CN107422718A - A kind of industrial robot failure diagnosis method - Google Patents
A kind of industrial robot failure diagnosis method Download PDFInfo
- Publication number
- CN107422718A CN107422718A CN201710321410.XA CN201710321410A CN107422718A CN 107422718 A CN107422718 A CN 107422718A CN 201710321410 A CN201710321410 A CN 201710321410A CN 107422718 A CN107422718 A CN 107422718A
- Authority
- CN
- China
- Prior art keywords
- failure
- industrial robot
- robot
- data
- model
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a kind of industrial robot failure diagnosis method, is related to industrial robot and fault diagnosis technology field.The method for diagnosing faults includes parametrization physical model, the full failure tree-model of structure industrial robot;Obtain the real-time running data of industrial robot;Dynamic simulation is carried out to the real-time operating conditions of industrial robot;Breakdown judge is carried out according to theoretical analysis result and actual monitoring result;According to fault tree models, fault reasoning is carried out, finds all possible causes for causing failure;The possible cause of failure is diagnosed one by one, regulation and control instruction corresponding to generation, drive robot motion, failure cause is confirmed according to feedback information.The present invention takes full advantage of existing data in control system, it is not necessary to increases other physical equipments in addition, takes full advantage of the design theory of equipment, has simple and practical property;Specific failure cause can simply and effectively be confirmed.
Description
Technical field
The present invention relates to industrial robot and fault diagnosis technology field, specifically, refers to a kind of industrial robot event
Hinder diagnostic method, by establishing the complete fault tree of industrial robot, and then realize the status monitoring to industrial robot and event
Barrier diagnosis.
Background technology
With " industry 4.0 ", " intelligence manufacture " and " the successive proposition of the developing goal such as made in China 2025 " and progressively bright
Really, industrial robot integrates automation, informationization, intelligent manufacturing equipment as a kind of, in the industrial production positive hair
Wave more and more important effect.Ensure reliability, stability and the security of industrial robot in the process of running, be to ensure
The essential condition that industrial production is persistently carried out without any confusion.However, industrial robot complicated electromechanical structure and residing in itself
Changeable working environment, bring no small challenge to maintenance work.
Fault diagnosis (Fault Diagnosis) refers to by detecting plant equipment under relative static conditions or in operation
Status information, measurement signal is handled and analyzed, is gone through with reference to known architectural characteristic and parameter and diagnosis object
History situation, the real time status of plant equipment and its parts is quantitatively identified, before equipment does not break down, it is run
Situation is forecast, and predicts relevant exception or failure;After the failure occurs, the position of failure, reason and degree are made
Judge in time, so that it is determined that maintenance scheme.Traditional maintenance mode, mainly include correction maintenance and periodic maintenance, already can not
Meet the needs that modern times industrial equipment is safeguarded.Modern fault diagnosis technology has improved system since the 1970s is born
Important function has been played in terms of the reliability and security of system.Modern fault diagnosis mainly include status monitoring, fault diagnosis and
The content of three aspects of failure predication.
The work characteristics of industrial robot is that it is to periodically carry out identical task, and this is to a certain extent to event
Barrier diagnosis brings facility.But simultaneously, because industrial robot perform be high speed production task, its fault diagnosis need to the greatest extent
Possibly meet the requirement of real-time.Therefore, the fault diagnosis of industrial robot needs a kind of simple, directly perceived, practicality and is easy to
The method for diagnosing faults of realization, to ensure the security of operation, ensure operating accuracy, improve maintenance efficiency, save maintenance cost.
The content of the invention
For overcome the deficiencies in the prior art, solves the problems, such as the professional technique in particular industry field, the present invention proposes one
Kind is applied to the simple, directly perceived, practical of industrial robot and the method for diagnosing faults being easily achieved.
A kind of industrial robot failure diagnosis method of the present invention, is mainly realized by following steps:
The first step, build the parametrization physical model of industrial robot;
Second step, build the full failure tree-model of industrial robot;
3rd step, obtain the real-time running data of industrial robot;
4th step, dynamic simulation is carried out to the real-time operating conditions of industrial robot;
5th step, breakdown judge is carried out according to theoretical analysis result and actual monitoring result;
6th step, according to fault tree models, fault reasoning is carried out, finds all possible causes for causing failure;
Specially:The failure symptom feature of industrial robot is matched and verified with the content of each node of fault tree;
The direction of matching is top-down, is progressively refined, until obtaining all possible causes of failure generation.
7th step, the possible cause of failure is diagnosed one by one, " suiting the remedy to the case ", regulation and control instruction corresponding to generation, driven
Mobile robot is moved, and failure cause is confirmed according to feedback information.
The detailed process of the parametrization physical model of structure industrial robot is in the first step:
101) by the mechanical structure progress manual measurement to industrial robot, or set according to it
Drawing or threedimensional model etc. are counted, directly obtains the critical physical parameter of industrial robot, including physical dimension and Mass Distribution, and
By the way that the physical parameters such as inertia are calculated;
102) physical parameter according to 101), according to D-H parametric methods, the kinematics model of industrial robot is built,
Set up the relation between joint angles and end effector pose;
103) size according to 101), quality and inertia parameter, according to newton-Lagrangian method, industrial machine is built
The kinetic model of device people, it is established that the relation between joint angles, angular speed, angular acceleration and joint moment.
The detailed process of the full failure tree-model of structure industrial robot is in second step:
201) from conventional fault diagnosis example and diagnostic experiences, extraction and summary fault diagnosis knowledge, machine is tentatively established
The fault tree models of people;The fault diagnosis knowledge includes numbering, symptom, reason, position, significance level and the solution party of failure
Case;
202) according to theory analysis and the result of reasoning from logic, the fault tree models in arranging supplement and improving 201), by
Step sets up complete fault tree models.
The real-time running data detailed process of acquisition industrial robot is in 3rd step:
301) PLC control instructions, supply voltage, current of electric are read from robot control system;
302) kinematic data, including joint angles, angular speed, angular acceleration are read from robot control system;
303) dependent dynamics data are read from robot control system, mainly including motor torque, rotating speed;
304) temperature, the humidity of environment, the inclination angle of each joint arm, vibration data are read from external sensor.
Dynamic simulation is specially in 4th step:
401) the Real Time Kinematic data according to kinematics model 102) and 302), to the real time kinematics of industrial robot
Posture is emulated, and is showed the motion process of industrial robot in a manner of data-driven three-dimensional physical model;
402) according to dynamics data 303), the real-time torque state of each joint motor of industrial robot is replenished
401) on three-dimensional physical model.
Breakdown judge is specially in 5th step:
501) according to kinematics model 102) and kinematic data 302), by way of seeking Inverse Kinematics Solution, obtain
Obtain theory movement data corresponding to a certain particular moment each joint, including angle, angular speed, angular acceleration data.
502) according to kinetic model 103) and 501) the theory movement data in each joint, pass through demanded driving force and parse
The mode of solution obtains theoretical power data corresponding to each joint of a certain particular moment, including motor torque data.
503) by the way that theoretical analysis result and real-time monitoring result are compared, judge whether it breaks down;
If 504) currently have occurred and that failure, accident analysis is carried out, goes to the 6th step.
7th step is specially:
701) according to the possible cause that reasoning obtains in the 6th step, regulation and control instruction corresponding to generation, is sent to industry item by item
Robot controller, the people's motion of driving industrial machinery;
702) industrial robot trial operation situation is monitored, judges whether still failure;
If 703) still failure, illustrates failure caused by not being this kind of reason, the progress of the next item down failure cause is gone to
Confirm, until confirming specific failure cause;
If 704) normal operation, illustrate strictly failure caused by this kind of reason, terminate this diagnosis process, provide
Last diagnostic conclusion.
Compared with prior art, the present invention has advantages below:
(1) dynamic simulation proposed by the present invention is particularly suitable for being aided with software realization, can provide lively 3-D view.
In this way, software systems, when Fault Identification is carried out, operating personnel can intuitively supervise its operation.
(2) fault distinguishing method proposed by the present invention, existing data in control system are taken full advantage of, it is not necessary in addition
Increase other physical equipments, take full advantage of the design theory of equipment, there is simple and practical property.
(3) method proposed by the present invention that top-down successively reasoning is carried out by fault tree, is more suitable for industrial machine
The failure diagnostic process of this complex device of people, tends to draw more definite failure analysis result.
(4) it is proposed by the present invention according to possible failure cause, corresponding control instruction is generated and sent one by one, and monitoring is anti-
Feedforward information, the method for carrying out failure cause confirmation, substantially constitutes the closed loop of fault diagnosis, more meets regular job in logic
Custom, also more can simply and effectively confirm specific failure cause.
Brief description of the drawings
Fig. 1 is the industrial robot failure diagnosis method schematic flow sheet of the present invention;
Fig. 2 is the industrial robot manipulator PUMA560 structure and coordinate schematic diagram used in the embodiment of the present invention;
Fig. 3 is the industrial robot failure diagnosis method flow chart of the present invention;
Fig. 4 is the fault tree schematic diagram of the foundation of the present invention;
Fig. 5 is the dynamic simulation schematic diagram of the present invention;
Fig. 6 is the fault reasoning schematic diagram of the present invention;
Fig. 7 is that the failure regulation and control of the present invention further determine that the method schematic diagram of specific failure.
Embodiment
The present invention is described in detail with reference to the accompanying drawings and detailed description.The present embodiment is with the technology of the present invention side
Implemented premised on case, give detailed embodiment and specific operating process, but the present embodiment is only exemplarily
Present disclosure is explained, and it is not intended that limitation to protection scope of the present invention.
As shown in figure 1, the present embodiment is with a classical six degree of freedom series connection industrial robot manipulator as shown in Figure 2
PUMA560 (bibliography [1]:Publishing house of Cai Zixing, Xie Bin robotics [M] Tsing-Hua University, 2015.) exemplified by, illustrate this
The industrial robot failure diagnosis method of invention, dynamic simulation is carried out by the way of parameterized model, using based on parsing mould
The method of type carries out Fault Identification, the reasoning of possible breakdown reason is carried out using FTA, using the side regulated and controled one by one
Formula carries out the confirmation of specific failure cause.Specifically, flow as shown in Figure 3, comprises the following steps:
1. build the parametrization physical model of industrial robot.
PUMA560 link rod coordinate system (such as Fig. 4) is established, according to Three Dimensional Design Model, obtains CD data (such as table
1):
The PUMA560 of table 1 threedimensional model design parameter
Connecting rod i | αt-1/(°) | at-1/(m) | θt/(°) | dt/(m) | Range of variables |
1 | 0 | 0 | 90 | 0 | - 160~160 |
2 | -90 | 0 | 0 | 0.1491 | - 225~45 |
3 | 0 | 0.4318 | -90 | 0 | - 45~225 |
4 | -90 | -0.0203 | 0 | 0.4331 | - 110~170 |
5 | 90 | 0 | 0 | 0 | - 100~100 |
6 | -90 | 0 | 0 | 0 | - 266~266 |
Wherein, aiFor along xi, from ziIt is moved to zi+ 1 distance;αiFor around xi, from ziRotate to zi+ 1 angle; diFor edge
Zi, from xi- 1 is moved to xiDistance;θiFor around zi, from xi- 1 rotates to xiAngle.
Foundation D-H parametric methods, build the kinematics model of industrial robot, it is established that joint angles and end effector position
Relation between appearance.
0Ti=0T1(θ1)1T2(θ2)2T3(θ3)......i-1Ti(θi)
Wherein,i-1Ti(θi) be from coordinate system { i-1 } to { i } transformation matrix,0TiSeat for robot end to pedestal
Mark conversion.
According to dimensional parameters, mass parameter and inertia parameter, according to newton-Lagrangian method, industrial robot is built
Kinetic model, establish joint angles q, angular speedAngular acceleration(see reference relation between joint moment T document
[2]: Armstrong B,Khatib O,Burdick J.The explicit dynamic model and inertial
parameters of the PUMA 560 arm[C]//IEEE International Conference on Robotics
and Automation.Proceedings. IEEE,1986:It is 510-518) as follows:
Wherein, T is joint moment vector;A (q) is kinematics energy matrix, and B (q) is coriolis force matrix, and C (q) is inertia
Torque battle array, G (q) are gravity vector;Q is joint angles variable,For joint angular speed,For joint angular acceleration.
2. build the full failure tree-model of industrial robot.
From conventional fault diagnosis example and diagnostic experiences, refine and summarize fault diagnosis knowledge, build fault tree models.
First, it is basic machine failure, servo respectively by the failure of industrial robot from three parts are macroscopically divided into
The system failure and control system failure.
Then, will each part segment one by one, wherein, by servo-drive system failure be divided into motor do not turn, motor reversal, electricity
Machine rotary speed unstabilization is fixed and motor speed has the part of deviation four;Basic machine failure be divided into belt wheel failure, decelerator trouble and
Bearing fault;Control system failure is divided into initialization mistake, memory error, miscommunication and check errors.It is in this way, preliminary
Establish the fault tree models of robot.
Then, possible failure cause is obtained, such as causes motor not for each specific failure symptom, by analysis reasoning
The reason for turning is probably load excessive, power circuit exception phase shortage, power input exception or drive corruption failure.
According to theory analysis and the result of reasoning from logic, arrange supplement and improve fault tree models, it is established that industrial machine
The fault tree models (as shown in Figure 5) of people.
3. obtain the real-time running data of industrial robot.
1) PLC control instructions, supply voltage, current of electric are read from robot control system;
2) kinematic data (including joint angles, angular speed and angular acceleration) is read from robot control system;
3) dependent dynamics data (including motor torque, rotating speed) are read from robot control system;
4) temperature, the humidity of environment, the inclination angle of each joint arm, vibration data are read from external sensor.
4. the operation conditions of pair industrial robot carries out dynamic simulation.
The parametrization physical model for the industrial robot established according to the 1st step and the Real Time Kinematic data collected are right
The real time kinematics posture of industrial robot carries out dynamic simulation, to robot in a manner of data-driven parameterizes physical model
(Robot) motion process is showed (as shown in fig. 6, digitized representation joint sequence number in figure).
5. pair industrial robot carries out breakdown judge.
According to the kinematics model of industrial robot and the exercise data that collects, by way of seeking Inverse Kinematics Solution,
Obtain theory movement data (including angle, angular speed, angular acceleration) corresponding to particular moment each joint.
According to kinetic model and the theory movement data in each joint, spy is obtained by way of demanded driving force analytic solutions
Theoretical power data (motor torque) corresponding to each joint is carved in timing.
By the way that theoretical analysis result and Real-time Monitoring Data are compared, judge whether it breaks down.It is if current
Failure is had occurred and that, then goes to step 6 and carries out accident analysis.
As shown in fig. 7, the motor torque and rotary speed data collected is analyzed.By the actual speed and meter of motor
Obtained theoretical rotational speed compares, it can be determined that obtains current motor failure and belongs to any situation, if theoretical rotational speed is not
It is zero and actual speed is zero, then it is assumed that be that motor does not turn failure;, will be actual if actual speed and theoretical rotational speed have deviation
Rotating speed deviation is contrasted with speed tolerance, if deviation is smaller in the range of allowing, then it is assumed that belong to other failures,
If deviation is larger to exceed permissible range, then it is assumed that belonging to motor speed has deviation fault;If motor steering is opposite, then it is assumed that
It is motor reversal failure.According to the conclusion of breakdown judge, foundation step 6 can further confirm that the concrete reason of failure.
For motor torque failure, as shown in fig. 7, by motor angle, angular speed and angular acceleration binding kineticses model
Ideal torque is obtained, if there is deviation between ideal torque and motor actual torque, and deviation is then recognized in the range of allowing
To be other non-torque failure;Otherwise it is assumed that it is torque deviation failure.
6. the possible cause of combination failure tree-model reasoning trouble-shooting.
The progress of the node content of the failure symptom feature of industrial robot and fault tree is top-down, progressively refine ground
With with checking, until obtain failure generation all possible causes.
According to fault tree models as shown in Figure 5, one of servo-drive system failure symptom (motor does not turn) is analyzed.It is right
The reason for causing motor not turn, makes inferences, and can obtain four kinds of possible failure causes, including load excessive, circuit abnormality lack
Phase, abnormity of power supply, drive corruption.
7. reason carries out the concrete reason that diagnosis regulation and control confirm failure one by one.
All possible causes obtained according to fault tree reasoning, regulation and control instruction corresponding to generation, is sent to industrial machine item by item
Device people's controller, drive industrial robot motion.Industrial robot trial operation situation is monitored, is judged whether according to feedback information
Still failure.If still failure, illustrate failure caused by not being this kind of reason, go to a kind of lower failure cause and carry out really
Recognize, until confirming specific failure cause;If normal operation, illustrate strictly failure caused by this kind of reason, terminate this
Secondary diagnosis process, provides last diagnostic conclusion.
One of the reason for not turning for motor --- loading moment is excessive to carry out analysis regulation and control.First determining whether present load is
It is no to be more than nominal load, if present load is more than nominal load, the regulation and control prompting for reducing load is provided, if reducing load
Afterwards, failure symptom disappears, then explanation is caused by load excessive;If present load is already less than nominal load, and motor is former
Barrier symptom still has, then illustrates the reason for not being load excessive, carrying out the next item down reason according to fault tree, (circuit abnormality lacks
Phase) analysis and regulation and control.
Claims (7)
- A kind of 1. industrial robot failure diagnosis method, it is characterised in that:Comprise the following steps,The first step, build the parametrization physical model of industrial robot;Second step, build the full failure tree-model of industrial robot;3rd step, obtain the real-time running data of industrial robot;4th step, dynamic simulation is carried out to the real-time operating conditions of industrial robot;5th step, breakdown judge is carried out according to theoretical analysis result and actual monitoring result;6th step, according to fault tree models, fault reasoning is carried out, finds all possible causes for causing failure;Specially:The failure symptom feature of industrial robot is matched and verified with the content of each node of fault tree;Matching Direction to be top-down, progressively refine, until obtaining all possible causes of failure generation;7th step, all possible causes of failure are diagnosed one by one, regulation and control instruction corresponding to generation, driving robot fortune It is dynamic, failure cause is confirmed according to feedback information.
- A kind of 2. industrial robot failure diagnosis method according to claim 1, it is characterised in that:Work is built in the first step The detailed process of the parametrization physical model of industry robot is:101) by carrying out manual measurement to the mechanical structure of industrial robot, or according to design drawing or threedimensional model, directly Connect to obtain the physical parameter of industrial robot, including physical dimension and Mass Distribution, and by the way that inertia physical parameter is calculated;102) physical parameter according to 101), according to D-H parametric methods, the kinematics model of industrial robot is built, is established Play the relation between joint angles and end effector pose;103) size according to 101), quality and inertia parameter, according to newton-Lagrangian method, industrial robot is built Kinetic model, it is established that the relation between joint angles, angular speed, angular acceleration and joint moment.
- A kind of 3. industrial robot failure diagnosis method according to claim 1, it is characterised in that:Work is built in second step The detailed process of the full failure tree-model of industry robot is:201) from conventional fault diagnosis example and diagnostic experiences, extraction and summary fault diagnosis knowledge, robot is tentatively established Fault tree models;The fault diagnosis knowledge includes numbering, symptom, reason, position, significance level and the solution of failure;202) according to theory analysis and the result of reasoning from logic, the fault tree models in arranging supplement and improving 201), progressively build Erect complete fault tree models.
- A kind of 4. industrial robot failure diagnosis method according to claim 1, it is characterised in that:Described in 3rd step The real-time running data of industrial robot includes:PLC control instructions, supply voltage, current of electric;Joint angles, angular speed, angle Acceleration;Motor torque, rotating speed;Temperature, the humidity of environment, the inclination angle of each joint arm, vibration data.
- A kind of 5. industrial robot failure diagnosis method according to claim 1, it is characterised in that:Dynamically imitated in 4th step It is true to be specially:401) according to kinematics model and Real Time Kinematic data, the real time kinematics posture of industrial robot is emulated, with The mode of data-driven three-dimensional physical model is showed the motion process of industrial robot;402) according to dynamics data, the three dimensional physical mould that the real-time torque state of each joint motor of industrial robot is replenished In type.
- A kind of 6. industrial robot failure diagnosis method according to claim 1, it is characterised in that:Failure is sentenced in 5th step It is disconnected to be specially:501) according to kinematics model and kinematic data, by way of seeking Inverse Kinematics Solution, it is each to obtain a certain particular moment Theory movement data corresponding to joint, including angle, angular speed, angular acceleration data;502) according to kinetic model and the theory movement data in each joint, certain is obtained by way of demanded driving force analytic solutions Theoretical power data corresponding to one particular moment each joint, including motor torque data;503) by the way that theoretical analysis result and real-time monitoring result are compared, judge whether it breaks down;If 504) currently have occurred and that failure, go to the 6th step and carry out accident analysis.
- A kind of 7. industrial robot failure diagnosis method according to claim 1, it is characterised in that:7th step is specific For,701) according to all possible causes that reasoning obtains in the 6th step, regulation and control instruction corresponding to generation, is sent to industry item by item Robot controller, the people's motion of driving industrial machinery;702) industrial robot trial operation situation is monitored, judges whether still failure;If 703) still failure, illustrates failure caused by not being this kind of reason, goes to the next item down failure cause and confirmed, Until confirming specific failure cause;If 704) normal operation, illustrate strictly failure caused by this kind of reason, terminate this diagnosis process, provide final Diagnosis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710321410.XA CN107422718A (en) | 2017-05-09 | 2017-05-09 | A kind of industrial robot failure diagnosis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710321410.XA CN107422718A (en) | 2017-05-09 | 2017-05-09 | A kind of industrial robot failure diagnosis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107422718A true CN107422718A (en) | 2017-12-01 |
Family
ID=60425670
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710321410.XA Pending CN107422718A (en) | 2017-05-09 | 2017-05-09 | A kind of industrial robot failure diagnosis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107422718A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108615047A (en) * | 2018-03-23 | 2018-10-02 | 绍兴诺雷智信息科技有限公司 | The construction method of fault diagnosis knowledge model towards Wind turbines equipment |
CN108646680A (en) * | 2018-05-10 | 2018-10-12 | 广东赛诺梵信息技术有限公司 | A kind of industrial robot critical data application system |
CN109993318A (en) * | 2017-12-28 | 2019-07-09 | 中国船舶重工集团公司第七一一研究所 | The method and apparatus of the troubleshooting of marine diesel |
CN111086025A (en) * | 2019-12-25 | 2020-05-01 | 南京熊猫电子股份有限公司 | Multi-fault-cause diagnosis system and method applied to industrial robot |
CN111221307A (en) * | 2020-01-16 | 2020-06-02 | 佛山科学技术学院 | Industrial robot state evaluation method and system |
CN111283731A (en) * | 2020-03-17 | 2020-06-16 | 安徽智训机器人技术有限公司 | Industrial robot operation fault determination method and system |
CN111290347A (en) * | 2018-12-10 | 2020-06-16 | 北京京东尚科信息技术有限公司 | Monitoring method and system |
CN112045671A (en) * | 2019-06-06 | 2020-12-08 | 南京理工大学 | Universal mechanical arm motion state detection system |
CN116483054A (en) * | 2023-04-19 | 2023-07-25 | 广州市阳普机电工程有限公司 | Industrial robot running state monitoring and early warning system and method |
US11714702B1 (en) | 2022-02-10 | 2023-08-01 | International Business Machines Corporation | Device underperformance identification and solution |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1737423A (en) * | 2005-08-10 | 2006-02-22 | 东北大学 | Method and apparatus for realizing integration of fault-diagnosis and fault-tolerance for boiler sensor based on Internet |
CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
CN101630146A (en) * | 2009-07-30 | 2010-01-20 | 上海交通大学 | Simulation control system for remote tele-operation of lunar rover |
CN101657766A (en) * | 2007-04-13 | 2010-02-24 | 西门子共同研究公司 | Be used for the online fault detect of distributed factory control systems and avoid framework |
CN103926845A (en) * | 2014-04-17 | 2014-07-16 | 哈尔滨工业大学 | Ground-based simulation system for space robot visual servo to capture moving target and simulation method |
CN104267711A (en) * | 2014-11-03 | 2015-01-07 | 四川烟草工业有限责任公司 | Running state monitoring and failure diagnosis method for tobacco logistics system |
JP2015162090A (en) * | 2014-02-27 | 2015-09-07 | 三菱日立パワーシステムズ株式会社 | Fault diagnosis method and fault diagnosis apparatus |
CN105955719A (en) * | 2016-04-20 | 2016-09-21 | 北京航空航天大学 | Airborne safety-critical system security requirement tracking chain establishment and maintenance method |
-
2017
- 2017-05-09 CN CN201710321410.XA patent/CN107422718A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1737423A (en) * | 2005-08-10 | 2006-02-22 | 东北大学 | Method and apparatus for realizing integration of fault-diagnosis and fault-tolerance for boiler sensor based on Internet |
CN101657766A (en) * | 2007-04-13 | 2010-02-24 | 西门子共同研究公司 | Be used for the online fault detect of distributed factory control systems and avoid framework |
CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
CN101630146A (en) * | 2009-07-30 | 2010-01-20 | 上海交通大学 | Simulation control system for remote tele-operation of lunar rover |
JP2015162090A (en) * | 2014-02-27 | 2015-09-07 | 三菱日立パワーシステムズ株式会社 | Fault diagnosis method and fault diagnosis apparatus |
CN103926845A (en) * | 2014-04-17 | 2014-07-16 | 哈尔滨工业大学 | Ground-based simulation system for space robot visual servo to capture moving target and simulation method |
CN104267711A (en) * | 2014-11-03 | 2015-01-07 | 四川烟草工业有限责任公司 | Running state monitoring and failure diagnosis method for tobacco logistics system |
CN105955719A (en) * | 2016-04-20 | 2016-09-21 | 北京航空航天大学 | Airborne safety-critical system security requirement tracking chain establishment and maintenance method |
Non-Patent Citations (2)
Title |
---|
王盼: "基于模型的机械臂执行器故障诊断", 《知网硕士学位论文库》 * |
陈世健: "工业机器人状态监测与故障诊断系统的研究", 《道客巴巴》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993318A (en) * | 2017-12-28 | 2019-07-09 | 中国船舶重工集团公司第七一一研究所 | The method and apparatus of the troubleshooting of marine diesel |
CN108615047A (en) * | 2018-03-23 | 2018-10-02 | 绍兴诺雷智信息科技有限公司 | The construction method of fault diagnosis knowledge model towards Wind turbines equipment |
CN108615047B (en) * | 2018-03-23 | 2022-07-01 | 绍兴诺雷智信息科技有限公司 | Fault diagnosis knowledge model construction method for wind turbine generator equipment |
CN108646680A (en) * | 2018-05-10 | 2018-10-12 | 广东赛诺梵信息技术有限公司 | A kind of industrial robot critical data application system |
CN111290347A (en) * | 2018-12-10 | 2020-06-16 | 北京京东尚科信息技术有限公司 | Monitoring method and system |
CN112045671A (en) * | 2019-06-06 | 2020-12-08 | 南京理工大学 | Universal mechanical arm motion state detection system |
CN111086025A (en) * | 2019-12-25 | 2020-05-01 | 南京熊猫电子股份有限公司 | Multi-fault-cause diagnosis system and method applied to industrial robot |
CN111221307A (en) * | 2020-01-16 | 2020-06-02 | 佛山科学技术学院 | Industrial robot state evaluation method and system |
CN111221307B (en) * | 2020-01-16 | 2021-08-31 | 佛山科学技术学院 | Industrial robot state evaluation method and system |
CN111283731A (en) * | 2020-03-17 | 2020-06-16 | 安徽智训机器人技术有限公司 | Industrial robot operation fault determination method and system |
US11714702B1 (en) | 2022-02-10 | 2023-08-01 | International Business Machines Corporation | Device underperformance identification and solution |
CN116483054A (en) * | 2023-04-19 | 2023-07-25 | 广州市阳普机电工程有限公司 | Industrial robot running state monitoring and early warning system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107422718A (en) | A kind of industrial robot failure diagnosis method | |
CN109129574B (en) | Cloud fault diagnosis system and method for service robot motion system | |
CN110666800A (en) | Industrial robot with multithreading strategy demonstrator | |
CN105911863A (en) | Multi-robot cooperative clamping system neural network trajectory tracking control method | |
CN107614212A (en) | Industrial robot and its fault judgment method | |
Deters et al. | Accurate bolt tightening using model-free fuzzy control for wind turbine hub bearing assembly | |
CN106826819A (en) | Truss robot anticollision detection method and device | |
CN109459254A (en) | A kind of articulated robot dynamics semi-physical simulation platform | |
CN111823235A (en) | Collision detection method for picking mechanical arm | |
CN101745916A (en) | Parallel robot device with functions of fault tolerance and fault correction and fault tolerating and correcting method thereof | |
Antonya et al. | Co-simulation environment for the analysis of the driving simulator’s actuation | |
CN102568626B (en) | Remote monitoring and maintaining system based on mechanical arms | |
CN113221372B (en) | BDD-based industrial robot PMS system reliability analysis method | |
Yu et al. | Modelling and adaptive control of NAO robot arm | |
CN114367975A (en) | Verification system of series industrial robot control algorithm | |
Han et al. | Reconfigurable wireless control system for a dual-arm cooperative robotic system | |
Lu | Application of PLC control technology in intelligent automatic control | |
Zhang et al. | Design and development of a novel redundant and fault-tolerant actuator unit for heavy-duty parallel manipulators | |
Han et al. | Residual-Based Fault Detection of Abnormal Joint Running State of Industrial Collaborative Robot | |
CN112045671A (en) | Universal mechanical arm motion state detection system | |
Youchun et al. | Design of Multimodal Neural Network Control System for Mechanically Driven Reconfigurable Robot | |
Zhang et al. | Twin Tracking Method of Elevator Tractor Condition Based on Neural Network | |
Pascault | Finite-time tracking of trajectories in task space for stewart platform | |
CN113358350B (en) | RV reduction gear dust-resistant reliability testing device | |
Guo et al. | TFFC-RNN: A new RNN based approach for bearing and misalignment compound fault |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171201 |
|
WD01 | Invention patent application deemed withdrawn after publication |