CN111300146A - Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal - Google Patents
Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal Download PDFInfo
- Publication number
- CN111300146A CN111300146A CN201911199533.6A CN201911199533A CN111300146A CN 111300146 A CN111300146 A CN 111300146A CN 201911199533 A CN201911199533 A CN 201911199533A CN 111300146 A CN111300146 A CN 111300146A
- Authority
- CN
- China
- Prior art keywords
- optimal
- wear
- frequency
- prediction
- fitness
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/0957—Detection of tool breakage
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
A numerical control machine tool wear amount on-line prediction method based on spindle current and vibration signals is characterized in that trial operation processing is repeatedly carried out on a numerical control machine tool spindle provided with a sensor by utilizing a plurality of tools of the same type under the same working condition, original processing wear data is measured, according to three wear stages of an initial rapid wear stage, a normal wear stage and a rapid wear stage of the tools, an optimal feature set for training is respectively extracted from the three wear stages, a support vector regression prediction model is trained, and finally the trained model is adopted to carry out on-line real-time prediction on the tool wear amount in the actual processing process; according to the invention, through data obtained by repeated experiments of a plurality of cutters with the same type under the same condition, not only can characteristic parameters related to cutter abrasion in each abrasion stage in an original signal be fully mined, but also the degree of association with the cutter abrasion amount is further enhanced through a post-processing mode, so that the constructed support vector regression prediction model can obtain higher prediction precision and good popularization.
Description
Technical Field
The invention relates to a technology in the field of machining, in particular to a high-precision numerical control machine tool wear loss online prediction method based on spindle current and vibration signals.
Background
Numerically controlled machine tools are an important basic equipment for modern advanced manufacturing techniques, and machine downtime caused by tool failure accounts for approximately 1/5-1/3 of the total machine downtime. For a numerical control machine tool provided with a relatively mature cutter monitoring system, the fault downtime can be reduced by 75%, and the machining efficiency can be improved by 10-60%. The existing cutter state monitoring technology can generally achieve accurate prediction on the type of the cutter abrasion state, but has low prediction accuracy on abrasion loss, poor instantaneity and popularization, and difficult large-scale application to industrial production.
Disclosure of Invention
The invention provides an online prediction method of the tool wear of a numerical control machine tool based on spindle current and vibration signals, aiming at the defects that the prediction model of the existing tool monitoring technology is low in precision and the model established based on single tool experimental data is poor in popularization.
The invention is realized by the following technical scheme:
the invention relates to a numerical control machine tool wear amount online prediction method based on spindle current and vibration signals, which comprises the steps of repeatedly performing trial operation processing on a numerical control machine tool spindle provided with a sensor by utilizing a plurality of tools of the same type under the same working condition and measuring original processing wear data, respectively extracting an optimal feature set for training according to three wear stages of an initial rapid wear stage, a normal wear stage and a rapid wear stage of the tools, training a support vector regression prediction model, and finally performing online real-time tool wear amount prediction in the actual processing process by adopting the trained model.
The original processing wear data comprises a spindle vibration time domain signal measured by an acceleration sensor, a spindle single-phase current time domain signal measured by a current sensor and a corresponding cutter wear amount measured by a microscope.
The extraction comprises the following steps: and according to a wear curve obtained by fitting the tool wear amount and the corresponding feed times, extracting the time domain characteristics of the single-phase current time domain signal of the spindle, and extracting the time domain characteristics, the frequency domain characteristics and the time-frequency domain characteristics of the vibration time domain signal of the spindle.
The optimal feature set is as follows: according to the correlation coefficients of all the characteristics and the wear curve, acquiring the characteristics corresponding to the correlation coefficients which are larger than the threshold value in multiple experiments as effective characteristics; preferably, the valid features are obtained by performing gaussian weighted moving average and normalization processing.
The support vector regression machine prediction model is preferably a support vector regression model based on genetic algorithm parameter optimization.
The training is to select the mean square error of model abrasion loss prediction as population fitness by taking all feed data of part of cutters as a training set and the rest as a test set, and perform selection, crossing and variation operations according to the individual fitness to generate a new population and calculate the current fitness of each individual; and selecting the optimal individual, comparing the optimal individual with the recorded optimal fitness, determining whether to update the optimal parameter and the optimal fitness, and performing iterative training to obtain an optimal prediction model.
Technical effects
The invention integrally solves the technical problems that: the method avoids using a cutting force sensor which is high in price and poor in industrial applicability but can most directly reflect the wear condition of the cutter, and selects and uses a vibration sensor and a current sensor which are good in economy and high in industrial applicability to predict the wear of the cutter. Although the model established based on single tool data in the prior art has high prediction accuracy, due to the complexity of cutting experiments and the interference of various accidental factors, if the tools of the same type are used for repeated experiments under the same experimental conditions, the prediction effect of the model is poor, namely the model established by using the single tool is not suitable for another tool, even under the completely same processing conditions.
Compared with the prior art, the invention provides the data of repeated experiments by using the cutters of the same type, and the related characteristics which repeatedly appear in a plurality of groups of experiments are respectively extracted according to three abrasion stages to be used as the optimal characteristic set of the stage. Compared with a method for selecting characteristics of a single tool data in the whole abrasion stage, the method can greatly improve the generalization of the model on the basis of keeping higher prediction precision. The unexpected technical effects that result from this include:
a large number of characteristic parameters of a signal time domain, a signal frequency domain and a signal time-frequency domain are respectively extracted in three abrasion stages, potential characteristics highly related to abrasion loss in different stages in the signal can be fully mined, the characteristics highly related to the abrasion loss are screened out through calculating a correlation coefficient to serve as an optimal characteristic set, and then post-processing of Gaussian weighted moving average is carried out, so that the correlation degree of the characteristics and the abrasion loss can be further improved, and the accuracy of a final prediction model is improved.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a flowchart of an embodiment of a method for online prediction of tool wear;
FIG. 3 is a schematic diagram of a wear curve of tool wear and feed times fitted to an embodiment;
FIG. 4 is a flowchart of an embodiment tool wear prediction model construction;
FIG. 5 is a schematic diagram of the embodiment of genetic algorithm parameter optimization population fitness change;
FIG. 6 is a schematic error diagram of the sectional prediction model of the tool wear according to the embodiment.
Detailed Description
As shown in fig. 1 and fig. 2, a specific flow of a tool wear amount prediction method according to this embodiment includes the following steps:
step 1, setting cutting parameters as follows: the main shaft rotation speed is 2000RPM, the feed speed is 300mm/min, the cutting depth is 1mm, the cutting width is 4.5mm, three 3-edge flat-head end mills with the diameter of 8mm of the Hitachi Vickers are used for carrying out face milling on 45 steel workpieces under the parameter setting, the length of each feed is 120mm, a Kistler three-axis acceleration sensor is used for collecting main shaft vibration signals, and a current sensor is used for collecting main shaft single-phase current signals.
The sampling frequency of the vibration signal is 20kHz, and the sampling frequency of the current signal is 5 kHz.
Preferably, the machine is stopped and the cutter is unloaded once after each machining period, the wear amount of the rear cutter face of the cutter is measured by a microscope, the corresponding feed times are recorded, and the three cutters respectively cut 290 cutters, 280 cutters and 320 cutters and stop collecting when the rear milling cutter reaches the dull grinding standard.
Step 2, as shown in fig. 3, one of the wear curves is obtained by fitting according to the measured wear amount and the corresponding feed times, and is divided into three wear stages according to the wear amount variation trend: an initial rapid wear phase, a normal wear phase and a rapid wear phase.
And 3, respectively extracting the time domain characteristics of the current signals, the time domain characteristics of the vibration signals, the frequency domain characteristics and the time-frequency domain characteristics.
The time domain features include: mean, variance, standard deviation, root mean square, maximum, peak to peak, rectified mean, form factor, peak factor, kurtosis factor, impulse factor, mean square amplitude, margin factor, skewness index.
The frequency domain features are preferably obtained by discrete fourier transform before extraction.
The frequency domain features include: a center-of-gravity frequency characterizing a center of gravity of a location of the spectrum, a frequency variance characterizing a degree of dispersion of the spectral distribution, and a mean-square frequency characterizing a change in location of a main band of the spectrum, wherein: when the abrasion loss of the cutter is increased, the frequency spectrum structure is changed, so that the center of gravity frequency is changed
Frequency variance
Mean square frequency
Wherein: f represents frequency, w (f) is the amplitude corresponding to the frequency, and N is the sampling frequency.
The time-frequency domain features are extracted by wavelet packet decomposition and empirical mode decomposition, and specifically the method comprises the following steps: firstly, 4-layer wavelet packet decomposition is carried out on each component of the original vibration signal by using a db4 wavelet basis, and then the energy value, the percentage of energy of each frequency band and the time domain characteristics of a reconstructed signal of each frequency band are respectively extracted from 16 frequency bands.
Said energy value
Wherein: eiIs the energy value, x, of the ith sub-bandijJ decomposition coefficients in the ith sub-band after wavelet packet decomposition are obtained; percentage of energy in each frequency band
The empirical mode decomposition in this embodiment obtains the first 8 signal components, and takes the total energy of each component as a characteristic parameter.
And 4, calculating the correlation coefficient of each characteristic obtained in the step 3 and the wear amount corresponding to the feed in the step 1 respectively for the three wear stages, so as to screen out the respective optimal characteristic set of each wear stage.
The optimal feature set is as follows: the set of all features whose correlation coefficient is greater than the threshold and which appeared repeatedly in the above three sets of experiments.
The correlation coefficient, i.e. Pearson's correlation coefficient
Wherein: xi、YiThe ith values representing the characteristic parameter and the wear amount respectively,
respectively representing the mean values of the characteristic vector and the abrasion loss, r is a Pearson correlation coefficient,the value range is [ -1,1 [)]The more extreme values in the interval represent stronger correlation, wherein 1 represents complete positive correlation, -1 represents complete negative correlation, and 0 represents no correlation.
The threshold values for the three wear phases are preferably 0.9, 0.6 and 0.8.
And 5, sequentially carrying out Gaussian weighted moving average and normalization processing on each feature in the optimal feature set to obtain a regular feature set.
The data sliding window size of the moving average of the three wear phases in this embodiment is selected to be 25, 60, 65, respectively.
The normalization processing is as follows: maximum and minimum normalization method for converting raw data into [0,1 ] by linear transformation]Within the interval, the formula is:
wherein: x is the input value, y is the normalized value, xmin、xmaxRespectively representing the minimum and maximum values of the sequence.
And 6, taking the regular feature set as input, the tool wear amount as output, taking the data obtained in the step 1 as a test set and a training set, respectively constructing and training a support vector regression model based on genetic algorithm parameter optimization, and using the trained model for online real-time tool wear amount prediction in the actual machining process.
The test set and the training set refer to: in 890 samples of the three knives collected in step 1, all samples of two knives are selected as training set data, and the sample of the remaining one knife is selected as test set data.
The parameters needing to be optimized in the support vector regression model are penalty coefficients and fault-tolerant interval zones, and the method specifically comprises the following steps:
① given training sample { (x)i,yi),i＝1,…,n|xi∈RNY ∈ R }, it is desirable to fit a function f such that f (x)i) And yiIs as small as possible, setting the maximum deviation to ε in the support vector regression model, only if | f (x)i)-yi|>ε, the error is calculated. This is equivalent to constructing a spacer band of width 2 epsilon centered on f (x), where the sample falls into it, and the prediction is considered to be unbiased, where f (x) < w, x > + b, where w and b are the weight and bias terms, respectively.
② by introducing a penalty parameter C and a slack variable ξ, the support vector regression problem can be transformed into:
converting the constrained optimization problem into an unconstrained problem by introducing a lagrange multiplier, lagrange function:
③ the conditions necessary for the optimal solution to the constraint problem, namely the KKT condition:
the dual problem can be solved by substituting the formula:
to obtain
Therefore, the temperature of the molten metal is controlled,
in this embodiment, the optimization interval is set to C ∈ [0,35 ]],ε∈[0.005,1]。
As shown in fig. 4, a flowchart for building a tool wear prediction model is shown, and the specific steps of the building and training process in this embodiment include:
step 6.1: selecting the mean square error of model abrasion loss prediction as population fitness, setting the number of individuals in a population to be 20, the maximum evolution algebra to be 50 and the optimization interval of two parameters;
step 6.2: initializing a population, calculating the fitness value of each individual, and recording an initial parameter as an optimal parameter and an initial fitness value as an optimal fitness;
step 6.3: according to the fitness of the individual, carrying out selection, crossing and mutation operations to generate a new population and calculate the current fitness of each individual; selecting the optimal individual and comparing the optimal fitness with the recorded optimal fitness to determine whether to update the optimal parameters and the optimal fitness;
step 6.4: outputting the current optimal parameters when the maximum iteration times are reached or the termination condition is met, otherwise returning to the step 6.3;
step 6.5: and constructing an optimal prediction model by taking the obtained optimal parameters as final parameters of the support vector regression model.
The online real-time prediction comprises the following steps: and (3) acquiring a feature set as the input of the support vector regression model according to the post-processing method after feature acquisition, extraction and screening in the steps 1, 3, 4 and 5, and acquiring the output of the feature set in real time, namely the predicted value of the tool wear amount in the current state.
As shown in fig. 4, the variation of the population optimal fitness and the average fitness with the algebra in the normal wear stage in the parameter optimization process of the genetic algorithm in this embodiment is shown in fig. 5, which is an error map of the tool wear amount piecewise optimal prediction model in this embodiment on the whole test set.
The prediction accuracy on the test set in this example is shown in the following table:
| evaluation index | Value of |
| Mean square error | 175.2592μm2 |
| Average relative error | 14.56％ |
| Mean absolute error | 9.3552μm |
| Maximum absolute error | 57.4960μm |
It can be seen that the model constructed by the method still has high prediction accuracy, the average relative error of the whole test set is 14.56%, and the average absolute error is 9.3552 μm. Although the maximum absolute error is as high as 57.4960 μm, the absolute error of the middle part is below 12 μm except for the large error at the beginning and near dull stage.
The invention utilizes two processing signals of spindle vibration and current which are easy to collect, compared with the method that most of the processing signals are divided into a training set and a testing set by using the whole service life experimental data of a single cutter, and the prediction precision on the testing set is used as an evaluation index, the invention emphasizes the generalization of the model, so the experimental data of a plurality of cutters is used as the training set, and the established model is used for predicting and verifying the accuracy of the model on the other cutter, and the prediction result in the embodiment proves the generalization of the modeling method of the invention; compared with the method that the characteristics of the whole process from the new cutter to the dull grinding of the cutter are extracted as a whole, the method provided by the invention can be used for respectively extracting the characteristics according to the three wear stages, can better eliminate the interference of the processing environment and accidental factors under the condition of ensuring higher prediction accuracy, and has good adaptability and popularization for cutter wear prediction under the experimental condition of the same type of cutter under the same working condition.
The foregoing embodiments may be modified in many different ways by those skilled in the art without departing from the spirit and scope of the invention, which is defined by the appended claims and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (7)
1. A numerical control machine tool wear amount on-line prediction method based on spindle current and vibration signals is characterized in that trial run processing is repeatedly carried out on a numerical control machine tool spindle provided with a sensor by utilizing a plurality of tools of the same type under the same working condition, original processing wear data is measured, according to three wear stages of an initial rapid wear stage, a normal wear stage and a rapid wear stage of the tools, an optimal feature set for training is respectively extracted from the wear stages and a support vector regression model is trained, and finally the trained model is adopted to carry out on-line real-time prediction on the tool wear amount in the actual processing process;
the original processing wear data comprise a main shaft vibration time domain signal measured by an acceleration sensor, a main shaft single-phase current time domain signal measured by a current sensor and a corresponding cutter wear amount measured by a microscope;
the extraction comprises the following steps: and according to a wear curve obtained by fitting the tool wear amount and the corresponding feed times, extracting the time domain characteristics of the single-phase current time domain signal of the spindle, and extracting the time domain characteristics, the frequency domain characteristics and the time-frequency domain characteristics of the vibration time domain signal of the spindle.
2. The method for on-line prediction of abrasion loss of numerical control machine tool cutter according to claim 1, characterized in that the plurality of cutters of the same model, in particular three 3-edge flat-end milling cutters with a diameter of 8mm, are used for face milling 45 steel workpieces, the length of each feed is 120mm, a Kistler triaxial acceleration sensor is used for collecting spindle vibration signals, and a current sensor is used for collecting spindle single-phase current signals.
3. The method for on-line prediction of abrasion loss of numerical control machine tool cutter according to claim 1 or 2, characterized in that the optimal feature set is: the correlation coefficient is greater than the threshold value and the set of all the characteristics which repeatedly appear in a plurality of groups of experiments, namely the characteristic corresponding to the correlation coefficient greater than the threshold value is obtained as an effective characteristic according to the correlation coefficients of all the characteristics and the wear curve, and the effective characteristic is obtained through Gaussian weighted moving average and normalization processing;
the correlation coefficient, i.e. Pearson's correlation coefficient
Wherein: xi、YiThe ith values representing the characteristic parameter and the wear amount respectively,
respectively representing the mean value of the characteristic vector and the abrasion loss, wherein r is a Pearson correlation coefficient and has a value range of [ -1,1]The more extreme values in the interval represent stronger correlation, wherein 1 represents complete positive correlation, -1 represents complete negative correlation, and 0 represents no correlation.
4. The method for on-line prediction of the abrasion loss of a numerical control machine tool cutter according to claim 1, wherein the time domain features comprise: the method comprises the following steps: mean, variance, standard deviation, root mean square, maximum, peak-to-peak, rectified mean, form factor, peak factor, kurtosis factor, impulse factor, mean square amplitude, margin factor, skewness index;
the frequency domain features include: characterizing spectral localityA center of gravity frequency of the heart, a frequency variance characterizing a degree of dispersion of the spectral distribution, and a mean square frequency characterizing a change in position of the spectral main band, wherein: when the abrasion loss of the cutter is increased, the frequency spectrum structure is changed, so that the center of gravity frequency is changed
Frequency variance
Mean square frequency
Wherein: f represents frequency, w (f) is amplitude corresponding to the frequency, and N is sampling frequency;
the time-frequency domain features are extracted by wavelet packet decomposition and empirical mode decomposition, and specifically the method comprises the following steps: firstly, 4-layer wavelet packet decomposition is carried out on each component of the original vibration signal by using a db4 wavelet basis, and then the energy value, the percentage of energy of each frequency band and the time domain characteristics of a reconstructed signal of each frequency band are respectively extracted from 16 frequency bands.
5. The method for on-line prediction of the abrasion loss of the numerical control machine tool cutter according to claim 1, characterized in that the training uses part of the characteristic data as a training set, the rest part of the characteristic data as a test set, the mean square error of model abrasion loss prediction is selected as population fitness, and according to the individual fitness, selection, crossing and variation operations are performed to generate a new population and calculate the current fitness of each individual; and selecting the optimal individual, comparing the optimal individual with the recorded optimal fitness, determining whether to update the optimal parameter and the optimal fitness, and performing iterative training to obtain an optimal prediction model.
6. The method for on-line prediction of abrasion loss of numerical control machine tool cutter according to claim 1 or 5, wherein the support vector regression prediction model is a support vector regression model based on genetic algorithm parameter optimization, and the construction and training process comprises the following specific steps:
step 1: selecting the mean square error of model abrasion loss prediction as population fitness, setting the number of individuals in a population to be 20, the maximum evolution algebra to be 50 and the optimization interval of two parameters;
step 2: initializing a population, calculating the fitness value of each individual, and recording an initial parameter as an optimal parameter and an initial fitness value as an optimal fitness;
and step 3: according to the fitness of the individual, carrying out selection, crossing and mutation operations to generate a new population and calculate the current fitness of each individual; selecting the optimal individual and comparing the optimal fitness with the recorded optimal fitness to determine whether to update the optimal parameters and the optimal fitness;
and 4, step 4: outputting the current optimal parameters when the maximum iteration times are reached or the termination condition is met, otherwise returning to the step 3;
and 5: and constructing an optimal prediction model by taking the obtained optimal parameters as final parameters of the support vector regression model.
7. The method for on-line predicting the abrasion loss of the numerical control machine tool cutter according to claim 6, wherein the parameters to be optimized of the support vector regression model based on genetic algorithm parameter optimization are penalty coefficients and fault-tolerant spacing bands, and the specific optimization steps comprise:
① given training sample { (x)i,yi),i＝1,…,n|xi∈RNY ∈ R } fitting function f, let f (x)i) And yiHas a maximum deviation of ε, i.e. when | f (x)i)-yi|>E, the error is calculated, which is equivalent to constructing a spacing band with a width of 2 e, centered on f (x), and when the sample falls into it, the prediction is considered as not biased, f (x) is equal to<w,x>+ b, where w, b are weight and bias terms, respectively;
② by introducing a penalty parameter C and a slack variable ξ, the support vector regression problem can be transformed into:
converting the constrained optimization problem into an unconstrained problem by introducing a lagrange multiplier, lagrange function:
③ the conditions necessary for the optimal solution to the constraint problem, namely the KKT condition:
the dual problem can be solved by substituting the formula:
to obtain
Thus, it is possible to provide
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911199533.6A CN111300146B (en) | 2019-11-29 | 2019-11-29 | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911199533.6A CN111300146B (en) | 2019-11-29 | 2019-11-29 | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111300146A true CN111300146A (en) | 2020-06-19 |
| CN111300146B CN111300146B (en) | 2021-04-02 |
Family
ID=71157932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911199533.6A Active CN111300146B (en) | 2019-11-29 | 2019-11-29 | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111300146B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111716150A (en) * | 2020-06-30 | 2020-09-29 | 大连理工大学 | Evolution learning method for intelligently monitoring cutter state |
| CN111721835A (en) * | 2020-06-28 | 2020-09-29 | 上海理工大学 | Intelligent monitoring method for grinding wheel state of hollow drill |
| CN111975453A (en) * | 2020-07-08 | 2020-11-24 | 温州大学 | Numerical simulation driven machining process cutter state monitoring method |
| CN112008495A (en) * | 2020-07-28 | 2020-12-01 | 成都飞机工业（集团）有限责任公司 | Cutter damage identification method based on vibration monitoring |
| CN112179947A (en) * | 2020-09-27 | 2021-01-05 | 上海飞机制造有限公司 | Cutter wear early warning method based on multi-feature factor statistics |
| CN112372371A (en) * | 2020-10-10 | 2021-02-19 | 上海交通大学 | Method for evaluating abrasion state of numerical control machine tool cutter |
| CN112720071A (en) * | 2021-01-27 | 2021-04-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN112764391A (en) * | 2020-12-29 | 2021-05-07 | 浙江大学 | Dynamic adjustment method for tool fleeing of numerical control gear hobbing machine tool |
| CN112757053A (en) * | 2020-12-25 | 2021-05-07 | 清华大学 | Model fusion tool wear monitoring method and system based on power and vibration signals |
| CN112917242A (en) * | 2021-02-07 | 2021-06-08 | 中国矿业大学 | Cutting method for prolonging service life of cutter |
| CN113618491A (en) * | 2021-08-23 | 2021-11-09 | 浙江工业大学 | Method for establishing broach wear state recognition model |
| CN114161227A (en) * | 2021-12-28 | 2022-03-11 | 福州大学 | Cutter wear loss monitoring method based on simulation feature and signal feature fusion |
| CN114248152A (en) * | 2021-12-31 | 2022-03-29 | 江苏洵谷智能科技有限公司 | Cutter wear state evaluation method based on optimization features and lion group optimization SVM |
| CN114536104A (en) * | 2022-03-25 | 2022-05-27 | 成都飞机工业（集团）有限责任公司 | Dynamic prediction method for tool life |
| CN114888635A (en) * | 2022-04-27 | 2022-08-12 | 哈尔滨理工大学 | Cutter state monitoring method |
| CN115157005A (en) * | 2022-08-12 | 2022-10-11 | 华侨大学 | Cutter wear monitoring method, device, equipment and storage medium based on strain |
| CN115431099A (en) * | 2022-08-17 | 2022-12-06 | 南京工大数控科技有限公司 | Method for calculating and compensating abrasion loss of milling cutter disc in real time based on spindle current |
| CN115563872A (en) * | 2022-10-10 | 2023-01-03 | 中铁十八局集团有限公司 | TBM hob abrasion loss prediction method based on DE-SVR algorithm |
| CN116449770A (en) * | 2023-06-15 | 2023-07-18 | 中科航迈数控软件(深圳)有限公司 | Machining method, device and equipment of numerical control machine tool and computer storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4514797A (en) * | 1982-09-03 | 1985-04-30 | Gte Valeron Corporation | Worn tool detector utilizing normalized vibration signals |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| RU2015114109A (en) * | 2015-04-17 | 2016-11-10 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Нижегородский государственный технический университет им. Р.Е. Алексеева" (НГТУ) | A method for determining the resistance parameters of a cutting tool during processing on CNC machines |
| FR3034693B1 (en) * | 2015-04-13 | 2018-01-12 | Centre Technique Des Industries Mecaniques Et Du Decolletage | METHOD OF MONITORING A MILLING PROCESS |
| CN108581633A (en) * | 2018-04-11 | 2018-09-28 | 温州大学 | A method of based on the more sensor monitoring cutting tool states of genetic algorithm optimization |
| CN108620949A (en) * | 2017-03-24 | 2018-10-09 | 郑芳田 | Cutter abrasion monitoring and prediction technique |
| CN108857577A (en) * | 2018-08-31 | 2018-11-23 | 上海实极机器人自动化有限公司 | Cutting-tool wear state monitoring method and equipment |
| CN109015111A (en) * | 2018-07-06 | 2018-12-18 | 华中科技大学 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
| CN109158953A (en) * | 2018-09-04 | 2019-01-08 | 温州大学激光与光电智能制造研究院 | A kind of cutting-tool wear state on-line monitoring method and system |
| CN109753923A (en) * | 2018-12-29 | 2019-05-14 | 晋西车轴股份有限公司 | Monitoring method, system, equipment and the computer readable storage medium of tool abrasion |
| CN110263474A (en) * | 2019-06-27 | 2019-09-20 | 重庆理工大学 | A kind of cutter life real-time predicting method of numerically-controlled machine tool |
| CN110303380A (en) * | 2019-07-05 | 2019-10-08 | 重庆邮电大学 | A kind of cutting tool for CNC machine method for predicting residual useful life |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
-
2019
- 2019-11-29 CN CN201911199533.6A patent/CN111300146B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4514797A (en) * | 1982-09-03 | 1985-04-30 | Gte Valeron Corporation | Worn tool detector utilizing normalized vibration signals |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| FR3034693B1 (en) * | 2015-04-13 | 2018-01-12 | Centre Technique Des Industries Mecaniques Et Du Decolletage | METHOD OF MONITORING A MILLING PROCESS |
| RU2015114109A (en) * | 2015-04-17 | 2016-11-10 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Нижегородский государственный технический университет им. Р.Е. Алексеева" (НГТУ) | A method for determining the resistance parameters of a cutting tool during processing on CNC machines |
| CN108620949A (en) * | 2017-03-24 | 2018-10-09 | 郑芳田 | Cutter abrasion monitoring and prediction technique |
| CN108581633A (en) * | 2018-04-11 | 2018-09-28 | 温州大学 | A method of based on the more sensor monitoring cutting tool states of genetic algorithm optimization |
| CN109015111A (en) * | 2018-07-06 | 2018-12-18 | 华中科技大学 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
| CN108857577A (en) * | 2018-08-31 | 2018-11-23 | 上海实极机器人自动化有限公司 | Cutting-tool wear state monitoring method and equipment |
| CN109158953A (en) * | 2018-09-04 | 2019-01-08 | 温州大学激光与光电智能制造研究院 | A kind of cutting-tool wear state on-line monitoring method and system |
| CN109753923A (en) * | 2018-12-29 | 2019-05-14 | 晋西车轴股份有限公司 | Monitoring method, system, equipment and the computer readable storage medium of tool abrasion |
| CN110263474A (en) * | 2019-06-27 | 2019-09-20 | 重庆理工大学 | A kind of cutter life real-time predicting method of numerically-controlled machine tool |
| CN110303380A (en) * | 2019-07-05 | 2019-10-08 | 重庆邮电大学 | A kind of cutting tool for CNC machine method for predicting residual useful life |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111721835A (en) * | 2020-06-28 | 2020-09-29 | 上海理工大学 | Intelligent monitoring method for grinding wheel state of hollow drill |
| CN111721835B (en) * | 2020-06-28 | 2023-03-31 | 上海理工大学 | Intelligent monitoring method for grinding wheel state of hollow drill |
| CN111716150A (en) * | 2020-06-30 | 2020-09-29 | 大连理工大学 | Evolution learning method for intelligently monitoring cutter state |
| CN111975453B (en) * | 2020-07-08 | 2022-03-08 | 温州大学 | Numerical simulation driven machining process cutter state monitoring method |
| CN111975453A (en) * | 2020-07-08 | 2020-11-24 | 温州大学 | Numerical simulation driven machining process cutter state monitoring method |
| CN112008495A (en) * | 2020-07-28 | 2020-12-01 | 成都飞机工业（集团）有限责任公司 | Cutter damage identification method based on vibration monitoring |
| CN112179947A (en) * | 2020-09-27 | 2021-01-05 | 上海飞机制造有限公司 | Cutter wear early warning method based on multi-feature factor statistics |
| CN112179947B (en) * | 2020-09-27 | 2023-11-17 | 上海飞机制造有限公司 | Cutter abrasion early warning method based on multi-feature factor statistics |
| CN112372371A (en) * | 2020-10-10 | 2021-02-19 | 上海交通大学 | Method for evaluating abrasion state of numerical control machine tool cutter |
| CN112757053A (en) * | 2020-12-25 | 2021-05-07 | 清华大学 | Model fusion tool wear monitoring method and system based on power and vibration signals |
| CN112764391A (en) * | 2020-12-29 | 2021-05-07 | 浙江大学 | Dynamic adjustment method for tool fleeing of numerical control gear hobbing machine tool |
| CN112764391B (en) * | 2020-12-29 | 2022-04-26 | 浙江大学 | Dynamic adjustment method for tool fleeing of numerical control gear hobbing machine tool |
| CN112720071A (en) * | 2021-01-27 | 2021-04-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN112720071B (en) * | 2021-01-27 | 2021-11-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN112917242A (en) * | 2021-02-07 | 2021-06-08 | 中国矿业大学 | Cutting method for prolonging service life of cutter |
| CN113618491A (en) * | 2021-08-23 | 2021-11-09 | 浙江工业大学 | Method for establishing broach wear state recognition model |
| CN114161227A (en) * | 2021-12-28 | 2022-03-11 | 福州大学 | Cutter wear loss monitoring method based on simulation feature and signal feature fusion |
| CN114161227B (en) * | 2021-12-28 | 2024-05-03 | 福州大学 | Cutter abrasion loss monitoring method based on simulation feature and signal feature fusion |
| CN114248152A (en) * | 2021-12-31 | 2022-03-29 | 江苏洵谷智能科技有限公司 | Cutter wear state evaluation method based on optimization features and lion group optimization SVM |
| CN114248152B (en) * | 2021-12-31 | 2024-05-10 | 江苏洵谷智能科技有限公司 | Cutter abrasion state evaluation method based on optimization features and lion group optimization SVM |
| CN114536104A (en) * | 2022-03-25 | 2022-05-27 | 成都飞机工业（集团）有限责任公司 | Dynamic prediction method for tool life |
| CN114888635B (en) * | 2022-04-27 | 2023-07-25 | 哈尔滨理工大学 | Cutter state monitoring method |
| CN114888635A (en) * | 2022-04-27 | 2022-08-12 | 哈尔滨理工大学 | Cutter state monitoring method |
| CN115157005B (en) * | 2022-08-12 | 2023-12-05 | 华侨大学 | Method, device, equipment and storage medium for monitoring tool wear based on strain |
| CN115157005A (en) * | 2022-08-12 | 2022-10-11 | 华侨大学 | Cutter wear monitoring method, device, equipment and storage medium based on strain |
| CN115431099A (en) * | 2022-08-17 | 2022-12-06 | 南京工大数控科技有限公司 | Method for calculating and compensating abrasion loss of milling cutter disc in real time based on spindle current |
| CN115563872A (en) * | 2022-10-10 | 2023-01-03 | 中铁十八局集团有限公司 | TBM hob abrasion loss prediction method based on DE-SVR algorithm |
| CN115563872B (en) * | 2022-10-10 | 2024-04-12 | 中铁十八局集团有限公司 | TBM hob abrasion loss prediction method based on DE-SVR algorithm |
| CN116449770A (en) * | 2023-06-15 | 2023-07-18 | 中科航迈数控软件(深圳)有限公司 | Machining method, device and equipment of numerical control machine tool and computer storage medium |
| CN116449770B (en) * | 2023-06-15 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Machining method, device and equipment of numerical control machine tool and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111300146B (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111300146B (en) | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal | |
| CN110303380B (en) | Method for predicting residual life of cutter of numerical control machine tool | |
| CN104537415B (en) | A kind of non-linear process industry failure predication and recognition methodss based on compressed sensing and DROS ELM | |
| CN104723171A (en) | Cutter wear monitoring method based on current and acoustic emission compound signals | |
| CN111475921A (en) | Tool residual life prediction method based on edge calculation and L STM network | |
| CN101870076B (en) | Method for predicting service life of guide pair of numerical control machine on basis of performance degradation model | |
| CN102848266B (en) | Machine tool spindle accuracy prediction method | |
| CN103264317B (en) | A kind of appraisal procedure of Milling Process cutter operational reliability | |
| CN109318055A (en) | A kind of milling cutter state of wear feature extraction Multipurpose Optimal Method | |
| CN113126564B (en) | Digital twin driven numerical control milling cutter abrasion on-line monitoring method | |
| CN116070527B (en) | Milling cutter residual life prediction method based on degradation model | |
| CN112668105B (en) | Helicopter transmission shaft abnormity judgment method based on SAE and Mahalanobis distance | |
| CN112372371B (en) | Method for evaluating abrasion state of numerical control machine tool cutter | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN103839106A (en) | Ball grinding mill load detecting method for optimizing BP neural network based on genetic algorithm | |
| CN104708497A (en) | Tool wear monitoring system based on current and sound emission composite signals | |
| CN113752089A (en) | Cutter state monitoring method based on singularity Leersian index | |
| CN111721835A (en) | Intelligent monitoring method for grinding wheel state of hollow drill | |
| CN204525045U (en) | A kind of Tool Wear Monitoring system based on electric current and sound emission composite signal | |
| CN114749996A (en) | Tool residual life prediction method based on deep learning and time sequence regression model | |
| CN113485244A (en) | Numerical control machine tool control system and method based on cutter wear prediction | |
| CN114326593B (en) | Cutter life prediction system and method | |
| Jeet et al. | Multi-parametric optimization during drilling of aerospace alloy (UNS A97068) using hybrid RSM-GRA, GA and SA | |
| Wang et al. | Surface roughness prediction of large shaft grinding via attentional CNN-LSTM fusing multiple process signals | |
| Xie et al. | A generic evolutionary ensemble learning framework for surface roughness prediction in manufacturing |
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 |