Cutter life prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a cutter service life prediction method and device, electronic equipment and a storage medium, and relates to the technical field of cutter quality monitoring, and the method comprises the steps: obtaining machining information; obtaining current values of at least part of preset evaluation indexes according to the processing information; at least part of the preset evaluation indexes comprise comprehensive vibration indexes; the current value of the comprehensive vibration index is determined based on tool turret vibration information and spindle vibration information; and inputting the current value of the comprehensive vibration index and the current values of other preset evaluation indexes into a tool life prediction model to obtain the residual life of the tool. According to the method, the tool tower vibration information and the spindle vibration information are obtained to determine the comprehensive vibration index, the tool wear dynamic change characteristics are comprehensively captured, and the prediction reliability can be ensured under different complex working conditions. The tool life prediction model is constructed by integrating the coupling relationship among the preset evaluation indexes, which is beneficial to improving the comprehensiveness and adaptability of the model and realizing comprehensive, reliable and accurate tool residual life online monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of tool quality monitoring, and in particular to a tool life prediction method, device, electronic equipment and storage medium. Background Art

[0002] In CNC machine tool processing, cutting tools are core components that directly impact the workpiece. Their quality and wear directly impact machining accuracy, production efficiency, and equipment safety. Tool wear or failure can lead to dimensional deviations, reduced surface quality, and even equipment failure or accidents. Therefore, real-time monitoring of remaining tool life and timely tool replacement are key to ensuring process stability and cost-effectiveness.

[0003] However, in related technologies, the method of evaluating tool quality mainly relies on stopping the machine to disassemble the tool for offline inspection, which affects processing efficiency and has obvious limitations. Summary of the Invention

[0004] The problem solved by the present invention is how to realize on-line monitoring of tool quality.

[0005] To solve the above problems, the present invention provides a tool life prediction method, comprising:

[0006] Acquiring processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information;

[0007] Obtaining current values of at least some of the preset evaluation indicators based on the machining information; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information;

[0008] The current value of the comprehensive vibration index and the current values of the other preset evaluation indicators are input into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

[0009] Optionally, obtaining current values of at least some preset evaluation indicators based on the processing information includes:

[0010] Performing feature extraction on the turret vibration information and the spindle vibration information respectively to obtain turret vibration features and spindle vibration features;

[0011] Determining, based on the machining information, a first adjustable weight corresponding to the turret vibration characteristic and a second adjustable weight corresponding to the spindle vibration characteristic;

[0012] A current value of the comprehensive vibration index is obtained according to the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic.

[0013] Optionally, the machining information further includes the aspect ratio of the workpiece, the spindle bearing temperature, the spindle speed, the tool overhang ratio, and the cutting force; and determining the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic based on the machining information includes:

[0014] When the aspect ratio is greater than a preset aspect ratio, and / or when the spindle bearing temperature is greater than a preset temperature, and / or when the spindle speed is greater than a preset speed, the first adjustable weight is greater than the second adjustable weight;

[0015] When the tool overhang ratio is greater than a preset ratio, and / or when the cutting force is greater than a preset cutting force, the first adjustable weight is less than the second adjustable weight.

[0016] Optionally, the processing information further includes spindle power information, tool temperature, workpiece temperature, material coefficient, and cutting parameters; the at least some of the preset evaluation indicators further include power indicators, temperature gradient indicators, and process indicators; and obtaining current values of at least some of the preset evaluation indicators based on the processing information includes:

[0017] Extracting features from the spindle power information to obtain spindle vibration features, and determining a current value of the power indicator based on the spindle vibration features;

[0018] obtaining a current value of the temperature gradient index based on a difference between the tool temperature and the workpiece temperature;

[0019] Based on the material coefficient and the cutting parameter, a current value of the process indicator is obtained.

[0020] Optionally, before inputting the current value of the comprehensive vibration index and the current values of the other preset evaluation indexes into the tool life prediction model, the method further includes:

[0021] Obtaining historical values of each of the preset evaluation indicators based on the acquired historical processing information;

[0022] Associating the historical value of each preset evaluation indicator with the corresponding historical tool remaining life to obtain a training data set; wherein the historical tool remaining life is used to indicate the corresponding remaining life of the tool when the historical processing information is obtained;

[0023] The training data set is used to train a preset initial model to obtain the tool life prediction model.

[0024] Optionally, the remaining life of the historical tool satisfies:

[0025]

[0026] Wherein, T represents the remaining life of the historical tool; G represents the historical value of the process index; a v represents the historical value of the comprehensive vibration index, α represents the preset first fitting parameter corresponding to the comprehensive vibration index; ω represents the historical value of the power index, β represents the preset second fitting parameter corresponding to the power index; ΔT represents the historical value of the temperature gradient index, and γ represents the preset third fitting parameter corresponding to the temperature gradient index.

[0027] Optionally, after obtaining the remaining life of the tool, the method further includes:

[0028] When the remaining life of the tool is less than or equal to a preset first life and greater than or equal to a preset second life, generating a cutting parameter adjustment prompt message; wherein the preset first life is greater than the preset second life;

[0029] When the remaining life of the tool is less than the preset second life and greater than the preset third life, generating a tool preparation prompt message; wherein the preset second life is greater than the preset third life;

[0030] When the remaining life of the tool is less than or equal to the preset third life, a tool retraction instruction is generated.

[0031] The present invention, by acquiring processing information such as turret and spindle vibration information during workpiece machining, facilitates providing a reliable reference for subsequent tool life prediction. Since vibrations caused by tool wear are transmitted to the turret through the tool and also to the spindle through the workpiece in contact with the tool, acquiring turret and spindle vibration information in the present invention facilitates a comprehensive understanding of the actual vibration conditions caused by tool wear. Based on this information, the current values of at least some of the preset evaluation indicators are obtained, which facilitates quantification of the preset evaluation indicators and ensures the accuracy of subsequent tool remaining life predictions. In particular, at least some of the preset evaluation indicators in the present invention include a comprehensive vibration indicator. Because the turret and spindle have different vibration response sensitivities and response characteristics to tool wear under different working conditions, the present invention determines the current value of the comprehensive vibration indicator based on the turret and spindle vibration information, which can fully capture the dynamic changes in tool wear. Furthermore, the tool life prediction model in the present invention is constructed based on each of the preset evaluation indicators, which facilitates integrating the coupling relationships between the preset evaluation indicators and improving the comprehensiveness and adaptability of the tool life prediction model. In this way, after obtaining the current value of the comprehensive vibration index and the current values of other preset evaluation indicators, the present invention can input them into the tool life prediction model pre-built based on each preset evaluation indicator. By utilizing multivariate information fusion, the reliability of the tool remaining life prediction can be ensured under different complex working conditions, and comprehensive, reliable and accurate tool remaining life online monitoring can be achieved. This ensures processing efficiency while also helping to avoid tool quality problems affecting workpiece processing quality.

[0032] The present invention also provides a tool life prediction device, comprising:

[0033] An acquisition module, which is used to acquire processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information;

[0034] a processing module configured to obtain, based on the machining information, current values of at least some of the preset evaluation indicators; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information;

[0035] A prediction module is used to input the current value of the comprehensive vibration index and the current values of other preset evaluation indicators into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

[0036] The advantages of the tool life prediction device provided by the present invention and the tool life prediction method are basically the same as those of the prior art, and will not be repeated here.

[0037] The present invention also provides an electronic device, comprising a memory and a processor;

[0038] The memory is used to store computer programs;

[0039] The processor is configured to implement the tool life prediction method described above when executing the computer program.

[0040] The advantages of the electronic device provided by the present invention and the tool life prediction method compared with the prior art are basically the same, and will not be repeated here.

[0041] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the tool life prediction method as described above is implemented.

[0042] The advantages of the computer-readable storage medium provided by the present invention and the tool life prediction method compared to the prior art are basically the same and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 Schematic diagram of the process of tool life prediction method according to an embodiment of the present invention;

[0044] Figure 2 Schematic diagram of the structure of a tool life prediction device according to an embodiment of the present invention;

[0045] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0047] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0048] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0049] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0050] In response to the problems existing in the above-mentioned related technologies, this embodiment provides a tool life prediction method, device, electronic device and storage medium.

[0051] like Figure 1 As shown, a tool life prediction method provided by an embodiment of the present invention includes the following steps:

[0052] S1: Acquire processing information during the workpiece processing; wherein the processing information includes turret vibration information and spindle vibration information.

[0053] Specifically, the processing information referred to in this embodiment represents various types of information in the process of processing parts, and the processing information may include turret vibration information and spindle vibration information. Among them, the turret is the core component of the machine tool, which mainly serves as a carrier and switching device for the tool. The spindle, as another core component of the machine tool, is mainly used to fix the workpiece in combination with the fixture and drive the workpiece to rotate. The tool is positioned and driven by the turret, and cooperates with the spindle to drive the workpiece to rotate, thereby completing the removal of the workpiece material. After the tool is worn, it is easy to change the stability of the cutting process, thereby causing vibration. The vibration of the cutting process will be transmitted to the turret through the tool on the one hand, and on the other hand, it will be transmitted to the spindle through the workpiece in contact with the tool. In this embodiment, the turret vibration information and the spindle vibration information during the workpiece processing process can be obtained respectively by a vibration detection device.

[0054] Optionally, in this embodiment, a three-axis vibration sensor disposed on the turret may be used to measure and obtain turret vibration information, and a three-axis vibration sensor disposed on the spindle may be used to obtain spindle vibration information.

[0055] S2: Obtaining current values of at least some of the preset evaluation indicators based on the processing information; wherein at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information.

[0056] Specifically, the preset evaluation index referred to in this embodiment represents an indicator capable of evaluating tool quality and can be set in advance. The comprehensive vibration index referred to in this embodiment represents an indicator that evaluates tool quality by combining turret vibration and spindle vibration. The current value of the preset evaluation index referred to in this embodiment is determined based on processing information acquired during workpiece machining and is used to quantify the preset evaluation index.

[0057] In one embodiment, the preset evaluation index includes a comprehensive vibration index, and the current value of the comprehensive vibration index can be determined based on the turret vibration information and the spindle vibration information. For example, in this embodiment, the turret vibration signal and the spindle vibration signal can be obtained once every fixed period (e.g., 50ms), and all turret vibration signals obtained within a preset time period (e.g., 2 minutes) are used as turret vibration information, and all spindle vibration signals obtained within a preset time period are used as spindle vibration information. On this basis, the current value of the comprehensive vibration index can be obtained based on the sum of the first vibration mean corresponding to the turret vibration information and the second vibration mean corresponding to the spindle vibration information.

[0058] S3: Inputting the current value of the comprehensive vibration index and the current values of other preset evaluation indicators into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each preset evaluation indicator.

[0059] Specifically, in this embodiment, a tool life prediction model can be pre-built based on each preset evaluation index. For example, historical processing information during the historical workpiece processing process can be obtained, and the historical values corresponding to each preset evaluation index can be obtained based on the historical processing information. On this basis, the wear amount corresponding to the tool when the historical processing information is obtained can be determined by offline measurement or other means, and the remaining life corresponding to the wear amount can be obtained according to the preset mapping relationship (such as wear amount 0 corresponds to 100% remaining life, wear amount 0.05mm corresponds to 0% remaining life), and the historical tool remaining life can be obtained. The historical values of each preset evaluation index are used as input, and the corresponding historical tool remaining life is used as output to train a preset initial model (such as an LSTM neural network model) to obtain a tool life prediction model. In actual use, the current value of the comprehensive vibration index and the current values of other preset evaluation indicators are input into the tool life prediction model to obtain the tool remaining life.

[0060] In this embodiment, acquiring processing information, such as turret and spindle vibration information, during workpiece machining facilitates providing a reliable reference for subsequent tool life prediction. Because vibrations caused by tool wear are transmitted to the turret through the tool and also to the spindle through the workpiece in contact with the tool, acquiring turret and spindle vibration information in this embodiment facilitates a comprehensive understanding of the actual vibration conditions caused by tool wear. Based on this information, the current values of at least some of the preset evaluation indicators are determined based on the processing information, which facilitates quantification of these indicators and ensures the accuracy of subsequent tool remaining life predictions. In this embodiment, at least some of the preset evaluation indicators include a comprehensive vibration indicator. Because the turret and spindle have different vibration response sensitivities and response characteristics to tool wear under different operating conditions, determining the current value of the comprehensive vibration indicator based on the turret and spindle vibration information in this embodiment comprehensively captures the dynamic characteristics of tool wear. Consequently, the tool life prediction model in this embodiment is constructed based on these preset evaluation indicators, which facilitates integrating the coupling relationships between these indicators and improves the comprehensiveness and adaptability of the tool life prediction model. In this way, after obtaining the current value of the comprehensive vibration index and the current values of other preset evaluation indicators, this embodiment can input them into the tool life prediction model pre-built based on each preset evaluation indicator. By utilizing multivariate information fusion, the reliability of the tool remaining life prediction can be ensured under different complex working conditions, and comprehensive, reliable and accurate online monitoring of the tool remaining life can be achieved. This ensures processing efficiency while also helping to avoid tool quality problems affecting workpiece processing quality.

[0061] Optionally, obtaining current values of at least some of the preset evaluation indicators based on the processing information includes:

[0062] Feature extraction is performed on the turret vibration information and the spindle vibration information respectively to obtain the turret vibration feature and the spindle vibration feature;

[0063] Determining a first adjustable weight corresponding to a turret vibration characteristic and a second adjustable weight corresponding to a spindle vibration characteristic based on the machining information;

[0064] The current value of the comprehensive vibration index is obtained according to the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic.

[0065] Specifically, in this embodiment, after obtaining the turret vibration information and the spindle vibration information, feature extraction can be performed on them respectively to obtain the turret vibration feature and the spindle vibration feature. Among them, the feature extraction referred to in this embodiment may include distribution feature extraction and statistical feature extraction. Accordingly, the turret vibration feature and the spindle vibration feature may both include distribution feature values and statistical feature values. For example, for the turret vibration information, a model such as a single-class support vector machine can be used to extract its distribution feature to obtain a distribution feature value. And a statistical feature extraction can be performed on it (such as obtaining the mean corresponding to multiple consecutive turret vibration signal values included in the turret vibration information) to obtain a statistical feature value. Then, the turret vibration feature is obtained based on the distribution feature value and the statistical feature value. Similarly, feature extraction can also be performed on the spindle vibration information to obtain the spindle vibration feature, which will not be repeated here.

[0066] Optionally, before extracting features from the turret vibration information and the spindle vibration information, the vibration signals contained therein may be subjected to wavelet packet decomposition, which is beneficial for filtering out low-frequency noise and retaining high-frequency features (such as tool chipping signals).

[0067] In one embodiment, a first adjustable weight corresponding to the turret vibration characteristic and a second adjustable weight corresponding to the spindle vibration characteristic can be determined based on the processing information. For example, assuming that the processing information includes the signal-to-noise ratios corresponding to the turret vibration information and the spindle vibration information, respectively, a weight allocation strategy can be pre-established based on the signal-to-noise ratio difference: when the absolute value of the signal-to-noise ratio difference between the turret vibration signal and the spindle vibration signal is less than 10%, the first adjustable weight is equal to the second adjustable weight. When the signal-to-noise ratio difference between the turret vibration signal and the spindle vibration signal is positive and greater than 10%, the first adjustable weight is greater than the second adjustable weight. When the signal-to-noise ratio difference between the turret vibration signal and the spindle vibration signal is negative and less than -10%, the first adjustable weight is less than the second adjustable weight. Based on this, the current value of the comprehensive vibration index can be obtained based on the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic.

[0068] In this embodiment, feature extraction is performed on the turret vibration information and the spindle vibration information respectively to obtain the turret vibration feature and the spindle vibration feature, which can quickly extract the key features related to tool wear, thereby improving the efficiency and accuracy of subsequent tool life prediction. Since the processing information can reflect the actual working conditions of the workpiece processing process, this embodiment determines the first adjustable weight corresponding to the turret vibration feature and the second adjustable weight corresponding to the spindle vibration feature based on the processing information, and then obtains the current value of the comprehensive vibration index based on the first adjustable weight corresponding to the turret vibration feature and the second adjustable weight corresponding to the spindle vibration feature. This is conducive to being compatible with the differences in the influence of the turret vibration feature and the spindle vibration feature on the actual wear of the tool under complex working conditions, thereby dynamically adjusting the weights of different vibration features according to the actual working conditions. While improving the adaptability of the tool remaining life prediction method to complex environments, it can also ensure the accuracy and reliability of the tool remaining life prediction.

[0069] Optionally, the machining information further includes a workpiece aspect ratio, a spindle bearing temperature, a spindle speed, a machining mode, a tool overhang ratio, and a cutting force; and determining a first adjustable weight corresponding to the turret vibration characteristic and a second adjustable weight corresponding to the spindle vibration characteristic based on the machining information includes:

[0070] When the aspect ratio is greater than a preset aspect ratio, and / or when the spindle bearing temperature is greater than a preset temperature, and / or when the spindle speed is greater than a preset speed, the first adjustable weight is greater than the second adjustable weight;

[0071] When the tool overhang ratio is greater than a preset ratio, and / or when the cutting force is greater than a preset cutting force, the first adjustable weight is less than the second adjustable weight.

[0072] Specifically, the aspect ratio of the workpiece in this embodiment represents the ratio between the total length of the workpiece and the diameter of the workpiece. The spindle bearing temperature referred to in this embodiment represents the temperature of the bearing that cooperates with the spindle during the workpiece processing process, which can be obtained based on a temperature detection device (such as an infrared temperature measuring device). The spindle speed referred to in this embodiment represents the speed of the spindle in the process of driving the workpiece to rotate, which can be obtained based on a speed measuring device (such as an encoder, etc.). The tool overhang ratio referred to in this embodiment represents the ratio of the tool overhang length to the total tool length, which can be measured and calculated in advance. The cutting force referred to in this embodiment represents the force generated by the interaction between the tool and the workpiece during the processing process. In actual use, the cutting force detected by the machine tool's status detection system can be directly received.

[0073] In this embodiment, the default values of the first adjustable weight and the second adjustable weight can be equal (such as both are 0.5). When the aspect ratio of the workpiece is greater than the preset aspect ratio (such as 10 to 15), the workpiece can be regarded as a slender rod, which may cause the spindle to vibrate greatly during the processing. At this time, the first adjustable weight of the turret vibration characteristic is greater than the second adjustable weight of the spindle vibration characteristic (such as the first adjustable weight is 0.2 and the second adjustable weight is 0.8), which is beneficial to avoid the additional vibration of the spindle caused by the processing of the slender rod affecting the reliability of the tool life prediction. When the spindle bearing temperature is greater than the preset temperature (such as 70°C), it indicates that the spindle bearing may have poor lubrication or severe wear. At this time, the first adjustable weight of the turret vibration characteristic is greater than the second adjustable weight of the spindle vibration characteristic, which is beneficial to reduce the abnormal vibration of the spindle caused by spindle bearing wear and other reasons that affect the accuracy of the tool remaining life prediction. When the spindle speed is greater than the preset speed, the vibration caused by factors such as unbalanced force will be further aggravated. At this time, the first adjustable weight of the turret vibration characteristic is greater than the second adjustable weight of the spindle vibration characteristic, which is beneficial to reducing the impact of abnormal vibration of the spindle caused by the spindle's own problems on the accuracy of tool remaining life prediction.

[0074] When the tool overhang ratio is greater than a preset ratio (such as 70%), the vibration signal is greatly attenuated during the process of being transmitted from the end of the tool to the turret. At this time, the turret vibration characteristic has a relatively low response to the vibration caused by tool wear. When the cutting force is greater than the preset cutting force (such as 80% of the limit cutting force), the abnormal change in cutting force caused by tool wear can be more realistically reflected in the spindle vibration characteristic. Under the above working conditions, the first adjustable weight for controlling the turret vibration characteristic is smaller than the second adjustable weight of the spindle vibration characteristic (such as the first adjustable weight is 0.7 and the second adjustable weight is 0.3), which is conducive to making full use of the high sensitivity of the spindle vibration characteristic under special working conditions, thereby ensuring the accuracy of tool life prediction.

[0075] Optionally, the processing information further includes spindle power information, tool temperature, workpiece temperature, material coefficient, and cutting parameters; at least some of the preset evaluation indicators further include power indicators, temperature gradient indicators, and process indicators; and obtaining current values of at least some of the preset evaluation indicators based on the processing information includes:

[0076] Extract the spindle power information to obtain the spindle vibration characteristics, and determine the current value of the power index based on the spindle vibration characteristics;

[0077] Based on the difference between the tool temperature and the workpiece temperature, the current value of the temperature gradient index is obtained;

[0078] Based on the material coefficients and cutting parameters, the current values of the process indicators are obtained.

[0079] Specifically, in this embodiment, after obtaining the spindle power information, feature extraction can be performed on it to obtain the spindle power feature. Among them, the feature extraction referred to in this embodiment may include distribution feature extraction and statistical feature extraction. Accordingly, the spindle power feature may include distribution feature values and statistical feature values. For example, a model such as a single-class support vector machine can be used to perform distribution feature extraction on the spindle power information to obtain distribution feature values. And statistical feature extraction can be performed on it (such as obtaining the peak values corresponding to multiple consecutive spindle power signal values in the spindle power information) to obtain statistical feature values. Then, the spindle power feature is obtained based on the distribution feature values and statistical feature values.

[0080] Optionally, before extracting features from the spindle power information, the spindle power signal in the spindle power information may be normalized based on a sliding time window, which is beneficial for eliminating the influence of fluctuations in machining parameters.

[0081] In one embodiment, a temperature detection device can measure the tool temperature and workpiece temperature separately, and based on the difference between the tool temperature and the workpiece temperature, the current value of the temperature gradient indicator can be obtained. For example, reference values corresponding to different difference intervals can be set in advance. In actual use, the difference interval within which the difference between the tool temperature and the workpiece temperature falls can be determined, and the reference value corresponding to this difference interval can be used as the current value of the temperature gradient indicator.

[0082] In one embodiment, the material coefficient referred to in this embodiment may include a tool material coefficient and a workpiece material coefficient; the cutting parameters may include a cutting speed and a feed rate; based on the material coefficient and the cutting parameters, the current value of the process indicator is obtained, including: obtaining a material constant according to the ratio of the tool material coefficient and the workpiece material coefficient, and determining a process correction coefficient according to the ratio of the cutting speed and the feed rate (such as pre-setting a reference correction coefficient corresponding to different ratio intervals, and using the reference correction coefficient corresponding to the ratio interval where the ratio of the cutting speed and the feed rate is located as the process correction coefficient); and then obtaining the current value of the process indicator based on the material constant and the process correction coefficient.

[0083] In this embodiment, spindle power information can reflect the energy consumption characteristics of the machining process, which are often closely related to tool wear. By extracting the spindle power signal to obtain the spindle vibration characteristics, the dynamic changes in spindle power characteristics caused by tool wear during machining can be fully captured. This effectively reflects the impact of tool wear on spindle power, thus providing a reliable reference for tool life prediction.

[0084] In this embodiment, the temperature difference between the tool and the workpiece reflects the distribution and transfer characteristics of the processing heat, and these characteristics are often closely related to cutting parameters, tool wear and material properties. By determining the difference between the tool temperature and the workpiece temperature, the temperature gradient characteristics can be effectively extracted, and the current value of the temperature gradient index can be obtained. The introduction of the temperature gradient index can more intuitively reflect the distribution of thermal loads during the processing process and further reveal the relationship between tool wear and temperature gradient characteristics. Especially under high-load processing conditions, the temperature gradient index can provide an important reference for the identification of early tool wear compared to other preset evaluation indicators such as the comprehensive vibration index.

[0085] In this embodiment, the material coefficient reflects the physical properties of the material, while the cutting parameters reflect the mechanical properties of the workpiece during machining. Different tool and workpiece materials have different corresponding vibration and damping properties, and the degree to which tool wear affects spindle and turret vibration varies under different cutting parameters. Therefore, in this embodiment, the current value of the process indicator is derived based on the material coefficient and cutting parameters. This helps to explore the impact of material and mechanical properties on tool wear-induced vibration in actual working conditions, thereby further improving the comprehensiveness, reliability, and accuracy of tool life prediction.

[0086] Optionally, before inputting the current value of the comprehensive vibration index and the current values of other preset evaluation indicators into the tool life prediction model, the method further includes:

[0087] Obtain historical values of each preset evaluation indicator based on the acquired historical processing information;

[0088] The historical values of each preset evaluation index are associated with the corresponding historical tool remaining life to obtain a training data set; wherein the historical tool remaining life is used to indicate the corresponding remaining life of the tool when the historical processing information is obtained;

[0089] The preset initial model is trained using the training data set to obtain the tool life prediction model.

[0090] Specifically, the historical processing information referred to in this embodiment represents processing information from the historical workpiece processing process. Historical values of each preset evaluation indicator can be derived based on this historical processing information. It should be understood that the method for deriving historical values of each preset evaluation indicator based on historical processing information in this embodiment is substantially the same as the method for deriving current values of each preset evaluation indicator based on processing information described above, and will not be further described here.

[0091] In this embodiment, the corresponding remaining life of the tool when the historical processing information is obtained can be determined. For example, the historical remaining life of the tool can be determined by actually measuring the wear amount or by a preset fitting relationship (i.e., the fitting relationship between the preset evaluation index and the remaining life of the tool). The historical values of each preset evaluation index are associated with the corresponding historical remaining life of the tool to obtain a training data set. The training data set is used to train a preset initial model (such as an LSTM neural network model) to obtain a tool life prediction model. This embodiment constructs a training model based on the historical values of the preset evaluation index and the corresponding historical remaining life of the tool, and uses the training model to train the preset initial model, which is conducive to fully learning and mining the coupling relationship between each preset evaluation index and the remaining life of the tool under complex working conditions through the model. While improving the adaptability of the model to complex working conditions, it can also break the limitations and unreliability of tool life prediction using a single evaluation index, and comprehensively improve the accuracy of tool life prediction.

[0092] Optionally, the remaining life of the historical tool meets:

[0093]

[0094] Among them, T represents the remaining life of the historical tool; G represents the historical value of the process index; A v represents the historical value of the comprehensive vibration index, α represents the preset first fitting parameter corresponding to the comprehensive vibration index; ω represents the historical value of the power index, β represents the preset second fitting parameter corresponding to the power index; ΔT represents the historical value of the temperature gradient index, and γ represents the preset third fitting parameter corresponding to the temperature gradient index.

[0095] In this embodiment, combined with the above-mentioned processing information affecting the historical values corresponding to the preset evaluation indicators, the historical tool remaining life can further meet the following requirements:

[0096]

[0097] Where G=(C d / C g )·(v / Δs), C d Indicates the tool material coefficient, C g represents the workpiece material coefficient, v represents the cutting speed, and Δs represents the feed rate; Q1 represents the first adjustable weight, Q2 represents the second adjustable weight, A k1 Represents the distribution characteristic value corresponding to the turret vibration information, A j1 Indicates the statistical characteristic value (such as mean) corresponding to the turret vibration information, A k2 Indicates the distribution characteristic value corresponding to the spindle vibration information, A j2 Indicates the statistical characteristic value (such as mean) corresponding to the spindle vibration information; pω =p k / p j , p k Indicates the distribution characteristic value corresponding to the spindle power information, p j Statistical characteristic value (such as peak value) corresponding to the spindle power information; ΔT = T d -T g , T d Indicates tool temperature, T g Indicates the workpiece temperature.

[0098] In this embodiment, the preset first fitting parameter, the preset second fitting parameter, and the preset third fitting parameter can be set in advance. For example, an estimate of the historical remaining tool life can be obtained based on the default values of each fitting parameter combined with the historical values of each preset evaluation indicator. On this basis, the actual value of the historical remaining tool life can be obtained (e.g., based on offline measurement). By adjusting each fitting parameter to continuously reduce the deviation between the estimated value and the actual value, each preset fitting parameter is determined, thereby achieving accurate fitting of the remaining tool life based on each preset evaluation indicator and the corresponding fitting parameter.

[0099] Optionally, after obtaining the remaining tool life, the remaining tool life prediction method further includes the following steps:

[0100] When the remaining life of the tool is less than or equal to a preset first life and greater than or equal to a preset second life, a cutting parameter adjustment prompt message is generated; wherein the preset first life is greater than the preset second life;

[0101] When the remaining life of the tool is less than the preset second life and greater than the third life, a tool preparation prompt message is generated; wherein the second life is greater than the preset third life;

[0102] When the remaining tool life is less than or equal to the preset third life, a retract instruction is generated.

[0103] Specifically, in this embodiment, the preset first life, the preset second life and the preset third life can be preset, and different preset lives represent different stages of the remaining life of the tool, which can correspond to different degrees of wear of the tool. Among them, the preset first life (such as 100%) is greater than the preset second life (such as 70%), and the preset second life is greater than the preset third life (such as 20%). For example, when the remaining life of the tool is less than or equal to the preset first life and greater than or equal to the preset second life, it means that the remaining life of the tool is between 70% and 100%, and a cutting parameter adjustment prompt message can be generated at this time. When the remaining life of the tool is less than the preset second life and greater than the third life, it means that the remaining life of the tool is between 20% and 70%, and a tool preparation prompt message can be generated at this time. When the remaining life of the tool is less than or equal to the preset third life, it means that the remaining life of the tool is less than 20%, and a tool retraction instruction can be generated at this time.

[0104] In this embodiment, the tool wear condition can be evaluated based on the relationship between the predicted remaining tool life and each preset life. When the remaining tool life is less than or equal to the preset first life and greater than or equal to the preset second life, it can be regarded as the tool being slightly worn. At this time, a cutting parameter adjustment prompt message is generated, which is conducive to avoiding further wear of the tool. When the remaining tool life is less than the preset second life and greater than the preset third life, it can be regarded as the tool being moderately worn. At this time, a tool preparation prompt message is generated, which is conducive to avoiding excessive downtime during subsequent tool changes, affecting the processing efficiency of the workpiece. When the remaining tool life is less than or equal to the preset third life, it can be regarded as the tool being severely worn. At this time, a tool retraction command is generated to stop the tool from processing the workpiece, which is conducive to avoiding safety accidents caused by tool instability or breakage. In this way, by setting a multi-level response strategy in this embodiment, it is conducive to the rational use of the prediction results of the remaining tool life, thereby ensuring the processing quality of the workpiece while also improving the safety of the processing process.

[0105] like Figure 2 As shown, an embodiment of the present invention provides a tool life prediction device 200, comprising:

[0106] An acquisition module 210 is configured to acquire processing information during workpiece processing; wherein the processing information includes turret vibration information and spindle vibration information;

[0107] a processing module 220 configured to obtain current values of at least some of the preset evaluation indicators based on the machining information; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information;

[0108] The prediction module 230 is used to input the current value of the comprehensive vibration index and the current values of other preset evaluation indicators into the tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

[0109] The tool life prediction device and tool life prediction method provided in this embodiment can produce substantially the same technical effects, which will not be described in detail here.

[0110] like Figure 3 As shown, an electronic device 300 provided by an embodiment of the present invention includes a memory 310 and a processor 320; the memory 310 is used to store computer programs; the processor 320 is used to implement the tool life prediction method as described above when executing the computer program.

[0111] In other words, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when executing the computer program:

[0112] Acquiring processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information;

[0113] Obtaining current values of at least some of the preset evaluation indicators based on the machining information; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information;

[0114] The current value of the comprehensive vibration index and the current values of the other preset evaluation indicators are input into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

[0115] The electronic device and the tool life prediction method provided in this embodiment can produce substantially the same technical effects, which will not be described in detail here.

[0116] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the tool life prediction method described above is implemented.

[0117] In other words, a non-volatile computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following operations:

[0118] Acquiring processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information;

[0119] Obtaining current values of at least some of the preset evaluation indicators based on the machining information; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information;

[0120] The current value of the comprehensive vibration index and the current values of the other preset evaluation indicators are input into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

[0121] The computer-readable storage medium provided in this embodiment and the tool life prediction method can produce substantially the same technical effects, which will not be described in detail here.

[0122] An electronic device 300 that can serve as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 300 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0123] The electronic device 300 includes a computing unit that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0124] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM). In this application, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present invention. In addition, the functional units in the various embodiments of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit. The above-mentioned integrated units can be implemented in the form of hardware or software functional units.

[0125] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A tool life prediction method, characterized in that: include: Acquiring processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information; Obtaining current values of at least some of the preset evaluation indicators based on the machining information; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information; The current value of the comprehensive vibration index and the current values of the other preset evaluation indicators are input into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

2. The tool life prediction method according to claim 1, characterized in that: Obtaining current values of at least some of the preset evaluation indicators based on the processing information includes: Performing feature extraction on the turret vibration information and the spindle vibration information respectively to obtain turret vibration features and spindle vibration features; Determining, based on the machining information, a first adjustable weight corresponding to the turret vibration characteristic and a second adjustable weight corresponding to the spindle vibration characteristic; A current value of the comprehensive vibration index is obtained according to the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic.

3. The tool life prediction method according to claim 2, characterized in that: The processing information further includes the aspect ratio of the workpiece, the spindle bearing temperature, the spindle speed, the tool overhang ratio, and the cutting force; and determining the first adjustable weight corresponding to the turret vibration characteristic and the second adjustable weight corresponding to the spindle vibration characteristic based on the processing information includes: When the aspect ratio is greater than a preset aspect ratio, and / or when the spindle bearing temperature is greater than a preset temperature, and / or when the spindle speed is greater than a preset speed, the first adjustable weight is greater than the second adjustable weight; When the tool overhang ratio is greater than a preset ratio, and / or when the cutting force is greater than a preset cutting force, the first adjustable weight is less than the second adjustable weight.

4. The tool life prediction method according to claim 1, characterized in that: The processing information further includes spindle power information, tool temperature, workpiece temperature, material coefficient, and cutting parameters; the at least some of the preset evaluation indicators further include power indicators, temperature gradient indicators, and process indicators; and obtaining current values of at least some of the preset evaluation indicators based on the processing information includes: Extracting features from the spindle power information to obtain spindle vibration features, and determining a current value of the power indicator based on the spindle vibration features; obtaining a current value of the temperature gradient index based on a difference between the tool temperature and the workpiece temperature; Based on the material coefficient and the cutting parameter, a current value of the process indicator is obtained.

5. The tool life prediction method according to claim 4, characterized in that: Before inputting the current value of the comprehensive vibration index and the current values of the other preset evaluation indexes into the tool life prediction model, the method further includes: Obtaining historical values of each of the preset evaluation indicators based on the acquired historical processing information; Associating the historical value of each preset evaluation indicator with the corresponding historical tool remaining life to obtain a training data set; wherein the historical tool remaining life is used to indicate the corresponding remaining life of the tool when the historical processing information is obtained; The training data set is used to train a preset initial model to obtain the tool life prediction model.

6. The tool life prediction method according to claim 5, characterized in that: The remaining life of the historical tool meets the following requirements: Wherein, T represents the remaining life of the historical tool; G represents the historical value of the process index; A v represents the historical value of the comprehensive vibration index, α represents the preset first fitting parameter corresponding to the comprehensive vibration index; ω represents the historical value of the power index, β represents the preset second fitting parameter corresponding to the power index; ΔT represents the historical value of the temperature gradient index, and γ represents the preset third fitting parameter corresponding to the temperature gradient index.

7. The tool life prediction method according to claim 1, characterized in that: After obtaining the remaining life of the tool, the method further includes: When the remaining life of the tool is less than or equal to a preset first life and greater than or equal to a preset second life, generating a cutting parameter adjustment prompt message; wherein the preset first life is greater than the preset second life; When the remaining life of the tool is less than the preset second life and greater than the preset third life, generating a tool preparation prompt message; wherein the preset second life is greater than the preset third life; When the remaining life of the tool is less than or equal to the preset third life, a tool retraction instruction is generated.

8. A tool life prediction device, characterized in that: include: An acquisition module, which is used to acquire processing information during the workpiece processing process; wherein the processing information includes turret vibration information and spindle vibration information; a processing module configured to obtain, based on the machining information, current values of at least some of the preset evaluation indicators; wherein the at least some of the preset evaluation indicators include a comprehensive vibration indicator; and the current value of the comprehensive vibration indicator is determined based on the turret vibration information and the spindle vibration information; A prediction module is used to input the current value of the comprehensive vibration index and the current values of other preset evaluation indicators into a tool life prediction model to obtain the remaining life of the tool; wherein the tool life prediction model is constructed based on each of the preset evaluation indicators.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the tool life prediction method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the tool life prediction method according to any one of claims 1 to 7 is implemented.

Images