CN113600896A - Method for monitoring wear state signal of milling cutter of numerical control machine tool - Google Patents
Method for monitoring wear state signal of milling cutter of numerical control machine tool Download PDFInfo
- Publication number
- CN113600896A CN113600896A CN202110905565.4A CN202110905565A CN113600896A CN 113600896 A CN113600896 A CN 113600896A CN 202110905565 A CN202110905565 A CN 202110905565A CN 113600896 A CN113600896 A CN 113600896A
- Authority
- CN
- China
- Prior art keywords
- milling cutter
- image
- monitoring
- machine tool
- numerical control
- 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
- 238000003801 milling Methods 0.000 title claims abstract description 136
- 238000012544 monitoring process Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000001133 acceleration Effects 0.000 claims abstract description 15
- 238000013461 design Methods 0.000 claims abstract description 10
- 230000007246 mechanism Effects 0.000 claims description 44
- 238000012545 processing Methods 0.000 claims description 27
- 238000005299 abrasion Methods 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 230000002902 bimodal effect Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000006740 morphological transformation Effects 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims 1
- 238000012216 screening Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 10
- 238000000498 ball milling Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000003754 machining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 239000005350 fused silica glass Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23C—MILLING
- B23C9/00—Details or accessories so far as specially adapted to milling machines or cutter
-
- 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
- B23Q17/22—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring existing or desired position of tool or work
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Machine Tool Sensing Apparatuses (AREA)
Abstract
A wear state signal monitoring method for a milling cutter of a numerical control machine tool comprises the following steps: a three-component dynamometer is arranged between a workpiece and a workbench of the numerical control machine tool, the three-component dynamometer measures cutting forces in three directions in space in a voltage mode, 3 piezoelectric acceleration sensors are arranged on the workpiece and used for measuring vibration signals, a noise sensor is arranged on the outer side of the workbench, and voltage signals of the three-component dynamometer, voltage signals of the piezoelectric acceleration sensors and sound pressure signals of the noise sensor are collected into an upper computer; the milling cutter is positioned above a workpiece, and is mounted on a main shaft of a numerical control machine tool through a positioning clamp so as to freely move in X, Y, Z shaft three directions. The method for monitoring the wear state signal of the milling cutter of the numerical control machine tool is reasonable in design, combines indirect monitoring with direct monitoring, and avoids the problems that a single monitoring method is easy to be interfered by noise, large in monitoring data and low in monitoring accuracy.
Description
Technical Field
The invention belongs to the technical field of numerical control machines, and particularly relates to a method for monitoring a wear state signal of a milling cutter of a numerical control machine.
Background
The main factor of the numerical control machine tool failure is cutter failure, and great economic loss can be caused if the failure state of the cutter cannot be monitored early and effectively. According to statistics, 1/5-1/3 of total downtime of the numerical control machine tool is caused by cutter failure, and the downtime of the numerical control machine tool with the cutter monitoring system can be reduced by 75 percent, so that the productivity is improved, and the utilization rate of the machine tool can be improved by more than 50 percent. Therefore, the real-time online monitoring of the cutter in the numerical control machine tool is of great significance.
The method for monitoring the abrasion of the numerical control machine tool cutter in the prior art generally judges the abrasion state and the health service life of the cutter by monitoring the change of a machining parameter in the machining process, including machine tool power, an acoustic emission signal, the vibration frequency of the cutter or a workpiece and the like. Therefore, there is a need to develop a wear status signal monitoring method for a milling cutter of a numerically controlled machine tool to solve the above problems.
Chinese patent application No. CN201920091081.9 discloses a trinity sensor anchor clamps and multimode cutter wearing and tearing state monitoring system, through having integrateed three kinds of sensors, can real-time accurate detection data signal, guarantees the precision, realizes cutting monitoring system's front end monitoring function, does not solve milling cutter wearing and tearing state signal monitoring and has the problem that the acquisition information volume is limited, the interference killing feature is relatively weak.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects, the invention aims to provide a method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the method is reasonable in design, indirect monitoring and direct monitoring are combined, the problems of high possibility of noise interference, large monitoring data and low monitoring accuracy caused by a single monitoring method are avoided, and the application prospect is wide. .
The purpose of the invention is realized by the following technical scheme:
a wear state signal monitoring method for a milling cutter of a numerical control machine tool comprises the following steps:
(1) a three-component dynamometer is arranged between a workpiece and a workbench of the numerical control machine tool, the three-component dynamometer measures cutting forces in three directions in space in a voltage mode, 3 piezoelectric acceleration sensors are arranged on the workpiece and used for measuring vibration signals, a noise sensor is arranged on the outer side of the workbench, and voltage signals of the three-component dynamometer, voltage signals of the piezoelectric acceleration sensors and sound pressure signals of the noise sensor are collected into an upper computer; the milling cutter is positioned above a workpiece, and is mounted on a main shaft of a numerical control machine tool through a positioning clamp so as to freely move in three directions of X, Y, Z axes;
(2) the visual detection device is arranged on the outer side of the milling cutter and fixed through a clamp, the visual detection device comprises a light source, a CCD camera, a lens and an image acquisition card, the outer side of the milling cutter is arranged on the light source, the CCD camera is positioned between the milling cutter and the light source, the lens is arranged on the CCD camera and faces the milling cutter, the CCD camera is connected with the image acquisition card, and the image acquisition card adopts IEEE1394 to connect an upper computer to transmit an image of the milling cutter;
(3) after the voltage signals of the three-component dynamometer, the voltage signals of the piezoelectric acceleration sensor and the voltage signals of the noise sensor which are obtained by the upper computer are analyzed and screened by kernel principal component, signal identification of the wear state of the milling cutter is realized through a network model of BPNN; the milling cutter image obtained by the upper computer is subjected to image processing, then the upper computer extracts the milling cutter image abrasion area subjected to image processing by adopting machine vision software, and finally the abrasion loss of the milling cutter is quantified to determine the abrasion state of the milling cutter, so that the abrasion monitoring of the cutter is realized.
The method for monitoring the wear state signal of the milling cutter of the numerical control machine tool is reasonable in design, combines indirect monitoring with direct monitoring, judges the wear state and the health life of the milling cutter by monitoring the change of processing parameters in the processing process, including cutting force signals, vibration signals and sound pressure signals in three directions in the processing process of the milling cutter, and monitors the wear of the milling cutter based on machine vision by the direct monitoring, accurately provides a wear quantitative value of the milling cutter at a certain moment, and can avoid the calculation cost of processing a large amount of data.
Further, the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool comprises the following specific steps of: the rotating speed of the ball mill is 250r/min, the ball milling mode adopts positive and negative rotation ball milling, the ball milling time is 6h, and the fused quartz powder after ball milling passes through a 500-mesh sieve.
Further, in the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the positioning fixture in the step (1) comprises a clamping mechanism, an annular fixed base, a shell and a rotating bottom plate, wherein the clamping mechanism is installed on the annular fixed base and is used for clamping and stretching a cutter handle of the milling cutter; the annular fixed base is used for supporting the milling cutter and is fixedly connected with the main shaft; the rotating bottom plate is arranged in the inner circle of the annular fixed base or on the upper surface of the annular fixed base, the shell is buckled on the rotating bottom plate, and the shell is fixedly connected with the rotating bottom plate through a connecting rod; a clamping mechanism is arranged between the shell and the rotating bottom plate; the middle part of the shell is provided with a through hole communicated with the clamping port of the clamping mechanism, and the inner side of the through hole is used for the clamping mechanism to clamp the cutter handle of the milling cutter.
The milling cutter handle is clamped and opened through the positioning clamp, so that the milling cutter is accurately positioned, and the detection efficiency of milling cutter abrasion is improved. The main shaft is driven to move through the movable sliding rail of the X, Y, Z shaft on the numerical control machine tool, and then the main shaft drives the positioning fixture to freely move in three directions of the X, Y, Z shaft, so that multidirectional adjustment is realized, and the detection position of the milling cutter can be flexibly adjusted. The inner circle diameter size of the annular fixing base is larger than the limit accommodating size of the clamping mechanism in the complete relaxation state, so that the cutter handle of the milling cutter can easily penetrate through the annular fixing base and can be inserted into the clamping mechanism for clamping.
Further, in the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the clamping mechanism comprises a lower fixing block, at least three clamping eccentric wheels and an upper fixing block; the bottom of the lower fixing block is fixedly connected with the annular fixing base, and the top of the lower fixing block is provided with a groove; the clamping eccentric wheel comprises a supporting column, a sliding column and an eccentric wheel, the bottom end of the supporting column is fixedly connected with the rotating bottom plate, the eccentric wheel is eccentrically sleeved on the supporting column, the wheel edge of the eccentric wheel is fixedly connected with the sliding column, and the sliding column is slidably arranged in the groove; the upper fixing block is connected with the lower fixing block, and a groove formed in the lower surface of the upper fixing block is opposite to a groove formed in the top of the lower fixing block.
The rotating bottom plate and the supporting columns are driven to rotate through the rotating shell, so that the sliding columns slide in the grooves, the clamping mechanism is opened, and the shell rotates reversely to clamp the clamping mechanism. The sliding column is limited when sliding through the upper fixing block. During the clamping or opening process of the clamping mechanism, the track of the sliding column sliding in the groove is not a straight line but a curved arc line.
Furthermore, according to the signal monitoring method for the wear state of the milling cutter of the numerical control machine tool, the annular fixing base is provided with the positioning pins with the same number as the connecting rods, each positioning pin is connected with the corresponding connecting rod through a spring, and the spring is used for driving the clamping mechanism to recover to a clamping state by utilizing the deformed elastic force after being expanded; the shell is provided with a rotating rod, and the shell and the rotating bottom plate are driven to rotate by rotating the rotating rod, so that the clamping and the opening of the clamping mechanism are realized.
Under the normal state that the milling cutter handle is not placed, the clamping mechanism is in a clamping state due to the stretching action of the spring, namely the plurality of clamping eccentric wheels are in an aggregation state. When the milling cutter handle is placed to be clamped, the rotating rod is pulled to drive the shell and the rotating bottom plate to rotate, so that one end of a supporting column clamping the eccentric wheel rotates along with the shell and the rotating bottom plate to drive the eccentric wheel to rotate, one end of the sliding column is arranged in a groove between the upper fixing block and the lower fixing block to slide, and finally the clamping mechanism is opened.
Further, in the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the CCD camera in the step (2) is a high-resolution industrial digital CCD camera, and the lens is a double-telecentric machine vision lens.
Further, in the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the step of the structural design of the network model of the BPNN in the step (3) is as follows:
(1) designing an input layer: the number of nodes of the input layer is equal to the characteristic number of voltage signals of the three-component dynamometer, voltage signals of the piezoelectric acceleration sensor and voltage signals of the noise sensor (4) which are analyzed and screened by the kernel principal component;
(2) designing an output layer: the number of the nodes of the output layer is 3 states of initial, normal and rapid abrasion of the milling cutter, and the number of the nodes of the output layer is 3;
(3) hidden layer design: the number of hidden layer nodes is represented by k = (a + b)/2+ c, c ∈ [1, 10 ].
Further, in the method for monitoring a wear state signal of a milling cutter of a numerical control machine tool, the image processing in the step (3) includes the following steps:
(1) histogram equalization: the upper computer obtains a histogram of a milling cutter image shot and collected by the CCD camera through an image collection card, calculates a new gray level, then corrects the new histogram into a reasonable gray level, calculates a new histogram of the collected image, and generates a new image;
(2) denoising an image: carrying out mean value filtering processing on the image, carrying out weighted average calculation on the field points of the pixel points to be processed of the image by using weight coefficients, and endowing the obtained calculation result to the points until each pixel point in the image is processed;
(3) threshold segmentation: performing threshold segmentation on the image by adopting a bimodal method;
(4) image edge extraction: and (3) carrying out image edge extraction detection on the image by adopting a canny operator, and then, adopting comprehensive operation of expansion and corrosion to make the edge information of the image clearer.
After the upper computer acquires the milling cutter image, in order to enable the upper computer to better identify the characteristic information of the milling cutter abrasion, a series of image processing needs to be firstly carried out on the milling cutter image, so that the useful information of the milling cutter image is enhanced, and the upper computer can more quickly and accurately identify and detect the abrasion defect of the milling cutter. Meanwhile, in the image acquisition process, the phenomena of poor illumination, irregular operation and the like can be inevitably generated, the obtained image has deviation from the ideal, such as noise, the position of the image needs to be corrected and the like, and the problems can cause great interference on the accuracy of image analysis.
According to the invention, histogram equalization is firstly carried out, the background part in the image of the operated milling cutter is inhibited, the abrasion area on the milling cutter is highlighted, the contrast of the image is improved, and the detection of abrasion in the following process is facilitated; denoising the image through mean filtering; the purpose of carrying out threshold segmentation on the image to be detected is to segment the wear information of the milling cutter from the background of the milling cutter, so that convenience is provided for the next processing; the image edge extraction is carried out on the image after the threshold segmentation, so that the edge information of the image is conveniently extracted, and the integrity of the edge information is the basis of the subsequent image identification.
Further, in the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool, the wear region of the milling cutter image in the step (3) is extracted, the extreme point is obtained by using morphological reconstruction on the image after image processing, an extreme point is obtained, wherein both the background region and the non-wear region of the milling cutter belong to the local extreme point, the boundary of each region does not belong to the local extreme point, and finally the boundary of the wear region of the milling cutter is extracted through morphological transformation.
Compared with the prior art, the invention has the following beneficial effects:
the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool is reasonable in design, combines indirect monitoring with direct monitoring, avoids the problems of high possibility of noise interference, large monitoring data and low monitoring accuracy caused by a single monitoring method, judges the wear state and the health life of the milling cutter by monitoring the change of processing parameters in the processing process, including cutting force signals, vibration signals and sound pressure signals in three directions in the processing process of the milling cutter, and accurately gives a wear quantitative value of the milling cutter at a certain moment by directly monitoring the wear of the milling cutter based on machine vision, can avoid the calculation cost for processing a large amount of data, and has a wide application prospect.
Drawings
FIG. 1 is a schematic layout view of a signal monitoring method for the wear state of a milling cutter of a numerically-controlled machine tool according to the present invention;
FIG. 2 is a frame diagram of the signal monitoring method for the wear state of the milling cutter of the numerical control machine tool according to the present invention;
FIG. 3 is a schematic structural diagram of a positioning mechanism of the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool according to the present invention;
FIG. 4 is an assembly view of a positioning mechanism of the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool according to the present invention;
in the figure: the device comprises a workbench 1, a three-component dynamometer 2, a piezoelectric acceleration sensor 3, a noise sensor 4, an upper computer 5, a positioning clamp 6, a tightening mechanism 61, a lower fixing block 611, a clamping eccentric wheel 612, a supporting column 6121, a sliding column 6122, an eccentric wheel 6123, an upper fixing block 613, an annular fixing base 62, a positioning pin 621, a spring 622, a shell 63, a rotating rod 631, a rotating bottom plate 64, a connecting rod 65, a milling cutter 7, a spindle 8, a visual detection device 9, a light source 91, a CCD camera 92, a lens 93, an image acquisition card 94, a numerical control machine tool a and a workpiece b.
Detailed Description
The invention will be further elucidated with reference to the accompanying figures 1-4 and specific examples.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
A wear state signal monitoring method for a milling cutter of a numerical control machine tool comprises the following steps:
(1) a three-component force measuring instrument 2 is arranged between a workpiece b and a workbench 1 of the numerical control machine tool, the three-component force measuring instrument 2 measures cutting forces in three directions in a space in a voltage mode, 3 piezoelectric acceleration sensors 3 are arranged on the workpiece for measuring vibration signals, a noise sensor 4 is arranged on the outer side of the workbench 1, and voltage signals of the three-component force measuring instrument 2, voltage signals of the piezoelectric acceleration sensors 3 and sound pressure signals of the noise sensor 4 are collected into an upper computer 5; the milling cutter 7 is positioned above a workpiece, and the milling cutter 7 is mounted on a main shaft 8 of a numerical control machine tool through a positioning clamp 6 so as to freely move in three directions of X, Y, Z axes;
(2) a visual detection device 9 is arranged on the outer side of the milling cutter 7, the visual detection device 9 is fixed through a clamp, the visual detection device 9 comprises a light source 91, a CCD camera 92, a lens 93 and an image acquisition card 94, the outer side of the milling cutter 7 is arranged on the light source 91, the CCD camera 92 is positioned between the milling cutter 7 and the light source 91, the CCD camera 92 is provided with the lens 93 and faces the milling cutter 7, the CCD camera 92 is connected with the image acquisition card 94, and the image acquisition card 94 adopts IEEE1394 to connect with an upper computer 5 to transmit milling cutter images;
(3) after the voltage signal of the three-component dynamometer 2, the voltage signal of the piezoelectric acceleration sensor 3 and the voltage signal of the noise sensor 4 which are obtained by the upper computer 5 are analyzed and screened by kernel principal component, signal identification of the wear state of the milling cutter 7 is realized through a network model of BPNN; the milling cutter image obtained by the upper computer 5 is subjected to image processing, then the upper computer 5 extracts the milling cutter image abrasion area subjected to image processing by adopting machine vision software, and finally, the abrasion loss of the milling cutter is quantified to determine the abrasion state of the milling cutter, so that the abrasion monitoring of the cutter is realized.
The positioning fixture 6 in the step (1) comprises a clamping mechanism 61, an annular fixed base 62, a housing 63 and a rotating base plate 64, wherein the clamping mechanism 61 is mounted on the annular fixed base 62, and the clamping mechanism 61 is used for clamping and expanding the tool shank of the milling cutter 7; the annular fixed base 62 is used for supporting the milling cutter 7, and the annular fixed base 62 is fixedly connected with the main shaft 8; the rotating base plate 64 is arranged in the inner circle of the annular fixed base 62 or on the upper surface of the annular fixed base 62, the shell 63 is buckled on the rotating base plate 64, and the shell 63 is fixedly connected with the rotating base plate 64 through a connecting rod 65; a clamping mechanism 61 is arranged between the shell 63 and the rotating base plate 64; the middle of the shell 63 is provided with a through hole communicated with the clamping port of the clamping mechanism 61, and the inner side of the through hole is used for the clamping mechanism 61 to clamp the cutter handle of the milling cutter 7.
The handle of the milling cutter 7 is clamped and opened through the positioning clamp 6, so that the milling cutter 7 is accurately positioned, and the detection efficiency of the abrasion of the milling cutter 7 is improved. The main shaft is driven to move by the movable sliding rail of the X, Y, Z shaft on the numerical control machine tool a, and then the main shaft 8 drives the positioning clamp 6 to freely move in three directions of the X, Y, Z shaft, so that multidirectional adjustment is realized, and the detection position of the milling cutter 7 can be flexibly adjusted. The inner diameter of the annular fixing base 62 is larger than the limit accommodation size of the clamping mechanism 61 in the fully relaxed state, so that the shank of the milling cutter 7 can easily pass through the annular fixing base 72 and be inserted into the clamping mechanism 71 for clamping.
Further, the clamping mechanism 61 comprises a lower fixing block 611, at least three clamping eccentric wheels 612, and an upper fixing block 613; the bottom of the lower fixing block 611 is fixedly connected with the annular fixing base 62, and a groove is formed in the top of the lower fixing block 611; the clamping eccentric wheel 612 comprises a supporting column 6121, a sliding column 6122 and an eccentric wheel 6123, the bottom end of the supporting column 6121 is fixedly connected with the rotating base plate 64, the eccentric wheel 6123 is eccentrically sleeved on the supporting column 6121, the wheel edge of the eccentric wheel 6123 is fixedly connected with the sliding column 6122, and the sliding column 6122 is slidably arranged in the groove; the upper fixing block 613 is connected to the lower fixing block 611, and a groove formed in the lower surface of the upper fixing block 613 is opposite to a groove formed in the top of the lower fixing block 611.
The rotating base plate 64 and the supporting column 6121 are driven to rotate by rotating the shell 73, so that the sliding column 6122 slides in the groove to open the clamping mechanism 61, and the shell 63 rotates reversely to clamp the clamping mechanism 61. The upper fixing block 613 is used for limiting the sliding column 6122 during sliding. During the clamping or opening process of the clamping mechanism 61, the track of the sliding column 6122 sliding in the groove is not a straight line, but a curved arc.
Furthermore, the annular fixing base 62 is provided with positioning pins 621 the same as the number of the connecting rods 65, each positioning pin 621 is connected with the corresponding connecting rod 65 through a spring 622, and the spring 622 is used for driving the clamping mechanism 61 to return to a clamping state by utilizing the deformed elastic force after being expanded; the shell 63 is provided with a rotating rod 631, and the shell 63 and the rotating base plate 64 are driven to rotate by rotating the rotating rod 631, so that the clamping and the opening of the clamping mechanism 61 are realized.
In a normal state where the shank of the milling cutter 7 is not inserted, the clamping mechanism 61 is in a clamped state, i.e., the plurality of clamping eccentrics 612 are in a converged state, due to the stretching action of the spring 62. When the milling cutter 7 is put in the cutter handle for clamping, the rotating rod 731 is pulled to drive the shell 63 and the rotating bottom plate 64 to rotate, so that one end of the supporting column 6121 of the clamping eccentric 612 rotates along with the outer shell 63 and the rotating bottom plate 646123, drives the eccentric 6123 to rotate, so that one end of the sliding column 6122 slides in the groove between the upper fixing block 613 and the lower fixing block 611, and finally the clamping mechanism 61 is opened, at this time, the milling cutter 7 is placed at the clamping position of the central through hole of the positioning clamp 6, the spring 622 is stretched to have elastic force, the rotating rod 631 is loosened, the spring 22 automatically retracts to a normal state by utilizing the elastic deformation principle of the spring 6226, and the shell 63 and the rotating bottom plate 64 are driven to reversely rotate to the original position, thereby realized clamping mechanism 61's auto-lock and pressed from both sides tightly, realized the centering to handle of a knife and milling cutter 7 to the realization is to the radial and axial accurate location of handle of a knife.
The CCD camera 92 in the step (2) is a high-resolution industrial digital CCD camera, and the lens 93 is a double telecentric machine vision lens.
The BPNN network model in the step (3) has the following structural design steps:
(1) designing an input layer: the number of nodes of the input layer is equal to the characteristic number of voltage signals of the three-component dynamometer 2, voltage signals of the piezoelectric acceleration sensor 3 and voltage signals of the noise sensor 4 which are analyzed and screened by the kernel principal component;
(2) designing an output layer: the number of the nodes of the output layer is 3 states of initial, normal and rapid abrasion of the milling cutter 7, and the number of the nodes of the output layer is 3;
(3) hidden layer design: the number of hidden layer nodes is represented by k = (a + b)/2+ c, c ∈ [1, 10 ].
The image processing in the step (3) comprises the following steps:
(1) histogram equalization: the upper computer 5 obtains a histogram of the milling cutter image photographed and collected by the CCD camera 92 through the image acquisition card 94, calculates a new gray level, then corrects the new histogram to a reasonable gray level, calculates a new histogram of the collected image, and generates a new image;
(2) denoising an image: carrying out mean value filtering processing on the image, carrying out weighted average calculation on the field points of the pixel points to be processed of the image by using weight coefficients, and endowing the obtained calculation result to the points until each pixel point in the image is processed;
(3) threshold segmentation: performing threshold segmentation on the image by adopting a bimodal method;
(4) image edge extraction: and (3) carrying out image edge extraction detection on the image by adopting a canny operator, and then, adopting comprehensive operation of expansion and corrosion to make the edge information of the image clearer.
After the upper computer acquires the milling cutter image, in order to enable the upper computer to better identify the characteristic information of the milling cutter abrasion, a series of image processing needs to be firstly carried out on the milling cutter image, so that the useful information of the milling cutter image is enhanced, and the upper computer can more quickly and accurately identify and detect the abrasion defect of the milling cutter. Meanwhile, in the image acquisition process, the phenomena of poor illumination, irregular operation and the like can be inevitably generated, the obtained image has deviation from the ideal, such as noise, the position of the image needs to be corrected and the like, and the problems can cause great interference on the accuracy of image analysis.
According to the invention, histogram equalization is firstly carried out, the background part in the image of the operated milling cutter is inhibited, the abrasion area on the milling cutter is highlighted, the contrast of the image is improved, and the detection of abrasion in the following process is facilitated; denoising the image through mean filtering; the purpose of carrying out threshold segmentation on the image to be detected is to segment the wear information of the milling cutter from the background of the milling cutter, so that convenience is provided for the next processing; the image edge extraction is carried out on the image after the threshold segmentation, so that the edge information of the image is conveniently extracted, and the integrity of the edge information is the basis of the subsequent image identification.
Extracting the worn area of the milling cutter image in the step (3), solving extreme points of the image after image processing by using morphological reconstruction to obtain an extreme point diagram, wherein the background area and the unworn area of the milling cutter belong to local extreme points, the boundary of each area does not belong to the local extreme points, and finally extracting the boundary of the worn area of the milling cutter through morphological transformation.
In conclusion, the method for monitoring the wear state signal of the milling cutter of the numerical control machine tool is reasonable in design, combines indirect monitoring with direct monitoring, avoids the problems of high possibility of noise interference, large monitoring data and low monitoring accuracy rate caused by a single monitoring method, and has wide application prospect
The preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, however, the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the technical idea of the present invention, and these simple modifications are within the protective scope of the present invention.
It should be noted that the various technical features described in the above embodiments can be combined in any suitable manner without contradiction, and the invention is not described in any way for the possible combinations in order to avoid unnecessary repetition.
In addition, any combination between the embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the idea of the present invention.
Claims (8)
1. A method for monitoring a wear state signal of a milling cutter of a numerical control machine tool is characterized by comprising the following steps:
a three-component force measuring instrument (2) is arranged between a workpiece and a workbench (1) of a numerical control machine tool, the three-component force measuring instrument (2) measures cutting forces in three directions in a space in a voltage mode, 3 piezoelectric acceleration sensors (3) are arranged on the workpiece and used for measuring vibration signals, a noise sensor (4) is arranged on the outer side of the workbench (1), and voltage signals of the three-component force measuring instrument (2), voltage signals of the piezoelectric acceleration sensors (3) and sound pressure signals of the noise sensor (4) are collected into an upper computer (5); the milling cutter (7) is positioned above a workpiece, and the milling cutter (7) is mounted on a main shaft (8) of a numerical control machine tool through a positioning clamp (6) so as to freely move in three directions of an X, Y, Z shaft;
a visual detection device (9) is arranged on the outer side of the milling cutter (7), the visual detection device (9) is fixed through a clamp, the visual detection device (9) comprises a light source (91), a CCD camera (92), a lens (93) and an image acquisition card (94), the outer side of the milling cutter (7) is arranged on the light source (91), the CCD camera (92) is located between the milling cutter (7) and the light source (91), the lens (93) is mounted on the CCD camera (92) and faces the milling cutter (7), the CCD camera (92) is connected with the image acquisition card (94), and the image acquisition card (94) is connected with an upper computer (5) through IEEE1394 so as to transmit milling cutter images;
after the voltage signal of the three-component dynamometer (2), the voltage signal of the piezoelectric acceleration sensor (3) and the voltage signal of the noise sensor (4) obtained by the upper computer (5) are analyzed and screened by kernel principal component, signal identification of the abrasion state of the milling cutter (7) is realized through a BPNN network model; the milling cutter image obtained by the upper computer (5) is subjected to image processing, then the upper computer (5) adopts machine vision software to extract the image wear area of the milling cutter subjected to image processing, and finally the wear amount of the milling cutter is quantized to determine the wear state of the milling cutter, so that the wear monitoring of the cutter is realized.
2. The method for monitoring the wear state signal of the milling cutter of the numerical control machine tool according to claim 1, wherein the positioning fixture (6) in the step (1) comprises a clamping mechanism (61), an annular fixed base (62), a shell (63) and a rotating base plate (64), wherein the clamping mechanism (61) is installed on the annular fixed base (62), and the clamping mechanism (61) is used for clamping and expanding the shank of the milling cutter (7); the annular fixed base (62) is used for supporting the milling cutter (7), and the annular fixed base (62) is fixedly connected with the main shaft (8); the rotating bottom plate (64) is arranged in the inner circle of the annular fixed base (62) or on the upper surface of the annular fixed base (62), the shell (63) is buckled on the rotating bottom plate (64), and the shell (63) is fixedly connected with the rotating bottom plate (64) through a connecting rod (65); a clamping mechanism (61) is arranged between the shell (63) and the rotating bottom plate (64); the middle of the shell (63) is provided with a through hole communicated with a clamping port of the clamping mechanism (61), and the clamping mechanism (61) is used for clamping a cutter handle of the milling cutter (7) on the inner side of the through hole.
3. The method for monitoring the signal of the wear state of the milling cutter of the numerical control machine tool according to claim 2, characterized in that the clamping mechanism (61) comprises a lower fixed block (611), at least three clamping eccentric wheels (612), an upper fixed block (613); the bottom of the lower fixing block (611) is fixedly connected with the annular fixing base (62), and the top of the lower fixing block (611) is provided with a groove; the clamping eccentric wheel (612) comprises a supporting column (6121), a sliding column (6122) and an eccentric wheel (6123), the bottom end of the supporting column (6121) is fixedly connected with the rotating base plate (64), the eccentric wheel (6123) is eccentrically sleeved on the supporting column (6121), the wheel edge of the eccentric wheel (6123) is fixedly connected with the sliding column (6122), and the sliding column (6122) is slidably arranged in the groove; the upper fixing block (613) is connected with the lower fixing block (611), and a groove formed in the lower surface of the upper fixing block (613) is opposite to a groove formed in the top of the lower fixing block (611).
4. The method for monitoring the wear state signal of the milling cutter of the numerical control machine tool according to claim 3, wherein the annular fixing base (62) is provided with the same number of positioning pins (621) as the number of the connecting rods (65), each positioning pin (621) is connected with the corresponding connecting rod (65) through a spring (622), and the spring (622) is used for driving the clamping mechanism (61) to return to the clamping state by utilizing the deformed elastic force after being expanded; the shell (63) is provided with a rotating rod (631), and the shell (63) and the rotating base plate (64) are driven to rotate by rotating the rotating rod (631), so that clamping and opening of the clamping mechanism (61) are realized.
5. The method for monitoring the signal of the wear state of the milling cutter of the numerical control machine tool according to claim 1, wherein the CCD camera (92) in the step (2) adopts a high-resolution industrial digital CCD camera, and the lens (93) adopts a double telecentric machine vision lens.
6. The method for monitoring the wear state signal of the milling cutter of the numerical control machine tool according to claim 1, wherein the step of designing the network model of the BPNN in the step (3) is as follows:
designing an input layer: the number of nodes of the input layer is equal to the characteristic number of voltage signals of the three-component dynamometer (2), voltage signals of the piezoelectric acceleration sensor (3) and voltage signals of the noise sensor (4) after kernel principal component analysis and screening;
designing an output layer: the number of the nodes of the output layer is 3 states of initial, normal and rapid abrasion of the milling cutter (7), and the number of the nodes of the output layer is 3;
hidden layer design: the number of hidden layer nodes is represented by k = (a + b)/2+ c, c ∈ [1, 10 ].
7. The method for monitoring a wear state signal of a milling cutter of a numerical control machine tool according to claim 1, wherein the image processing in the step (3) comprises the steps of:
(1) histogram equalization: the upper computer (5) obtains a histogram of the milling cutter image photographed and collected by the CCD camera (92) through the image collection card (94), calculates a new gray level, then corrects the gray level to a reasonable gray level, calculates a new histogram of the collected image, and generates a new image;
(2) denoising an image: carrying out mean value filtering processing on the image, carrying out weighted average calculation on the field points of the pixel points to be processed of the image by using weight coefficients, and endowing the obtained calculation result to the points until each pixel point in the image is processed;
(3) threshold segmentation: performing threshold segmentation on the image by adopting a bimodal method;
(4) image edge extraction: and (3) carrying out image edge extraction detection on the image by adopting a canny operator, and then, adopting comprehensive operation of expansion and corrosion to make the edge information of the image clearer.
8. The method for monitoring the signal of the wear state of the milling cutter of the numerical control machine tool according to claim 1, wherein the wear region of the milling cutter image in the step (3) is extracted, the extreme points are obtained by using morphological reconstruction on the image after image processing to obtain an extreme point diagram, wherein the background region and the non-wear region of the milling cutter belong to local extreme points, the boundary of each region does not belong to the local extreme points, and finally the boundary of the wear region of the milling cutter is extracted through morphological transformation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110905565.4A CN113600896A (en) | 2021-08-05 | 2021-08-05 | Method for monitoring wear state signal of milling cutter of numerical control machine tool |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110905565.4A CN113600896A (en) | 2021-08-05 | 2021-08-05 | Method for monitoring wear state signal of milling cutter of numerical control machine tool |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113600896A true CN113600896A (en) | 2021-11-05 |
Family
ID=78339853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110905565.4A Pending CN113600896A (en) | 2021-08-05 | 2021-08-05 | Method for monitoring wear state signal of milling cutter of numerical control machine tool |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113600896A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114571286A (en) * | 2022-03-17 | 2022-06-03 | 上海大学 | Tool wear state monitoring method and system based on friction electrification principle |
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 |
CN117697000A (en) * | 2024-02-05 | 2024-03-15 | 山东恩特机床有限公司 | Milling vibration measuring instrument |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102564314A (en) * | 2011-12-06 | 2012-07-11 | 上海交通大学 | Orthogonal vision detection system for detecting wear condition of end mill |
CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
CN105196114A (en) * | 2015-11-05 | 2015-12-30 | 西安科技大学 | Real-time online tool wear monitoring method based on wavelet analysis and neural network |
CN108803492A (en) * | 2018-07-20 | 2018-11-13 | 南京梵科智能科技有限公司 | A kind of numerically-controlled machine tool cutter head fault diagnosis system |
CN109822399A (en) * | 2019-04-08 | 2019-05-31 | 浙江大学 | Cutting tool for CNC machine state of wear prediction technique based on parallel deep neural network |
CN110488753A (en) * | 2019-08-29 | 2019-11-22 | 山东大学 | Whirling tool periscopic testing agency, forecasting system and method |
CN110576336A (en) * | 2019-09-11 | 2019-12-17 | 大连理工大学 | Method for monitoring abrasion loss of deep hole machining tool based on SSAE-LSTM model |
CN111958321A (en) * | 2020-08-09 | 2020-11-20 | 西北工业大学 | Numerical control machine tool cutter wear degree identification method based on deep neural network |
CN112247674A (en) * | 2020-10-10 | 2021-01-22 | 北京理工大学 | Cutter wear prediction method |
CN112872908A (en) * | 2021-02-03 | 2021-06-01 | 哈尔滨理工大学 | Positioning fixture for cutter wear detection and experiment platform |
-
2021
- 2021-08-05 CN CN202110905565.4A patent/CN113600896A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102564314A (en) * | 2011-12-06 | 2012-07-11 | 上海交通大学 | Orthogonal vision detection system for detecting wear condition of end mill |
CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
CN105196114A (en) * | 2015-11-05 | 2015-12-30 | 西安科技大学 | Real-time online tool wear monitoring method based on wavelet analysis and neural network |
CN108803492A (en) * | 2018-07-20 | 2018-11-13 | 南京梵科智能科技有限公司 | A kind of numerically-controlled machine tool cutter head fault diagnosis system |
CN109822399A (en) * | 2019-04-08 | 2019-05-31 | 浙江大学 | Cutting tool for CNC machine state of wear prediction technique based on parallel deep neural network |
CN110488753A (en) * | 2019-08-29 | 2019-11-22 | 山东大学 | Whirling tool periscopic testing agency, forecasting system and method |
CN110576336A (en) * | 2019-09-11 | 2019-12-17 | 大连理工大学 | Method for monitoring abrasion loss of deep hole machining tool based on SSAE-LSTM model |
CN111958321A (en) * | 2020-08-09 | 2020-11-20 | 西北工业大学 | Numerical control machine tool cutter wear degree identification method based on deep neural network |
CN112247674A (en) * | 2020-10-10 | 2021-01-22 | 北京理工大学 | Cutter wear prediction method |
CN112872908A (en) * | 2021-02-03 | 2021-06-01 | 哈尔滨理工大学 | Positioning fixture for cutter wear detection and experiment platform |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114571286A (en) * | 2022-03-17 | 2022-06-03 | 上海大学 | Tool wear state monitoring method and system based on friction electrification principle |
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 |
CN117697000A (en) * | 2024-02-05 | 2024-03-15 | 山东恩特机床有限公司 | Milling vibration measuring instrument |
CN117697000B (en) * | 2024-02-05 | 2024-05-10 | 山东恩特机床有限公司 | Milling vibration measuring instrument |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113600896A (en) | Method for monitoring wear state signal of milling cutter of numerical control machine tool | |
CN110587377B (en) | Method for monitoring defects of milling cutter on line | |
CN109822398B (en) | Numerical control machine tool broken cutter detection system and method based on deep learning | |
CN108490880B (en) | Method for monitoring wear state of cutting tool of numerical control machine tool in real time | |
CN110355608A (en) | Based on the tool abrasion prediction technique from attention mechanism and deep learning | |
CN109352416B (en) | Alarming method and device for clamping chips of machine tool spindle and/or winding chips of cutter | |
CN100361785C (en) | Digitized precise curve grinding integrated control system | |
CN105945651A (en) | Online cutter abrasion detecting device and method for precise milling of ball head milling cutter | |
CN113378725B (en) | Multi-scale-channel attention network-based tool fault diagnosis method, equipment and storage medium | |
CN112487890B (en) | Bearing acoustic signal fault diagnosis method based on parallel sparse filtering | |
JP2019098515A (en) | Blade tool state inspection system and method | |
CN111660141A (en) | Milling cutter wear state identification method based on spindle driving current and irrelevant to working conditions | |
CN102323059B (en) | Shaft pivoted hub bearing unit monitoring system for axial pivoting force and displacement and method | |
CN103941645A (en) | Thin-wall part complex working condition machining state monitoring method | |
CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
JP2021082126A (en) | Abnormality detection device, abnormality detection method and program | |
CN110346130A (en) | A kind of boring flutter detection method based on empirical mode decomposition and time-frequency multiple features | |
CN114714145B (en) | Graham angle field enhanced contrast learning monitoring method for cutter wear state | |
CN116257747A (en) | Early abnormality detection method for rotor system of fusion kurtosis and convolution self-encoder | |
JP2004534664A (en) | Inspection device and inspection method for machining process of machine tool | |
CN112946072A (en) | Abrasive belt wear state monitoring method based on machine learning | |
CN114670061A (en) | Machine vision-based composite tool service life monitoring system and method | |
Li et al. | Tool fault diagnosis based on improved multiscale network and feature fusion | |
KR20240020419A (en) | Micro drill bit grinding system with machine learning-based wear diagnosis | |
Wang et al. | A detection system of tool parameter using machine vision |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211105 |