CN112475904A - Numerical control milling and boring machine machining precision prediction method based on thermal analysis - Google Patents
Numerical control milling and boring machine machining precision prediction method based on thermal analysis Download PDFInfo
- Publication number
- CN112475904A CN112475904A CN202011265306.1A CN202011265306A CN112475904A CN 112475904 A CN112475904 A CN 112475904A CN 202011265306 A CN202011265306 A CN 202011265306A CN 112475904 A CN112475904 A CN 112475904A
- Authority
- CN
- China
- Prior art keywords
- data
- numerical control
- data set
- value
- training
- 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
- B23P—METAL-WORKING NOT OTHERWISE PROVIDED FOR; COMBINED OPERATIONS; UNIVERSAL MACHINE TOOLS
- B23P23/00—Machines or arrangements of machines for performing specified combinations of different metal-working operations not covered by a single other subclass
- B23P23/02—Machine tools for performing different machining operations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Automatic Control Of Machine Tools (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to the field of precision machining control of numerical control machines, in particular to a method for predicting machining precision of a numerical control milling and boring machine based on thermal analysis. The method comprises the following steps: s1, acquiring characteristic quantity in real time in the processing process to obtain a thermal characteristic data set; s2, respectively calculating the heat value of a rolling bearing of the machine tool, the heat value of a ball screw, the heat value of a motor and the heat value of a hydrostatic guide rail oil film according to the thermal characteristic feature data set to obtain a heat source attribute data set; s3, clustering the heat source attribute data set by adopting a rapid search and density peak searching algorithm; s4, training the data set by adopting an extension neural network algorithm, S5, continuously acquiring the thermal characteristic attribute value of the numerical control milling and boring machine, and calculating to obtain a heat source attribute data set; s6, acquiring state data of the influence of heat generated by the numerical control milling and boring machine on the machining precision in the current state by adopting the trained extension neural network algorithm; and S7, estimating the machining precision according to the state data of the whole machining process.
Description
Technical Field
The invention relates to the field of precision machining control of numerical control machines, in particular to a method for predicting machining precision of a numerical control milling and boring machine based on thermal analysis.
Background
The numerical control machine tool is a high-end precision machining device, well solves the problem of machining of complex, precise, small-batch and various parts, is a flexible and high-efficiency automatic machine tool, represents the development direction of modern machine tool control technology, and is a typical mechanical and electrical integration product. The numerical control machine tool is a bright bead on the crown of the modern mechanical processing industry, and advanced enterprises of Japan and Germany firmly occupy the market in the field of high-end precision machine tools. The machining precision of the machine tool is an important technical index for measuring the level of the numerical control machine tool. Research shows that in the machining process of the machine tool, the error caused by the thermal deformation of the tool bit accounts for more than 25% of the overall machining error of the machine tool, so how to control the error caused by the thermal deformation is one of the key factors for improving the overall machining precision of the machine tool.
The premise of controlling the machining error caused by the thermal deformation of the machine tool is to analyze the heat generated in the machining process of the machine tool, quantitatively analyze and calculate the influence of the heat generated on the machining precision of the lathe. However, in the prior art, no method for effectively analyzing the heat generated by the machine tool and the influence of the heat on the machining precision of the lathe exists. Particularly in a boring and milling machine tool with high heat in the machining process, the problem is mainly solved by improving the cooling efficiency of a cooling system in the prior art, and the machining precision is not predicted and controlled based on thermal analysis.
Disclosure of Invention
In order to solve the problem that the influence of thermal deformation on the machining precision of a boring and milling machine cannot be effectively analyzed in the prior art, the invention provides a numerical control boring and milling machine machining precision prediction method based on thermal analysis.
The invention is realized by adopting the following technical scheme:
a numerical control milling and boring machine machining precision prediction method based on thermal analysis comprises the following steps:
s1, acquiring characteristic quantities used for calculating the thermal characteristic values of the numerical control milling and boring machine in real time in the machining process to obtain a thermal characteristic data set;
s2, respectively calculating the heat production value Q of the rolling bearing of the machine tool according to the thermal characteristic feature data set1Ball screw heat value Q2Motor heat value phi and hydrostatic guideway oil film heat value QNObtaining a heat source attribute data set;
wherein, the heat value of the rolling bearing is calculated by adopting the following formula:
Q1＝1.047·M1·n1
in the formula: n is1For bearing rotational speed, M1Friction torque of a rolling bearing;
the heat value of the ball screw is calculated by adopting the following formula:
Q2＝1.2π·M2·n2
in the formula: n is2For ball screw speed, M2The friction torque of the screw nut;
the heat value of the motor is calculated by adopting the following formula:
in the formula: mm is the output torque of the driving motor, n3The rotating speed of the driving motor;
the calculation formula of the oil film calorific value of the hydrostatic guideway is as follows:
QN＝μAv/h
in the formula: mu is the dynamic viscosity of the oil, A is the bearing area of the sealing belt part, and mu v/h is equal to the shear stress of the sealing belt part;
s3, clustering the heat source attribute data set by adopting a rapid search and density peak searching algorithm, determining three clustering centers according to a decision diagram, and respectively defining three categories as a qualified state (eq), a metastable state (he) and an error state (ue) according to requirements;
s4, training the clustered attribute data set by using an extension neural network algorithm until reaching a specified training error rate, and finishing a training process;
s5, continuously acquiring the thermal characteristic attribute values of the numerical control milling and boring machine, and calculating to obtain a heat source attribute data set;
s6, identifying the heat source attribute data set acquired in real time by adopting an extension neural network algorithm after training according to the distance between the data points and the categories in the heat source data set, and acquiring state data of the influence of heat generation of the numerical control boring and milling machine on the processing precision in the current state;
and S7, counting the sum of the state data in the machining process and the sum of the state data, and estimating the machining precision by adopting the following error accumulation formula:
wherein N is the sum of the sampling and recognizing state numbers in the workpiece processing process, and N iseqIs the sum of the number of states for which the state data is qualified in the sampling and identification process, NueThe method is characterized in that the method is the sum of the number of states of which the state data are errors in the sampling and identifying process, and k is an influence coefficient of thermal deformation estimated through historical data on the precision in the machine tool boring and washing machining process and is determined according to an empirical value.
Further, in step S1, the feature quantities of the thermal characteristic value include: bearing speed n1Antifriction bearing friction torque M1Rotational speed n of ball screw2Friction torque M of lead screw nut2(ii) a Output torque Mm of driving motor and rotation speed n of driving motor3The dynamic viscosity mu of the oil and the bearing area A of the sealing belt part; the sampling frequency for real-time collection of characteristic quantities is 5-8 Hz.
Further, in step S4, the training process of the extended neural network algorithm is as follows:
defining a heat source attribute data set as
NdFor the total number of data points, the ith data point can be written as
The class representing the ith data point is p, the data point has n attributes, and the training phase comprises the following steps:
(1) determining the classical domain of each heat generation on the precision influence state category as an initial weight according to the following formula
Wherein k is 1 … Nc，NcThe total number of categories;
(2) calculating initial class center for each heat production on precision-affecting state class
(3) Reading a data point in the ith thermal signature dataset and the class p to which the data point belongs
(4) Calculating data points according to the formula of calculation of extension distance in the theory of extension
Distance from the kth class
(5) Finding data points
The category o with the smallest distance to the kth category is such that the following holds, if o ═ p, operation (7) is performed, otherwise operation (6) is performed
EDio＝min{EDik}；
(6) Updating the pth category center and the pth category center with the following formula
Updating the pth class weight and the pth class weight using the following formula
Wherein, eta is the learning rate, and the typical value eta is 0.001;
(7) repeating the steps 3-6, finishing a training period when all the data are trained, inputting the first data again and performing training in the next period;
(8) when the target error rate is reached, ending the training process of the extension neural network recognition algorithm;
further, the target error rate is calculated by the formula:
where E is the target error rate, NMFor error data of all training periods, NPAll data for all training periods.
Further, the target error rate value is E ≦ 1x10-7。
Further, in step S6, the identification process includes the following steps:
(1) reading the final weight value of the training stage;
(2) using the formula Zk＝{zk1,zk2,…,zkn}，
Calculating an initial category center;
(3) reading data points collected in real time
Xt＝{xt1,xt2,...,xtn}，
Using the formula
Calculating the distance between the acquired data points and each category;
(4) if it satisfies
The data point belongs to the category o;
(5) and sequentially finishing the identification of all the collected data points, and determining the state data of the influence of the heat generation of the numerical control milling and boring machine on the machining precision under the current state.
The numerical control milling and boring machine machining precision prediction method based on thermal analysis has the following beneficial effects:
when the heat production quantity of the boring and milling machine in the processing process is analyzed, in order to facilitate the quantitative processing of data, the heat of four heat production units, namely the heat production value of a rolling bearing, the heat production value of a ball screw, the heat production value of a motor and the heat production value of a hydrostatic guideway oil film, is selected with side emphasis, so that a heat source attribute data set used for thermal analysis is formed, the prediction of a final result is not influenced, and the difficulty of data acquisition and processing is greatly reduced.
The invention also adopts a rapid searching and searching density peak value algorithm to cluster the heat source attribute data set, thereby accurately obtaining the clustering center of the data set and facilitating the subsequent training and identification of the data set by adopting a neural recognition network algorithm; based on the recognition result, the analysis result is quantified by utilizing the idea of error accumulation to obtain the final evaluation of the influence of the analysis result on the machining precision, the evaluation result has extremely high reference value and higher consistency with the influence of the numerical control boring thermal deformation on the actual workpiece machining precision, and the evaluation result can be used as a good machining precision prediction index.
Drawings
Fig. 1 is a processing procedure sequence diagram of the method for predicting the machining accuracy of the numerical control boring and milling machine based on thermal analysis in example 1.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, the present embodiment provides a method for predicting machining accuracy of a numerical control boring and milling machine based on thermal analysis, which includes the following steps:
first, data acquisition
And collecting characteristic quantities used for calculating the thermal characteristic numerical values of the numerical control milling and boring machine in real time to obtain a thermal characteristic data set.
The characteristic quantities of the thermal characteristic values include: bearing speed n1, rolling bearing friction torque M1, ball screw speed n2 and friction torque M2 of a screw nut; the output torque Mm of the driving motor, the rotating speed n3 of the driving motor, the dynamic viscosity mu of the oil liquid and the bearing area A of the sealing belt part; the sampling frequency for collecting the characteristic quantity in real time is 5 Hz.
Respectively calculating the heat value Q of the rolling bearing of the machine tool according to the thermal characteristic feature data set1Ball screw heat value Q2Motor heat value phi and hydrostatic guideway oil film heat value QNObtaining a heat source attribute data set;
wherein, the heat value of the rolling bearing is calculated by adopting the following formula:
Q1＝1.047·M1·n1
in the formula: n is1For bearing rotational speed, M1Friction torque of a rolling bearing;
the heat value of the ball screw is calculated by adopting the following formula:
Q2＝1.2π·M2·n2
in the formula: n is2For ball screw speed, M2The friction torque of the screw nut;
the heat value of the motor is calculated by adopting the following formula:
in the formula: mm is the output torque of the driving motor, n3The rotating speed of the driving motor;
the calculation formula of the oil film calorific value of the hydrostatic guideway is as follows:
QN＝μAv/h
in the formula: mu is the dynamic viscosity of the oil, A is the bearing area of the sealing belt part, and mu v/h is equal to the shear stress of the sealing belt part;
second, algorithm training
Based on the clustered data set, the training process of the extensible neural network algorithm is as follows:
defining a heat source attribute data set as
NdFor the total number of data points, the ith data point can be written as
The class representing the ith data point is p, the data point has n attributes, and the training phase comprises the following steps:
(1) determining the classical domain of each heat generation on the precision influence state category as an initial weight according to the following formula
Wherein k is 1 … Nc，NcThe total number of categories;
(2) calculating initial class center for each heat production on precision-affecting state class
(3) Reading a data point in the ith thermal signature dataset and the class p to which the data point belongs
(4) Calculating data points according to the formula of calculation of extension distance in the theory of extension
Distance from the kth class
(5) Finding data points
The category o with the smallest distance to the kth category is such that the following holds, if o ═ p, operation (7) is performed, otherwise operation (6) is performed
EDio＝min{EDik}；
(6) Updating the pth category center and the pth category center with the following formula
Updating the pth class weight and the pth class weight using the following formula
Wherein, eta is the learning rate, and the typical value eta is 0.001;
(7) repeating the steps 3-6, finishing a training period when all the data are trained, inputting the first data again and performing training in the next period;
(8) and when the target error rate is reached, ending the training process of the extension neural network recognition algorithm.
The target error rate is calculated by the formula:
where E is the target error rate, NMFor error data of all training periods, NPAll data for all training periods.
The target error rate is equal to or less than 1x10-7。
Third, algorithm identification
Acquiring a thermal characteristic attribute value of the numerical control boring and milling machine in real time, and calculating to obtain a heat source attribute data set;
identifying a heat source attribute data set acquired in real time by adopting an extension neural network algorithm after training is completed according to the distance between a data point in a newly acquired heat source data set and a category, and acquiring state data of the influence of heat generation of the numerical control boring and milling machine on the processing precision in the current state;
the steps of the identification phase are as follows:
(1) reading the final weight value of the training stage;
(2) using the formula Zk＝{zk1,zk2,…,zkn}，
Calculating an initial category center;
(3) reading data points collected in real time
Xt＝{xt1,xt2,...,xtn}，
Using the formula
Calculating the distance between the acquired data points and each category;
(4) if it satisfies
The data point belongs to the category o;
(5) and sequentially finishing the identification of all the collected data points, and determining the state data of the influence of the heat generation of the numerical control milling and boring machine on the machining precision under the current state.
Fourthly, prediction of machining precision
Counting the sum of the state data and the sum of all the state data in the machining process, and estimating the machining precision by adopting the following error accumulation formula:
wherein N is the sum of the sampling and recognizing state numbers in the workpiece processing process, and N iseqIs the sum of the number of states for which the state data is qualified in the sampling and identification process, NueThe method is characterized in that the method is the sum of the number of states of which the state data are errors in the sampling and identifying process, and k is an influence coefficient of thermal deformation estimated through historical data on the precision in the machine tool boring and washing machining process and is determined according to an empirical value.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A numerical control milling and boring machine machining precision prediction method based on thermal analysis is characterized by comprising the following steps:
s1, acquiring characteristic quantities used for calculating the thermal characteristic values of the numerical control milling and boring machine in real time in the machining process to obtain a thermal characteristic data set;
s2, respectively calculating the heat production value Q of the rolling bearing of the machine tool according to the thermal characteristic feature data set1Ball screw heat value Q2Motor heat value phi and hydrostatic guideway oil film heat value QN；
Wherein, the heat value of the rolling bearing is calculated by adopting the following formula:
Q1＝1.047·M1·n1
in the formula: n is1For bearing rotational speed, M1Friction torque of a rolling bearing;
the heat value of the ball screw is calculated by adopting the following formula:
Q2＝1.2π·M2·n2
in the formula: n is2For ball screw speed, M2The friction torque of the screw nut;
the heat value of the motor is calculated by adopting the following formula:
in the formula: mm is the output torque of the driving motor, n3The rotating speed of the driving motor;
the calculation formula of the oil film calorific value of the hydrostatic guideway is as follows:
QN＝μAv/h
in the formula: mu is the dynamic viscosity of the oil, A is the bearing area of the sealing belt part, and mu v/h is equal to the shear stress of the sealing belt part;
s3, clustering the heat source attribute data set by adopting a rapid search and density peak searching algorithm, determining three clustering centers according to a decision diagram, and respectively defining three categories as a qualified state (eq), a metastable state (he) and an error state (ue) according to requirements;
s4, training the clustered attribute data set by using an extension neural network algorithm until reaching a specified training error rate, and finishing a training process;
s5, continuously acquiring the thermal characteristic attribute values of the numerical control milling and boring machine, and calculating to obtain a heat source attribute data set;
s6, identifying the heat source attribute data set acquired in real time by adopting an extension neural network algorithm after training according to the distance between the data points and the categories in the heat source data set, and acquiring state data of the influence of heat generation of the numerical control boring and milling machine on the processing precision in the current state;
and S7, counting the sum of the state data in the machining process and the sum of the state data, and estimating the machining precision by adopting the following error accumulation formula:
wherein N is the sum of the sampling and recognizing state numbers in the workpiece processing process, and N iseqIs the sum of the number of states for which the state data is qualified in the sampling and identification process, NueThe method is characterized in that the method is the sum of the number of states of which the state data are errors in the sampling and identifying process, and k is an influence coefficient of thermal deformation estimated through historical data on the precision in the machine tool boring and washing machining process and is determined according to an empirical value.
2. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 1, wherein: in step 1, the characteristic quantities of the thermal characteristic value include: bearing speed n1Antifriction bearing friction torque M1Rotational speed n of ball screw2Friction torque M of lead screw nut2(ii) a Output torque Mm of driving motor and rotation speed n of driving motor3The dynamic viscosity mu of the oil and the bearing area A of the seal belt portion.
3. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 1, wherein: in step S4, the training process of the extended neural network algorithm is as follows:
defining a heat source attribute data set as
NdFor the total number of data points, the ith data point can be written as
The class representing the ith data point is p, the data point has n attributes, and the training phase comprises the following steps:
(1) determining the classical domain of each heat generation on the precision influence state category as an initial weight according to the following formula
Wherein k is 1 … Nc，NcThe total number of categories;
(2) calculating initial class center for each heat production on precision-affecting state class
Zk＝{zk1,zk2,…,zkn}，
(3) Reading a data point in the ith thermal signature dataset and the class p to which the data point belongs
(4) Calculating data points according to the formula of calculation of extension distance in the theory of extension
Distance from the kth class
(5) Finding data points
The category o with the smallest distance to the kth category is such that the following holds, if o ═ p, operation (7) is performed, otherwise operation (6) is performed
EDio＝min{EDik}；
(6) Updating the pth category center and the pth category center with the following formula
Updating the pth class weight and the pth class weight using the following formula
Wherein, eta is the learning rate, and the typical value eta is 0.001;
(7) repeating the steps 3-6, finishing a training period when all the data are trained, inputting the first data again and performing training in the next period;
(8) and when the target error rate is reached, ending the training process of the extension neural network recognition algorithm.
4. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 3, wherein: the calculation formula of the target error rate is as follows:
where E is the target error rate, NMFor error data of all training periods, NPAll data for all training periods.
5. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 4, wherein: the target error rate value is E less than or equal to 1x10-7。
6. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 1, wherein: in step S6, the identification process includes the following steps:
(1) reading the final weight value of the training stage;
(2) using the formula Zk＝{zk1,zk2,…,zkn}，
Calculating an initial category center;
(3) reading data points collected in real time
Xt＝{xt1,xt2,…,xtn}，
Using the formula
Calculating the distance between the acquired data points and each category;
(4) if it satisfies
The data point belongs to the category o;
(5) and sequentially finishing the identification of all the collected data points, and determining the state data of the influence of the heat generation of the numerical control milling and boring machine on the machining precision under the current state.
7. The method for predicting the machining accuracy of the numerical control milling and boring machine based on the thermal analysis as claimed in claim 1, wherein: and in the step S1, the sampling frequency of the real-time collected characteristic quantity is 5-8 Hz.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011265306.1A CN112475904B (en) | 2020-11-12 | 2020-11-12 | Numerical control milling and boring machine machining precision prediction method based on thermal analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011265306.1A CN112475904B (en) | 2020-11-12 | 2020-11-12 | Numerical control milling and boring machine machining precision prediction method based on thermal analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112475904A true CN112475904A (en) | 2021-03-12 |
| CN112475904B CN112475904B (en) | 2021-09-28 |
Family
ID=74929978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011265306.1A Active CN112475904B (en) | 2020-11-12 | 2020-11-12 | Numerical control milling and boring machine machining precision prediction method based on thermal analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112475904B (en) |
Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446994A (en) * | 2008-12-18 | 2009-06-03 | 浙江大学 | Modeling method of thermal error least squares support vector machine of numerically-controlled machine tool |
| CN101620431A (en) * | 2009-06-22 | 2010-01-06 | 江俊逢 | Digital control method and system for carrying out real-time compensation for thermal deformation errors |
| CN102479261A (en) * | 2010-11-23 | 2012-05-30 | 大连创达技术交易市场有限公司 | Novel least square support vector machine modeling method for thermal error of numerical control machine |
| CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
| CN103926874A (en) * | 2013-12-03 | 2014-07-16 | 江苏齐航数控机床有限责任公司 | Selection optimization method of numerically-controlled machine tool thermal error compensation modeling temperature measuring point combination |
| CN103984287A (en) * | 2014-03-12 | 2014-08-13 | 江苏齐航数控机床有限责任公司 | Numerically-controlled machine tool thermal error compensation grey neural network modeling method |
| CN104200019A (en) * | 2014-08-27 | 2014-12-10 | 电子科技大学 | Method for simulating thermal characteristic numerical value of heavy numerical control floor type boring and milling machine |
| CN104597842A (en) * | 2015-02-02 | 2015-05-06 | 武汉理工大学 | BP neutral network heavy machine tool thermal error modeling method optimized through genetic algorithm |
| DE102017011290A1 (en) * | 2016-12-14 | 2018-06-14 | Fanuc Corporation | Machine learning apparatus, CNC apparatus and machine learning method for detecting a sign of occurrence of chatter in the tool of a machine tool |
| CN108363870A (en) * | 2018-02-11 | 2018-08-03 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling method based on deep learning |
| US10112247B2 (en) * | 2015-09-29 | 2018-10-30 | Fanuc Corporation | Wire electric discharge machine having movable axis abnormal load warning function |
| CN109146209A (en) * | 2018-11-02 | 2019-01-04 | 清华大学 | Machine tool spindle thermal error prediction technique based on wavelet neural networks of genetic algorithm |
| DE102018115413A1 (en) * | 2017-07-04 | 2019-01-10 | Fanuc Corporation | DEVICE FOR COMPENSATING THERMAL SHIFT |
| DE102018005652A1 (en) * | 2017-07-25 | 2019-01-31 | Fanuc Corporation | INFORMATION PROCESSING DEVICE |
| CN109606364A (en) * | 2018-11-19 | 2019-04-12 | 江苏大学 | A kind of variable speed lower leaf formula self study extension neural network lane holding control method of intelligent automobile |
| CN109709895A (en) * | 2019-01-22 | 2019-05-03 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling training method based on image threshold setting |
| CN109739181A (en) * | 2019-01-22 | 2019-05-10 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling detection method based on detection neural network |
| CN109800537A (en) * | 2019-02-20 | 2019-05-24 | 大连理工大学 | A kind of machine tool thermal error model reliability degree calculation method based on deep neural network and Monte Carlo method |
| CN110039373A (en) * | 2019-04-04 | 2019-07-23 | 华中科技大学 | A kind of main shaft of numerical control machine tool thermal deformation prediction technique and system |
| CN110543140A (en) * | 2019-07-26 | 2019-12-06 | 四川大学 | time characteristic-based numerical control machine tool spindle system thermal key point selection modeling method |
| CN110929758A (en) * | 2019-10-24 | 2020-03-27 | 河海大学 | Complex data-oriented clustering algorithm for rapidly searching and finding density peak |
| CN111259498A (en) * | 2020-01-14 | 2020-06-09 | 重庆大学 | Axle system thermal error modeling method and thermal error compensation system based on LSTM neural network |
| CN111414977A (en) * | 2020-03-09 | 2020-07-14 | 西南交通大学 | Weighted integration temperature sensitive point combination selection method for machine tool spindle thermal error modeling |
| CN111459094A (en) * | 2020-03-09 | 2020-07-28 | 西南交通大学 | Regional selection method for temperature sensitive point combination in machine tool spindle thermal error modeling |
| CN111596612A (en) * | 2020-05-11 | 2020-08-28 | 上海交通大学 | Numerical control machine tool thermal error compensation method and system based on workpiece dimension data |
| EP3715989A1 (en) * | 2019-03-29 | 2020-09-30 | Siemens Aktiengesellschaft | Method and device for monitoring a milling process |
| CN111914930A (en) * | 2020-07-30 | 2020-11-10 | 上海工程技术大学 | Density peak value clustering method based on self-adaptive micro-cluster fusion |
-
2020
- 2020-11-12 CN CN202011265306.1A patent/CN112475904B/en active Active
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446994A (en) * | 2008-12-18 | 2009-06-03 | 浙江大学 | Modeling method of thermal error least squares support vector machine of numerically-controlled machine tool |
| CN101620431A (en) * | 2009-06-22 | 2010-01-06 | 江俊逢 | Digital control method and system for carrying out real-time compensation for thermal deformation errors |
| CN102479261A (en) * | 2010-11-23 | 2012-05-30 | 大连创达技术交易市场有限公司 | Novel least square support vector machine modeling method for thermal error of numerical control machine |
| CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
| CN103926874A (en) * | 2013-12-03 | 2014-07-16 | 江苏齐航数控机床有限责任公司 | Selection optimization method of numerically-controlled machine tool thermal error compensation modeling temperature measuring point combination |
| CN103984287A (en) * | 2014-03-12 | 2014-08-13 | 江苏齐航数控机床有限责任公司 | Numerically-controlled machine tool thermal error compensation grey neural network modeling method |
| CN104200019A (en) * | 2014-08-27 | 2014-12-10 | 电子科技大学 | Method for simulating thermal characteristic numerical value of heavy numerical control floor type boring and milling machine |
| CN104597842A (en) * | 2015-02-02 | 2015-05-06 | 武汉理工大学 | BP neutral network heavy machine tool thermal error modeling method optimized through genetic algorithm |
| US10112247B2 (en) * | 2015-09-29 | 2018-10-30 | Fanuc Corporation | Wire electric discharge machine having movable axis abnormal load warning function |
| DE102017011290A1 (en) * | 2016-12-14 | 2018-06-14 | Fanuc Corporation | Machine learning apparatus, CNC apparatus and machine learning method for detecting a sign of occurrence of chatter in the tool of a machine tool |
| DE102018115413A1 (en) * | 2017-07-04 | 2019-01-10 | Fanuc Corporation | DEVICE FOR COMPENSATING THERMAL SHIFT |
| DE102018005652A1 (en) * | 2017-07-25 | 2019-01-31 | Fanuc Corporation | INFORMATION PROCESSING DEVICE |
| CN108363870A (en) * | 2018-02-11 | 2018-08-03 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling method based on deep learning |
| CN109146209A (en) * | 2018-11-02 | 2019-01-04 | 清华大学 | Machine tool spindle thermal error prediction technique based on wavelet neural networks of genetic algorithm |
| CN109606364A (en) * | 2018-11-19 | 2019-04-12 | 江苏大学 | A kind of variable speed lower leaf formula self study extension neural network lane holding control method of intelligent automobile |
| CN109709895A (en) * | 2019-01-22 | 2019-05-03 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling training method based on image threshold setting |
| CN109739181A (en) * | 2019-01-22 | 2019-05-10 | 宁波大学 | A kind of main shaft of numerical control machine tool thermal error modeling detection method based on detection neural network |
| CN109800537A (en) * | 2019-02-20 | 2019-05-24 | 大连理工大学 | A kind of machine tool thermal error model reliability degree calculation method based on deep neural network and Monte Carlo method |
| EP3715989A1 (en) * | 2019-03-29 | 2020-09-30 | Siemens Aktiengesellschaft | Method and device for monitoring a milling process |
| CN110039373A (en) * | 2019-04-04 | 2019-07-23 | 华中科技大学 | A kind of main shaft of numerical control machine tool thermal deformation prediction technique and system |
| CN110543140A (en) * | 2019-07-26 | 2019-12-06 | 四川大学 | time characteristic-based numerical control machine tool spindle system thermal key point selection modeling method |
| CN110929758A (en) * | 2019-10-24 | 2020-03-27 | 河海大学 | Complex data-oriented clustering algorithm for rapidly searching and finding density peak |
| CN111259498A (en) * | 2020-01-14 | 2020-06-09 | 重庆大学 | Axle system thermal error modeling method and thermal error compensation system based on LSTM neural network |
| CN111414977A (en) * | 2020-03-09 | 2020-07-14 | 西南交通大学 | Weighted integration temperature sensitive point combination selection method for machine tool spindle thermal error modeling |
| CN111459094A (en) * | 2020-03-09 | 2020-07-28 | 西南交通大学 | Regional selection method for temperature sensitive point combination in machine tool spindle thermal error modeling |
| CN111596612A (en) * | 2020-05-11 | 2020-08-28 | 上海交通大学 | Numerical control machine tool thermal error compensation method and system based on workpiece dimension data |
| CN111914930A (en) * | 2020-07-30 | 2020-11-10 | 上海工程技术大学 | Density peak value clustering method based on self-adaptive micro-cluster fusion |
Non-Patent Citations (2)
| Title |
|---|
| 杨漪: "加工中心热误差机理分析及误差实时补偿研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 陈诚，等: "考虑运行条件的Elman网络丝杠驱动系统热误差建模", 《光学精密工程》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112475904B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Deep learning-based tool wear prediction and its application for machining process using multi-scale feature fusion and channel attention mechanism | |
| CN105718876B (en) | A kind of appraisal procedure of ball-screw health status | |
| CN111366123B (en) | Part surface roughness and cutter wear prediction method based on multi-task learning | |
| Shen et al. | Dynamic joint distribution alignment network for bearing fault diagnosis under variable working conditions | |
| Li et al. | Similarity-measured isolation forest: anomaly detection method for machine monitoring data | |
| Guo et al. | Online remaining useful life prediction of milling cutters based on multisource data and feature learning | |
| WO2019001220A1 (en) | Decision tree based turning process energy consumption prediction system and method of numerically controlled lathe | |
| CN112529341B (en) | Drilling well leakage probability prediction method based on naive Bayesian algorithm | |
| CN108803486A (en) | Numerical control machining tool heat error prediction based on deep learning network in parallel and compensation method | |
| CN106842922B (en) | Numerical control machining error optimization method | |
| Xu et al. | CNC internal data based incremental cost-sensitive support vector machine method for tool breakage monitoring in end milling | |
| CN116448419A (en) | Zero sample bearing fault diagnosis method based on depth model high-dimensional parameter multi-target efficient optimization | |
| CN111639461A (en) | Tool wear state detection method aiming at industrial unbalanced data | |
| CN116186499A (en) | Numerical control machining surface roughness prediction method | |
| CN111814728A (en) | Method for recognizing wear state of cutting tool of numerical control machine tool and storage medium | |
| CN114789364B (en) | Multi-index drilling quality control method and device and equipment thereof | |
| CN114429152A (en) | Rolling bearing fault diagnosis method based on dynamic index antagonism self-adaption | |
| Oberle et al. | A use case to implement machine learning for life time prediction of manufacturing tools | |
| CN117194995A (en) | Rail vehicle RAMS data association analysis method based on data mining | |
| CN112475904B (en) | Numerical control milling and boring machine machining precision prediction method based on thermal analysis | |
| Peng et al. | A tool wear condition monitoring method for non-specific sensing signals | |
| CN113884300A (en) | Rolling bearing fault diagnosis method for deep anti-migration learning | |
| CN109648397B (en) | Broach life prediction method based on correlation between width of cutting edge strip and broaching load | |
| CN117034601A (en) | Soft measurement modeling method for overflow granularity in multi-station ore dressing process | |
| K. Rai et al. | Prediction of drill-bit breakage from degradation signals using Mahalanobis-Taguchi system analysis |
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 |