Controlling of Pneumatic Muscle Actuator Systems by Parallel Structure of Neural Network and Proportional Controllers (PNNP)

Al-Ibadi, Alaa; Nefti‐Meziani, Samia; Davis, Steve

doi:10.3389/frobt.2020.00115

Cited by 11 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The encoder sends the rotating angle as feedback, which is proportional to the resistance value to the controller input as shown in Figure 11. The presented controller system, parallel neural network and proportional (PNNP), in the previous article [47] have been used to control the twisting angle. The training process is done by (trainlm) (MATLAB 2020a) for 100 iterations and at 10 −7 mean square error (MSE).…”

Section: Control the Twisting Anglementioning

confidence: 99%

See 1 more Smart Citation

Design, Implementation, and Kinematics of a Twisting Robot Continuum Arm Inspired by Human Forearm Movements

et al. 2022

Self Cite

View full text Add to dashboard Cite

In this article, a soft robot arm that has the ability to twist in two directions is designed. This continuum arm is inspired by the twisting movements of the human upper limb. In this novel continuum arm, two contractor pneumatic muscle actuators (PMA) are used in parallel, and a self-bending contraction actuator (SBCA) is laid between them to establish the twisting movement. The proposed soft robot arm has additional features, such as the ability to contract and bend in multiple directions. The kinematics for the proposed arm is presented to describe the position of the distal end centre according to the dimensions and positions of the actuators and the bending angle of the SBCA in different pressurized conditions. Then, the rotation behaviour is controlled by a high precision controller system.

show abstract

Section: Control the Twisting Anglementioning

confidence: 99%

“…The controller system is built by a parallel structure of the NARMA-L2 Neural Network (NN) control system and proportional (P) controller. The NN ensures accuracy, while the P controller increases the system response [47].…”

Section: Control the Twisting Anglementioning

confidence: 99%

Design, Implementation, and Kinematics of a Twisting Robot Continuum Arm Inspired by Human Forearm Movements

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The PID controller is generally used due to less cost and simplicity in design. Nevertheless, the linear PID controller cannot respond to variations in the operating situation and thus cannot exhibit optimal performance [15]. On the other hand, the fuzzy-based controller is nonlinear, but its gain values must be manually tuned and need human intervention.…”

Section: Literature Reviewmentioning

confidence: 99%

Robust Modified Flower Pollination Algorithm for Power Quality Enhancement in an Autonomous 31-Level Cascaded H-Bridge Photovoltaic Inverter with Partial Shading Conditions

Sahu¹,

Nayak

Choudhury

2022

IJRITCC

View full text Add to dashboard Cite

The effect of global warming and the scarcity of fossil fuels has created an enormous problem in today’s era. To overcome such a problem, renewable energy sources, particularly solar energy, play a crucial role in meeting the developing need for power. However, the design of the Solar Photovoltaic (PV) system is interrupted by various factors such as the effect of temperature, isolation, aging, partial shading conditions, etc. Among all the factors mentioned, partial shading results in the significant diminution of power. To address this shading effect and enhance the flexibility of the PV system in terms of better utilization and energy extraction, a 31-Level Cascaded H-Bridge Multilevel Inverter (CHB-MLI) has been implemented to the autonomous PV system comprising of Maximum Power Point Tracking (MPPT) controller, boost converter and variable loads in MATLAB/Simulink architecture. To track maximum power from PV during varying irradiance and temperature and to further improve the system performance in terms of better convergence speed, an MPPT system with a Modified Flower Pollination Algorithm (MFPA) based PID controller has been proposed in this paper. To justify the suggested approach, the is-landed PV system is led to variation in irradiance and load. A detailed comparison of the proposed MFPA technique with classical control techniques has been meticulously discussed. The results obtained indicate that the suggested MFPA tuned PID with MLI outperforms the conventional methods in better system stability, reduced harmonics, and enhanced capacity to track maximum power from the PV system. In addition to this, the Total Harmonic Distortion (THD) using Fast Fourier Transform (FFT) has been found to verify IEEE-1547 power quality constraints. The values are found to be well within limits, thus justifying its real-time applications.

show abstract

“…The use of the classification of signals with categorical values is more common. The more focused approaches are shown in [24], where learned control mechanisms were used, reinforcement learning [25] or learned differentiable models [26].…”

Section: Measuring and Estimating A Stiffnessmentioning

confidence: 99%

Gaining a Sense of Touch Object Stiffness Estimation Using a Soft Gripper and Neural Networks

et al. 2021

View full text Add to dashboard Cite

Soft grippers are gaining significant attention in the manipulation of elastic objects, where it is required to handle soft and unstructured objects, which are vulnerable to deformations. The crucial problem is to estimate the physical parameters of a squeezed object to adjust the manipulation procedure, which poses a significant challenge. The research on physical parameters estimation using deep learning algorithms on measurements from direct interaction with objects using robotic grippers is scarce. In our work, we proposed a trainable system which performs the regression of an object stiffness coefficient from the signals registered during the interaction of the gripper with the object. First, using the physics simulation environment, we performed extensive experiments to validate our approach. Afterwards, we prepared a system that works in a real-world scenario with real data. Our learned system can reliably estimate the stiffness of an object, using the Yale OpenHand soft gripper, based on readings from Inertial Measurement Units (IMUs) attached to the fingers of the gripper. Additionally, during the experiments, we prepared three datasets of IMU readings gathered while squeezing the objects—two created in the simulation environment and one composed of real data. The dataset is the contribution to the community providing the way for developing and validating new approaches in the growing field of soft manipulation.

show abstract

Controlling of Pneumatic Muscle Actuator Systems by Parallel Structure of Neural Network and Proportional Controllers (PNNP)

Cited by 11 publications

References 39 publications

Design, Implementation, and Kinematics of a Twisting Robot Continuum Arm Inspired by Human Forearm Movements

Design, Implementation, and Kinematics of a Twisting Robot Continuum Arm Inspired by Human Forearm Movements

Robust Modified Flower Pollination Algorithm for Power Quality Enhancement in an Autonomous 31-Level Cascaded H-Bridge Photovoltaic Inverter with Partial Shading Conditions

Gaining a Sense of Touch Object Stiffness Estimation Using a Soft Gripper and Neural Networks

Contact Info

Product

Resources

About