Method and equipment for determining early warning parameters of hole drill tool and storage medium

Abstract

The invention relates to the technical field of intelligent manufacturing, in particular to a method and equipment for determining early warning parameters of a hole drill tool and a storage medium. The method comprises the following steps: determining a target wear stage of a hole drill tool based on a preprocessed vibration signal and an original current signal, and determining a target weight coefficient combination corresponding to the target wear stage; according to the current vibration kurtosis, the current acoustic emission energy, the current temperature difference and corresponding weight coefficients in the target weight coefficient combination, calculating to obtain a current weighted score; according to the current weighted score and the historical weighted score, the change rate of the current weighted score is calculated, and according to the size relation between the change rate of the current weighted score and the constraint change rate, the current remaining life needed by hole drill tool early warning is determined. According to the method, the state of the hole drill tool is monitored in real time by introducing various types of signals, and the differentiated influence of different wear stages on the hole drill tool is considered, so that the accuracy of the predicted residual life of the hole drill tool is ensured, and the prediction accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and particularly relates to a method for determining warning parameters of a hole drilling tool. Background Art

[0002] Hole drilling is a key process for machining high-precision holes in the manufacturing industry. During the workpiece manufacturing process, the hole drilling tool continuously bears complex working conditions such as high axial force, frictional heat, and difficult chip evacuation. The hole drilling tool is prone to failure faults such as wear, chipping, and coating peeling, resulting in a decline in machining quality and even workpiece scrapping. Generally, it is judged by human experience, lacking intelligent monitoring and warning.

[0003] Regarding the automated monitoring technology of hole drilling tools related to intelligent manufacturing technology, it performs automated warning based on the current signal of the motor during hole drilling tool machining, and only roughly predicts the remaining life of the hole drilling tool through the fluctuation of the current signal, resulting in a large error in the predicted remaining life. Summary of the Invention

[0004] In view of the above problems, this application provides a method, device, and storage medium for determining warning parameters of a hole drilling tool, which intelligently and automatically predicts the remaining life of the hole drilling tool through multiple types of signals to improve the prediction accuracy.

[0005] According to one aspect of this application, a method for determining warning parameters of a hole drilling tool is provided. The determination method includes: based on the preprocessed vibration signal and the original current signal, determining the target wear stage of the hole drilling tool, and determining the target weight coefficient combination corresponding to the target wear stage; the target weight coefficient combination includes the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy respectively; according to the current vibration kurtosis, current acoustic emission energy, current temperature difference, and the corresponding weight coefficients in the target weight coefficient combination, calculating the current weighted score; wherein, the current vibration kurtosis and current acoustic emission energy are parameters determined based on the preprocessed vibration signal and sound signal respectively, and the current temperature difference is a parameter determined according to the preprocessed sound signal and temperature signal; according to the current weighted score and the historical weighted score, calculating the current weighted score change rate, and determining the current remaining life required for warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate; wherein, the constraint change rate is a parameter determined based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool.

[0006] In another exemplary embodiment, the determination method further includes: determining a vibration kurtosis threshold, a temperature difference threshold, and an acoustic emission energy threshold required for early warning according to the material parameters of the hole drilling tool; comparing the current vibration kurtosis, the current temperature difference, and the current acoustic emission energy with the vibration kurtosis threshold, the temperature difference threshold, and the acoustic emission energy threshold respectively to obtain a plurality of comparison results; and if any comparison result indicates being greater than the corresponding threshold, giving an early warning.

[0007] In another exemplary embodiment, the determination method further includes: matching the material parameters of the hole drilling tool with a plurality of preset material parameters, and if the matching fails, determining a target preset material with the highest matching degree with the material parameters; selecting historical thresholds corresponding to the target preset material of a preset quantity as initial training samples; adjusting the quantity and / or parameter values of the initial training samples based on the parameter difference between the material parameters and the material parameters of the target preset material; and training a new threshold based on the adjusted training samples to be used as the threshold corresponding to the hole drilling tool.

[0008] In another exemplary embodiment, determining a target preset material with the highest matching degree with the material parameters includes: matching the high-frequency material parameters in the material parameters with the preset material parameters and calculating the corresponding matching degree; wherein the high-frequency material parameters are parameters associated with any one of the vibration kurtosis, the temperature difference, and the acoustic emission energy; performing weighted summation on the matching degrees of the high-frequency material parameters in each preset material to calculate the matching degree corresponding to each preset material; wherein each high-frequency material parameter in each preset material has its own weight coefficient; and taking the preset material corresponding to the preset material parameter with the highest matching degree as the target preset material.

[0009] In another exemplary embodiment, the determination method further includes: identifying a target frequency band signal involved in the coolant noise in the current sound signal; determining a decomposition layer number based on the frequency of the target frequency band signal and the frequency of the coolant noise to decompose the target frequency band signal to obtain multiple layers of sub-target frequency band signals; determining noise nodes in each layer of sub-target frequency band signals based on a preset strategy, and calculating a frequency threshold corresponding to each layer of noise nodes based on the frequencies of other nodes in the sub-target frequency band signals where the noise nodes of each layer are located; and if the frequency of the noise node is less than the corresponding frequency threshold, filtering the coolant noise in the corresponding noise node to obtain the filtered multiple layers of sub-target frequency band signals, so as to complete the preprocessing of the current sound signal and obtain the preprocessed sound signal.

[0010] In another exemplary embodiment, the preset policy includes a preset energy entropy and / or a preset zero-crossing value; determining the noise nodes in the sub-target frequency band signals of each layer based on the preset policy includes: traversing the nodes in the sub-target frequency band signals of each layer, and taking the traversed nodes as target nodes; if the energy entropy of the target node is greater than the corresponding preset energy entropy in the preset policy, and / or the zero-crossing value of the target node is greater than the corresponding preset zero-crossing value, then determining the target node as a noise node to determine the noise nodes in the sub-target frequency band signals of each layer.

[0011] In another exemplary embodiment, calculating the frequency threshold corresponding to the noise node of each layer based on the frequencies of other nodes in the sub-target frequency band signal of the layer where the noise node of each layer is located includes: multiplying the frequencies of each of the other nodes in the sub-target frequency band signal of the layer where the noise node of each layer is located by the weight coefficient corresponding to their respective frequency bands to obtain the weighted values corresponding to each of the other nodes in the sub-target frequency band signal of the layer where the noise node of each layer is located; summing up the weighted values corresponding to all the other nodes in the sub-target frequency band signal of the layer where the noise node of each layer is located, and taking the calculated sum value as the frequency threshold corresponding to the noise node of the corresponding layer.

[0012] In another exemplary embodiment, determining the current remaining life required for the warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate includes: if the current weighted score change rate is greater than or equal to the constraint change rate, determining a first correction coefficient according to the ratio of the current weighted score change rate to the constraint change rate, and calculating the current remaining life required for the warning of the hole drilling tool based on the first correction coefficient, the current weighted change rate, and the current weighted score; if the current weighted score change rate is less than the constraint change rate, determining a second correction coefficient according to the ratio of the current weighted score change rate to the constraint change rate, and calculating the current remaining life required for the warning of the hole drilling tool based on the second correction coefficient, the current weighted change rate, and the current weighted score; wherein, the calculation formulas of the first correction coefficient and the second correction coefficient are different; determining the replacement time of the hole drilling tool based on the current remaining life and the remaining time required for the current operation of the hole drilling tool.

[0013] In another exemplary embodiment, the determination method further includes: when the hole drilling tool finishes the current operation, collecting the hole diameter after the current operation ends to calculate the taper; if the absolute value of the difference between the taper and the predicted taper is greater than a preset value, correcting the weight coefficient in the target weight coefficient combination and the constraint change rate, and retraining the digital twin model; wherein, the predicted taper is a parameter predicted by the digital twin model based on the material parameters, geometric parameters, and historical operation data of the hole drilling tool.

[0014] In another exemplary embodiment, the determination method further includes: filtering the original vibration signal and the original temperature signal, and performing time-domain alignment on the filtered corresponding signals to obtain a preprocessed vibration signal and a preprocessed temperature signal; wherein, the original vibration signal is a vibration signal collected at different positions in the tool tip area at different acquisition frequencies at the current moment; based on the preprocessed sound signal and the preprocessed temperature signal, determining an abnormal area of the current hole drilling tool, and taking the difference between the temperature signals between the abnormal area and the surrounding area as the current temperature difference.

[0015] According to one aspect of the present application, there is provided an electronic device, including: a controller; a memory for storing one or more programs, which when executed by the controller, are used to execute the above determination method.

[0016] According to one aspect of the present application, there is also provided a computer-readable storage medium, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the above determination method.

[0017] According to one aspect of the present application, there is also provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above determination method.

[0018] The present application monitors the state of the hole drilling tool in real time by introducing various types of signals, and considers the differential effects of different wear stages on the hole drilling tool, that is, by the preprocessed vibration signal and the original current signal, determining the target wear stage of the hole drilling tool, according to the target weight coefficient combination corresponding to the target wear stage, and calculating three real-time state parameters (i.e., vibration kurtosis, acoustic emission energy, temperature difference), determining the corresponding real-time weighted score, and introducing the physically constrained transformation rate determined in real time for physical constraint to ensure the accuracy of the predicted remaining life of the hole drilling tool, thereby improving the prediction accuracy.

[0019] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present application, and are used together with the description to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other accompanying drawings based on these drawings without creative efforts.

[0021] Figure 1 is a schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in an exemplary embodiment of the present application.

[0022] Figure 2 is based on Figure 1 Another schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment.

[0023] Figure 3 is based on Figure 1 Another schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment.

[0024] Figure 4 is a schematic diagram of hierarchical decomposition of a target frequency band signal shown in an exemplary embodiment of the present application.

[0025] Figure 5 is based on Figure 3 Another schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment.

[0026] Figure 6 is based on Figure 3 Another schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment.

[0027] Figure 7 is a schematic diagram of the frequency band interval positions of noise nodes and other nodes in a sub-target frequency band signal shown in an exemplary embodiment of the present application.

[0028] Figure 8 is based on Figure 1 Another schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment.

[0029] Figure 9 is a schematic diagram of the application scenario of the method for determining warning parameters of the hole drilling tool of the present application.

[0030] Figure 10 is a schematic structural diagram of a device for determining warning parameters of a hole drilling tool shown in an exemplary embodiment of the present application.

[0031] Figure 11It is a schematic structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application. Detailed implementation manners

[0032] Here, the exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0033] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the drawings are only exemplary illustrations and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined. Therefore, the actual execution order may change according to the actual situation.

[0035] In the present application, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0036] Intelligent manufacturing is to realize the intelligence and innovation of the entire manufacturing value chain and is a further improvement in the deep integration of informatization and industrialization. Intelligent manufacturing integrates information technology, advanced manufacturing technology, automation technology, and artificial intelligence technology.

[0037] Regarding the automated monitoring technology of hole drilling tools related to intelligent manufacturing technology, when the hole drilling tool processes a workpiece, it performs automated warning based on the current signal of the motor, and can only roughly predict the remaining life of the hole drilling tool through the fluctuation of the current signal, resulting in a large error in the predicted remaining life.

[0038] For the process of deep hole drilling with a relatively high depth-to-diameter ratio, things like processing failures caused by the failure of the hole drilling tool often occur, usually accounting for more than 30% of the total processing failures. Therefore, it is urgent to improve the accuracy of automatically predicting the remaining life of the hole drilling tool.

[0039] To this end, one aspect of the present application provides a method for determining warning parameters of a hole drilling tool. For details, please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for determining warning parameters of a hole drilling tool shown in an exemplary embodiment of the present application. The determination method at least includes S110 to S130, which are introduced in detail as follows: S110: Based on the preprocessed vibration signal and the original current signal, determine the target wear stage of the hole drilling tool, and determine the target weight coefficient combination corresponding to the target wear stage; the target weight coefficient combination includes the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy respectively.

[0040] In this embodiment, corresponding preprocessing is performed on the original vibration signal, the original temperature signal, and the original sound signal. The preprocessing includes unified preprocessing for all types of signals. For example, the corresponding invalid signals in the original vibration signal, the original temperature signal, and the original sound signal are filtered, and the time domain characteristics of all signals are unified to facilitate the standardized processing of different types of signals; the preprocessing also includes personalized preprocessing for a certain type of signal. For example, for the original sound signal, noise filtering is performed so that the preprocessed sound signal can focus on the sound during the operation of the hole drilling tool, avoiding the adverse impact of noise on the prediction result, thereby improving the accuracy of the prediction result. Among them, the unified processing and the personalized preprocessing can be superimposed. For example, noise filtering (personalized preprocessing) is performed on the sound signal after the time domain characteristics are aligned (unified preprocessing) to obtain the preprocessed sound signal, further optimizing the accuracy of the sound signal, thereby improving the accuracy of the prediction result. Since the original current signal can reflect characteristics such as motor speed and power and does not require corresponding preprocessing, in this embodiment, the original current signal is directly used for relevant calculations. In some embodiments, it can be used after preprocessing the original current signal. The present application does not limit it.

[0041] The preprocessed vibration signal is a vibration signal characterizing the vibration generated by the contact between the hole drilling tool and the workpiece to be machined, including but not limited to the transient impact signal when the hole drilling tool contacts the workpiece to be machined, such as the pulse wave generated by chipping. The original vibration signal can be the signal collected by a vibration sensor installed at the clamping end of the hole drilling tool. The original current signal is a signal characterizing the current condition of the spindle motor at the current moment. By combining it with the shaft torque, the load fluctuation and wear degree of the hole drilling tool can be analyzed. If only the original current signal is analyzed, the chipping stage and other wear stages cannot be detected. The wear stages of the hole drilling tool are generally divided into the initial wear stage, the steady wear stage, and the severe wear stage. In the initial wear stage, the wear rate of the tool is relatively fast, the vibration kurtosis is slightly higher than the reference vibration kurtosis, and the change of the current signal is small (0 - 5%); in the steady wear stage, the wear rate of the tool tends to be gentle, the wear amount increases uniformly with the operation time, the vibration kurtosis tends to the reference vibration kurtosis, and the change of the current signal is moderate (5% - 15%); in the severe wear stage, the wear rate of the tool rises sharply, and chipping, cracks or plastic deformation may occur, the vibration kurtosis is significantly greater than the reference vibration kurtosis, and the change of the current signal is drastic (>15%). In multiple calibration experiments, the reference vibration kurtosis is 3, and the vibration signals and current signals in different wear stages are respectively recorded; based on the vibration signals in different wear stages, the vibration kurtosis in different wear stages is calculated to obtain the vibration kurtosis interval corresponding to each wear stage. For example, in the initial wear stage: [4.5, 6), in the steady wear stage: [1.2, 4.5), in the severe wear stage: [6, +∞]. According to the current signals in different wear stages, the current signal change rate in each wear stage is calculated. In the initial wear stage: (0, 5%), in the steady wear stage: [5%, 15%], in the severe wear stage: (15%, +∞).

[0042] In this embodiment, the preprocessed vibration signal and the original current signal are combined and analyzed to calculate the current vibration kurtosis and the current current change rate, and the target wear stage of the hole drilling tool at the current moment can be accurately determined. Based on the calibrated vibration kurtosis intervals and calibrated current change rate intervals corresponding to different wear stages determined in the above calibration experiments, the hole drilling tool wear stage determination table shown in Table 1 is constructed. In the construction of Table 1, considering that the current signal change rate can more accurately reflect the wear stage than the vibration kurtosis, the influence proportion of the current signal change rate on the determination of the wear stage is greater than that of the vibration kurtosis, that is, an adaptive fine-tuning is performed on the corresponding wear stage.

[0043] Exemplarily, the calculated current vibration kurtosis and current current change rate are respectively matched with the calibrated vibration kurtosis interval and the calibrated current change rate interval in Table 1 to determine two different types of intervals that are both successfully matched, and the wear stage corresponding to these two successfully matched intervals is used as the target wear stage of the hole drilling tool at the current moment. For example, if the current vibration kurtosis and current current change rate are 4.5 and 6% respectively, the target wear stage of the current hole drilling tool can be quickly determined to be the stable wear stage.

[0044] Among them, each wear stage corresponds to its own weight coefficient combination, and each weight coefficient combination includes the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy respectively. For the relevant weight coefficients in the weight coefficient combination of each wear stage, the sensitivity of various types of parameters in different wear stages is different in the calibration experiment, and the influence range and influence effect may also be different. The initial wear stage is mainly dominated by mechanical running-in, the vibration signal is sensitive, and the influence effects of temperature difference and acoustic emission energy are quite the same, so the weight coefficients corresponding to the two can be set the same. For example, the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy in the initial wear stage are 0.6, 0.2, and 0.2 respectively. The stable wear stage shows thermo-mechanical coupling influence and is in a thermal-mechanical equilibrium state. The vibration signal and temperature signal are relatively sensitive, so the weight coefficients corresponding to the two can be set the same. For example, the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy in the stable wear stage are 0.4, 0.4, and 0.2 respectively. The severe wear stage represents the precursor of macroscopic cracks / cutting edge chipping, the sound signal is the dominant one, the temperature signal is also relatively sensitive, and the vibration signal has the weakest influence. The weight coefficient corresponding to the high-frequency acoustic emission energy in this wear stage can be set to the maximum. For example, the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy in the severe wear stage are 0.2, 0.3, and 0.5 respectively.

[0045] Because in different wear stages, the influence range and influence effect of different types of parameters may be different, by adjusting the weight coefficients corresponding to the corresponding parameters, the influence proportion of the corresponding parameters on the corresponding wear stage is adjusted, so that the calculated weighted score is more in line with the current scenario and more accurate.

[0046] S120: Calculate the current weighted score according to the current vibration kurtosis, current acoustic emission energy, current temperature difference, and the corresponding weight coefficients in the target weight coefficient combination; among them, the current vibration kurtosis and current acoustic emission energy are parameters determined based on the preprocessed vibration signal and sound signal respectively, and the current temperature difference is a parameter determined according to the preprocessed sound signal and temperature signal.

[0047] The weighted score is a parameter characterizing the health or degradation state of the hole drilling tool. For example, the weighted score is a value ranging from 0 (healthy) to 1 (unhealthy) characterizing the health of the hole drilling tool. For another example, the weighted score is a value ranging from 0 (not degraded) to 1 (fully degraded) characterizing the degradation degree of the hole drilling tool.

[0048] Exemplary calculation method in S120: Multiply the current vibration kurtosis, the current acoustic emission energy, and the current temperature difference by their respective corresponding weight coefficients in the target weight coefficient combination, and sum up the calculated products to obtain the current weighted score. For example, after numerically processing the current vibration kurtosis, the current acoustic emission energy, and the current temperature difference, the obtained values are 8, 7, and 6 respectively. The weight coefficients corresponding to the vibration kurtosis, the temperature difference, and the acoustic emission energy in the target weight coefficient combination are 50%, 30%, and 20% respectively; the current weighted score = 8×50% + 7×30% + 6×20% = 7.3.

[0049] S130: Calculate the current weighted score change rate based on the current weighted score and the historical weighted score, and determine the current remaining life required for early warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate; where the constraint change rate is a parameter determined based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool.

[0050] To avoid the influence of a single accidental error on the prediction result, in this embodiment, the historical weighted score is introduced to calculate the current weighted score change rate, and physical constraints are imposed through the constraint change rate to avoid the prediction result deviating too much due to accidental errors. The constraint change rate is a parameter determined in real time based on the parameters of the hole drilling tool itself, as well as the target historical weighted score and the current weighted score, and is not a fixed preset parameter, achieving the purpose of dynamically constraining relevant parameters to a certain extent. The target historical weighted score is the weighted score corresponding to multiple historical moments characterizing the target wear stage. Here, the target wear stage can also be understood as multiple target wear stages, that is, it can be the historical weighted scores in multiple target wear stages. At the same time, the higher the correlation between the parameters of the hole drilling tool itself and the target historical weighted score, the closer the determined constraint change rate is to the current scenario and the more accurate it is. For example, the higher the matching degree between the historical material parameters and historical geometric parameters of the historical hole drilling tool corresponding to the target historical weighted score and the material parameters and geometric parameters of the current hole drilling tool, the higher the degree of management of the target historical weighted score and the current scenario, and the closer the determined constraint change rate is to the current scenario.

[0051] The following gives an exemplary description of the calculation method of the current weighted score change rate: Exemplarily, the historical weighted score in the process of calculating the current weighted score change rate is the historical weighted score corresponding to the previous moment. Exemplary calculation method: Divide the absolute value of the difference between the current weighted score and the historical weighted score at the previous moment by the historical weighted score at the previous moment to obtain the current weighted score change rate.

[0052] In another example, the historical weighted score in the process of calculating the current weighted score change rate is the historical weighted scores corresponding to multiple historical moments. Exemplary calculation method: Perform an averaging operation on the historical weighted scores corresponding to multiple historical moments adjacent to the current moment, divide the absolute value of the difference between the calculated average value and the current weighted score by the calculated average value to obtain the current weighted score change rate.

[0053] Next, an exemplary description will be given of the determination method of the constraint change rate, that is, how to determine the constraint change rate based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool: ΔR max =α×(|HV score - HV ref | / HV ref + |K IC score - K IC ref | / K IC ref + |K score - K ref | / K ref )+β×|G score - G ref | / G ref +γ×|R - R history | / R history ; Wherein, ΔR max represents the constraint change rate; α, β, and γ respectively represent the weight coefficients of the corresponding parameters, and the sum of the three weight coefficients is 100%. α, β, and γ can be the same, each being 1 / 3, indicating that the influence ratios of the material parameters, geometric parameters, and weighted scores on the constraint change rate are the same. In some embodiments, in order to highlight the influence of the material's own parameters on the constraint change rate, α and β can be made greater than γ. For example, both α and β are 0.45 and γ is 0.1. The specific values of the weight coefficients in this embodiment are not limited, and they can be determined according to relevant calibration experiments. HV score 、HV ref respectively represent the current material hardness and the standard material hardness. The material hardness characterizes the ability of the material to resist local plastic deformation, and |HV score - HV ref | / HV ref represents the hardness change rate between the current material hardness and the standard material hardness; K IC score 、KIC ref respectively represent the toughness of the current material and the toughness of the standard material. The material toughness characterizes the ability of the material to resist crack propagation and is related to fatigue resistance and chipping resistance performance, |K IC score -K IC ref | / K IC ref represents the toughness change rate between the toughness of the current material and the toughness of the standard material; K score 、K ref respectively represent the thermal conductivity of the current material and the thermal conductivity of the standard material,|K score - K ref | / K ref represents the thermal conductivity change rate between the thermal conductivity of the current material and the thermal conductivity of the standard material; G score represents the geometric score, a score calculated based on geometric parameters. For example, the edge radius × the clearance angle / the chip flute width; G ref represents the geometric score of the standard tool,|G score - G ref | / G ref characterizes the geometric difference change rate between the current hole drilling tool and the standard tool; R represents the current weighted score; R history represents the target historical weighted score, which can be the average of the historical weighted scores of a preset small number of samples (corresponding to the material parameters and geometric parameters of the current hole drilling tool);|R - R history | / R history represents the weighted score change rate. The standard material hardness, the standard material toughness, and the standard material thermal conductivity all refer to the material parameters of the target standard material (a standard material that is the same or similar to the current tool material and the current tool geometric parameters. For example, if the current tool material is aluminum alloy with a certain geometric size, then the relevant parameters of the aluminum alloy standard material with the same geometric size are selected for calculation). These parameters are all standard parameters accurately measured for each standard material in the calibration experiment. For example, in the calibration experiment, for the standard tool of aluminum alloy (with geometric parameters being the calibrated geometric parameters) and the standard tool of stainless steel. In order to simplify the relationship between the constraint change rate and the material parameter change rate, the geometric parameter change rate, and the weighted score change rate, the present application linearizes the relationship between the constraint change rate and them. In order to reflect the maximum constraint ability and calculate the maximum constraint change rate, the present application does not consider the positive and negative impacts of the material parameter transformation rate, the geometric parameter transformation rate, and the weighted score transformation rate on the constraint change rate, that is, does not consider the positive and negative of the three change rates, and regards the three change rates as positive impact parameters to calculate the constraint change rate with the maximum constraint ability. The above formula for the constraint change rate is applicable to simple scenarios and does not consider other influencing factors. In some embodiments, relevant item parameters can be corrected, and / or other factors affecting the constraint change rate can be considered to meet the calculation requirements of different scenarios.

[0054] In some embodiments, a hard threshold constraint may be imposed on the calculated ΔR max , that is, when ΔR max is greater than a preset hard threshold. One possible reason is that the characterized current calculated constraint change rate may not meet the requirements. It is necessary to check whether the material parameters, geometric parameters, target historical weighted score, and current weighted score conform to the numerical law: whether the numerical units are disordered, whether the numerical values themselves are significantly incorrect, etc., to avoid the situation where the calculated constraint change rate deviates from the actual application meaning due to calculation parameter errors. Another possible reason is that the target historical weighted score no longer conforms to the latest data change trend, and the target historical weighted score needs to be updated to ensure that the subsequent calculated ΔR max meets the hard threshold constraint conditions. For the above two possible reasons, a step-by-step investigation can be carried out. For example: first, check whether the material parameters, geometric parameters, target historical weighted score, and current weighted score conform to the numerical law; if they conform, update the target historical weighted score, and the calculated weighted score of the current calculated ΔR max and the current weighted score R, such as the constrained weighted score calculated by (1±ΔR max )×R, can be used as a basic training sample for updating the target historical weighted score. Based on this basic training sample, a small number (e.g., less than 50) of training samples are amplified to complete the update of the target historical weighted score. If they do not conform, specific error parameters need to be checked, corrected, and recalculated.

[0055] The following is an exemplary description of how to determine the current remaining life required for hole drilling tool warning based on the magnitude relationship between the current weighted score change rate and the constraint change rate: If the current weighted score change rate is greater than or equal to the constraint change rate, a first correction coefficient is determined based on the ratio of the current weighted score change rate to the constraint change rate, and the current remaining life required for hole drilling tool warning is calculated based on the first correction coefficient, the current weighted change rate, and the current weighted score. If the current weighted score change rate is less than the constraint change rate, a second correction coefficient is determined based on the ratio of the current weighted score change rate to the constraint change rate, and the current remaining life required for hole drilling tool warning is calculated based on the second correction coefficient, the current weighted change rate, and the current weighted score. Among them, the calculation formulas for the first correction coefficient and the second correction coefficient are different, and the corresponding correction coefficients can be calculated according to the following formulas: If the current weighted score change rate is greater than or equal to the constraint change rate, it indicates that the change in the current weighted score is out of constraint. In this scenario, the hole drilling tool will accelerate fatigue decay, and this scenario conforms to the material fatigue decay law of Paris' law. Paris' law describes the crack generated in materials due to fatigue under cyclic loading: da / dN = C(ΔK)m ; where, da / dN represents the crack growth length per load cycle; ΔK represents the stress intensity factor amplitude (i.e., the difference between the maximum stress intensity factor and the minimum stress intensity factor), which is related to the load magnitude, material geometry, etc.; C represents the through-crack propagation coefficient, which is related to the inherent properties of the material; m represents the sensitivity of the crack growth rate to ΔK, which is affected by environmental factors such as temperature and the stability of the environment where the material is located. According to Paris' law (i.e., from ΔK m it can be known), in this scenario, the fatigue decay of the hole drilling tool shows an exponential growth trend. Therefore, the change trend of the remaining life of the hole drilling tool is also an exponential trend. It is necessary to perform an exponential correction on the remaining life of the hole drilling tool to make the calculated current remaining life score more accurate and more in line with the current scenario. According to this law and relevant experimental data. It is explored that the first correction coefficient = 0.5×e 1 -ΔR / ΔRmax , the current remaining life score = 0.5×e 1-ΔR / ΔRmax ×(1 - R); of course, in some embodiments, the calculation formula of the first correction coefficient is different, but the same is that they are all calculated through an exponential formula, and no further examples will be given here. If the current weighted score change rate is less than the constraint change rate, it indicates that the change of the current weighted score does not deviate from the constraint. In this working condition, the fatigue decay trend of the hole drilling tool conforms to a linear change trend. Therefore, the change of the remaining life of the hole drilling tool is a linear change, and a linear adjustment of the remaining life of the hole drilling tool can be performed. The second correction coefficient = 1.2 - 0.3×ΔR / ΔR max . The current remaining life score = 1.2 - 0.3×ΔR / ΔR max ×(1 - R). Based on the current life score in the corresponding situation, the corresponding preset remaining life is determined, so as to obtain the current remaining life required for the hole drilling tool warning; where, ΔR max represents the constraint change rate; ΔR represents the current weighted score change rate; R represents the current weighted score; (1 - R) represents the initial current remaining life score, that is, the uncorrected initial score.

[0056] In this embodiment, according to the magnitude relationship between the current weighted score change rate and the constraint change rate, the corresponding correction coefficient calculation formula is selected to calculate the corresponding correction coefficient, and the calculated correction coefficient is combined with the current weighted change rate and the current weighted score to calculate the current remaining life score, so as to quickly obtain the current remaining life required for the hole drilling tool warning. The calculation method of the remaining life in this embodiment is more accurate. For the magnitude relationship between the two parameters, different correction coefficient calculation formulas are preset, so that the calculated correction coefficient better meets the data accuracy requirements of the actual scenario, improves the scenario adaptability of the correction coefficient, and makes the finally determined remaining life more accurate.

[0057] In some embodiments, if the change rate of the current weighted score is less than the constraint change rate, it indicates that the change rate of the current weighted score conforms to the data change law, and the data accuracy is relatively high. If data correction is performed again, the data accuracy cannot be significantly improved, but the data processing process will be lengthened. Therefore, in order to balance the data processing efficiency while ensuring the data accuracy, no processing is performed on the current weighted score, and the current remaining life is quickly determined directly based on the mapping relationship between the current weighted score and the preset remaining life. For example, the current remaining life score = (1 - R), where R represents the current weighted score; the corresponding preset remaining life is determined based on the current life score, so as to obtain the current remaining life required for the warning of the hole drilling tool.

[0058] In order to reduce the situation of downtime due to failures during the operation of the hole drilling tool, some embodiments of the present application consider the required duration of the operation to accurately determine the replacement time of the hole drilling tool: the replacement time of the hole drilling tool is determined based on the current remaining life and the remaining duration required for the current operation of the hole drilling tool. For example, if the current remaining life is 10 hours and the remaining duration required for the current operation of the hole drilling tool is 9 hours, then there is no need to replace the hole drilling tool before the end of the current operation, and the remaining service life of the hole drilling tool after the end of the current operation is 1 hour. If the required duration of the next operation is 2 hours, in order to avoid downtime failures caused by insufficient service life of the hole drilling tool during the next operation, the hole drilling tool should be replaced before the start of the next operation. This embodiment combines the remaining life of the hole drilling tool with the remaining duration required for the operation, which can avoid downtime failures caused by insufficient remaining service life of the tool during the operation, thereby reducing the downtime probability during the operation, preventing the workpiece from not meeting the standards due to downtime failures, and further ensuring the workpiece qualification rate.

[0059] The present application monitors the state of the hole drilling tool in real time by introducing multiple types of signals, and obtains four different types of signals: vibration, sound, heat, and electricity. According to the preprocessed vibration signal and the original electrical signal, the target wear stage of the hole drilling tool is determined. According to the target weight coefficient combination corresponding to the target wear stage and three calculated real-time state parameters (i.e., vibration kurtosis, acoustic emission energy, temperature difference), the corresponding real-time weighted score is determined, and a physically constrained transformation rate determined in real time is introduced to ensure the accuracy of the predicted remaining life of the hole drilling tool, thereby improving the prediction accuracy.

[0060] The warning operation in the related art needs to comprehensively analyze a variety of types of parameters to determine the warning signal, which highly depends on the comprehensive analysis process of the data and ignores the fault signals represented by local parameters.

[0061] To this end, in another exemplary embodiment of the present application, an early warning method based on a single type of parameter is added. For details, please refer to Figure 2 , Figure 2 is a schematic flow chart of another method for determining the early warning parameters of a hole drilling tool shown in the exemplary embodiment shown. This determination method, on the basis of S110 to S130 shown in Figure 1 , at least further includes S210 to S230, which are introduced in detail as follows: Figure 1 shown. S210: According to the material parameters of the hole drilling tool, determine the vibration kurtosis threshold, temperature difference threshold, and acoustic emission energy threshold required for early warning.

[0062] The material parameters include but are not limited to hardness, thermal conductivity, toughness, etc.

[0063] Exemplarily, the vibration kurtosis threshold = 2.5 (base value) + 0.05 × hardness; the temperature difference threshold = 150 - 0.3 × thermal conductivity (W / m·K); the acoustic emission energy threshold = 200 + 10 × toughness (MPa·m^0.5). The prerequisite for this example calculation method is that the material parameters of the hole drilling tool are preset material parameters, that is, the material parameters of the hole drilling tool are matched with the preset material parameters. If the corresponding preset material parameters are successfully matched, the corresponding threshold can be directly obtained based on the above calculation method.

[0064] If the matching fails, that is, the material parameters of the hole drilling tool and the preset material parameters both fail to match, it indicates that the material of the hole drilling tool is a new material. Determine the target preset material with the highest material parameter matching degree (that is, use the preset material with the highest material parameter matching degree with the new material as the target preset material), and select the historical thresholds corresponding to the preset number of target preset materials as the initial training samples.

[0065] Adjust the quantity and / or parameter values of the initial training samples based on the parameter differences between the material parameters of the material and the material parameters of the target preset material. Exemplarily, the target preset material is titanium alloy, and the new material is not titanium alloy. Analyze the differences between the material parameters of the new material and the material parameters of titanium alloy, including but not limited to analyzing the differences in parameters such as hardness, thermal conductivity, and toughness. For example, the differences in the numerical values of the corresponding parameters, as well as the total difference of all parameter differences: If the difference in thermal conductivity between the new material and the target preset material is large, the proportion of the quantity of the temperature difference threshold in the initial training samples can be reduced, and / or based on the relationship between the thermal conductivity and the temperature difference threshold, adaptively correct the numerical value of the temperature difference threshold. For example, the greater the thermal conductivity, the smaller the temperature difference threshold. If the thermal conductivity of the new material is greater than that of titanium alloy, the size of the temperature difference threshold in the initial training samples can be reduced. If the total difference of all parameter differences between the new material and the target preset material is large, reduce the total quantity of the initial training samples. Train a new threshold based on the adjusted training samples to be used as the threshold corresponding to the hole drilling tool, including: input the adjusted training samples into the training model, that is, input the multiple thresholds corresponding to various parameters into the training model for training to obtain their respective corresponding new thresholds.

[0066] The following will introduce in detail how to determine the target preset material with the highest matching degree with the material parameters: Match the high-frequency material parameters in the material parameters with the preset material parameters and calculate the corresponding matching degree; among them, the high-frequency material parameters are parameters associated with any one of the vibration kurtosis, temperature difference, and acoustic emission energy, and the high-frequency material parameters are parameters that affect the value of any one of the vibration kurtosis, temperature difference, and acoustic emission energy. Among them, "associated" means that there is an interaction relationship between the parameters. For example, the material thermal conductivity is a parameter closely related to the temperature difference. The temperature differences of materials with different material thermal conductivities may be different, that is, there is a correlation between the material thermal conductivity and the temperature difference size.

[0067] Because the high-frequency material parameters are parameters associated with any one of the vibration kurtosis, temperature difference, and acoustic emission energy, selecting the high-frequency material parameters as the matching object can find a preset material that is similar to the new material in terms of vibration kurtosis, temperature difference, and acoustic emission energy, thereby providing support for the preset data and avoiding the distortion of the calculated threshold due to the lack of reference parameters for the new material.

[0068] Perform weighted summation on the matching degrees of the high-frequency material parameters in each preset material to calculate the matching degree corresponding to each preset material; among them, each high-frequency material parameter in each preset material corresponds to its own weight coefficient.

[0069] Exemplarily, for the high-frequency material parameters of the preset material titanium alloy, namely hardness, thermal conductivity coefficient, and toughness, the corresponding weight coefficients are 50%, 20%, and 10% respectively. The parameter matching degrees of titanium alloy and the new material in terms of hardness, thermal conductivity coefficient, and toughness are 70%, 60%, and 40% respectively. Then, the calculated matching degree of titanium alloy = 50%×70% + 20%×60% + 10%×40% = 51%. By analogy, the matching degrees of each preset material are calculated, and the preset material corresponding to the highest matching degree among them is used as the target preset material. Through such refined calculations, the target preset material with a very high similarity to the new material can be accurately determined from multiple preset materials, and the relevant parameters corresponding to the target preset material can be used as a reference for the new material.

[0070] S220: Compare the current vibration kurtosis, current temperature difference, and current acoustic emission energy with the vibration kurtosis threshold, temperature difference threshold, and acoustic emission energy threshold respectively to obtain multiple comparison results.

[0071] S230: If any comparison result indicates being greater than the corresponding threshold, give an alarm.

[0072] In this embodiment, single-item alarms can be performed based on the current vibration kurtosis, current temperature difference, and current acoustic emission energy monitored at the current moment, that is, the respective alarm methods for multiple single-type parameters are set to attach importance to the fault signals represented by local single parameters.

[0073] In the related technical scenarios, generally, the processing, analysis, and alarm of data are integrated in the cloud for functional integration. If a communication failure occurs, it will affect the normal progress of the actual operation site, and the operation site cannot give an alarm for relevant faults in a timely manner. Therefore, the above S210 to S230 can be executed at the edge end of the operation site, that is, any determination method of the present application is loaded on the determination system. The determination system is used as the execution subject. The determination system includes not only the cloud server but also the edge end of the operation site, etc. The edge end can perform local data analysis, so as to give an alarm for single-type faults in a timely manner to ensure the timeliness of the alarm at the operation site and avoid safety accidents. The cloud server can perform operations with higher computational resource requirements such as digital twin simulation and model training, so as to cooperate with the edge end to optimize the operation process and make the operation more efficient and smooth.

[0074] During the deep hole drilling process, since the drill is in a deep and relatively enclosed space, there is a large amount of noise in the collected sound signal. In the related technology, generally, hard thresholding noise reduction processing is performed on the original sound signal, which will cause the sound signal after noise reduction processing to be distorted, resulting in large signal fluctuations and affecting the accuracy of the parameters obtained by subsequent calculations.

[0075] To this end, in another exemplary embodiment of the present application, hierarchical noise reduction processing is performed on the current sound signal to achieve refined noise reduction and avoid signal distortion. For details, please refer to Figure 3 , Figure 3 is a schematic flow chart of another method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment shown in Figure 1 . Based on S110 to S130 shown in Figure 1 , this determination method at least further includes S310 to S340, which are introduced in detail as follows: S310: Identify the target band signal involved in the coolant noise in the current sound signal.

[0076] In this embodiment, the coolant noise mainly includes: Turbulence noise: The noise generated by the high-speed impact of the coolant on the tool / workpiece surface to form a turbulent flow, mainly involving a wide frequency band (10 Hz to 50 kHz), and the involved band signal can be determined through octave analysis; Drop impact noise: The sound of the coolant droplets directly hitting the tool surface / workpiece, mainly involving a wide frequency band (20 Hz to 80 kHz), and the involved band signal can be detected through short-time zero-crossing rate; Cavitation bubble noise: The sound caused by the rupture of coolant bubbles due to local low pressure, mainly involving high-frequency bursts (100 Hz to 300 kHz), and the involved band signal can be determined by spectral kurtosis analysis.

[0077] S320: Based on the frequency of the target band signal and the frequency of the coolant noise, determine the decomposition layer number to decompose the target band signal to obtain multiple layers of sub-target band signals.

[0078] Based on the frequency of the target band signal and the frequency of the coolant noise, calculate the current signal-to-noise ratio, thereby determining the current decomposition layer number to decompose the target band signal into the corresponding number of multiple layers of sub-target band signals.

[0079] The decomposition layer number represents the corresponding number of decomposition operations for the target band signal, and the total number of signal layers is the decomposition layer number plus one. Exemplarily, please refer to Figure 4 , Figure 4 is a schematic diagram of the hierarchical decomposition of the target band signal shown in an exemplary embodiment of the present application. Among them, the determined decomposition layer number is 2, which means that the target band signal A will be decomposed 2 times, and there are a total of 3 layers of signals. The first layer signal is the target band signal A; the second layer signal is the signal decomposed based on the first layer signal, and the second layer signal is the sub-target band signals A1, A2...; the third layer signal is the signal decomposed based on each signal in the second layer signal, and the third layer signal is the sub-target band signals A11, A12, A21, A22, A23.

[0080] S330: Determine the noise nodes in the sub-target frequency band signals of each layer based on a preset strategy, and calculate the frequency threshold corresponding to each noise node based on the frequencies of other nodes in the sub-target frequency band signal of the layer where each noise node is located.

[0081] The preset strategy is a strategy for identifying noise nodes in a signal, including but not limited to the determination strategy of energy entropy and the determination strategy of a preset zero-crossing value.

[0082] A noise node represents a node of non-target signals such as noise in a frequency band signal. Filtering the noise at the corresponding noise node can make the characteristics of the target signal more obvious.

[0083] Exemplarily, the decomposition level is 2, that is, the target frequency band signal A is decomposed, and a total of 3 levels of signals are obtained. The first level is the original target frequency band signal A, the second level is the sub-target frequency band signals A1 and A2, and the third level is the sub-target frequency band signals A11, A12, A21, A22, and A23. The number of noise nodes in each sub-target frequency band signal can be one or multiple, and the present application does not limit it.

[0084] For the first-level signal, the nodes in the target frequency band signal A other than the noise node a are used as other nodes in A, and the frequency threshold corresponding to the noise node a is calculated based on the frequencies of each other node. For the second-level signal, the nodes in the sub-target frequency band signal A1 other than the noise node a' are used as other nodes in A1, and the frequency threshold corresponding to the noise node a' is calculated based on the frequencies of each other node, and so on. The frequency thresholds corresponding to the noise nodes in each second-level signal are calculated, so as to calculate the frequency thresholds corresponding to all noise nodes respectively.

[0085] S340: If the frequency of a noise node is less than its corresponding frequency threshold, filter the coolant noise in the corresponding noise node to obtain the filtered multi-layer sub-target frequency band signals, so as to complete the preprocessing of the current sound signal and obtain the preprocessed sound signal.

[0086] The "filtering" here can be understood as directly deleting the noise at the corresponding noise node. In some embodiments, it can be understood as weakening the noise at the corresponding noise node, that is, deleting part of the noise. The intensity of the weakening operation can be determined according to the level of the sub-target frequency band signal to which the noise node belongs, that is, each level corresponds to a corresponding weakening intensity. For example, the weakening intensity of the first level is the largest and decreases in turn, so that the preprocessed sound signal is smoother and the target features in the signal are more obvious.

[0087] In the process of filtering signals at different levels, filtering is generally performed based on the decomposition order, that is, the band signals obtained by decomposition first are filtered first, which easily ignores the impact of processing resources. That is, the processing resources required for filtering the band signals obtained by decomposition first are relatively large, and situations such as lag and stagnation are likely to occur, resulting in the inability to filter subsequent band signals normally. Therefore, in some embodiments, the currently available processing resources will be monitored. If the processing resources required for the currently to-be-filtered band signal are greater than the currently available processing resources, the filtering order of the currently to-be-filtered band signal will be adjusted backward to preferentially meet the filtering requirements of subsequent band signals, so as to avoid the occurrence of lag and stagnation during the processing of band signals due to insufficient available processing resources, and make the filtering process of band signals smoother.

[0088] The calculation of the frequency thresholds of each noise node takes into account the sub-target band signal where the noise node is located, other nodes in the sub-target band signal, and the level where it is located, and dynamically determines the corresponding frequency thresholds from three different levels, improving the adaptability of the frequency thresholds and making the frequency thresholds more adaptable to different scenarios.

[0089] The related technology directly filters the original band signal according to a fixed threshold at one time, without considering the impact of signal distortion, node band fluctuation, etc. on the signal characterization features after filtering, and it is easy to over-filter, resulting in signal distortion or large node band fluctuations. This application performs multi-level decomposition of the target band signal, determines the corresponding frequency thresholds based on other signals in the sub-target band signal at each level where each noise node is located to determine whether to filter it, so as to perform adaptive filtering on signals at each level, and avoid signal distortion and large band fluctuations on the premise of ensuring the filtered signal characteristics.

[0090] In another exemplary embodiment of this application, it introduces how to determine the noise nodes in each sub-target band signal based on a preset strategy. For details, please refer to Figure 5 , Figure 5 is based on Figure 3 The flow diagram of another method for determining the warning parameters of a hole drilling tool shown in the exemplary embodiment shown. This determination method in S330 as shown in Figure 3 at least further includes S510 to S520; among them, the preset strategy includes a preset energy entropy and / or a preset zero crossing value, and the details are introduced as follows: S510: Traverse the nodes in each layer of the sub-target band signal, and use the traversed nodes as target nodes.

[0091] This application traverses the nodes in each sub-target band signal at each level to ensure that each node is determined without omission to determine whether it is a noise node, so as to comprehensively and without omission determine all noise nodes.

[0092] S520: If the energy entropy of the target node is greater than the corresponding preset energy entropy in the preset policy, and / or the zero-crossing value of the target node is greater than the corresponding preset zero-crossing value, then the target node is determined as a noise node to determine the noise nodes in the sub-target frequency band signals of each layer.

[0093] The energy entropy detection method can effectively distinguish noise (high entropy) and valid signals (low entropy), and the zero-crossing value detection method can identify high-frequency noise. The combination of the two methods can identify the noise of coolant droplets directly hitting the tool surface / workpiece that is easily overlooked. Because in the deep hole drilling scenario, the tool tip can be approximately regarded as being in a closed space, and the noise of coolant droplets has a greater impact on the characteristics of the target signal. The two methods for determining noise nodes listed in this application mainly highlight the attention to the easily overlooked noise, and do not mean that this application only covers these two methods for determining noise nodes. This application can also be combined with other common detection methods for collaborative detection to determine the corresponding noise nodes.

[0094] The method for determining noise nodes in this application includes the method of energy entropy and / or zero-crossing value. By combining the two methods for determining noise nodes, while ensuring the determination process of key noise nodes, attention is paid to the noise of coolant droplets in the deep hole drilling scenario, thus meeting the determination requirements of noise nodes in specific scenarios to comprehensively and accurately determine the corresponding noise nodes.

[0095] In another exemplary embodiment of this application, it is introduced how to calculate the frequency threshold corresponding to each layer of noise nodes based on the frequencies of other nodes in the sub-target frequency band signals of the layers where each layer of noise nodes is located. For details, please refer to Figure 6 , Figure 6 is based on Figure 3 shown in the flow diagram of another method for determining the warning parameters of a hole drilling tool shown in the exemplary embodiment. This determination method in S330 as shown in Figure 3 at least further includes S610 to S620, which are introduced in detail as follows: S610: Multiply the frequencies of each of the other nodes in the sub-target frequency band signals of the layers where each layer of noise nodes is located by the weight coefficients corresponding to their respective frequency bands to obtain the weighted values corresponding to each of the other nodes in the sub-target frequency band signals of the layers where each layer of noise nodes is located.

[0096] The weight coefficients corresponding to each frequency band interval can be the same or different. In some embodiments, in order to ensure the smoothness of the frequency band interval where the noise node is located after filtering the noise node, the proportion of the weight coefficients corresponding to the other nodes near the noise node is increased, that is, the weight coefficient corresponding to the frequency band interval where the noise node is located is made greater than the weight coefficients corresponding to other frequency band intervals.

[0097] S620: Calculate the sum of the weighted values corresponding to all other nodes in the sub-target frequency band signal of the layer where each noise node is located, and use the calculated sum value as the frequency threshold corresponding to the noise node of the corresponding layer.

[0098] Combined with Figure 7 For illustrative purposes, Figure 7 FIG. is a schematic diagram of the frequency band interval positions of noise nodes and other nodes in the sub-target frequency band signal shown in an exemplary embodiment of the present application. Among them, the sub-target frequency band signal A1 belongs to the second-level signal. The sub-target frequency band signal A1 includes four frequency band intervals, and each frequency band interval corresponds to a corresponding weight coefficient: the weight coefficient corresponding to the first frequency band interval is 0.2, the weight coefficient corresponding to the second frequency band interval is 0.4, the weight coefficient corresponding to the third frequency band interval is 0.2, and the weight coefficient corresponding to the fourth frequency band interval is 0.2; the noise node a' of the sub-target frequency band signal A1 is placed in the second frequency band interval, and an example of the calculation formula for the frequency threshold corresponding to the noise node a' is as follows: Y = m1×(a1 + a2 + …… + a n ) + m2×(b1 + b2 + …… + b n ) + …… + m z ×(x1 + x2 + …… + x n ); Wherein, Y represents the frequency threshold corresponding to the noise node, and m1, m2 …… m z represent the weight coefficients corresponding to different frequency band intervals, and a 1、 a2 …… a n , b 1、 b2 …… b n , x 1、 x2 …… x n respectively represent the frequencies of other nodes in the corresponding frequency band intervals.

[0099] The present application does not limit the number of nodes in each frequency band interval. If the frequency band interval is equally divided, the number of nodes in each frequency band interval is the same. Then, except for the frequency band interval where the noise node is located, the number of other nodes in other frequency band intervals is the same, and the number of other nodes in the frequency band interval where the noise node is located is less than the number of other nodes in other frequency band intervals (i.e., excluding the noise node).

[0100] In some embodiments, in order to reflect the influence of the level on the frequency threshold, it is also necessary to consider the level to which the frequency band signal to which the noise node belongs, and introduce a level coefficient to correct the frequency threshold. An example of the calculation formula is as follows: Y = Q[m1×(a1 + a2 + …… + a n ) + m2×(b1 + b2 + …… + b n ) + …… + mz ×(x1 + x2 + …… + x n )]; where Q represents the layer coefficient corresponding to the layer to which the band signal belongs, and the interpretations of other parameters refer to the above formula. In this embodiment, by adjusting the layer coefficients of different layers, the frequency thresholds of different layers can be adjusted, that is, the filtering degree of noise nodes of different layers can be adjusted, so as to flexibly and accurately filter noise nodes.

[0101] By analyzing the nodes in the signal, this application takes into account the influence of other nodes on the noise nodes and the influence of the frequency band interval where the nodes are located. In some embodiments, the influence of the signal layer where the noise nodes are located is also taken into account, so as to accurately determine the frequency threshold corresponding to the corresponding noise node, and the scene adaptability is higher.

[0102] The relevant parameters involved in the determination method in each of the above exemplary embodiments can be applied to the digital twin model to predict the operation result. In order to improve the accuracy of the operation result, this application analyzes the prediction result and the actual result to determine whether to correct the digital twin model. The specific introduction is as follows: When the hole drilling tool finishes the current operation, collect the hole diameter after the current operation is completed to calculate the taper; if the absolute value of the difference between the taper and the predicted taper is greater than the preset value, correct the weight coefficient and the constraint change rate in the target weight coefficient combination, and retrain the digital twin model; where the predicted taper is a parameter predicted by the digital twin model based on the material parameters, geometric parameters, and historical operation data of the hole drilling tool.

[0103] The prediction process of the digital twin model not only requires the relevant parameters of the hole drilling tool (i.e., material parameters, geometric parameters, etc.), but also needs to combine historical operations and data for collaborative prediction. For the prediction accuracy of the digital twin model, the historical operation data is selected as the historical operation data of the historical hole drilling tool that is the same as or similar to the current hole drilling tool. For example, if the current hole drilling tool is made of titanium alloy, then select the historical operation data of the titanium alloy (or materials with similar properties) historical hole drilling tool with the same or similar material parameters and geometric sizes.

[0104] Exemplarily, when the current operation is completed, scan the hole diameter size of the machined workpiece. If the difference between the hole diameter size and the hole diameter size predicted by the digital twin model is 0.003 mm, the digital twin model needs to be retrained to improve the prediction accuracy of the digital twin model in real time.

[0105] In another exemplary embodiment of this application, it describes how to preprocess the corresponding parameters and how to determine the current temperature difference based on the preprocessed relevant parameters. For details, please refer to Figure 8 , Figure 8 is based on Figure 1Flow schematic diagram of another method for determining warning parameters of a hole drilling tool shown in the exemplary embodiment. Based on S110 to S130 shown in Figure 1 as shown, it further includes at least S810 to S820, which are introduced in detail as follows: S810: Filter the original vibration signal and the original temperature signal, and perform time-domain alignment on the corresponding filtered signals to obtain the preprocessed vibration signal and the preprocessed temperature signal; wherein, the original vibration signal is the vibration signal collected at different positions in the tool tip area at different sampling frequencies at the current moment.

[0106] The original vibration signal, the original temperature signal, and the original vibration signal represent the original signals collected by the acquisition device or equipment. For example, two high-frequency sensors (20 to 50 kHz) installed at the tool clamping end collect vibration signals at different sampling frequencies. The infrared thermal imager collects the temperature of the tool tip area at a frame rate of 100 Hz to obtain the corresponding temperature signal. The original sound signal collected by the acoustic emission sensor array.

[0107] S810 only exemplifies the preprocessing process of the original vibration signal and the original temperature signal. The preprocessing of the original sound signal can refer to S310 to S340 above. In some embodiments, the original sound signal is also filtered and S310 to S340 are executed to denoise the filtered sound signal to obtain the preprocessed sound signal. Similarly, the filtered vibration signal, temperature signal, and sound signal can be time-domain aligned to unify the time-domain characteristics between different signals to achieve the standardization of multiple types of signals. Among them, the filtering process includes but is not limited to invalid signal filtering and feature processing. For example, the corresponding blank signal (one of the invalid signals) is removed, and the Kalman filter is used to compensate the original temperature signal measured by the infrared thermal imager, that is, the original temperature signal is compensated.

[0108] In the related art, the vibration signal is collected only at a single fixed sampling frequency, which may cause the collected vibration signal to be unable to or disadvantageously represent specific characteristics, such as the chip entanglement feature. In this application, an acoustic emission sensor array is set up to collect multiple vibration signals at different positions in the tool tip area at different sampling frequencies. The chip entanglement feature frequency band can be extracted from the multiple vibration signals at different frequencies, and the acoustic emission energy mutation is identified by comparing the acoustic emission energy between the vibration signals at different frequencies to obtain the characteristic signs before tool fracture. Therefore, this application can better identify the chip entanglement feature frequency band (3 - 5 kHz) and the acoustic emission energy mutation before tool fracture.

[0109] S820: Based on the preprocessed sound signal and the preprocessed temperature signal, determine the abnormal area of the current hole drilling tool, and use the difference in the temperature signal between the abnormal area and the surrounding area as the current temperature difference.

[0110] The preprocessed sound signal here is the sound signal obtained by performing the above S310 to S340 for noise reduction processing.

[0111] The related art usually directly determines the temperature abnormal area based on the temperature signal. However, this temperature abnormal area may only be an area that is temporarily abnormal due to excessive friction temperature in a local part of the tool, and it may not necessarily represent the true abnormal area of the hole drilling tool, which is somewhat different from the abnormal area defined here. The abnormal area here is an area determined based on the processed sound signal and temperature signal. This abnormal area can not only represent the temperature abnormal area in the related art, but also represent the abnormal area when the hole drilling tool is in the true wear stage. According to the difference in the temperature signal between this abnormal area and the surrounding area, the current temperature difference is determined, and the current temperature difference is combined with the current vibration kurtosis and the current acoustic emission energy for analysis to determine the current remaining life of the hole drilling tool.

[0112] This application can generate a corresponding regional thermal image based on the preprocessed temperature signal, generate an acoustic emission spectrogram based on the preprocessed sound signal, and determine the abnormal area of the hole drilling tool according to the regional thermal image and the acoustic emission spectrogram. Exemplarily, the temperature abnormal area in the regional thermal image and the high-frequency energy aggregation area in the acoustic emission spectrogram are respectively determined, and the overlapping area of the temperature abnormal area and the high-frequency energy aggregation area is used as the abnormal area. In some embodiments, corresponding thermal image features and acoustic emission features are extracted from the overlapping area to determine the abnormal type of this abnormal area. For example, if a high-temperature point coincides with a high-frequency energy peak in the overlapping area, it indicates that the hole drilling tool may have a chipped edge. Another example is that if the high-temperature gradient area in the overlapping area corresponds to broadband energy, it indicates that the hole drilling tool may have a thermal crack. Another example is that based on the temperature fluctuation area and sideband frequency points in the overlapping area, it can be determined whether the coating of the hole drilling tool has peeled off.

[0113] In summary, this application determines the abnormal area of the current hole drilling tool more accurately based on the preprocessed sound signal and temperature signal, and the characterization meaning is wider than the temperature abnormal area in the related art. In some embodiments, the corresponding abnormal type can also be determined according to the thermal and acoustic features in the abnormal area, having a more accurate and extensive abnormal positioning ability.

[0114] In another exemplary embodiment of this application, an exemplary description of the application scenarios of the above multiple determination methods is given. For details, please refer to Figure 9 , Figure 9It is a schematic diagram of the application scenario of the method for determining the warning parameters of the hole drilling tool in this application. Among them, it includes the operation equipment end 100, the edge end 200, and the server 300. The three ends can be connected by wireless communication. This application does not limit the connection method between them. The physical distance between the operation equipment end 100 and the edge end 200 is relatively close. In some scenarios, the two can communicate data through a wired connection method, that is, the two can be placed at the operation site. The server 300 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. Among them, multiple servers can form a blockchain, and the server is a node on the blockchain. The server 300 can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This is not limited here either.

[0115] The operation equipment end 100 includes a hole drilling tool and a collection device arranged at a corresponding position. The collection device is used to collect the original vibration signal, the original sound signal, the original temperature signal, and the original current signal. Generally, the operation equipment end 100 directly sends relevant data to the server 300 in the cloud. However, in order to relieve the data processing pressure of the server 300 and avoid the situation of untimely warning due to poor remote communication, the edge end 200 can realize local data analysis, analyze and calculate based on various collected original signals, and calculate the current vibration kurtosis, the current acoustic emission energy, and the current temperature difference; compare their magnitudes with their respective corresponding thresholds respectively, so as to timely give a warning of single-type faults, ensure the timeliness of warning at the operation site, and avoid safety accidents. Of course, the server 300 can also integrate all functions to act as an execution subject to execute any of the determination methods shown in the above exemplary embodiments. The examples are as follows: The server 300 determines the target wear stage of the hole drilling tool based on the preprocessed vibration signal and the original current signal, and determines the target weight coefficient combination corresponding to the target wear stage; the target weight coefficient combination includes the weight coefficients corresponding to the vibration kurtosis, the temperature difference, and the acoustic emission energy respectively.

[0116] The server 300 calculates the current weighted score based on the current vibration kurtosis, the current acoustic emission energy, the current temperature difference, and the corresponding weight coefficients in the target weight coefficient combination; wherein, the current vibration kurtosis and the current acoustic emission energy are parameters determined based on the preprocessed vibration signal and sound signal respectively, and the current temperature difference is a parameter determined based on the preprocessed sound signal and temperature signal; the current vibration kurtosis, the current acoustic emission energy, and the current temperature difference can be parameters calculated by the server 300, or can be parameters calculated by the edge device 200 and sent to the server 300.

[0117] The server 300 calculates the current weighted score change rate based on the current weighted score and the historical weighted score, and determines the current remaining life required for the warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate; wherein, the constraint change rate is a parameter determined based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool.

[0118] Another aspect of the present application also provides a device for determining warning parameters of a hole drilling tool, as Figure 10 shown, Figure 10 is a schematic structural diagram of a device for determining warning parameters of a hole drilling tool shown in an exemplary embodiment of the present application. The determining device 1000 includes: A first determining module 1010, configured to determine the target wear stage of the hole drilling tool based on the preprocessed vibration signal and the original current signal, and determine the target weight coefficient combination corresponding to the target wear stage; the target weight coefficient combination includes the weight coefficients corresponding to the vibration kurtosis, temperature difference, and acoustic emission energy respectively.

[0119] A calculation module 1030, configured to calculate the current weighted score according to the current vibration kurtosis, the current acoustic emission energy, the current temperature difference, and the corresponding weight coefficients in the target weight coefficient combination; wherein, the current vibration kurtosis and the current acoustic emission energy are parameters determined based on the preprocessed vibration signal and sound signal respectively, and the current temperature difference is a parameter determined based on the preprocessed sound signal and temperature signal.

[0120] A second determining module 1050, configured to calculate the current weighted score change rate according to the current weighted score and the historical weighted score, and determine the current remaining life required for the warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate; wherein, the constraint change rate is a parameter determined based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool.

[0121] It should be noted that the determination device provided in the above embodiments and the determination method provided in the foregoing embodiments belong to the same concept. The specific manners in which each module and unit perform operations have been described in detail in the method embodiments and will not be elaborated here.

[0122] On the other hand, the present application also provides an electronic device, including: a controller; a memory for storing one or more programs, which, when executed by the controller, are configured to execute the above-mentioned determination method.

[0123] Please refer to Figure 11 , Figure 11 which is a schematic structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application, and shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application.

[0124] It should be noted that Figure 11 the computer system 1100 of the electronic device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0125] As Figure 11 shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1102 or the program loaded from the storage section 1108 into the random access memory (RAM) 1103, such as executing the method in the above embodiments. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, ROM 1102, and RAM 1103 are connected to each other through a bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.

[0126] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom can be installed into the storage section 1108 as needed.

[0127] Specifically, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1109, and / or installed from the removable medium 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are performed.

[0128] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0130] The units involved in the embodiments of the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0131] On the other hand, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned determination method is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist alone without being assembled into the electronic device.

[0132] On the other hand, the present application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the determination method provided in the above various embodiments.

[0133] According to one aspect of the embodiments of the present application, a computer system is also provided, including a central processing unit (CPU). It can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage part into a random access memory (RAM), such as executing the method in the above embodiments. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0134] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. A removable medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive as needed, so that a computer program read from it can be installed into the storage part as needed.

[0135] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation of the present application. Those of ordinary skill in the art can easily make corresponding adaptations or modifications according to the main concept and spirit of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope required by the claims.

Claims

1. A method for determining warning parameters of a hole drilling tool, characterized in that, The determination method includes: Based on the preprocessed vibration signal and the original current signal, determine the target wear stage of the hole drilling tool, and determine the target weight coefficient combination corresponding to the target wear stage; the target weight coefficient combination includes the weight coefficients corresponding to vibration kurtosis, temperature difference, and acoustic emission energy respectively; According to the current vibration kurtosis, current acoustic emission energy, current temperature difference, and the corresponding weight coefficients in the target weight coefficient combination, calculate the current weighted score; wherein, the current vibration kurtosis and current acoustic emission energy are parameters determined based on the preprocessed vibration signal and sound signal respectively, and the current temperature difference is a parameter determined according to the preprocessed sound signal and temperature signal; According to the current weighted score and the historical weighted score, calculate the current weighted score change rate, and determine the current remaining life required for early warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate; wherein, the constraint change rate is a parameter determined based on the material parameters, geometric parameters, target historical weighted score, and current weighted score of the hole drilling tool.

2. The determination method according to claim 1, wherein The determination method further includes: According to the material parameters of the hole drilling tool, determine the vibration kurtosis threshold, temperature difference threshold, and acoustic emission energy threshold required for early warning; Compare the current vibration kurtosis, current temperature difference, and current acoustic emission energy with the vibration kurtosis threshold, temperature difference threshold, and acoustic emission energy threshold respectively to obtain multiple comparison results; If any comparison result indicates being greater than the corresponding threshold, give an early warning.

3. The determination method according to claim 2, characterized in that, The determination method further includes: Match the material parameters of the hole drilling tool with multiple preset material parameters. If the match fails, determine the target preset material with the highest matching degree with the material parameters; Select the historical thresholds corresponding to the target preset material with a preset number as the initial training samples; Based on the parameter difference between the material parameters and the material parameters of the target preset material, adjust the quantity and / or parameter values of the initial training samples; Train a new threshold based on the adjusted training samples to be used as the threshold corresponding to the hole drilling tool.

4. The determination method according to claim 3, wherein Determining the target preset material with the highest matching degree with the material parameters includes: Match the high-frequency material parameters in the material parameters with the preset material parameters and calculate the corresponding matching degree; wherein, the high-frequency material parameters are parameters associated with any one of the vibration kurtosis, temperature difference, and acoustic emission energy; Perform weighted summation on the matching degrees of the high-frequency material parameters in each preset material to calculate the matching degree corresponding to each preset material; wherein, each high-frequency material parameter in each preset material has its own weight coefficient; Take the preset material corresponding to the preset material parameter with the highest matching degree as the target preset material.

5. The determination method according to claim 1, characterized in that The determination method further includes: Identify the target frequency band signal involved in the coolant noise in the current sound signal; Based on the frequency of the target frequency band signal and the frequency of the coolant noise, determine the decomposition layer number to decompose the target frequency band signal to obtain multiple layers of sub-target frequency band signals; Determine the noise nodes in the sub-target frequency band signals of each layer based on a preset strategy, and calculate the frequency threshold corresponding to each layer of noise nodes based on the frequencies of other nodes in the sub-target frequency band signals of the layer where each layer of noise nodes is located; If the frequency of the noise node is less than its corresponding frequency threshold, filter the coolant noise in the corresponding noise node to obtain the filtered multi-layer sub-target frequency band signals, so as to complete the preprocessing of the current sound signal and obtain the preprocessed sound signal.

6. The determination method according to claim 5, wherein The preset strategy includes a preset energy entropy and / or a preset zero-crossing value; Determining the noise nodes in the sub-target frequency band signals of each layer based on a preset strategy includes: Traverse the nodes in the sub-target frequency band signals of each layer, and use the traversed nodes as target nodes; If the energy entropy of the target node is greater than the corresponding preset energy entropy in the preset strategy, and / or the zero-crossing value of the target node is greater than the corresponding preset zero-crossing value, then determine the target node as a noise node to determine the noise nodes in the sub-target frequency band signals of each layer.

7. The determination method according to claim 5, characterized in that Calculating the frequency threshold corresponding to each layer of noise nodes based on the frequencies of other nodes in the sub-target frequency band signals of the layer where each layer of noise nodes is located includes: Multiply the frequencies of each other node in the sub-target frequency band signal of the layer where each layer of noise nodes is located by the weight coefficient corresponding to their respective frequency band intervals to obtain the weighted values corresponding to each other node in the sub-target frequency band signal of the layer where each layer of noise nodes is located; Sum up the weighted values corresponding to all other nodes in the sub-target frequency band signal of the layer where each layer of noise nodes is located, and use the calculated sum value as the frequency threshold corresponding to the noise nodes of the corresponding layer.

8. The determination method according to any one of claims 1 to 7, characterized in that, Determine the current remaining life required for the warning of the hole drilling tool according to the magnitude relationship between the current weighted score change rate and the constraint change rate, including: If the current weighted score change rate is greater than or equal to the constraint change rate, determine a first correction coefficient according to the ratio of the current weighted score change rate to the constraint change rate, and calculate the current remaining life required for the warning of the hole drilling tool based on the first correction coefficient, the current weighted change rate, and the current weighted score; If the current weighted score change rate is less than the constraint change rate, determine a second correction coefficient according to the ratio of the current weighted score change rate to the constraint change rate, and calculate the current remaining life required for the warning of the hole drilling tool based on the second correction coefficient, the current weighted change rate, and the current weighted score; wherein, the calculation formulas of the first correction coefficient and the second correction coefficient are different; Determine the replacement time of the hole drilling tool based on the current remaining life and the remaining time required for the current operation of the hole drilling tool.

9. An electronic device, characterized in that, Including: A controller; A memory for storing one or more programs, which when executed by the controller, cause the controller to implement the determination method described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, Stored thereon are computer-readable instructions, which when executed by a processor of a computer, cause the computer to execute the determination method described in any one of claims 1 to 8.

Images