Intelligent tool management system and method for automobile parts processing

Abstract

The present application relates to the field of intelligent management technology, and specifically discloses an intelligent tool management system and method for automobile parts processing, which collects the state image and cutting parameter data of the tool by installing sensors on the machine tool, and uses deep learning technology to extract the appearance visual features and cutting performance features of the tool, and then accurately evaluates the degree of tool wear based on the multimodal fusion features of the two, so as to intelligently judge whether the tool needs to be replaced. In this way, real-time monitoring of the tool wear state and intelligent tool management can be achieved to ensure high quality and high efficiency of automobile parts processing.

Description

Technical Field

[0001] The present application relates to the field of intelligent management technology, and more specifically, to an intelligent tool management system and method for automobile parts processing. Background Art

[0002] Traditional tool management methods mainly rely on manual inspection and experience to select tools, evaluate wear and replace tools. This management model is not only inefficient, but also difficult to accurately monitor the status of tools, which may lead to unstable processing quality and increase production costs. With the development of intelligent manufacturing, enterprises have an increasing demand for intelligent and refined tool management. Traditional tool management methods can no longer meet the efficient and precise production requirements of the modern automotive manufacturing industry.

[0003] Therefore, an intelligent tool management system and method for automobile parts processing is expected. Summary of the invention

[0004] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides an intelligent tool management system and method for automobile parts processing, which collects the state image and cutting parameter data of the tool by installing a sensor on the machine tool, and uses deep learning technology to extract the appearance visual features and cutting performance features of the tool, and then accurately evaluates the wear degree of the tool based on the multimodal fusion features of the two, so as to intelligently judge whether the tool needs to be replaced. In this way, real-time monitoring of the tool wear state and intelligent tool management can be achieved to ensure high quality and high efficiency of automobile parts processing.

[0005] Accordingly, according to one aspect of the present application, there is provided an intelligent tool management system for automobile parts processing, which includes:

[0006] A tool status information acquisition module is used to acquire a tool status image captured by a camera, and a time series of cutting force, a time series of cutting speed, and a time series of cutting temperature during tool operation collected by a sensor group deployed on a machine tool;

[0007] A tool cutting performance feature extraction module, used to extract the global time series correlation feature of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector;

[0008] A tool texture feature extraction module, used to extract the texture features of the tool state image to obtain a HOG feature vector of the tool state image;

[0009] A feature optimization fusion module is used to perform feature optimization fusion on the HOG feature vector of the tool state image and the feature vector representing the tool cutting performance to obtain a comprehensive feature vector representing the tool wear state;

[0010] The tool management result generation module is used to determine whether the tool needs to be replaced based on the comprehensive characterization feature vector of the tool wear state.

[0011] In the above-mentioned intelligent tool management system for automobile parts processing, the tool cutting performance feature extraction module includes: a cutting parameter time series encoding unit, which is used to time series encode the time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature respectively to obtain the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector, and the cutting temperature time series correlation feature vector; a cutting parameter global correlation analysis unit, which is used to arrange the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector, and the cutting temperature time series correlation feature vector into a cutting parameter global feature matrix and then obtain the tool cutting performance characterization feature vector through a cutting parameter global correlation analyzer based on a convolutional neural network.

[0012] In the above-mentioned intelligent tool management system for automobile parts processing, the cutting parameter timing encoding unit is used to: respectively pass the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature through a cutting parameter timing feature extractor based on an LSTM model to obtain the cutting force timing association feature vector, the cutting speed timing association feature vector and the cutting temperature timing association feature vector.

[0013] In the above-mentioned intelligent tool management system for automobile parts processing, the tool texture feature extraction module is used to: calculate the gradient direction histogram of the tool state image to obtain the HOG feature vector of the tool state image.

[0014] In the above-mentioned intelligent tool management system for automobile parts processing, the feature optimization fusion module includes: a feature importance perception unit, which is used to perceive the feature importance of the tool cutting performance characterization feature vector based on the feature sub-dimensional distribution based on the tool state image HOG feature vector to obtain the optimized tool cutting performance characterization feature vector; a fusion unit, which is used to fuse the tool state image HOG feature vector and the optimized tool cutting performance characterization feature vector to obtain the comprehensive characterization feature vector of the tool wear state.

[0015] In the above-mentioned intelligent tool management system for automobile parts processing, the feature importance perception unit is used to: calculate the positional difference between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a first viewpoint metric representation vector; calculate the positional point multiplication between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a second viewpoint metric representation vector; calculate the positional sum between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a third viewpoint metric representation vector; calculate the gradient amplitude of each position in the first viewpoint metric representation vector, the second viewpoint metric representation vector and the third viewpoint metric representation vector to obtain a first viewpoint metric perception vector, a second viewpoint metric perception vector and a third viewpoint metric perception vector; input the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector into a backward machine learning reverse multi-viewpoint perception optimization module to obtain a reverse multi-viewpoint perception optimization representation vector; calculate the positional point multiplication between the reverse multi-viewpoint perception optimization representation vector and the tool cutting performance characterization feature vector to obtain the optimized tool cutting performance characterization feature vector.

[0016] In the above-mentioned intelligent tool management system for automobile parts processing, the tool management result generation module is used to: pass the comprehensive characterization feature vector of the tool wear state through a classifier-based tool replacement manager to obtain a management result, and the management result is used to indicate whether the tool needs to be replaced.

[0017] According to another aspect of the present application, there is provided an intelligent tool management method for automobile parts processing, which comprises:

[0018] Acquire the tool state image captured by the camera, and the time series of cutting force, cutting speed and cutting temperature during the tool operation process captured by the sensor group deployed on the machine tool;

[0019] Extracting the global time series correlation features of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector;

[0020] Extracting texture features of the tool state image to obtain a tool state image HOG feature vector;

[0021] Performing feature optimization fusion on the HOG feature vector of the tool state image and the feature vector representing the cutting performance of the tool to obtain a comprehensive feature vector representing the tool wear state;

[0022] Based on the comprehensive characterization feature vector of the tool wear state, it is determined whether the tool needs to be replaced.

[0023] Compared with the prior art, the intelligent tool management system and method for automobile parts processing provided by this application collects the state image and cutting parameter data of the tool by installing sensors on the machine tool, and uses deep learning technology to extract the appearance visual features and cutting performance features of the tool, and then accurately evaluates the wear degree of the tool based on the multimodal fusion features of the two, so as to intelligently judge whether the tool needs to be replaced. In this way, real-time monitoring of the tool wear state and intelligent tool management can be achieved to ensure high quality and high efficiency of automobile parts processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0025] Figure 1 The block diagram is of an intelligent tool management system for automobile parts machining according to an embodiment of the present application.

[0026] Figure 2 Schematic diagram of the architecture of an intelligent tool management system for automobile parts processing according to an embodiment of the present application.

[0027] Figure 3 It is a block diagram of a tool cutting performance feature extraction module in an intelligent tool management system for automobile parts processing according to an embodiment of the present application.

[0028] Figure 4 It is a block diagram of a feature optimization fusion module in an intelligent tool management system for automobile parts machining according to an embodiment of the present application.

[0029] Figure 5 The present invention is a flowchart of an intelligent tool management method for automobile parts processing according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] Below, the embodiments of the present application will be described in more detail in conjunction with the accompanying drawings, and the above and other purposes, features and advantages of the present application will become more apparent. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0031] Figure 1 The block diagram is of an intelligent tool management system for automobile parts machining according to an embodiment of the present application. Figure 2FIG. 1 is a schematic diagram of the architecture of an intelligent tool management system for automobile parts processing according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the embodiment of the present application, the intelligent tool management system 100 for automobile parts processing includes: a tool state information acquisition module 110, which is used to obtain the tool state image captured by the camera, and the time series of cutting force, cutting speed and cutting temperature during the operation of the tool collected by the sensor group deployed on the machine tool; a tool cutting performance feature extraction module 120, which is used to extract the global time series correlation characteristics of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector; a tool texture feature extraction module 130, which is used to extract the texture features of the tool state image to obtain the tool state image HOG feature vector; a feature optimization fusion module 140, which is used to perform feature optimization fusion on the tool state image HOG feature vector and the tool cutting performance characterization feature vector to obtain a tool wear state comprehensive characterization feature vector; a tool management result generation module 150, which is used to determine whether the tool needs to be replaced based on the tool wear state comprehensive characterization feature vector.

[0032] As mentioned in the above background technology, the traditional tool management method mainly relies on manual inspection and experience judgment to select, evaluate and replace tools. This management mode is not only inefficient, but also difficult to accurately monitor the status of the tool, which may lead to unstable processing quality and increase production costs. With the development of intelligent manufacturing, enterprises have increasingly increased their demand for intelligent and refined tool management, and the traditional tool management method can no longer meet the efficient and accurate production requirements of the modern automobile manufacturing industry. In response to the above technical problems, the technical concept of this application is to use the Internet of Things technology, big data analysis and machine learning algorithms to comprehensively monitor the use status of the tool and make intelligent decisions. By installing sensors on the machine tool to collect the state image and cutting parameter data of the tool, and using deep learning technology to extract the appearance visual features and cutting performance features of the tool, the wear degree of the tool is accurately evaluated based on the multimodal fusion features of the two, so as to intelligently judge whether the tool needs to be replaced. In this way, real-time monitoring of the tool wear status and intelligent tool management can be achieved to ensure high quality and high efficiency of automobile parts processing.

[0033] In the above-mentioned intelligent tool management system 100 for automobile parts processing, the tool state information acquisition module 110 is used to obtain the tool state image captured by the camera, and the time series of cutting force, cutting speed and cutting temperature during the operation of the tool collected by the sensor group deployed on the machine tool. It should be understood that the tool state image captured by the camera provides direct visual feedback of the tool appearance, which can reveal the geometric changes of the tool, such as wear, chipping, cracks, etc., and is an important basis for judging whether the tool needs to be replaced. The parameter data such as cutting force, cutting speed and cutting temperature during the operation of the tool reflect the dynamic performance of the tool during the processing, which not only reveals the interaction between the tool and the workpiece, but also reflects the performance of the tool under different working conditions. For example, the change of cutting force may indicate that the tool wear is aggravated, and the increase of cutting temperature may mean that the tool is overheated or the wear is aggravated. In the evaluation of the wear state of the tool, the evaluation method that relies on a single data source often has limitations and is easily affected by factors such as noise and error. In the technical solution of the present application, by combining the tool state image and the cutting parameter time series data, a multimodal characterization of the tool wear state can be achieved, and the accuracy and reliability of the tool wear evaluation can be improved.

[0034] In the above-mentioned intelligent tool management system 100 for automobile parts processing, the tool cutting performance feature extraction module 120 is used to extract the global time series correlation features of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector. Figure 3 FIG. 1 is a block diagram of a tool cutting performance feature extraction module in an intelligent tool management system for automobile parts processing according to an embodiment of the present application. Figure 3 As shown, the tool cutting performance feature extraction module 120 includes: a cutting parameter time series encoding unit 121, which is used to time series encode the time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature to obtain a cutting force time series correlation feature vector, a cutting speed time series correlation feature vector, and a cutting temperature time series correlation feature vector; a cutting parameter global correlation analysis unit 122, which is used to arrange the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector, and the cutting temperature time series correlation feature vector into a cutting parameter global feature matrix and then obtain the tool cutting performance characterization feature vector through a cutting parameter global correlation analyzer based on a convolutional neural network.

[0035] Specifically, the cutting parameter time series encoding unit 121 is used to perform time series encoding on the time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature to obtain a cutting force time series correlation feature vector, a cutting speed time series correlation feature vector, and a cutting temperature time series correlation feature vector. In a specific example of the present application, the processing method of performing time series encoding on the time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature is to pass the time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature through a cutting parameter time series feature extractor based on an LSTM model to obtain the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector, and the cutting temperature time series correlation feature vector. It should be understood that the parameters such as cutting force, cutting speed, and cutting temperature in the cutting process are all time-varying data, and there is a strong time series dependence in the time dimension. In order to effectively extract the time series correlation change feature pattern of each parameter, in the technical solution of the present application, an LSTM (long short-term memory network) model is used to perform time series encoding on the time series data of each parameter. Those skilled in the art should know that the LSTM model can capture long-term dependencies in time series data while avoiding gradient vanishing or exploding in long-term dependency problems, thereby being able to capture the changing patterns and trends of various cutting parameters in the time series and more accurately reflect the operating status and performance of the tool.

[0036] Specifically, the cutting parameter global correlation analysis unit 122 is used to arrange the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector and the cutting temperature time series correlation feature vector into a cutting parameter global feature matrix, and then obtain the tool cutting performance characterization feature vector through a cutting parameter global correlation analyzer based on a convolutional neural network. It should be understood that cutting force, cutting speed and cutting temperature are important indicators reflecting the cutting performance of a tool, and there are complex interactions and correlations between the three. In order to further capture the global correlation between various cutting parameters and more comprehensively describe the cutting performance of the tool, in the technical solution of the present application, first, by arranging the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector and the cutting temperature time series correlation feature vector into a matrix form, the global correlation between various cutting parameters is established. Furthermore, a convolutional neural network (CNN) is used as a cutting parameter global correlation analyzer, and the local feature extraction and abstraction capabilities of the CNN model are used to analyze the cutting parameter global feature matrix. Through the combination of convolutional layers, pooling layers and activation functions, CNN can effectively capture the potential correlation patterns between various cutting parameters, such as the coordinated changes in cutting force, speed and temperature caused by tool wear, further enhancing the ability to characterize tool cutting performance.

[0037] In the above-mentioned intelligent tool management system 100 for automobile parts processing, the tool texture feature extraction module 130 is used to extract the texture features of the tool state image to obtain the HOG feature vector of the tool state image. In a specific example of the present application, the processing method for extracting the texture features of the tool state image is to calculate the gradient direction histogram of the tool state image to obtain the HOG feature vector of the tool state image. It should be understood that in the tool state image, information such as tool wear, chipping, cracks, etc. is usually expressed in the form of texture changes. HOG (Histogram of Oriented Gradients) is an effective image feature descriptor, especially suitable for capturing edge and structural information in an image, and is therefore often used for object recognition and image analysis. In the technical solution of the present application, by calculating the gradient direction histogram of the tool state image, the texture features in the image, such as the edge contour of the wear area, the sharp change of chipping, and the discontinuity of the crack, can be extracted, thereby intuitively reflecting the wear state of the tool.

[0038] In the above-mentioned intelligent tool management system 100 for automobile parts processing, the feature optimization fusion module 140 is used to optimize and fuse the HOG feature vector of the tool state image and the feature vector representing the cutting performance of the tool to obtain a comprehensive feature vector representing the tool wear state. It should be understood that the HOG feature vector of the tool state image and the feature vector representing the cutting performance of the tool respectively describe the tool state from two different dimensions of image texture and cutting performance. By integrating the information of the two, the complementary information between the two can be fully utilized to improve the accuracy and robustness of tool wear state recognition. In particular, in the technical solution of the present application, it is considered that the feature vector representing the cutting performance of the tool is a feature extracted based on time series data (such as cutting force, cutting speed and cutting temperature), while the HOG feature vector of the tool state image is a feature extracted based on image data. These two data types reflect different aspects of the tool state and may have differences in feature expression. In addition, the cutting performance feature vector is a time series feature extracted by the LSTM model, while the HOG feature vector of the tool state image is extracted by the gradient direction histogram of the image. There are essential differences between these two feature extraction methods in the way of processing data and extracting features, which may lead to semantic inconsistency between the two. In addition, the cutting performance characterization feature vector reflects the dynamic changes of the tool during operation, while the tool state image HOG feature vector reflects more the static features of the tool state image. The inconsistency between the dynamic features and the static features in the time dimension may lead to the lack of causal association between the two. In other words, there is a lack of posterior-prior causal association between the tool cutting performance characterization feature vector and the tool state image HOG feature vector. In order to solve this problem, in the technical solution of the present application, before the feature interactive fusion of the tool state image HOG feature vector and the tool cutting performance characterization feature vector, the feature importance of the tool cutting performance characterization feature vector based on the feature sub-dimensional distribution is further perceived based on the tool state image HOG feature vector.

[0039] Figure 4 FIG. 1 is a block diagram of a feature optimization fusion module in an intelligent tool management system for automobile parts processing according to an embodiment of the present application. Figure 4 As shown, the feature optimization fusion module 140 includes: a feature importance perception unit 141, which is used to perceive the feature importance of the tool cutting performance characterization feature vector based on the feature sub-dimensional distribution based on the tool state image HOG feature vector to obtain the optimized tool cutting performance characterization feature vector; a fusion unit 142, which is used to fuse the tool state image HOG feature vector and the optimized tool cutting performance characterization feature vector to obtain the comprehensive characterization feature vector of the tool wear state.

[0040] Specifically, the feature importance perception unit 141 is used to: calculate the positional difference between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a first viewpoint metric representation vector; calculate the positional point multiplication between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a second viewpoint metric representation vector; calculate the positional sum between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a third viewpoint metric representation vector; calculate the gradient amplitude of each position in the first viewpoint metric representation vector, the second viewpoint metric representation vector and the third viewpoint metric representation vector to obtain a first viewpoint metric perception vector, a second viewpoint metric perception vector and a third viewpoint metric perception vector; input the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector into a backward machine learning reverse multi-viewpoint perception optimization module to obtain a reverse multi-viewpoint perception optimization representation vector; calculate the positional point multiplication between the reverse multi-viewpoint perception optimization representation vector and the tool cutting performance characterization feature vector to obtain the optimized tool cutting performance characterization feature vector.

[0041] The calculation process of the reverse multi-view perception optimization representation vector is specifically expressed by the formula:

[0042] ;

[0043] in, , and The first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are represented by The eigenvalues ​​at the positions, are three eigenvalues ​​of corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector The mean of is the standard deviation of three eigenvalues ​​at corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector, represents the maximum value of three eigenvalues ​​at corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector, represents the linear rectification function, represents the normalized exponential function, represents the reverse multi-view perception optimization representation vector The feature value at each position.

[0044] Specifically, in the technical solution of the present application, based on the HOG feature vector of the tool state image, the feature vector characterizing the tool cutting performance is optimized based on the feature importance perception of the feature sub-dimension distribution, and the process includes first calculating the position difference, point multiplication and sum between the feature vector characterizing the tool cutting performance and the HOG feature vector of the tool state image through multi-view analysis to obtain three viewpoint metric representation vectors, and quantifying the relationship between features from different angles. Then, the gradient amplitude of each position in these viewpoint metric representation vectors is calculated through backward error perception to identify key change points to provide a basis for feature optimization.

[0045] Then, the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are input into the backward machine learning reverse multi-viewpoint perception optimization module, wherein the backward machine learning reverse multi-viewpoint perception optimization module captures the significant comprehensive ability factor of the feature importance perception (Feature Importance Perception) of the feature sub-dimension distribution of the corresponding position in the first to third viewpoint metric perception vectors by adopting a squeeze-incentive mechanism composed of -functions. Then, the position point multiplication between the reverse multi-viewpoint perception optimization representation vector and the tool cutting performance characterization feature vector is calculated to perform backward optimization perception (Backward Optimization Perception) on the tool cutting performance characterization feature vector to adjust the tool cutting performance characterization feature vector so as to better associate it with the tool state image HOG feature vector, thereby enhancing the causal relationship between the tool cutting performance characterization feature vector and the tool state image HOG feature vector. In this way, the optimized tool cutting performance characterization feature vector is then feature-fused with the tool state image HOG feature vector, which can more accurately reflect the wear state of the tool and significantly improve the accuracy and stability of subsequent tool wear state recognition.

[0046] In the above-mentioned intelligent tool management system 100 for automobile parts processing, the tool management result generation module 150 is used to determine whether the tool needs to be replaced based on the comprehensive characterization feature vector of the tool wear state. In a specific example of the present application, the implementation method of determining whether the tool needs to be replaced based on the comprehensive characterization feature vector of the tool wear state is to pass the comprehensive characterization feature vector of the tool wear state through a tool replacement manager based on a classifier to obtain a management result, and the management result is used to indicate whether the tool needs to be replaced. That is, a classification algorithm is used to perform feature analysis on the comprehensive characterization feature vector of the tool wear state to determine whether the tool needs to be replaced. Specifically, the comprehensive characterization feature vector of the tool wear state is input into a pre-trained classifier, and the classifier performs feature learning and classification mapping on the comprehensive characterization feature vector of the tool wear state based on the model parameters obtained by training, so as to output a corresponding management result, clearly indicating whether the current tool needs to be replaced. If the management result shows that the tool needs to be replaced, the tool replacement operation is triggered during the actual automotive parts processing process to ensure the stability of processing quality and production efficiency; if the management result shows that the tool does not need to be replaced, the tool can continue to be used for subsequent cutting operations, while continuously monitoring the tool wear status to ensure timely replacement before wear affects the processing accuracy. Through such an intelligent decision-making process, it is possible to accurately evaluate and timely manage the tool wear status, effectively avoid processing quality problems caused by tool wear, improve production efficiency, and reduce production costs.

[0047] In summary, the intelligent tool management system for automobile parts processing according to the embodiment of the present application is explained, which collects the state image and cutting parameter data of the tool by installing sensors on the machine tool, and uses deep learning technology to extract the appearance visual features and cutting performance features of the tool, and then accurately evaluates the wear degree of the tool based on the multimodal fusion features of the two, so as to intelligently judge whether the tool needs to be replaced. In this way, real-time monitoring of the tool wear state and intelligent tool management can be achieved to ensure high quality and high efficiency of automobile parts processing.

[0048] Figure 5 Flow chart of the intelligent tool management method for automobile parts processing according to the embodiment of the present application. Figure 5As shown, according to the embodiment of the present application, the intelligent tool management method for automobile parts processing includes the following steps: S110, acquiring a tool state image captured by a camera, and a time series of cutting force, a time series of cutting speed, and a time series of cutting temperature during tool operation captured by a sensor group deployed on a machine tool; S120, extracting the global temporal correlation features of cutting parameters from the time series of cutting force, the time series of cutting speed, and the time series of cutting temperature to obtain a tool cutting performance characterization feature vector; S130, extracting the texture features of the tool state image to obtain a tool state image HOG feature vector; S140, performing feature optimization fusion on the tool state image HOG feature vector and the tool cutting performance characterization feature vector to obtain a tool wear state comprehensive characterization feature vector; S150, determining whether the tool needs to be replaced based on the tool wear state comprehensive characterization feature vector.

[0049] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent tool management method for automobile parts processing have been referred to above. Figures 1 to 4 The invention has been introduced in detail in the description of the intelligent tool management system for automobile parts processing, and therefore, its repeated description will be omitted.

[0050] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0051] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the module division is only a logical function division, and there may be other division methods in actual implementation. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0052] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0053] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0054] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0055] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0056] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent tool management system for automobile parts processing, characterized in that: include: A tool status information acquisition module is used to acquire a tool status image acquired by a camera, and a time series of cutting force, a time series of cutting speed, and a time series of cutting temperature during tool operation acquired by a sensor group deployed on a machine tool; A tool cutting performance feature extraction module is used to extract the global time series correlation feature of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector; A tool texture feature extraction module, used to extract the texture features of the tool state image to obtain a HOG feature vector of the tool state image; A feature optimization fusion module is used to perform feature optimization fusion on the HOG feature vector of the tool state image and the feature vector representing the tool cutting performance to obtain a comprehensive feature vector representing the tool wear state; A tool management result generation module, used to determine whether the tool needs to be replaced based on the comprehensive characterization feature vector of the tool wear state; Wherein, the feature optimization fusion module includes: A feature importance perception unit, used for performing feature importance perception based on feature sub-dimension distribution on the tool cutting performance characterization feature vector based on the tool state image HOG feature vector to obtain an optimized tool cutting performance characterization feature vector; A fusion unit, used for fusing the HOG feature vector of the tool state image and the feature vector representing the optimized tool cutting performance to obtain a comprehensive feature vector representing the tool wear state; Wherein, the feature importance perception unit is used to: Calculating the position difference between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a first viewpoint metric representation vector; Calculate the position point multiplication between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a second viewpoint metric representation vector; Calculating the positional sum between the tool cutting performance characterization feature vector and the tool state image HOG feature vector to obtain a third viewpoint metric representation vector; Calculating the gradient magnitude of each position in the first viewpoint metric representation vector, the second viewpoint metric representation vector, and the third viewpoint metric representation vector to obtain a first viewpoint metric perception vector, a second viewpoint metric perception vector, and a third viewpoint metric perception vector; Inputting the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector into a backward machine learning inverse multi-viewpoint perception optimization module to obtain a reverse multi-viewpoint perception optimization representation vector; The optimized tool cutting performance characterization feature vector is obtained by calculating the position point multiplication between the reverse multi-view perception optimization representation vector and the tool cutting performance characterization feature vector.

2. The intelligent tool management system for automobile parts processing according to claim 1 is characterized in that: The tool cutting performance feature extraction module comprises: A cutting parameter time series encoding unit, used for respectively performing time series encoding on the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a cutting force time series associated feature vector, a cutting speed time series associated feature vector and a cutting temperature time series associated feature vector; A cutting parameter global correlation analysis unit is used to arrange the cutting force time series correlation feature vector, the cutting speed time series correlation feature vector and the cutting temperature time series correlation feature vector into a cutting parameter global feature matrix and then obtain the tool cutting performance characterization feature vector through a cutting parameter global correlation analyzer based on a convolutional neural network.

3. The intelligent tool management system for automobile parts processing according to claim 2 is characterized in that: The cutting parameter timing encoding unit is used for: The time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature are respectively passed through a cutting parameter time series feature extractor based on an LSTM model to obtain the cutting force time series associated feature vector, the cutting speed time series associated feature vector and the cutting temperature time series associated feature vector.

4. The intelligent tool management system for automobile parts processing according to claim 3 is characterized in that: The tool texture feature extraction module is used to: The gradient direction histogram of the tool state image is calculated to obtain the HOG feature vector of the tool state image.

5. The intelligent tool management system for automobile parts processing according to claim 4 is characterized in that: The tool management result generating module is used for: The tool wear state comprehensive characterization feature vector is passed through a tool replacement manager based on a classifier to obtain a management result, and the management result is used to indicate whether the tool needs to be replaced.

6. An intelligent tool management method for automobile parts processing, using the intelligent tool management system for automobile parts processing according to claim 1, characterized in that: include: Acquire the tool state image captured by the camera, and the time series of cutting force, cutting speed and cutting temperature during the tool operation process captured by the sensor group deployed on the machine tool; Extracting the global time series correlation features of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector; Extracting texture features of the tool state image to obtain a tool state image HOG feature vector; Performing feature optimization fusion on the HOG feature vector of the tool state image and the feature vector representing the cutting performance of the tool to obtain a comprehensive feature vector representing the tool wear state; Based on the comprehensive characterization feature vector of the tool wear state, it is determined whether the tool needs to be replaced.

7. The intelligent tool management method for automobile parts processing according to claim 6 is characterized in that: Extracting the global time series correlation features of cutting parameters from the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature to obtain a tool cutting performance characterization feature vector, including: Performing time series coding on the time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature respectively to obtain a cutting force time series correlation feature vector, a cutting speed time series correlation feature vector and a cutting temperature time series correlation feature vector; The cutting force time series correlation feature vector, the cutting speed time series correlation feature vector and the cutting temperature time series correlation feature vector are arranged into a cutting parameter global feature matrix and then used through a cutting parameter global correlation analyzer based on a convolutional neural network to obtain the tool cutting performance characterization feature vector.

8. The intelligent tool management method for automobile parts processing according to claim 7 is characterized in that: The time series of the cutting force, the time series of the cutting speed, and the time series of the cutting temperature are respectively time-series encoded to obtain a cutting force time series correlation feature vector, a cutting speed time series correlation feature vector, and a cutting temperature time series correlation feature vector, including: The time series of the cutting force, the time series of the cutting speed and the time series of the cutting temperature are respectively passed through a cutting parameter time series feature extractor based on an LSTM model to obtain the cutting force time series associated feature vector, the cutting speed time series associated feature vector and the cutting temperature time series associated feature vector.

Images