Cutting tool life monitoring method, computer device and storage medium
By obtaining the motor torque signal in the strong irradiation cutting system and matching it with the life cycle model, the applicability problem of tool health monitoring is solved, and the accurate prediction and early warning of tool life is achieved to ensure the safe operation of the equipment.
Patent Information
- Application Number
- CN202210055282.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-18
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2042-01-18
AI Technical Summary
The existing tool health monitoring methods cannot be applied to strong radiation cutting systems, resulting in the inability to effectively monitor the health status and life of the tool.
By obtaining the motor torque signal generated during the cutting process, extracting torque characteristics, and matching it with the tool life cycle model library, the tool lifespan is determined, including segment division, signal energy analysis and similarity calculation, to achieve tool wear stage and life predict.
Under a strong irradiation environment, the monitoring of tool health status and life prediction are achieved, and early warning signals are issued in a timely manner to ensure the safe operation of tools and equipment.
Smart Images

Figure CN114529052B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a cutting tool life monitoring method, computer equipment, storage medium and computer program product. Background Art
[0002] The cold extrusion cutting system for thick-walled pipes adopts a cold extrusion chipless cutting method with a slow cutting speed and no processing accuracy requirements, but it pays more attention to monitoring the impact of tool wear on cutting force and the impact on the tool during extrusion fracture.
[0003] In traditional technology, tool health monitoring is usually achieved by collecting tool vibration, noise, temperature, stress and other signals. However, unlike general industrial machining scenarios, the thick-walled pipe cold extrusion cutting system is in a strong radiation environment, and vibration sensors, pickups, force sensors, etc. cannot maintain long-term effective work.
[0004] There is currently no effective solution to the problem that tool health monitoring methods in related technologies cannot be applied to tool health status monitoring in high-irradiation cutting systems. Summary of the invention
[0005] Based on this, it is necessary to provide a cutting tool life monitoring method, computer equipment, computer readable storage medium and computer program product that can be used for monitoring the health status of cutting tools in strong radiation cutting systems in response to the above technical problems.
[0006] In a first aspect, the present application provides a cutting tool life monitoring method. The method comprises:
[0007] Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal;
[0008] Acquire a tool life cycle model library, and query a first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque characteristic, wherein each tool life cycle model includes a motor torque characteristic of the corresponding tool throughout its entire life cycle;
[0009] The tool life of the tool to be monitored is determined according to the first torque characteristic and the first tool life cycle model.
[0010] In one embodiment, extracting the first torque feature of the first motor torque signal includes:
[0011] Acquire a section division rule, and divide the first motor torque signal into at least one section according to the section division rule;
[0012] Analyze each section of the first motor torque signal to obtain a second motor torque signal of multiple frequency bands corresponding to each section;
[0013] The signal energy values of the second motor torque signal in the plurality of frequency bands are acquired, and the maximum signal energy value among the signal energy values of the second motor torque signal in the plurality of frequency bands is determined as the first torque feature of the corresponding section in the first motor torque signal.
[0014] In one embodiment, the segment division rules include:
[0015] Rule 1: dividing the first motor torque signal into at least one section according to the start and end time of at least one cutting subtask of the tool to be monitored during the cutting process;
[0016] Alternatively, rule two, dividing the first motor torque signal into at least one section according to the tool feed amount and / or tool speed of the tool to be monitored during the cutting process.
[0017] In one embodiment, querying the first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque feature includes:
[0018] Respectively calculating similarities between the first torque feature and torque features of multiple tool life cycle models in the tool life cycle model library to obtain multiple feature similarity values;
[0019] A first tool life cycle model that best matches the first torque feature is determined according to the multiple feature similarity values.
[0020] In one embodiment, determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model comprises:
[0021] Obtaining, according to the first torque characteristic, an initial torque characteristic corresponding to the tool to be monitored when executing a first cutting subtask and a cut-off torque characteristic when executing a last cutting subtask;
[0022] Obtaining the tool wear stage currently in which the tool to be monitored is located according to the initial torque characteristics, the cut-off torque characteristics and the first tool life cycle model of the tool to be monitored, wherein the tool wear stage includes a rapid wear stage, a running-in stage and a prone to failure stage;
[0023] The tool life of the tool to be monitored is determined according to the tool wear stage that the tool to be monitored is currently in.
[0024] In one embodiment, querying the first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque feature includes:
[0025] Determining whether the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold;
[0026] When it is determined that the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold, respectively calculating similarities between the first torque feature and torque features of multiple tool life cycle models in the tool life cycle model library to obtain multiple feature similarity values;
[0027] A plurality of first tool life cycle models matching the first torque feature are determined according to a preset feature similarity threshold and the plurality of feature similarity values.
[0028] In one embodiment, after determining a plurality of first tool life cycle models matching the first torque feature according to a preset feature similarity threshold and the plurality of feature similarity values, the method further comprises:
[0029] Obtaining a mapping relationship between torque characteristics and tool life according to the plurality of first tool life cycle models;
[0030] The tool life of the tool to be monitored is determined according to the mapping relationship and the first torque characteristic.
[0031] In a second aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
[0032] Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal;
[0033] Acquire a tool life cycle model library, and query a first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque characteristic, wherein each tool life cycle model includes a motor torque characteristic of the corresponding tool throughout its entire life cycle;
[0034] The tool life of the tool to be monitored is determined according to the first torque characteristic and the first tool life cycle model.
[0035] In a third aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0036] Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal;
[0037] Acquire a tool life cycle model library, and query a first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque characteristic, wherein each tool life cycle model includes a motor torque characteristic of the corresponding tool throughout its entire life cycle;
[0038] The tool life of the tool to be monitored is determined according to the first torque characteristic and the first tool life cycle model.
[0039] In a fourth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0040] Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal;
[0041] Acquire a tool life cycle model library, and query a first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque characteristic, wherein each tool life cycle model includes a motor torque characteristic of the corresponding tool throughout its entire life cycle;
[0042] The tool life of the tool to be monitored is determined according to the first torque characteristic and the first tool life cycle model.
[0043] The above-mentioned cutting tool life monitoring method, computer equipment, storage medium and computer program product obtain the first motor torque signal generated by the tool to be monitored during the cutting process, and extract the first torque feature of the first motor torque signal; obtain a tool life cycle model library, and query the first tool life cycle model that matches the tool to be monitored from the tool life cycle model library according to the first torque feature, wherein each tool life cycle model includes the motor torque characteristics of the corresponding tool throughout its life cycle; determine the tool life of the tool to be monitored according to the first torque feature and the first tool life cycle model, thereby solving the problem that the tool health monitoring method in the related technology cannot be applied to the health status monitoring of the tool in the strong radiation cutting system, and realizes the health status monitoring of the tool in the strong radiation cutting system, and can timely issue early warning signals during the period when the tool is prone to failure, thereby ensuring the safe operation of the tool and equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1A hardware structure block diagram of a terminal of a cutting tool life monitoring method in one embodiment;
[0045] Figure 2 A force analysis diagram of a cutting tool in one embodiment;
[0046] Figure 3 A schematic diagram of a process of a cutting tool life monitoring method in one embodiment;
[0047] Figure 4 is a frequency spectrum diagram of a torque signal of a feed motor during a tool cutting process in one embodiment;
[0048] Figure 5 A feed motor torque signal filtering diagram of a tool cutting process in one embodiment;
[0049] Figure 6 A motor torque signal diagram after three-layer wavelet transform decomposition in one embodiment;
[0050] Figure 7 is a torque feature map extracted by wavelet packet decomposition in one embodiment;
[0051] Figure 8 A schematic flow chart of a cutting tool life monitoring method according to a preferred embodiment;
[0052] Fig. 9 A tool life cycle signal energy curve diagram in one embodiment;
[0053] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0055] The cutting tool life monitoring method provided in the embodiment of the present application can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 4 is a hardware structure diagram of a terminal of the cutting tool life monitoring method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.
[0056] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the cutting tool life monitoring method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0057] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
[0058] Different from general industrial machining scenarios, the thick-walled pipe cold extrusion cutting system is in a strong radiation environment, and vibration sensors, pickups, force sensors, etc. cannot maintain long-term effective operation. Therefore, in the operating environment, the thick-walled pipe cold extrusion cutting system can only use the motor signals of each axis placed outside the hot chamber, such as current signals, torque signals, etc., to build a mapping relationship between tool wear and force through time domain and frequency domain analysis and comparison, and then predict tool health and estimated life.
[0059] like Figure 2 The figure shows the force analysis diagram of the tool. When the tool assembly is cutting the workpiece 3, the tool 1 and the main disc 2 are driven by two motors to realize radial feeding and revolution. The tool 1 is subjected to the centrifugal force F r =mrω 2 , extrusion cutting force F N , gravity works together: F 合 =F N +mrω2 -mgsin(ωt), reflected in the motor torque M=μr F 合 , where ω is the motor speed and μ is the friction coefficient between the tool assembly and the wire coil. Therefore, when the speed is constant, as the tool wear increases, F N As the tool life increases, the required motor torque will also increase, that is, the motor torque signal can reflect the degree of tool wear, that is, the tool life. Therefore, by analyzing the motor torque and other signals during cutting, the current tool wear can be estimated, the tool life can be predicted, and an early warning signal can be issued before the tool breaks.
[0060] In this embodiment, a cutting tool life monitoring method is provided. It should be noted that this embodiment is used for a cutting system in a strong radiation environment. Figure 3 is a flow chart of the cutting tool life monitoring method of this embodiment, such as Figure 3 As shown, the process includes the following steps:
[0061] Step 302: Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal.
[0062] The first motor torque signal includes data collected continuously according to a preset signal collection time during the entire cutting process from the initial cutting to the monitoring of the tool to be monitored. The first torque feature can be any existing method for extracting signal features.
[0063] Step 304, obtain a tool lifecycle model library, and query the first tool lifecycle model that matches the tool to be monitored from the tool lifecycle model library according to the first torque characteristic, wherein each tool lifecycle model includes the motor torque characteristic of the corresponding tool throughout its entire life cycle.
[0064] The tool lifecycle model library includes motor torque features of motor torque signals of multiple tool historical cutting processes. When querying the first tool lifecycle model that matches the tool to be monitored, any existing feature similarity calculation method can be used, and the first tool lifecycle model can be one or more.
[0065] Step 306 : determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model.
[0066] Among them, tool life refers to the entire cutting process from the first use of the tool to the time of edge breakage, which can be calculated based on the number of cuts or cutting time.
[0067] In the above-mentioned cutting tool life monitoring method, the motor torque characteristics of the motor torque signal of the tool to be monitored are extracted to match the tool life cycle model, and then the matched first tool life cycle model is used to determine the tool life of the tool to be monitored, so that the tool to be monitored can be discovered in time before the blade breaks, thereby ensuring the safety of tool cutting and the quality of the workpiece being cut. In addition, by collecting the motor torque signal of the motor placed outside the hot chamber of the strong radiation environment cutting system to estimate the tool life, it can be used for a long time in the working environment of the strong radiation environment cutting system, overcome the noise signal interference of the various stages of the reduction box in the long transmission chain, and can timely issue early warning signals during the tool failure period, thereby ensuring the safe operation of the tool and equipment.
[0068] In one embodiment, before extracting the first torque feature of the first motor torque signal, data preprocessing is performed on the first motor torque signal to remove noise in the signal.
[0069] Specifically, by converting the time domain signal of the first motor torque signal into a frequency domain signal, removing the corresponding noise frequency domain signal from the frequency domain signal, and finally inversely converting it back to the time domain signal, the noise signal can be effectively filtered. Figure 4 The feed motor torque signal spectrum of the tool cutting process is shown in the figure. It can be seen from the figure that the effective part of the sampling signal is concentrated in the low frequency band, so a low-pass filter is selected to filter out the high-frequency noise in the signal. Figure 5 The feed motor torque signal filtering diagram of the tool cutting process shown shows the signal comparison before and after filtering the motor torque signal noise using a low-pass filter.
[0070] By performing noise reduction processing on the collected signals, the subsequent feature extraction process will not be disturbed by noise, thereby improving the accuracy of life prediction.
[0071] In one embodiment, extracting a first torque feature of a first motor torque signal includes:
[0072] Acquire a segment division rule, and divide the first motor torque signal into at least one segment according to the segment division rule; analyze each segment of the first motor torque signal to obtain a second motor torque signal of multiple frequency bands corresponding to each segment; acquire signal energy values of the second motor torque signals of the multiple frequency bands, and determine the maximum signal energy value among the signal energy values of the second motor torque signals of the multiple frequency bands as the first torque feature of the corresponding segment in the first motor torque signal.
[0073] The wavelet packet decomposition method is used to divide the first motor torque signal of each section into second motor torque signals of multiple frequency bands.
[0074] Specifically, the first motor torque signal collected during the entire cutting process of the tool to be monitored is divided into motor torque signals of multiple sections according to the section division rule, and the motor torque signal of each section is decomposed by wavelet packet. Figure 6 The signal shown is obtained by performing a three-layer wavelet transform decomposition on the motor torque signal of a certain section using the wavelet packet decomposition method, as shown in Figure 6 The motor torque signal of this section is split into 8 different frequency bands, generating motor torque signals in 8 different frequency bands. The energy value obtained by summing the squares of the amplitudes of discrete points in the first frequency band is used as the first torque characteristic value. The energy value of the first frequency band is also the maximum energy value among all frequency bands. Figure 7 The figure shows the torque characteristic diagram extracted by wavelet packet decomposition, where the horizontal axis is the number of cuts and the vertical axis is the maximum energy value, i.e., the first torque characteristic value.
[0075] In practical applications, the signal data of the tool operation process has the characteristics of non-stationary or quasi-stationary. The time-frequency domain analysis method can accurately characterize the characteristics of the cutting process signal data. Common methods for time-frequency domain analysis are wavelet transform (WT) and empirical mode decomposition (EMD). Compared with empirical mode decomposition, wavelet transform has a solid theoretical basis. Wavelet packet decomposition is a more sophisticated analysis method than wavelet transform. Wavelet packet decomposition performs multi-level decomposition on the full frequency band of signal data, which can separate the energy of each frequency band related to the tool wear in the signal data, and the change in relative energy in each frequency band reflects the change in tool wear. The related technology squares the amplitude of discrete points in each frequency band to obtain the energy value of each frequency band, and the vector composed of the energy values of each frequency band is used as the torque feature vector. In this embodiment, only calculating the energy value of the first frequency band reduces the amount of calculation compared to calculating the energy values of all frequency bands, and improves the efficiency of cutting tool life monitoring. Only the maximum energy value of the signal energy values in multiple frequency bands obtained after wavelet packet decomposition is used as the torque characteristic value, which can characterize the tool signal characteristics while reducing the amount of calculation and improving the monitoring efficiency.
[0076] In one embodiment, the segment division rules include:
[0077] Rule 1: Divide the first motor torque signal into at least one segment according to the start and end time of at least one cutting subtask of the tool to be monitored during the cutting process;
[0078] Alternatively, rule two, the first motor torque signal is divided into at least one section according to the tool feed amount and / or tool rotation speed of the tool to be monitored during the cutting process.
[0079] Among them, rule one is to divide according to the number of cuts, that is, one cut is a segment, and rule two is to divide the segments according to different feed rates and different tool speeds during the tool cutting process. The two segment division rules can be selected according to the actual application situation, with the purpose of extracting features that can more accurately express the tool wear situation. You can use one of the segment division rules to divide the segments alone, or you can combine the two rules to divide the segments, for example, first divide it into multiple segments according to rule one, and then divide the segment into multiple sub-segments according to rule two.
[0080] In one embodiment, querying a first tool lifecycle model matching the tool to be monitored from a tool lifecycle model library according to the first torque feature includes:
[0081] The similarities between the first torque feature and the torque features of multiple tool life cycle models in the tool life cycle model library are calculated respectively to obtain multiple feature similarity values; and a first tool life cycle model that best matches the first torque feature is determined according to the multiple feature similarity values.
[0082] Among them, similarity can be measured using methods such as threshold method and feature comparison.
[0083] In one embodiment, determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model comprises:
[0084] According to the first torque characteristic, an initial torque characteristic corresponding to the tool to be monitored when executing the first cutting subtask and a cutoff torque characteristic when executing the last cutting subtask are obtained; according to the initial torque characteristic, the cutoff torque characteristic and the first tool life cycle model of the tool to be monitored, the tool wear stage currently in which the tool to be monitored is obtained, wherein the tool wear stage includes a rapid wear stage, a running-in stage and a prone to failure stage; according to the tool wear stage currently in which the tool to be monitored is located, the tool life of the tool to be monitored is determined.
[0085] The initial torque feature is the first torque feature value in the first torque feature, and the cut-off torque feature is the last torque feature value in the first torque feature.
[0086] Specifically, by calculating the difference between the cut-off torque feature and the initial torque feature, the difference and the first tool life cycle model are used to determine the stage of the cut-off torque feature in the entire tool life cycle. In practical applications, the entire life cycle of a tool generally goes through a 25% rapid wear stage, a 50% running-in stage, and a 25% prone to failure stage. After the wear stage of the tool is determined, the remaining tool life can be roughly predicted based on the stage of the tool and the above ratio, so as to provide timely warnings and improve production efficiency.
[0087] In one embodiment, querying a first tool lifecycle model matching the tool to be monitored from a tool lifecycle model library according to the first torque feature includes:
[0088] Determine whether the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold; when it is determined that the number of tool life cycle models in the tool life cycle model library is greater than the preset threshold, respectively calculate the similarity between the first torque feature and the torque features of multiple tool life cycle models in the tool life cycle model library to obtain multiple feature similarity values; determine multiple first tool life cycle models that match the first torque feature based on the preset feature similarity threshold and the multiple feature similarity values.
[0089] When it is determined that the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold, it means that the number of tool life cycle models in the tool life cycle model library at this time is large enough to be used for training the data-driven model.
[0090] Further, in one of the embodiments, after determining a plurality of first tool life cycle models matching the first torque feature according to a preset feature similarity threshold and a plurality of feature similarity values, the method further comprises:
[0091] A mapping relationship between torque characteristics and tool life is obtained according to a plurality of first tool life cycle models; and the tool life of the tool to be monitored is determined according to the mapping relationship and the first torque characteristics.
[0092] In this embodiment, a tool life prediction model can be obtained by training a data-driven model using multiple tool life cycle models that are most similar to the tool to be monitored in the tool life cycle model library, and the life of the tool to be monitored can be predicted using the trained tool life prediction model.
[0093] In one of the embodiments, a radiation-resistant vibration sensor is used to collect vibration signals of a cutting tool to be monitored during the cutting process, and the vibration signals are used to implement health monitoring of the cutting tool.
[0094] In practical applications, if there is a suitable radiation-resistant vibration sensor, the signal collected by the radiation-resistant vibration sensor can be used to monitor the health of the tool to be monitored.
[0095] The present embodiment is described and illustrated below through preferred embodiments.
[0096] Figure 8 It is a flow chart of the cutting tool life monitoring method of this preferred embodiment.
[0097] like Figure 8 As shown, the cutting tool life monitoring method includes the following steps:
[0098] Step S801, obtaining a historical motor torque signal and a motor torque signal of a tool to be monitored.
[0099] Step S802: data preprocessing.
[0100] In a preferred embodiment, both the historical motor torque signal and the motor torque signal of the tool to be monitored need to be preprocessed to remove noise in the signal. Specifically, the time domain signal of the motor torque signal is converted into a frequency domain signal, a low-pass filter is used to filter out high-frequency noise in the signal, and finally the inverse conversion is restored to the time domain signal.
[0101] Step S803: signal analysis.
[0102] Specifically, the motor torque signal of the tool to be monitored is analyzed for similarity with multiple historical motor torque signals. If the similarities with multiple historical motor torque signals are all lower than the threshold δ, it indicates that other faults may exist in the equipment during the cutting process of the tool to be monitored. Otherwise, proceed to step S804.
[0103] Step S804: feature extraction.
[0104] Specifically, the torque features in the historical torque signal and the motor torque signal of the tool to be monitored are extracted by wavelet packet decomposition method. The torque feature is the signal energy value of the first frequency band after wavelet packet decomposition.
[0105] Step S805, generating a tool life cycle energy curve model library.
[0106] Specifically, multiple tool life cycle curves corresponding to multiple historical motor torque signals are obtained by feature extraction and curve fitting, and multiple tool life cycle curves form a tool life cycle energy curve model library. And the motor torque signal and its energy characteristics collected each time are updated to the tool life cycle energy curve model library.
[0107] Step S806, predicting the tool life using the tool life cycle energy curve model library.
[0108] Specifically, when the number of tool life cycle curves in the tool life cycle energy curve model library is less than a threshold, the tool life cycle energy curve in the tool life cycle energy curve model library that is most similar to the tool to be monitored is used to predict the tool life to be monitored. Tools generally go through a 25% rapid wear stage, a 50% running-in stage, and a 25% prone to failure stage. When the wear stage of the current torque characteristic of the tool to be monitored is determined, the remaining tool life is roughly predicted by the above ratio.
[0109] When the number of tool life cycle curves in the tool life cycle energy curve model library is greater than a threshold, the life of the tool to be monitored is predicted by multiple tool life cycle energy curves in the tool life cycle energy curve model library whose similarity with the tool to be monitored is greater than a preset similarity threshold. Specifically, multiple tool life cycle models with similarity greater than a preset similarity threshold are used in combination with a deep learning network and a multi-model fusion algorithm to train a data-driven model to obtain a tool life prediction model, and the motor torque characteristics of the tool to be monitored are input into the trained tool life prediction model to obtain a life prediction value of the tool to be monitored.
[0110] like Fig. 9 The figure shows the tool life cycle signal energy curve obtained by using the cutting tool life monitoring method of the preferred embodiment. The broken line in the figure is the trend diagram of the time-frequency domain characteristics (signal maximum energy) extracted from the torque signal of the feed motor during cutting after wavelet packet analysis with the number of cuts. In the early cutting, the characteristic decreases significantly, and enters the running-in period after about 10-15 cuts. As the number of cuts increases, the tool undergoes a 25% rapid wear period, a 50% running-in period, and a 25% prone to failure period. Curve fitting of the trend graph can be well matched with the historical tool health status curve. The curve can be inferred that the tool life is about 55-70 times, which is consistent with the chipping after 65 cuts in the experiment. Therefore, the cutting tool life monitoring method of the present application can timely issue early warning signals during the tool prone to failure period, effectively guide operations, reduce unnecessary downtime, ensure the safe operation of tools and equipment, and improve production efficiency.
[0111] In a preferred embodiment, the collected motor signals of the tool's entire life cycle are used to form historical motor torque signals. When a large-scale tool life cycle energy curve model library has not yet been formed, the difference between the wavelet packet energy characteristics of the tool's current cutting state and the first cutting state is determined by the threshold method and feature comparison method, thereby estimating its wear degree and comparing it with the energy characteristics of the tool when the tool is broken in the existing model library to give an estimate of the tool's current life. The motor torque signal and its energy characteristics collected each time are updated to the tool life cycle energy curve model library. When the model library data volume is large enough, a neural network regression model between the tool energy characteristics and life can be established through methods such as deep learning networks and multi-model fusion algorithms, thereby achieving more accurate and faster tool life prediction.
[0112] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0113] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a cutting tool life monitoring method is implemented.
[0114] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0115] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0116] Step 302: Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal.
[0117] Step 304, obtain a tool lifecycle model library, and query the first tool lifecycle model that matches the tool to be monitored from the tool lifecycle model library according to the first torque characteristic, wherein each tool lifecycle model includes the motor torque characteristic of the corresponding tool throughout its entire life cycle.
[0118] Step 306 : determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model.
[0119] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0120] Step 302: Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal.
[0121] Step 304, obtain a tool lifecycle model library, and query the first tool lifecycle model that matches the tool to be monitored from the tool lifecycle model library according to the first torque characteristic, wherein each tool lifecycle model includes the motor torque characteristic of the corresponding tool throughout its entire life cycle.
[0122] Step 306 : determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model.
[0123] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0124] Step 302: Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal.
[0125] Step 304, obtain a tool lifecycle model library, and query the first tool lifecycle model that matches the tool to be monitored from the tool lifecycle model library according to the first torque characteristic, wherein each tool lifecycle model includes the motor torque characteristic of the corresponding tool throughout its entire life cycle.
[0126] Step 306 : determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model.
[0127] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.
[0128] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.
[0129] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.
[0130] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.
Claims
1. A cutting tool life monitoring method, characterized in that: The method comprises: Acquire a first motor torque signal generated by the tool to be monitored during the cutting process, and extract a first torque feature of the first motor torque signal; Acquire a tool life cycle model library, and query a first tool life cycle model matching the tool to be monitored from the tool life cycle model library according to the first torque characteristic, wherein each tool life cycle model includes a motor torque characteristic of the corresponding tool throughout its entire life cycle; determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model; The step of extracting the first torque feature of the first motor torque signal comprises: Acquire a section division rule, and divide the first motor torque signal into at least one section according to the section division rule; Using a wavelet packet decomposition method, the first motor torque signal of each section is divided into second motor torque signals of multiple frequency bands; Acquire signal energy values of the second motor torque signal of the plurality of frequency bands, and determine the maximum signal energy value among the signal energy values of the second motor torque signal of the plurality of frequency bands as the first torque feature of the corresponding segment in the first motor torque signal; wherein the maximum signal energy value among the signal energy values of the second motor torque signal of the plurality of frequency bands is an energy value obtained by summing the squares of the amplitudes of discrete points in the first frequency band; The querying, from the tool life cycle model library, of a first tool life cycle model that matches the tool to be monitored according to the first torque feature includes: Determining whether the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold; When it is determined that the number of tool life cycle models in the tool life cycle model library is less than a preset threshold, respectively calculating similarities between the first torque feature and torque features of multiple tool life cycle models in the tool life cycle model library to obtain multiple feature similarity values; Determining a first tool life cycle model that best matches the first torque feature according to the multiple feature similarity values; When it is determined that the number of tool life cycle models in the tool life cycle model library is greater than a preset threshold, respectively calculating similarities between the first torque feature and torque features of multiple tool life cycle models in the tool life cycle model library to obtain multiple feature similarity values; A plurality of first tool life cycle models matching the first torque feature are determined according to a preset feature similarity threshold and the plurality of feature similarity values.
2. The method according to claim 1, characterized in that The segment division rules include: Rule 1: dividing the first motor torque signal into at least one section according to the start and end time of at least one cutting subtask of the tool to be monitored during the cutting process; Alternatively, rule two, dividing the first motor torque signal into at least one section according to the tool feed amount and / or tool speed of the tool to be monitored during the cutting process.
3. The method according to claim 1, characterized in that: Determining the tool life of the tool to be monitored according to the first torque characteristic and the first tool life cycle model includes: Obtaining, according to the first torque characteristic, an initial torque characteristic corresponding to the tool to be monitored when executing a first cutting subtask and a cut-off torque characteristic when executing a last cutting subtask; Obtaining the tool wear stage currently in which the tool to be monitored is located according to the initial torque characteristics, the cut-off torque characteristics and the first tool life cycle model of the tool to be monitored, wherein the tool wear stage includes a rapid wear stage, a running-in stage and a prone to failure stage; The tool life of the tool to be monitored is determined according to the tool wear stage that the tool to be monitored is currently in.
4. The method according to claim 1, characterized in that: After determining a plurality of first tool life cycle models matching the first torque feature according to a preset feature similarity threshold and the plurality of feature similarity values, the method further includes: Obtaining a mapping relationship between torque characteristics and tool life according to the plurality of first tool life cycle models; The tool life of the tool to be monitored is determined according to the mapping relationship and the first torque characteristic.
5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cutting tool life monitoring method according to any one of claims 1 to 4 are implemented.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cutting tool life monitoring method according to any one of claims 1 to 4 are implemented.
7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the cutting tool life monitoring method according to any one of claims 1 to 4 are implemented.
