine the local hardness deviation position of the raw material according to the local hardness deviation cutting time point and the cutting process path;

[0108] The abnormal fluctuation degree of the tool vibration signal data and the cutting force change data is determined according to the fluctuation uniformity abnormal data of the tool vibration signal data and the cutting force change data, the local hardness change of the raw material is determined according to the abnormal fluctuation degree, and the local hardness deviation information of a preset number of raw materials is obtained according to the local hardness deviation position and the local hardness change.

[0109] It should be noted that by introducing the isolation forest algorithm, the isolation forest algorithm constructs multiple decision trees (i.e., "isolation trees") by randomly selecting cutting values. Fluctuation uniformity outliers are more easily isolated than normal data. Because fluctuation uniformity outliers usually have different characteristics, making them easier to be isolated during random cutting, fluctuation uniformity abnormal data usually have a shorter path length in the isolation tree. The isolation forest evaluates the degree of abnormality by calculating the average path length of each data point in the isolation tree. Data points with shorter path lengths are considered to be fluctuation uniformity abnormal data; the feature matrix of the vibration signal and cutting force contains the changes in the tool vibration signal and cutting force in each time period. Through the isolation forest algorithm, abnormal fluctuations in these data, that is, fluctuation uniformity abnormal data, can be detected; when the tool vibration signal data and cutting force change data simultaneously show fluctuation uniformity abnormalities, it is considered that the raw material has local hardness deviations, and the local hardness deviation position and abnormal fluctuation degree of the raw material are determined according to the local hardness deviation cutting time point and the cutting processing path to determine the local hardness change, the local hardness change is whether the hardness increases or decreases, and the degree of increase or decrease; by combining the tool vibration signal data and the cutting force change data, the local hardness deviation that may exist in the cutting process can be captured more accurately, and a single data type may be affected by noise or other interference, resulting in unstable recognition results. The combination of dual data can reduce this impact, because different types of data can complement each other and enhance the robustness of the system to various interference factors; the local hardness deviation information includes the local hardness deviation position and the local hardness change, and the local hardness change is whether the local hardness becomes hard or soft, and the degree of change.

[0110] According to an embodiment of the present invention, the local hardness deviation information is clustered to obtain a clustering result, specifically:

[0111] Integrate the local hardness deviation information of a preset number of raw materials, and convert the local hardness deviation information into a binary coding method to obtain a local hardness deviation data set;

[0112] Construct K clusters, randomly select K data points from the local hardness deviation dataset as the initial centroids, and use them as the cluster centers of the K clusters;

[0113] Calculate the Euclidean distance between each data point and each cluster center in the local hardness deviation dataset, and assign each data point to the cluster with the closest Euclidean distance;

[0114] For each cluster, the mean of all data points in the cluster is calculated, and the mean is used as the new cluster center. The Euclidean distance of each data point to the new cluster center is calculated repeatedly and iteratively, and clusters are assigned and cluster centers are updated until the change in the cluster center is less than the preset value. The clustering operation is stopped, and the clustering results of the local hardness deviation information of a preset number of raw materials are obtained.

[0115] It should be noted that the local hardness deviation information is clustered by the K-means clustering algorithm, and the clustering result is to cluster the local hardness deviation information of the local hardness sheet deviation of the raw material with similar hardness changes and similar local hardness deviation positions into one category, for example, the local hardness softening is within a preset range and the local hardness deviation information with similar positions is clustered into one category. The K-means clustering algorithm can quickly classify similar local hardness deviation information into one category, better identify the situation of local hardness deviation in the current batch of raw materials, and where local hardness deviation frequently occurs.

[0116] According to an embodiment of the present invention, the position distribution of the local hardness deviation of the current batch of raw materials is determined according to the clustering results, and the cutting processing path and cutting process parameters of the automobile control unit are adjusted according to the position distribution to obtain the cutting and forming processing optimization plan of the automobile control unit, which is specifically:

[0117] Determine the position distribution of local hardness deviations in the current batch of raw materials according to the clustering results, and determine the position distribution of local hardening and local softening of the raw materials according to the position distribution, and mark them as local hardness increase distribution areas and local hardness decrease distribution areas;

[0118] It should be noted that the location distribution of local hardness deviations in the current batch of raw materials is determined based on the clustering results. The local hardness decrease distribution area is the area where local hardness decreases frequently occur in the current batch of raw materials, and the local hardness increase distribution area is the area where local hardness increases frequently occur.

[0119] If the local hardness decreases in the current batch of raw materials, the probability of the local hardness decrease in the current batch of raw materials is determined according to the local hardness deviation information, and the local hardness decrease distribution area of ​​the vehicle control unit is predicted according to the local hardness decrease distribution area and the spatial interpolation method;

[0120] Obtain the stress distribution of the automobile control unit in the working state, determine the impact of the local hardness reduction distribution area of ​​the automobile control unit on the quality of the automobile control unit according to the stress distribution, if the quality impact is greater than the preset quality impact value and the occurrence probability is less than the preset occurrence probability value, determine the quality sampling frequency of the automobile control unit after production according to the occurrence probability, if the occurrence probability of the local hardness reduction of the current batch of raw materials is greater than or equal to the preset value, cancel the processing of the batch of raw materials;

[0121] It should be noted that if the local hardness of the current batch of raw materials decreases, since the obtained tool vibration signal and cutting force change data are the data of the part that the tool needs to cut on the raw materials, the local hardness decrease area of ​​the automotive control unit is predicted through spatial interpolation (such as Kriging interpolation, inverse distance weighted interpolation, etc.). This method uses the hardness information of known data points to estimate the hardness distribution of the unmeasured area, thereby predicting the local hardness decrease distribution of the automotive control unit produced by this batch of raw materials; if there is a deviation in the local hardness decrease of the raw materials, this may cause quality problems in the processed parts, affecting the efficiency of the entire production line and the qualified rate of the product. By determining the probability of hardness decrease and the impact assessment, if the impact is greater than the preset value and the probability of occurrence is less than the preset value, the quality sampling frequency is adjusted; if the probability of occurrence is high, the processing of this batch of raw materials is directly cancelled to avoid quality problems.

[0122] If the local hardness increase occurs in the current batch of raw materials, the hardness increase of the local hardness increase distribution area in the current batch of raw materials is determined according to the local hardness deviation information. If the hardness increase is greater than the preset increase, a Voronoi diagram is constructed, and the area where the local hardness increase is greater than the preset increase is regarded as an obstacle. The path is reconstructed based on the Voronoi path planning algorithm to determine whether the cutting path can avoid the obstacle.

[0123] If possible, the cutting path of the automobile control unit is replanned according to the Voronoi diagram to obtain the optimized cutting path. If not, the cutting control parameters of the local hardness increase distribution area are adjusted according to the hardness increase adjustment of the local hardness increase distribution area to obtain the optimized cutting and forming processing plan for the automobile control unit.

[0124] It should be noted that when the local hardness of the raw material increases, problems may occur during the cutting process, such as increased tool wear, abnormal cutting force, and reduced surface quality. By marking the area where the hardness increase is greater than the preset increase as an obstacle, it is considered that the local hardness increase is large when the hardness increase is greater than the preset increase. Processing according to the current cutting process parameters will cause excessive wear of the tool; the Voronoi diagram is constructed according to the Voronoi path planning algorithm. The Voronoi diagram is a mathematical tool used to divide the space into several regions, each of which corresponds to a specific "seed point". It can help identify and plan obstacles in the cutting path (such as areas with increased hardness), and determine whether the areas with local increased hardness can be bypassed for processing; if the tool can bypass the hardness deviation area where the local hardness increase is greater than the preset value when cutting the raw material, the cutting path is optimized to obtain the optimized cutting path; if it cannot be avoided, it means that the areas with local increased hardness may cover the key parts of the cutting path, resulting in the inability to completely avoid these areas even if the optimized path is used. At this time, by adjusting the cutting control parameters (such as reducing the cutting speed, reducing the feed rate, reducing the cutting depth, etc.), it can adapt to the characteristics of the areas with local increased hardness, reduce tool wear and abnormal cutting force, thereby improving the processing quality and ensuring the surface finish and dimensional accuracy of the processed surface.

[0125] According to an embodiment of the present invention, it also includes:

[0126] Obtaining appearance texture image data of automobile control units produced by cutting tools at different degrees of wear;

[0127] Extracting texture features of the appearance texture image data based on an image processing algorithm, wherein the texture features include texture length, width, depth, and direction;

[0128] Marking the wear degree of the texture features, building a wear degree recognition model based on a convolutional neural network, and importing the texture features marked with the wear degree into the wear degree recognition model for sample training;

[0129] Perform actual production operations on the automobile control unit according to the automobile control unit cutting and forming processing optimization plan, obtain appearance picture data of the automobile control unit in real time, and extract real-time texture features of the appearance picture data;

[0130] The real-time texture features are imported into the wear degree recognition model for analysis to determine the wear degree of the tool under the current production state. If the wear degree is greater than a preset value, the tool is replaced.

[0131] It should be noted that by obtaining the appearance texture image data of the automotive control unit produced after tool processing under different degrees of wear, and extracting texture features (such as length, width, depth, direction, etc.) based on image processing algorithms, the degree of tool wear can be accurately identified and annotated. By importing these annotated texture feature data into the convolutional neural network for training, an accurate wear degree recognition model can be constructed to realize the automatic recognition of tool wear degree; by accurately identifying and monitoring the wear state of the tool, the tool can be replaced at the appropriate time to avoid premature replacement or use of over-worn tools, thereby extending the service life of the tool. At the same time, optimizing the timing of tool replacement can also reduce processing errors and downtime caused by tool wear, thereby reducing production costs.

[0132] According to an embodiment of the present invention, it also includes:

[0133] Obtaining a production sample of the automobile control unit after production according to the automobile control unit cutting and forming processing optimization plan, performing a production dimensional accuracy test on the production sample, and obtaining a dimensional accuracy test result;

[0134] A dimension accuracy threshold is preset, and an analysis is performed based on the dimension accuracy detection result and the preset dimension accuracy threshold. If the dimension accuracy detection result is less than the dimension accuracy threshold, a movable range of the cutting tool is obtained;

[0135] Dividing the movable range into N small cubes according to preset sizes, and marking the vertices of each small cube as cutting tool calibration points;

[0136] Acquire the position information of each cutting tool calibration point, perform a moving operation on the cutting tool according to the position information of each cutting tool calibration point, and acquire the actual position information of the cutting tool after the cutting tool moves according to the position information of the calibration point;

[0137] Comparing the actual position information with the position information of the cutting tool calibration point, determining the position deviation between the actual position of the cutting tool and each cutting tool calibration point, and determining the position calibration coefficient of the cutting tool at each cutting tool calibration point according to the position deviation;

[0138] The cutting tool position is calibrated according to the position calibration coefficient.

[0139] It should be noted that the position calibration of the tool is crucial to ensure machining accuracy. Minor position deviations of the tool may accumulate, resulting in dimensional errors in the machining results. Therefore, the position of the cutting tool during the machining process must be precisely controlled and calibrated to ensure that the tool can cut along the expected path and meet the high-precision machining requirements; by performing dimensional accuracy detection on the automotive control unit after production, and comparing the detection results with the preset dimensional accuracy threshold, the situation of dimensional accuracy not meeting the standard can be discovered in time. Then, by calibrating the position of the tool, the dimensional error can be reduced, ensuring that the produced automotive control unit can meet the design requirements and improve the machining accuracy; by dividing the movable range of the cutting tool into multiple small cubes, generating calibration points and obtaining the position information of the calibration points, the tool position can be automatically adjusted. This can reduce manual intervention and improve production efficiency; by obtaining the actual position information of the tool and comparing it with the position information of the calibration point, the position deviation can be accurately calculated and the calibration coefficient can be determined, and real-time adjustments can be made to form a closed-loop control.

[0140] Figure 4 A block diagram of a cutting and forming processing analysis system for an automobile control unit of the present invention is shown.

[0141] The second aspect of the present invention further provides a vehicle control unit cutting and forming processing analysis system 4, the system comprising: a memory 41, a processor 42, the memory comprising a vehicle control unit cutting and forming processing analysis method program, the vehicle control unit cutting and forming processing analysis method program when executed by the processor, implements the following steps:

[0142] Acquire design drawing data of the automobile control unit and appearance data of the raw materials of the automobile control unit to be processed, and determine a cutting process path of the automobile control unit according to the design drawing data and the appearance data;

[0143] Acquire material information of the raw material, determine the cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and material information, and obtain the cutting process parameters of the vehicle control unit;

[0144] Cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data;

[0145] Identifying local hardness deviation of the raw material based on the data feature, and determining location information where the local hardness deviation occurs, to obtain local hardness deviation information;

[0146] Performing clustering operation on the local hardness deviation information to obtain a clustering result;

[0147] The location distribution of local hardness deviations in the current batch of raw materials is determined according to the clustering results, and the cutting path and cutting process parameters of the automobile control unit are adjusted according to the location distribution to obtain an optimization plan for cutting and forming of the automobile control unit.

[0148] The present invention discloses a method for analyzing the cutting and forming of an automobile control unit, including: obtaining design drawing data and raw material appearance data, determining the cutting path; determining the cutting tool and control parameters according to the material information and appearance data of the raw material, and obtaining the cutting process parameters; cutting the raw material, recording the tool vibration signal and cutting force change, and extracting data features; identifying the local hardness deviation of the raw material and its position information, and forming the local hardness deviation information; clustering the deviation information to determine the deviation distribution; adjusting the cutting path and process parameters according to the clustering results, and proposing a cutting and forming optimization plan. The method improves the processing accuracy and efficiency.

[0149] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0150] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they 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 present embodiment.

[0151] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0152] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0153] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0154] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for analyzing cutting and forming of an automobile control unit, characterized in that: The following steps are involved: Acquire design drawing data of the automobile control unit and appearance data of the raw materials of the automobile control unit to be processed, and determine a cutting process path of the automobile control unit according to the design drawing data and the appearance data; Acquire material information of the raw material, determine the cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and material information, and obtain the cutting process parameters of the vehicle control unit; Cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data; Identifying local hardness deviation of the raw material based on the data feature, and determining location information where the local hardness deviation occurs, to obtain local hardness deviation information; Performing clustering operation on the local hardness deviation information to obtain a clustering result; Determine the position distribution of the local hardness deviation of the current batch of raw materials according to the clustering results, adjust the cutting process path and cutting process parameters of the automobile control unit according to the position distribution, and obtain the cutting and forming process optimization plan of the automobile control unit; The position distribution of the local hardness deviation of the current batch of raw materials is determined according to the clustering results, and the cutting processing path and cutting process parameters of the automobile control unit are adjusted according to the position distribution to obtain the cutting and forming processing optimization plan of the automobile control unit, which is specifically: Determine the position distribution of local hardness deviations in the current batch of raw materials according to the clustering results, and determine the position distribution of local hardening and local softening of the raw materials according to the position distribution, and mark them as local hardness increase distribution areas and local hardness decrease distribution areas; If the local hardness decreases in the current batch of raw materials, the probability of the local hardness decrease in the current batch of raw materials is determined according to the local hardness deviation information, and the local hardness decrease distribution area of ​​the vehicle control unit is predicted according to the local hardness decrease distribution area and the spatial interpolation method; Obtain the stress distribution of the automobile control unit in the working state, determine the impact of the local hardness reduction distribution area of ​​the automobile control unit on the quality of the automobile control unit according to the stress distribution, if the quality impact is greater than the preset quality impact value and the occurrence probability is less than the preset occurrence probability value, determine the quality sampling frequency of the automobile control unit after production according to the occurrence probability, if the occurrence probability of the local hardness reduction of the current batch of raw materials is greater than or equal to the preset value, cancel the processing of the batch of raw materials; If the local hardness increase occurs in the current batch of raw materials, the hardness increase of the local hardness increase distribution area in the current batch of raw materials is determined according to the local hardness deviation information. If the hardness increase is greater than the preset increase, a Voronoi diagram is constructed, and the area where the local hardness increase is greater than the preset increase is regarded as an obstacle. The path is reconstructed based on the Voronoi path planning algorithm to determine whether the cutting path can avoid the obstacle. If possible, the cutting path of the automobile control unit is replanned according to the Voronoi diagram to obtain the optimized cutting path. If not, the cutting control parameters of the local hardness increase distribution area are adjusted according to the hardness increase adjustment of the local hardness increase distribution area to obtain the optimized cutting and forming processing plan for the automobile control unit.

2. The method for analyzing cutting and forming of an automobile control unit according to claim 1, characterized in that: The obtaining of the design drawing data of the automobile control unit and the appearance data of the raw material of the automobile control unit to be processed, and determining the cutting processing path of the automobile control unit according to the design drawing data and the appearance data, is specifically as follows: Acquire design drawing data of the vehicle control unit, convert the design drawing data into an electronic image format, and obtain electronic design drawing data; Converting the electronic design drawing data into a grayscale image, and calculating the gradient and gradient amplitude of each pixel in the grayscale image in the x direction and the y direction based on the Sobel operator; Find the pixel with the largest gradient amplitude in the grayscale image, compare the pixel with the adjacent pixel values ​​in the gradient direction of the pixel along the gradient direction of the pixel, retain the pixels with local maximum values, and suppress the pixel values ​​that do not constitute the maximum value to 0, so as to obtain a non-maximum suppression image; Setting a high threshold and a low threshold of the non-maximum suppression image, classifying pixels of the non-maximum suppression image according to the high threshold and the low threshold, marking pixels exceeding the high threshold as strong edges, marking pixels between the high and low thresholds as weak edges, and marking pixels below the low threshold as non-edge areas, connecting weak edges and strong edges, and obtaining contour data of the vehicle control unit; Constructing a three-dimensional model of the appearance contour of the vehicle control unit according to the contour data; Acquire the raw material appearance data of the automobile control unit to be processed, construct a raw material three-dimensional model according to the raw material appearance data, compare the appearance contour three-dimensional model of the automobile control unit with the raw material three-dimensional model, mark the cutting area of ​​the raw material, and obtain a three-dimensional model of the area to be cut; The three-dimensional model of the area to be cut is analyzed based on the Voronoi path algorithm to determine the cutting path of the automobile control unit.

3. The method for analyzing cutting and forming of an automobile control unit according to claim 1, characterized in that: The material information of the raw material is obtained, and the cutting tool and cutting control parameters of the automobile control unit are determined according to the appearance data and material information of the raw material to obtain the cutting process parameters of the automobile control unit, specifically: Acquire material information of the raw material, acquire hardness information of the raw material through the Internet according to the material information, determine the material of the cutting tool according to the hardness information, and determine the type of the cutting tool according to the appearance data of the raw material; Analyzing the wear resistance of the cutting tool according to the hardness information of the raw material and the material of the cutting tool, and obtaining data on the influence of the cutting speed on the wear resistance of the cutting tool; Determine the cutting speed and cutting depth of the cutting tool according to the influencing data, determine the plasticity and toughness of the raw material according to the material information of the raw material, determine the feed rate of the cutting tool according to the plasticity and toughness, and obtain the cutting control parameters of the automobile control unit processing according to the cutting speed, cutting depth and feed rate; The cutting tool material, cutting tool type and cutting control parameters are integrated to obtain the cutting process parameters of the automobile control unit.

4. The method for analyzing cutting and forming of an automobile control unit according to claim 1, characterized in that: The cutting process is performed on a preset amount of raw materials according to the cutting process path and cutting process parameters, and the tool vibration signal data and cutting force change data of the raw materials during the cutting process are recorded in real time, and data features of the tool vibration signal data and cutting force change data are extracted, specifically: Cutting a preset number of current batches of raw materials according to the cutting process path and cutting process parameters, and acquiring tool vibration signal data and cutting force change data during the cutting process of the raw materials in real time according to the vibration sensor and the force sensor; The tool vibration signal data and cutting force change data are segmented according to a preset time window size, and the standard deviation of the data in each time window is calculated to obtain the vibration signal window standard deviation data and the cutting force window standard deviation data; According to the vibration signal window standard deviation data and the cutting force window standard deviation data, the standard deviation distribution of each window data is counted; By comparing the relative changes of the standard deviation data of each vibration signal window and the standard deviation data of the cutting force window, and evaluating the data fluctuation uniformity of the tool vibration signal data and the cutting force change data according to the standard deviation distribution of each window data, the data fluctuation uniformity evaluation result of the tool vibration signal data and the cutting force change data in each time window is obtained; The data fluctuation uniformity evaluation results of the tool vibration signal data and the cutting force change data in each time window are time-labeled to obtain the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period.

5. The method for analyzing cutting and forming of an automobile control unit according to claim 1, characterized in that: The identifying of the local hardness deviation of the raw material based on the data feature and determining the location information where the local hardness deviation occurs to obtain the local hardness deviation information is specifically: The tool vibration signal data and cutting force variation data are used to construct a feature matrix based on the data fluctuation uniformity characteristics in each time period to obtain a vibration signal feature matrix and a cutting force feature matrix; An isolation forest algorithm is introduced, and outlier analysis is performed on the vibration signal feature matrix and the cutting force feature matrix respectively according to the isolation forest algorithm, and the feature matrix entering the outlier analysis is calibrated as an outlier analysis state matrix; A data cutting point is randomly selected in the value range of the outlier analysis state matrix, the outlier analysis state matrix is ​​divided into two parts according to the data cutting point, and the data cutting is repeated on the two parts of the outlier analysis state matrix after the cutting, until each outlier analysis state matrix after the cutting has only one data point, thereby obtaining an isolation forest of the outlier analysis state matrix; Calculate the number of divisions of each data point in the outlier analysis state matrix from the root node to the leaf node according to the isolation forest, obtain the path length of each data point, and calculate the average path length of each data point in the isolation forest according to the path length; An abnormality score is given to each data point according to the average path length, and a data point with an abnormality score greater than a preset value is marked as an abnormal data point. When the abnormal value analysis of the vibration signal feature matrix and the cutting force feature matrix is ​​completed, the abnormal data point is mapped to the data fluctuation uniformity characteristics of the tool vibration signal data and the cutting force change data in each time period to obtain the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data; Align the fluctuation uniformity abnormal data of the tool vibration signal data and the fluctuation uniformity abnormal data of the cutting force change data in time series, and when the tool vibration signal data and the cutting force change data simultaneously show fluctuation uniformity abnormality, mark the time period as the cutting time point where the raw material shows local hardness deviation; Determine the local hardness deviation position of the raw material according to the local hardness deviation cutting time point and the cutting process path; The abnormal fluctuation degree of the tool vibration signal data and the cutting force change data is determined according to the fluctuation uniformity abnormal data of the tool vibration signal data and the cutting force change data, the local hardness change of the raw material is determined according to the abnormal fluctuation degree, and the local hardness deviation information of a preset number of raw materials is obtained according to the local hardness deviation position and the local hardness change.

6. The method for analyzing cutting and forming of an automobile control unit according to claim 1, characterized in that: The clustering operation is performed on the local hardness deviation information to obtain a clustering result, which is specifically: Integrate the local hardness deviation information of a preset number of raw materials, and convert the local hardness deviation information into a binary coding method to obtain a local hardness deviation data set; Construct K clusters, randomly select K data points from the local hardness deviation dataset as the initial centroids, and use them as the cluster centers of the K clusters; Calculate the Euclidean distance between each data point and each cluster center in the local hardness deviation dataset, and assign each data point to the cluster with the closest Euclidean distance; For each cluster, the mean of all data points in the cluster is calculated, and the mean is used as the new cluster center. The Euclidean distance of each data point to the new cluster center is calculated repeatedly and iteratively, and clusters are assigned and cluster centers are updated until the change in the cluster center is less than the preset value. The clustering operation is stopped, and the clustering results of the local hardness deviation information of a preset number of raw materials are obtained.

7. An automobile control unit cutting and forming processing analysis system, characterized in that: The automobile control unit cutting and forming processing analysis system comprises a storage device and a processor, wherein the storage device comprises an automobile control unit cutting and forming processing analysis method program, and when the automobile control unit cutting and forming processing analysis method program is executed by the processor, the following steps are implemented: Acquire design drawing data of the automobile control unit and appearance data of the raw materials of the automobile control unit to be processed, and determine a cutting process path of the automobile control unit according to the design drawing data and the appearance data; Acquire material information of the raw material, determine the cutting tool and cutting control parameters of the vehicle control unit according to the raw material appearance data and material information, and obtain the cutting process parameters of the vehicle control unit; Cutting a preset amount of raw materials according to the cutting process path and cutting process parameters, recording in real time the tool vibration signal data and cutting force change data during the cutting process of the raw materials, and extracting data features of the tool vibration signal data and cutting force change data; Identifying local hardness deviation of the raw material based on the data feature, and determining location information where the local hardness deviation occurs, to obtain local hardness deviation information; Performing clustering operation on the local hardness deviation information to obtain a clustering result; Determine the position distribution of the local hardness deviation of the current batch of raw materials according to the clustering results, adjust the cutting process path and cutting process parameters of the automobile control unit according to the position distribution, and obtain the cutting and forming process optimization plan of the automobile control unit; The position distribution of the local hardness deviation of the current batch of raw materials is determined according to the clustering results, and the cutting processing path and cutting process parameters of the automobile control unit are adjusted according to the position distribution to obtain the cutting and forming processing optimization plan of the automobile control unit, which is specifically: Determine the position distribution of local hardness deviations in the current batch of raw materials according to the clustering results, and determine the position distribution of local hardening and local softening of the raw materials according to the position distribution, and mark them as local hardness increase distribution areas and local hardness decrease distribution areas; If the local hardness decreases in the current batch of raw materials, the probability of the local hardness decrease in the current batch of raw materials is determined according to the local hardness deviation information, and the local hardness decrease distribution area of ​​the vehicle control unit is predicted according to the local hardness decrease distribution area and the spatial interpolation method; Obtain the stress distribution of the automobile control unit in the working state, determine the impact of the local hardness reduction distribution area of ​​the automobile control unit on the quality of the automobile control unit according to the stress distribution, if the quality impact is greater than the preset quality impact value and the occurrence probability is less than the preset occurrence probability value, determine the quality sampling frequency of the automobile control unit after production according to the occurrence probability, if the occurrence probability of the local hardness reduction of the current batch of raw materials is greater than or equal to the preset value, cancel the processing of the batch of raw materials; If the local hardness increase occurs in the current batch of raw materials, the hardness increase of the local hardness increase distribution area in the current batch of raw materials is determined according to the local hardness deviation information. If the hardness increase is greater than the preset increase, a Voronoi diagram is constructed, and the area where the local hardness increase is greater than the preset increase is regarded as an obstacle. The path is reconstructed based on the Voronoi path planning algorithm to determine whether the cutting path can avoid the obstacle. If possible, the cutting path of the automobile control unit is replanned according to the Voronoi diagram to obtain the optimized cutting path. If not, the cutting control parameters of the local hardness increase distribution area are adjusted according to the hardness increase adjustment of the local hardness increase distribution area to obtain the optimized cutting and forming processing plan for the automobile control unit.

Images