Tool condition analysis methods, devices, equipment and media

Abstract

This application provides a tool condition analysis method, apparatus, equipment, and medium, relating to the field of tool monitoring technology in CNC machining. In this application, firstly, a vibration data sequence generated by monitoring a target tool is acquired; secondly, each vibration data point in the vibration data sequence is mapped to form a vibration mapping image; then, feature distribution data reflecting the distribution of each feature point in the vibration mapping image is extracted from the vibration mapping image; finally, based on the feature distribution data and pre-determined feature distribution analysis rules, the target tool condition data is determined. Based on the above, this approach can improve upon the problems of low accuracy in tool condition analysis results in existing technologies or the limitations in applicable scenarios due to reliance on video and image monitoring.

Description

Technical Field

[0001] This application relates to the field of tool monitoring technology in CNC machining, and more specifically, to a tool condition analysis method, device, equipment, and medium. Background Technology

[0002] CNC machining is an indispensable part of modern manufacturing, and its accuracy and efficiency largely determine product quality and production efficiency. As a key component of CNC machining, the performance and condition of cutting tools directly affect machining results and quality. Tool abnormalities, such as tool wear and breakage, can reduce machining accuracy or even fail to meet machining requirements, increasing production costs and leading to production accidents. Therefore, research on tool abnormality identification and analysis technology is of great significance for improving the quality and efficiency of CNC machining. However, current technologies for tool condition analysis lack accuracy, or rather, rely heavily on video and image monitoring, limiting their applicability. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a tool condition analysis method, apparatus, device and medium to improve the problem of low accuracy of tool condition analysis results in the prior art or the problem of limited applicability due to reliance on video and image monitoring.

[0004] To achieve the above objectives, this application adopts the following technical solution:

[0005] A tool condition analysis method, comprising:

[0006] A vibration data sequence generated by monitoring the target tool is obtained, wherein the vibration data sequence includes multiple vibration data corresponding to multiple time points;

[0007] The vibration data in the vibration data sequence is mapped to form a vibration mapping image, wherein the distribution of each feature point in the vibration mapping image is used to reflect the distribution of each vibration data in the vibration data sequence, and each feature point corresponds one-to-one with each vibration data.

[0008] Extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image;

[0009] Based on the feature distribution data and the predetermined feature distribution analysis rules, the target tool state data is determined, wherein the target tool state data is used to reflect the state of the target tool.

[0010] In a preferred embodiment of this application, the step of mapping each vibration data point in the vibration data sequence to form a vibration mapping image in the above-described tool condition analysis method includes:

[0011] Determine the initial mapping image;

[0012] Each vibration data point in the vibration data sequence is determined to have a first coordinate value and a second coordinate value in the initial mapping image, wherein the first coordinate value is related to the resolution of the corresponding vibration data and the initial mapping image, and the second coordinate value is related to the sequence position of the corresponding vibration data in the vibration data sequence.

[0013] Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a vibration mapping image.

[0014] In a preferred embodiment of this application, in the above-described tool condition analysis method, the step of determining the first coordinate value and the second coordinate value of each vibration data point in the vibration data sequence in the initial mapping image includes:

[0015] The center point of the image is determined in the initial mapped image, wherein the resolution of the initial mapped image in the row direction is equal to the resolution in the column direction;

[0016] The center point of the image is determined as the pole, and the straight line that passes through the center point of the image and extends along the row direction is determined as the polar axis to construct a polar coordinate system.

[0017] Each vibration data point in the vibration data sequence is traversed sequentially to form the currently traversed vibration data.

[0018] Based on the currently traversed vibration data, a first coordinate value is determined, and based on the sequence position of the currently traversed vibration data in the vibration data sequence, a second coordinate value is determined. The first coordinate value is used to reflect the polar radius of the currently traversed vibration data in the polar coordinate system, and the second coordinate value is used to reflect the polar angle of the currently traversed vibration data in the polar coordinate system.

[0019] In a preferred embodiment of this application, in the above-described tool condition analysis method, the step of determining a first coordinate value based on the currently traversed vibration data, and determining a second coordinate value based on the sequence position of the currently traversed vibration data in the vibration data sequence, includes:

[0020] Based on the target mapping parameters, the currently traversed vibration data is mapped to form vibration data mapping values, and the first coordinate value is determined based on the vibration data mapping values. The target mapping parameters are determined based on the ratio between the vibration data with the maximum value in the vibration data sequence and half of the resolution in the row direction.

[0021] If the vibration data currently being traversed belongs to the first vibration data in the vibration data sequence, then the second coordinate value of the vibration data currently being traversed is determined to be 0 degrees.

[0022] If the vibration data currently being traversed does not belong to the first vibration data in the vibration data sequence, then the second coordinate value of the previous vibration data and a predetermined angle threshold are summed to form the second coordinate value of the vibration data currently being traversed. The angle threshold is related to the spindle speed of the target tool and the acquisition frequency of the vibration data sequence.

[0023] In a preferred embodiment of this application, in the above-described tool condition analysis method, the step of mapping each vibration data point in the vibration data sequence to the initial mapping image based on the first coordinate value and the second coordinate value to form a vibration mapping image includes:

[0024] Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a candidate mapping image, wherein the feature points in the candidate mapping image correspond one-to-one with the vibration data;

[0025] The stable signal feature regions in the candidate mapping image are filtered out to remove the white noise corresponding to the cutting and non-cutting states of the target tool, thus obtaining the vibration mapping image.

[0026] In a preferred embodiment of this application, the step of filtering out stable signal feature regions in the candidate mapping image to remove white noise corresponding to the cutting and non-cutting states of the target tool, thereby obtaining a vibration mapping image, in the above-described tool state analysis method includes:

[0027] Using the center of the candidate mapping image as the center of a circle, multiple concentric circles are determined based on multiple radius values ​​that increase sequentially from 0 to the target value. The radius value with the maximum value is equal to half the resolution of the candidate mapping image in the row direction. The first coordinate value and the second coordinate value are used to characterize the polar radius and polar angle of the corresponding feature points, respectively, and the resolution of the candidate mapping image in the row direction is equal to the resolution in the column direction.

[0028] For each of the plurality of concentric circles, the number of feature points in the candidate mapping image that pass through the circumference of the concentric circle is determined, and the number of feature points of the concentric circle is obtained.

[0029] Curve fitting is performed using the radius of the concentric circles and the number of feature points as the x and y axes, respectively. In the fitted curve, it is determined whether the trend of the curve before the point where the number of feature points has the maximum value is monotonically increasing.

[0030] When the trend of the curve before the point with the maximum number of feature points is monotonically increasing, each feature point surrounded by the concentric circles with the maximum number of feature points in the candidate mapping image is filtered out to form a vibration mapping image.

[0031] In a preferred embodiment of this application, in the above-described tool condition analysis method, the step of extracting feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image includes:

[0032] Multiple straight lines passing through the center of the image are determined from the vibration mapping image, wherein the vibration mapping image is an image formed based on feature points formed by polar coordinate mapping of each vibration data in the vibration data sequence;

[0033] For each of the multiple straight lines, the number of feature points passing through that straight line in the vibration mapping image is determined, forming the number of feature points corresponding to that straight line;

[0034] The line corresponding to the number of feature points with the maximum value is determined, and based on the line, the vibration mapping image is segmented to form at least two segmented regions;

[0035] Based on the at least two segmented regions and the number of feature points in each segmented region, feature distribution data is determined.

[0036] In a preferred embodiment of this application, the step of determining multiple straight lines passing through the center of the image from the vibration mapping image in the above-described tool condition analysis method includes:

[0037] Determine any straight line passing through the center of the vibration mapping image;

[0038] Starting from any one of the straight lines, each time the target angle is reached, a new straight line passing through the center of the image is determined in the vibration mapping image to form multiple straight lines.

[0039] In a preferred embodiment of this application, the step of determining the target tool state data based on the feature distribution data and predetermined feature distribution analysis rules in the above-described tool state analysis method includes:

[0040] Determine whether the number of segmented regions in the feature distribution data is the same as the number of target teeth in the feature distribution analysis rules, wherein the number of target teeth is equal to the number of cutting teeth of the target tool, and the segmented regions are formed by region segmentation based on the distribution of each feature point in the vibration mapping image;

[0041] If the number of segmented regions is not equal to the target number of teeth, then target tool state data for characterizing tool usage errors is obtained;

[0042] If the number of segmented regions is equal to the number of target teeth, then target tool state data for characterizing tooth consistency is obtained based on the consistency between the number of feature points in each segmented region. The higher the consistency between the number of feature points in each segmented region, the higher the consistency of the amount of cutting by each tooth of the target tool.

[0043] In a preferred embodiment of this application, the step of acquiring the vibration data sequence formed by monitoring the target tool in the above-described tool condition analysis method includes:

[0044] Obtain the raw sequence of vibration data generated by monitoring the target tool;

[0045] The original sequence of vibration data is transformed in the frequency domain to form a vibration spectrum.

[0046] The signals corresponding to the frequency band regions in the high-frequency band of the vibration spectrum where the energy exceeds the energy threshold are filtered, and the filtered data is converted back to the time domain to form a vibration data sequence.

[0047] This application also provides a tool condition analysis device, including:

[0048] The vibration data acquisition module is used to acquire a vibration data sequence formed by monitoring the target tool, wherein the vibration data sequence includes multiple vibration data corresponding to multiple time points;

[0049] The vibration data mapping module is used to map each vibration data in the vibration data sequence to form a vibration mapping image. The distribution of each feature point in the vibration mapping image is used to reflect the distribution of each vibration data in the vibration data sequence, and there is a one-to-one correspondence between each feature point and each vibration data.

[0050] The feature distribution extraction module is used to extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image;

[0051] The tool condition analysis module is used to determine the target tool condition data based on the feature distribution data and the pre-determined feature distribution analysis rules, wherein the target tool condition data is used to reflect the condition of the target tool.

[0052] Based on the above, this application also provides an electronic device, including:

[0053] Memory, used to store computer programs;

[0054] A processor connected to the memory is used to execute the computer program stored in the memory to implement the tool condition analysis method described above.

[0055] Based on the above, this application also provides a computer-readable storage medium storing a computer program that executes the various steps of the tool condition analysis method described above when the computer program is run.

[0056] The tool condition analysis method, apparatus, equipment, and medium provided in this application first acquire a vibration data sequence formed by monitoring the target tool; second, map each vibration data point in the vibration data sequence to form a vibration mapping image; then, extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image; finally, determine the target tool condition data based on the feature distribution data and pre-determined feature distribution analysis rules. Based on the above, by utilizing vibration sensors to collect data information during tool processing, i.e., vibration data sequences, and combining them with image mapping processing technology, time-series data can be mapped into images, enabling effective extraction of tool features from the images. This improves the accuracy of tool condition identification and solves the problems of low accuracy and complex physical operations in existing technologies. Furthermore, the entire process requires no machine downtime, ensuring processing efficiency. Secondly, this solution is unaffected by factors such as processing materials and processing methods, possessing high versatility and can be widely applied to various CNC machining scenarios, effectively solving the problem of poor versatility in existing technologies. Since no machine downtime is required for inspection, an early warning can be issued immediately upon detection of anomalies, preventing a decline in processing quality or production accidents, and significantly improving production efficiency and safety. Based on this, the solution proposed in this application can address the problems of low accuracy in tool condition analysis results or the limitations in applicability due to reliance on video and image monitoring in existing technologies. Attached Figure Description

[0057] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings.

[0058] Figure 1A structural block diagram of an electronic device provided in an embodiment of this application.

[0059] Figure 2 This is a flowchart illustrating the tool state analysis method provided in an embodiment of this application.

[0060] Figure 3 This is a schematic diagram of the image Simg provided in the embodiments of this application, showing the angle as zero degrees and the direction of angle increase.

[0061] Figure 4 The image obtained by the mapping transformation processing provided in the embodiments of this application.

[0062] Figure 5 The Num that varies with i provided in the embodiments of this application i The curve showing the changing pattern of the value.

[0063] Figure 6 This is a block diagram of the tool condition analysis device provided in an embodiment of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0065] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0066] like Figure 1 As shown in the figure, an embodiment of this application provides an electronic device. The electronic device may include a memory, a processor, and a tool status analysis device.

[0067] Specifically, the memory and the processor are electrically connected directly or indirectly to enable data transmission or interaction. For example, the memory and the processor can be electrically connected via one or more communication buses or signal lines. The tool condition analysis device includes at least one software functional module stored in the memory in the form of software or firmware. The processor is used to execute executable computer programs stored in the memory, such as the software functional modules and computer programs included in the tool condition analysis device, to implement the tool condition analysis method provided in the embodiments of this application.

[0068] Optionally, the memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0069] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0070] Understandable. Figure 1 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown may include, for example, a communication unit for exchanging information with other devices, such as sensors.

[0071] Combination Figure 2 This application also provides a tool condition analysis method applicable to the aforementioned electronic device. The method steps defined in the relevant process of the tool condition analysis method can be implemented by the electronic device. The following will describe... Figure 2 The specific process shown will be explained in detail.

[0072] Step S110: Obtain the vibration data sequence generated by monitoring the target tool.

[0073] In this embodiment of the application, the electronic device can acquire a vibration data sequence formed by monitoring the target tool. The vibration data sequence includes multiple vibration data corresponding to multiple time nodes, such as vibration data corresponding to the first time node, vibration data corresponding to the second time node, vibration data corresponding to the third time node, vibration data corresponding to the fourth time node, vibration data corresponding to the fifth time node, etc.

[0074] Step S120: Map each vibration data in the vibration data sequence to form a vibration mapping image.

[0075] In this embodiment, after acquiring the vibration data sequence, the electronic device can map each vibration data point in the vibration data sequence to form a vibration mapping image. The distribution of feature points in the vibration mapping image reflects the distribution of each vibration data point in the vibration data sequence, and each feature point corresponds one-to-one with each vibration data point. After mapping, one vibration data point can form one feature point. For example, the vibration data corresponding to the first time node can be mapped to one feature point, the vibration data corresponding to the second time node can be mapped to one feature point, the vibration data corresponding to the third time node can be mapped to one feature point, the vibration data corresponding to the fourth time node can be mapped to one feature point, and the vibration data corresponding to the fifth time node can be mapped to one feature point.

[0076] Step S130: Extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image.

[0077] In this embodiment of the application, when forming the vibration mapping image, the electronic device can extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image, such as the number of feature points distributed in each region of the image.

[0078] Step S140: Based on the feature distribution data and the predetermined feature distribution analysis rules, determine the target tool state data.

[0079] In this embodiment, after extracting the feature distribution data, the electronic device can determine the target tool state data based on the feature distribution data and a pre-determined feature distribution analysis rule. The target tool state data reflects the state of the target tool. For example, the feature distribution analysis rule can differ depending on the type of state to be analyzed. For instance, if it is necessary to analyze the consistency of multiple (e.g., two) cutting teeth, the feature distribution analysis rule can compare the consistency of the number of feature points distributed in each region of the feature distribution data.

[0080] Based on the above, by utilizing vibration sensors to collect data information during tool processing—namely, vibration data sequences—and combining this with image mapping processing technology, the time-series data can be mapped into images. This allows for the effective extraction of tool features from the images, thereby improving the accuracy of tool condition recognition. This solves the problems of low accuracy and complex physical operations in existing technologies, while ensuring processing efficiency by eliminating the need for machine downtime. Secondly, this solution is unaffected by factors such as processing materials and methods, possessing high versatility and applicable to various CNC machining scenarios, effectively addressing the poor versatility of existing technologies. Since no machine downtime is required for detection, an early warning can be issued immediately upon detecting anomalies, preventing degradation in processing quality or production accidents, significantly improving production efficiency and safety. Therefore, the solution proposed in this application can improve upon the problems of low accuracy in tool condition analysis results or the limitations in applicability due to reliance on video and image monitoring in existing technologies.

[0081] Firstly, regarding step S110, it should be noted that the specific method for obtaining the vibration data sequence formed by monitoring the target tool is not limited and can be selected according to actual needs.

[0082] For example, the raw vibration data sequence generated by monitoring the target tool can be directly obtained, and then this raw vibration data sequence can be directly determined as the vibration data sequence. In this way, the efficiency of condition analysis can be improved to a certain extent.

[0083] For example, in another alternative implementation, in order to improve the reliability of the obtained vibration data sequence, the above step S110 may further include steps S111, S112 and S113, the specific contents of each step are as follows.

[0084] Step S111: Obtain the original sequence of vibration data generated by monitoring the target tool.

[0085] In this embodiment, the raw vibration data sequence generated by monitoring the target tool can be obtained. It should be noted that the raw vibration data sequence generated by the vibration sensor monitoring the target tool can be obtained in real time, or a pre-acquired and stored raw vibration data sequence can be obtained from a database.

[0086] Step S112: The original sequence of vibration data is converted into a frequency domain to form a vibration spectrum.

[0087] In this embodiment of the application, after obtaining the original vibration data sequence, the original vibration data sequence can be converted into a frequency domain to form a vibration spectrum. That is, the original vibration data sequence in the time domain is converted into a vibration spectrum in the frequency domain.

[0088] Step S113: The signal corresponding to the frequency band region in the high-frequency band of the vibration spectrum where the energy exceeds the energy threshold is filtered, and the filtered data is converted back to the time domain to form a vibration data sequence.

[0089] In this embodiment, after forming the vibration spectrum, the signals corresponding to the frequency band regions in the high-frequency band of the vibration spectrum where the energy exceeds an energy threshold (the specific value of the energy threshold can be configured according to actual needs, i.e., used to determine whether the energy is large) can be filtered, and the filtered data can be converted back to the time domain to form a vibration data sequence. In other words, the original vibration data sequence can be filtered so that interference information can be removed or suppressed to a certain extent, thereby obtaining a vibration data sequence with relatively higher reliability.

[0090] Alternatively, in other embodiments, after obtaining the vibration spectrum, the frequency band region exceeding the energy threshold can be determined first. Then, based on the frequency band region, a bandpass filtering method can be selected to filter the original vibration data sequence All(Vib) in the time domain to form the filtered data, i.e., the vibration data sequence, which can be represented by Pro(Vib).

[0091] For example, in a specific application scenario:

[0092] First, all machining steps can be decomposed according to the CNC machining program of the part to be machined. From the decomposed machining step data, it can be determined that there are machining steps that use two-tooth milling cutters, denoted as T(a,Zi). Here, T represents the set of all machining steps included in the two-tooth milling machining of the part, a represents the number of machining steps that include the two-tooth milling process, i.e. how many two-tooth milling cutters there are, Z represents the number of teeth, Z has a value of 2, and i represents the specified machining step, and i∈[1,a].

[0093] Secondly, a CNC machining program that meets the tool error prevention analysis was designed and obtained. Machining based on this program can obtain vibration data that characterizes the tool teeth information, guiding the machining of the part. For any two-tooth end mill i, the machining path is generated using CAM computer-aided manufacturing software and simulated to ensure that no spatial collisions occur, thus ensuring the correctness and integrity of the program. At the same time, the spindle speed Speed ​​at the start of machining is strictly controlled to be less than the set threshold Sthreshold. The tool feed rate, depth of cut, and other data are also set to values ​​that meet normal milling requirements. It should be noted that the setting of the speed Speed ​​is very important, as it is the key to determining whether the collected vibration data can reflect the number of tool teeth. Therefore, the tool speed Speed ​​during machining must not exceed the corresponding set value.

[0094] Then, prepare the workpiece for clamping and simultaneously replace the cutting tools.

[0095] Next, machining and data acquisition preparation begin. During machining, the toolpath is executed according to the designed program, and the corresponding part is milled based on the parameters set in the designed program. Data acquisition relies on pre-installed sensors to acquire corresponding data (Data). Data may include: spindle speed (Speed), power (Pow), vibration data (Vib), and tooth count (Teech), among which the acquired vibration data (Vib) is the core. The real-time acquired data set is defined as Data (Speed, Pow, Vib, Teech).

[0096] Furthermore, ensuring the acquired data meets the set format is crucial for providing numerical support for subsequent tool tooth count analysis. This is a prerequisite for accurately analyzing tool teeth without shutting down the machine. The specific strategy is as follows: First, a data acquisition mode is set up, with data acquisition completed at the machine tool end and data analysis performed on the host computer (a dedicated computer for tool error prevention). The machine tool end sends data, and the host computer end receives data, using a publish-subscribe model. First, data publishing objects and data subscription objects are created, and data publishing and subscription are bound to the same IP address and port. To ensure data real-time performance, the subscription end (host computer end) receives data in a non-waiting mode. According to the error handling and resource management, when the receiving end cannot obtain data, it handles the exception by checking whether the connection is interrupted, releases the corresponding memory resources, and reconnects to ensure normal data acquisition. The entire data (Speed, Pow, Vib, Teech) is packaged into key-value pairs. The format of sending a data item is {"Time": "XX; "Speed": "XX"; "Vib": "XX"; "Teech": "XX"}, and includes a timestamp to ensure data continuity. Based on the design pattern, the data sending and receiving ends of the entire method are independent and do not affect each other.

[0097] Finally, the collected data is filtered, that is, the vibration data (Vib) in the collected Data is processed to reduce high-frequency information and noise components, thereby improving the effect of feature mapping in the next step. The specific process is as follows: The host computer obtains each piece of data {"Time": "XX"; "Speed": "XX"; "Vib": "XX"; "Teech": "XX"}, and parses Time, Speed, Vib, and Teech based on key-value pairs. Let the time interval of each data transmission be t, and the unit time length of data analysis be T. The Vib in each data is concatenated to obtain the complete vibration data X within the unit time. Vib (m), m = 0, 1, 2, ..., N-1, where m is the data sequence number, N = T / t is the data sequence length, and the data is concatenated sequentially from beginning to end based on a time interval t; for X vib (m) is transformed to obtain the frequency sequence of the vibration data, where n is the frequency sequence number of the data. The corresponding transformation formula is:

[0098] ;

[0099] in, The transformation operator sequence is defined as follows: j is a unit complex number. It has periodicity. , This can be expressed as a formula:

[0100] ;

[0101] Where 2r = n, after completing the transformation and processing of All(Vib) data, the frequency band characteristics of All(Vib) are analyzed, high-frequency noise is filtered out, and mid- and low-frequency noise is left, which can reflect the characteristic information of tool cutting. The filtering process is as follows: based on the above-processed data All(Vib), the spectrum curve is analyzed, the frequency band region with high energy in the high-frequency band is determined, and the bandpass filtering method is selected to filter All(Vib). The filtering frequency band is selected to be the frequency band region with high energy in the high-frequency band, so that the corresponding signal is filtered. Let the processed data be represented by Pro(Vib).

[0102] Secondly, regarding step S120, it should be noted that the specific method of mapping each vibration data in the vibration data sequence is not limited and can be selected according to actual needs.

[0103] For example, in an alternative implementation, in order to ensure that each vibration data in the vibration data sequence can be reliably mapped to the vibration mapping image for representation, the above step S120 may further include steps S121, S122 and S123, as detailed below.

[0104] Step S121: Determine the initial mapping image.

[0105] In the embodiments of this application, an initial mapping image can be determined. For example, the initial mapping image can be a blank image, such as each pixel being white.

[0106] Step S122: Determine the first coordinate value and the second coordinate value of each vibration data in the vibration data sequence in the initial mapping image.

[0107] In this embodiment, a first coordinate value and a second coordinate value can be determined for each vibration data point in the vibration data sequence within the initial mapping image. The first coordinate value is related to the resolution of the corresponding vibration data and the initial mapping image, while the second coordinate value is related to the sequence position of the corresponding vibration data point in the vibration data sequence. In other words, the first coordinate value can be determined based on the resolution of the vibration data and the initial mapping image, and the second coordinate value can be determined based on the sequence position of the vibration data point in the vibration data sequence. Thus, the first coordinate value and the second coordinate value corresponding to each vibration data point can be obtained.

[0108] Step S123: Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a vibration mapping image.

[0109] In this embodiment, after forming the first coordinate value and the second coordinate value corresponding to each vibration data point, each vibration data point in the vibration data sequence can be mapped onto the initial mapping image based on the first coordinate value and the second coordinate value to form a vibration mapping image. For example, based on the first coordinate value and the second coordinate value corresponding to each vibration data point, a corresponding feature point can be determined in the initial mapping image. For instance, each pixel corresponding to the first coordinate value and the second coordinate value corresponding to each vibration data point in the initial mapping image can be determined as a feature point, and the pixel can be changed from white to black.

[0110] It is understood that in step S122 above, the specific method of determining the first coordinate value and the second coordinate value of each vibration data in the vibration data sequence in the initial mapping image is not limited. For example, in an alternative embodiment, in order to effectively characterize the distribution of the corresponding vibration data through the first coordinate value and the second coordinate value, step S122 above may further include steps S122a, S122b, S122c and S122d, the specific contents of each step are as follows.

[0111] Step S122a: Determine the center point of the image in the initial mapped image.

[0112] In this embodiment of the application, the center point of the image can be determined in the initial mapped image, wherein the resolution of the initial mapped image in the row direction is equal to the resolution in the column direction, that is, the number of pixels in the row direction is equal to the number of pixels in the column direction.

[0113] Step S122b: The center point of the image is determined as the pole, and the straight line passing through the center point of the image and extending along the row direction is determined as the polar axis, so as to construct a polar coordinate system.

[0114] In this embodiment of the application, after determining the center point of the image, the center point of the image can be determined as the pole, and the straight line that passes through the center point of the image and extends along the row direction can be determined as the polar axis to construct a polar coordinate system, which facilitates polar coordinate mapping.

[0115] Step S122c: Iterate through each vibration data in the vibration data sequence in sequence to form the vibration data currently being iterated.

[0116] In this embodiment of the application, after the polar coordinate system is constructed, each vibration data in the vibration data sequence can be traversed sequentially to form the currently traversed vibration data. For example, the first traversed vibration data is the first vibration data in the vibration data sequence, the second traversed vibration data is the second vibration data in the vibration data sequence, and the last traversed vibration data is the last vibration data in the vibration data sequence.

[0117] Step S122d: Based on the currently traversed vibration data, determine the first coordinate value, and based on the sequence position of the currently traversed vibration data in the vibration data sequence, determine the second coordinate value.

[0118] In this embodiment, after forming the currently traversed vibration data, a first coordinate value can be determined based on the currently traversed vibration data, and a second coordinate value can be determined based on the sequence position of the currently traversed vibration data in the vibration data sequence. The first coordinate value reflects the polar radius (the distance between a feature point and a pole) of the currently traversed vibration data in the polar coordinate system, and the second coordinate value reflects the polar angle (the angle between the line connecting the feature point and the pole and the polar axis) of the currently traversed vibration data in the polar coordinate system. Thus, each vibration data point in the vibration data sequence can be mapped to a polar coordinate feature point through polar coordinate transformation.

[0119] It is understood that the method of determining the mapping of the two polar coordinates in step S122d above is not limited. For example, in an alternative implementation, in order to ensure that the vibration data can be effectively represented in the initial mapping image, step S122d above may further include the following steps, such as step d1, step d2 and step d3.

[0120] Step d1: Based on the target mapping parameters, the currently traversed vibration data is mapped to form vibration data mapping values, and the first coordinate value is determined based on the vibration data mapping values.

[0121] In this embodiment, the currently traversed vibration data can be mapped based on a target mapping parameter to form a vibration data mapping value. A first coordinate value is then determined based on this vibration data mapping value (for example, the vibration data mapping value can be used as the first coordinate value). The target mapping parameter is determined based on the ratio between the vibration data with the maximum value in the vibration data sequence and half the resolution in the row direction. For example, the target mapping parameter is equal to the ratio between the vibration data with the maximum value in the vibration data sequence and half the resolution in the row direction. For instance, the first coordinate value corresponding to the vibration data with the maximum value is equal to half the resolution in the row direction. Furthermore, the first coordinate value corresponding to vibration data equal to 0 is also equal to 0, i.e., it is located at an extreme point. In other words, the larger the vibration data, the larger the corresponding first coordinate value and the farther away from the extreme point; conversely, the smaller the vibration data, the smaller the corresponding first coordinate value and the closer to the extreme point.

[0122] Step d2: If the vibration data currently being traversed belongs to the first vibration data in the vibration data sequence, then the second coordinate value of the vibration data currently being traversed is determined to be 0 degrees.

[0123] In this embodiment of the application, if the second coordinate value of the currently traversed vibration data belongs to the first vibration data in the vibration data sequence, then the second coordinate value of the currently traversed vibration data is determined to be 0 degrees.

[0124] Step d3: If the vibration data currently being traversed does not belong to the first vibration data in the vibration data sequence, then the second coordinate value of the previous vibration data and the predetermined angle threshold are summed to form the second coordinate value of the vibration data currently being traversed.

[0125] In this embodiment, for the second coordinate value of the currently traversed vibration data, if the currently traversed vibration data does not belong to the first vibration data in the vibration data sequence, the second coordinate value of the previous vibration data is summed with a predetermined angle threshold to form the second coordinate value of the currently traversed vibration data. For example, the second coordinate value of the first vibration data is 0 degrees, the second coordinate value of the second vibration data is the angle threshold, the second coordinate value of the third vibration data is twice the angle threshold, the second coordinate value of the fourth vibration data is three times the angle threshold, the second coordinate value of the fifth vibration data is four times the angle threshold, and the second coordinate value of the Xth vibration data is (X-1) times the angle threshold. The angle threshold is related to the spindle speed of the target tool and the acquisition frequency of the vibration data sequence.

[0126] For example, the angle threshold can be obtained based on the following formula:

[0127] u angle =360 / ((1 / (Speed / 60))*V fre );

[0128] Among them, u angle V represents the angle threshold, Speed ​​represents the spindle speed, and V represents the spindle speed. fre Indicates the sampling frequency.

[0129] It is understood that the specific method of forming the vibration mapping image in step S123 above is not limited. For example, in an alternative embodiment, in order to improve the reliability of the formed vibration mapping image, step S123 above may further include steps S123a and S123b, the specific contents of each step are as follows.

[0130] Step S123a: Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a candidate mapping image.

[0131] In this embodiment, each vibration data point in the vibration data sequence can be mapped to the initial mapping image based on the first coordinate value and the second coordinate value, forming a candidate mapping image. The feature points in the candidate mapping image correspond one-to-one with the vibration data points. For example, for each vibration data point, the pixel corresponding to the first and second coordinate values ​​in the initial mapping image can be determined as a feature point; specifically, the pixel can be changed from white to black. Based on this, after mapping the corresponding feature points for each vibration data point, a candidate mapping image can be formed.

[0132] Step S123b: Filter out the stable signal feature regions in the candidate mapping image to remove the white noise corresponding to the cutting and non-cutting states of the target tool, and obtain the vibration mapping image.

[0133] In this embodiment of the application, after the candidate mapping image is formed, the stable signal feature regions in the candidate mapping image can be filtered out to remove the white noise corresponding to the cutting and non-cutting states of the target tool, thereby obtaining a vibration mapping image.

[0134] It is understood that in step S123b above, the specific method of filtering out the white noise corresponding to the cutting and non-cutting states of the target tool is not limited. For example, in an alternative embodiment, in order to fully filter out the white noise, step S123b above may further include steps b1, b2, b3 and b4, the specific contents of which are as follows.

[0135] Step b1: Using the center of the candidate mapped image as the center of the circle, and based on multiple radius values ​​that increase sequentially from 0 to the target value, determine multiple concentric circles.

[0136] In this embodiment, the center of the candidate mapping image can be used as the center of a circle, and multiple concentric circles can be determined based on multiple radius values ​​that increase sequentially from 0 to the target value. The radius value with the largest value is equal to half the resolution of the candidate mapping image in the row direction. The first coordinate value and the second coordinate value are used to characterize the polar radius and polar angle of the corresponding feature point, respectively, and the resolution of the candidate mapping image in the row direction is equal to the resolution in the column direction. It should be noted that the difference between two adjacent radius values ​​(i.e., the magnitude of the increase) can be related to the required filtering accuracy; the smaller the difference, the higher the accuracy. The number of concentric circles is also related to the required filtering accuracy; the larger the number, the higher the accuracy.

[0137] Step b2: For each of the plurality of concentric circles, determine the number of feature points in the candidate mapping image that pass through the circumference of the concentric circle, and obtain the number of feature points of the concentric circle.

[0138] In this embodiment of the application, after forming the plurality of concentric circles, for each of the plurality of concentric circles, the number of feature points in the candidate mapping image that pass through the circumference of the concentric circle can be determined, and the number of feature points of the concentric circle can be obtained.

[0139] Step b3: Perform curve fitting using the radius of the concentric circles and the number of feature points as the x and y coordinates, and determine whether the trend of the curve before the point with the maximum number of feature points is monotonically increasing.

[0140] In this embodiment of the application, after obtaining the number of feature points for each concentric circle, curve fitting can be performed using the radius value of the concentric circle and the number of feature points as the abscissa and ordinate (e.g., the radius value as the abscissa and the number of feature points as the ordinate). In the fitted curve, it is determined whether the trend of the curve before the point with the maximum number of feature points (i.e., the curve to the left of the point with the maximum number of feature points, or the curve corresponding to each point with a smaller radius value) is monotonically increasing.

[0141] Step b4: When the trend of the curve before the point with the maximum number of feature points is monotonically increasing, filter out each feature point surrounded by the concentric circle with the maximum number of feature points in the candidate mapping image to form a vibration mapping image.

[0142] In this embodiment, when the trend of the curve preceding the point with the maximum number of feature points is monotonically increasing, each feature point enclosed by the concentric circles with the maximum number of feature points in the candidate mapping image can be filtered out (for example, black feature points can be updated to white), forming a vibration mapping image. It should be noted that, in an alternative implementation, when the trend of the curve preceding the point with the maximum number of feature points is not monotonically increasing, it can be determined whether the trend of the curve preceding the point with the second largest number of feature points is monotonically increasing. If the trend of the curve preceding the point with the second largest number of feature points is monotonically increasing, each feature point enclosed by the concentric circles with the second largest number of feature points in the candidate mapping image can be filtered out, forming a vibration mapping image. When the trend of the curve preceding the point with the second largest number of feature points is not monotonically increasing, the same processing logic can be applied to the point with the third largest number of feature points. This determines whether the trend of the curve preceding the point with the third largest number of feature points is monotonically increasing. If the trend of the curve preceding the point with the third largest number of feature points is monotonically increasing, each feature point enclosed by the concentric circles with the third largest number of feature points in the candidate mapping image is filtered out to form a vibration mapping image. In other words, the last feature point with a monotonically increasing trend can be found, and then each feature point enclosed by the corresponding concentric circles can be filtered out to form a vibration mapping image.

[0143] It should be noted that in other embodiments, multiple radius values ​​can be randomly determined between 0 and the target value. Then, the center of the candidate mapping image is used as the center of a circle, and multiple concentric circles are determined based on the multiple radius values. Next, for each of the multiple concentric circles, the number of feature points passing through the circumference of that concentric circle in the candidate mapping image is determined, thus obtaining the feature point count of that concentric circle. Further, curve fitting is performed using the radius value of the concentric circles and the number of feature points as the x and y coordinates, and in the fitted curve, it is determined whether the trend of the curve before the point with the maximum number of feature points is monotonically increasing. Finally, when the trend of the curve before the point with the maximum number of feature points is monotonically increasing, each feature point enclosed by the concentric circle with the maximum number of feature points in the candidate mapping image is filtered out, forming a vibration mapping image.

[0144] Corresponding to the steps included in step S120 above, in a specific application scenario:

[0145] 1) Create a new single-channel image Simg with a resolution and size of (Ncol, Nrow), where Ncol and Nrow represent the number of columns and rows of the image Simg, respectively. In order to ensure that the image Simg after mapping and processing based on the data Pro (Vib) (i.e. vibration data sequence) is more conducive to feature analysis, the number of rows and columns of the image are made equal, and the corresponding values ​​can be odd numbers.

[0146] 2) The radian or angle u corresponding to each vibration data point is determined based on the spindle speed Speed ​​and the vibration sensor acquisition frequency Vfre. angle The corresponding calculation formula is u angle =360 / ((1 / (Speed / 60))*V fre The mapping transformation process begins with the center position (Ncol / 2, Nrow / 2) of the image Simg as the origin position of the vibration data;

[0147] 3) Normalization processing method of plotting data: the maximum value in a set of data Pro(Vib) is plotted, and the distance of that point from the center of Simg is Ncol / 2. If a point is plotted at (Ncol / 2, Nrow / 2), it means that the corresponding vibration value is zero. Other values ​​are normalized in this way and the corresponding points are plotted. The larger the value in Pro(Vib), the farther the corresponding feature point is from the center of the image Simg, but it does not exceed the boundary of the image.

[0148] 4) Using the first vibration data in Pro (Vib) as the correspondence to zero degrees, take the zero-degree angle in the image Simg as the center position (num). c / 2,num r / 2) In the horizontal right direction, subsequent data angles are superimposed, increasing counterclockwise, with each increase in angle equal to u. angle ,like Figure 3 As shown;

[0149] 5) In the Simg image, sequentially overlay the feature points of each vibration data point in Pro(Vib) at its corresponding accumulated angle until all corresponding vibration data in Pro(Vib) are plotted. This process completes the image mapping, resulting in the Simg image. Figure 4 As shown.

[0150] In addition, after the image is generated, the stationary signal feature regions in the image are filtered out based on the designed normalized scale-space stationary data filtering method. These stationary signals are the white noise corresponding to the cutting and non-cutting states of the tool, and need to be removed to improve the accuracy of tool tooth count determination. The specific steps are as follows:

[0151] (1) Create a new image Cimg with the same size as the image Simg. Find a point C(x,y) through the geometric center of the image Cimg, where x represents the column value corresponding to the geometric center and y represents the row value corresponding to the geometric center.

[0152] (2) Using the geometric center C(x,y) as the center, generate a set (Circle(i)) of concentric circles with a radius value that gradually increases from 0. The gray value of the generated circle is 0. Here, Set represents the combination of generated circles, i represents the index of the number of circles with different radius values, the maximum value of the corresponding radius is half the number of rows of the image Cimg, the span of the gradually increasing value is Step=1, the radius is a positive integer, and the number of concentric circles Set (Circle(i)) is Ncol / 2.

[0153] (3) After completing the drawing of the image Cimg, for each circle (Circle(i)) in the image Cimg, calculate the number Num of points with a gray value of 0 (black feature points) on the circumference of the circle and corresponding to the same position in the image Simg. i (P, P(x,y)=0), Num represents the number of points, and P(x,y) represents the points that satisfy the gray-level relationship and their corresponding coordinates;

[0154] (4) For each i, calculate its corresponding Num. i Numerical value;

[0155] (5) Using Radius as the x-axis, Num i Plot a curve (Line) showing the change of Numi values ​​as i changes, with the numerical value as the ordinate. Figure 5 As shown;

[0156] (6) The position where the maximum value appears in the statistical curve Line, and the curve to the left of the maximum value point satisfies the monotonically increasing rule, then the circle where the Radius is located is the circle to be calculated for filtering stationary data;

[0157] (7) The image Simg is filtered by the circle containing the Radius corresponding to the maximum value. That is, the gray values ​​of all points in the circle are set to the same gray values ​​as the background (e.g., black feature points are updated to white). The filtering process is completed, and the corresponding result image is the vibration mapping image Rimg.

[0158] Thirdly, regarding step S130, it should be noted that the specific method for extracting the feature distribution data that reflects the distribution of each feature point in the vibration mapping image is not limited and can be selected according to actual needs.

[0159] For example, in an alternative implementation, in order to ensure that the determined feature distribution data has a better tool state characterization capability, the above step S130 may further include steps S131, S132, S133 and S134, the specific contents of each step are as follows.

[0160] Step S131: Determine multiple straight lines passing through the center of the image from the vibration mapping image.

[0161] In this embodiment of the application, multiple straight lines passing through the center of the image can be determined from the vibration mapping image, such as 2 lines, 3 lines, 4 lines, 100 lines, 360 lines, etc. The vibration mapping image is an image formed based on feature points generated by polar coordinate mapping of each vibration data point in the vibration data sequence, and the center of the vibration mapping image is the pole of the polar coordinate system.

[0162] Step S132: For each of the multiple straight lines, determine the number of feature points in the vibration mapping image that pass through the straight line, and form the number of feature points corresponding to the straight line.

[0163] In this embodiment of the application, after determining multiple straight lines, the number of feature points passing through the vibration mapping image in each of the multiple straight lines can be determined to form the number of feature points corresponding to the straight line.

[0164] Step S133: Determine the straight line corresponding to the number of feature points with the maximum value, and based on the straight line, perform region segmentation on the vibration mapping image to form at least two segmented regions.

[0165] In this embodiment of the application, after determining the number of feature points corresponding to each straight line, the straight line corresponding to the number of feature points with the maximum value can be determined, and based on the straight line, the vibration mapping image can be segmented to form at least two segmented regions. For example, when there is one straight line corresponding to the number of feature points with the maximum value, the vibration mapping image can be segmented into two segmented regions, corresponding to the case where the target tool has two cutting teeth.

[0166] Step S134: Based on the at least two segmented regions and the number of feature points in each segmented region, determine the feature distribution data.

[0167] In this embodiment of the application, after obtaining the at least two segmented regions and the number of feature points in each segmented region, feature distribution data can be determined based on the at least two segmented regions and the number of feature points in each segmented region. For example, the number of segmented regions and the number of feature points in each segmented region can be used as the feature distribution data.

[0168] It is understood that in step S131 above, the specific method of determining multiple straight lines passing through the center of the image from the vibration mapping image is not limited and can be selected according to actual needs.

[0169] For example, in an alternative implementation, multiple straight lines passing through the center of the vibration mapping image can be randomly determined.

[0170] For example, in another alternative implementation, in order to determine a reliable segmentation region based on the determined multiple straight lines, the above step S131 may further include steps S131a and S131b, the specific contents of each step are as follows.

[0171] Step S131a: Determine any straight line passing through the center of the vibration mapping image from the vibration mapping image.

[0172] In this embodiment of the application, any straight line passing through the center of the image can be determined from the vibration mapping image, that is, the first straight line can be determined. Alternatively, the straight line where the polar axis of the polar coordinates is located can be determined as the first straight line.

[0173] Step S131b: Starting from any one of the straight lines, each time the target angle is reached, a new straight line passing through the center of the image is determined in the vibration mapping image to form multiple straight lines.

[0174] In this embodiment, after determining any one straight line, starting from that one straight line, a new straight line passing through the center of the vibration mapping image is determined each time the target angle is reached, thus forming multiple straight lines. For example, the target angle can be 1°, thereby forming 360 straight lines. In other embodiments, the target angle can also be 0.5°, or 2°, etc.

[0175] It should be noted that, in a specific application scenario, the feature distribution data can be determined based on the following steps:

[0176] (1) A straight line Line is randomly generated through the geometric center of the vibration mapping image Rimg. The slope of the line is k and the intercept is b. The initial value of k corresponding to the initial line is a random initial value.

[0177] (2) Count the number of black gray points (i.e. feature points) in the vibration mapping image Rimg that fall on the line Line under the current slope k;

[0178] (3) Count the slope k of the line by changing it, and count the number of points Numk corresponding to each line Line in the range of 0-360 degrees. k is the value corresponding to each degree increase.

[0179] (4) After completing the calculation of the number Numk value corresponding to all 360 lines with different slopes, the largest value max(Numk) and its corresponding slope max(k) are obtained by comparison.

[0180] (5) The straight line corresponding to the slope max(k) can divide Rimg into two regions, part1 and part2. Each region can characterize the corresponding characteristics of the cutting tooth during the cutting process.

[0181] (6) Calculate the number of points contained in the low gray value (i.e. black points) in regions part1 and part2 respectively. The area feature value of each region is represented by the number of points, and denoted as Size1 and Size2. Size1 and Size2 are the feature information to be calculated.

[0182] Fourthly, regarding step S140, it should be noted that the specific method for determining the target tool status data is not limited and can be selected according to actual needs.

[0183] For example, in an alternative implementation, it can be directly determined whether the number of each segmented region in the feature distribution data is consistent. If they are consistent, it indicates that the amount of cutting by each cutting tooth is also consistent. Alternatively, if they are not consistent, it indicates that the amount of cutting by each cutting tooth is also inconsistent, such as the presence of abnormalities that are not conducive to processing, like breakage.

[0184] For example, in another alternative implementation, in order to ensure that the obtained target tool state data has high reliability, the above step S140 may further include steps S141, S142 and S143, the specific contents of each step are as follows.

[0185] Step S141: Determine whether the number of segmented regions in the feature distribution data is the same as the target number of teeth in the feature distribution analysis rule.

[0186] In this embodiment of the application, it can be determined whether the number of segmented regions in the feature distribution data is the same as the target number of teeth in the feature distribution analysis rule. The target number of teeth is equal to the number of teeth on the target cutting tool (e.g., 2), and the segmented regions are formed by region segmentation based on the distribution of feature points in the vibration mapping image.

[0187] Step S142: If the number of segmented regions is not equal to the target number of teeth, then target tool state data for characterizing tool usage errors is obtained.

[0188] In this embodiment of the application, after comparing the number of segmented regions with the target number of teeth, if the number of segmented regions is not equal to the target number of teeth (e.g., less than or greater than the target number of teeth), target tool state data for characterizing tool usage errors is obtained.

[0189] Step S143: If the number of segmented regions is equal to the target number of teeth, then based on the consistency between the number of feature points in each segmented region, target tool state data for characterizing tooth consistency is obtained.

[0190] In this embodiment, after comparing the number of segmented regions with the target number of teeth, if the number of segmented regions equals the target number of teeth, it indicates that the tool is being used correctly. Therefore, target tool state data characterizing tooth consistency can be obtained based on the consistency between the number of feature points in each segmented region. The higher the consistency between the number of feature points in each segmented region, the higher the consistency in the amount of cutting by each tooth of the target tool. For example, if the target part uses a tool with two teeth, two segmented regions can be obtained after the above steps. If the number of corresponding segmented regions exceeds or is less than two, the corresponding tool is being used incorrectly; conversely, if the number of corresponding segmented regions is two, further judgment is required. Specifically, if there are two corresponding segmented regions, and the ratio of the corresponding region areas (such as the number of feature points) Size1 and Size2 is close to 1, it indicates that the amount of cutting by each cutting tooth of the tool is equal, the tool is being used correctly, and the corresponding cutting teeth have good consistency, without any abnormalities such as breakage that are detrimental to processing. When the corresponding area ratio is small (such as less than a threshold, such as 0.9, 0.8, 0.7, etc.), it indicates that the consistency of the tool is poor and it needs to be replaced to meet the needs of tool error prevention and high-quality processing in the CNC machining of parts.

[0191] Additionally, it should be noted that if the analysis reveals an incorrect tool or that the tool does not meet the machining requirements, the tool must be replaced. After replacement, the tool is analyzed and judged in the same way until it meets the requirements for the tool used in machining the corresponding part. After completing the error-proofing judgment for the tool used in the part, the part is formally machined. During the machining process, the Pow data in each acquired Data (Speed, Pow, Vib, Teech) is monitored and compared in real time. If it exceeds the set upper limit, it indicates an anomaly, and an anomaly monitoring and warning should be issued.

[0192] Finally, process data is recorded. Each time the tool is changed, error prevention judgment is performed based on the designed method. At the same time, process data is recorded, including the rotation speed, tool name, number of parts in the area, size of each area feature value, area ratio, and whether the tool was used incorrectly, so as to meet the need for full-process traceability of process data.

[0193] Combination Figure 6 This application also provides a tool condition analysis device applicable to the aforementioned electronic device. The tool condition analysis device may include a vibration data acquisition module, a vibration data mapping module, a feature distribution extraction module, and a tool condition analysis module.

[0194] Specifically, the vibration data acquisition module can be used to acquire a vibration data sequence formed by monitoring the target tool, wherein the vibration data sequence includes multiple vibration data corresponding to multiple time points. In this embodiment, the vibration data acquisition module can be used to perform... Figure 2 The relevant content regarding the vibration data acquisition module in step S110 shown can be found in the previous description of step S110.

[0195] In detail, the vibration data mapping module can be used to map each vibration data in the vibration data sequence to form a vibration mapping image. The distribution of feature points in the vibration mapping image reflects the distribution of each vibration data in the vibration data sequence, and there is a one-to-one correspondence between each feature point and each vibration data. In this embodiment, the vibration data mapping module can be used to perform... Figure 2 The details of step S120 shown above, and the relevant content regarding the vibration data mapping module, can be found in the preceding description of step S120.

[0196] Specifically, the feature distribution extraction module can be used to extract feature distribution data from the vibration mapping image to reflect the distribution of each feature point in the vibration mapping image. In this embodiment, the feature distribution extraction module can be used to perform... Figure 2 The relevant content regarding the feature distribution extraction module in step S130 shown can be found in the previous description of step S130.

[0197] Specifically, the tool condition analysis module can be used to determine target tool condition data based on the feature distribution data and pre-determined feature distribution analysis rules, wherein the target tool condition data reflects the condition of the target tool. In this embodiment, the tool condition analysis module can be used to perform... Figure 2 The relevant content regarding the tool condition analysis module in step S140 shown can be found in the previous description of step S140.

[0198] It is understood that, in an alternative implementation, the vibration data acquisition module may specifically be used to: acquire the original sequence of vibration data formed by monitoring the target tool; perform frequency domain conversion on the original sequence of vibration data to form a vibration spectrum; filter the signal corresponding to the frequency band region in the high-frequency band of the vibration spectrum where the energy exceeds the energy threshold, and convert the filtered data back to the time domain to form a vibration data sequence.

[0199] It is understood that, in an alternative implementation, the vibration data mapping module may specifically be used to: determine an initial mapping image; determine a first coordinate value and a second coordinate value for each vibration data in the vibration data sequence in the initial mapping image, wherein the first coordinate value is related to the resolution of the corresponding vibration data and the initial mapping image, and the second coordinate value is related to the sequence position of the corresponding vibration data in the vibration data sequence; and based on the first coordinate value and the second coordinate value, map each vibration data in the vibration data sequence to the initial mapping image to form a vibration mapping image.

[0200] Understandably, in an alternative implementation, the feature distribution extraction module can specifically be used to: determine multiple straight lines passing through the center of the image from the vibration mapping image, wherein the vibration mapping image is an image formed based on feature points formed by polar coordinate mapping of each vibration data in the vibration data sequence; for each of the multiple straight lines, determine the number of feature points passing through the line in the vibration mapping image, forming the feature point count corresponding to the line; determine the line corresponding to the maximum number of feature points, and based on the line, perform region segmentation on the vibration mapping image to form at least two segmented regions; and determine feature distribution data based on the at least two segmented regions and the number of feature points in each segmented region.

[0201] Understandably, in an alternative implementation, the tool state analysis module can specifically be used to: determine whether the number of segmented regions in the feature distribution data is the same as the target number of teeth in the feature distribution analysis rules, wherein the target number of teeth is equal to the number of cutting teeth of the target tool, and the segmented regions are formed by region segmentation based on the distribution of each feature point in the vibration mapping image; if the number of segmented regions is not equal to the target number of teeth, then target tool state data for characterizing tool usage errors is obtained; if the number of segmented regions is equal to the target number of teeth, then target tool state data for characterizing tooth consistency is obtained based on the consistency between the number of feature points in each segmented region, wherein the higher the consistency between the number of feature points in each segmented region, the higher the consistency of the amount of cutting by each cutting tooth of the target tool.

[0202] In this embodiment of the application, corresponding to the tool condition analysis method applied to the electronic device described above, a computer-readable storage medium is also provided, which stores a computer program that executes the various steps of the tool condition analysis method when the computer program is run.

[0203] The steps executed by the aforementioned computer program during runtime will not be described in detail here, but can be found in the explanation of the tool condition analysis method above.

[0204] In summary, the tool condition analysis method, apparatus, equipment, and medium provided in this application first acquire a vibration data sequence generated by monitoring the target tool; second, map each vibration data point in the vibration data sequence to form a vibration mapping image; then, extract feature distribution data reflecting the distribution of each feature point in the vibration mapping image; finally, determine the target tool condition data based on the feature distribution data and pre-determined feature distribution analysis rules. Based on the above, by utilizing vibration sensors to collect data information during tool processing—i.e., vibration data sequences—and combining it with image mapping processing technology, time-series data can be mapped into images, enabling effective extraction of tool features from the images. This improves the accuracy of tool condition identification and solves the problems of low accuracy and complex physical operations in existing technologies. Furthermore, the entire process requires no machine downtime, ensuring processing efficiency. Moreover, this solution is unaffected by processing materials or methods, possessing high versatility and can be widely applied to various CNC machining scenarios, effectively addressing the poor versatility of existing technologies. Since no machine downtime is required for inspection, an early warning can be issued immediately upon detection of anomalies, preventing a decline in processing quality or production accidents, and significantly improving production efficiency and safety. Based on this, the solution proposed in this application can address the problems of low accuracy in tool condition analysis results or the limitations in applicability due to reliance on video and image monitoring in existing technologies.

[0205] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0206] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0207] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, electronic device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0208] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A tool condition analysis method, characterized in that, include: A vibration data sequence generated by monitoring the target tool is obtained, wherein the vibration data sequence includes multiple vibration data corresponding to multiple time points; The vibration data in the vibration data sequence is mapped to form a vibration mapping image, wherein the distribution of each feature point in the vibration mapping image is used to reflect the distribution of each vibration data in the vibration data sequence, and each feature point corresponds one-to-one with each vibration data. Multiple straight lines passing through the center of the vibration mapping image are determined from the vibration mapping image, wherein the vibration mapping image is an image formed based on feature points formed by polar coordinate mapping of each vibration data in the vibration data sequence; for each of the multiple straight lines, the number of feature points passing through the line in the vibration mapping image is determined, forming the feature point count corresponding to the line; the line corresponding to the feature point count with the maximum value is determined, and based on the line, the vibration mapping image is segmented to form at least two segmented regions; based on the at least two segmented regions and the number of feature points in each segmented region, feature distribution data is determined; Based on the feature distribution data and the predetermined feature distribution analysis rules, the target tool state data is determined, wherein the target tool state data is used to reflect the state of the target tool.

2. The tool condition analysis method according to claim 1, characterized in that, The step of mapping each vibration data in the vibration data sequence to form a vibration mapping image includes: Determine the initial mapping image; Each vibration data point in the vibration data sequence is determined to have a first coordinate value and a second coordinate value in the initial mapping image, wherein the first coordinate value is related to the resolution of the corresponding vibration data and the initial mapping image, and the second coordinate value is related to the sequence position of the corresponding vibration data in the vibration data sequence. Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a vibration mapping image.

3. The tool condition analysis method according to claim 2, characterized in that, The step of determining the first coordinate value and the second coordinate value of each vibration data in the vibration data sequence in the initial mapping image includes: The image center point is determined in the initial mapped image, wherein the resolution of the initial mapped image in the row direction is equal to the resolution in the column direction; The center point of the image is determined as the pole, and the straight line that passes through the center point of the image and extends along the row direction is determined as the polar axis to construct a polar coordinate system. Each vibration data point in the vibration data sequence is traversed sequentially to form the currently traversed vibration data. Based on the currently traversed vibration data, a first coordinate value is determined, and based on the sequence position of the currently traversed vibration data in the vibration data sequence, a second coordinate value is determined. The first coordinate value is used to reflect the polar radius of the currently traversed vibration data in the polar coordinate system, and the second coordinate value is used to reflect the polar angle of the currently traversed vibration data in the polar coordinate system.

4. The tool condition analysis method according to claim 3, characterized in that, The steps of determining a first coordinate value based on the currently traversed vibration data, and determining a second coordinate value based on the sequence position of the currently traversed vibration data in the vibration data sequence, include: Based on the target mapping parameters, the currently traversed vibration data is mapped to form vibration data mapping values, and the first coordinate value is determined based on the vibration data mapping values. The target mapping parameters are determined based on the ratio between the vibration data with the maximum value in the vibration data sequence and half of the resolution in the row direction. If the vibration data currently being traversed belongs to the first vibration data in the vibration data sequence, then the second coordinate value of the vibration data currently being traversed is determined to be 0 degrees. If the vibration data currently being traversed does not belong to the first vibration data in the vibration data sequence, then the second coordinate value of the previous vibration data and a predetermined angle threshold are summed to form the second coordinate value of the vibration data currently being traversed. The angle threshold is related to the spindle speed of the target tool and the acquisition frequency of the vibration data sequence.

5. The tool condition analysis method according to claim 2, characterized in that, The step of mapping each vibration data point in the vibration data sequence to the initial mapping image based on the first coordinate value and the second coordinate value to form a vibration mapping image includes: Based on the first coordinate value and the second coordinate value, each vibration data in the vibration data sequence is mapped to the initial mapping image to form a candidate mapping image, wherein the feature points in the candidate mapping image correspond one-to-one with the vibration data; The stable signal feature regions in the candidate mapping image are filtered out to remove the white noise corresponding to the cutting and non-cutting states of the target tool, thus obtaining the vibration mapping image.

6. The tool condition analysis method according to claim 5, characterized in that, The step of filtering out stable signal feature regions in the candidate mapping image to remove white noise corresponding to the cutting and non-cutting states of the target tool, and obtaining a vibration mapping image, includes: Using the center of the candidate mapping image as the center of a circle, multiple concentric circles are determined based on multiple radius values ​​that increase sequentially from 0 to the target value. The radius value with the maximum value is equal to half the resolution of the candidate mapping image in the row direction. The first coordinate value and the second coordinate value are used to characterize the polar radius and polar angle of the corresponding feature points, respectively, and the resolution of the candidate mapping image in the row direction is equal to the resolution in the column direction. For each of the plurality of concentric circles, the number of feature points in the candidate mapping image that pass through the circumference of the concentric circle is determined, and the number of feature points of the concentric circle is obtained. Curve fitting is performed using the radius of the concentric circles and the number of feature points as the x and y axes, respectively. In the fitted curve, it is determined whether the trend of the curve before the point where the number of feature points has the maximum value is monotonically increasing. When the trend of the curve before the point with the maximum number of feature points is monotonically increasing, each feature point surrounded by the concentric circles with the maximum number of feature points in the candidate mapping image is filtered out to form a vibration mapping image.

7. The tool condition analysis method according to claim 1, characterized in that, The step of determining multiple straight lines passing through the center of the image from the vibration mapping image includes: Determine any straight line passing through the center of the vibration mapping image; Starting from any one of the straight lines, each time the target angle is reached, a new straight line passing through the center of the image is determined in the vibration mapping image to form multiple straight lines.

8. The tool condition analysis method according to claim 1, characterized in that, The step of determining the target tool state data based on the feature distribution data and the pre-determined feature distribution analysis rules includes: Determine whether the number of segmented regions in the feature distribution data is the same as the number of target teeth in the feature distribution analysis rules, wherein the number of target teeth is equal to the number of teeth of the target tool, and the segmented regions are formed by region segmentation based on the distribution of each feature point in the vibration mapping image; If the number of segmented regions is not equal to the target number of teeth, then target tool state data for characterizing tool usage errors is obtained; If the number of segmented regions is equal to the number of target teeth, then target tool state data for characterizing tooth consistency is obtained based on the consistency between the number of feature points in each segmented region. The higher the consistency between the number of feature points in each segmented region, the higher the consistency of the amount of cutting by each tooth of the target tool.

9. The tool condition analysis method according to any one of claims 1-8, characterized in that, The step of acquiring the vibration data sequence formed by monitoring the target tool includes: Obtain the raw sequence of vibration data generated by monitoring the target tool; The original sequence of vibration data is transformed in the frequency domain to form a vibration spectrum. The signals corresponding to the frequency band regions in the high-frequency band of the vibration spectrum where the energy exceeds the energy threshold are filtered, and the filtered data is converted back to the time domain to form a vibration data sequence.

10. A tool condition analysis device, characterized in that, include: The vibration data acquisition module is used to acquire a vibration data sequence formed by monitoring the target tool, wherein the vibration data sequence includes multiple vibration data corresponding to multiple time points; The vibration data mapping module is used to map each vibration data in the vibration data sequence to form a vibration mapping image. The distribution of each feature point in the vibration mapping image is used to reflect the distribution of each vibration data in the vibration data sequence, and each feature point corresponds one-to-one with each vibration data. The feature distribution extraction module is used to determine multiple straight lines passing through the center of the vibration mapping image from the vibration mapping image, wherein the vibration mapping image is an image formed based on feature points formed by polar coordinate mapping of each vibration data in the vibration data sequence; for each of the multiple straight lines, the number of feature points passing through the line in the vibration mapping image is determined to form the feature point count corresponding to the line; the line corresponding to the feature point count with the maximum value is determined, and based on the line, the vibration mapping image is segmented to form at least two segmented regions; based on the at least two segmented regions and the number of feature points in each segmented region, feature distribution data is determined; The tool condition analysis module is used to determine the target tool condition data based on the feature distribution data and the pre-determined feature distribution analysis rules, wherein the target tool condition data is used to reflect the condition of the target tool.

11. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the tool condition analysis method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a computer program that, when executed, performs the tool condition analysis method according to any one of claims 1-9.

Images