CN116258075A - Fault learning method for speed reducer of industrial robot - Google Patents
Fault learning method for speed reducer of industrial robot Download PDFInfo
- Publication number
- CN116258075A CN116258075A CN202310128261.0A CN202310128261A CN116258075A CN 116258075 A CN116258075 A CN 116258075A CN 202310128261 A CN202310128261 A CN 202310128261A CN 116258075 A CN116258075 A CN 116258075A
- Authority
- CN
- China
- Prior art keywords
- gear
- speed reducer
- abrasion
- value
- industrial robot
- 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
- 239000003638 chemical reducing agent Substances 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005299 abrasion Methods 0.000 claims abstract description 56
- 230000006870 function Effects 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000005452 bending Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fault learning method for an industrial robot speed reducer, which comprises the following steps: s1, acquiring a fluctuation data set of a historical target time interval of an industrial robot speed reducer, and performing objective function calculation according to fluctuation data of a speed reducer gear; s2, performing initial training of a neural network according to a target learning function, and predicting abrasion of a speed reducer gear by setting constraint conditions; and S3, performing relevance analysis on the gear abrasion sample of the speed reducer according to the target learning function converged by the constraint condition, so as to calculate the loss value of gear abrasion failure.
Description
Technical Field
The invention relates to the field of industrial robot learning, in particular to a fault learning method for a speed reducer of an industrial robot.
Background
The industrial robot is in a high-load and high-strength running state for a long time, and key parts such as a speed reducer and the like of the industrial robot are easy to break down and irreversibly wear, so that the key parts are key problems of predictive maintenance of enterprises, but the predictive maintenance research of key parts of a mechanical system under the current data drive is mainly based on balanced numbers, and noise and data in running data of the industrial robot are typical unbalanced problems. In the prior art, after corresponding parameter data is collected, corresponding fault parameters cannot be quickly learned, which is needed to be solved by a person skilled in the art.
Disclosure of Invention
The invention aims at least solving the technical problems in the prior art, and particularly creatively provides a fault learning method for an industrial robot speed reducer.
In order to achieve the above object of the present invention, the present invention provides a fault learning method for an industrial robot speed reducer, characterized by comprising the steps of:
s1, acquiring a fluctuation data set of a historical target time interval of an industrial robot speed reducer, and performing objective function calculation according to fluctuation data of a speed reducer gear;
s2, performing initial training of a neural network according to a target learning function, and predicting abrasion of a speed reducer gear by setting constraint conditions;
and S3, performing relevance analysis on the gear abrasion sample of the speed reducer according to the target learning function converged by the constraint condition, so as to calculate the loss value of gear abrasion failure.
Preferably, in the above technical solution, the S1 includes:
s1-1, according to t E [0, T of the industrial robot reducer in an operation time interval]Collecting a data set U in which gear wear fluctuations occur T =[u t1 ,u t2 ,...,u tn ]Wherein u is tn The speed reducer gear wear fluctuation corresponding to the t-th time node is valued, and the average value of fluctuation data in a time interval is calculated asWhen the obtained fluctuation data is larger than the average valueForm a high value set when the obtained fluctuation data is smaller than the mean +.>Forming a low value set according to the variance eta of the high value set high And variance η of low value set low And when the fluctuation data is suddenly increased or reduced, calculating the fluctuation data according to the gear loss objective function of the speed reducer.
Preferably, in the above technical solution, the S1 includes:
s1-2, establishing a loss objective function according to the total abrasion amount of the gear of the speed reducer and the expected abrasion degree:
min V={v 1 ,v 2 ,v 3 }
wherein v is 1 Representing the sum of deformation offset of a gear and bending strength value of the gear, wherein P is total input power of the speed reducer, beta is power distribution coefficient of the gear, d is diameter of the gear, and q is the power distribution coefficient of the gear i Input control rate, s, for gear rotation, i < th > revolution j Load power for the j-th gear; w (w) ij For binary selection variables, continuous sampling is performed when 1 is the jth gear rotation at the ith turn, and intermittent sampling is performed when 0 is the jth gear rotation at the ith turn; mu is stress concentration coefficient, W i Representing the total power set of all j gear rotations i turns, z ij The expected power consumption value for all gears; delta is the gear loss coefficient;
v 2 a fluctuation degree calculation formula representing the abrasion of the gear;
v 3 representing the effective utilization state function of the gear;
X 1 is the fatigue distribution parameter between adjacent gear revolution, lambda is the tooth of adjacent gear revolutionCoefficient of wheel fatigue difference, a ij As the actual fatigue difference value between the adjacent gear revolutions,is the expected fatigue difference value between adjacent gear revolutions.
Preferably, in the above technical solution, the S1 further includes:
X 2 is a gear shear stress distribution parameter; f is the axial force obtained by the gear, L is the thickness of the gear, M is the cross-sectional area of the gear, and epsilon is the effective stress coefficient of the shear stress of the gear;
Y 1 for continuously running wear degree of gear load, Y 2 For correcting the stress coefficient of the gear, Y 3 Is the dynamic load coefficient of the gear.
Preferably, in the above technical solution, the S2 includes:
in the process of calculating the objective function, in order to improve the learning accuracy and reduce the step length, the gear loss of the speed reducer is refined through constraint conditions; the constraint relation between the expected abrasion power consumption of each gear and the actual gear abrasion power in the gear abrasion process is as follows:
as a limiting condition of gear power, the minimum value of the total power P input to the speed reducer needs to be larger than the value of the whole power set, t total For j gears rotating i turnsAll of the time that is expected to be spent,average time for a single gear; />Is rounded upwards; s is(s) mean Is the average load power of the gears.
Preferably, in the above technical solution, the S3 includes:
the gear wear loss value is estimated asWherein H is lost For gear abrasion learning failure sample point, H total The total number of the failure samples; />Learning a failure sample point minimum value for gear wear, < >>Learning a failure sample point maximum value for gear wear; />Learning a failure sample point average value for gear wear; />The failure adjustment coefficient of the gear abrasion sample is adjusted;
after constraint sampling of the gear abrasion failure sample and failure adjustment are carried out, the corresponding gear abrasion failure range can be known, and gear abrasion association degree analysis is carried out according to corresponding judgment conditions. In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
an objective function model is established, and the model is used for predicting the abrasion degree of the gear through constraint conditions so as to realize state monitoring and fault prediction of parts of the industrial robot speed reducer. Meanwhile, by integrating the theoretical model, a predictive working method aiming at key parts of the industrial robot is designed and developed, and the technical effects of real-time state monitoring and residual life prediction of key parts of the industrial robot represented by a speed reducer, long service life strategy maintenance and the like are achieved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
fig. 1 is a general schematic of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
As shown in fig. 1, the invention discloses a fault learning method for an industrial robot speed reducer, which comprises the following steps:
s1, acquiring a fluctuation data set of a historical target time interval of an industrial robot speed reducer, and performing objective function calculation according to fluctuation data of a speed reducer gear;
s2, performing initial training of a neural network according to a target learning function, and predicting abrasion of a speed reducer gear by setting constraint conditions;
and S3, performing relevance analysis on the gear abrasion sample of the speed reducer according to the target learning function converged by the constraint condition, so as to calculate the loss value of gear abrasion failure and judge the relevance between the failure of the speed reducer and the gear abrasion of the speed reducer.
Preferably, in the above technical solution, the S1 includes:
s1-1, according to t E [0, T of the industrial robot reducer in an operation time interval]The time value of T is 60s-120s, and a data set U with gear wear fluctuation is collected T =[u t1 ,u t2 ,...,u tn ]Wherein u is tn The value of the fluctuation of the wear of the gear of the speed reducer corresponding to the t-th time node is taken, fluctuation data in a corresponding time interval are required to be continuously collected in the process of carrying out preliminary training on the wear data of the speed reducer, and the average value of the fluctuation data in the time interval is calculated asWhen the obtained fluctuation data is larger than the mean +.>Form a high value set when the obtained fluctuation data is smaller than the mean +.>Forming a low value set according to the variance eta of the high value set high And variance η of low value set low When the fluctuation data is suddenly increased or suddenly decreased, calculating the fluctuation data according to a gear loss objective function of the speed reducer;
s1-2, establishing a loss objective function according to the total abrasion amount of the gear of the speed reducer and the expected abrasion degree:
min V={v 1 ,v 2 ,v 3 }
wherein v is 1 Representing the sum of deformation offset of a gear and bending strength value of the gear, and calculating the deformation state of the gear, wherein P is the total input power of the speed reducer, beta is the power distribution coefficient of the gear, d is the diameter of the gear, and q i Input control rate, s, for gear rotation, i < th > revolution j Load power for the j-th gear; w (w) ij For binary selection variables, continuous sampling is performed when 1 is the jth gear rotation at the ith turn, and intermittent sampling is performed when 0 is the jth gear rotation at the ith turn; mu is stress concentration coefficient, W i Representing all power sets of all j gear rotation i circles, wherein the power sets mean that load power of a single gear rotation one circle is subjected to data recording, and load power data sets of all j gear rotation i weights are formed; z ij The expected power consumption value for all gears; delta is the gear loss coefficient;
v 2 a fluctuation degree calculation formula representing the abrasion of the gear;
v 3 representing the effective utilization state function of the gear;
X 1 is the fatigue distribution parameter between adjacent gear revolution, lambda is the gear fatigue difference coefficient of adjacent gear revolution, a ij As the actual fatigue difference value between the adjacent gear revolutions,as the expected fatigue difference value between the adjacent gear revolutions,
X 2 is a gear shear stress distribution parameter; f is the axial force obtained by the gear, L is the thickness of the gear, M is the cross-sectional area of the gear, and epsilon is the effective stress coefficient of the shear stress of the gear;
Y 1 for continuously running wear degree of gear load, Y 2 For correcting the stress coefficient of the gear, Y 3 Is the dynamic load coefficient of the gear;
calculating the fatigue degree, shear stress and wear fluctuation degree of the gear, so as to quantitatively calculate uncertain data conditions, obtain distribution parameters and curve fluctuation of gear wear, and generate corresponding sample values according to fluctuation states of variables, thereby primarily judging the gear wear;
the method can be applied to the abrasion data analysis of the central wheel, the planet wheel, the crank shaft, the cycloid wheel and the bell gear of the speed reducer in the abrasion calculation of the gear of the speed reducer.
Preferably, in the above technical solution, the S2 includes:
in the process of calculating the objective function, in order to improve the learning accuracy and reduce the step length, the gear loss of the speed reducer is refined through constraint conditions; the constraint relation between the expected abrasion power consumption of each gear and the actual gear abrasion power in the gear abrasion process is as follows:
as a limiting condition of gear power, the minimum value of the total power P input to the speed reducer needs to be larger than the value of the whole power set, t total For all expected times of use for j gear rotations i,average time for a single gear; />Is rounded upwards; s is(s) mean Average load power for the gears;
according to the gear abrasion power in the continuous working process, the gear abrasion prediction method plays an important role in gear abrasion prediction, the fatigue degree of the gears and the deformation state of the gears are distributed and sequentially depicted through setting corresponding constraint conditions, and according to the fitness calculation result formed by each gear in the working process, the association degree judgment is formed between the gear abrasion degree and the faults of the speed reducer.
Preferably, in the above technical solution, the S3 includes:
the gear wear loss value is estimated asWherein H is lost For gear abrasion learning failure sample point, H total The total number of the failure samples; />Learning a failure sample point minimum value for gear wear, < >>Learning a failure sample point maximum value for gear wear; />Learning a failure sample point average value for gear wear; />The failure adjustment coefficient of the gear abrasion sample is adjusted;
after constraint sampling of the gear abrasion failure sample and failure adjustment are carried out, the corresponding gear abrasion failure range can be known, and gear abrasion association degree analysis is carried out according to corresponding judgment conditions. When the minimum value of the failure sample point is larger than the actual failure sample point, the loss estimated value is 1, the gear abrasion fault risk is judged to be higher, when the maximum value of the failure sample point is smaller than or equal to the actual failure sample point, the loss estimated value is 0, the gear abrasion fault risk is judged to be lower, and the gear abrasion fault risk is judged to be lower according to the average value of samples
The method of the invention is beneficial to the fault management of the speed reducer. Compared with manual decision, the objective function value in the invention S1 is optimized greatly, because the model decision is optimized in the global range of the gear loss of the speed reducer; from all features, model decisions help their users to connect the speed reducer gear loss plan with the data of the actual change rate of the industrial robot speed reducer for management in the industrial robot update component plan.
The model optimization solution which is convenient for visual understanding is generated by continuously learning an improved objective function calculation algorithm suitable for the characteristics of the model, wherein the algorithm is based on the selection of the number of gear wearing and the number of wearing revolutions, and the invalid search space of the solution is reduced by setting constraint conditions, so that the model is convenient for reference of model users.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (6)
1. The fault learning method for the speed reducer of the industrial robot is characterized by comprising the following steps of:
s1, acquiring a fluctuation data set of a historical target time interval of an industrial robot speed reducer, and performing objective function calculation according to fluctuation data of a speed reducer gear;
s2, performing initial training of a neural network according to a target learning function, and predicting abrasion of a speed reducer gear by setting constraint conditions;
and S3, performing relevance analysis on the gear abrasion sample of the speed reducer according to the target learning function converged by the constraint condition, so as to calculate the loss value of gear abrasion failure.
2. The fault learning method for an industrial robot speed reducer according to claim 1, wherein S1 includes:
s1-1, according to t E [0, T of the industrial robot reducer in an operation time interval]Collecting a data set U in which gear wear fluctuations occur T =[u t1 ,u t2 ,...,u tn ]Wherein u is tn The speed reducer gear wear fluctuation corresponding to the t-th time node is valued, and the average value of fluctuation data in a time interval is calculated asWhen the obtained fluctuation data is larger than the mean +.>Form a high value set when the obtained fluctuation data is smaller than the mean +.>Forming a low value set according to the variance eta of the high value set high And variance η of low value set low And when the fluctuation data is suddenly increased or reduced, calculating the fluctuation data according to the gear loss objective function of the speed reducer.
3. The fault learning method for an industrial robot speed reducer according to claim 2, wherein the S1 includes:
s1-2, establishing a loss objective function according to the total abrasion amount of the gear of the speed reducer and the expected abrasion degree:
min V={v 1 ,v 2 ,v 3 }
wherein v is 1 Representing the sum of deformation offset of a gear and bending strength value of the gear, wherein P is total input power of the speed reducer, beta is power distribution coefficient of the gear, d is diameter of the gear, and q is the power distribution coefficient of the gear i Input control rate, s, for gear rotation, i < th > revolution j Load power for the j-th gear; w (w) ij For binary selection variables, continuous sampling is performed when 1 is the jth gear rotation at the ith turn, and intermittent sampling is performed when 0 is the jth gear rotation at the ith turn; mu is stress concentration coefficient, W i Representing the total power set of all j gear rotations i turns, z ij The expected power consumption value for all gears; delta is the gear loss coefficient;
v 2 a fluctuation degree calculation formula representing the abrasion of the gear;
v 3 representing the effective utilization state function of the gear;
X 1 is the fatigue distribution parameter between adjacent gear revolution, lambda is the gear fatigue difference coefficient of adjacent gear revolution, a ij As the actual fatigue difference value between the adjacent gear revolutions,is the expected fatigue difference value between adjacent gear revolutions.
4. The method for industrial robot speed reducer failure learning according to claim 3, wherein S1 further comprises:
X 2 is a gear shear stress distribution parameter; f is the axial force obtained by the gear, L is the thickness of the gear, M is the cross-sectional area of the gear, and epsilon is the effective stress coefficient of the shear stress of the gear;
Y 1 for continuously running wear degree of gear load, Y 2 For correcting the stress coefficient of the gear, Y 3 Is the dynamic load coefficient of the gear.
5. The fault learning method for an industrial robot speed reducer according to claim 1, wherein S2 includes:
in the process of calculating the objective function, in order to improve the learning accuracy and reduce the step length, the gear loss of the speed reducer is refined through constraint conditions; the constraint relation between the expected abrasion power consumption of each gear and the actual gear abrasion power in the gear abrasion process is as follows:
as a limiting condition of gear power, the minimum value of the total power P input to the speed reducer needs to be larger than the value of the whole power set, t total For all expected times of use for j gear rotations i,average time for a single gear; />Is rounded upwards; s is(s) mean Is the average load power of the gears.
6. The fault learning method for an industrial robot speed reducer according to claim 1, wherein the S3 includes:
the gear wear loss value is estimated asWherein H is lost For gear abrasion learning failure sample point, H total The total number of the failure samples; />Learning a failure sample point minimum value for gear wear, < >>Learning a failure sample point maximum value for gear wear; />Learning a failure sample point average value for gear wear; />The failure adjustment coefficient of the gear abrasion sample is adjusted;
after constraint sampling of the gear abrasion failure sample and failure adjustment are carried out, the corresponding gear abrasion failure range can be known, and gear abrasion association degree analysis is carried out according to corresponding judgment conditions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310128261.0A CN116258075B (en) | 2023-02-16 | 2023-02-16 | Fault learning method for speed reducer of industrial robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310128261.0A CN116258075B (en) | 2023-02-16 | 2023-02-16 | Fault learning method for speed reducer of industrial robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116258075A true CN116258075A (en) | 2023-06-13 |
CN116258075B CN116258075B (en) | 2024-04-23 |
Family
ID=86685883
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310128261.0A Active CN116258075B (en) | 2023-02-16 | 2023-02-16 | Fault learning method for speed reducer of industrial robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116258075B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110096796A (en) * | 2019-04-29 | 2019-08-06 | 电子科技大学 | The analysis method for reliability of industrial robot RV retarder under a kind of multi-invalidation mode |
US20200005201A1 (en) * | 2018-07-02 | 2020-01-02 | Demand Energy Networks, Inc. | Stochastic economic optimization of electrical systems, and related systems, apparatuses, and methods |
US20210081791A1 (en) * | 2019-09-13 | 2021-03-18 | Osaro | Computer-Automated Robot Grasp Depth Estimation |
JP2021092971A (en) * | 2019-12-10 | 2021-06-17 | キヤノン株式会社 | Control method, control unit, machine plant, control program, and recording medium |
CN115512795A (en) * | 2022-09-29 | 2022-12-23 | 东南大学 | Method for accurately measuring wear resistance of material based on machine learning |
-
2023
- 2023-02-16 CN CN202310128261.0A patent/CN116258075B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200005201A1 (en) * | 2018-07-02 | 2020-01-02 | Demand Energy Networks, Inc. | Stochastic economic optimization of electrical systems, and related systems, apparatuses, and methods |
CN110096796A (en) * | 2019-04-29 | 2019-08-06 | 电子科技大学 | The analysis method for reliability of industrial robot RV retarder under a kind of multi-invalidation mode |
US20210081791A1 (en) * | 2019-09-13 | 2021-03-18 | Osaro | Computer-Automated Robot Grasp Depth Estimation |
JP2021092971A (en) * | 2019-12-10 | 2021-06-17 | キヤノン株式会社 | Control method, control unit, machine plant, control program, and recording medium |
CN115512795A (en) * | 2022-09-29 | 2022-12-23 | 东南大学 | Method for accurately measuring wear resistance of material based on machine learning |
Non-Patent Citations (1)
Title |
---|
闫宗庆: "基于有限元和油液分析的齿轮疲劳寿命预测研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 01, pages 029 - 297 * |
Also Published As
Publication number | Publication date |
---|---|
CN116258075B (en) | 2024-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5774633A (en) | Supporting neural network method for process operation | |
CN111507490B (en) | Method and system for predictively maintaining spindle of numerical control machine tool based on multi-source data driving | |
CN109766745B (en) | Reinforced learning tri-state combined long-time and short-time memory neural network system and training and predicting method | |
CN102411308A (en) | Adaptive control method of dissolved oxygen (DO) based on recurrent neural network (RNN) model | |
CN108562709A (en) | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine | |
CN108536106B (en) | Aeration system dissolved oxygen online regulation and control method based on Kalman filtering-extreme learning machine | |
CN116067432B (en) | Escalator variable working condition fault diagnosis method | |
CN113343591B (en) | Product key part life end-to-end prediction method based on self-attention network | |
CN115879245A (en) | Method for evaluating long-life transmission fatigue reliability of medium carbon steel gear | |
CN116258075B (en) | Fault learning method for speed reducer of industrial robot | |
CN116871978A (en) | Drilling tool state monitoring method based on multi-sensor fusion | |
CN115358533A (en) | Predictive maintenance management system based on big data | |
CN116957120A (en) | Device state history trend anomaly prediction method based on data analysis | |
CN117390960A (en) | Intelligent analysis method for machining precision of numerical control machine tool | |
CN113204849A (en) | Gear peeling fault detection method for gear box | |
CN112767692A (en) | Short-term traffic flow prediction system based on SARIMA-GA-Elman combined model | |
CN114149076B (en) | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system | |
CN112487580B (en) | Nuclear power plant important pump gear box operational state evaluation method | |
Peng et al. | Wind turbine blades icing failure prognosis based on balanced data and improved entropy | |
Juuso et al. | Combining process and condition monitoring data | |
CN113011463B (en) | Improved GA-BP-based Chinese herbal medicine equipment bearing life prediction method | |
Tang et al. | Intelligent health evaluation method of slewing bearing adopting multiple types of signals from monitoring system | |
CN118114005B (en) | Belt conveyor bearing self-adaptive phasing and digital-analog fusion life prediction method | |
CN117332608A (en) | Real-time reliability assessment method for online RUL prediction result of rotary machine | |
CN114219175B (en) | Mechanical property prediction method for container coiled plate |
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 |