A Robot Self-learning Grasping Control Method Based on Gaussian Process and Bayesian Algorithm

2018 ◽  
pp. 79-98
Author(s):  
Yong Tao ◽  
Hui Liu ◽  
Xianling Deng ◽  
Youdong Chen ◽  
Hegen Xiong ◽  
...  
Keyword(s):  
Gaussian Process ◽  
Control Method ◽  
Bayesian Algorithm ◽  
Self Learning

scholarly journals Novel Intelligent and Sensorless Proportional Valve Control with Self-Learning Ability

2016 ◽  
Vol 2016 ◽  
pp. 1-6
Author(s):  
Bayram Akdemir
Keyword(s):  
Pulse Width ◽  
Pulse Width Modulation ◽  
Control Method ◽  
Low Voltage ◽  
Control Unit ◽  
Control Signal ◽  
Learning Ability ◽  
Learning Abilities ◽  
Valve Control ◽  
Self Learning

Linear control is widely used for any fluid or air flows in many automobile, robotics, and hydraulics applications. According to signal level, valve can be controlled linearly. But, for many valves, hydraulics or air is not easy to control proportionally because of flows dynamics. As a conventional solution, electronic driver has up and down limits. After manually settling up and down limits, control unit has proportional blind behavior between two points. This study offers a novel valve control method merging pulse width and amplitude modulation in the same structure. Proposed method uses low voltage AC signal to understand the valve position and uses pulse width modulation for power transfer to coil. DC level leads to controlling the valve and AC signal gives feedback related to core moving. Any amplitude demodulator gives core position as voltage. Control unit makes reconstruction using start and end points to obtain linearization at zero control signal and maximum control signal matched to minimum demodulated amplitude level. Proposed method includes self-learning abilities to keep controlling in hard environmental conditions such as dust, temperature, and corrosion. Thus, self-learning helps to provide precision control for hard conditions.

A self-learning propotional–integral–derivative control of grouting pressure using the back-propagation model

2018 ◽  
Vol 232 (8) ◽  
pp. 1090-1099
Author(s):  
Fengling Li ◽  
Zhixiang Hou ◽  
Juan Chen
Keyword(s):  
Control Method ◽  
Tracking Error ◽  
Back Propagation ◽  
Propagation Model ◽  
Test Method ◽  
Iteration Algorithm ◽  
Grouting Pressure ◽  
Geological Conditions ◽  
Self Learning ◽  
Derivative Control

For the security of grouting process of dam foundation, grouting pressure control is one of the most important problems. In order to avoid dangerous grouting pressure fluctuation and improve the control precision, a feedback propotional–integral–derivative control method was presented for the whole grouting system. Because the grouting pressure is affected by many factors such as grouting flow, grouts density, and geological conditions, the parameters of propotional–integral–derivative must be tuned. In this article, the adaptive tuning method is presented. The back-propagation artificial neural networks model was proposed to simulate the grouting control process, and sensitivity analysis algorithm based on orthogonal test method was adopted for the selection of input variables. To obtain the optimal propotional–integral–derivative parameters, an iteration algorithm was used in each sampling interval time and the discrete Lyapunov function of the tracking error. The simulation results showed that self-learning propotional–integral–derivative tuning was robust and effective for the realization of the automatic control device in the grouting process.

Design of Neural Network Controller for Space Robot with Flexible Manipulators

2013 ◽  
Vol 394 ◽  
pp. 393-397
Author(s):  
Jing Ma ◽  
Wen Hui Zhang ◽  
Zhi Hua Zhu
Keyword(s):  
Neural Network ◽  
Pid Control ◽  
Control Method ◽  
System Optimization ◽  
Space Robot ◽  
Learning Ability ◽  
Flexible Manipulators ◽  
Neural Network Controller ◽  
Non Linear System ◽  
Self Learning

Neural network self-learning optimization PID control algorithm is put forward for free-floating space robot with flexible manipulators. Firstly, dynamics model of space flexible robot is established, then, neural network with good learning ability is used to approach non-linear system. Optimization algorithm of network weights is designed to speed up the learning speed and the adjustment velocity. Error function is offered by PID controller. The neural network self-learning PID control method can improve the control precision.

Self-learning control for coordinated collision avoidance of automated vehicles

2019 ◽  
pp. 095440701988788
Author(s):  
Yan Wang ◽  
Guodong Yin ◽  
Yanjun Li ◽  
Saif Ullah ◽  
Weichao Zhuang ◽  
...  
Keyword(s):  
Collision Avoidance ◽  
Control Method ◽  
Learning Control ◽  
Traffic Information ◽  
Steering Control ◽  
Control Effect ◽  
Driving Experience ◽  
Collision Avoidance Control ◽  
Avoidance Control ◽  
Self Learning

For the improvement of automotive active safety and the reduction of traffic collisions, significant efforts have been made on developing a vehicle coordinated collision avoidance system. However, the majority of the current solutions can only work in simple driving conditions, and cannot be dynamically optimized as the driving experience grows. In this study, a novel self-learning control framework for coordinated collision avoidance is proposed to address these gaps. First, a dynamic decision model is designed to provide initial braking and steering control inputs based on real-time traffic information. Then, a multilayer artificial neural networks controller is developed to optimize the braking and steering control inputs. Next, a proportional–integral–derivative feedback controller is used to track the optimized control inputs. The effectiveness of the proposed self-learning control method is evaluated using hardware-in-the-loop tests in different scenarios. Experimental results indicate that the proposed method can provide good collision avoidance control effect. Furthermore, vehicle stability during the coordinated collision avoidance control can be gradually improved by the self-learning method as the driving experience grows.

Application of Single Neuron Adaptive PID Controller in Flow Control System

2014 ◽  
Vol 602-605 ◽  
pp. 1052-1055 ◽  
Author(s):  
Ze Kang ◽  
Cheng Qiang Yin ◽  
Shao Min Teng
Keyword(s):  
Control System ◽  
Flow Control ◽  
Pid Controller ◽  
Single Neuron ◽  
Control Method ◽  
Dynamic Performance ◽  
Oxide Concentration ◽  
Flow Control System ◽  
Self Learning

Oxide concentration at reactor inlet is one of the most important factor effecting the quality of ethylene oxide concentration. A control method with adaptive PID of single neuron is propose using the parameter self-learning with adaptive PID controller of single neuron for the oxide flow control system. The simulation results show that this design scheme has a better dynamic performance than traditional PID scheme to verify the feasibility of this method.

Research on pH Value for City Sewage Optimized Control Based on HDP

2013 ◽  
Vol 706-708 ◽  
pp. 976-980
Author(s):  
Sheng Yong Lei
Keyword(s):  
Treatment Process ◽  
Control Method ◽  
Ph Value ◽  
Sewage Treatment ◽  
Response Speed ◽  
Learning System ◽  
System Control ◽  
Action Model ◽  
The City ◽  
Self Learning

During the city sewage treatment process, pH value has the nonlinear control characteristics of pure lag, large inertia and so on. This paper presents the adaptive system control method based on HDP (heuristic dynamic programming) in view of the above features. Three neural networks which are action, model and critic constitute a self-learning system for the approximate dynamic program the optimal performance index function to realize the optimized control on pH value. The emulation experiments show that this method has better control effects comparing with the traditional method PID on steady-state error, overshoot, response speed and anti-jamming ability.

Self-Learning Control of PMA-Actuated Knee-Joint Rehabilitation Training Device Based on Fuzzy Neural Network

2011 ◽  
Vol 467-469 ◽  
pp. 1645-1650
Author(s):  
Xiao Li ◽  
Xia Hong ◽  
Ting Guan
Keyword(s):  
Neural Network ◽  
Knee Joint ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Control Method ◽  
Learning Control ◽  
Training Device ◽  
Rehabilitation Training ◽  
Fuzzy Neural ◽  
Self Learning

To solve the problem of the delay, nonlinearity and time-varying properties of PMA-actuated knee-joint rehabilitation training device, a self-learning control method based on fuzzy neural network is proposed in this paper. A self-learning controller was designed based on the combination of pid controller, feedforward controller, fuzzy neural network controller, and learning mechanism. It was applied to the isokinetic continuous passive motion control of the PMA-actuated knee-joint rehabilitation training device. The experiments proved that the self-learning controller has the properties of high control accuracy and unti-disturbance capability, comparing with pid controller. This control method provides the beneficial reference for improving the control performance of such system.

scholarly journals Optimal Control of Microgrid Operation Based on Fuzzy Sliding Mode Droop Control

Energies ◽  
2019 ◽  
Vol 12 (19) ◽  
pp. 3600 ◽  
Author(s):  
Zhu ◽  
Wang ◽  
Liu ◽  
Wang ◽  
Tai ◽  
...  
Keyword(s):  
Optimal Control ◽  
Power Distribution ◽  
Cooperative Control ◽  
Control Method ◽  
Sliding Mode ◽  
Droop Control ◽  
Power Sources ◽  
Fuzzy Sliding Mode ◽  
Fuzzy Control Strategy ◽  
Self Learning

In the application of microgrid systems that include wind power, photovoltaic systems, diesel generators, and battery storage, the cooperative control and optimisation of power distribution between power sources is a major issue. Recently, the droop control has been used widely in microgrids. However, droop control relies mainly on the line parameter model between the grid and the load. Therefore, to improve the performance of the microgrid, the optimal control of microgrid operation based on the fuzzy sliding mode droop control method is considered in this paper. To begin, system parameters were obtained by modeling droop control with self-learning fuzzy control strategy. Then, to improve the accuracy of the power distribution in the multi-micro source system, the nonlinear differential smoothing control method was employed. Finally, by comparing the self-learning fuzzy sliding mode control based on drooping strategy and the traditional droop control method, it was demonstrated that the method proposed can effectively reduce the fluctuation of the bus voltage and improve the output voltage quality of the microgrid system.

scholarly journals Adaptive Backlash Compensation Method Based on Touch State Observation for a Solid Ducted Rocket

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
An Wang ◽  
Qinghua Zeng ◽  
Likun Ma ◽  
Hongfu Wang
Keyword(s):  
Control Method ◽  
Compensation Method ◽  
Learning Ability ◽  
Limited Information ◽  
Hysteresis Model ◽  
Gas Generator ◽  
State Observation ◽  
State Variation ◽  
Ducted Rocket ◽  
Self Learning

A hysteresis model was built to describe the backlash of the flow regulator in a solid ducted rocket, and its influence on the engine control was also analyzed in this study. An adaptive backlash compensation method was proposed under two challenges: limited information and backlash state variation caused by the harsh environment in the gas generator. The touch state is designed and its observation is used to get the state of backlash, and a compensation control method using the existing information was carried out combined with the motion intention. This method greatly shortened the time during the transition and reduced the hysteresis effect on the control system. Furthermore, the compensation method is improved and acquires a self-learning ability, the compensation parameter changes adaptively during the process of flow regulation, and it is able to meet the challenge of an unknown and variable state of backlash. Finally, the validation of the compensation method was carried out with two simulations.

A Fuzzy Self-Learning Control Method with Application to Hydroforming Processes

1995 ◽  
Vol 117 (3) ◽  
pp. 297-303 ◽  
Author(s):  
H. J. Park ◽  
H. S. Cho
Keyword(s):  
Tracking Control ◽  
Control Method ◽  
Learning Control ◽  
Design Parameters ◽  
High Quality ◽  
Control Scheme ◽  
Series Of Experiments ◽  
Quality Of Products ◽  
Self Learning

In this paper, a tracking control of hydroforming pressure which is used for precision forming of sheet metals, is considered. In this process, forming pressure of the process needs to be strictly controlled to ensure high quality of the forming products. However, conventional control method alone makes it difficult to achieve satisfactory control performance due to complexities and uncertainties of the process. To overcome this problem, a fuzzy self-learning control scheme is proposed. In the proposed scheme, a series of experiments were performed to show the effectiveness of the proposed control scheme and to investigate influence of the design parameters of the proposed algorithm. The experimental results show that the proposed fuzzy self-learning controller can guarantee good tracking performance and thus, high quality of products even when knowledge of the process is vague, imprecise and fragmentary.

Sign in / Sign up

Export Citation Format

Share Document