CN115741692A - High-precision control method and system for hydraulic mechanical arm based on data driving - Google Patents
High-precision control method and system for hydraulic mechanical arm based on data driving Download PDFInfo
- Publication number
- CN115741692A CN115741692A CN202211441323.5A CN202211441323A CN115741692A CN 115741692 A CN115741692 A CN 115741692A CN 202211441323 A CN202211441323 A CN 202211441323A CN 115741692 A CN115741692 A CN 115741692A
- Authority
- CN
- China
- Prior art keywords
- pid controller
- particle
- mechanical arm
- adaptive
- hydraulic mechanical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000002245 particle Substances 0.000 claims abstract description 164
- 230000003044 adaptive effect Effects 0.000 claims abstract description 70
- 238000005457 optimization Methods 0.000 claims abstract description 56
- 238000013507 mapping Methods 0.000 claims abstract description 36
- 230000006870 function Effects 0.000 claims description 31
- 230000000739 chaotic effect Effects 0.000 claims description 19
- 230000013016 learning Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000005728 strengthening Methods 0.000 claims description 4
- 230000002349 favourable effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000035772 mutation Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 230000009326 social learning Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000004200 deflagration Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000010720 hydraulic oil Substances 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention belongs to the field of hydraulic mechanical arm control, and provides a high-precision control method and a high-precision control system for a hydraulic mechanical arm based on data driving, wherein the method comprises the steps of obtaining the current joint angle and the expected joint angle of the hydraulic mechanical arm; based on the current joint angle of the hydraulic mechanical arm, eliminating the fluctuation of the joint angle error in the early tracking stage by using a differential tracker to obtain the filtered angle error; optimizing the control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm based on the filtered angle error to obtain the particle optimization control parameters of the PID controller; optimizing the particle optimization control parameters of the PID controller by using a fuzzy control algorithm according to the filtered angle error and the derivative of the filtered angle error to obtain the fuzzy optimization control parameters of the PID controller; and obtaining the optimal control parameter of the PID controller according to the sum of the particle optimization control parameter of the PID controller and the fuzzy optimization control layer parameter of the PID controller.
Description
Technical Field
The invention belongs to the technical field of hydraulic mechanical arm control, and particularly relates to a high-precision control method and system of a hydraulic mechanical arm based on data driving.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the development of computer technology and artificial intelligence, robots are used in many scenarios. The hydraulic driving mechanical arm is widely applied to various special operation fields such as rescue and emergency, military, agriculture, deep sea exploration and the like due to the advantages of large output torque, stable transmission, high control precision and the like. Aiming at petrochemical deflagration environment, the robot needs to complete emergency treatment operations such as valve closing and leakage stoppage, and in order to meet the operation task requirement of a non-structural object in a complex environment, the hydraulic drive mechanical arm needs to have fine operation capability.
The hydraulic drive robot is a typical electromechanical hydraulic system, and has high nonlinearity (friction, pressure flow of a valve, saturation, hysteresis nonlinearity and the like), parameter uncertainty (change of viscous friction and coulomb friction coefficient caused by abrasion or lubrication conditions, change of hydraulic oil elastic modulus caused by environmental change) and the like, so that the difficulty of accurate modeling of the hydraulic system is increased.
Disclosure of Invention
In order to solve the problems, the invention provides a high-precision control method and a high-precision control system for a hydraulic mechanical arm based on data driving.
According to some embodiments, a first aspect of the present invention provides a method for controlling a hydraulic mechanical arm with high precision based on data driving, which adopts the following technical solutions:
a high-precision control method of a hydraulic mechanical arm based on data driving comprises the following steps:
acquiring a current joint angle and an expected joint angle of the hydraulic mechanical arm;
based on the current joint angle of the hydraulic mechanical arm, a differential tracker is utilized to eliminate the fluctuation of joint angle errors in the early tracking stage;
determining control parameters of a PID controller by utilizing fuzzy control based on the current joint angle and the expected joint angle of the hydraulic mechanical arm after the error is eliminated;
optimizing the control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm to obtain the optimal control parameters of the PID controller;
and controlling the hydraulic mechanical arm to a desired joint angle based on the optimal control parameters of the PID controller.
Further, the optimizing the control parameters of the PID controller by using the Tent mapping-based adaptive elite strategy particle swarm optimization comprises the following steps:
taking control parameters of a PID controller as a particle swarm, initializing the particle swarm based on Tent chaos, and randomly generating positions of all particles;
calculating a fitness function value of each particle by selecting a fitness function;
generating a chaotic sequence by adopting a self-adaptive elite variation strategy, increasing the optimizing range of particles and obtaining elite particles;
for each particle, comparing the adaptive value with the adaptive value of the optimal position that the particle has undergone, and if the adaptive value is better than the adaptive value, taking the adaptive value as the current individual optimal position;
comparing the adaptive value of each particle with the adaptive value of the optimal position experienced by the whole particle swarm, and if the adaptive value is better than the adaptive value, taking the adaptive value as the optimal position of the current swarm;
updating the self-adaptive weight and the learning factor;
updating the speed and the position of the particle through the individual optimal position and the group optimal position;
if the termination condition is not met, returning to continue to calculate the fitness function value of each particle; otherwise, exiting the algorithm to obtain an optimal solution;
and determining the particle optimization control parameters of the PID controller based on the optimal solution.
Further, the generating of the chaotic sequence by the adaptive elite variation strategy to increase the particle optimization range and obtain the elite particles comprises:
using the gbest as population elite particles, and performing adaptive variation operation on the gbest in the population evolution process of each generation;
if the adaptive value of the new individual gbest after the variation is superior to the adaptive value of the original gbest, the gbest replaces the original gbest and participates in the new round of evolution process;
the new global optimum gbest will attract other particles during the subsequent evolution, thus helping the particles to jump out of the local optimum.
Further, the selection rule of the fitness function is:
and adopting an error absolute value time integral performance index as a minimum objective function for parameter selection.
Further, the initializing the particle swarm based on Tent chaos by taking the control parameters of the PID controller as the particle swarm and randomly generating the positions of all the particles comprises:
locate the particle at the position x i Each dimension x of k K =1, … n, mapped to [0,1 ] according to the following equation]At intervals
In the formula: [ ak, bk]Is a k-dimension variable x ik The domain of (3);
generating chaos sequence according to Tent mapping formula iteration M times
Mapping the points in the chaotic sequence back to the original space according to the following formula;
from these mixturesChaos sequence obtaining x i Chaos point sequence after Tent mapping:
further, the adaptive weight value is updated by using the following formula:
(1)ω min and ω max Is a preset minimum and maximum coefficient of inertia, ω min Take 0.4, omega max Taking 0.9;
(2)
the average fitness of all particles in the d iteration is obtained;
(3)
namely the minimum fitness of all particles in the d iteration;
(4) The smaller the fitness is, the closer the optimal solution is, and the local search is more needed at the moment; the larger the fitness, the farther away from the optimal solution, and then the global search is needed.
Further, an asynchronously varying learning factor is employed, c 1 、c 2 The formula is as follows:
in the formula, learning factor c 1 Linearly decreasing with increasing number of iterations, c 2 Linear increment, in the early stages of optimization, c 1 Larger, c 2 Smaller, is beneficial to strengthening the global search capability, and c is carried out at the later stage of optimization 2 Gradually increase, c 1 And the reduction is continuous, so that the convergence to the global optimal solution is facilitated.
According to some embodiments, a second aspect of the present invention provides a high-precision control system for a hydraulic mechanical arm based on data driving, which adopts the following technical solutions:
a high-precision control system of a hydraulic mechanical arm based on data driving comprises:
the data acquisition module is configured to acquire a current joint angle and an expected joint angle of the hydraulic mechanical arm;
the joint angle error filtering module is configured to eliminate the fluctuation of the joint angle error in the early tracking stage by using a differential tracker based on the current joint angle of the hydraulic mechanical arm;
a PID controller parameter determination module configured to determine a control parameter of a PID controller by using fuzzy control based on the current joint angle and the expected joint angle of the hydraulic mechanical arm after the error is eliminated;
the PID controller parameter optimization module is configured to optimize the control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm to obtain the optimal control parameters of the PID controller;
a hydraulic robotic arm control module configured to control the hydraulic robotic arm to a desired joint angle based on the optimal control parameters of the PID controller.
According to some embodiments, a third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps in a data-drive-based hydraulic robot high-precision control method according to the first aspect.
According to some embodiments, a fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of a method for high precision control of a hydraulic mechanical arm based on data drive according to the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, an improved particle swarm algorithm and a fuzzy control are adopted to optimize PID parameters and a differential tracker is combined for filtering, the method does not depend on a system accurate model, a complex control rate is not required to be designed, and a large amount of data is not required to be trained offline, so that the system has higher convergence speed, higher convergence precision and higher stability; the model-free controller based on data driving, which has the advantages of less required system model information, strong anti-interference capability and easy engineering realization, has important engineering significance.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a block diagram of a high-precision control system of a hydraulic mechanical arm based on data driving according to an embodiment of the invention;
FIG. 2 is a flow chart of a Tent mapping-based adaptive elitism strategy particle swarm algorithm according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the invention may be combined with each other without conflict.
Example one
As shown in fig. 1, the present embodiment provides a high-precision control method for a hydraulic mechanical arm based on data driving. In this embodiment, the method includes the steps of:
acquiring a current joint angle and an expected joint angle of the hydraulic mechanical arm;
based on the current joint angle of the hydraulic mechanical arm, eliminating the fluctuation of the joint angle error in the early tracking stage by using a differential tracker to obtain the filtered angle error;
optimizing the control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm based on the filtered angle error to obtain the particle optimization control parameters of the PID controller;
optimizing the particle optimization control parameters of the PID controller by using a fuzzy control algorithm according to the filtered angle error and the derivative of the filtered angle error to obtain the fuzzy optimization control parameters of the PID controller;
obtaining the optimal control parameter of the PID controller according to the sum of the particle optimization control parameter of the PID controller and the fuzzy optimization control layer parameter of the PID controller;
and controlling the hydraulic mechanical arm to a desired joint angle based on the optimal control parameters of the PID controller.
Specifically, the optimization of the control parameters of the PID controller by using the Tent mapping-based adaptive elite strategy particle swarm algorithm comprises the following steps:
taking the control parameters of the PID controller as a particle swarm, initializing the particle swarm based on Tent chaos, and randomly generating the positions and the speeds of all the particles;
calculating a fitness function value of each particle by selecting a fitness function;
generating a chaotic sequence by adopting a self-adaptive elite variation strategy, increasing the optimizing range of particles and obtaining elite particles;
for each particle, comparing the adaptive value with the adaptive value of the optimal position which the particle has undergone, and if the adaptive value is better than the adaptive value, taking the adaptive value as the current individual optimal position;
comparing the adaptive value of each particle with the adaptive value of the optimal position experienced by the whole particle swarm, and if the adaptive value is better than the adaptive value, taking the adaptive value as the optimal position of the current swarm;
updating the self-adaptive weight and the learning factor;
updating the speed and the position of the particles through the individual optimal position and the group optimal position;
if the termination condition is not met, returning to continue to calculate the fitness function value of each particle; otherwise, exiting the algorithm to obtain an optimal solution;
and determining the particle optimization control parameters of the PID controller based on the optimal solution.
Specifically, the generating of the chaotic sequence by adopting the adaptive elite variation strategy to increase the particle optimization range and obtain the elite particles comprises the following steps:
taking the gbest as population elite particles, and performing self-adaptive variation operation on the gbest in the population evolution process of each generation;
if the adaptive value of the new individual gbest after the variation is superior to the adaptive value of the original gbest, the gbest replaces the original gbest and participates in the new round of evolution process;
the new global optimum gbest will attract other particles during the subsequent evolution, thus helping the particles to jump out of the local optimum.
Specifically, the selection rule of the fitness function is:
and adopting an error absolute value time integral performance index as a minimum objective function for parameter selection.
Specifically, the initializing the particle swarm based on Tent chaos by taking the control parameters of the PID controller as the particle swarm, and randomly generating the positions of all the particles includes:
locate the particle at the position x i Each dimension x of (a) k K =1, … n, mapped to [0,1 ] according to the following equation]At intervals
In the formula: [ ak, bk]Is a k-dimension variable x ik The domain of (3);
generating chaos sequence according to Tent mapping formula iteration M times
Mapping the points in the chaotic sequence back to the original space according to the following formula;
deriving x from these chaotic sequences i Chaos point column after Tent mapping:
specifically, the adaptive weight value is updated by using the following formula:
(1)ω min and ω max Is a preset minimum and maximum coefficient of inertia, ω min Take 0.4, omega max Taking 0.9;
(2)
the average fitness of all particles in the d iteration is obtained;
(3)
i.e. all particles at the d-th iterationMinimum fitness;
(4) The smaller the fitness is, the closer the optimal solution is, and the local search is more needed at the moment; the larger the fitness, the farther away from the optimal solution, and then the global search is needed.
In particular, an asynchronously varying learning factor, c, is used 1 、c 2 The formula is as follows:
in the formula, learning factor c 1 Linearly decreasing with increasing number of iterations, c 2 Linear increment, in the early stages of optimization, c 1 Larger, c 2 Smaller, is beneficial to strengthening the global search capability, and c is carried out at the later stage of optimization 2 Gradually increase, c 1 And the reduction is continuous, so that the convergence to the global optimal solution is facilitated.
Specifically, the detailed process of the method according to this embodiment includes:
acquiring a current joint angle and an expected joint angle of the hydraulic mechanical arm;
based on the current joint angle of the hydraulic mechanical arm, eliminating the fluctuation of the joint angle error in the early tracking stage by using a differential tracker to obtain the filtered angle error;
the filtered angle error signal of the hydraulic mechanical arm provides input for an improved particle swarm parameter optimizing module, wherein the improved particle swarm algorithm is a self-adaptive elite strategy particle swarm algorithm based on Tent mapping, and optimized parameters kp ', ki ' and kd ' are output;
the filtered angle error signal of the hydraulic mechanical arm and the derivative of the signal are used as input to enter a fuzzy logic module, and optimized parameters kp ', ki ', kd ' are obtained through a fuzzy experience library;
adding the optimized parameters obtained by the improved particle swarm optimization module and the fuzzy logic module to obtain an optimal control parameter kp.ki.kd;
i.e., kp = kp ' + kp ", ki = ki ' + ki", kd = kd ' + kd ".
And controlling the hydraulic mechanical arm to a desired joint angle based on the optimal control parameters of the PID controller.
1. The self-adaptive elite strategy particle swarm algorithm based on Tent mapping comprises the following steps:
particle swarm optimization simulates birds in a flock of birds by designing a particle without mass, which has only two attributes: speed, which represents how fast the movement is, and position, which represents the direction of the movement. And each particle independently searches an optimal solution in a search space, records the optimal solution as a current individual extremum, shares the individual extremum with other particles in the whole particle swarm, finds the optimal individual extremum as a current global optimal solution of the whole particle swarm, and adjusts the speed and the position of each particle in the particle swarm according to the found current individual extremum and the current global optimal solution shared by the whole particle swarm.
v i ＝w×v i +c 1 ×rand()×(pbest i -x i )+c 2 ×rand()×(gbest i -x i )
x i ＝x i +v i
v i Is the velocity of the particle; random numbers with rand () between (0,1); x is the number of i The current position of the particle; w is an inertia factor, the value of the inertia factor is non-negative, the value of the inertia factor is large, the global optimizing capacity is strong, and the local optimizing capacity is weak; the value is small, the global optimization capability is weak, and the local optimization capability is strong; c. C 1 ，c 2 It is a learning factor related to the experience of the particle itself and the experience of the society (group) in its motion.
If c is 1 ＝0，c 2 Not equal to 0, the particles have no self experience, and only social experience is that the convergence speed is possibly very high, but when the problem of more complex processing is solved, the particles are easy to fall into a local optimal point;
if c is 1 ≠0，c 2 =0, then the particle has no information shared by the population, only experience of its own, one scale since the individuals have no interactionA population of m is equivalent to m individual particles and thus the probability of obtaining an optimal solution is very small.
If c is 1 ＝c 2 If the number is not more than 0, the particles do not have any empirical information, and the motion of the particle group is disordered.
In the particle swarm optimization algorithm, the inertia weight and the learning factor have important influence on the PSO algorithm, and the PSO algorithm embodies that the particles inherit the previous speed and capacity and directly influence the searching speed and the searching precision of the algorithm. Because the standard PSO algorithm is easy to mature early and oscillation phenomenon is generated near the global optimal solution generated in the later period of searching, and the like, the global searching capability is hoped to be enhanced in the early period and the local searching capability is hoped to be improved in the later period. According to the problems, a self-adaptive elite strategy particle swarm algorithm based on Tent mapping is provided.
The specific components of the Tent mapping-based adaptive elite strategy particle swarm algorithm will be described below.
First, in the initial stage of search, the present embodiment focuses on global search capability, and therefore it is desirable to expand the search range to traverse as many particles as possible, and thus chaotic mapping is introduced.
Tent chaos mapping:
the motion state with randomness obtained by a deterministic equation is generally called as chaos, and a variable presenting the chaos state is called as a chaos variable. Chaos is a relatively common phenomenon that exists in nonlinear systems. The change of a chaotic variable within a certain range has randomness, ergodicity and regularity. The characteristics of the chaotic variables are utilized to carry out optimization search, so that the algorithm can jump out of local optimization, the group diversity can be maintained, the global search optimization performance of the algorithm is improved, and different chaotic mapping operators have greater influence on the chaotic optimization process. The literature indicates that Tent mapping has better traversal uniformity than logistic mapping through comparison, and the chaos optimization method based on Tent mapping has higher optimization efficiency.
Tent mapping:
according to Tent mapping, the particles i generate chaotic point lists in the feasible domain according to the following steps:
(1) Locate the particle at the position x i Each dimension x of k K =1, … n, mapped to [0,1 ] according to the following equation]At intervals
In the formula: [ a ] A k ,b k ]Is a k-dimension variable x ik The domain of (2).
(2) Generating chaos sequence according to Tent mapping formula iteration M times
(3) The points in the chaotic sequence are mapped back to the original space according to the following formula
(4) The chaos point sequence of xi after Tent mapping can be obtained by the chaos sequences:
when f is larger than favg, the particle quality is poor, the global search capability and the social learning capability of the particle are enhanced, and the self-learning capability of the particle is reduced; when f is less than favg, the particle quality is good, the local search capability and the self-learning capability of the particle should be enhanced, the social learning capability of the particle is reduced, and the particle with good quality is protected. The algorithm is beneficial to searching for a global optimal solution, the particle convergence speed is improved, and the possibility of falling into local optimal is reduced.
In the middle stage of search, the local search capability is focused on, the convergence rate of particle search is accelerated, and therefore local particles with better performance are expected to be screened out quickly, and a self-adaptive elite variation strategy is introduced.
2. Adaptive elite variation strategy
To further reduce the likelihood of the particle becoming trapped in the local optimum, an adaptive elite variation strategy (AEM) was introduced to help the particle jump out of the local optimum. The AEM takes the gbest as a population elite particle, and performs adaptive mutation operation on the gbest in the population evolution process of each generation. If the adaptive value of the new individual (gbest) after the mutation is superior to the adaptive value of the original gbest, the gbest replaces the original gbest and participates in the new round of evolution process. The new global optimal individual gbest will attract other particles in the subsequent evolution process, thus helping the particles jump out of the local optimal bit. The AEM mutation operation is:
gbest * ＝gbest+F(xm)
wherein F (xm) is a variant perturbation function defined as
F(xm)＝arctan(xm)/Π+C
In the formula, xm is a variation seed generated by self-adaptation, C is an undetermined constant, and different variation constants are selected by self-adaptation along with different fitness standard deviations st, specifically:
wherein st is the standard deviation, f i Is the fitness value of the ith individual, f gbest Is g best And (4) adapting the value. When the population is more aggregated, i.e. f i →f gbest And in time, the smaller the value of st is, the smaller the distance between the characteristic individuals is, and thus the larger the value of C is, the larger the variation quantity of the corresponding F function is generated. Conversely, the smaller the value of C is, the smaller the variation obtained by the F function is.
The variable xm adaptively controls the size of the variation according to the following formula
Wherein j =1,2.., N is the dimension; lambda is the undetermined constant taken to be 10; t is the number of iterations, t max Is the maximum number of iterations; r (j) is the distance of all individual averages avgptest to gbest in the j dimension; r is max Is the maximum distance in each dimension.
r(j)＝|gbest(j)-avgpbest(j)|
Where pbest [ i ] [ j ] is the position of the ith particle in the jth dimension.
On one hand, the performance of the particles at the initial stage of population iteration is poor, and the variation value is large, so that enough disturbance can be caused to the population, and the solution space is expanded; but as the iteration progresses, the variance will gradually decrease, thereby ensuring that the problem smoothly converges to an optimal value. On the other hand, when the extreme values of the groups tend to be consistent (r is smaller), the self-adaptive variation obtains a larger variation value, and the searching capability of the algorithm is enhanced; on the contrary, when the group search is sufficient, the variance value is reduced to avoid the fluctuation of the optimal value, thereby accelerating the convergence speed of the algorithm.
According to the analysis, the gbest obtains a large variation amount through the disturbance function F at the initial stage of the algorithm, so that enough disturbance is caused to a search space, the global search capability of the algorithm is enhanced, and the variation rate is gradually reduced along with the deepening of iteration, so that the oscillation of the optimal solution is effectively avoided, and the convergence rate of the population is accelerated.
In the later stage of searching, the problem of local optimum is hopefully avoided, so that a self-adaptive weight and a linear learning factor are introduced to enable a particle swarm algorithm to be dynamically adjusted, and finally a global optimum solution is obtained.
3. Self-adaptive weight:
(1) wmin and wmax are preset minimum and maximum inertia coefficients, generally wmin is 0.4 and wmax is 0.9;
(2) favg is the average fitness of all particles in the d-th iteration;
(3)
namely the minimum fitness of all particles in the d iteration;
(4) The smaller the fitness is, the closer the optimal solution is, and the local search is more needed at the moment; the larger the fitness, the farther away from the optimal solution, and then the global search is needed.
4. Linear learning factor:
in the PSO algorithm, learning factors give the particles the ability to self-summarize and learn from globally optimal particles. Learning factors with asynchronous variation, c 1 、c 2 The formula is as follows:
as can be seen from the equation, the learning factor c 1 Linearly decreasing with increasing number of iterations, c 2 And linearly increasing. At the beginning of the optimization, c 1 Larger, c 2 Smaller, is beneficial to strengthening the global search capability, and c is carried out at the later stage of optimization 2 Gradually increase, c 1 And the reduction is continuous, so that the convergence to the global optimal solution is facilitated.
And finally, selecting a fitness function as an evaluation index of the Tent mapping-based adaptive elite strategy particle swarm algorithm.
5. Selecting a fitness function:
in order to prevent the control energy from being overlarge, a square term of control input is added into the objective function, and in order to avoid overshoot, a penalty function is adopted, namely once overshoot is generated, the overshoot is used as one item of an optimal index.
J＝∫(w 1 ×|e(t)|+w 2 ×u 2 (t)+w 4 ×|ey(t)|)dt+w 3 ×t u
e (t) is the systematic error, u (t) is the controller output, t u For the rise time, ey (t) = y (t) -y (t-1), y (t) is the controlled object output, w 1 ，w 2 ，w 3 ，w 4 Is a weight value, and w 4 ＞＞w 1 。
6. Integral flow of self-adaptive elite strategy particle swarm algorithm based on Tent mapping
1) Initializing a particle swarm based on Tent chaos, and randomly generating the positions and the speeds of all particles;
2) Calculating the fitness function value of each particle by reasonably selecting the fitness function;
3) Generating a chaotic sequence by adopting a self-adaptive elite variation strategy, increasing the optimizing range of particles and obtaining elite particles;
4) Comparing the adaptive value with the adaptive value of the optimal position which the particle has undergone, and if the adaptive value is better, taking the adaptive value as the current individual optimal position;
5) Comparing the adaptive value of each particle with the adaptive value of the optimal position experienced by the whole particle swarm, and if the adaptive value is better, taking the adaptive value as the optimal position of the current swarm;
6) Updating the self-adaptive weight and the learning factor according to a formula;
7) Updating the speed and the position of the particles through the individual optimal position and the group optimal position;
8) If the termination condition is not met (usually the preset maximum iteration number and the lower limit value of the adaptive value), returning to the step 2); otherwise, an algorithm is deduced to obtain an optimal solution.
2. TD differential tracker
In order to solve the shock caused by the sudden change of the initial signal, a differential tracker is added to eliminate the large fluctuation of ec (derivative of joint angle error, one of the input ends of fuzzy control) in the early stage of tracking, and the large fluctuation is regarded as noise elimination. The tracking differentiator avoids the problem that a classical differentiator has an amplifying effect on noise. The command signal can be tracked monotonically for a limited time using TD.
Second order differential tracker input x 1 A tracking signal being the input signal v; x is the number of 2 Is x 1 The differential signal of (a); h is a sampling period; r determines the tracking speed of the signal, called the speed factor; h is a total of 0 Filtering the noise of the signal, called filtering factor; fhan is the fastest synthesis function and serves to better arrange the transition of the reference signal so that overshoot does not occur.
3. Fuzzy control
1. Fuzzification interface
The deviation e and the deviation ec are selected as fuzzy linguistic variables. The actual basic arguments from e, ec are set to [ -30,30] and [ -50,50]. Selecting language variable values of e and ec: positive is PB, positive is PM, positive is PS, zero is Z, negative is NS, negative is NM, negative is NB, membership function of e and ec is triangle except NS and PB are Gaussian.
2. Rule base
(1) Kp accelerates the response speed of the system and improves the response precision of the system. The larger Kp is, the higher the response speed is, but overshoot is easy to generate, and the stability of the system is reduced; too short Kp can affect the dynamic characteristics and the adjustment precision of the system due to too long response time of the system.
(2) Ki eliminates the residual error of the system, and the larger the Ki is, the faster the error of the system is reduced. However, if Ki is too large, integral saturation phenomenon can be generated at the initial stage of the response process, so that large overshoot is caused; if Ki is too small, the system error is difficult to eliminate, and the system adjustment precision is influenced.
(3) Kd predicts the trend of error change, avoids the serious overshoot of the controlled quantity, and can improve the dynamic characteristic of the system for the controlled object with larger inertia or lag. However, too large Kd will prolong the conditioning time and reduce the interference immunity of the system.
3. Fuzzy inference
The conclusion of fuzzy reasoning mainly depends on fuzzy implication relation
And a synthetic algorithm between the fuzzy relation and the fuzzy set, wherein the fuzzy implication relation is generally determined for a determined fuzzy inference system, the synthetic algorithm is not unique, and the Mamdani fuzzy inference method is the most commonly used inference method.
4. Defuzzification
The gravity center method comprises the following steps:
4. PID controller controls mechanical arm
And controlling the hydraulic mechanical arm to operate to the expected joint angle according to the optimized optimal control parameter of the PID controller.
Example two
The embodiment provides a hydraulic mechanical arm high accuracy control system based on data drive, includes:
the data acquisition module is configured to acquire a current joint angle and an expected joint angle of the hydraulic mechanical arm;
the joint angle error filtering module is configured to eliminate the fluctuation of the joint angle error in the early stage of tracking by using a differential tracker based on the current joint angle of the hydraulic mechanical arm to obtain a filtered angle error;
the PID controller particle optimization module is configured to optimize control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm based on the filtered angle error to obtain particle optimization control parameters of the PID controller;
the PID controller fuzzy optimization module is configured to optimize the particle optimization control parameters of the PID controller by using a fuzzy control algorithm according to the filtered angle error and the derivative of the filtered angle error to obtain the fuzzy optimization control parameters of the PID controller;
the PID controller optimal parameter determination module is configured to obtain the optimal control parameter of the PID controller according to the sum of the particle optimization control parameter of the PID controller and the fuzzy optimization control layer parameter of the PID controller;
a hydraulic robotic arm control module configured to control the hydraulic robotic arm to a desired joint angle based on the optimal control parameters of the PID controller.
The modules are the same as the corresponding steps in the implementation examples and application scenarios, but are not limited to the disclosure of the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical functional division, and in actual implementation, there may be another division, for example, a plurality of modules may be combined or may be integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps in a data-drive-based hydraulic robot high-precision control method as described in the first embodiment above.
Example four
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps in the method for controlling the hydraulic mechanical arm based on the data drive based on the high precision as the embodiment one.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive changes in the technical solutions of the present invention.
Claims (10)
1. A high-precision control method of a hydraulic mechanical arm based on data driving is characterized by comprising the following steps:
acquiring a current joint angle and an expected joint angle of the hydraulic mechanical arm;
based on the current joint angle of the hydraulic mechanical arm, eliminating the fluctuation of the joint angle error in the early tracking stage by using a differential tracker to obtain the filtered angle error;
optimizing the control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm based on the filtered angle error to obtain the particle optimization control parameters of the PID controller;
optimizing the particle optimization control parameters of the PID controller by using a fuzzy control algorithm according to the filtered angle error and the derivative of the filtered angle error to obtain the fuzzy optimization control parameters of the PID controller;
obtaining the optimal control parameter of the PID controller according to the sum of the particle optimization control parameter of the PID controller and the fuzzy optimization control layer parameter of the PID controller;
and controlling the hydraulic mechanical arm to a desired joint angle based on the optimal control parameters of the PID controller.
2. The high-precision control method for the hydraulic mechanical arm based on the data driving as claimed in claim 1, wherein the optimizing the control parameters of the PID controller by using the Tent mapping based adaptive elite strategy particle swarm algorithm comprises:
taking the control parameters of the PID controller as a particle swarm, initializing the particle swarm based on Tent chaos, and randomly generating the positions of all particles;
calculating a fitness function value of each particle by selecting a fitness function;
generating a chaotic sequence by adopting a self-adaptive elite variation strategy, increasing the optimizing range of particles and obtaining elite particles;
for each particle, comparing the adaptive value with the adaptive value of the optimal position which the particle has undergone, and if the adaptive value is better than the adaptive value, taking the adaptive value as the current individual optimal position;
comparing the adaptive value of each particle with the adaptive value of the optimal position experienced by the whole particle swarm, and if the adaptive value is better than the adaptive value, taking the adaptive value as the optimal position of the current swarm;
updating the self-adaptive weight and the learning factor;
updating the speed and the position of the particle through the individual optimal position and the group optimal position;
if the termination condition is not met, returning to continue to calculate the fitness function value of each particle; otherwise, exiting the algorithm to obtain an optimal solution;
and determining the particle optimization control parameters of the PID controller based on the optimal solution.
3. The method for controlling the hydraulic mechanical arm with high precision based on data driving as claimed in claim 2, wherein the generating of the chaotic sequence by the adaptive elite variation strategy to increase the particle optimizing range and obtain the elite particles comprises:
taking the gbest as population elite particles, and performing self-adaptive variation operation on the gbest in the population evolution process of each generation;
if the adaptive value of the new individual gbest after the variation is superior to the adaptive value of the original gbest, the gbest replaces the original gbest and participates in the new round of evolution process;
the new global optimum gbest will attract other particles during the subsequent evolution, thus helping the particles to jump out of the local optimum.
4. The method for controlling the hydraulic mechanical arm with high precision based on the data driving as claimed in claim 2, wherein the selection rule of the fitness function is as follows:
and adopting an error absolute value time integral performance index as a minimum objective function for parameter selection.
5. The method for controlling the hydraulic mechanical arm with high precision based on data driving as claimed in claim 2, wherein the taking the control parameters of the PID controller as a particle swarm, initializing the particle swarm based on Tent chaos, and randomly generating the positions of all the particles comprises:
locate the particle at the position x i Each dimension x of (a) k K =1, … n, mapped to [0,1 ] according to the following equation]At intervals
In the formula: [ ak, bk]Is a k-dimension variable x ik The domain of (3);
generating chaos sequence according to Tent mapping formula iteration M times
Mapping the points in the chaotic sequence back to the original space according to the following formula;
deriving x from these chaotic sequences i Chaos point column after Tent mapping:
6. the method for controlling the hydraulic mechanical arm based on data driving according to claim 2, wherein the adaptive weight updating adopts the following formula:
(1)ω min and ω max Is a preset minimum and maximum coefficient of inertia, ω min Take 0.4, omega max Taking 0.9;
(2)
the average fitness of all particles in the d iteration is obtained;
(3)
namely the minimum fitness of all particles in the d iteration;
(4) The smaller the fitness is, the closer the optimal solution is, and the local search is more needed at the moment; the larger the fitness, the farther away from the optimal solution, and then the global search is needed.
7. The method for controlling the hydraulic mechanical arm with high precision based on the data driving as claimed in claim 2, characterized in that an asynchronously changed learning factor, c, is adopted 1 、c 2 The formula is as follows:
in the formula, learning factor c 1 Linearly decreasing with increasing number of iterations, c 2 Linear increment, in the early stages of optimization, c 1 Larger, c 2 Small, is favorable for strengthening global search capability, and c is carried out at the later stage of optimization 2 Gradually increase, c 1 And the reduction is continuous, so that the convergence to the global optimal solution is facilitated.
8. A hydraulic mechanical arm high-precision control system based on data driving is characterized by comprising:
the data acquisition module is configured to acquire a current joint angle and an expected joint angle of the hydraulic mechanical arm;
the joint angle error filtering module is configured to eliminate the fluctuation of the joint angle error in the early stage of tracking by using a differential tracker based on the current joint angle of the hydraulic mechanical arm to obtain a filtered angle error;
the PID controller particle optimization module is configured to optimize control parameters of the PID controller by using a Tent mapping-based adaptive elite strategy particle swarm algorithm based on the filtered angle error to obtain particle optimization control parameters of the PID controller;
the PID controller fuzzy optimization module is configured to optimize the particle optimization control parameters of the PID controller by using a fuzzy control algorithm according to the filtered angle error and the derivative of the filtered angle error to obtain the fuzzy optimization control parameters of the PID controller;
the PID controller optimal parameter determination module is configured to obtain the optimal control parameter of the PID controller according to the sum of the particle optimization control parameter of the PID controller and the fuzzy optimization control layer parameter of the PID controller;
a hydraulic robotic arm control module configured to control the hydraulic robotic arm to a desired joint angle based on the optimal control parameters of the PID controller.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of a method for high-precision control of a hydraulic manipulator based on data actuation according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of a method for high precision control of a hydraulic mechanical arm based on data actuation according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441323.5A CN115741692A (en) | 2022-11-17 | 2022-11-17 | High-precision control method and system for hydraulic mechanical arm based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441323.5A CN115741692A (en) | 2022-11-17 | 2022-11-17 | High-precision control method and system for hydraulic mechanical arm based on data driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115741692A true CN115741692A (en) | 2023-03-07 |
Family
ID=85372786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211441323.5A Pending CN115741692A (en) | 2022-11-17 | 2022-11-17 | High-precision control method and system for hydraulic mechanical arm based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115741692A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117506936A (en) * | 2024-01-04 | 2024-02-06 | 唐山先坤工业机器人有限公司 | Mechanical arm control method and master-slave control system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257569A1 (en) * | 2013-03-11 | 2014-09-11 | Board Of Trustees Of The Leland Stanford Junior University | Model-less control for flexible manipulators |
| CN109947124A (en) * | 2019-04-25 | 2019-06-28 | 南京航空航天大学 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
| CN110450156A (en) * | 2019-07-30 | 2019-11-15 | 洛阳润信机械制造有限公司 | The optimum design method of multi-freedom Mechanism adaptive fuzzy controller |
| CN111129548A (en) * | 2019-12-27 | 2020-05-08 | 南京航空航天大学 | Improved particle swarm optimization fuzzy PID fuel cell temperature control method |
| CN111261909A (en) * | 2020-01-15 | 2020-06-09 | 武汉理工大学 | Maximum net power tracking control device and method for fuel cell system |
| CN114670207A (en) * | 2022-05-09 | 2022-06-28 | 山东大学 | Mechanical arm compliance control method and system based on wild dog optimization algorithm |
| CN114865952A (en) * | 2022-06-07 | 2022-08-05 | 长春工业大学 | Multi-motor synchronous control method for mechanical arm |
-
2022
- 2022-11-17 CN CN202211441323.5A patent/CN115741692A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257569A1 (en) * | 2013-03-11 | 2014-09-11 | Board Of Trustees Of The Leland Stanford Junior University | Model-less control for flexible manipulators |
| CN109947124A (en) * | 2019-04-25 | 2019-06-28 | 南京航空航天大学 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
| CN110450156A (en) * | 2019-07-30 | 2019-11-15 | 洛阳润信机械制造有限公司 | The optimum design method of multi-freedom Mechanism adaptive fuzzy controller |
| CN111129548A (en) * | 2019-12-27 | 2020-05-08 | 南京航空航天大学 | Improved particle swarm optimization fuzzy PID fuel cell temperature control method |
| CN111261909A (en) * | 2020-01-15 | 2020-06-09 | 武汉理工大学 | Maximum net power tracking control device and method for fuel cell system |
| CN114670207A (en) * | 2022-05-09 | 2022-06-28 | 山东大学 | Mechanical arm compliance control method and system based on wild dog optimization algorithm |
| CN114865952A (en) * | 2022-06-07 | 2022-08-05 | 长春工业大学 | Multi-motor synchronous control method for mechanical arm |
Non-Patent Citations (1)
| Title |
|---|
| 赵俊;陈建军;: "混沌粒子群优化的模糊神经PID控制器设计", 西安电子科技大学学报, no. 01, 15 February 2008 (2008-02-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117506936A (en) * | 2024-01-04 | 2024-02-06 | 唐山先坤工业机器人有限公司 | Mechanical arm control method and master-slave control system |
| CN117506936B (en) * | 2024-01-04 | 2024-03-08 | 唐山先坤工业机器人有限公司 | Mechanical arm control method and master-slave control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pugh et al. | Discrete multi-valued particle swarm optimization | |
| Kubalík et al. | Symbolic regression methods for reinforcement learning | |
| Lin et al. | Observer-based indirect adaptive fuzzy-neural tracking control for nonlinear SISO systems using VSS and H∞ approaches | |
| Jacobsen | A generic architecture for hybrid intelligent systems | |
| CN113093526B (en) | Overshoot-free PID controller parameter setting method based on reinforcement learning | |
| CN115741692A (en) | High-precision control method and system for hydraulic mechanical arm based on data driving | |
| CN110389556A (en) | Control device and control method | |
| Zebin et al. | Dynamic modeling and fuzzy logic control of a two-link flexible manipulator using genetic optimization techniques | |
| Udawatta et al. | Fuzzy-chaos hybrid controller for controlling of nonlinear systems | |
| Subudhi et al. | Fuzzy and neuro-fuzzy approaches to control a flexible single-link manipulator | |
| Shelton et al. | Controlling a truck with an adaptive critic CMAC design | |
| Yang et al. | Self-evolving data cloud-based PID-like controller for nonlinear uncertain systems | |
| Williams et al. | Locally weighted regression pseudo-rehearsal for adaptive model predictive control | |
| Ravari et al. | A novel hybrid Fuzzy-PID controller for tracking control of robot manipulators | |
| Ursu et al. | Artificial intelligence based synthesis of semiactive suspension systems | |
| Maity et al. | Stable optimal self-tuning interval type-2 fuzzy controller for servo position control system | |
| Abdelhedi et al. | Nonlinear PID and feedforward control of robotic manipulators | |
| Dao et al. | New hybrid SPEA/R-deep learning to predict optimization parameters of cascade FOPID controller according engine speed in powertrain mount system control of half-car dynamic model | |
| Arsene et al. | Control of autonomous robots using fuzzy logic controllers tuned by genetic algorithms | |
| Shern et al. | Performance analysis of position tracking control with PID Controller using an Improved Optimization Technique | |
| Soltanpour et al. | Optimal adaptive fuzzy integral sliding model control for electrically driven SCARA robot manipulator | |
| Tavakolpour-Saleh et al. | Iterative learning control of two coupled nonlinear spherical tanks | |
| Ravichandran et al. | Knowledge based approach for online self-tuning of PID-control | |
| Prabu et al. | Dynamic control of three-link SCARA manipulator using adaptive neuro fuzzy inference system | |
| Hackett et al. | Locomotion as a risk-mitigating behavior in uncertain environments: A rapid planning and few-shot failure adaptation approach |
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 |