Cutting tool operation monitoring alarm

Abstract

The invention relates to the field of cutting tool machining, and discloses a cutting tool operation monitoring alarm which comprises a sound collection module which collects sound information generated in the cutting tool operation process through a sensor and transmits the collected sound information to a signal processing module. The sound acquisition module is connected with a signal processing module, and the signal processing module receives sound information acquired by the sound acquisition module, converts an original analog signal into a digital signal and transmits the digital signal to the data analysis and judgment module. Based on multiple parameters such as workpiece materials and cutting depth which are collected in real time, the dynamic threshold value module automatically optimizes a sound monitoring threshold value through an innovative algorithm. And under the complex working conditions of different materials and different cutting parameters, the system can be quickly adapted, and the false alarm rate is reduced to an extremely low level. The situation of frequent false alarm caused by working condition changes in a traditional fixed threshold monitoring mode is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of cutting tool processing, in particular to a cutting tool operation monitoring alarm. Background Art

[0002] As the manufacturing industry develops towards high precision and high efficiency, cutting processing, as the core process of mechanical manufacturing, its tool operation status directly affects product quality and production efficiency.

[0003] The current mainstream monitoring methods in the industry are mainly divided into two categories: manual judgment based on experience and basic sensor monitoring. In the manual judgment process, the status is usually determined by listening to the sound made by the tool during cutting. During normal cutting, the tool emits a steady, regular sound; when the tool is worn or damaged, the sound becomes sharp, noisy, or periodic. For example, when the tool edge is slightly worn, the frequency of the cutting sound will increase slightly; if the tool edge is chipped, it will be accompanied by a sudden sharp and piercing sound. In the basic sensor monitoring process, acceleration vibration sensors are installed in key locations such as the machine tool spindle and tool holder to collect tool vibration signals in real time. The sensor converts mechanical vibration into an electrical signal and transmits it to the data acquisition system for processing. After the system pre-processes the signal through filtering and amplification, it uses time domain analysis (such as calculating the root mean square value and peak value of the vibration signal) and frequency domain analysis (such as Fourier transform to obtain the vibration frequency component) to determine whether the tool has abnormal vibration.

[0004] Considering that manual monitoring relies on the operator to judge the tool status by listening to sounds and observing chip shapes, this method is significantly affected by individual experience differences, fatigue and other factors, and the recognition accuracy of early wear (flank wear <0.1mm) is low; and although basic sensor monitoring (such as vibration sensors and current sensors) can realize partial parameter collection, there are the following problems: First, a single sensor cannot fully reflect the complex working conditions of the tool. For example, the vibration signal is easily disturbed by the resonance of the machine tool, and the current signal is greatly affected by load fluctuations; second, the threshold setting mostly uses fixed parameters, which is difficult to adapt to the normal operating range of the tool under different materials and cutting parameters, resulting in a high false alarm rate, which seriously affects the practicality of the monitoring system. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a cutting tool operation monitoring alarm, which solves the problem that manual monitoring of the cutting tool status relies on the operator's experience, is greatly affected by individual differences and fatigue, and has a low accuracy rate in identifying early wear. Basic sensor monitoring has a single parameter that is difficult to fully reflect complex working conditions, and the fixed threshold setting is easily interfered with, resulting in a high false alarm rate, which seriously affects the practicality of monitoring.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a cutting tool operation monitoring alarm, including a sound collection module, the sound collection module uses a sensor to collect sound information generated during the operation of the cutting tool, and transmits the collected sound information to the signal processing module, the sound collection module is connected to a signal processing module, the signal processing module receives the sound information collected from the sound collection module, and converts the original analog signal into a digital signal, and then transmits it to the data analysis and judgment module, the signal processing module is connected to a data analysis and judgment module, the data analysis and judgment module receives the converted digital signal, and comprehensively judges whether the current cutting tool has a fault problem from multiple angles based on an adaptive weighted evidence fusion algorithm, when it is judged that the cutting tool has a fault, the data analysis and judgment module starts the alarm module, when it is judged that the cutting tool is normal, the normal operation of the device is ensured, the data analysis and judgment module is connected to an alarm module, and the alarm module uses an alarm sound to notify the staff as soon as possible that there is a fault problem with the cutting tool.

[0007] Preferably, the sensor is specifically: a MEMS microphone, a piezoelectric accelerometer, or a fiber optic microphone.

[0008] Preferably, the sound information includes: root mean square value RMS, main frequency, kurtosis, and frequency band ratio.

[0009] Preferably, the data analysis and judgment module is connected to a dynamic threshold module, which adjusts the sound threshold of the cutting tool during the cutting process according to a multi-parameter and adaptive weighted evidence fusion algorithm, adapts to the sound characteristics of different working conditions, takes into account multiple parameters affecting the sound of the cutting tool, and further improves the accuracy of subsequent judgment of whether the cutting tool is faulty.

[0010] Preferably, in the dynamic threshold module, the adaptive weighted evidence fusion algorithm is specifically:

[0011] 1. First, adjust the multi-parameter values ​​and weights to quantify the impact of different parameters on the sound, further improve the accuracy of threshold adjustment, and ensure the accuracy of subsequent comprehensive calculations, including:

[0012]

[0013] in:

[0014] w i represents the weight coefficient of the i-th parameter, i = 1-5, corresponding to material, depth, speed, tool, and wear respectively;

[0015] λ iRepresents the sensitivity coefficient of i, λ = 1-5, corresponding to material, depth, speed, tool, and wear, respectively, representing the importance of different parameters to sound judgment. For example: tool wear has the greatest impact on sound, so λ5 = 2.5, and cutting speed has a smaller impact on sound, so λ3 = 1.2;

[0016] x′ i represents the standardized parameter value;

[0017] 2. Substitute the weights into the multi-parameter values ​​to comprehensively calculate the current cutting tool sound fault threshold value, avoiding the limitations of single parameter judgment and improving the accuracy of fault detection, including:

[0018]

[0019] Where: T j Represents the jth sound threshold after adjustment, including RMS threshold and main frequency threshold;

[0020] T j,base Represents basic thresholds, including reference values ​​under standard working conditions;

[0021] k i,j represents the influence coefficient of parameter i on threshold j;

[0022] 3. Then, the adjusted cutting tool sound fault threshold value and the collected cutting tool sound value are used for judgment and calculation:

[0023]

[0024] Where: F represents the comprehensive failure index, the larger the value, the higher the failure probability; S j Represents real-time sound feature values, including RMS, main frequency, kurtosis, and frequency band ratio; β j Represents the importance weight of the sound feature. For example, when β1 = 0.4, RMS is the most important; α i,j represents the correlation coefficient of parameter i to threshold j;

[0025]

[0026] Finally, a conclusion on the cutting tool's operating status is given and transmitted to the alarm module when the conclusion shows attention, warning, or severe warning.

[0027] Preferably, in the dynamic threshold module, the multiple parameters include:

[0028] Workpiece material parameters: standardized value of workpiece material hardness;

[0029] Cutting depth: normalized value of cutting depth;

[0030] Cutting speed: normalized value of cutting speed;

[0031] Tool material parameters: standardized value of tool material hardness;

[0032] Tool wear parameters; normalized values ​​of tool flank wear.

[0033] An alarm for a cutting tool operation monitoring and control system includes a cutting tool support, the bottom of which is rotatably connected to a cutting tool, an outer wall of which is fixedly connected to a monitoring alarm, and a front end of which is fixedly connected to a display.

[0034] The present invention provides a cutting tool operation monitoring alarm. It has the following beneficial effects:

[0035] 1. This invention uses multiple sensors, such as MEMS microphones and piezoelectric accelerometers, to collaboratively collect multidimensional signals, including sound and vibration. It then uses an adaptive weighted evidence fusion algorithm to conduct in-depth analysis of multiple characteristic parameters, including root mean square (RMS) value and main frequency. Compared to traditional single-sensor monitoring, this method improves the accuracy of identifying early tool wear.

[0036] 2. Based on real-time data collection of multiple parameters, such as workpiece material and cutting depth, the dynamic threshold module of this invention automatically optimizes the sound monitoring threshold using an innovative algorithm. The system rapidly adapts to complex working conditions involving varying materials and cutting parameters, minimizing false alarm rates. This avoids the frequent false alarms associated with varying working conditions associated with traditional fixed-threshold monitoring methods, reduces disruption to normal production processes, and ensures a more stable and reliable monitoring system.

[0037] 3. The present invention automatically categorizes tool faults by setting different fault levels. When the data analysis and judgment module detects an anomaly, it assigns a level based on the severity of the fault, such as "Caution" or "Warning," and triggers an alarm of the corresponding level, allowing staff to quickly understand the severity of the cutting tool fault and address it immediately. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A perspective view of the present invention;

[0039] Figure 2 It is a system flow chart of the present invention.

[0040] Among them, 1. Cutting tool support; 2. Cutting tool; 3. Display; 4. Monitoring alarm. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] Please see the attached Figure 1 -Attached Figure 2 An embodiment of the present invention provides a cutting tool operation monitoring alarm, including a cutting tool support 1, a cutting tool 2 is rotatably connected to the bottom of the cutting tool support 1, a monitoring alarm 4 is fixedly connected to the outer wall of the cutting tool support 1, and a display 3 is fixedly connected to the front end of the monitoring alarm 4.

[0043] A control system for a cutting tool operation monitoring alarm includes a sound collection module that uses a sensor to collect sound information generated during the operation of the cutting tool and transmits the collected sound information to a signal processing module;

[0044] The sensors are: MEMS microphone, piezoelectric accelerometer, fiber optic microphone;

[0045] Sound information includes but is not limited to: RMS, main frequency, kurtosis, and frequency band ratio;

[0046] The sound collection module is connected to a signal processing module, which receives the sound information collected by the sound collection module and converts the original analog signal into a digital signal, which is then transmitted to the data analysis and judgment module. The signal processing module is connected to a data analysis and judgment module, which receives the converted digital signal and comprehensively judges from multiple angles whether the current cutting tool has a fault problem based on an adaptive weighted evidence fusion algorithm. When it is judged that the cutting tool has a fault, the data analysis and judgment module starts the alarm module. When it is judged that the cutting tool is normal, the normal operation of the device is guaranteed. The data analysis and judgment module is connected to an alarm module, which uses an alarm sound to notify the staff of a fault problem in the cutting tool as soon as possible, and timely maintenance to ensure production efficiency.

[0047] The data analysis and judgment module is connected to a dynamic threshold module. The dynamic threshold module adjusts the sound threshold of the cutting tool during the cutting process based on multiple parameters and an adaptive weighted evidence fusion algorithm. This module adapts to the sound characteristics of different working conditions and considers multiple parameters that affect the cutting tool sound, further improving the accuracy of subsequent judgments on whether the cutting tool is faulty.

[0048] Multiple parameters include:

[0049] Workpiece material parameters: standardized value of workpiece material hardness;

[0050] Cutting depth: normalized value of cutting depth;

[0051] Cutting speed: normalized value of cutting speed;

[0052] Tool material parameters: standardized value of tool material hardness;

[0053] Tool wear parameters; normalized values ​​of tool flank wear;

[0054] The adaptive weighted evidence fusion algorithm is specifically as follows:

[0055] 1. First, adjust the multi-parameter values ​​and weights to quantify the impact of different parameters on the sound, further improve the accuracy of threshold adjustment, and ensure the accuracy of subsequent comprehensive calculations, including:

[0056]

[0057] in:

[0058] w i represents the weight coefficient of the i-th parameter, i = 1-5, corresponding to material, depth, speed, tool, and wear respectively;

[0059] λ i Represents the sensitivity coefficient of i, λ = 1-5, corresponding to material, depth, speed, tool, and wear, respectively, representing the importance of different parameters to sound judgment. For example: tool wear has the greatest impact on sound, so λ5 = 2.5, and cutting speed has a smaller impact on sound, so λ3 = 1.2;

[0060] x′ i represents the standardized parameter value;

[0061] 2. Substitute the weights into the multi-parameter values ​​to comprehensively calculate the current cutting tool sound fault threshold value, avoiding the limitations of single parameter judgment and improving the accuracy of fault detection, including:

[0062]

[0063] Where: T j Represents the jth sound threshold after adjustment, including RMS threshold and main frequency threshold;

[0064] T j,base Represents basic thresholds, including reference values ​​under standard working conditions;

[0065] k i,j represents the influence coefficient of parameter i on threshold j;

[0066] 3. Then, the adjusted cutting tool sound fault threshold value and the collected cutting tool sound value are used for judgment and calculation:

[0067]

[0068] Where: F represents the comprehensive failure index, the larger the value, the higher the failure probability; S j Represents real-time sound feature values, including RMS, main frequency, kurtosis, and frequency band ratio; β j Represents the importance weight of the sound feature. For example, when β1 = 0.4, RMS is the most important; α i,j represents the correlation coefficient of parameter i to threshold j;

[0069]

[0070] Finally, a conclusion on the operating status of the cutting tool is given, and when the conclusion shows attention, warning, or severe warning, it is transmitted to the alarm module for timely feedback and notification to the staff.

[0071] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A cutting tool operation monitoring and control system, characterized in that: It includes a sound collection module, which uses a sensor to collect sound information generated during the operation of the cutting tool, and transmits the collected sound information to the signal processing module. The sound collection module is connected to a signal processing module. The signal processing module receives the sound information collected from the sound collection module and converts the original analog signal into a digital signal, which is then transmitted to the data analysis and judgment module. The signal processing module is connected to a data analysis and judgment module. The data analysis and judgment module receives the converted digital signal and comprehensively judges from multiple angles whether the current cutting tool has a fault problem based on an adaptive weighted evidence fusion algorithm. When it is judged that the cutting tool has a fault, the data analysis and judgment module starts the alarm module. When it is judged that the cutting tool is normal, the normal operation of the device is guaranteed. The data analysis and judgment module is connected to an alarm module, and the alarm module uses an alarm sound to notify the staff as soon as possible that there is a fault problem with the cutting tool.

2. A cutting tool operation monitoring and control system according to claim 1, characterized in that: In the sound collection module, the sensor is specifically: a MEMS microphone, a piezoelectric accelerometer, and a fiber optic microphone.

3. A cutting tool operation monitoring and control system according to claim 1, characterized in that: In the sound collection module, the sound information includes: root mean square value RMS, main frequency, kurtosis, and frequency band ratio.

4. A cutting tool operation monitoring and control system according to claim 1, characterized in that: The data analysis and judgment module is connected to a dynamic threshold module, which adjusts the sound threshold of the cutting tool during the cutting process based on a multi-parameter and adaptive weighted evidence fusion algorithm to adapt to the sound characteristics of different working conditions, consider multiple parameters that affect the sound of the cutting tool, and further improve the accuracy of subsequent judgment of whether the cutting tool is faulty.

5. A cutting tool operation monitoring and control system according to claim 4, characterized in that: In the dynamic threshold module, the adaptive weighted evidence fusion algorithm is specifically as follows: First, we adjust the multi-parameter values ​​and weights to quantify the impact of different parameters on the sound, further improve the accuracy of threshold adjustment, and ensure the accuracy of subsequent comprehensive calculations, including: in: w i represents the weight coefficient of the i-th parameter, i = 1-5, corresponding to material, depth, speed, tool, and wear respectively; λ i Represents the sensitivity coefficient of i, λ = 1-5, corresponding to material, depth, speed, tool, and wear, respectively, representing the importance of different parameters to sound judgment. For example: tool wear has the greatest impact on sound, so λ5 = 2.5, and cutting speed has a smaller impact on sound, so λ3 = 1.2; x′ i represents the standardized parameter value; Then, the weights are substituted into the multi-parameter values ​​to comprehensively calculate the current cutting tool sound fault threshold value, avoiding the limitations of single parameter judgment and improving the accuracy of fault detection, including: Where: T j Represents the jth sound threshold after adjustment, including RMS threshold and main frequency threshold; T j,base Represents basic thresholds, including reference values ​​under standard working conditions; k i,j represents the influence coefficient of parameter i on threshold j; Then, the adjusted cutting tool sound fault threshold value and the collected cutting tool sound value are used for judgment and calculation: Where: F represents the comprehensive failure index, the larger the value, the higher the failure probability; S j Represents real-time sound feature values, including RMS, main frequency, kurtosis, and frequency band ratio; β j Represents the importance weight of the sound feature. For example, when β1 = 0.4, RMS is the most important; α i,j represents the correlation coefficient of parameter i to threshold j; Finally, a conclusion on the cutting tool's operating status is given and transmitted to the alarm module when the conclusion shows attention, warning, or severe warning.

6. A cutting tool operation monitoring and control system according to claim 5, characterized in that: In the dynamic threshold module, the multiple parameters include: Workpiece material parameters: standardized value of workpiece material hardness; Cutting depth: normalized value of cutting depth; Cutting speed: normalized value of cutting speed; Tool material parameters: standardized value of tool material hardness; Tool wear parameters; normalized values ​​of tool flank wear.

7. An alarm device for a cutting tool operation monitoring and control system according to any one of claims 1 to 6, characterized in that: The invention comprises a cutting tool support (1), wherein the bottom of the cutting tool support (1) is rotatably connected to a cutting tool (2), the outer wall of the cutting tool support (1) is fixedly connected to a monitoring alarm (4), and the front end of the monitoring alarm (4) is fixedly connected to a display (3).

Images