High-performance diamond cutter wear detection device and method

Abstract

The invention discloses a high-performance diamond cutter wear detection device and method, and relates to the technical field of wear detection, and the device comprises a structural characteristic obtaining module which obtains cutter structural characteristics; the cutting working condition characteristic acquisition module is used for acquiring cutting working condition characteristics of the cutter; the wear risk assessment module is used for carrying out wear risk assessment; the maintenance period optimization module is used for receiving the real-time cutting working condition and adaptively optimizing the tool maintenance period and the detection index priority; and the optimization module is adjusted, and the real-time cutting parameters are optimized. The technical problems that the detection frequency cannot be dynamically optimized according to different cutting working conditions, the timeliness and accuracy of wear detection are insufficient, and the service life of the tool is influenced in the existing tool wear detection are solved, and the purposes of dynamically adjusting the detection period and the index priority according to the change of the cutting working conditions, improving the timeliness and accuracy of wear detection and improving the working efficiency are achieved. The service life of the cutter is prolonged, and the technical effect of online nondestructive flaw detection of the high-performance diamond cutter is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of wear detection, and particularly to a high-performance diamond tool wear detection device and method. Background Art

[0002] Currently, there are many drawbacks in the existing tool wear detection technologies. Traditional detection methods often adopt a fixed detection frequency without considering the differences in cutting conditions at all. In actual production, the cutting conditions are complex and variable, and factors such as different workpiece materials, cutting speeds, feed rates, and working environments (such as temperature and humidity) will all have varying degrees of influence on tool wear. However, the existing detection technologies cannot respond to these changes. In the working conditions where the tool wears quickly, the fixed detection frequency may lead to untimely detection, unable to detect the early wear signs of the tool in time, making the tool only be noticed when the wear is serious, which not only affects the machining accuracy but also may lead to workpiece scrapping, increasing production costs; while in the working conditions where the tool wears slowly, there will be over-detection, frequently interrupting production for detection, wasting a large amount of time and resources, and reducing production efficiency. At the same time, there are also obvious deficiencies in the accuracy of the existing wear detection technologies. Most rely on simple manual observation or single detection indicators, lacking in-depth analysis of the tool wear mechanism and comprehensive multi-parameter evaluation. For example, only judging tool wear by observing the surface roughness of the machined surface or the cutting sound cannot comprehensively and accurately grasp the wear state of the tool, and it is easy to ignore potential defects and subtle wear changes inside the tool. This lack of timeliness and accuracy in detection makes the tool unable to be maintained and replaced in a timely and effective manner, unable to achieve precise on-line non-destructive flaw detection, and greatly affecting the service life of the tool.

[0003] The technical problems that the existing tool wear detection cannot dynamically optimize the detection frequency according to different cutting conditions, the timeliness and accuracy of wear detection are insufficient, and the service life of the tool is affected. Summary of the Invention

[0004] This application provides a high-performance diamond tool wear detection device and method for solving the technical problems that the existing tool wear detection cannot dynamically optimize the detection frequency according to different cutting conditions, the timeliness and accuracy of wear detection are insufficient, and the service life of the tool is affected.

[0005] In view of the above problems, this application provides a high-performance diamond tool wear detection device and method.

[0006] In the first aspect of this application, a high-performance diamond tool wear detection device is provided. The device includes: A structure characteristic acquisition module is used to acquire the tool structure characteristics, where the tool structure characteristics include diamond material characteristics and substrate material characteristics; a cutting condition characteristic acquisition module is used to acquire the tool cutting condition characteristics, where the tool cutting condition characteristics include the working environment change range and the cutting parameter floating range; a wear risk assessment module is used to combine the tool structure characteristics and the tool cutting condition characteristics to conduct a wear risk assessment, analyze and determine the structurally weak areas and high wear areas of the tool, and conduct area level division to label the area maintenance level for each area; a maintenance inspection period optimization module is used to receive the real-time cutting conditions, where the real-time cutting conditions include the real-time cutting environment and real-time cutting parameters, and adaptively optimize the tool maintenance inspection period and the priority of the detection indicators according to the real-time cutting conditions; an adjustment and optimization module is used to conduct multi-element damage assessment detection on the structurally weak areas and high wear areas according to the tool maintenance inspection period and the priority of the detection indicators, and adjust and optimize the real-time cutting parameters according to the damage assessment detection results.

[0007] In the second aspect of the present application, a high-performance diamond tool wear detection method is provided, and the method includes: Acquire the tool structure characteristics, where the tool structure characteristics include diamond material characteristics and substrate material characteristics; acquire the tool cutting condition characteristics, where the tool cutting condition characteristics include the working environment change range and the cutting parameter floating range; combine the tool structure characteristics and the tool cutting condition characteristics to conduct a wear risk assessment, analyze and determine the structurally weak areas and high wear areas of the tool, and conduct area level division to label the area maintenance level for each area; receive the real-time cutting conditions, where the real-time cutting conditions include the real-time cutting environment and real-time cutting parameters, and adaptively optimize the tool maintenance inspection period and the priority of the detection indicators according to the real-time cutting conditions; conduct multi-element damage assessment detection on the structurally weak areas and high wear areas according to the tool maintenance inspection period and the priority of the detection indicators, and adjust and optimize the real-time cutting parameters according to the damage assessment detection results.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages: A structural characteristic acquisition module is used to acquire the structural characteristics of a tool; a cutting condition characteristic acquisition module is used to acquire the cutting condition characteristics of the tool; a wear risk assessment module is used to combine the tool structural characteristics and the tool cutting condition characteristics to conduct a wear risk assessment, analyze and determine the structurally weak areas and high-wear areas of the tool, and conduct area level division to label the area maintenance level for each area; a maintenance inspection cycle optimization module is used to receive the real-time cutting conditions and adaptively optimize the tool maintenance inspection cycle and the priority of detection indicators according to the real-time cutting conditions; an adjustment and optimization module is used to conduct multiple damage assessment detections on the structurally weak areas and high-wear areas according to the tool maintenance inspection cycle and the priority of detection indicators, and adjust and optimize the real-time cutting parameters according to the damage assessment detection results. It achieves the technical effects of dynamically adjusting the detection cycle and the priority of indicators according to the changes in cutting conditions, improving the timeliness and accuracy of wear detection, extending the service life of the tool, and realizing the online non-destructive flaw detection of high-performance diamond tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0010] Figure 1 FIG. is a schematic structural diagram of a high-performance diamond tool wear detection device provided by an embodiment of the present application; Figure 2 FIG. is a schematic flow diagram of a high-performance diamond tool wear detection method provided by an embodiment of the present application.

[0011] Description of the reference numerals: Structural characteristic acquisition module 10, cutting condition characteristic acquisition module 20, wear risk assessment module 30, maintenance inspection cycle optimization module 40, adjustment and optimization module 50. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The present application provides a high-performance diamond tool wear detection device and method, which are used to solve the technical problems that the existing tool wear detection cannot dynamically optimize the detection frequency according to different cutting conditions, and the timeliness and accuracy of wear detection are insufficient, affecting the service life of the tool.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a high-performance diamond tool wear detection device, and the device includes: A structural characteristic acquisition module 10, configured to acquire tool structural characteristics, where the tool structural characteristics include diamond material characteristics and substrate material characteristics.

[0015] Specifically, to obtain the diamond material characteristics and substrate material (such as cobalt-based alloy, copper-based alloy, etc.) characteristics in the tool structural characteristics, a series of professional means will be adopted. For the diamond material, a Raman spectrometer is used to analyze the crystal structure integrity and impurity situation. By measuring the Raman shift and peak intensity, it is judged whether there are lattice defects and the type and content of impurities; a scanning electron microscope (SEM) is used to observe the microscopic morphology of the diamond, including grain size, shape and distribution state, and these characteristics will affect the wear resistance and cutting performance of the tool. For the substrate material, if it is a cobalt-based alloy or a copper-based alloy, an X-ray fluorescence spectrometer (XRF) is used to accurately determine its chemical composition and determine the content of main elements such as cobalt and copper and other trace elements; metallographic analysis technology is adopted to observe the substrate material sample after grinding, polishing and corrosion treatment, and a metallographic microscope is used to analyze its metallographic structure, such as the phase structure (γ-phase, ε-phase ratio, etc.) of the cobalt-based alloy, the grain size and morphology of the copper-based alloy, etc., so as to comprehensively master the organizational structure characteristics of the substrate material; at the same time, hardness testing equipment, such as a Rockwell hardness tester and a Vickers hardness tester, is used to measure the hardness of the substrate material to understand its ability to resist deformation and wear. Through these methods, the diamond material characteristics and substrate material characteristics in the tool structural characteristics can be accurately obtained.

[0016] A cutting condition characteristic acquisition module 20, configured to acquire tool cutting condition characteristics, where the tool cutting condition characteristics include the working environment change range and the cutting parameter floating range.

[0017] Specifically, to obtain the cutting condition characteristics of the tool, that is, the working environment change range and the cutting parameter floating range, multiple monitoring devices and technical means need to work together. In terms of monitoring the working environment change range, multiple environmental sensors are arranged around the tool working area. For the temperature sensor, high-precision thermocouples or infrared thermometers are used and installed near the tool cutting area to measure the change of the environmental temperature during the cutting process in real time and accurately record the temperature fluctuation range. For example, when high-speed cutting metal materials, it is monitored whether the temperature fluctuates between 50 - 500 °C. The humidity sensor selects capacitive or resistive sensors to measure the humidity change of the working environment to judge whether the humidity changes within the range of 30% - 80% relative humidity. These humidity data have important effects on the use effect of the cutting fluid and the corrosion conditions of the tool and the workpiece. In addition, gas sensors are used to monitor the harmful gas components and concentrations in the working environment to ensure that when cutting some special materials, such as metals containing sulfur and phosphorus, the gas environment changes can be grasped in time to ensure the safety of operators and prevent the tool from being chemically corroded. In terms of obtaining the cutting parameter floating range, with the help of sensors and monitoring systems, the cutting force sensor generally adopts strain gauge type or piezoelectric type sensors and is installed on the tool shank or the machine tool workbench to accurately measure the magnitude and direction change of the cutting force during the cutting process and record the fluctuation range of the cutting force in different cutting stages. For example, during rough machining, the cutting force may change between 500 - 2000 N, and during finish machining, it fluctuates between 100 - 500 N. The rotational speed sensor can be an optoelectronic or magnetoelectric sensor and is installed near the machine tool spindle to monitor the rotational speed of the tool in real time and determine its rotational speed floating range under different machining tasks. For example, when milling aluminum alloy, the rotational speed may be adjusted between 1000 - 5000 revolutions per minute. The feed rate is measured by a displacement sensor installed on the machine tool feed axis, commonly a grating scale or a magnetic grating scale. By measuring the displacement of the tool per unit time, the change range of the feed rate is obtained. For example, in turning machining, the feed rate changes between 0.05 - 0.5 mm / r. Through the data collected by these sensors, after signal conditioning and data processing, the working environment change range and the cutting parameter floating range in the cutting condition characteristics of the tool can be accurately obtained, providing key data support for subsequent tool wear risk assessment and cutting process optimization.

[0018] The wear risk assessment module 30 is used to combine the tool structure characteristics and the tool cutting condition characteristics to conduct wear risk assessment, analyze and determine the structurally weak areas and high wear areas of the tool, and conduct regional grade division to label the regional maintenance grade for each area.

[0019] Specifically, for the tool structure characteristics, a finite element analysis software is used to calculate the mechanical stability of high-performance diamond tools. The hardness and brittleness data of diamond materials and the mechanical parameters of substrate materials (such as cobalt-based alloys and copper-based alloys) are input into the software to simulate the stress distribution and deformation of the tool under different cutting forces and cutting heats. At the same time, through material microscopic detection equipment, such as scanning electron microscope (SEM) combined with energy spectrum analysis (EDS), the interfacial element distribution and bonding strength between diamond and substrate materials are evaluated to extract the structurally weak areas. For the tool cutting condition characteristics, sensors are used to collect cutting parameters in real time. For example, the cutting speed is obtained through a rotational speed sensor, and the feed rate is measured through a displacement sensor; environmental monitoring equipment is used to obtain environmental parameters, such as temperature and humidity sensors to monitor the environmental temperature and humidity. At the same time, the material characteristics are obtained by analyzing the material composition and hardness test of the material to be cut. During the cutting process, with the help of an optical measurement system, such as a laser displacement sensor, the cutting contact position and contact area are determined to locate the high wear areas. In the correlation analysis section, a database is established to store cutting parameters, environmental parameters, and corresponding wear defect type data. Data mining algorithms, such as the Apriori algorithm, are used to analyze the correlation rules between data, establish a parameter-defect correlation group, and extract correlation detection indicators. Then, the analytic hierarchy process (AHP) is used to compare the importance of each correlation detection indicator pairwise, construct a judgment matrix, calculate the weight of each indicator, and generate the initial detection indicator priority. Finally, for the structurally weak areas and high wear areas, according to the area characteristics and the extracted correlation detection indicators, the area detection indicator type matching is realized. Using the weighted average method, considering the weight of each indicator and the influence degree of the area on the overall performance of the tool, the comprehensive weight of each area is calculated, and then the area maintenance level of each area is generated, providing a scientific basis for the precise maintenance of the tool.

[0020] The maintenance cycle optimization module 40 is used to receive real-time cutting conditions, where the real-time cutting conditions include real-time cutting environment and real-time cutting parameters, and adaptively optimize the tool maintenance cycle and the detection indicator priority according to the real-time cutting conditions.

[0021] Specifically, it receives in real time the real-time cutting condition information including the real-time cutting environment and real-time cutting parameters. By monitoring in real time the dynamic changes of cutting parameters (such as cutting speed, feed rate, cutting depth, etc.) and environmental parameters (such as environmental temperature, humidity, cutting fluid condition, etc.), it uses a preset risk assessment model to evaluate the risk trend of associated detection indicators. For example, if the cutting speed suddenly increases significantly and the environmental temperature rises, combined with historical data and algorithm models, it judges the impact degree on the tool wear risk, and then generates multiple risk adjustment coefficients such as risk acceleration coefficient and risk mitigation coefficient. Based on these risk adjustment coefficients, the priority of the initial detection indicators is corrected. It recalculates the priority weights of each detection indicator according to the influence degree of different risk adjustment coefficients on each detection indicator, so as to generate a detection indicator priority that better fits the current actual situation. At the same time, multiple risk adjustment coefficients are fused and calculated. For example, weighted average or neural network fusion methods are used to integrate these coefficients into a comprehensive result. According to this fusion result, the cycle optimization direction is extracted. If the fusion result shows that the current risk is high, the tool maintenance and inspection cycle is shortened to detect the tool wear condition more frequently; if the risk is low, the maintenance and inspection cycle is appropriately extended to reduce the maintenance cost on the premise of ensuring the normal use of the tool, and finally the adaptive optimization of the tool maintenance and inspection cycle is realized.

[0022] The adjustment and optimization module 50 is used to perform multi-factor damage assessment detection on the structurally weak area and the high wear area according to the tool maintenance and inspection cycle and the detection indicator priority, and adjust and optimize the real-time cutting parameters according to the damage assessment detection result.

[0023] Specifically, when the tool maintenance inspection cycle arrives, based on the determined priority of the detection indicators, multi-element damage assessment detection is carried out for the structurally weak areas and highly worn areas. Using a variety of high-precision sensors, such as piezoelectric sensors for measuring cutting force, infrared sensors for monitoring temperature, and acceleration sensors for detecting tool vibration, etc., data collection is carried out for the relevant detection indicators in each area. These sensors integrate the large amount of data collected to construct a multi-element damage assessment matrix containing different areas and different indicators. According to the priority of the detection indicators, corresponding weights are assigned to the data in the matrix for calibration to obtain a standard damage assessment matrix. Based on the standard damage assessment matrix, the ideal solution and the negative ideal solution are respectively defined for each structurally weak area and highly worn area. By calculating the relative distances between each area and the ideal solution and the negative ideal solution, the comprehensive defect score is obtained, thus completing the overall wear risk assessment and generating the damage assessment detection result. For example, if the relative distance between a highly worn area and the ideal solution is large, it indicates that the wear condition of this area is relatively serious. According to the damage assessment detection result, the high-risk wear areas and their corresponding wear degree values are extracted. Through a pre-established optimization model, control optimization vectors are extracted for these high-risk areas and wear degree values. This vector includes a cutting parameter optimization vector and an environmental parameter optimization vector. Then, an analysis of the associated influence between the environmental parameters and the cutting parameters is carried out, and a binary cross-tuning correlation coefficient is generated using a data analysis algorithm. If the environmental parameter optimization vector is a positive influence vector, it indicates that environmental optimization helps to reduce tool wear. At this time, after weakening the cutting parameter optimization vector using the binary cross-tuning correlation coefficient, the cutting parameters are optimized and adjusted; if the environmental parameter optimization vector is a negative influence vector, then after strengthening the cutting parameter optimization vector using the binary cross-tuning correlation coefficient, the cutting parameters are adjusted. For example, if it is found that the high temperature in the cutting area is an important factor leading to tool wear (the environmental parameter optimization vector is a positive influence vector), and the cutting speed is too fast (one of the cutting parameter optimization vectors), then the adjustment range of the cutting speed is appropriately reduced to achieve the purpose of both reducing tool wear and ensuring machining efficiency, thus completing the adjustment and optimization of the real-time cutting parameters.

[0024] In a possible implementation manner, the wear risk assessment module 30 further includes: A structurally weak area extraction unit, configured to perform mechanical stability calculation and material adhesion evaluation according to the tool structure characteristics, and extract the structurally weak areas according to the comprehensive analysis results.

[0025] A highly worn area extraction unit, configured to extract the material characteristics of the material to be cut, as well as the cutting contact position and contact area according to the tool cutting condition characteristics, perform tool wear distribution positioning, and extract the highly worn areas.

[0026] Specifically, after obtaining the tool structure characteristics, a finite element analysis software is used to calculate the mechanical stability. First, the geometric model of the tool is accurately imported into the software, including the diamond part and the substrate material part, and it is constructed according to the actual size and shape. For the diamond and the substrate material, accurate parameters such as elastic modulus and Poisson's ratio are set in the software according to their respective material properties. When simulating the tool operation, corresponding loads are applied according to common cutting conditions, such as dynamic and static loads like simulated cutting force and impact force, to make it as close as possible to the force condition of the tool during actual machining. Through the calculation function of the software, the stress and strain distribution of the tool under these loads are analyzed, and the areas where stress concentration occurs are observed. The areas with stress concentration are often less mechanically stable. For the evaluation of material adhesion, the adhesion stability between the diamond and the substrate material is mainly analyzed. On the one hand, the adhesion process during tool manufacturing is investigated in detail, and key process parameters such as welding temperature, pressure, and time are collected. Different welding methods (such as laser welding, electron beam welding, etc.) and process parameters have a great impact on the adhesion effect. For example, during laser welding, if the welding temperature is too high, it may cause local overheating of the material and affect the adhesion quality. On the other hand, high-precision measuring equipment such as optical microscopes and electron microscopes is used to measure the adhesion contact area between the diamond and the substrate material, accurate to the bonding situation at the microscopic level. Considering factors such as the adhesion process and the adhesion contact area, the material adhesion is evaluated. If there are defects in the adhesion process and the adhesion contact area is small, the material adhesion in this area is low. Finally, based on the results of the mechanical stability calculation and the material adhesion evaluation, the structurally weak areas are extracted. The areas with obvious stress concentration and low material adhesion are marked as structurally weak areas. For example, in the finite element analysis, it is found that the stress in a certain area far exceeds the average level, and at the same time, a small adhesion contact area and adhesion defects are observed in this area under the microscope, then this area is determined as a structurally weak area for subsequent key monitoring and maintenance.

[0027] When extracting the high-wear area based on the tool cutting condition characteristics, first, the material characteristics of the workpiece to be cut need to be obtained, including information such as its placement position, height, and size. These factors will affect the force condition and heat distribution during cutting. For example, if the placement position of the workpiece to be cut is inaccurate, it may lead to uneven cutting force and accelerate tool wear. At the same time, accurately measure the cutting contact position and contact area, which is crucial for judging the tool wear distribution. Using these data and combining with the tool wear theoretical model, the tool wear distribution is located. For example, through analysis, it is found that in the area with a large cutting contact area and concentrated cutting force, the tool wear rate is usually faster. After comprehensive analysis, the areas on the tool with relatively serious wear and high wear rate, that is, the high-wear areas, are determined.

[0028] In a possible implementation manner, the wear risk assessment module 30 further includes: An association detection index extraction unit is used to perform association analysis on cutting parameters and environmental parameters with wear defect types respectively, establish multiple parameter-defect association groups, and extract multiple association detection indexes according to the multiple parameter-defect association groups.

[0029] An initial detection index priority generation unit is used to perform initial detection weight configuration on the multiple association detection indexes and generate an initial detection index priority.

[0030] A regional maintenance level generation unit is used to perform regional detection index type matching on the structurally weak areas and high wear areas respectively, and perform comprehensive weight analysis according to the matched regional detection index types to generate the regional maintenance levels of each area.

[0031] Specifically, various data during the cutting process are continuously collected, including cutting parameters such as cutting speed, feed rate, and cutting depth, as well as environmental parameters such as environmental temperature and humidity. At the same time, the types of wear defects generated by the tool are recorded in detail, such as chipping, increased wear, and deteriorated surface roughness. These data are sorted into a transaction dataset, and each transaction represents a cutting process, which contains all the corresponding parameters of the cutting and the types of wear defects that occur. Subsequently, the Apriori algorithm is used to process the dataset. Support threshold and confidence threshold are set. Support is used to measure the frequency of occurrence of a certain parameter-defect combination in the dataset, and confidence measures the reliability of the occurrence of the corresponding defect when a certain parameter appears. The algorithm starts to mine frequent item sets, that is, parameter-defect combinations that meet the support threshold. For example, by scanning the dataset multiple times, calculate the support of different parameter and wear defect type combinations, and find the frequently occurring combinations. For example, when the cutting speed is higher than a certain threshold and the environmental temperature is higher than a specific value, the chipping phenomenon of the tool occurs frequently. Based on these frequent item sets, strong association rules are further generated, that is, rules that meet the confidence threshold, thereby establishing multiple parameter-defect association groups. From these association groups, multiple association detection indexes are extracted. For example, "the probability of tool chipping when the cutting speed is higher than X and the environmental temperature is higher than Y" is used as an association detection index. Using these indexes, the tool wear risk can be evaluated more accurately, providing a strong basis for tool maintenance.

[0032] Comprehensively sort out each related detection index and consider their unique value and importance in reflecting the tool wear risk. For example, some indexes are closely related to the wear of key parts of the tool, and they have a great impact on the overall performance of the tool; while some indexes are also related to wear, but the degree of influence is relatively small. Then, use the Analytic Hierarchy Process (AHP) to make pairwise comparisons of the importance of each related detection index, judge the relative importance of one index compared to another index when evaluating the tool wear risk, and construct a judgment matrix. Through the calculation and analysis of the judgment matrix, the relative weight of each related detection index is obtained. Finally, sort these related detection indexes according to the weight size. The index with a larger weight is ranked higher in the detection priority sequence, and thus the initial detection index priority is successfully generated. This priority provides clear guidance for subsequent tool detection work, ensuring that under limited detection resources and time, the key indexes that can best reflect the tool wear risk are detected first, greatly improving the detection efficiency and accuracy, and laying a solid foundation for timely discovering potential problems of the tool and ensuring the stable operation of the tool.

[0033] For structurally weak areas, based on the analysis results of their mechanical stability and material adhesion in the early stage, identify the key factors that may lead to the failure of this area. For example, if a structurally weak area is due to poor adhesion between diamond and the substrate material, which is prone to stress concentration under the action of cutting force, then the detection indicators related to cutting force (such as the magnitude of cutting force, the fluctuation range of cutting force) and the indicators related to material adhesion (such as the temperature change at the joint, because temperature change may affect the adhesion effect) become the matching types of detection indicators. For highly worn areas, determine the matching types of detection indicators according to their formation reasons, such as the hardness of the material to be cut, the cutting contact position and area, etc. If the highly worn area is caused by a large cutting contact area and high hardness of the material to be cut, then indicators such as the tool surface temperature (high-hardness materials generate more heat during cutting, which will accelerate tool wear) and the change rate of tool surface wear amount are included in the matching scope. After determining the matching types of detection indicators for each area, conduct a comprehensive weight analysis. Collect a large amount of historical data, which includes the values of each detection indicator under different working conditions and the corresponding tool wear degree and area maintenance situation. Use the multiple linear regression analysis method to analyze the influence degree of each detection indicator on the area wear degree. For example, through regression analysis, determine how much the wear degree of the structurally weak area will increase when the fluctuation range of cutting force increases by a certain value. According to the analysis results, assign corresponding weights to each detection indicator. Give higher weights to the indicators that have a greater impact on area wear; give lower weights to the indicators with less impact. Integrate and calculate the weights of all matching detection indicators within each area to obtain the comprehensive weight score of each area. According to the pre-set comprehensive weight score interval, divide the area maintenance levels. For example, the comprehensive weight score between 80 - 100 is the first-level maintenance area, where the wear risk of this area is high and needs key attention; 50 - 79 is the second-level maintenance area, which needs regular detection; below 50 points is the third-level maintenance area, with relatively low wear risk. In this way, complete the generation of area maintenance levels for structurally weak areas and highly worn areas, so as to arrange tool maintenance work targeted in the follow-up.

[0034] In a possible implementation manner, the maintenance cycle optimization module 40 further includes: A risk adjustment coefficient generation unit, which is used to monitor the dynamic changes of cutting parameters and environmental parameters in real time, conduct a risk trend assessment of associated detection indicators, and generate multiple risk adjustment coefficients according to the assessment results.

[0035] A detection indicator priority generation unit, which is used to correct the initial detection indicator priority based on the multiple risk adjustment coefficients to generate a detection indicator priority.

[0036] A cycle optimization direction extraction unit, which is used to fuse and calculate the multiple risk adjustment coefficients, extract the cycle optimization direction according to the fusion result, and adaptively optimize the tool maintenance cycle.

[0037] Specifically, cutting parameters (such as cutting force, rotational speed, feed rate) and environmental parameters (such as temperature, humidity, cutting fluid concentration) are collected at high frequency through various sensors. Using the sliding window technique, the collected time series data is segmented, and each window contains parameter values within a fixed time length. For the risk trend assessment of the correlation detection index, a logistic regression algorithm is adopted. A training set is constructed based on historical data, where the independent variables are the parameter values within each window, and the dependent variable is the corresponding tool wear state (normal, mild wear, severe wear, etc.). By training the logistic regression model, the quantitative relationship between each parameter and the tool wear risk is determined. During real-time monitoring, the parameter values of the current sliding window are input into the trained model, and the model outputs the probabilities of the tool being in different wear risk states. For example, if the probability of severe wear output by the model exceeds a set threshold (such as 0.3), it is determined that the current risk trend is a high risk. A risk adjustment coefficient is generated according to the risk assessment result, using the ARIMA model in time series analysis. The ARIMA model is used to predict the change trend of parameters in the future for a period of time. If the logistic regression assessment is a high risk, combined with the predicted parameter changes of the ARIMA model, the risk acceleration coefficient is calculated. For example, if it is predicted that the cutting force will continue to rise in the next few time steps and the increase amplitude is large, then the risk acceleration coefficient will increase accordingly. On the contrary, if the assessment is a low risk and the parameter changes are stable, a risk mitigation coefficient is generated.

[0038] After generating multiple risk adjustment coefficients, the correction of the initial detection index priorities begins. First, sort out the existing list of initial detection index priorities, and clarify each detection index (such as cutting force fluctuation detection, temperature change detection, etc.) and its corresponding initial weight. Match each risk adjustment coefficient with the associated detection index. For example, if the risk acceleration coefficient is related to the cutting force, find the weight corresponding to the cutting force fluctuation detection in the initial detection index. Adopt a weighted correction method. For the detection index corresponding to the risk acceleration coefficient, increase its weight by a certain proportion. For example, if the risk acceleration coefficient related to the cutting force is 1.5 and the original weight of the cutting force fluctuation detection index is 0.3, then the corrected weight is 0.3×1.5 = 0.45. For the detection index corresponding to the risk mitigation coefficient, reduce the weight by a proportion. After completing the correction of all detection index weights, reorder the detection indexes according to the new weight sizes. The index with the larger weight has a higher priority, generating a detection index priority that fits the current tool cutting condition and risk situation, ensuring that in subsequent detections, the indexes that have a more significant impact on the tool wear risk are given priority, and more efficiently guaranteeing the normal use of the tool and the smooth progress of processing.

[0039] After aggregating multiple risk adjustment coefficients, the weighted average method is used for fusion. First, different weights are assigned to them according to the importance of each risk adjustment coefficient's influence on tool wear. For example, the risk adjustment coefficient caused by the sudden change of cutting force is given a higher weight because it has a greater impact on tool wear; the risk adjustment coefficient caused by the change of environmental humidity has a relatively small impact on tool wear, so the weight is lower. After multiplying each risk adjustment coefficient by its corresponding weight and summing them up, the fusion result is obtained. If the fusion result is higher than the set high-risk threshold, it indicates that the current tool wear risk is at a high level. Then, shorten the tool maintenance and inspection cycle, detect and maintain the tool more frequently, and discover potential problems in a timely manner; if the fusion result is lower than the set low-risk threshold, it means that the tool wear risk is relatively low, so appropriately extend the maintenance and inspection cycle to reduce the maintenance cost while ensuring the normal operation of the tool; if the fusion result is between the high and low risk thresholds, keep the current maintenance and inspection cycle unchanged. In this way, the adaptive optimization of the tool maintenance and inspection cycle is realized, making it match the actual tool wear risk situation.

[0040] In a possible implementation manner, the maintenance and inspection cycle optimization module 40 further includes: A multi-element loss assessment detection execution unit, configured to regularly execute multi-element loss assessment detection according to the tool maintenance and inspection cycle.

[0041] An associated detection index configuration unit, configured to number multiple structurally weak areas and high wear areas, and configure the associated detection indexes for each area.

[0042] An index status set generation unit, configured to perform multi-element sensing detection on the associated detection indexes to generate an index status set for each detection area.

[0043] A multi-element loss assessment matrix construction unit, configured to construct a multi-element loss assessment matrix according to the numbered multiple structurally weak areas and high wear areas, in combination with the index status sets of each detection area.

[0044] A standard loss assessment matrix generation unit, configured to calibrate the weights of the multi-element loss assessment matrix according to the priority of the detection indexes to generate a standard loss assessment matrix.

[0045] A loss assessment detection result generation unit, configured to perform multi-element loss assessment detection on the structurally weak areas and high wear areas based on the standard loss assessment matrix to generate a loss assessment detection result.

[0046] Specifically, according to the pre-set tool maintenance cycle, multi-dimensional damage assessment and testing work is carried out. When the set maintenance time node is reached, the current cutting operation of the tool is first suspended to ensure that the testing environment is relatively stable. Then, professional technicians are arranged to use testing equipment to conduct comprehensive testing of the tool from multiple dimensions. An ultrasonic flaw detector is used to check whether there are defects such as cracks inside the tool, an electron microscope is used to observe the microscopic wear of the tool surface, and a hardness tester is used to measure the hardness changes of key parts of the tool. At the same time, the cutting parameter data of the tool in the most recent maintenance cycle, such as cutting force, cutting speed, feed rate, etc., as well as environmental parameter data such as cutting temperature and humidity, are collected. These test data obtained by different methods and equipment are summarized and integrated, and the wear state and damage degree of the tool are accurately judged from multiple perspectives such as material properties, physical properties, and working conditions. The multi-dimensional damage assessment test is completed to provide a reliable basis for the formulation of subsequent tool maintenance strategies.

[0047] After the identification of the weak areas and high wear areas of the tool structure is completed, these areas are assigned unique numbers in turn according to specific sequence rules to facilitate subsequent management and operation. After the numbering is completed, the most suitable related detection indicators are configured for each area according to the formation cause and potential risk characteristics. For the weak structural areas caused by defects in the material bonding process, detection indicators that can detect the material bonding strength and stress distribution at the joint are configured; for the high wear areas caused by uneven force during the cutting process, cutting force fluctuation monitoring, tool surface wear change tracking and other detection indicators are configured to ensure that each area can be monitored in a targeted manner, providing comprehensive and accurate data support for tool health assessment.

[0048] For the configured related detection indicators, multiple sensing technologies are used for multi-sensor detection. The cutting temperature is monitored in real time by infrared temperature sensors to obtain cutting temperature change rate data; the change in cutting edge micro-morphology is measured regularly by atomic force microscope; the cutting force fluctuation amplitude data is collected by piezoelectric force sensor, etc. The data collected by these sensors are integrated to generate the indicator status set of each detection area. For example, the indicator status set of area numbered 005 may include information such as the cutting temperature change rate of 5℃ / min, the change in cutting edge micro-morphology of 0.002μm, and the cutting force fluctuation amplitude of 3N.

[0049] Based on multiple numbered structurally weak areas and high wear areas, as well as the set of index statuses of each generated detection area, a multivariate loss assessment matrix is constructed. The rows of the matrix represent different numbered areas, and the columns correspond to each associated detection index. Taking an example of having 5 areas and 4 associated detection indexes, the first row of the matrix records the index data of area No. 001, such as the change rate of cutting temperature, the change amount of cutting edge microtopography, the fluctuation range of cutting force, and the change value of bonding strength; the second row records the corresponding data of area No. 002, and so on.

[0050] Since the importance degrees of different detection indexes for tool wear judgment are different, according to the pre-determined priority of detection indexes, the multivariate loss assessment matrix is calibrated with weights. For example, through a large number of experiments and data analysis, it is determined that the weight of the change rate of cutting temperature is 0.4, the weight of the change amount of cutting edge microtopography is 0.3, the weight of the fluctuation range of cutting force is 0.2, and the weight of the change value of bonding strength is 0.1. By multiplying each element in the matrix by the corresponding weight, a standard loss assessment matrix is generated, making the data in the matrix more accurately reflect the wear risks of each area.

[0051] For each structurally weak area and high wear area, based on the best performance parameters for the normal operation of the tool and the worst performance parameters for the inability to operate normally, the ideal solution and the negative ideal solution are precisely defined respectively. Then, the associated detection index values of each structurally weak area and high wear area are accurately extracted from the standard loss assessment matrix, and using a distance calculation formula, such as the Euclidean distance formula, the relative distances between each area and the ideal solution and the negative ideal solution are calculated to measure the gap between the actual situation of each area and the best and worst situations. After that, according to the pre-set calculation rules, the comprehensive defect score of each area is calculated based on the relative distances. This score comprehensively reflects the wear degree of this area. Finally, by integrating the comprehensive defect scores of all areas and combining the pre-set wear risk level division criteria, a comprehensive assessment of the overall wear risk of the tool is carried out, clearly judging whether the tool is in a state of slight wear, moderate wear or severe wear, etc., so as to generate a detailed and instructive loss assessment detection result, providing a strong basis for the subsequent maintenance and replacement decisions of the tool.

[0052] In a possible implementation manner, the loss assessment detection result generation unit further includes: An ideal solution definition unit, which is used to define the ideal solution and the negative ideal solution respectively for each structurally weak area and high wear area.

[0053] A relative distance calculation unit, which is used to extract the associated detection index values of each structurally weak area and high wear area based on the standard loss assessment matrix, and calculate the relative distances between each area and the ideal solution and the negative ideal solution.

[0054] The overall wear risk assessment unit is used to calculate and generate the comprehensive defect score of each area according to the relative distance, and conduct an overall wear risk assessment based on the comprehensive defect score of each area to generate a damage assessment and detection result.

[0055] Specifically, for each structurally weak area and high-wear area, the ideal solution and the negative ideal solution are defined respectively. The ideal solution represents the perfect numerical values of various associated detection indicators in this area when the tool is in the best operating state. For example, for the high-wear area of the tool edge, the cutting temperature in its ideal solution may be set to the temperature value at which the tool material can stably cut with the least wear, and the change amount of the edge shape is set to zero, that is, there is no wear deformation. The negative ideal solution is the numerical values of various associated detection indicators in this area when the tool is completely ineffective or extremely severely worn. For example, the cutting temperature reaches the limit tolerance temperature of the tool material, and the change amount of the edge shape exceeds the maximum range that can be used normally.

[0056] After completing the construction of the standard damage assessment matrix, in-depth analysis is carried out on each structurally weak area and high-wear area based on this matrix. From the standard damage assessment matrix, the associated detection indicator values corresponding to each structurally weak area and high-wear area are accurately extracted in sequence according to the area number. For example, the first row of data in the matrix corresponds to area 001, and the data such as the cutting force fluctuation value, temperature change amount, and tool surface roughness change in this row are the associated detection indicator values of area 001. For each area with the indicator values extracted, it is compared with the previously defined ideal solution and negative ideal solution. The ideal solution represents the ideal numerical values of each indicator when the tool is in a perfect state, and the negative ideal solution represents the numerical values of each indicator when the tool is in the worst state. Taking the Euclidean distance calculation method as an example, for a certain area, the difference between its associated detection indicator value and the corresponding indicator value in the ideal solution is squared, then the sum of the squares of all indicator differences is added, and finally the square root of the sum is taken to obtain the relative distance between this area and the ideal solution. This distance value quantifies the degree of difference between this area and the best state. In the same way, calculate the difference between the associated detection indicator value of this area and the corresponding indicator value in the negative ideal solution, and follow the above steps of taking the square root of the sum of squares to obtain the relative distance between this area and the negative ideal solution. This distance reflects the degree of closeness between this area and the worst state. Through the calculation of these two relative distances, the deviation of each area from the ideal and worst cases in the current state can be comprehensively and accurately measured, providing key data support for subsequent assessment of the wear degree of the area.

[0057] After obtaining the relative distances of each region from the ideal solution and the negative ideal solution, weights are set according to the different degrees of influence of each correlation detection index on tool wear, and the sum of all index weights is 1. For example, after analysis, the weights of the three main correlation detection indexes, namely cutting temperature, tool surface roughness, and cutting force, are determined to be 0.5, 0.2, and 0.3 respectively. When calculating the comprehensive defect score, the relative distances of each region from the ideal solution and the negative ideal solution on each index are multiplied by the corresponding index weights respectively and then summed up after weighting. Suppose the relative distances of a certain region from the ideal solution on these three indexes are A, B, and C respectively, and the relative distances from the negative ideal solution are D, E, and F respectively. The calculation method of the comprehensive defect score is as follows: First, calculate the weighted sum related to the ideal solution (0.5×A + 0.2×B + 0.3×C) and the weighted sum related to the negative ideal solution (0.5×D + 0.2×E + 0.3×F) respectively, and then divide the weighted sum related to the negative ideal solution by the result of adding these two weighted sums, that is, (0.5×D + 0.2×E + 0.3×F)÷(0.5×A + 0.2×B + 0.3×C + 0.5×D + 0.2×E + 0.3×F), so as to obtain the comprehensive defect score of this region. The higher the score, the more serious the wear defect of this region. After calculating the comprehensive defect scores of each region, an overall wear risk assessment is carried out. For a single part, the comprehensive defect score is compared with a pre-set wear threshold. If the comprehensive defect score of a certain region is lower than the low wear threshold, it is determined that this region is in a low wear state; if the score is between the low wear threshold and the high wear threshold, it is in a medium wear state; if it is higher than the high wear threshold, it is in a high wear state. The wear states of all structurally weak regions and high wear regions are summarized and analyzed, and an overall damage degree assessment is carried out according to factors such as the proportion of the number of regions in different wear states and the wear degree of key regions. If the high wear state regions are concentrated in the key parts of the tool and account for a large proportion, the overall damage degree is high; if most regions are in a low wear state, the overall damage degree is low. According to the overall damage degree assessment result, combined with the specific wear conditions of each region, a detailed loss assessment and detection result is generated, clearly indicating which regions of the tool are severely worn, which regions can still be used normally, and the overall wear risk level of the tool, providing an accurate basis for the subsequent repair, replacement, or adjustment of machining parameters of the tool.

[0058] In a possible implementation manner, the adjustment and optimization module 50 further includes: A wear degree value extraction unit, configured to extract high-risk wear regions and wear degree values based on the loss assessment and detection result.

[0059] A control optimization vector extraction unit, configured to extract control optimization vectors for the high-risk wear regions and wear degree values, where the control optimization vectors include a cutting parameter optimization vector and an environment parameter optimization vector.

[0060] A binary cross - modulation correlation coefficient generation unit for analyzing the correlated influence between environmental parameters and cutting parameters and generating a binary cross - modulation correlation coefficient.

[0061] A cutting parameter optimization unit for, when the environmental parameter optimization vector is a positive influence vector, weakening the cutting parameter optimization vector through the binary cross - modulation correlation coefficient and then optimizing the cutting parameters.

[0062] A cutting parameter optimization vector enhancement unit for, when the environmental parameter optimization vector is a negative influence vector, enhancing the cutting parameter optimization vector through the binary cross - modulation correlation coefficient and then optimizing the cutting parameters.

[0063] Specifically, high - risk wear areas and corresponding wear degree values are extracted. Through the analysis of the loss assessment detection results, those areas with a comprehensive defect score exceeding a specific high - risk threshold are screened out, determined as high - risk wear areas, and the corresponding quantitative wear degree values are obtained, which can intuitively reflect the severity of wear in that area.

[0064] After the high-risk wear area and the corresponding wear degree value are determined, it is necessary to conduct in-depth analysis and extract the control optimization vector, which includes the cutting parameter optimization vector and the environmental parameter optimization vector. For the high-risk wear area, the urgency and general direction of optimization are first determined based on the severity of the wear degree. If the wear degree is light, the optimization direction focuses on fine-tuning to maintain tool performance and processing efficiency; if the wear degree is severe, the parameters need to be adjusted significantly. In terms of the cutting parameter optimization vector, consider the cutting speed, feed rate and cutting depth. For example, if the wear in the high-risk wear area is caused by excessive cutting speed, then in the cutting parameter optimization vector, the optimization direction of the cutting speed is to reduce it. The specific reduction value should refer to factors such as the degree of wear, tool material characteristics, and workpiece material hardness. If the tool material has good high temperature resistance and the workpiece material has low hardness, even if the wear degree is high, the reduction in cutting speed may be relatively small; on the contrary, if the tool material is brittle and the workpiece material has high hardness, the reduction will be larger. For the feed rate and cutting depth, they are also adjusted according to the specific conditions of the wear area. If the wear is concentrated on the cutting edge of the tool, the feed speed needs to be appropriately reduced to avoid excessive pressure on the cutting edge and aggravate the wear; if the overall wear of the tool is relatively uniform, the cutting depth needs to be adjusted to change the contact state between the tool and the workpiece, thereby controlling the wear. The extraction of the environmental parameter optimization vector revolves around factors such as temperature, humidity, and lubrication conditions in the processing environment. If the appearance of the high-risk wear area is related to the high temperature of the processing environment, the optimization direction of the temperature in the environmental parameter optimization vector is to reduce the temperature, which can be achieved by adding cooling equipment or adjusting the coolant flow and temperature. If humidity has an impact on tool wear, such as the tool is prone to rust and aggravate wear in a humid environment, then the optimization direction is to control humidity, and dehumidification equipment can be used. For lubrication conditions, if insufficient lubrication leads to aggravated wear, the optimization vector includes increasing the amount of lubricant used and replacing a more suitable lubricant type. Through a comprehensive analysis of the high-risk wear area and the wear degree value, and taking various factors into consideration, accurate cutting parameter optimization vectors and environmental parameter optimization vectors are determined, which provides strong support for the subsequent effective reduction of tool wear and improvement of processing quality and efficiency.

[0065] Use the ridge regression machine learning algorithm to analyze the correlation between environmental parameters and cutting parameters and generate binary cross-tuning coefficients. First, the collected environmental parameters (such as environmental temperature, humidity, lubrication status, etc.) and cutting parameters (cutting speed, feed rate, cutting depth, etc.) are used as independent variables, and the tool wear amount or machining quality index is used as the dependent variable to construct a data set. The data is preprocessed by standardization to eliminate the influence of dimension, so that different parameters are in the same order of magnitude. Then, the processed data is divided into a training set and a test set. In the training stage, the ridge regression model is used to solve the problem of multicollinearity by introducing a regularization term (ridge coefficient), so that the model can learn the relationship between environmental parameters, cutting parameters and the dependent variable during the training process. After training, based on the coefficients obtained from model training, the cross-term coefficients between environmental parameters and cutting parameters are calculated, and these cross-term coefficients constitute the binary cross-tuning coefficients, which can quantitatively reflect the influence degree of the interaction between environmental parameters and cutting parameters on tool wear or machining quality.

[0066] When it is determined that the environmental parameter optimization vector is a positive influence vector, it indicates that the current environmental factors play a positive role in tool wear. For example, suitable environmental temperature, good lubrication conditions, etc. help to reduce the tool wear degree and maintain the stable performance of the tool. At this time, with the help of the previously generated binary cross-tuning coefficients, the cutting parameter optimization vector is weakened. The binary cross-tuning coefficients accurately quantify the degree of interaction between environmental parameters and cutting parameters. In the context of a positive influence vector, this coefficient is used to appropriately reduce the originally planned adjustment amplitude of cutting parameters. For example, initially based on the tool wear situation, the planned cutting parameter optimization plan was to reduce the cutting speed by 20%. However, due to the positive influence of environmental parameters, through the calculation of binary cross-tuning coefficients, it is determined that the reduction amplitude of the cutting speed is adjusted to 10%. While ensuring that the tool wear is within an acceptable range, it is possible to maintain a relatively high machining efficiency as much as possible, and avoid prolonging the machining time and reducing the production efficiency due to excessive adjustment of cutting parameters. The weakened cutting parameter optimization vector is applied to the actual cutting parameter optimization process. By adjusting key parameters such as cutting speed, feed speed, and cutting depth, on the basis of making use of good environmental conditions, the machining process is further optimized to achieve a balance between tool wear control and machining efficiency improvement.

[0067] When it is confirmed that the environmental parameter optimization vector is a negative impact vector, it means that the current environmental factors have an adverse effect on tool wear. For example, a high-temperature environment exacerbates tool wear, and insufficient lubrication leads to increased friction. In this case, in order to effectively reduce tool wear and ensure machining quality and tool life, it is necessary to use the generated binary cross-correlation coefficient to enhance the cutting parameter optimization vector. The binary cross-correlation coefficient reflects in detail the degree of correlation between environmental parameters and cutting parameters. In the case of a negative impact vector, according to this coefficient, the original adjustment strength of the cutting parameters is increased. For example, the initially proposed cutting parameter optimization plan is to reduce the feed rate by 15%. However, due to the negative impact of environmental factors, through the operation of the binary cross-correlation coefficient, it is determined that the reduction amplitude of the feed rate is increased to 25%. In this way, using the enhanced cutting parameter optimization vector, other cutting parameters such as cutting speed and cutting depth are also adjusted accordingly. By changing the cutting parameters more significantly, the negative effects brought by environmental factors are offset, and under harsh environmental conditions, tool wear is minimized as much as possible to ensure the smooth progress of machining and the stability of machining accuracy.

[0068] Embodiment 2, based on the same inventive concept as a high-performance diamond tool wear detection device in the foregoing embodiment, as Figure 2 shown, the present application provides a high-performance diamond tool wear detection method. The method in the embodiments of the present application and the device embodiments are based on the same inventive concept. Among them, the method includes: Step S100: Obtain the tool structure characteristics, where the tool structure characteristics include diamond material characteristics and substrate material characteristics.

[0069] Step S200: Obtain the tool cutting condition characteristics, where the tool cutting condition characteristics include the working environment change range and the cutting parameter floating range.

[0070] Step S300: Combine the tool structure characteristics and the tool cutting condition characteristics to conduct a wear risk assessment, analyze and determine the structurally weak areas and high-wear areas of the tool, and conduct area level division to label the area maintenance level for each area.

[0071] Step S400: Receive the real-time cutting condition, where the real-time cutting condition includes the real-time cutting environment and real-time cutting parameters, and adaptively optimize the tool maintenance and inspection cycle and the detection index priority according to the real-time cutting condition.

[0072] Step S500: According to the tool maintenance and inspection cycle and the detection index priority, conduct a multi-factor damage assessment and detection on the structurally weak areas and high-wear areas, and adjust and optimize the real-time cutting parameters according to the damage assessment and detection results.

[0073] Further, step S300 further includes: Step S310: Perform mechanical stability calculation and material adhesion evaluation based on the tool structure characteristics, and extract the structurally weak areas according to the comprehensive analysis results.

[0074] Step S320: Extract the material characteristics of the material to be cut, as well as the cutting contact position and contact area according to the tool cutting condition characteristics, perform tool wear distribution positioning, and extract the high wear areas.

[0075] Further, step S300 further includes: Step S330: Perform correlation analysis between the cutting parameters and environmental parameters and the wear defect types respectively, establish multiple parameter-defect correlation groups, and extract multiple correlation detection indicators according to the multiple parameter-defect correlation groups.

[0076] Step S340: Perform initial detection weight configuration on the multiple correlation detection indicators to generate an initial detection index priority.

[0077] Step S350: Match the area detection index types for the structurally weak areas and high wear areas respectively, and perform comprehensive weight analysis according to the matched area detection index types to generate the area maintenance levels for each area.

[0078] Further, step S400 further includes: Step S410: Monitor the dynamic changes of the cutting parameters and environmental parameters in real time, perform risk trend assessment of the correlation detection indicators, and generate multiple risk adjustment coefficients according to the assessment results.

[0079] Step S420: Based on the multiple risk adjustment coefficients, correct the initial detection index priority to generate a detection index priority.

[0080] Step S430: Perform fusion calculation on the multiple risk adjustment coefficients, extract the cycle optimization direction according to the fusion result, and adaptively optimize the tool maintenance and inspection cycle.

[0081] Further, step S500 further includes: Step S510: Regularly perform multi-element loss determination detection according to the tool maintenance and inspection cycle.

[0082] Step S520: Number the multiple structurally weak areas and high wear areas, and configure the correlation detection indicators for each area.

[0083] Step S530: Perform multi-element sensing detection for the correlation detection indicators to generate an index status set for each detection area.

[0084] Step S540: Construct a multi-element loss determination matrix according to the numbered multiple structurally weak areas and high wear areas, combined with the index status set of each detection area.

[0085] Step S550: According to the priority of the detection indexes, calibrate the weights of the multi - element loss assessment matrix to generate a standard loss assessment matrix.

[0086] Step S560: Based on the standard loss assessment matrix, conduct multi - element loss assessment detection on the structurally weak areas and highly worn areas to generate a loss assessment detection result.

[0087] Further, step S560 further includes: Step S561: For each structurally weak area and highly worn area, define the ideal solution and the negative ideal solution respectively.

[0088] Step S562: Based on the standard loss assessment matrix, extract the associated detection index values of each structurally weak area and highly worn area respectively, and calculate the relative distances between each area and the ideal solution and the negative ideal solution.

[0089] Step S563: According to the relative distances, calculate and generate the comprehensive defect score of each area, and conduct an overall wear risk assessment based on the comprehensive defect score of each area to generate a loss assessment detection result.

[0090] Further, step S500 further includes: Step S570: Based on the loss assessment detection result, extract the high - risk wear areas and the wear degree values; for the high - risk wear areas and the wear degree values, extract the control optimization vectors, where the control optimization vectors include the cutting parameter optimization vector and the environmental parameter optimization vector; conduct an associated influence analysis between the environmental parameters and the cutting parameters to generate a binary cross - modulation correlation coefficient; when the environmental parameter optimization vector is a positive influence vector, weaken the cutting parameter optimization vector through the binary cross - modulation correlation coefficient and then optimize the cutting parameters; when the environmental parameter optimization vector is a negative influence vector, enhance the cutting parameter optimization vector through the binary cross - modulation correlation coefficient and then optimize the cutting parameters.

[0091] It should be noted that the above - mentioned sequence of embodiments of the present application is only for description and does not represent the advantages or disadvantages of the embodiments. And the above - mentioned specific embodiments of this specification are described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi - tasking and parallel processing are also possible or may be advantageous.

[0092] The above - mentioned are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0093] This specification and the drawings are merely exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A high-performance diamond tool wear detection device, characterized in that The device includes: A structural characteristic acquisition module for acquiring the structural characteristics of a tool, where the structural characteristics of the tool include diamond material characteristics and substrate material characteristics; A cutting condition characteristic acquisition module for acquiring the cutting condition characteristics of the tool, where the cutting condition characteristics of the tool include the working environment change range and the cutting parameter floating range; A wear risk assessment module for combining the structural characteristics of the tool and the cutting condition characteristics of the tool to conduct a wear risk assessment, analyzing and determining the structurally weak areas and high wear areas of the tool, and performing area level division to label the area maintenance level for each area; A maintenance inspection cycle optimization module for receiving real-time cutting conditions, where the real-time cutting conditions include real-time cutting environment and real-time cutting parameters, and adaptively optimizing the tool maintenance inspection cycle and the priority of detection indicators according to the real-time cutting conditions; An adjustment and optimization module for performing multi-factor damage assessment detection on the structurally weak areas and high wear areas according to the tool maintenance inspection cycle and the priority of detection indicators, and adjusting and optimizing the real-time cutting parameters according to the damage assessment detection results.

2. The high-performance diamond tool wear detection device according to claim 1, characterized in that, The wear risk assessment module further includes: A structurally weak area extraction unit for performing mechanical stability calculation and material adhesion evaluation according to the structural characteristics of the tool, and extracting the structurally weak areas according to the comprehensive analysis results; A high wear area extraction unit for extracting the material characteristics of the material to be cut, as well as the cutting contact position and contact area according to the cutting condition characteristics of the tool, performing tool wear distribution positioning, and extracting the high wear areas.

3. The high-performance diamond tool wear detection device according to claim 2, characterized in that, The wear risk assessment module further includes: An associated detection indicator extraction unit for performing associated analysis of cutting parameters and environmental parameters with wear defect types respectively, establishing multiple parameter-defect associated groups, and extracting multiple associated detection indicators according to the multiple parameter-defect associated groups; An initial detection indicator priority generation unit for performing initial detection weight configuration on the multiple associated detection indicators to generate an initial detection indicator priority; An area maintenance level generation unit for respectively performing area detection indicator type matching on the structurally weak areas and high wear areas, and performing comprehensive weight analysis according to the matched area detection indicator types to generate the area maintenance level for each area.

4. The high-performance diamond tool wear detection device according to claim 3, characterized in that, The maintenance inspection cycle optimization module further includes: A risk adjustment coefficient generation unit for real-time monitoring of the dynamic changes of cutting parameters and environmental parameters, performing risk trend assessment of associated detection indicators, and generating multiple risk adjustment coefficients according to the assessment results; A detection indicator priority generation unit for correcting the initial detection indicator priority based on the multiple risk adjustment coefficients to generate a detection indicator priority; A cycle optimization direction extraction unit for performing fusion calculation on the multiple risk adjustment coefficients, extracting the cycle optimization direction according to the fusion result, and adaptively optimizing the tool maintenance inspection cycle.

5. The high-performance diamond tool wear detection device according to claim 1, characterized in that, The adjustment and optimization module further includes: A multi-factor damage assessment detection execution unit for regularly performing multi-factor damage assessment detection according to the tool maintenance inspection cycle; An associated detection indicator configuration unit for numbering multiple structurally weak areas and high wear areas, and configuring the associated detection indicators for each area. An index status set generation unit, configured to perform multi-sensor detection on the associated detection index, and generate an index status set for each detection area; A multi-element damage assessment matrix construction unit, configured to construct a multi-element damage assessment matrix according to a plurality of numbered structurally weak areas and high wear areas, in combination with the index status sets of each detection area; A standard damage assessment matrix generation unit, configured to perform weight calibration on the multi-element damage assessment matrix according to the detection index priority, and generate a standard damage assessment matrix; A damage assessment detection result generation unit, configured to perform multi-element damage assessment detection on the structurally weak areas and high wear areas based on the standard damage assessment matrix, and generate a damage assessment detection result.

6. The high-performance diamond tool wear detection device according to claim 5, characterized in that The damage assessment detection result generation unit further includes: An ideal solution definition unit, configured to define an ideal solution and a negative ideal solution for each structurally weak area and high wear area respectively; A relative distance calculation unit, configured to respectively extract the associated detection index values of each structurally weak area and high wear area based on the standard damage assessment matrix, and calculate the relative distances of each area from the ideal solution and the negative ideal solution; An overall wear risk assessment unit, configured to calculate and generate a comprehensive defect score for each area according to the relative distances, and perform an overall wear risk assessment according to the comprehensive defect scores of each area to generate a damage assessment detection result.

7. The high-performance diamond tool wear detection device according to claim 1, characterized in that The adjustment and optimization module further includes: A wear degree value extraction unit, configured to extract high-risk wear areas and wear degree values based on the damage assessment detection result; A control optimization vector extraction unit, configured to extract a control optimization vector for the high-risk wear areas and wear degree values, where the control optimization vector includes a cutting parameter optimization vector and an environmental parameter optimization vector; A binary cross-tuning correlation coefficient generation unit, configured to perform an analysis of the associated influence between environmental parameters and cutting parameters, and generate a binary cross-tuning correlation coefficient; A cutting parameter optimization unit, configured to, when the environmental parameter optimization vector is a positive influence vector, optimize the cutting parameters after weakening the cutting parameter optimization vector through the binary cross-tuning correlation coefficient; A cutting parameter optimization vector enhancement unit, configured to, when the environmental parameter optimization vector is a negative influence vector, optimize the cutting parameters after enhancing the cutting parameter optimization vector through the binary cross-tuning correlation coefficient.

8. A method for detecting the wear of a high-performance diamond cutting tool, characterized in that, The method is implemented by a high-performance diamond tool wear detection device according to any one of claims 1-7, and the method includes: Obtaining the tool structure characteristics, where the tool structure characteristics include diamond material characteristics and substrate material characteristics; Obtaining the tool cutting condition characteristics, where the tool cutting condition characteristics include the working environment change range and the cutting parameter floating range; Combining the tool structure characteristics and the tool cutting condition characteristics, performing a wear risk assessment, analyzing and determining the structurally weak areas and high wear areas of the tool, and performing area level division to label the area maintenance level for each area; Receiving the real-time cutting condition, where the real-time cutting condition includes the real-time cutting environment and the real-time cutting parameters, and adaptively optimizing the tool maintenance inspection period and the detection index priority according to the real-time cutting condition; According to the tool maintenance inspection cycle and the priority of detection indicators, perform multi-factor damage assessment detection on the structurally weak areas and high-wear areas, and adjust and optimize the real-time cutting parameters according to the results of the damage assessment detection.

Images