Machine tool cutter quality detection method

Abstract

The invention discloses a machine tool cutter quality detection method, and relates to the technical field of cutter detection. The method comprises the following steps: scanning a new cutter by using three-dimensional laser to obtain accurate geometric data, analyzing a material by using an X-ray fluorescence spectrophotometer to determine trace elements, and constructing a characteristic model containing mechanical properties; during cutting, multi-source monitoring is carried out, cutting force and the like are measured, sound and strain are monitored through an acoustic monitoring system and a fiber grating sensor respectively, and data are synchronously processed; evaluating wear according to a multi-parameter fusion evaluation model, and calculating a wear rate; and comparing real-time data with the feature model by using a deep learning algorithm to diagnose defects, and carrying out acousto-optic and short message early warning when an early warning value is exceeded. Accurate data are obtained through advanced equipment and multi-source monitoring, real-time monitoring can be achieved, and the cutter problem can be early warned in time; the service life of the cutter can be comprehensively managed, replacement is reasonably arranged, good adaptability and expansibility are achieved, wireless transmission and cloud computing are adopted, and flexible configuration can be achieved according to needs.

Description

Technical Field

[0001] This invention relates to the field of cutting tool inspection technology, and in particular to a method for inspecting the quality of machine tool cutting tools. Background Technology

[0002] In the field of modern machining, the quality of machine tool cutting tools plays a decisive role in machining accuracy, production efficiency, and product quality. With the continuous development of the manufacturing industry, the performance requirements for machine tool cutting tools are becoming increasingly stringent, highlighting the growing importance of tool quality inspection.

[0003] Traditional machine tool quality inspection methods primarily focus on static testing, such as using simple measuring tools like calipers and micrometers to measure the tool's geometric dimensions. This method can only inspect the tool's basic external parameters and cannot obtain information about the tool's internal material composition or potential defects. Furthermore, the measurement accuracy is limited, making it difficult to meet the stringent quality requirements of high-precision machining. Additionally, evaluating the tool material through hardness testing also provides limited information and cannot fully understand the tool's performance during actual cutting.

[0004] During the use of cutting tools, due to the lack of effective real-time monitoring methods, operators often rely solely on experience to judge the wear condition of the tools. When the tools wear to a certain extent, it leads to decreased machining accuracy, increased surface roughness, and even damage to the workpiece. By the time these problems are discovered, some losses may have already occurred. Furthermore, traditional inspection methods cannot detect micro-cracks, chipping, and other defects that appear during cutting. These defects may rapidly propagate in subsequent machining, leading to tool failure and severely impacting production efficiency and product quality. Therefore, developing a method that can comprehensively, in real-time, and accurately detect the quality of machine tool cutting tools is of significant practical importance. Summary of the Invention

[0005] This invention proposes a method for quality inspection of machine tool cutting tools to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for inspecting the quality of machine tool cutting tools, comprising:

[0007] Tool basic data pre-acquisition and feature model construction: Three-dimensional laser scanning technology is used to scan the machine tool tool to obtain the tool's three-dimensional geometric data, including the tool's helix angle, rake angle, and clearance angle geometric features; at the same time, X-ray fluorescence spectrometry is used to analyze the tool material, and a feature model of the tool is constructed based on the acquired geometric data and material information; a mechanical performance model is established in combination with material properties, and the stress distribution and deformation of the tool under different cutting conditions are simulated through finite element analysis;

[0008] Real-time dynamic monitoring of cutting parameters: In addition to real-time monitoring of cutting force, cutting temperature, cutting speed and feed rate during tool cutting, an acoustic monitoring system is also introduced; acoustic signal processing algorithms are used to analyze the sound characteristics of the tool during cutting, and fiber optic grating sensors are used to monitor the strain of the tool, and the collected data is processed in time synchronization.

[0009] Comprehensive tool wear assessment: Based on the collected cutting force, cutting temperature, cutting speed, feed rate, acoustic characteristics, and strain data, a parameter fusion assessment model is used to calculate the degree of tool wear; the formula is as follows: Where W represents the degree of tool wear, P i These represent cutting force, cutting temperature, cutting speed, feed rate, acoustic characteristics, and strain parameters, respectively. i The weighting coefficients for the corresponding parameters are determined through optimization based on experimental data using machine learning algorithms, with the sum of the weighting coefficients being 1. Simultaneously, the concept of wear rate is introduced, and the wear rate is calculated by monitoring the degree of wear at different time points. Where R is the wear rate, ΔW is the difference in wear degree between two adjacent time points, and Δt is the time interval; when the wear rate exceeds the set threshold, the tool wear is judged to be abnormal.

[0010] Quality Defect Diagnosis and Early Warning: The system compares the collected real-time tool data with the feature model and uses deep learning algorithms to diagnose quality defects. Convolutional Neural Networks (CNNs) are used to extract and classify features from image data, and Recurrent Neural Networks (RNNs) are used to analyze time-series data to determine whether there are quality defects in the tool. If quality defects are detected in the tool or the wear degree or wear rate exceeds the warning value, the system issues an early warning signal, which includes audible and visual alarms and SMS notifications.

[0011] Furthermore, in the basic data pre-acquisition and feature model construction steps of the tool, the tool holder is specifically inspected and modeled; ultrasonic flaw detection technology is used to detect whether there are defects such as cracks inside the tool holder, and at the same time, a dynamic model of the tool holder is established, considering the connection characteristics between the tool holder and the machine tool spindle, and analyzing the vibration characteristics and stability of the tool holder when rotating.

[0012] Furthermore, in the real-time dynamic monitoring step of cutting parameters, the parameters of the cutting fluid are monitored. Sensors are used to measure the concentration, temperature, and flow rate of the cutting fluid. The cutting fluid parameters are incorporated into a multi-parameter fusion evaluation model, and the improved formula is as follows: Among them, the newly added P n+1 P n+2 P n+3 These represent the cutting fluid concentration, temperature, and flow rate, respectively, k n+1 k n+2 k n+3The weighting coefficients for the corresponding parameters are also determined through optimization using machine learning algorithms.

[0013] Furthermore, in the comprehensive tool wear assessment step, the influence of different cutting stages on wear assessment is considered. The cutting process is divided into the initial break-in stage, the stable cutting stage, and the rapid wear stage. The current cutting stage is identified by analyzing the changing trends of cutting force and temperature parameters. At different stages, the weight coefficients in the parameter fusion assessment model are adjusted.

[0014] Furthermore, in the quality defect diagnosis and early warning step, a tool quality database is established to store the inspection data, diagnostic results and usage records of each tool in the database. Data mining technology is used to analyze the database to find the patterns and influencing factors of tool quality defects.

[0015] Furthermore, in the real-time dynamic monitoring step of cutting parameters, wireless transmission technology is used to transmit the collected data to the monitoring center. Bluetooth Low Energy (BLE) or ZigBee protocols are used for data transmission.

[0016] Furthermore, in the comprehensive evaluation step of tool wear, a fuzzy comprehensive evaluation method is introduced; the measured value of each parameter is fuzzified and divided into different fuzzy levels, and then a comprehensive evaluation is performed according to fuzzy rules to obtain the fuzzy evaluation result of the tool wear degree; finally, through defuzzification processing, the fuzzy evaluation result is converted into the actual wear degree value.

[0017] Furthermore, in the tool basic data pre-acquisition and feature model construction steps, the surface roughness of the tool is measured. The surface roughness of the tool is measured using an atomic force microscope (AFM), and the surface roughness information is incorporated into the tool feature model to analyze the influence of surface roughness on tool cutting performance and wear.

[0018] Furthermore, a cloud-based remote diagnostic platform is developed for the quality defect diagnosis and early warning process. Operators can access the remote diagnostic platform via the Internet to view real-time detection data, diagnostic results, and early warning information of the cutting tools.

[0019] Furthermore, in the real-time cutting parameter dynamic monitoring step, the vibration state of the machine tool is monitored. An acceleration sensor is used to measure the vibration acceleration of the machine tool, and the relationship between machine tool vibration and tool quality is analyzed. When the machine tool vibration is abnormal, the tool is checked for problems to avoid tool damage or a decrease in machining quality due to machine tool vibration.

[0020] Compared with existing technologies, the beneficial effects of this invention are:

[0021] In terms of detection accuracy, this method employs advanced equipment such as three-dimensional laser scanning technology and X-ray fluorescence spectrometers, enabling precise acquisition of the tool's geometric dimensions and material information, achieving an extremely high level of measurement accuracy. Simultaneously, by combining multi-source real-time monitoring methods, such as acoustic monitoring systems and fiber optic grating sensors, high-precision measurements of multiple parameters during the cutting process are achieved, providing reliable data support for accurate tool quality assessment. This allows for the detection of minute defects and potential problems that are difficult to detect using traditional methods, significantly improving the accuracy and reliability of the detection.

[0022] From a real-time monitoring perspective, this method can collect and analyze data in real time during the cutting process, promptly detecting accelerated tool wear and quality defects. Through a multi-parameter fusion evaluation model and intelligent diagnostic algorithms, it can quickly and accurately determine the tool's condition and immediately issue warning signals when problems occur. This allows operators to take timely measures to avoid machining quality degradation and production accidents caused by tool problems, thereby improving production efficiency and product quality.

[0023] In tool life management, this method comprehensively manages the entire lifecycle of tools by establishing tool characteristic models and quality databases. It can analyze tool wear patterns and performance under different cutting conditions, providing a scientific basis for tool design and use. Based on real-time monitoring data and wear assessment results, tool replacement time can be rationally scheduled, avoiding premature or delayed replacement, thereby extending tool life and reducing production costs.

[0024] Furthermore, this method exhibits excellent adaptability and scalability. Employing wireless transmission technology and a cloud computing platform, it enables remote data transmission and sharing, allowing operators to access tool inspection information anytime, anywhere. Simultaneously, the system can be flexibly configured according to different tool types and machining requirements, adapting to diverse production needs. Attached Figure Description

[0025] Figure 1 This is a schematic block diagram of a machine tool cutting tool quality inspection method proposed in this invention;

[0026] Figure 2 This is a schematic block diagram illustrating the relationship between tool wear and cutting time in a machine tool quality inspection method proposed in this invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0029] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0030] Reference Figure 1 and Figure 2 Specific implementation method of a machine tool cutting tool quality inspection method

[0031] Step 1: Pre-acquisition of basic tool data and construction of feature model

[0032] Before quality inspection of machine tool cutting tools, basic data pre-collection is necessary for new tools. A high-precision 3D laser scanning device is used to perform a full-range scan of the tool, with a scanning accuracy of ±0.005mm. During the scan, the device rotates around the tool at multiple angles to acquire precise 3D geometric data, such as the tool's helix angle, rake angle, and clearance angle, among other complex geometric features. Simultaneously, an X-ray fluorescence spectrometer is used for in-depth analysis of the tool material. This spectrometer can accurately detect the types and contents of trace elements in the tool, down to the ppm level. By testing multiple sample tools, the proportion range of each element in different tool materials is recorded, forming a material database.

[0033] Based on the collected geometric data and material information, a feature model of the cutting tool was constructed using specialized modeling software. This model not only includes the tool's static geometric features but also incorporates material properties to establish a mechanical performance model. Finite element analysis software was used to simulate the stress distribution and deformation of the tool under different cutting conditions. For example, different cutting forces, cutting speeds, and feed rates were set to analyze the stress concentration areas and deformation levels of the tool under these conditions. Below are some example data:

[0034] Tool type Helix angle (°) Front angle (°) Rear angle (°) Proportion of main alloying elements (%) Tool A 30 10 8 Tungsten 70, Cobalt 10, Titanium 5 Knife B 35 12 9 Tungsten 65, Cobalt 12, Titanium 6

[0035] Step Two: Multi-Source Real-Time Dynamic Monitoring of Cutting Parameters During the cutting process, multiple parameters need to be monitored in real time. A high-precision cutting force sensor is used to measure the cutting force, with a measurement range of 0-5000N and an accuracy of ±10N. The sensor is installed near the tool holder and can accurately sense the force acting on the tool during cutting. An infrared thermometer is used to measure the cutting temperature, with a measurement accuracy of ±5℃. This thermometer can monitor the temperature changes in the tool cutting area in real time. An encoder is used to measure the cutting speed, with an accuracy of ±0.1m / min. Simultaneously, an acoustic monitoring system is introduced, using a high-sensitivity microphone to collect sound signals during the cutting process, with a frequency response range of 20Hz-20kHz. Acoustic signal processing algorithms are used to analyze the collected sound signals, extracting features such as frequency distribution and sound pressure level changes. Furthermore, a fiber optic grating sensor is used to monitor the tool strain, with a measurement accuracy of ±1με. The collected multi-source data is processed in time synchronization to ensure data accuracy and consistency. Additionally, feed rate monitoring is added, using a displacement sensor to measure the feed rate with a measurement accuracy of ±0.001mm. Here is some example data:

[0036] Monitoring parameters Measurement range Measurement accuracy Cutting force 0-5000N ±10N Cutting temperature 0-1000℃ ±5℃ Cutting speed 0-500m / min ±0.1m / min feed rate 0-10mm / r ±0.001mm

[0037] Step 3: Multi-dimensional Comprehensive Assessment of Tool Wear. Based on the collected parameters such as cutting force F, cutting temperature T, cutting speed V, feed rate f, acoustic characteristic indicators (e.g., average sound pressure level, frequency characteristic value, etc.), and strain value, a multi-parameter fusion assessment model is used to calculate the degree of tool wear W. The specific formula is as follows: Among them, P i Each of the above parameters represents k respectively. i The weighting coefficients for the corresponding parameters were determined through optimization using machine learning algorithms based on a large amount of experimental data, with the sum of the weighting coefficients being 1. Simultaneously, the concept of wear rate was introduced, and the wear rate was calculated by continuously monitoring the wear level at different time points. Where ΔW is the difference in wear degree between two adjacent time points, and Δt is the time interval. When the wear rate exceeds a set threshold (pre-set according to tool type and usage requirements, generally 0.01-0.1 / min), tool wear is considered to have intensified. Furthermore, the influence of different cutting stages on wear assessment is considered. The cutting process is divided into an initial break-in stage, a stable cutting stage, and a rapid wear stage. By analyzing the changing trends of parameters such as cutting force and temperature, the current cutting stage is automatically identified. At different stages, the weight coefficients in the multi-parameter fusion assessment model are adjusted to improve the accuracy of wear assessment. For example, in the initial break-in stage, the weights of cutting force and temperature parameters are appropriately increased; in the rapid wear stage, the weights of acoustic characteristics and strain parameters are increased. Below are some example data:

[0038] Cutting stage Cutting force weight Cutting temperature weight Acoustic feature weights Strain weight Initial break-in phase 0.3 0.3 0.1 0.1 Stable cutting stage 0.2 0.2 0.2 0.2 Rapid wear stage 0.1 0.1 0.3 0.3

[0039] Step 4: Intelligent Diagnosis and Early Warning of Quality Defects

[0040] The collected real-time tool data is compared with the feature model, and deep learning algorithms are used for quality defect diagnosis. Convolutional neural networks (CNNs) are used to extract and classify features from image data (such as tool surface cracks and notches), and recurrent neural networks (RNNs) are used to analyze time-series data (such as changes in cutting force and temperature over time) to determine whether there are quality defects in the tool.

[0041] If a tool is found to have quality defects or if its wear level or rate exceeds a warning threshold, the system immediately issues a warning signal. The warning signal includes audible and visual alarms and SMS notifications, ensuring operators can take timely action. Simultaneously, a tool quality database is established, storing the inspection data, diagnostic results, and usage records for each tool. Data mining techniques are used to analyze the database to identify potential patterns and influencing factors of tool quality defects. For example, the system analyzes the wear and defect rates of different tool materials and geometries under various cutting conditions, providing a reference for tool design and use.

[0042] In practical applications, by comprehensively implementing the above steps, the quality of machine tool cutting tools can be detected in a comprehensive, real-time and accurate manner, tool wear and defects can be detected in a timely manner, production efficiency and product quality can be improved, and production costs can be reduced.

[0043] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for inspecting the quality of machine tool cutting tools, characterized in that, include: Tool basic data pre-acquisition and feature model construction: Three-dimensional laser scanning technology is used to scan the machine tool tool to obtain the tool's three-dimensional geometric data, including the tool's helix angle, rake angle, and clearance angle geometric features; at the same time, X-ray fluorescence spectrometry is used to analyze the tool material, and a feature model of the tool is constructed based on the acquired geometric data and material information; a mechanical performance model is established in combination with material properties, and the stress distribution and deformation of the tool under different cutting conditions are simulated through finite element analysis; Real-time dynamic monitoring of cutting parameters: In addition to real-time monitoring of cutting force, cutting temperature, cutting speed and feed rate during tool cutting, an acoustic monitoring system is also introduced; acoustic signal processing algorithms are used to analyze the sound characteristics of the tool during cutting, and fiber optic grating sensors are used to monitor the strain of the tool, and the collected data is processed in time synchronization. Comprehensive tool wear assessment: Based on the collected cutting force, cutting temperature, cutting speed, feed rate, acoustic characteristics, and strain data, a parameter fusion assessment model is used to calculate the degree of tool wear; the formula is as follows: Where W represents the degree of tool wear, P i These represent cutting force, cutting temperature, cutting speed, feed rate, acoustic characteristics, and strain parameters, respectively. i The weighting coefficients for the corresponding parameters are determined through optimization based on experimental data using machine learning algorithms, with the sum of the weighting coefficients being 1. Simultaneously, the concept of wear rate is introduced, and the wear rate is calculated by monitoring the degree of wear at different time points. Where R is the wear rate, ΔW is the difference in wear degree between two adjacent time points, and Δt is the time interval; when the wear rate exceeds the set threshold, the tool wear is judged to be abnormal. Quality Defect Diagnosis and Early Warning: The system compares the collected real-time tool data with the feature model and uses deep learning algorithms to diagnose quality defects. Convolutional Neural Networks (CNNs) are used to extract and classify features from image data, and Recurrent Neural Networks (RNNs) are used to analyze time-series data to determine whether there are quality defects in the tool. If quality defects are detected in the tool or the wear degree or wear rate exceeds the warning value, the system issues an early warning signal, which includes audible and visual alarms and SMS notifications.

2. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the basic data pre-acquisition and feature model construction steps of the tool, the tool holder is specially inspected and modeled; ultrasonic flaw detection technology is used to detect whether there are cracks or other defects inside the tool holder; at the same time, a dynamic model of the tool holder is established, considering the connection characteristics between the tool holder and the machine tool spindle, and analyzing the vibration characteristics and stability of the tool holder when rotating.

3. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the real-time dynamic monitoring step of cutting parameters, the parameters of the cutting fluid are monitored. Sensors are used to measure the concentration, temperature, and flow rate of the cutting fluid. The cutting fluid parameters are incorporated into the parameter fusion evaluation model, and the improved formula is as follows: Among them, the newly added P n+1 P n+2 P n+3 These represent the cutting fluid concentration, temperature, and flow rate, respectively, k n+1 k n+2 k n+3 The weighting coefficients for the corresponding parameters are also determined through optimization using machine learning algorithms.

4. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the comprehensive tool wear assessment step, the influence of different cutting stages on wear assessment is considered. The cutting process is divided into the initial break-in stage, the stable cutting stage, and the rapid wear stage. The current cutting stage is identified by analyzing the changing trends of cutting force and temperature parameters. At different stages, the weight coefficients in the parameter fusion assessment model are adjusted.

5. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the quality defect diagnosis and early warning process, a tool quality database is established to store the inspection data, diagnostic results, and usage records of each tool in the database. Data mining techniques are then used to analyze the database to identify the patterns and influencing factors of tool quality defects.

6. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the real-time dynamic monitoring of cutting parameters, Bluetooth BLE or ZigBee protocol technology is used to transmit the collected data to the monitoring center.

7. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the comprehensive evaluation of tool wear, a fuzzy comprehensive evaluation method is introduced. The measured values ​​of each parameter are fuzzified and divided into different fuzzy levels. Then, a comprehensive evaluation is performed according to fuzzy rules to obtain the fuzzy evaluation result of the tool wear degree. Finally, through defuzzification, the fuzzy evaluation result is converted into the actual wear degree value.

8. The method for quality inspection of machine tool cutting tools according to claim 1, characterized in that, In the tool basic data pre-acquisition and feature model construction step, the surface roughness of the tool is measured. The surface roughness of the tool is measured using an atomic force microscope (AFM), and the surface roughness information is incorporated into the tool feature model to analyze the influence of surface roughness on tool cutting performance and wear.

9. A method for inspecting the quality of machine tool cutting tools according to claim 1, characterized in that, In the quality defect diagnosis and early warning process, a cloud-based remote diagnostic platform is developed, allowing operators to access the platform via the internet to view real-time tool detection data, diagnostic results, and early warning information.

10. A method for inspecting the quality of machine tool cutting tools according to claim 1, characterized in that, In the real-time cutting parameter dynamic monitoring step, the vibration state of the machine tool is monitored. An accelerometer is used to measure the vibration acceleration of the machine tool, and the relationship between machine tool vibration and tool quality is analyzed. When the machine tool vibration is abnormal, the tool is checked for problems to avoid tool damage or deterioration of machining quality due to machine tool vibration.

Images