CN110488608B - Intelligent kinetic parameter identification method and module for driving and controlling integrated control system - Google Patents
Intelligent kinetic parameter identification method and module for driving and controlling integrated control system Download PDFInfo
- Publication number
- CN110488608B CN110488608B CN201910751714.9A CN201910751714A CN110488608B CN 110488608 B CN110488608 B CN 110488608B CN 201910751714 A CN201910751714 A CN 201910751714A CN 110488608 B CN110488608 B CN 110488608B
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- parameter identification
- kinetic
- neural network
- 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.)
- Active
Links
Images
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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
An intelligent kinetic parameter identification method and a module for a driving and controlling integrated control system are disclosed, wherein the kinetic parameter identification method comprises the steps of S1, establishing a nominal model based on a Lagrange kinetic model; s2, establishing an actual dynamic model on the basis of the nominal model; s3, obtaining neural network training sample data; and S4, training the parameter identification neural network. The method has the advantages of simple modeling, high estimation precision and capability of identifying the parameters which cannot be modeled.
Description
Technical Field
The invention belongs to the field of cooperative robots, and particularly relates to an intelligent kinetic parameter identification method and module for a driving and controlling integrated control system.
Background
With the development of industrial automation technology, industrial robots play an important role in more and more production tasks, but limited by technical maturity and implementation cost, some complex operation tasks still need to be completed manually by people, thereby forcing the generation of cooperative robots capable of operating in a human-machine co-fusion environment. Compared with the traditional industrial robot, the cooperative robot does not need an independent isolation space, can cooperate closely with human beings to complete production tasks, for example, on the assembly line of 3C products, the human beings can complete complex assembly tasks, and the cooperative robot can rapidly and accurately complete part picking and placing tasks, so that the cooperative work division is greatly improved in production efficiency, and the production cost is reduced. In order to achieve the cooperation goal, a safe human-computer interaction environment needs to be ensured, and requirements on control of the cooperative robot in terms of accuracy and flexibility are far higher than those of a traditional robot. At present, industrial robots generally adopt a distributed control mode of a central motion controller and a plurality of servo drivers, and the mode is convenient in layout and simple in application. Most of the traditional industrial robots work in a position control mode, each joint utilizes a driver to realize accurate position loop PID control, and receives the instruction requirement of a motion controller through a bus. For a cooperative robot, complex algorithms such as feedforward control and compliance control need to be realized, a distributed architecture has the problems of limited signal transmission rate and a synchronization mechanism, and the real-time performance and the rapidity of the distributed architecture hardly meet the requirements of the cooperative robot. In order to solve the problem, a driving and controlling integrated controller for a cooperative robot is provided at present, and has the characteristics of compact structure, high response speed, high control precision, low cost and the like. However, the existing integrated control device still has the following problems in application: firstly, the algorithm implementation still needs a controller at an upper layer, which can generate the problems of data transmission, real-time performance and synchronization among different systems; secondly, most of the existing kinetic model parameter identification algorithms are realized by iterative estimation based on the traditional excitation track and least square method, the modeling is complex, the estimation precision is not high, and the parameters which can not be modeled can not be identified.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent kinetic parameter identification method and a module for a driving and controlling integrated control system, which have the advantages of simple modeling, high estimation precision and capability of identifying the parameters which cannot be modeled for the society.
The technical scheme of the invention is as follows: the intelligent kinetic parameter identification method for the driving and controlling integrated control system comprises the following steps:
s1, establishing a nominal model based on the Lagrangian dynamic model;
according to the motion state of the mechanical arm, the motion speed of any point on each connecting rod of the mechanical arm is obtained; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the lagrangian function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system:
wherein D (q) e Rn×nIs a symmetric positive definite inertia matrix;
is a matrix of Coriolis force and centrifugal force; g (q) ε R n×1Is a gravity term matrix;
q is the angular displacement vector of the joint of the mechanical arm,
The angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
S2, building an actual dynamic model based on the nominal model, where the above-built dynamic equation is the nominal model of the robot arm, and in the actual robot arm system, there are some parameters that are difficult to model, such as: friction, play, deformation, etc. Taking these factors into account, the actual kinetic equation of the actual kinetic model of the mechanical arm is:
in the above formula, F (q) represents the friction of the joint movement,
the disturbance in the motion of the robot arm is represented, and the disturbance comprises load variation, modeling error or/and electrical interference. The two parameters are difficult to establish through a theoretical model and need to be identified by a certain means.
S3, obtaining neural network training sample data, setting the mechanical arm to be in a torque working mode, selecting a smooth torque curve within a joint torque range [ min, max ] as the input of the mechanical arm, and obtaining the angular displacement, the angular speed and the angular acceleration of each joint by using the code disc of each joint. Setting sampling time as T in a sampling period T, and adopting N groups of torque; and taking the data of angular displacement, angular velocity and angular acceleration as one-time training sample data.
S4, training parameter identification neural network, obtaining theoretical output value from the torque tau (k) in the sample data through a nominal model
Combining the moments tau (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value
The difference between the actual output value and the identified output value is used to obtain the output error
Establishing a loss function of the parameter identification neural network by using the output error; and training the neural network by adopting an optimization strategy of self-learning evolution so as to complete the correction of the dynamic model.
The invention also provides an intelligent kinetic parameter identification module for the driving and controlling integrated control system, which comprises:
based on a nominal model (1) of a Lagrange dynamic model, solving the motion speed of any point on each connecting rod of the mechanical arm according to the motion state of the mechanical arm; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the Lagrange function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system;
The actual dynamic model (2) is used for establishing an actual dynamic model on the basis of the nominal model, and a preset parameter which is difficult to model is added from the actual use of the mechanical arm system to obtain an actual dynamic equation of the mechanical arm actual dynamic model;
the neural network training sample acquisition module (3) is used for acquiring neural network training sample data, setting the mechanical arm into a torque working mode, selecting a smooth torque curve in a range from minimum to maximum joint torque as the input of the mechanical arm, and acquiring the angular displacement, the angular speed and the angular acceleration of each joint by using a code disc of each joint; setting sampling time as (T) in a sampling period (T), and taking N groups of data containing torque, angular displacement, angular velocity and angular acceleration as one-time training sample data;
a parameter identification neural network training module (4) for training the parameter identification neural network and obtaining a theoretical output value from the torque tau (k) in the sample data through a nominal model
Combining the moments tau (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value 
The difference between the actual output value and the identification output value is obtained to obtain an output error
Establishing a loss function of the parameter identification neural network by using the output error; and training the neural network by adopting an optimization strategy of self-learning evolution so as to complete the correction of the dynamic model.
As an improvement to the present invention, the nominal kinetic equation is:
wherein D (q) ε Rn×nIs a symmetric and positive definite inertia matrix;
is a matrix of coriolis force and centrifugal force; g (q) ε Rn×lIs a gravity term matrix;
q is the angular displacement vector of the joint of the mechanical arm,
The angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
As an improvement to the present invention, the actual kinetic equation is:
in the above formula, F (q) represents the friction of the joint movement,
representing disturbances in the motion of the robot arm.
As an improvement to the invention, the disturbances include load variations, modeling errors or/and electrical disturbances.
As an improvement to the present invention, the parameters that are difficult to model include a friction parameter, a clearance parameter, or/and a deformation parameter of the robot arm.
The method has the advantages of simple modeling, high estimation precision and capability of identifying the parameters which cannot be modeled.
Drawings
FIG. 1 is a schematic block flow diagram of one embodiment of the method of the present invention.
Fig. 2 is a block diagram of an embodiment of the module of the present invention.
Detailed Description
Referring to fig. 1, fig. 1 discloses an intelligent kinetic parameter identification method for a control integrated control system, which includes the following steps:
s1, establishing a nominal model based on the Lagrangian dynamic model;
according to the motion state of the mechanical arm, the motion speed of any point on each connecting rod of the mechanical arm is obtained; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the lagrangian function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system:
wherein D (q) e Rn×nIs a symmetric positive definite inertia matrix;
is a matrix of Coriolis force and centrifugal force;
G(q)∈Rn×lis a gravity term matrix;
q is the angular displacement vector of the joint of the mechanical arm, 
The angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
S2, building an actual dynamic model based on the nominal model, where the above-built dynamic equation is the nominal model of the robot arm, and in the actual robot arm system, there are some parameters that are difficult to model, such as: friction, play, deformation, etc. Taking these factors into account, the actual kinetic equation of the actual kinetic model of the mechanical arm is:
in the above formula, F (q) represents the friction of the joint movement,
the disturbance in the motion of the robot arm is represented, and the disturbance comprises load variation, modeling error or/and electrical interference. The two parameters are difficult to establish through a theoretical model and need to be identified by a certain means.
S3, obtaining neural network training sample data, setting the mechanical arm to be in a torque working mode, selecting a smooth torque curve within a joint torque range [ min, max ] as the input of the mechanical arm, and obtaining the angular displacement, the angular speed and the angular acceleration of each joint by using the code disc of each joint. Setting sampling time as T in a sampling period T, and adopting N groups of torque; and taking the data of angular displacement, angular velocity and angular acceleration as one-time training sample data.
S4, training parameter identification neural network, obtaining theoretical output value from the torque tau (k) in the sample data through a nominal model
Combining the moments tau (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value
The difference between the actual output value and the identification output value is obtained to obtain an output error
Establishing a loss function of the parameter identification neural network by using the output error; and training the neural network by adopting an optimization strategy of self-learning evolution so as to complete the correction of the dynamic model.
Referring to fig. 2, the present invention further provides an intelligent kinetic parameter identification module for driving and controlling an integrated control system, including:
based on a nominal model (1) of a Lagrange dynamic model, solving the motion speed of any point on each connecting rod of the mechanical arm according to the motion state of the mechanical arm; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the Lagrange function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system;
The actual dynamic model (2) is used for establishing an actual dynamic model on the basis of the nominal model, and a preset parameter which is difficult to model is added from the actual use of the mechanical arm system to obtain an actual dynamic equation of the mechanical arm actual dynamic model;
the neural network training sample acquisition module (3) is used for acquiring neural network training sample data, setting the mechanical arm into a torque working mode, selecting a smooth torque curve in the range from the minimum to the maximum of joint torque as the input of the mechanical arm, and acquiring the angular displacement, the angular speed and the angular acceleration of each joint by using a code disc of each joint; setting sampling time as (T) in a sampling period (T), and taking N groups of data containing torque, angular displacement, angular velocity and angular acceleration as one-time training sample data;
a parameter identification neural network training module (4),
obtaining theoretical output value of torque tau (k) in sample data through nominal model
Combining the moments tau (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value
The difference between the actual output value and the identified output value is used to obtain the output error 
Establishing a loss function of the parameter identification neural network by using the output error; and training the neural network by adopting an optimization strategy of self-learning evolution so as to complete the correction of the dynamic model.
Preferably, the nominal kinetic equation is:
wherein D (q) e Rn×nIs a symmetric positive definite inertia matrix;
is a matrix of Coriolis force and centrifugal force; g (q) ε Rn×lIs a gravity term matrix;
q is joint angular displacement vector of mechanical armQuantity of,
The angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
Preferably, the actual kinetic equation is:
in the above formula, F (q) represents the friction of the joint movement,
representing disturbances in the motion of the robot arm.
Preferably, the disturbance includes load variation, modeling error, or/and electrical interference.
Preferably, the parameters difficult to model include a friction parameter, a clearance parameter, or/and a deformation parameter of the robot arm.
Claims (8)
1. An intelligent kinetic parameter identification method for a driving and controlling integrated control system is characterized by comprising the following steps:
s1, establishing a nominal model based on a Lagrange dynamic model, and obtaining the movement speed of any point on each connecting rod of the mechanical arm according to the movement state of the mechanical arm; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the Lagrange function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system;
S2, establishing an actual dynamic model on the basis of the nominal model, and adding preset parameters which are difficult to model from the actual use of the mechanical arm system to obtain an actual dynamic equation of the actual dynamic model of the mechanical arm; the parameters difficult to model comprise friction parameters, clearance parameters or/and deformation parameters of the mechanical arm;
s3, obtaining neural network training sample data, setting the mechanical arm to be in a torque working mode, selecting a smooth torque curve in a range from minimum to maximum of joint torque as input of the mechanical arm, and obtaining angular displacement, angular speed and angular acceleration of each joint by using code discs of each joint; setting sampling time as T in a sampling period T, and taking N groups of data containing moment, angular displacement, angular velocity and angular acceleration as one-time training sample data;
s4, training a parameter identification neural network, and obtaining a theoretical output value of the moment tau (k) in the sample data through a nominal model
Combining the moments τ (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value 
The difference between the actual output value and the identification output value is used to obtain an output error
Establishing a parameter identification loss function of the neural network by using the output error; training the neural network by adopting an optimization strategy of self-learning evolution so as to complete dynamicsAnd (5) modifying the model.
2. The intelligent kinetic parameter identification method for the drive-control integrated control system according to claim 1, characterized in that: the nominal kinetic equation is:
wherein D (q) e Rn×nIs a symmetric positive definite inertia matrix;
is a matrix of Coriolis force and centrifugal force; g (q) ε Rn×1Is a gravity term matrix;
q is the angular displacement vector of the joint of the mechanical arm,
Is the angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
3. The intelligent kinetic parameter identification method for the driving and controlling integrated control system according to claim 1 or 2, characterized in that: the actual kinetic equation is as follows:
in the above formula, F (q) represents the friction of the joint movement,
representing disturbances in the motion of the robot arm.
4. The intelligent kinetic parameter identification method for the drive-control integrated control system according to claim 3, characterized in that: the disturbances include load variations, modeling errors, or/and electrical disturbances.
5. An intelligent kinetic parameter identification module for a drive-control integrated control system, comprising:
based on a nominal model (1) of a Lagrange dynamic model, solving the motion speed of any point on each connecting rod of the mechanical arm according to the motion state of the mechanical arm; calculating the kinetic energy of each connecting rod of the mechanical arm in the motion process and the total kinetic energy of the motion of the whole mechanical arm; calculating potential energy of each connecting rod of the mechanical arm in the motion process and total potential energy of the whole mechanical arm relative to a reference potential energy surface in the motion process; constructing a Lagrange function of the mechanical arm system according to the obtained total kinetic energy and total potential energy of the mechanical arm; performing derivation operation on the Lagrange function obtained in the process to obtain a nominal kinetic equation of the mechanical arm system;
the actual dynamic model (2) is used for establishing an actual dynamic model on the basis of the nominal model, and from the actual use of the mechanical arm system, preset parameters which are difficult to model are added to obtain an actual dynamic equation of the mechanical arm actual dynamic model; the parameters difficult to model comprise friction parameters, clearance parameters or/and deformation parameters of the mechanical arm;
The neural network training sample acquisition module (3) is used for acquiring neural network training sample data, setting the mechanical arm into a torque working mode, selecting a smooth torque curve in a range from minimum to maximum joint torque as the input of the mechanical arm, and acquiring the angular displacement, the angular speed and the angular acceleration of each joint by using a code disc of each joint; setting sampling time as T in a sampling period T, and taking N groups of data containing moment, angular displacement, angular velocity and angular acceleration as one-time training sample data;
a parameter identification neural network training module (4) for obtaining a theoretical output value of the moment tau (k) in the sample data through a nominal model
Combining the moments τ (k) with the actual output values in the samples
Inputting the data into a parameter identification neural network to obtain an output correction value
The theoretical output value and the output correction value are combined to obtain an identification output value
Obtaining an output error by subtracting the actual output value from the identified output value
Establishing a parameter identification loss function of the neural network by using the output error; and training the neural network by adopting an optimization strategy of self-learning evolution so as to complete the correction of the dynamic model.
6. The intelligent kinetic parameter identification module for the control integrated control system according to claim 5, wherein the nominal kinetic equation is:
Wherein D (q) ε Rn×nIs a symmetric and positive definite inertia matrix;
is a matrix of coriolis force and centrifugal force; g (q) ε Rn×1Is a gravity term matrix;
q is the angular displacement vector of the joint of the mechanical arm,
Is the angular velocity vector of the mechanical arm,
Is the angular acceleration vector of the mechanical arm; tau epsilon to RnAnd controlling the moment vector for each joint of the mechanical arm.
7. The intelligent kinetic parameter identification module for the control integrated control system according to claim 5 or 6, wherein the actual kinetic equation is as follows:
in the above formula, F (q) represents the friction of the joint movement,
representing disturbances in the motion of the robot arm.
8. The intelligent kinetic parameter identification module for the drive and control integrated control system of claim 7, wherein the disturbance comprises load variation, modeling error or/and electrical interference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910751714.9A CN110488608B (en) | 2019-08-14 | 2019-08-14 | Intelligent kinetic parameter identification method and module for driving and controlling integrated control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910751714.9A CN110488608B (en) | 2019-08-14 | 2019-08-14 | Intelligent kinetic parameter identification method and module for driving and controlling integrated control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110488608A CN110488608A (en) | 2019-11-22 |
| CN110488608B true CN110488608B (en) | 2022-05-27 |
Family
ID=68551079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910751714.9A Active CN110488608B (en) | 2019-08-14 | 2019-08-14 | Intelligent kinetic parameter identification method and module for driving and controlling integrated control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110488608B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110062A (en) * | 2021-05-08 | 2021-07-13 | 湖南太观科技有限公司 | Robot control system based on deep physical network |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159084A (en) * | 2015-09-06 | 2015-12-16 | 台州学院 | Manipulator nerve network control system with interference observer and control method |
| CN105904461A (en) * | 2016-05-16 | 2016-08-31 | 西北工业大学 | Self-adaptive teleoperation control method for neural network based on radial basis function |
| CN107703756A (en) * | 2017-11-03 | 2018-02-16 | 广州视源电子科技股份有限公司 | Kinetic parameters discrimination method, device, computer equipment and storage medium |
| CN107984472A (en) * | 2017-11-13 | 2018-05-04 | 华南理工大学 | A kind of neural solver design method of change ginseng for redundant manipulator motion planning |
| CN108297093A (en) * | 2017-12-29 | 2018-07-20 | 中国海洋大学 | A kind of step identification method of Manipulator Dynamics parameter |
| CN108717492A (en) * | 2018-05-18 | 2018-10-30 | 浙江工业大学 | Manipulator Dynamic discrimination method based on improved artificial bee colony algorithm |
| CN109176525A (en) * | 2018-09-30 | 2019-01-11 | 上海神添实业有限公司 | A kind of mobile manipulator self-adaptation control method based on RBF |
| CN109676607A (en) * | 2018-12-30 | 2019-04-26 | 江苏集萃智能制造技术研究所有限公司 | A kind of zero-g control method of non-moment sensing |
| CN109702745A (en) * | 2019-01-18 | 2019-05-03 | 华南理工大学 | A kind of modeling method of joint of robot fluctuation moment of friction |
| CN109773794A (en) * | 2019-02-26 | 2019-05-21 | 浙江大学 | A kind of 6 axis Identification of Dynamic Parameters of Amanipulator method neural network based |
-
2019
- 2019-08-14 CN CN201910751714.9A patent/CN110488608B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159084A (en) * | 2015-09-06 | 2015-12-16 | 台州学院 | Manipulator nerve network control system with interference observer and control method |
| CN105904461A (en) * | 2016-05-16 | 2016-08-31 | 西北工业大学 | Self-adaptive teleoperation control method for neural network based on radial basis function |
| CN107703756A (en) * | 2017-11-03 | 2018-02-16 | 广州视源电子科技股份有限公司 | Kinetic parameters discrimination method, device, computer equipment and storage medium |
| CN107984472A (en) * | 2017-11-13 | 2018-05-04 | 华南理工大学 | A kind of neural solver design method of change ginseng for redundant manipulator motion planning |
| CN108297093A (en) * | 2017-12-29 | 2018-07-20 | 中国海洋大学 | A kind of step identification method of Manipulator Dynamics parameter |
| CN108717492A (en) * | 2018-05-18 | 2018-10-30 | 浙江工业大学 | Manipulator Dynamic discrimination method based on improved artificial bee colony algorithm |
| CN109176525A (en) * | 2018-09-30 | 2019-01-11 | 上海神添实业有限公司 | A kind of mobile manipulator self-adaptation control method based on RBF |
| CN109676607A (en) * | 2018-12-30 | 2019-04-26 | 江苏集萃智能制造技术研究所有限公司 | A kind of zero-g control method of non-moment sensing |
| CN109702745A (en) * | 2019-01-18 | 2019-05-03 | 华南理工大学 | A kind of modeling method of joint of robot fluctuation moment of friction |
| CN109773794A (en) * | 2019-02-26 | 2019-05-21 | 浙江大学 | A kind of 6 axis Identification of Dynamic Parameters of Amanipulator method neural network based |
Non-Patent Citations (3)
| Title |
|---|
| FRACTAL MODELLING FOR EMG PATTERN RECOGNITION VIA ARTIFICIAL NEURAL NETWORKS;M.E.Kirlangi等;《2000 IEEE International Conference on Acoustics,Speech,and Signal Processing》;20020806;第3610-3613页 * |
| 六自由度串联关节机器人惯性及摩擦参数辨识仿真;殷盛江;《中国优秀硕士学位论文全文数据库(信息科技辑)》;20160115(第1期);第I140-218页 * |
| 基于BP神经网络的机械臂轨迹控制研究;王頔等;《无线互联科技》;20160930(第18期);第106-109页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110488608A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111015649B (en) | Driving and controlling integrated control system | |
| CN110065070A (en) | A kind of robot adaptive impedance control system based on kinetic model | |
| CN108656112B (en) | Mechanical arm zero-force control experiment system for direct teaching | |
| CN109927032A (en) | A kind of mechanical arm Trajectory Tracking Control method based on High-Order Sliding Mode observer | |
| Duchaine et al. | Computationally efficient predictive robot control | |
| CN105479459A (en) | Zero-force control method and system for robot | |
| CN110394801B (en) | Joint control system of robot | |
| CN112276944A (en) | Man-machine cooperation system control method based on intention recognition | |
| CN109397265A (en) | A kind of joint type industrial robot dragging teaching method based on kinetic model | |
| CN111639749A (en) | Industrial robot friction force identification method based on deep learning | |
| CN103406909A (en) | Tracking control device and method of mechanical arm system | |
| CN111702767A (en) | Manipulator impedance control method based on inversion fuzzy self-adaptation | |
| CN107972036B (en) | Industrial robot dynamics control system and method based on TensorFlow | |
| CN110488608B (en) | Intelligent kinetic parameter identification method and module for driving and controlling integrated control system | |
| Jin et al. | Flexible actuator with variable stiffness and its decoupling control algorithm: Principle prototype design and experimental verification | |
| CN114750148A (en) | Force closed loop zero force control method and system for self-adaptive measurement of gravity | |
| Ren et al. | A novel neuro PID controller of remotely operated robotic manipulators | |
| CN113199477A (en) | Baxter mechanical arm track tracking control method based on reinforcement learning | |
| CN112643673A (en) | Mobile mechanical arm robust control method and system based on non-linear disturbance observer | |
| Nuritdinovich et al. | The concept of the mathematical description of the multi-coordinate mechatronic module of the robot | |
| CN202862218U (en) | Control system of mechanical arm | |
| Lesage et al. | Constructing Digital Twins for IEC61499 Based Distributed Control Systems | |
| CN113336092A (en) | Self-adaptive tracking control method for enhancing anti-swing performance of double-swing three-dimensional bridge crane | |
| CN114115252B (en) | Joint module robust control method based on inequality constraint | |
| Kastner et al. | Model-based control of a large-scale ball-on-plate system with experimental validation |
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 |