CN109396956B - Intelligent monitoring method for hob state of numerical control gear hobbing machine - Google Patents
Intelligent monitoring method for hob state of numerical control gear hobbing machine Download PDFInfo
- Publication number
- CN109396956B CN109396956B CN201811314647.6A CN201811314647A CN109396956B CN 109396956 B CN109396956 B CN 109396956B CN 201811314647 A CN201811314647 A CN 201811314647A CN 109396956 B CN109396956 B CN 109396956B
- Authority
- CN
- China
- Prior art keywords
- hob
- state
- hobbing
- sample
- stage
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000012546 transfer Methods 0.000 claims abstract description 6
- 238000007621 cluster analysis Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000005520 cutting process Methods 0.000 claims description 24
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 208000035874 Excoriation Diseases 0.000 claims description 9
- 238000005299 abrasion Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 9
- 206010062544 Tooth fracture Diseases 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 7
- 238000003754 machining Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000009191 jumping Effects 0.000 description 3
- 239000000306 component Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction 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
-
- 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
- B23Q17/0971—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 mechanical vibrations of parts of the machine
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Gear Processing (AREA)
Abstract
The invention discloses an intelligent monitoring method for the hob state of a numerical control gear hobbing machine, which comprises the following steps: step one, collecting B-axis vibration signals in real time; step two, carrying out data segmentation on the B-axis vibration signal; step three, constructing a hob state standard sample set X, and extracting an initial characteristic vector f of the sample0(ii) a Step (ii) ofFourthly, constructing a hob state mutual K neighbor graph G, and performing feature selection to form a sample feature vector f; and fifthly, constructing a hob state characteristic matrix F, establishing a fuzzy similarity relation matrix R, constructing a transfer closure t (R) for cluster analysis, and realizing hob state identification. According to the numerical control gear hobbing machine, the hob state mutual K neighbor graph is constructed, the vibration signal processing of the main shaft of the numerical control gear hobbing machine is combined with the graph theory, the online real-time monitoring of the hob state can be realized, so that the hob can be replaced and sharpened in time, the occurrence of expansion cracks and cutter tooth breakage is avoided, the dependence on the professional skill of an operator can be reduced, and the intelligent process of the numerical control gear hobbing machine is promoted.
Description
Technical Field
The invention relates to an intelligent monitoring method for cutter state, in particular to an intelligent monitoring method for hob state of a numerical control gear hobbing machine.
Background
With the advance of the fourth industrial revolution which is mainly made of intelligent manufacturing, the numerical control machine tool is also developed towards the direction of precision, high speed, high efficiency and intelligence, and the monitoring of the cutter state becomes the main breakthrough direction of numerical control machine tool manufacturers. The existing research shows that the cutter state monitoring can improve the processing efficiency by 10-60%, reduce the shutdown failure rate by 75%, improve the utilization rate of a machine tool by more than 50%, effectively avoid workpiece rejection and machine tool failure caused by cutter failure, and save the cost by more than 30%. Therefore, the cutter state monitoring technology has great significance for ensuring the quality of workpieces, ensuring the production safety and improving the production efficiency.
The hob is used as a core component of the numerical control gear hobbing machine, and gradually wears along with the increase of cutting time in the gear hobbing process, so that the machining efficiency and the machining quality are reduced, and the hob needs to be replaced or sharpened after being worn to a certain degree. At present, a user of a numerical control gear hobbing machine checks the state of a hob constantly through an organizer and judges the time for replacing the hob according to the experience of the worker. On the one hand, the labor cost is increased; on the other hand, cost waste is caused by too early replacement of the hob, the machining quality is reduced and the production cost is increased by too late replacement, and even the service life of the hob is stopped in advance. The hob is different from a common cutter, is expensive, effectively monitors the state of the hob in real time, improves the production efficiency and the yield and reduces the production cost.
Disclosure of Invention
In view of the above, an object of the present invention is to provide an intelligent monitoring method for hob state of a numerical control gear hobbing machine, which realizes real-time monitoring of the hob state through vibration signal characteristics of a B-axis (main shaft) in a hob hobbing cycle, and can automatically identify the hob wear state, so as to solve the defects of manual experience-based hob state inspection in the prior art.
The invention discloses an intelligent monitoring method for hob state of a numerical control gear hobbing machine, which comprises the following steps:
acquiring vibration analog quantity of a B shaft in a hob hobbing processing cycle in real time through a pre-buried vibration acceleration sensor, wherein the B shaft is a main shaft of a numerical control gear hobbing machine; the vibration analog quantity is accessed to a PLC controller by utilizing a machine tool bus and is converted into digital quantity through A/D, so that a B-axis vibration signal is obtained; dividing the roll cutting processing cycle into an idle roll cutting stage, a transition roll cutting stage and a steady-state roll cutting stage;
the idle hobbing stage represents the motion process of the hob before the hob contacts the gear blank;
the transitional hobbing stage represents the motion process of the hob for cutting in and cutting out the gear blank; when cutting, the contact area between the hob and the gear blank is gradually increased; when cutting, the contact area between the hob and the gear blank is gradually reduced;
the steady-state hobbing stage represents the motion process of the hob with the largest contact area with the gear blank and relative stability;
step two, performing data segmentation on the signals according to the peak jump characteristic of the B-axis vibration signals which periodically appears, and segmenting the vibration signals of a hobbing processing cycle into three sections in a time domain, wherein the three sections respectively correspond to an idle hobbing stage, a transition hobbing stage and a steady-state hobbing stage;
thirdly, carrying out a large number of hobbing cutter full life cycle hobbing machining experiments, selecting B-axis vibration signals of corresponding steady-state hobbing stages under various hobbing cutter states, constructing a hobbing cutter state standard sample set X, and carrying out sample labeling; extracting time domain characteristic parameters, frequency domain characteristic parameters and Hilbert envelope spectrum frequency domain characteristic parameters of samplesForming a sample initial feature vector f0；
Step four, constructing a hob state mutual K neighbor graph G by utilizing all samples in the hob state standard sample set X, and establishing a similarity matrix S and a Laplace matrix L of the graph G; carrying out de-equalization processing on the characteristic parameters; then calculating the Laplace score of each characteristic parameter, and selecting characteristics according to the Laplace score to form a sample characteristic vector f;
step five, according to the newly obtained hob steady-state hobbing stage B-axis vibration signal sample, combining the samples in the hob state standard sample set X and the labels thereof, constructing a hob state characteristic matrix F:
wherein m represents the number of samples in a hob state standard sample set X, q represents the number of B-axis vibration signal samples in a newly obtained hob steady-state hobbing stage, and l represents the dimensionality of a sample characteristic vector f; f. ofijJ-th feature representing the i-th sample, i ═ 1,2, …, m + q; j ═ 1,2, …, l; c. CkDenotes the sample number, k ═ 1,2, …, m;
and (3) standardizing the characteristic parameter values in the F according to a maximum value method, establishing a fuzzy similarity relation matrix R through a maximum and minimum method, constructing a transfer closure t (R), and performing cluster analysis by adopting a lambda intercept matrix method to realize hob state identification.
Further: in the first step, the pre-embedded vibration acceleration sensor is a vibration acceleration sensor pre-embedded in a bearing support at the end part of the shaft B in the assembling and manufacturing process of the numerical control gear hobbing machine.
Further: in the third step, the state of the hob comprises six types including a new hob, early abrasion, normal abrasion, rapid abrasion, expansion crack, cutter tooth fracture and the like, wherein the new hob refers to a brand-new hob or a hob subjected to sharpening;
in the hob state standard sample set X, the number of samples corresponding to the six types of hob states is equal; the sample labels are respectively: the method comprises the following steps of 1 representing a B-axis vibration signal sample in a new cutter state, 2 representing a B-axis vibration signal sample in an early wear state, 3 representing a B-axis vibration signal sample in a normal wear state, 4 representing a B-axis vibration signal sample in a rapid wear state, 5 representing a B-axis vibration signal sample in a crack propagation state and 6 representing a B-axis vibration signal sample in a cutter tooth fracture state;
the time domain characteristic parameters comprise 15 of mean value, root mean square value, variance, covariance, maximum amplitude, minimum amplitude, peak-to-peak value, median of amplitude, root mean square value of amplitude, waveform index, pulse index, kurtosis index, margin index, skewness, peak value factor and the like, the frequency domain characteristic parameters and the frequency domain characteristic parameters of the Hilbert envelope spectrum respectively comprise 5 of center-of-gravity frequency, mean square frequency, root mean square frequency, frequency variance, frequency standard deviation and the like, and the total number of the characteristic parameters is 25.
Further: in the fourth step, the feature selection is to arrange the laplacian scores of all the feature parameters of the sample in an ascending order, and select the feature parameters corresponding to the first l laplacian scores to form a sample feature vector f.
The invention has the beneficial effects that:
the invention relates to an intelligent monitoring method for hob state of a numerical control gear hobbing machine, which combines vibration signal processing of a main shaft of the numerical control gear hobbing machine with a map theory through construction of a mutual K neighbor graph of the hob state to realize feature selection and state identification of the hob state. The method has the advantages of small calculation amount, short calculation time and easy programming realization, can realize the online real-time monitoring of the state of the hob so as to timely replace and sharpen the hob, avoid the occurrence of expansion cracks and cutter tooth fracture, prolong the service life of the hob and reduce the production cost; the dependence on the professional skills of operators is reduced, and the intelligent process of the numerical control gear hobbing machine is promoted.
Drawings
FIG. 1 is a schematic of a B-axis vibration signal for a hobbing process cycle.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments.
The method for intelligently monitoring the hob state of the numerical control gear hobbing machine comprises the following steps of:
acquiring vibration analog quantity of a B shaft in a hob hobbing processing cycle in real time through a pre-buried vibration acceleration sensor, and setting a sampling frequency of 10000 HZ; the B shaft is a main shaft of the numerical control gear hobbing machine, and the pre-embedding of the vibration acceleration sensor means that the vibration acceleration sensor is pre-embedded in a bearing support at the end part of the B shaft in the assembling and manufacturing process of the numerical control gear hobbing machine. The vibration analog quantity is accessed to a PLC controller by utilizing a machine tool bus and is converted into digital quantity through A/D, so that a B-axis vibration signal is obtained; and dividing the hobbing processing cycle into an idle hobbing stage, a transition hobbing stage and a steady-state hobbing stage. And the idle hobbing stage represents the motion process of the hob before the hob is contacted with the gear blank, and the B-axis vibration signal is small in the idle hobbing stage. The transitional hobbing stage represents the motion process of the hob for cutting in and cutting out the gear blank; when cutting, the contact area between the hob and the gear blank is gradually increased; when cutting, the contact area between the hob and the gear blank is gradually reduced; the B-axis vibration signal is large at this stage. And the steady-state hobbing stage represents the motion process of the hob with the largest contact area with the gear blank and relatively stable, and the B-axis vibration signal is the largest at the stage.
In a rolling cutting processing cycle, the time consumption relationship of each stage is as follows: the transition hobbing stage < the idle hobbing stage < the steady-state hobbing stage, and the proportion of the B-axis vibration signal corresponding to the steady-state hobbing stage in the time domain is the largest.
And step two, aiming at the B-axis vibration signal in the hobbing processing cycle, because of the characteristics of small vibration signal in the idle hobbing stage, large vibration signal in the transition hobbing stage and maximum vibration signal in the steady-state hobbing stage, the peak value of the vibration signal jumps periodically, the B-axis vibration signal is subjected to data segmentation according to the peak value jumping characteristic, and the vibration signal of one hobbing processing cycle is segmented into three segments in the time domain, which correspond to the idle hobbing stage, the transition hobbing stage and the steady-state hobbing stage respectively. The peak jumping characteristic refers to jumping change of the B-axis vibration signal peak value when the next stage is started from one stage in the process of the hobbing processing cycle.
Step three, carrying out a large number of hobbing cutter full life cycle gear hobbing processing experiments, and selecting various types of hobbing cuttersConstructing a hob state standard sample set X by using a B-axis vibration signal in a corresponding steady-state hob-cutting stage in the hob state, and carrying out sample labeling; extracting time domain characteristic parameters, frequency domain characteristic parameters and Hilbert envelope spectrum frequency domain characteristic parameters of the sample to form an initial characteristic vector f of the sample0(ii) a The specific implementation steps are as follows:
1) selecting B-axis vibration signals of a steady-state hobbing stage corresponding to a hob in six states of new hob, early abrasion, normal abrasion, rapid abrasion, crack propagation, cutter tooth fracture and the like, and constructing a hob state standard sample set X, wherein the number of samples corresponding to the six hob states is equal.
2) Sample labeling is carried out on samples in a hob state standard sample set X, 1 represents a new hob state B-axis vibration signal sample, 2 represents an early wear state B-axis vibration signal sample, 3 represents a normal wear state B-axis vibration signal sample, 4 represents a rapid wear state B-axis vibration signal sample, 5 represents an extended crack state B-axis vibration signal sample, and 6 represents a hob tooth fracture state B-axis vibration signal sample.
3) And extracting time domain characteristic parameters, frequency domain characteristic parameters and Hilbert envelope spectrum frequency domain characteristic parameters of the samples. The time domain characteristic parameters comprise 15 of mean value, root mean square value, variance, covariance, maximum amplitude, minimum amplitude, peak-to-peak value, median of amplitude, root mean square value of amplitude, waveform index, pulse index, kurtosis index, margin index, skewness, peak factor and the like, the frequency domain characteristic parameters and the frequency domain characteristic parameters of the Hilbert envelope spectrum respectively comprise 5 of barycentric frequency, mean square frequency, root mean square frequency, frequency variance, frequency standard deviation and the like, and 25 characteristic parameters in total form a sample initial characteristic vector f0。
Step four, firstly utilizing m samples X in the hob state standard sample set Xi(i 1, 2.. m) constructing a hob-state mutual K-neighbor graph G, wherein m samples in X correspond to m nodes in the graph G; then establishing a similar matrix S and a Laplace matrix L of the mutual K neighbor graph G of the hob states; then, carrying out de-equalization processing on the characteristic parameters, calculating the Laplacian score of each characteristic parameter, and carrying out characteristic selection by taking the Laplacian score as a basis to form a sample characteristic vector f; in particular toThe implementation steps are as follows:
(1) setting a K value, and describing the distance between nodes by a standardized Euclidean distance:
in the formula (d)ijRepresenting a node xiAnd xjDistance between, n denotes the data dimension of the node, xik、xjkRespectively representing the k component, s, of the i and j nodeskRepresenting the standard deviation of the sample components.
Judging node x according to distanceiAnd xjIf the nodes are adjacent to each other, the node x is judged to be adjacent to each otheriAnd xjWith edge connections, then at wij＝dijThe value is taken as the weighting of the edge, otherwise, node xiAnd xjBorderless connection, wijTake 0.
(2) Establishing a similarity matrix S and a Laplace matrix L of the mutual K neighbor graph G of the hob states:
similarity matrix S:
laplace matrix L ═ D-S;
wherein, wijCalled hob state, K, weighted next to the edge of graph G, σ is the width of the thermonuclear, D diag (si) is the diagonal matrix, I (1, 1.., 1)TIs an m x 1 dimensional matrix.
(3) Definition Ps＝(fs1,fs2,fs3,...,fsm)TS characteristic parameter representing a standard sample set of hob states, wherein fstDenotes the s (s 1,2, r) th characteristic parameter of the t (t 1,2, r, m) th sample, and r denotes the sample initial characteristic vector f0In the present embodiment, r is 25; carrying out de-equalization processing on the characteristic parameters to obtain:
calculating Laplace score L of s-th characteristic parameters：
Wherein, Var (P)s) Representing the variance of the s-th characteristic parameter.
And (3) performing ascending order arrangement on the Laplace scores of all the characteristic parameters of the sample, and selecting the characteristic parameters corresponding to the first l Laplace scores to form a sample characteristic vector f.
And step five, according to a newly obtained hob steady-state hobbing stage B-axis vibration signal sample, combining samples and labels in a hob state standard sample set X, constructing a hob state characteristic matrix F by using a sample characteristic vector F, standardizing characteristic parameter values in the F by using a maximum value method, establishing a fuzzy similarity relation matrix R by using a maximum and minimum method, constructing a transfer closure t (R), and finally performing cluster analysis by using a lambda intercept matrix method to realize hob state identification. The specific implementation steps are as follows:
(1) constructing a hob state characteristic matrix F:
wherein m represents the number of samples in a hob state standard sample set X, q represents the number of newly obtained hob steady-state roll-cutting stage B-axis vibration signal samples, l represents the dimension of a sample characteristic vector f, and fijThe jth feature (i 1,2, …, m + q; j 1,2, …, l), c) representing the ith samplekDenotes the sample number, k ═ 1,2, …, m; in this example ck＝1,2,…6。
(2) And (3) normalizing the characteristic parameter values by adopting a maximum value method:
converting the hob state characteristic matrix F into:
(3) establishing a fuzzy similarity relation matrix R by a maximum and minimum method:
(4) constructing a transfer closure t (R) by a self-synthesis flat method, if
(k ═ 0, 1, 2.), then
Then, dynamically decreasing and selecting the lambda value to obtain a lambda intercept matrix t (R) of the transfer closure t (R)λ：
and selecting a proper lambda value, clustering the samples into six types, respectively corresponding to the six types of hob states, and realizing classification and identification of the newly obtained B-axis vibration signal sample at the steady-state hob hobbing stage according to the samples and labels thereof in the hob state standard sample set X, thereby determining the current hob state.
The intelligent monitoring method for the hob state of the numerical control gear hobbing machine has the advantages of small calculated amount, short calculation time, easiness in programming realization and the like, can realize online real-time monitoring of the hob state, is convenient for timely hob replacement and cutter grinding, avoids the occurrence of expansion cracks and hob tooth fracture, prolongs the service life of the hob, and reduces the production cost; the dependence on the professional skills of operators is reduced, and the intelligent process of the numerical control gear hobbing machine is promoted.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (4)
1. An intelligent monitoring method for the hob state of a numerical control gear hobbing machine is characterized by comprising the following steps:
acquiring vibration analog quantity of a B shaft in a hob hobbing processing cycle in real time through a pre-buried vibration acceleration sensor, wherein the B shaft is a main shaft of a numerical control gear hobbing machine; the vibration analog quantity is accessed to a PLC controller by utilizing a machine tool bus and is converted into digital quantity through A/D, so that a B-axis vibration signal is obtained; dividing the roll cutting processing cycle into an idle roll cutting stage, a transition roll cutting stage and a steady-state roll cutting stage;
the idle hobbing stage represents the motion process of the hob before the hob contacts the gear blank;
the transitional hobbing stage represents the motion process of the hob for cutting in and cutting out the gear blank; when cutting, the contact area between the hob and the gear blank is gradually increased; when cutting, the contact area between the hob and the gear blank is gradually reduced;
the steady-state hobbing stage represents the motion process of the hob with the largest contact area with the gear blank and relative stability;
step two, performing data segmentation on the signals according to the peak jump characteristic of the B-axis vibration signals which periodically appears, and segmenting the vibration signals of a hobbing processing cycle into three sections in a time domain, wherein the three sections respectively correspond to an idle hobbing stage, a transition hobbing stage and a steady-state hobbing stage;
thirdly, carrying out a large number of hobbing cutter full life cycle hobbing machining experiments, selecting B-axis vibration signals of corresponding steady-state hobbing stages under various hobbing cutter states, constructing a hobbing cutter state standard sample set X, and carrying out sample labeling; extracting time domain characteristic parameters, frequency domain characteristic parameters and Hilbert envelope spectrum frequency domain characteristic parameters of the sample to form an initial characteristic vector f of the sample0；
Step four, constructing a hob state mutual K neighbor graph G by utilizing all samples in the hob state standard sample set X, and establishing a similarity matrix S and a Laplace matrix L of the graph G; carrying out de-equalization processing on the characteristic parameters; then calculating the Laplace score of each characteristic parameter, and selecting characteristics according to the Laplace score to form a sample characteristic vector f;
step five, according to the newly obtained hob steady-state hobbing stage B-axis vibration signal sample, combining the samples in the hob state standard sample set X and the labels thereof, constructing a hob state characteristic matrix F:
wherein m represents the number of samples in a hob state standard sample set X, q represents the number of B-axis vibration signal samples in a newly obtained hob steady-state hobbing stage, and l represents the dimensionality of a sample characteristic vector f; f. ofijJ-th feature representing the i-th sample, i ═ 1,2, …, m + q; j ═ 1,2, …, l; c. CkDenotes the sample number, k ═ 1,2, …, m;
and (3) standardizing the characteristic parameter values in the F according to a maximum value method, establishing a fuzzy similarity relation matrix R through a maximum and minimum method, constructing a transfer closure t (R), and performing cluster analysis by adopting a lambda intercept matrix method to realize hob state identification.
2. The intelligent monitoring method for the hob state of the numerical control gear hobbing machine according to claim 1, characterized in that: in the first step, the pre-embedded vibration acceleration sensor is a vibration acceleration sensor pre-embedded in a bearing support at the end part of the shaft B in the assembling and manufacturing process of the numerical control gear hobbing machine.
3. The intelligent monitoring method for the hob state of the numerical control gear hobbing machine according to claim 1, characterized in that: in the third step, the state of the hob comprises six types including a new hob, early abrasion, normal abrasion, rapid abrasion, expansion crack, cutter tooth fracture and the like, wherein the new hob refers to a brand-new hob or a hob subjected to sharpening;
in the hob state standard sample set X, the number of samples corresponding to the six types of hob states is equal; the sample labels are respectively: the method comprises the following steps of 1 representing a B-axis vibration signal sample in a new cutter state, 2 representing a B-axis vibration signal sample in an early wear state, 3 representing a B-axis vibration signal sample in a normal wear state, 4 representing a B-axis vibration signal sample in a rapid wear state, 5 representing a B-axis vibration signal sample in a crack propagation state and 6 representing a B-axis vibration signal sample in a cutter tooth fracture state;
the time domain characteristic parameters comprise 15 of mean value, root mean square value, variance, covariance, maximum amplitude, minimum amplitude, peak-to-peak value, median of amplitude, root mean square value of amplitude, waveform index, pulse index, kurtosis index, margin index, skewness, peak value factor and the like, the frequency domain characteristic parameters and the frequency domain characteristic parameters of the Hilbert envelope spectrum respectively comprise 5 of center-of-gravity frequency, mean square frequency, root mean square frequency, frequency variance, frequency standard deviation and the like, and the total number of the characteristic parameters is 25.
4. The intelligent monitoring method for the hob state of the numerical control gear hobbing machine according to claim 1, characterized in that: in the fourth step, the feature selection is to arrange the laplacian scores of all the feature parameters of the sample in an ascending order, and select the feature parameters corresponding to the first l laplacian scores to form a sample feature vector f.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811314647.6A CN109396956B (en) | 2018-11-06 | 2018-11-06 | Intelligent monitoring method for hob state of numerical control gear hobbing machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811314647.6A CN109396956B (en) | 2018-11-06 | 2018-11-06 | Intelligent monitoring method for hob state of numerical control gear hobbing machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109396956A CN109396956A (en) | 2019-03-01 |
| CN109396956B true CN109396956B (en) | 2020-04-07 |
Family
ID=65471965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811314647.6A Active CN109396956B (en) | 2018-11-06 | 2018-11-06 | Intelligent monitoring method for hob state of numerical control gear hobbing machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109396956B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109933940B (en) * | 2019-03-22 | 2023-01-06 | 重庆大学 | Hobbing process parameter optimization method based on hob spindle vibration response model |
| CN113601261B (en) * | 2021-08-10 | 2022-06-14 | 中国科学院合肥物质科学研究院 | Monitoring method of online rapid optimization model for cutter |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ATE421717T1 (en) * | 1999-09-17 | 2009-02-15 | Eta Sa Mft Horlogere Suisse | SHOCKPROOF DEVICE FOR A GENERATOR DRIVEN BY A FLYFLOW MASS |
| CN102689230B (en) * | 2012-05-09 | 2014-04-09 | 天津大学 | Tool wear condition monitoring method based on conditional random field model |
| CN103264317B (en) * | 2013-05-16 | 2015-11-18 | 湖南科技大学 | A kind of appraisal procedure of Milling Process cutter operational reliability |
| CN103894883B (en) * | 2014-04-01 | 2016-08-17 | 西北工业大学 | Cutter distortion measured material and utilize this fixture to carry out cutter distortion On-line Measuring Method |
| CN104537157A (en) * | 2014-12-12 | 2015-04-22 | 深圳信息职业技术学院 | Confidence regression algorithm and device based on KNN (K-Nearest-Neighbor) |
| CN106570275B (en) * | 2016-11-07 | 2019-09-10 | 沈阳工业大学 | A kind of TBM hob abrasion prediction technique based on CAI value |
-
2018
- 2018-11-06 CN CN201811314647.6A patent/CN109396956B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109396956A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059442B (en) | Turning tool changing method based on part surface roughness and power information | |
| CN108490880B (en) | Method for monitoring wear state of cutting tool of numerical control machine tool in real time | |
| CN102621932B (en) | Energy consumption prediction method for use in service process of numerically-controlled machine tool | |
| CN111738578B (en) | Discrete type workshop scheduling method under dynamic environment | |
| CN109262368B (en) | Cutter failure determination method | |
| CN104781740A (en) | Modular system for real-time evaluation and monitoring of machining production-line overall performances calculated from each given workpiece, tool and machine | |
| CN105607579B (en) | A kind of machine tooling intelligent power saving control method and system | |
| CN111475921A (en) | Tool residual life prediction method based on edge calculation and L STM network | |
| CN111113150B (en) | Method for monitoring state of machine tool cutter | |
| CN109396956B (en) | Intelligent monitoring method for hob state of numerical control gear hobbing machine | |
| CN110109431B (en) | Intelligent acquiring system for OEE information of die casting machine | |
| CN113608482A (en) | Intelligent monitoring method, system and management system for precision machining tool | |
| CN116187725B (en) | Forging equipment management system for forging automatic line | |
| CN115755758A (en) | Machine tool machining control method based on neural network model | |
| CN111783544A (en) | Method for building diamond milling head state monitoring system for machining ceramic mobile phone back plate | |
| CN115351601A (en) | Tool wear monitoring method based on transfer learning | |
| CN111159487A (en) | Predictive maintenance intelligent system for automobile engine spindle | |
| CN114536104B (en) | Dynamic prediction method for tool life | |
| CN110647108B (en) | Data-driven numerical control turning element action energy consumption prediction method | |
| CN112526931B (en) | Quality control method for boring process of marine diesel engine body hole system | |
| CN114330491A (en) | Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve | |
| CN112559591A (en) | Outlier detection system and detection method for cold roll manufacturing process | |
| CN116128221B (en) | Digital twin-based dispatching method for remanufacturing production line of aero-hair blade | |
| CN110488775A (en) | Equipment state judgement and yield beat statistical system and method | |
| CN110738423B (en) | Comprehensive efficiency evaluation method for rolling and connecting equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240426 Address after: 317699 No.1 Shengyuan Road, Mechanical and Electrical Industry Functional Zone, Yuhuan City, Wenzhou City, Zhejiang Province Patentee after: ZHEJIANG SHUANGHUAN DRIVELINE Co.,Ltd. Country or region after: China Address before: 400044 No. 174 Sha Jie street, Shapingba District, Chongqing Patentee before: Chongqing University Country or region before: China |