Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator
This study derives a learning algorithm for a quaternion neural network using the steepest descent method extended to quaternion numbers. This applies the generalised Hamiltonian–Real calculus to obtain derivatives of a real–valued cost function concerning quaternion variables and designs a feedback...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/5/333 |
| _version_ | 1797498390211198976 |
|---|---|
| author | Kazuhiko Takahashi Eri Tano Masafumi Hashimoto |
| author_facet | Kazuhiko Takahashi Eri Tano Masafumi Hashimoto |
| author_sort | Kazuhiko Takahashi |
| collection | DOAJ |
| description | This study derives a learning algorithm for a quaternion neural network using the steepest descent method extended to quaternion numbers. This applies the generalised Hamiltonian–Real calculus to obtain derivatives of a real–valued cost function concerning quaternion variables and designs a feedback–feedforward controller as a control system application using such a network. The quaternion neural network is trained in real-time by introducing a feedback error learning framework to the controller. Thus, the quaternion neural network-based controller functions as an adaptive-type controller. The designed controller is applied to the control problem of a three-link robot manipulator, with the control task of making the robot manipulator’s end effector follow a desired trajectory in the Cartesian space. Computational experiments are conducted to investigate the learning capability and the characteristics of the quaternion neural network used in the controller. The experimental results confirm the feasibility of using the derived learning algorithm based on the generalised Hamiltonian–Real calculus to train the quaternion neural network and the availability of such a network for a control systems application. |
| first_indexed | 2024-03-10T03:32:46Z |
| format | Article |
| id | doaj.art-5820968560cd4cc4869c593ae57b508e |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-10T03:32:46Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-5820968560cd4cc4869c593ae57b508e2023-11-23T11:52:26ZengMDPI AGMachines2075-17022022-05-0110533310.3390/machines10050333Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot ManipulatorKazuhiko Takahashi0Eri Tano1Masafumi Hashimoto2Department of Information Systems Design, Faculty of Science and Engineering, Doshisha University, Kyoto 610-0394, JapanDepartment of Information Systems Design, Faculty of Science and Engineering, Doshisha University, Kyoto 610-0394, JapanDepartment of Intelligent Information Engineering and Sciences, Faculty of Science and Engineering, Doshisha University, Kyoto 610-0394, JapanThis study derives a learning algorithm for a quaternion neural network using the steepest descent method extended to quaternion numbers. This applies the generalised Hamiltonian–Real calculus to obtain derivatives of a real–valued cost function concerning quaternion variables and designs a feedback–feedforward controller as a control system application using such a network. The quaternion neural network is trained in real-time by introducing a feedback error learning framework to the controller. Thus, the quaternion neural network-based controller functions as an adaptive-type controller. The designed controller is applied to the control problem of a three-link robot manipulator, with the control task of making the robot manipulator’s end effector follow a desired trajectory in the Cartesian space. Computational experiments are conducted to investigate the learning capability and the characteristics of the quaternion neural network used in the controller. The experimental results confirm the feasibility of using the derived learning algorithm based on the generalised Hamiltonian–Real calculus to train the quaternion neural network and the availability of such a network for a control systems application.https://www.mdpi.com/2075-1702/10/5/333hypercomplex numbersquaternion neural networkgeneralised Hamiltonian–Real calculusfeedforward–feedback controllerrobot manipulator |
| spellingShingle | Kazuhiko Takahashi Eri Tano Masafumi Hashimoto Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator Machines hypercomplex numbers quaternion neural network generalised Hamiltonian–Real calculus feedforward–feedback controller robot manipulator |
| title | Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator |
| title_full | Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator |
| title_fullStr | Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator |
| title_full_unstemmed | Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator |
| title_short | Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised <inline-formula><math display="inline"><semantics><mi mathvariant="double-struck">HR</mi></semantics></math></inline-formula> Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator |
| title_sort | feedforward feedback controller based on a trained quaternion neural network using a generalised inline formula math display inline semantics mi mathvariant double struck hr mi semantics math inline formula calculus with application to trajectory control of a three link robot manipulator |
| topic | hypercomplex numbers quaternion neural network generalised Hamiltonian–Real calculus feedforward–feedback controller robot manipulator |
| url | https://www.mdpi.com/2075-1702/10/5/333 |
| work_keys_str_mv | AT kazuhikotakahashi feedforwardfeedbackcontrollerbasedonatrainedquaternionneuralnetworkusingageneralisedinlineformulamathdisplayinlinesemanticsmimathvariantdoublestruckhrmisemanticsmathinlineformulacalculuswithapplicationtotrajectorycontrolofathreelinkrobotmanipulator AT eritano feedforwardfeedbackcontrollerbasedonatrainedquaternionneuralnetworkusingageneralisedinlineformulamathdisplayinlinesemanticsmimathvariantdoublestruckhrmisemanticsmathinlineformulacalculuswithapplicationtotrajectorycontrolofathreelinkrobotmanipulator AT masafumihashimoto feedforwardfeedbackcontrollerbasedonatrainedquaternionneuralnetworkusingageneralisedinlineformulamathdisplayinlinesemanticsmimathvariantdoublestruckhrmisemanticsmathinlineformulacalculuswithapplicationtotrajectorycontrolofathreelinkrobotmanipulator |