A CNC tool breakage monitoring and control method, system, storage medium and program product

Abstract

The present invention discloses a CNC tool breakage monitoring and control method, system, storage medium and program product, the system includes an image acquisition module, an image processing module, a database, a tool breakage prediction module, a data processing and communication module and a CNC control execution module. The present invention realizes the monitoring function of tool temperature, tool wear, contact state between tool and workpiece, tool working path, tool moving speed and tool acceleration, wherein in monitoring tool wear, tool breakage can be very directly monitored, when tool breakage occurs, by analyzing the tool temperature, wear, contact state with workpiece, working path, moving speed and acceleration during working, it can be analyzed whether there is a tool breakage risk, and a comprehensive prediction is made for various factors of tool breakage, effectively reducing the probability of tool breakage, and protecting CNC machine tools, tools and workpieces, and at the same time, there is no need to use several different types of sensors in hardware.

Description

Technical Field

[0001] The present invention belongs to the field of computer numerical control technology and relates to tool monitoring and control of numerically controlled machine tools. Specifically, it relates to a CNC tool breakage monitoring and control method, system, storage medium and program product, which can predict and analyze the risk of tool breakage, realize active early warning and factor summarization of tool breakage, thereby effectively reducing the risk of tool breakage and improving the safety and efficiency of the machining process. Background Art

[0002] Computer Numerical Control (CNC) machining is a process that uses CNC machine tools to perform automated machining. During machining, the workpiece is machined mainly by automatically controlling the movement of the tool. During CNC machining, the tool, as a key tool, comes into direct contact with the workpiece and performs cutting operations, which will generate high temperature, wear and other phenomena, so the tool may break. Although tool breakage does not affect the operation of the CNC machine tool's power unit, after the tool breaks, the CNC machine tool will continue to work and cause damage to itself and the workpiece, so a tool breakage monitoring system is needed for monitoring.

[0003] At present, the tool breakage monitoring method is to install several sensors in the CNC for monitoring. Each sensor needs to work independently and judge the working status of the tool by collecting corresponding physical quantities. The monitoring effect of the tool during the working process is poor, and there are many shortcomings: First, the multi-sensor system is complex and costly. Each sensor requires an independent signal acquisition and processing device, which not only increases the complexity and cost of the system, but also leads to the difficulty of data processing and analysis. Secondly, the existing tool breakage monitoring system cannot predict tool breakage and analyze tool breakage factors, and most systems can only issue an alarm after the tool breaks, and cannot issue an early warning before the tool breaks, and cannot reduce the situation of tool breakage. In addition, the system cannot provide a detailed analysis of the reasons for tool breakage, and it is not convenient for staff to carry out targeted maintenance and improvements.

[0004] In summary, there are still many technical problems that need to be solved in the current tool breakage monitoring technology in CNC machining. These problems include high system complexity, difficulty in tool breakage prediction and tool breakage factor analysis, inability to issue warnings before tool breakage, inability to reduce tool breakage, and inconvenience for staff to analyze tool breakage factors. How to design an efficient, reliable, and easy-to-maintain tool breakage monitoring system to improve monitoring accuracy and reliability, achieve effective warnings before tool breakage, and provide detailed tool breakage cause analysis is a problem that needs to be solved urgently. Summary of the invention

[0005] (I) Purpose of the invention

[0006] The purpose of the present invention is to provide a CNC tool breakage monitoring and control method, system, storage medium and program product. By adopting post-shooting image processing technology, comprehensive monitoring of tool temperature, wear, contact status with workpiece, working path, moving speed and acceleration is achieved, which solves the problems in the above-mentioned prior art that tool breakage prediction and tool breakage factor analysis cannot be achieved, warning cannot be issued before tool breakage, tool breakage cannot be reduced, and it is also inconvenient for staff to analyze the tool breakage factors.

[0007] (II) Technical solution

[0008] In order to achieve the purpose of the invention and solve the technical problems, the present invention adopts the following technical solutions:

[0009] The first object of the present invention is to provide a CNC tool breakage monitoring and control method, which at least comprises the following implementation steps when executed:

[0010] SS1. Based on the image acquisition module installed in the CNC machine tool or set on the tool holder of the CNC machine tool, the working state of the tool is continuously photographed inside the CNC machine tool to obtain the working video data of the tool;

[0011] SS2. Extracting the captured images from the tool working video data, and processing the extracted captured images, wherein the image processing includes at least enhancement, edge processing and feature extraction;

[0012] SS3. Construct a database to pre-store standard tool working state related data, including image feature data, wear level data, a mapping relationship model between image features and tool temperature, and tool temperature under different working states, tool-workpiece contact state, tool working path, tool movement speed and acceleration standard range and threshold value, wherein the image feature data at least includes color features, texture features and shape features corresponding to different tool wear levels;

[0013] SS4. Based on the image feature data extracted after the image processing in step SS2 and combined with the standard tool related data pre-stored in the database, a comparison analysis is performed to comprehensively determine whether there is a risk of tool breakage;

[0014] SS5. Classify and process the tool breakage risk analysis results, and generate control instructions based on the tool breakage risk analysis results to make shutdown, alarm or adjust processing parameters.

[0015] The second invention object of the present invention is to provide a computer program product, including computer instructions, which instruct a computing device to execute the above-mentioned CNC tool breakage monitoring and control method of the present invention.

[0016] The third inventive object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned CNC tool breakage monitoring and control method of the present invention is implemented.

[0017] The fourth invention objective of the present invention is a CNC tool breakage monitoring and control system, which is used to monitor the working status of the tool in the CNC machining process in real time and analyze and predict the risk of tool breakage, including an image acquisition module, an image processing module, a database, a tool breakage prediction module, a data processing and communication module, and a CNC control execution module, characterized in that:

[0018] The image acquisition module is installed in the CNC machine tool or arranged on the tool holder of the CNC machine tool, and is used to continuously shoot the working state of the tool inside the CNC machine tool, obtain the working video data of the tool, and transmit the obtained video data to the downstream image processing module;

[0019] The input end of the image processing module is connected to the image acquisition module, which is used to receive the tool working video data and extract the captured images in the video, and process the extracted captured images at the same time, the image processing at least includes enhancement, edge processing and feature extraction, and transmits the processed image feature data to the downstream tool breakage prediction module;

[0020] The database pre-stores standard tool working state related data, including image feature data, wear level data, a mapping relationship model between image features and tool temperature, and tool temperature under different working states, tool-workpiece contact state, tool working path, tool movement speed and standard ranges and thresholds of acceleration, wherein the image feature data at least includes color features, texture features and shape features corresponding to different tool wear levels;

[0021] The input end of the tool breakage prediction module is communicatively connected to the image processing module and the database, and is used to perform comparison and analysis based on the image feature data extracted by the image processing module and combined with the standard tool related data pre-stored in the database, comprehensively judge whether there is a sign of tool breakage, and output the judgment result to the downstream data processing and communication module;

[0022] The input end of the data processing and communication module is communicatively connected to the tool breakage prediction module, and is used to receive and classify the analysis results of the tool breakage prediction module, and transmit the results to the CNC control execution module;

[0023] The input end of the CNC control execution module is communicatively connected to the data processing and communication module, and is used to generate control instructions according to the analysis results, and perform shutdown, alarm or adjustment of processing parameters based on the control instructions.

[0024] (III) Technical Effect

[0025] Compared with the prior art, the CNC tool breakage monitoring and control method, system, storage medium and program product of the present invention have the following beneficial and significant technical effects:

[0026] (1) In the present invention, the post-shooting image processing method is adopted to realize the monitoring functions of tool temperature, tool wear, contact state between tool and workpiece, tool working path, tool moving speed and tool acceleration. In monitoring tool wear, tool breakage can be monitored very directly. When tool breakage occurs, instructions can be output to the CNC control system in time. At the same time, by analyzing the tool temperature, wear, contact state with workpiece, working path, moving speed and acceleration during working, it can be analyzed whether there is a risk of tool breakage. A comprehensive prediction is made for various factors causing tool breakage, effectively reducing the probability of tool breakage, and protecting CNC machine tools, tools and workpieces. At the same time, there is no need to use several different types of sensors in terms of hardware, which reduces the use cost and maintenance cost / difficulty, and also improves the accuracy of tool breakage monitoring;

[0027] (2) In the present invention, image processing is used to add a tool setting monitoring module, which can monitor tool setting in real time and reduce the situation of tool breakage caused by tool calibration. In addition, in the present invention, the tool breakage analysis module normalizes and classifies the various tool breakage prediction situations after processing. When tool breakage occurs, it generates tool breakage factor data with tool temperature, tool wear, tool-workpiece contact status, tool working path, tool speed, and tool acceleration, which is convenient for staff to make adaptive improvements to CNC machine tools and tools based on tool breakage factors. At the same time, the image processing module includes a video recording unit that can record the video when the tool breakage occurs, and moving forward 5-10 minutes can facilitate professionals to judge the tool breakage factors by slowing down the overall video, which is convenient for targeted improvements to tools or CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The present invention is a flow chart of the CNC tool breakage monitoring and control method.

[0029] Figure 2 The schematic diagram of the CNC tool breakage monitoring and control system of the present invention is shown in FIG. DETAILED DESCRIPTION

[0030] In order to better understand the present invention, the content of the present invention is further explained in conjunction with the embodiments below. In the accompanying drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be understood as limitations on the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The structure and technical solution of the present invention are further described in detail below in conjunction with the accompanying drawings, and an embodiment of the present invention is given.

[0031] Example 1

[0032] The purpose of the present invention is to solve the problems in the prior art that it is impossible to predict blade breakage, analyze the factors causing blade breakage, issue warnings before blade breakage, reduce the number of blade breakages, and it is not convenient for staff to analyze the factors causing blade breakage. As a specific example, Figure 1 As shown, the CNC tool breakage monitoring and control method provided by the present invention mainly includes the following implementation steps when executed:

[0033] SS1. Based on the image acquisition module installed in the CNC machine tool or set on the tool holder of the CNC machine tool, the working state of the tool is continuously photographed inside the CNC machine tool to obtain the working video data of the tool;

[0034] SS2. Extracting the captured images from the tool working video data, and processing the extracted captured images, wherein the image processing includes at least enhancement, edge processing and feature extraction;

[0035] SS3. Construct a database to pre-store standard tool working state related data, including image feature data, wear level data, a mapping relationship model between image features and tool temperature, and tool temperature under different working states, tool-workpiece contact state, tool working path, tool movement speed and acceleration standard range and threshold value, wherein the image feature data at least includes color features, texture features and shape features corresponding to different tool wear levels;

[0036] SS4. Based on the image feature data extracted after the image processing in step SS2 and combined with the standard tool related data pre-stored in the database, a comparison analysis is performed to comprehensively determine whether there is a risk of tool breakage;

[0037] SS5. Classify and process the tool breakage risk analysis results, and generate control instructions based on the tool breakage risk analysis results to make shutdown, alarm or adjust processing parameters.

[0038] Through the above implementation steps, the CNC tool breakage monitoring and control method provided by the present invention can realize real-time monitoring of the tool working state and prediction of the risk of breakage. The method collects the processing process video in real time, processes and analyzes the collected image based on the standard data stored in the database, realizes real-time monitoring of the tool state and analyzes and predicts the risk of breakage, so that the CNC system can issue an early warning or automatically adjust the processing parameters before the tool breaks, effectively solving the problems of insufficient tool breakage prediction and incomplete analysis of tool breakage factors in the prior art, improving the safety and efficiency of the CNC processing process, facilitating the staff to conduct targeted analysis and optimization processing, and reducing the occurrence of tool breakage accidents.

[0039] Example 2

[0040] Corresponding to the above-mentioned embodiment 1, Figure 2 As shown, the present invention also proposes a CNC tool breakage monitoring and control system, including an image acquisition module (an industrial camera is preferably used in this embodiment), an image processing module, a database, a tool breakage prediction module, a data processing and communication module, and a CNC control execution module, wherein the industrial camera of the image acquisition module is installed in the CNC machine tool or arranged on the tool holder of the CNC machine tool, and is used to continuously shoot the working state of the tool inside the CNC machine tool, obtain the working video data of the tool, and transmit the obtained video data to the downstream image processing module; the input end of the image processing module communication is connected to the industrial camera of the image acquisition module, and is used to receive the working video data of the tool and extract the captured image in the video, and at the same time process the extracted captured image, and the image processing at least includes enhancement, edge processing and feature extraction, and the processed image feature data is transmitted to the downstream tool breakage prediction module.

[0041] At the same time, the database in the present invention is used to pre-store relevant data on the working status of standard tools, including image feature data, wear level data, a mapping relationship model between image features and tool temperature, and tool temperature under different working conditions, tool-workpiece contact status, tool working path, tool movement speed and acceleration standard ranges and thresholds, wherein the image feature data includes at least color features, texture features and shape features corresponding to different tool wear levels.

[0042] In addition, in the present invention, the input end of the tool breakage prediction module is communicatively connected to the image processing module and the database, and is used for comparison based on the image feature data extracted by the image processing module and combined with the standard tool related data pre-stored in the database, and based on the tool temperature, tool wear, tool-workpiece contact state, tool working path, tool movement speed and tool acceleration in the current working state, a comprehensive analysis is performed to determine whether there is a sign of tool breakage, and the judgment result is output to the downstream data processing and communication module; the input end of the data processing and communication module is communicatively connected to the tool breakage prediction module, and is used for receiving the analysis results of the tool breakage prediction module and performing classification processing, and transmitting the results to the CNC control system; the input end of the CNC control system is communicatively connected to the data processing and communication module, and is used for performing corresponding operations according to the analysis results, including but not limited to shutdown, alarm or adjustment of processing parameters.

[0043] In a preferred embodiment of the present invention, the tool breakage prediction module includes tool temperature prediction, and the specific operation process of tool temperature prediction includes: the industrial camera takes a tool image in real time during the tool working process, and the image is processed by the image processing module to obtain the current brightness characteristics, color characteristics, and texture characteristics of the tool, which are compared with the tool brightness characteristics, color characteristics, and texture characteristics pre-stored in the database, and based on the mapping relationship model between the image characteristics and the tool temperature pre-stored in the database, the tool temperature under the feature is obtained. When the temperature reaches the tool temperature threshold range set in the database, it means that there is a risk of tool breakage. The data processing and communication module sends a signal to the CNC control system, and the CNC control system executes the stop, alarm or other operations of the tool. The temperature of the tool will directly affect the service life of the tool. At the same time, if the temperature is too high during the working process of the tool, it will also bring the risk of tool breakage. Therefore, timely obtaining the tool temperature and comparing it with the tool temperature threshold can effectively predict the risk of tool breakage according to the tool working temperature and reduce the probability of tool breakage.

[0044] In a further preferred example, the construction of the mapping relationship model between image features and tool temperature includes: collecting image data during the tool working process, and extracting brightness features, color features, and texture features of the image data, and recording the actual tool temperature corresponding to each feature and storing it in a database, and setting a tool temperature threshold range in the database; based on the tool temperature data corresponding to the above brightness features, color features, and texture features, a linear regression statistical learning method is used to establish a mapping relationship model between tool temperature and image features, and it is pre-stored in a database, the model input is image features, and the output is temperature estimation, the model formula is: T = a·I1+b·I2+c·I3+d, where T is the estimated tool temperature, I1, I2 and I3 represent the brightness, color and texture feature values ​​extracted from the image, respectively, and a, b, c and d are model parameters learned through training data.

[0045] In a further preferred embodiment, the training process of a, b, c and d includes: the model parameters are usually randomly initialized at the beginning, or initialized according to a certain heuristic method. For each sample in the training data set, the input features are substituted into the model (i.e., the temperature estimation formula) to obtain a predicted temperature value, and the difference between the predicted temperature and the actual temperature is calculated using the loss function to obtain a loss value. According to the loss value, the gradient of the loss function to the model parameters is calculated by the chain rule, and the model parameters are updated according to the gradient using an optimization algorithm (gradient descent, stochastic gradient descent, Adam), and the above steps are repeated until a certain stopping criterion is met (such as reaching the maximum number of iterations, the loss value is lower than a certain threshold, and the performance of the validation set is no longer improved). Through this process, the model parameters will gradually be adjusted to minimize the difference between the predicted temperature and the actual temperature, so that the model can make more accurate predictions on unseen data. In the temperature estimation formula, a, b, c and d are learned through this training process.

[0046] In a preferred embodiment of the present invention, the tool breakage prediction module extracts the shape features of the tool while extracting the color features and texture features of the tool, so as to judge the wear condition of the tool. The specific operation process of judging the wear condition of the tool includes: storing the color features, texture features and shape features of the tool under different wear conditions in a database, and classifying the wear degree into levels of q, k1, k2, k3, kn, g, and g1, wherein q and g represent the excellent and poor states of the tool, k1, k2, k3, and kn are several levels between excellent and poor, and g1 represents that the tool is incomplete (broken), and the levels within a certain range are set as the state level that cannot continue to work; during the working process of the tool , the tool is photographed in real time, and the image processing module extracts the tool color features, texture features, and shape features, which are compared with the tool color features, texture features, and shape features pre-stored in the database to obtain the status level of the tool wear; when the comparison result reaches the preset level where it cannot continue to work, or the tool wear is in the g1 (breakage) state, the data processing and communication module outputs a signal to the CNC control system, and the CNC control system makes an output signal to stop working. The tool wear determines the accuracy of workpiece processing and the probability of tool breakage. By monitoring the tool wear in real time, it is possible to predict the tool breakage while improving the workpiece processing accuracy and reducing the probability of tool breakage.

[0047] In a preferred embodiment of the present invention, image segmentation is performed after the color features, shape features, and texture features of the tool are extracted, and the tool and workpiece areas in the image are segmented to monitor the contact state between the tool and the workpiece. The specific operation process includes: pre-storing in a database a standard range of contact area, contact length, and contact angle of the tool when processing the workpiece, and setting a threshold range for executing a CNC control system shutdown or alarm within the range; detecting the edge of the contact area between the tool and the workpiece by using a Canny or Sobel edge detection algorithm to obtain the shape and size of the contact area, and extracting features related to the contact state by calculating the number of pixels and geometric shapes, the features including the contact area, contact length, and contact angle; according to the extracted features, by calculating the pixels of the contact area The contact area is evaluated by the quantity or area size. The change of the contact area reflects the wear of the tool and the change of the cutting conditions. The continuity of the contact between the tool and the workpiece is evaluated by measuring the length of the contact area. The change of the contact length reflects the stability during the cutting process. The inclination of the contact between the tool and the workpiece is evaluated by calculating the angle of the contact area. The change of the contact angle reflects the change of the direction and size of the cutting force. By comparing the current contact state with the threshold range pre-stored in the database, it is detected whether there is an abnormal situation. The abnormal situation includes the reduction of the contact area, the change of the contact length, and the abnormal change of the contact angle. When the current contact state reaches the threshold range, it means that the current tool has a high risk of breakage, and the data processing and communication module outputs a signal to the CNC control system.

[0048] In a preferred embodiment of the present invention, the tool breakage prediction module also includes tool working path monitoring, and the specific operation process of tool working path monitoring includes: obtaining or presetting the path of the tool in the CNC control system from the CNC control system and storing it in the database, each path includes multiple points, each point has X, Y, Z coordinates and a timestamp, and presetting an X, Y, Z coordinate difference threshold range, which are stored in the database together; using the industrial camera to shoot and use the image processing module to obtain the X, Y, Z coordinates of the tool in real time, and obtain the current timestamp at the same time; using the Euclidean distance algorithm to search the database for the coordinate point of the corresponding time period on the preset path according to the current timestamp, and at the same time calculate the deviation between the coordinates obtained in real time and the coordinates of the corresponding time point in the database, and compare the deviation value with the threshold value to obtain two results (normal path, deviation path). The results are output to the CNC control system by the data processing and communication module, and the working path of the tool is generated by the CNC through external software, but there is a risk that the working path deviates from the original path due to factors such as cutting force and vibration during tool operation. When the working path deviates, there will be a risk of tool breakage. By real-time monitoring the working path of the tool, the workpiece processing accuracy is improved while reducing the risk of tool breakage caused by the deviation of the tool working path.

[0049] In a further preferred embodiment, the tool speed and acceleration are calculated by monitoring the tool working path. The specific process includes: firstly calculating the tool speed, extracting a time series of X, Y, and Z coordinate data from the path data obtained or preset in the CNC control system, each data point contains a coordinate value (X, Y, Z) and a corresponding timestamp, and the time interval between the data points remains constant; for each coordinate point (except the first one), the speed is obtained by calculating the displacement and time difference between it and the previous coordinate point, and the calculation formula is as follows: Among them, (x1, y1, z1) and (x2, y2, z2) are two consecutive coordinate points, Δd is the displacement value; continue to obtain the time difference (Δt) between two consecutive coordinate points; the moving speed v is equal to the displacement divided by the time difference, and the calculation formula is: In addition to the first two coordinate points, three consecutive coordinate points are obtained to calculate the tool acceleration. The speed difference Δv between two consecutive speeds is first calculated, and then the acceleration is calculated in combination with the time difference Δt. The standard values ​​of tool speed and acceleration are preset in the database, and a threshold is set at the same time. During the tool working process, the tool breakage prediction module continuously calculates the tool speed and tool acceleration, and compares them with the tool speed and tool acceleration thresholds stored in the database in real time. When the comparison result is within the threshold range, the signal is output to the CNC through the data processing and communication module. The tool speed and acceleration are one of the most direct factors causing tool breakage. By monitoring the path and coordinating the calculation at the same time, the tool movement speed and acceleration can be monitored in real time. When the movement speed and acceleration exceed the threshold, the CNC control system is notified in time to respond, thereby reducing the tool breakage caused by excessive movement speed and acceleration.

[0050] In a preferred embodiment of the present invention, the system also includes a tool setting monitoring module, which is communicatively connected to the image processing module and the database. The tool setting monitoring module uses the pictures taken by the industrial camera to cooperate with the image processing module to monitor whether the tool setting operation is performed before the tool works. The specific operation process includes: setting one or more fixed reference points on the CNC machine tool or the workpiece, using the image processing module to identify the position of the reference point after shooting with the industrial camera, setting a distance threshold between the tool and the reference point in the database, and calculating the distance between the tool and the reference point in real time, comparing the calculated distance with the threshold distance, and transmitting the comparison result to the CNC control system through the data processing and communication module. The tool setting monitoring can monitor the tool setting situation when the CNC is working, increase the probability of the tool being calibrated before work, and reduce the risk of tool breakage.

[0051] In a preferred embodiment of the present invention, the data processing and communication module is composed of a data processing unit and a communication unit. The data processing unit is used to process, calculate, and execute various data, and the communication unit is used to receive and transmit signals. The operation process of the data processing and communication module includes: the data processing unit receives the data generated by the tool breakage prediction module in real time, and classifies the data, and separately flashes and processes the tool temperature, tool wear condition, tool-workpiece contact state, tool working path, tool speed, and tool acceleration. At the same time, the database stores corresponding standard values ​​and threshold data for each category. When the data processing and communication module receives the data, it quickly matches two sets of corresponding data and sends them to the CNC control system and the tool breakage analysis module at the same time.

[0052] In a preferred embodiment of the present invention, the system further comprises a tool breakage analysis module, the input end of the tool breakage analysis module is connected to the data processing and communication module and the database for communication, and is used to generate a final tool breakage result. The specific operation process comprises: receiving the tool temperature, tool wear, contact state between the tool and the workpiece, tool working path, tool movement speed, tool acceleration and tool working state data output by the data processing and communication module, and using a neural network learning algorithm to train a model for recording and analyzing tool breakage factors, and the model is trained in large quantities through historical data; when a tool breakage result occurs, the tool breakage analysis module records the tool temperature, tool wear, contact state between the tool and the workpiece, tool working path, tool movement speed, tool acceleration and tool working state data at the time of tool breakage through the neural network learning model The tool diameter, tool speed, tool acceleration and tool setting data are collected together with the standard value and threshold value of the data stored in the database. Finally, the values ​​exceeding the threshold are arranged from large to small. The tool breakage factors are analyzed through the arrangement results. The factors include but are not limited to high tool temperature, severe wear, poor contact area / length / angle between the tool and the workpiece, inconsistent tool working path, too fast tool speed and acceleration, and failure to set the tool according to the standard. The tool breakage analysis module normalizes and classifies the various tool breakage prediction situations processed by the tool breakage monitoring module, predicts tool breakage in many aspects, and outputs instructions to the CNC control system in time after the tool breaks. This reduces the tool breakage and also reduces the loss in time when the tool breaks.

[0053] In a preferred embodiment of the present invention, the image processing module also includes a video recording unit, which is used to extract the video recorded by the industrial camera when the tool breakage occurs, and move the video time forward by 5-10 minutes to obtain a video segment of the tool breakage phenomenon. The video segment of the tool breakage phenomenon is finally transmitted to the tool breakage analysis module for storage. The video recording unit can record the video when the tool breakage occurs, and moving it forward by 5-10 minutes can facilitate professionals to judge the tool breakage factors by slowing down the overall video, so as to facilitate targeted improvements to the tool or CNC.

[0054] Example 3

[0055] On the basis of the above-mentioned embodiments 1 and 2, the present invention further provides a computer program product, including computer instructions, wherein the computer instructions instruct a computing device to execute the CNC tool breakage monitoring and control method as described in embodiment 1.

[0056] At the same time, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the CNC tool breakage monitoring and control method described in the above embodiment 1 is implemented.

[0057] In addition, the specific implementation of each step in the program can refer to the corresponding description of the corresponding steps and units in the above method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiment, which will not be repeated here.

[0058] The above-mentioned method and system according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as software or computer code that can be stored in a recording medium (such as CD ROM, RAM, floppy disk, USB disk, hard disk or magneto-optical disk), or can be implemented as computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and will be stored in a local recording medium, so that the method and system described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method and system described herein are implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method and system shown here.

[0059] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A CNC tool breakage monitoring and control system, comprising at least an image acquisition module, an image processing module, a database, a tool breakage prediction module, a data processing and communication module and a CNC control execution module, characterized in that: The image acquisition module is installed in the CNC machine tool or arranged on the tool holder of the CNC machine tool, and is used to continuously shoot the working state of the tool inside the CNC machine tool, obtain the working video data of the tool, and transmit the obtained video data to the downstream image processing module; The input end of the image processing module is communicatively connected to the image acquisition module, and is used to receive the tool working video data and extract the captured images in the video, and process the extracted captured images at the same time, wherein the image processing at least includes enhancement, edge processing and feature extraction, and the image feature data obtained after the image processing is transmitted to the downstream tool breakage prediction module; The database pre-stores standard tool working state related data, including image feature data, wear level data, a mapping relationship model between image features and tool temperature, and tool temperature under different working states, tool-workpiece contact state, tool working path, tool movement speed and standard ranges and thresholds of acceleration, wherein the image feature data at least includes color features, texture features and shape features corresponding to different tool wear levels; The input end of the tool breakage prediction module is communicatively connected to the image processing module and the database, and is used to perform comparison and analysis based on the image feature data extracted by the image processing module and combined with the standard tool related data pre-stored in the database, comprehensively judge whether there is a sign of tool breakage, and output the judgment result to the downstream data processing and communication module; The input end of the data processing and communication module is communicatively connected to the tool breakage prediction module, and is used to receive and classify the analysis results of the tool breakage prediction module, and transmit the results to the CNC control execution module; The input end of the CNC control execution module is communicatively connected to the data processing and communication module, and is used to generate control instructions according to the analysis results, and to make shutdown, alarm or adjustment of processing parameters based on the control instructions; Wherein, the tool breakage prediction module includes tool temperature prediction, and its specific operation process includes: during the tool working process, the industrial camera in the image acquisition module takes a tool image in real time, and the image is processed by the image processing module to obtain the current brightness feature, color feature, and texture feature of the tool and transmit it to the tool breakage prediction module, and the tool breakage prediction module compares the current image feature data obtained with the tool brightness feature, color feature, and texture feature pre-stored in the database, and obtains the tool temperature under the current image feature based on the mapping relationship model between the image feature and the tool temperature pre-stored in the database. When the tool temperature reaches the tool temperature threshold range set in the database, it means that there is a risk of tool breakage, and a signal is sent to the CNC control system through the data processing and communication module, and the CNC control system executes the stop, alarm or other operations of the tool; In addition, the mapping relationship model between the image features in the database and the tool temperature is constructed by: Collect image data during the tool working process, extract brightness features, color features, and texture features of the image data, record the actual tool temperature corresponding to each feature and store it in the database, and set the tool temperature threshold range in the database. Based on the tool temperature data corresponding to brightness features, color features, and texture features, a linear regression statistical learning method is used to establish the mapping relationship between tool temperature and image features, and it is pre-stored in the database. The model input is the image feature, and the output is the temperature estimate. The model formula is: In the formula, T is the estimated tool temperature, I 1. I 2 and I 3 represent the brightness, color and texture feature values ​​extracted from the image, respectively. a , b , c and d are the model parameters learned through training data.

2. The CNC tool breakage monitoring and control system according to claim 1, characterized in that: The tool breakage prediction module extracts the tool shape features while extracting the tool color features and texture features to determine the tool wear condition. The specific operation process of determining the tool wear condition includes: The color features, texture features and shape features of the tools under different wear conditions are stored in the database, and the wear degree is divided into levels of q, k1, k2, k3, kn, g, and g1, where q and g represent the good and bad tool states, k1, k2, k3, and kn are several levels between good and bad, and g1 represents the incomplete state of tool breakage, and the levels within a certain range are set as the state level that cannot continue to work; During the working process of the tool, the tool is photographed in real time, and the color features, texture features, and shape features of the tool are extracted by the image processing module, and compared with the color features, texture features, and shape features of the tool pre-stored in the database to obtain the wear status of the tool; When the comparison result reaches the preset level where the work cannot continue, or the tool wear condition is in the g1 state, the data processing and communication module outputs a signal to the CNC control system, and the CNC control system issues an output signal to stop working.

3. The CNC tool breakage monitoring and control system according to claim 2 is characterized in that: After extracting the tool color features, shape features, and texture features, image segmentation is performed to segment the tool and workpiece areas in the image to monitor the contact status between the tool and the workpiece. The specific operation process includes: Prestore in the database the standard ranges of the contact area, contact length and contact angle of the tool when machining the workpiece, and set the threshold range for executing the shutdown or alarm of the CNC control system within the range; The edge of the contact area between the tool and the workpiece is detected by an edge detection algorithm to obtain the shape and size of the contact area, and the features related to the contact state are extracted by calculating the number of pixels and geometric shapes, including the contact area, contact length, and contact angle; According to the extracted features, the size of the contact area is evaluated by calculating the number of pixels or the area size of the contact area, the continuity of the contact between the tool and the workpiece is evaluated by measuring the length of the contact area, and the inclination of the contact between the tool and the workpiece is evaluated by calculating the angle of the contact area; By comparing the current contact state with the threshold range stored in the database, it is detected whether there are abnormal conditions. Abnormal conditions include a decrease in contact area, a change in contact length, and an abnormal change in contact angle. When the current contact state reaches the threshold range, it means that the current tool has a high risk of breakage, and the data processing and communication module outputs a signal to the CNC control system.

4. The CNC tool breakage monitoring and control system according to claim 1, characterized in that: The tool breakage prediction module also includes tool working path monitoring, and its specific operation process includes: Get or preset the tool path in the CNC control system from the CNC control system and store it in the database. Each path contains multiple points, each point has x , y , z Coordinates and a timestamp, preset x , y , z The coordinate difference threshold range is stored in the database, and the image acquisition module is used to shoot the industrial camera and obtain the tool in real time using the image processing module. x , y , z Coordinates, and get the current timestamp; The Euclidean distance algorithm is used to search the coordinate points of the corresponding time period on the preset path in the database according to the current timestamp. At the same time, the deviation between the coordinates obtained in real time and the coordinates of the corresponding time point in the database is calculated. The deviation value is compared with the threshold to obtain two results: the normal path and the deviated path. The results are output to the CNC control system by the data processing and communication module.

5. The CNC tool breakage monitoring and control system according to claim 4, characterized in that: The tool moving speed and acceleration are calculated by monitoring the tool working path, and the specific process includes: First calculate the tool movement speed, extract a time series from the path data obtained or preset by the CNC control system x , y , z Coordinate data, each data point contains coordinate values ​​( x , y , z ) and corresponding timestamps, and the time interval between data points remains constant; For each coordinate point except the first one, the velocity is obtained by calculating the displacement and time difference between it and the previous coordinate point. The calculation formula is as follows: in,( x 1 、y 1 、z 1 )and( x 2 、y 2 、z 2 ) are two consecutive coordinate points, Δd is the displacement value; Continue to obtain the time difference Δ between two consecutive coordinate points t ; Movement Speed v It is equal to the displacement divided by the time difference, and its calculation formula is: ; In addition to the first two coordinate points, three consecutive coordinate points are obtained to calculate the tool acceleration. First, the speed difference Δ between two consecutive speeds is calculated. v , then combined with the time difference Δ t Calculating acceleration ; The standard values ​​of tool speed and acceleration are preset in the database, and a threshold is set at the same time. During the tool working process, the tool breakage prediction module continuously calculates the tool speed and tool acceleration, and compares them with the tool speed and tool acceleration thresholds stored in the database in real time. When the comparison result is within the threshold range, the signal is output to the CNC through the data processing and communication module.

6. The CNC tool breakage monitoring and control system according to claim 1, characterized in that: The system also includes a tool setting monitoring module, the input end of which is connected to the image processing module and the database. The tool setting monitoring module uses the image captured by the industrial camera in the image acquisition module to cooperate with the image processing module to monitor whether the tool is set before working. The specific operation process includes: One or more fixed reference points are set on the CNC machine tool or workpiece. After being photographed by the industrial camera in the image acquisition module, the image processing module is used to identify the position of the reference point, a distance threshold between the tool and the reference point is set in the database, and the distance between the tool and the reference point is calculated in real time. The calculated distance is compared with the threshold distance, and the comparison result is transmitted to the CNC control system through the data processing and communication module.

7. The CNC tool breakage monitoring and control system according to claim 6, characterized in that: The system also includes a tool breakage analysis module, the input end of which is connected to the data processing and communication module and the database for generating a final tool breakage result. The specific operation process includes: Receiving tool temperature, tool wear, tool-workpiece contact status, tool working path, tool speed, tool acceleration and tool working status data output by the data processing and communication module, and training a model using a neural network learning algorithm to record and analyze tool breakage factors, wherein the model is trained in large quantities through historical data; When tool breakage occurs, the tool breakage analysis module records the tool temperature, tool wear, contact status between tool and workpiece, tool working path, tool speed, tool acceleration and tool setting data at the time of tool breakage through the neural network learning model, and also records the standard value and threshold of the data stored in the database. Finally, the module arranges the data from large to small according to the value that exceeds the threshold. The tool breakage factors are analyzed through the arrangement results. The tool breakage factors include high tool temperature, severe wear, poor contact area / length / angle between tool and workpiece, inconsistent tool working path, too fast tool speed and acceleration, and failure to set the tool according to the standard.

8. The CNC tool breakage monitoring and control system according to claim 7, characterized in that: The data processing and communication module is composed of a data processing unit and a communication unit. The data processing unit is used to process, calculate, and execute various data, and the communication unit is used to receive and transmit signals. The operation process of the data processing and communication module includes: The data processing unit receives the data generated by the tool breakage prediction module in real time and classifies the data. It flashes and processes the tool temperature, tool wear, tool-workpiece contact status, tool working path, tool speed, and tool acceleration separately. At the same time, the database stores the corresponding standard value and threshold data for each category. When the data processing and communication module receives the data, it quickly matches the two corresponding groups of data and sends them to the CNC control system and the tool breakage analysis module at the same time.

9. The CNC tool breakage monitoring and control system according to claim 7, characterized in that: The image processing module also includes a video recording unit, which is used to extract the video recorded by the industrial camera when the knife breakage occurs, and move the video time forward 5-10 minutes to obtain a video segment of the knife breakage phenomenon. The video segment of the knife breakage phenomenon is finally transmitted to the knife breakage analysis module for storage.

Images