CN114523338A - Cutting tool wear state monitoring method based on noise analysis - Google Patents
Cutting tool wear state monitoring method based on noise analysis Download PDFInfo
- Publication number
- CN114523338A CN114523338A CN202210181323.XA CN202210181323A CN114523338A CN 114523338 A CN114523338 A CN 114523338A CN 202210181323 A CN202210181323 A CN 202210181323A CN 114523338 A CN114523338 A CN 114523338A
- Authority
- CN
- China
- Prior art keywords
- wear
- characteristic
- cutting tool
- noise
- cutter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005520 cutting process Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000003754 machining Methods 0.000 claims description 30
- 238000000354 decomposition reaction Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000005299 abrasion Methods 0.000 abstract description 8
- 238000003801 milling Methods 0.000 description 9
- 238000000227 grinding Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000000691 measurement method Methods 0.000 description 5
- 229910000838 Al alloy Inorganic materials 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/0957—Detection of tool breakage
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/098—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining by measuring noise
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a cutting tool wear state monitoring method based on noise analysis, which comprises the following steps: collecting noise signals of the numerical control machine tool corresponding to the cutting tool during working; preprocessing a noise signal; extracting characteristics representing tool wear; obtaining a tool wear characteristic standard value; acquiring a tool wear characteristic threshold value; obtaining a current value of a tool wear characteristic; and comparing the current value with the threshold value, and judging the wear state of the cutter. The invention does not need a measuring device, has high prediction speed and high accuracy, is convenient to install the sensor, does not influence the normal processing of the numerical control machine tool, and can realize the real-time monitoring of the abrasion state of the cutting tool of the numerical control machine tool.
Description
Technical Field
The invention belongs to the technical field of wear measurement and monitoring of cutting tools of numerical control machines, and particularly relates to a method for monitoring the wear state of a cutting tool based on noise analysis.
Background
In the machining process, along with the machining of the cutting tool, the tool is inevitably worn, when the tool wear is accumulated to a certain range, the problems of vibration of a machine tool, reduction of the surface quality of a workpiece and the precision of machining size and the like can be caused, waste products can be generated seriously, and the research of the real-time monitoring technology of the cutting tool wear state of the numerical control machine tool is helpful for reducing the problems.
The tool wear online state monitoring has been widely studied for many years, and some results have been achieved in the fields of tool wear, workpiece deformation, signal processing and identification, and some methods have been applied to industrial production. However, for thin-wall part machining in the fields of aviation and the like, a mature tool wear monitoring method is not available, and due to the fact that the thin-wall part has the machining characteristics of large height ratio and easiness in deformation during machining, the machining precision of the part is easily influenced by cutting force changes caused by tool wear.
The conventional method for monitoring the wear state of the cutting tool mainly comprises a direct measurement method and an indirect measurement method. The direct measurement method is based on the related characteristics of the volume loss of the cutter, changes of the appearance or the surface shape of the cutter are directly identified through direct contact or CCD imaging and the like, and then the abrasion of the cutter is measured. For example, chinese patent document (CN201210194166.2) discloses an intelligent measuring instrument and a measuring method for tool wear, in which a CCD camera captures an image of a tool mounted on a machine tool, the image is processed by image processing software, and then wear amount of the tool is directly measured by wear amount measurement and analysis software. The indirect measurement method is mainly used for indirectly monitoring the tool wear by monitoring various signals related to tool wear, such as cutting force, torque, vibration, spindle power and the like, and establishing a corresponding relation between the signal characteristics and the tool wear. The method for monitoring the wear state of the cutter by utilizing the cutting force, the torque and the power characteristic index of the main shaft is mainly used under the working condition that the machining parameters are fixed, and cannot be applied to actual mass production, particularly in the field of rough machining with certain fluctuation of the machining parameters. The methods such as vibration have the defects that the sensor is troublesome to install, even the structure of the machine tool needs to be changed, the normal processing of the machine tool is influenced, and the popularization and application difficulty in actual production is higher. Such indirect measurement methods are known as a method for monitoring tool wear of a numerical control machine tool as disclosed in chinese patent document (CN201010607532.3), a method for automatically monitoring tool status as disclosed in chinese patent document (CN97192053.2), and a method for online monitoring tool wear based on wavelet packet analysis and RBF neural network as disclosed in chinese patent document (CN 201810222486.1).
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a cutting tool wear state monitoring method based on noise analysis, wherein the real-time monitoring of the wear state of a cutting tool is realized by acquiring a noise signal during the processing of a numerical control machine tool, extracting wear characteristics strongly related to the tool wear, acquiring the current value of the wear characteristics during the normal processing of the cutting tool in real time and comparing the current value with a preset threshold value; the defects that the sensor in the prior art is troublesome to install, influences the normal machining of a machine tool, fixes cutting parameters, is difficult to apply to actual mass production and the like are overcome.
The technical scheme adopted by the invention for solving the technical problems is as follows: a cutting tool wear state monitoring method based on noise analysis comprises the following steps:
(1) collecting noise signals of the numerical control machine tool corresponding to the cutting tool during working;
(2) preprocessing the collected noise signal in the step (1) to obtain a noise signal section when the cutter to be monitored is machined;
(3) processing the noise signal section in the step (2) during the machining of the cutter to be monitored by using a preset processing mode to obtain a plurality of signal characteristics, and selecting a predicted wear characteristic strongly related to the wear of the cutting cutter;
(4) collecting wear characteristic data of a dull and worn out cutter during machining, and obtaining the maximum value of the data;
(5) setting the maximum value of the wear characteristics acquired in the step (4) as a wear characteristic standard value, and obtaining a wear characteristic threshold value according to the wear characteristic standard value;
(6) collecting the current value of the wear characteristic of the cutting tool in real time during normal processing;
(7) comparing whether the current value of the wear characteristic is larger than the threshold value of the wear characteristic, if so, judging that the cutter is worn; otherwise, returning to the step (6).
Further, the processing the noise signal segment during the machining of the tool to be monitored in the step (2) by using the preset processing mode is to process the noise signal segment during the machining of the tool to be monitored in the step (2) by using a wavelet packet decomposition technology, so as to obtain a plurality of signal characteristics, and select a predicted wear characteristic strongly related to the wear of the cutting tool.
Further, the plurality of signal characteristics includes a friction characteristic, a vibration characteristic, a power characteristic, and a mass characteristic.
Further, the selection of a predicted wear characteristic that strongly correlates with cutting tool wear is preferably a friction characteristic.
Further, the noise signal of the numerical control machine tool corresponding to the cutting tool in the step (1) is acquired by adopting a capacitive noise sensor. The acquisition of sensor signals does not need intervention equipment, does not influence the dynamic characteristics of the numerical control machine tool, and does not influence the normal processing of the numerical control machine tool.
Further, the noise signal in the step (2) is preprocessed in such a way that the noise signal collected in the step (1) is low-pass filtered to remove pathological and redundant data in the signal, so as to provide reliable data for extracting the wear characteristics of the cutting tool.
Further, in the step (5), a wear characteristic threshold value is obtained according to the wear characteristic standard value, and the wear characteristic standard value is directly defined as the wear characteristic threshold value.
Further, in the step (5), the wear characteristic threshold value is obtained according to the wear characteristic standard value, and the wear characteristic threshold value is obtained by adding or/and subtracting a product of the standard value and a set proportion from the wear characteristic standard value.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention adopts the method of collecting the noise signal of the numerical control machine tool corresponding to the cutting tool during working; preprocessing a noise signal to obtain a noise signal section when a cutter to be monitored is machined; processing the noise signal section to obtain a plurality of signal characteristics, and selecting predicted wear characteristics strongly related to the wear of the cutting tool; collecting wear characteristic data of a dull and worn out cutter during machining, and obtaining the maximum value of the data; setting the maximum value of the wear characteristic as a wear characteristic standard value, and obtaining a wear characteristic threshold value according to the wear characteristic standard value; collecting the current value of the wear characteristic of the cutting tool in real time during normal processing; comparing whether the current value of the wear characteristic is larger than the threshold value of the wear characteristic, if so, judging that the cutter is worn; otherwise, returning to the step of collecting the current value of the wear characteristic in real time during normal machining of the cutting tool. The invention realizes the monitoring of the abrasion state of the cutting tool by collecting the noise signal of the numerical control machine tool in real time during working, does not need additional measuring equipment, has convenient sensor installation, does not influence the dynamic characteristic of the numerical control machine tool, does not influence the normal processing of the numerical control machine tool, and realizes the real-time monitoring of the abrasion state of the cutting tool.
2. According to the invention, the wavelet packet decomposition technology is adopted to process the noise signal segment, so that a plurality of signal characteristics are obtained, and the predicted wear characteristics strongly related to the wear of the cutting tool are selected. The invention extracts a plurality of characteristics strongly related to cutter abrasion from noise signals by a wavelet packet decomposition method, has various monitoring dimensions, breaks through the technical bottleneck of fixed cutting conditions, can adapt to the condition of fluctuation change of cutting parameters, improves the application range and can be suitable for actual mass production.
The present invention will be described in further detail with reference to examples; however, the method for monitoring the wear state of a cutting tool based on noise analysis according to the present invention is not limited to the embodiment.
Drawings
FIG. 1 is a flow chart of a method of monitoring the wear state of a cutting tool based on noise analysis provided in an embodiment of the present invention;
FIG. 2 is a graph of tool wear characteristic changes over four cycles involved in a method of monitoring the wear state of a cutting tool based on noise analysis provided in an embodiment of the present invention;
fig. 3 is a graph showing a change curve of a current value of a friction characteristic of a cutting tool and a valve value and a corresponding change trend of a maximum value of the characteristic value, which are related to a method for monitoring a wear state of a cutting tool based on noise analysis according to an embodiment of the present invention.
Detailed Description
Examples
Referring to fig. 1, the method for monitoring the wear state of a cutting tool based on noise analysis of the present invention is to collect noise signals generated during machining of a numerical control machine, extract key features that can characterize tool wear through a series of signal processing and analysis, and compare the current value of the wear features with a feature threshold value to realize real-time monitoring of the wear state of the cutting tool.
In this embodiment, the method for monitoring the wear state of the cutting tool based on noise analysis mainly includes the following steps:
step (1): collecting noise signals of the numerical control machine tool corresponding to the cutting tool during working; in the embodiment, the method for monitoring the wear state of the cutting tool based on noise analysis is described by taking monitoring of the wear of the milling tool when the numerical control milling machine processes the aluminum alloy thin-wall part as an example. In the embodiment, the capacitive noise sensor is used for collecting the noise signal of the numerical control milling machine corresponding to the machining of the aluminum alloy thin-wall part by the cutting tool in the states of dull grinding and non-dull grinding, and it can be understood that in other embodiments, other types of noise sensors can be used. In the embodiment, the acquisition of the sensor signal does not need intervention equipment, does not influence the dynamic characteristic of the numerical control machine tool, and does not influence the normal processing of the numerical control machine tool.
Step (2): preprocessing a noise signal; and (3) preprocessing the collected noise signal in the step (1) to improve the reliability of the noise signal. Specifically, the noise signals collected by the capacitive noise sensor are subjected to low-pass filtering, pathological and redundant data in the signals are removed, and a reliable data source is provided for extracting the subsequent tool wear characteristics.
The low-pass filtering is a filtering method, and the rule is that low-frequency signals can normally pass through, and high-frequency signals exceeding a set critical value are blocked and weakened. But the magnitude of the blocking and attenuation will vary depending on the frequency and filtering procedure (purpose). Low-pass filtering can be simply thought of as: a frequency point is set which cannot pass when the signal frequency is higher than this frequency, which is the cut-off frequency in the digital signal, and all values are assigned to 0 when the frequency domain is higher than this cut-off frequency.
And (3): extracting characteristics representing tool wear; and extracting the characteristics representing the tool abrasion from the preprocessed noise signals by adopting a wavelet packet decomposition method. In this embodiment, friction characteristics are used as characteristics strongly related to tool wear, and it is understood that in other embodiments, other types of characteristic coefficients, such as vibration characteristics, power characteristics, mass characteristics, etc., may also be used, as shown in fig. 2.
Wavelet packet decomposition (wavelet transform), also called wavelet packet (wavelet packet) or Subband tree (Subband tree) and Optimal Subband tree structure (Optimal Subband tree structure), is a technique for analyzing an input signal using multi-iteration wavelet transform. The method can provide more fine decomposition for high-frequency signals, the decomposition has no redundancy and no omission, and the signals containing a large amount of medium and high-frequency information can be better analyzed in time frequency localization.
The process of extracting the cutter abrasion prediction signal characteristics by the wavelet packet decomposition method comprises the following steps:
firstly, decomposing the noise signal segment obtained in the step (2) in a plurality of frequency segments by a wavelet packet decomposition method. One layer of wavelet packet decomposition can divide the original frequency band into two, and k layer of wavelet packet decomposition can divide the original frequency band into 2kAnd the frequency band realizes a fine frequency band, and improves the resolution of the frequency. The k value is calculated as follows:
And respectively calculating the mean value, the variance, the total energy and the like of the cutter cutting noise signal segment in each frequency segment to obtain a plurality of signal characteristics.
Analyzing the correlation between the tool wear and each signal characteristic, and selecting the one with strong correlation with the tool wearAs a predictive signal characteristic for monitoring the wear state of the tool. The correlation analysis process comprises the following steps: firstly, making an average curve of each signal characteristic along with the processing time to obtain an average curve L of the cutter in 2 life cycles1(x),L2(x) (ii) a Then calculate
And e is smaller, the correlation between the tool wear and the signal characteristic is stronger, and the friction characteristic signal is selected as the predicted signal characteristic. XiRepresenting the tool machining time and N representing the number of tool machining time points monitored throughout the life cycle of the tool.
And (4): obtaining a tool wear characteristic standard value; in this embodiment, a noise signal corresponding to the numerically controlled milling machine when the dull-ground and failed cutter is machined is collected, a friction characteristic coefficient representing cutter wear is extracted from the noise signal, a maximum value of the friction characteristic coefficient is obtained, and a standard value of the friction characteristic measured by the numerically controlled milling machine cutter wear is obtained. That is, the friction characteristic standard value is the maximum value of the acquired friction characteristic coefficient.
And (5): acquiring a tool wear characteristic threshold value; in the step, a tool wear characteristic threshold value is obtained according to the tool wear characteristic standard value obtained in the step, and the preset characteristic threshold value is a threshold value of a tool dull-grinding failure standard. Basically, different numerically controlled machine tools may have different wear characteristics during machining. Therefore, it is not very accurate to determine whether the wear state of the tool meets the dull standard through a single numerical value. However, the wear characteristics of the corresponding machine tool during normal tool machining must be distributed around this standard value. Therefore, a certain range taking the standard value of the wear characteristic as the center is taken as a threshold value corresponding to the dull grinding failure standard of the cutter. Specifically, if a ratio is set, for example, ± 10% of the characteristic standard value is set, the upper limit of the characteristic threshold is: standard value + standard value 10%; the lower limit of the characteristic threshold is as follows: standard-standard 10%. The characteristic value between the upper limit and the lower limit of the threshold value can be used as a threshold value of the cutter dull grinding standard, and the specific threshold value is determined according to the type of the numerical control machine, the type of the cutter and the machining working condition. In this embodiment, the threshold value of the tool dull standard is a wear characteristic standard value, that is, the wear characteristic threshold value is equal to the wear characteristic standard value.
And (6): obtaining a current value of the wear characteristic of the cutter; in the embodiment, the maximum value of the wear characteristic signal of the numerical control milling machine during machining of the aluminum alloy thin-wall part is continuously acquired in real time until the main shaft stops rotating or the numerical control milling machine stops. The purpose is to continuously compare with the wear characteristic threshold value and judge the wear state of the cutter used by the numerical control milling machine.
And (7): comparing the current value of the wear characteristic with a wear characteristic threshold value, and judging the wear state of the cutter; and comparing the obtained current value of the wear characteristic of the cutter with a preset wear characteristic threshold value, judging the wear state of the cutter, and if the current value of the wear characteristic of a certain cutter is greater than the preset wear characteristic threshold value of the cutter, judging the wear state of the cutter to be a dull state. In this embodiment, when the current value of the wear characteristic when the numerical control milling machine is used for processing the aluminum alloy thin-wall part is extracted and is greater than the standard value of the wear characteristic, the wear state of the cutter is judged to be a dull state, an alarm is given, and the cutter is reminded to be replaced in time.
The invention relates to a method for monitoring the wear state of a cutting tool based on noise analysis, which adopts the steps of collecting the noise signal of a numerical control machine tool corresponding to the working of the cutting tool; preprocessing a noise signal to obtain a noise signal section when a cutter to be monitored is machined; processing the noise signal section to obtain a plurality of signal characteristics, and selecting predicted wear characteristics strongly related to the wear of the cutting tool; collecting wear characteristic data of a dull and worn out cutter during machining, and obtaining the maximum value of the data; setting the maximum value of the wear characteristic as a wear characteristic standard value, and obtaining a wear characteristic threshold value according to the wear characteristic standard value; collecting the current value of the wear characteristic of the cutting tool in real time during normal processing; comparing whether the current value of the wear characteristic is larger than the threshold value of the wear characteristic, if so, judging that the cutter is worn; otherwise, returning to the step of collecting the current value of the wear characteristic in real time during normal machining of the cutting tool. The invention realizes the cutter wear state monitoring by acquiring the noise signal of the numerical control machine tool in real time during working, does not need additional measuring equipment, has convenient sensor installation, does not influence the dynamic characteristic of the numerical control machine tool, does not influence the normal processing of the numerical control machine tool, and realizes the real-time monitoring of the wear state of the cutting cutter.
The invention discloses a cutting tool wear state monitoring method based on noise analysis, which adopts a wavelet packet decomposition technology to process a noise signal segment so as to obtain a plurality of signal characteristics, and selects predicted wear characteristics strongly related to cutting tool wear. The invention extracts a plurality of characteristics strongly related to cutter abrasion from noise signals by a wavelet packet decomposition method, has various monitoring dimensions, breaks through the technical bottleneck of fixed cutting conditions, can adapt to the condition of fluctuation change of cutting parameters, improves the application range and can be suitable for actual mass production.
The foregoing is considered as illustrative of the preferred embodiments of the invention and is not to be construed as limiting the invention in any way. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make many possible variations and modifications to the disclosed embodiments, or equivalent modifications, without departing from the scope of the disclosed embodiments. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.
Claims (8)
1. A cutting tool wear state monitoring method based on noise analysis is characterized by comprising the following steps:
(1) collecting noise signals of the numerical control machine tool corresponding to the cutting tool during working;
(2) preprocessing the collected noise signal in the step (1) to obtain a noise signal section when the cutter to be monitored is machined;
(3) processing the noise signal section in the step (2) during the cutter processing to be monitored by using a preset processing mode to obtain a plurality of signal characteristics, and selecting a predicted wear characteristic strongly related to the wear of the cutting cutter;
(4) collecting wear characteristic data of a dull and worn out cutter during machining, and obtaining the maximum value of the data;
(5) setting the maximum value of the wear characteristics acquired in the step (4) as a wear characteristic standard value, and obtaining a wear characteristic threshold value according to the wear characteristic standard value;
(6) collecting the current value of the wear characteristic of the cutting tool in real time during normal processing;
(7) comparing whether the current value of the wear characteristic is larger than the threshold value of the wear characteristic, and if so, judging that the cutter is worn; otherwise, returning to the step (6).
2. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 1, wherein: and (3) processing the noise signal section in the step (2) during the machining of the cutter to be monitored by using a preset processing mode, namely processing the noise signal section in the step (2) during the machining of the cutter to be monitored by using a wavelet packet decomposition technology so as to obtain a plurality of signal characteristics, and selecting a predicted wear characteristic strongly related to the wear of the cutting cutter.
3. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 2, wherein: the plurality of signal characteristics includes a friction characteristic, a vibration characteristic, a power characteristic, and a mass characteristic.
4. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 3, wherein: the selection of a predicted wear characteristic that strongly correlates with cutting tool wear is preferably a friction characteristic.
5. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 1, wherein: and (2) acquiring noise signals of the numerical control machine tool corresponding to the cutting tool in the step (1) during working by adopting a capacitive noise sensor.
6. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 1, wherein: and (3) preprocessing the collected noise signal in the step (1) in the step (2), namely performing low-pass filtering on the noise signal collected by the sensor to remove ill-conditioned and redundant data in the signal, and further providing reliable data for extracting the wear characteristics of the cutting tool.
7. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 1, wherein: and (5) obtaining a wear characteristic threshold value according to the wear characteristic standard value, wherein the wear characteristic standard value is directly defined as the wear characteristic threshold value.
8. The method of monitoring the wear state of a cutting tool based on noise analysis of claim 1, wherein: and (5) obtaining a wear characteristic threshold value according to the wear characteristic standard value, wherein the wear characteristic threshold value is obtained by adding or/and subtracting the product of the standard value and a set proportion from the wear characteristic standard value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210181323.XA CN114523338A (en) | 2022-02-25 | 2022-02-25 | Cutting tool wear state monitoring method based on noise analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210181323.XA CN114523338A (en) | 2022-02-25 | 2022-02-25 | Cutting tool wear state monitoring method based on noise analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114523338A true CN114523338A (en) | 2022-05-24 |
Family
ID=81624425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210181323.XA Pending CN114523338A (en) | 2022-02-25 | 2022-02-25 | Cutting tool wear state monitoring method based on noise analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114523338A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115008254A (en) * | 2022-05-30 | 2022-09-06 | 河源富马硬质合金股份有限公司 | Cutter state monitoring method in high-speed milling process |
| CN116604400A (en) * | 2023-06-09 | 2023-08-18 | 深圳宏友金钻石工具有限公司 | Method for monitoring abrasion state signal of milling cutter of numerical control machine tool |
| CN117030857A (en) * | 2023-10-07 | 2023-11-10 | 中科航迈数控软件(深圳)有限公司 | Tool flaw detection method based on phase control ultrasonic waves and related equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU1084662A2 (en) * | 1982-12-29 | 1984-04-07 | Предприятие П/Я Р-6877 | Device for checking wear of cutting tool |
| US4831365A (en) * | 1988-02-05 | 1989-05-16 | General Electric Company | Cutting tool wear detection apparatus and method |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| CN108972152A (en) * | 2018-10-12 | 2018-12-11 | 哈尔滨理工大学 | A kind of sound-power detection method monitoring abrasion of cutting tool state |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
| CN113146359A (en) * | 2021-03-10 | 2021-07-23 | 深圳市磐锋精密技术有限公司 | Numerical control machine tool control system for intelligently monitoring and diagnosing cutting state |
| CN113334144A (en) * | 2021-05-20 | 2021-09-03 | 武汉理工大学 | System and method for detecting wear state of milling cutter |
| CN113752089A (en) * | 2021-10-19 | 2021-12-07 | 山东农业大学 | Cutter state monitoring method based on singularity Leersian index |
| US20220168831A1 (en) * | 2019-04-15 | 2022-06-02 | Gleason-Pfauter Maschinenfabrik Gmbh | Method for producing or machining toothing |
-
2022
- 2022-02-25 CN CN202210181323.XA patent/CN114523338A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU1084662A2 (en) * | 1982-12-29 | 1984-04-07 | Предприятие П/Я Р-6877 | Device for checking wear of cutting tool |
| US4831365A (en) * | 1988-02-05 | 1989-05-16 | General Electric Company | Cutting tool wear detection apparatus and method |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| CN108972152A (en) * | 2018-10-12 | 2018-12-11 | 哈尔滨理工大学 | A kind of sound-power detection method monitoring abrasion of cutting tool state |
| US20220168831A1 (en) * | 2019-04-15 | 2022-06-02 | Gleason-Pfauter Maschinenfabrik Gmbh | Method for producing or machining toothing |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
| CN113146359A (en) * | 2021-03-10 | 2021-07-23 | 深圳市磐锋精密技术有限公司 | Numerical control machine tool control system for intelligently monitoring and diagnosing cutting state |
| CN113334144A (en) * | 2021-05-20 | 2021-09-03 | 武汉理工大学 | System and method for detecting wear state of milling cutter |
| CN113752089A (en) * | 2021-10-19 | 2021-12-07 | 山东农业大学 | Cutter state monitoring method based on singularity Leersian index |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115008254A (en) * | 2022-05-30 | 2022-09-06 | 河源富马硬质合金股份有限公司 | Cutter state monitoring method in high-speed milling process |
| CN115008254B (en) * | 2022-05-30 | 2024-06-04 | 河源富马硬质合金股份有限公司 | Method for monitoring state of cutter in high-speed milling process |
| CN116604400A (en) * | 2023-06-09 | 2023-08-18 | 深圳宏友金钻石工具有限公司 | Method for monitoring abrasion state signal of milling cutter of numerical control machine tool |
| CN117030857A (en) * | 2023-10-07 | 2023-11-10 | 中科航迈数控软件(深圳)有限公司 | Tool flaw detection method based on phase control ultrasonic waves and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114523338A (en) | Cutting tool wear state monitoring method based on noise analysis | |
| CN108490880B (en) | Method for monitoring wear state of cutting tool of numerical control machine tool in real time | |
| CN108356606B (en) | Tool wear online monitoring method based on wavelet packet analysis and RBF neural network | |
| CN111761409A (en) | Multi-sensor numerical control machine tool cutter wear monitoring method based on deep learning | |
| CN111660141B (en) | Milling cutter wear state identification method based on spindle driving current and irrelevant to working conditions | |
| CN113741377A (en) | Machining process intelligent monitoring system and method based on cutting characteristic selection | |
| Luo et al. | Real-time condition monitoring by significant and natural frequencies analysis of vibration signal with wavelet filter and autocorrelation enhancement | |
| CN112720071B (en) | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals | |
| CN114800040B (en) | Cutter wear monitoring method and system related to process-state data | |
| CN110555243B (en) | Two-dimensional map construction method for vibration information of machine tool spindle in milling process | |
| CN108629864B (en) | Vibration-based electric spindle radial precision characterization method and system | |
| CN105033763A (en) | Method for predicting abrasion state of numerically-controlled machine tool ball screw | |
| CN111958321B (en) | Numerical control machine tool cutter wear degree identification method based on deep neural network | |
| Mou et al. | A study of tool tipping monitoring for titanium milling based on cutting vibration | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN111761411A (en) | Cutter health prediction device and method based on vibration signals | |
| CN114714157B (en) | Grinding chatter monitoring method based on time-varying filtering empirical mode decomposition and instantaneous energy ratio | |
| CN115741235A (en) | Wear prediction and health management method based on five-axis machining center cutter | |
| CN116408501A (en) | On-machine unsupervised real-time monitoring method for hob abrasion state in channeling mode | |
| CN116871978A (en) | Drilling tool state monitoring method based on multi-sensor fusion | |
| Zhong et al. | Correlation analysis of cutting force and acoustic emission signals for tool condition monitoring | |
| CN210878880U (en) | Numerical control lathe cutter wearing and tearing monitoring system | |
| CN117407735A (en) | Tool wear modeling method based on evolution cluster analysis | |
| CN110744359A (en) | Numerical control lathe cutter wear monitoring system and method | |
| Chen et al. | Monitoring and analysis of ultraprecision metal cutting with acoustic emission |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220524 |
|
| RJ01 | Rejection of invention patent application after publication |