CN104742153A - Fault predication device of six-axis multi-joint industrial robot - Google Patents
Fault predication device of six-axis multi-joint industrial robot Download PDFInfo
- Publication number
- CN104742153A CN104742153A CN201510167521.0A CN201510167521A CN104742153A CN 104742153 A CN104742153 A CN 104742153A CN 201510167521 A CN201510167521 A CN 201510167521A CN 104742153 A CN104742153 A CN 104742153A
- Authority
- CN
- China
- Prior art keywords
- industrial robot
- displacement
- data
- characteristic value
- joint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
A fault predication device of a six-axis multi-joint industrial robot comprises a laser displacement measuring module, a central processor, a storage unit and a display module. The central processor sequentially executes the following steps: periodically receiving specific displacement process data of wrist end portions of the industrial robot, wherein the specific displacement process data is obtained by the detection of the laser displacement measuring module; comparing the displacement process data with a standard set displacement requirement, calculating displacement difference value data of a plurality of selected moments, and sending the displacement difference value data to the storage unit; applying time domain analysis, mean value extraction, standard deviation, square deviation, or the like to the displacement difference value data for obtaining a plurality of time domain characteristic values, and sending the time domain characteristic values to the storage unit; predicting a characteristic value sequence based on an ARIMA model for obtaining characteristic values of future moments; utilizing trained support vectors to classify states of the characteristic values of the future moments, so as to obtain a future degradation level estimation; and sending the degradation state prediction result to the display module. The fault predication device of the six-axis multi-joint industrial robot can predict the reduction gear wear-out failure of the industrial robot.
Description
Technical field
Patent of the present invention relates to a kind of six axle multi-joint industrial robot fault prediction devices, particularly a kind of six axle multi-joint industrial robot fault prediction devices based on laser displacement measurement.
Background technology
Current, China faces that comparatively serious labor cost rises violently, labor shortage problem.How utilizing industrial robot to replace most repeated manual labors, is an important topic of following Industrial-Enterprises in China transition and upgrade.
Six axle multi-joint industrial robots are popular industrial machine people that at present application is the most general, in welding, some glue, carrying, loading and unloading, spray paint, multiple operation field such as polishing is all widely used.The most important thing is reductor in six axle multi-joint industrial robot mechanical parts, comprise harmonic wave speed reducing machine and RV reductor.In use, the reductor of industrial robot all can wear and tear gradually, thus causes the positioning precision in each joint to be deteriorated, and probably affect the operation precision of robot entirety, some production links also can cause great negative effect to product quality.If the wear condition can carrying out reductor is monitored automatically, and forecasts wear trend, industrial robot can be helped to use enterprise to make rational maintaining and change and to arrange.
On the vibration signal data basis of patent of invention " a kind of oscillatory type robot palletizer failure prediction method " (application publication number CN104089790A) on the pedestal gathering robot palletizer and mechanical arm, by the overall variation tendency to two place's vibration signals, realize the failure predication of robot palletizer.
Although above-mentioned technology achieves initial achievements in robot fault prediction, have the following disadvantages:
(1) rational state forecast cannot be provided for robot performance's degradation information (vibration);
(2) vibration signal collected is easy to be subject to outside interference and data volume is large, must carry out rational data processing and feature extraction.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, six axle multi-joint industrial robot fault prediction devices are provided, make its structure simple, with low cost, easy to use, for the reductor wear condition of automatic monitoring and prediction six axle multi-joint industrial robot.
For realizing object of the present invention, the invention provides a kind of six axle multi-joint industrial robot fault prediction devices, this device comprises: laser displacement measurement module, central processing unit, memory cell and display module.For realizing the failure predication of six axle multi-joint industrial robots, central processing unit performs the program of following steps:
A) the particular displacement process data that laser displacement measurement module detects the industrial robot wrist distal portion obtained regularly is received;
B) the industrial robot displacement data received and standard setting displacement request are compared, calculate the shift differences data in the some selected moment of particular displacement process kind, and shift differences data are sent in the middle of memory cell;
C) time-domain analysis is carried out to displacement difference data, extract average, standard deviation, variance, kurtosis, maximum, minimum of a value as temporal signatures value, and characteristic value is sent in the middle of memory cell;
D) carry out characteristic value sequence prediction based on ARIMA model theory, obtain the characteristic value of future time;
E) utilize trained SVMs to carry out state classification to the characteristic value of future time, obtain in the future deteriorated horizontal estimated, and deterioration state is predicted the outcome send to display module.
The step that central processing unit of the present invention performs a) in particular displacement be certain section of straight-line displacement that artificial teach mode or other modes set.This straight-line displacement action is the displacement action that industrial robot regularly carries out after completing the process operations of several times setting.
Laser displacement measurement module of the present invention adopts one dimension laser displacement sensor, the positioning precision of required precision height and industrial robot.
Display module of the present invention can be any one display unit that industrial control system is conventional, such as eight sections of LED charactrons or liquid crystal display etc.
The present invention is a kind of six axle multi-joint industrial robot fault prediction devices, the principle that when this device weares and teares according to industrial robot reductor, positioning precision is deteriorated, regularly the particular displacement moving situation of industrial robot wrist distal portion is detected, judge after treatment to obtain six axle multi-joint industrial robot reductor wear conditions, have cost low, realize simple feature, be a kind of online industrial robot fault prediction device.
Accompanying drawing explanation
Fig. 1 is structured flowchart of the present invention;
Fig. 2 is method step schematic diagram of the present invention.
Detailed description of the invention
As shown in Figure 1, the present invention includes four parts: laser displacement measurement module 1, central processing unit 2, memory cell 3 and display module 4.This specific embodiment for be ABB AB six axle multi-joint industrial robot IRB1410 reductors wearing and tearing failure predication application, this robot be used for weld job.Therefore, laser displacement measurement module 1 of the present invention adopts the one dimension laser displacement sensor M18 of Lai Enshi company, and central processing unit 2 of the present invention and memory cell 3 are selected and ground magnificent industrial computer IPC-510 in addition, and display module 4 is DELL brand-name display.Grind magnificent industrial computer IPC-510 and run windows XP system.
Laser displacement measurement module 1 of the present invention is mounted in industrial robot working range, but does not affect the normal procedure action of robot, and sample frequency is set as 1000Hz.Manually teaching, aforementioned six axle multi-joint industrial robot IRB1410 complete in the middle of fixing welding job process, every welding job carries out 100 hours, this robot wrist distal portion moves in the measurement stroke of laser displacement measurement module 1 automatically, and carries out straight line uniform motion along beam direction.The stroke of this straight line uniform motion is 50cm (apart from adjustable), and the deadline is 2 seconds.
For realizing the failure predication of six axle multi-joint industrial robots, grinding in magnificent industrial computer IPC-510 and utilizing Visual C++ Development of Software Platform program, this program package is containing following steps (also namely central processing unit 2 of the present invention performs following steps):
A), after the every welding job of this industrial robot is carried out 100 hours, the straight-line displacement that laser displacement measurement module detects the industrial robot wrist distal portion obtained is received;
B) the linear uniform motion displacement request of the industrial robot displacement data received and setting is compared, calculate the shift differences of each sampling instant in 2 seconds, and shift differences data are sent in the middle of memory cell;
C) time-domain analysis is carried out to displacement difference data, extract average, standard deviation, variance, kurtosis, maximum, minimum of a value as temporal signatures value, and characteristic value is sent in the middle of memory cell;
D) carry out characteristic value sequence prediction based on ARIMA model theory, obtain the characteristic value of future time;
E) utilize trained SVMs to carry out state classification to the characteristic value of future time, obtain in the future deteriorated horizontal estimated, and deterioration state is predicted the outcome send to display module.
Above-mentioned five steps often carries out then regularly performing for 100 hours in industrial robot welding job.Steps d) be utilize ARIMA model theory, feature based value historical data carries out the time series forecasting of future time instance characteristic value.ARIMA model is utilized to carry out in the middle of data sequence forecasting process, should according to its theory calls, carry out data sequence stationary test and tranquilization process, model determines rank and parameter Estimation, and two steps prediction (characteristic value after namely predicting 100 × 2=200 hour) of realization character value sequence, the reductor wear levels of this characteristic value reaction industry robot.Step e) utilize trained SVMs to carry out state classification for the characteristic value after 200 hours, realize the robot reductor wear levels predicted estimate of 200 hours.SVMs is conventional mode identification method, the SVMs process training in advance that the present invention is used, can provide robot reductor wear condition based on the characteristic value of the wrist end straight-line motion accuracy data of aforementioned six axle multi-joint industrial robots and estimate.
Adopt above-mentioned step and technology, finally complete the failure predication of the six axle multi-joint industrial robot IRB1410 reductor wearing and tearing of ABB AB.
Claims (3)
1. an axle multi-joint industrial robot fault prediction device, comprise: laser displacement measurement module (1), central processing unit (2), memory cell (3) and display module (4), it is characterized in that: for realizing the failure predication of six axle multi-joint industrial robots, central processing unit (2) performs following steps:
A) the particular displacement process data that laser displacement measurement module detects the industrial robot wrist distal portion obtained regularly is received;
B) the industrial robot displacement data received and standard setting displacement request are compared, calculate the shift differences data in the some selected moment of particular displacement process kind, and shift differences data are sent in the middle of memory cell;
C) time-domain analysis is carried out to displacement difference data, extract average, standard deviation, variance, kurtosis, maximum, minimum of a value as temporal signatures value, and characteristic value is sent in the middle of memory cell;
D) carry out characteristic value sequence prediction based on ARIMA model theory, obtain the characteristic value of future time;
E) utilize trained SVMs to carry out state classification to the characteristic value of future time, obtain in the future deteriorated horizontal estimated, and deterioration state is predicted the outcome send to display module.
2. six axle multi-joint industrial robot fault prediction devices according to claim 1, is characterized in that, described laser displacement measurement module (1) is one dimension laser displacement sensor.
3. six axle multi-joint industrial robot fault prediction devices according to claim 1, it is characterized in that, the step that described central processing unit (2) performs a) in particular displacement be certain section of straight-line displacement that artificial teach mode or other modes set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510167521.0A CN104742153A (en) | 2015-04-01 | 2015-04-01 | Fault predication device of six-axis multi-joint industrial robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510167521.0A CN104742153A (en) | 2015-04-01 | 2015-04-01 | Fault predication device of six-axis multi-joint industrial robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104742153A true CN104742153A (en) | 2015-07-01 |
Family
ID=53582694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510167521.0A Pending CN104742153A (en) | 2015-04-01 | 2015-04-01 | Fault predication device of six-axis multi-joint industrial robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104742153A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105675038A (en) * | 2016-01-05 | 2016-06-15 | 中国计量学院 | Device for predicting faults of instruments |
| CN106695747A (en) * | 2015-11-13 | 2017-05-24 | 国网辽宁省电力有限公司检修分公司 | Valve hall inspection method and inspection robot based on laser radar |
| CN110990989A (en) * | 2019-06-05 | 2020-04-10 | 天津博诺智创机器人技术有限公司 | Industrial robot fault prediction method based on self-organization critical theory |
| CN111098331A (en) * | 2020-01-04 | 2020-05-05 | 中国矿业大学徐海学院 | Industrial robot capable of detecting joint wear degree in real time |
| CN111386179A (en) * | 2017-10-27 | 2020-07-07 | 费斯托股份两合公司 | Hardware module, robot system and method for operating a robot system |
| CN111829433A (en) * | 2019-04-18 | 2020-10-27 | 中国科学院沈阳自动化研究所 | Device and method for detecting motion parameters of gluing developing equipment |
| CN114454213A (en) * | 2022-01-26 | 2022-05-10 | 东华大学 | Industrial robot joint current signal abnormity detection method based on EEMD-HT-kurtosis analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008137102A (en) * | 2006-11-30 | 2008-06-19 | Matsushita Electric Works Ltd | Machine tool observation device |
| CN101241359A (en) * | 2007-02-06 | 2008-08-13 | Abb研究有限公司 | A method and a control system for monitoring the condition of an industrial robot |
| CN101263499A (en) * | 2005-07-11 | 2008-09-10 | 布鲁克斯自动化公司 | Intelligent condition monitoring and fault diagnostic system |
| CN102095573A (en) * | 2009-12-11 | 2011-06-15 | 上海卫星工程研究所 | State monitoring and diagnosis alarm method for mechanical component of satellite borne rotary equipment |
| CN102490086A (en) * | 2011-10-28 | 2012-06-13 | 浙江大学 | System for monitoring working state of boring rod in real time |
| CN102798581A (en) * | 2011-05-27 | 2012-11-28 | 宁夏天地奔牛实业集团有限公司 | On-line oil monitoring method and system for high-power speed reducer |
| CN102825504A (en) * | 2012-09-18 | 2012-12-19 | 重庆科技学院 | State detection method for main shaft of numerically-controlled machine tool |
-
2015
- 2015-04-01 CN CN201510167521.0A patent/CN104742153A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101263499A (en) * | 2005-07-11 | 2008-09-10 | 布鲁克斯自动化公司 | Intelligent condition monitoring and fault diagnostic system |
| JP2008137102A (en) * | 2006-11-30 | 2008-06-19 | Matsushita Electric Works Ltd | Machine tool observation device |
| CN101241359A (en) * | 2007-02-06 | 2008-08-13 | Abb研究有限公司 | A method and a control system for monitoring the condition of an industrial robot |
| CN102095573A (en) * | 2009-12-11 | 2011-06-15 | 上海卫星工程研究所 | State monitoring and diagnosis alarm method for mechanical component of satellite borne rotary equipment |
| CN102798581A (en) * | 2011-05-27 | 2012-11-28 | 宁夏天地奔牛实业集团有限公司 | On-line oil monitoring method and system for high-power speed reducer |
| CN102490086A (en) * | 2011-10-28 | 2012-06-13 | 浙江大学 | System for monitoring working state of boring rod in real time |
| CN102825504A (en) * | 2012-09-18 | 2012-12-19 | 重庆科技学院 | State detection method for main shaft of numerically-controlled machine tool |
Non-Patent Citations (2)
| Title |
|---|
| 张建民等: "面向机电系统状态监测与故障诊断的现代技术", 《北京理工大学学报》 * |
| 黄国龙: "基于阶比跟踪和AR模型的旋转机械故障诊断与状态预测技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106695747A (en) * | 2015-11-13 | 2017-05-24 | 国网辽宁省电力有限公司检修分公司 | Valve hall inspection method and inspection robot based on laser radar |
| CN105675038A (en) * | 2016-01-05 | 2016-06-15 | 中国计量学院 | Device for predicting faults of instruments |
| CN105675038B (en) * | 2016-01-05 | 2019-12-13 | 中国计量学院 | fault prediction device of instrument |
| CN111386179A (en) * | 2017-10-27 | 2020-07-07 | 费斯托股份两合公司 | Hardware module, robot system and method for operating a robot system |
| CN111386179B (en) * | 2017-10-27 | 2024-05-03 | 费斯托股份两合公司 | Hardware module, robot system and method for operating a robot system |
| CN111829433A (en) * | 2019-04-18 | 2020-10-27 | 中国科学院沈阳自动化研究所 | Device and method for detecting motion parameters of gluing developing equipment |
| CN110990989A (en) * | 2019-06-05 | 2020-04-10 | 天津博诺智创机器人技术有限公司 | Industrial robot fault prediction method based on self-organization critical theory |
| CN111098331A (en) * | 2020-01-04 | 2020-05-05 | 中国矿业大学徐海学院 | Industrial robot capable of detecting joint wear degree in real time |
| CN114454213A (en) * | 2022-01-26 | 2022-05-10 | 东华大学 | Industrial robot joint current signal abnormity detection method based on EEMD-HT-kurtosis analysis |
| CN114454213B (en) * | 2022-01-26 | 2023-12-12 | 东华大学 | Industrial robot joint current signal abnormality detection method based on EEMD-HT-kurtosis analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104742153A (en) | Fault predication device of six-axis multi-joint industrial robot | |
| EP2836881B1 (en) | Embedded prognostics on plc platforms for equipment condition monitoring, diagnosis and time-to-failure/service prediction | |
| US8190294B2 (en) | Detection of condition changes in an industrial robot system | |
| CN113175959B (en) | Fault detection robot and control method thereof | |
| US7643946B2 (en) | Method and system for appraising the wear of axles of a robot arm | |
| EP2431137A2 (en) | Reducer abnormality determination method, abnormality determination device, and robot system | |
| US11144032B2 (en) | Time to failure analysis of robotic arm cabling | |
| US11931905B2 (en) | Failure prediction method and failure prediction apparatus | |
| US11892815B2 (en) | Diagnostic apparatus | |
| CN105841736A (en) | Wireless self-diagnostic intelligent sensor | |
| CN112987682B (en) | Control method, control device and mechanical equipment | |
| CN110303491A (en) | Act history management system | |
| Er et al. | Approach towards sensor placement, selection and fusion for real-time condition monitoring of precision machines | |
| JP2024002993A (en) | Robot maintenance support device, robot maintenance support method, and robot maintenance support program | |
| KR20170121869A (en) | 3D Grinding vibration monitering system and method for grinding robot | |
| CN114034772A (en) | Expert system for detecting potential failure and predicting residual service life of roller | |
| Saritha et al. | Micro universal testing machine system for material property measurement | |
| CN111936278B (en) | Robot control device, maintenance management method, and computer-readable storage medium | |
| CN103793765A (en) | Satellite telemetering data predicting method based on Kalman smoothing | |
| US20210178615A1 (en) | Abnormality diagnosis device and abnormality diagnosis method | |
| EP3600799B1 (en) | Method, apparatus and system for monitoring industrial robot | |
| CN112123371A (en) | Robot fault prediction device and system, and robot fault prediction method | |
| CN115034117B (en) | Shore bridge metal structure life prediction system and method based on big data driving | |
| CN202648958U (en) | Numerical control pneumatic servo durability testing stand | |
| Tokhi et al. | Positional Health Assessment of Collaborative Robots Based on Long Short-Term Memory Auto-Encoder (LSTMAE) Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150701 |