Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot
In this paper, the aim is to classify torque signals that are received from a 3-DOF manipulator using a pattern recognition neural network (PR-NN). The output signals of the proposed PR-NN classifier model are classified into four indicators. The first predicts that no collisions occur. The other th...
| Main Authors: | , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
MDPI AG
2024-03-01
|
| 丛编: | Automation |
| 主题: | |
| 在线阅读: | https://www.mdpi.com/2673-4052/5/1/2 |
| _version_ | 1827307125685092352 |
|---|---|
| author | Khaled H. Mahmoud G. T. Abdel-Jaber Abdel-Nasser Sharkawy |
| author_facet | Khaled H. Mahmoud G. T. Abdel-Jaber Abdel-Nasser Sharkawy |
| author_sort | Khaled H. Mahmoud |
| collection | DOAJ |
| description | In this paper, the aim is to classify torque signals that are received from a 3-DOF manipulator using a pattern recognition neural network (PR-NN). The output signals of the proposed PR-NN classifier model are classified into four indicators. The first predicts that no collisions occur. The other three indicators predict collisions on the three links of the manipulator. The input data to train the PR-NN model are the values of torque exerted by the joints. The output of the model predicts and identifies the link on which the collision occurs. In our previous work, the position data for a 3-DOF robot were used to estimate the external collision torques exerted by the joints when applying collisions on each link, based on a recurrent neural network (RNN). The estimated external torques were used to design the current PR-NN model. In this work, the PR-NN model, while training, could successfully classify 56,592 samples out of 56,619 samples. Thus, the model achieved overall effectiveness (accuracy) in classifying collisions on the robot of 99.95%, which is almost 100%. The sensitivity of the model in detecting collisions on the links “Link 1, Link 2, and Link 3” was 97.9%, 99.7%, and 99.9%, respectively. The overall effectiveness of the trained model is presented and compared with other previous entries from the literature. |
| first_indexed | 2024-04-24T18:33:56Z |
| format | Article |
| id | doaj.art-f68afd7891ca42359a6dab0e92b85ea4 |
| institution | Directory Open Access Journal |
| issn | 2673-4052 |
| language | English |
| last_indexed | 2024-04-24T18:33:56Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Automation |
| spelling | doaj.art-f68afd7891ca42359a6dab0e92b85ea42024-03-27T13:20:55ZengMDPI AGAutomation2673-40522024-03-0151133410.3390/automation5010002Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial RobotKhaled H. Mahmoud0G. T. Abdel-Jaber1Abdel-Nasser Sharkawy2Mechatronics Department, Faculty of Industry and Energy Technology, New Cairo Technological University NCTU, Cairo 11835, EgyptMechanical Engineering Department, Faculty of Engineering, South Valley University, Qena 83523, EgyptMechanical Engineering Department, Faculty of Engineering, South Valley University, Qena 83523, EgyptIn this paper, the aim is to classify torque signals that are received from a 3-DOF manipulator using a pattern recognition neural network (PR-NN). The output signals of the proposed PR-NN classifier model are classified into four indicators. The first predicts that no collisions occur. The other three indicators predict collisions on the three links of the manipulator. The input data to train the PR-NN model are the values of torque exerted by the joints. The output of the model predicts and identifies the link on which the collision occurs. In our previous work, the position data for a 3-DOF robot were used to estimate the external collision torques exerted by the joints when applying collisions on each link, based on a recurrent neural network (RNN). The estimated external torques were used to design the current PR-NN model. In this work, the PR-NN model, while training, could successfully classify 56,592 samples out of 56,619 samples. Thus, the model achieved overall effectiveness (accuracy) in classifying collisions on the robot of 99.95%, which is almost 100%. The sensitivity of the model in detecting collisions on the links “Link 1, Link 2, and Link 3” was 97.9%, 99.7%, and 99.9%, respectively. The overall effectiveness of the trained model is presented and compared with other previous entries from the literature.https://www.mdpi.com/2673-4052/5/1/2collisions classificationindustrial robotneural networkpattern recognitionevaluationcomparison |
| spellingShingle | Khaled H. Mahmoud G. T. Abdel-Jaber Abdel-Nasser Sharkawy Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot Automation collisions classification industrial robot neural network pattern recognition evaluation comparison |
| title | Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot |
| title_full | Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot |
| title_fullStr | Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot |
| title_full_unstemmed | Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot |
| title_short | Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot |
| title_sort | neural network based classifier for collision classification and identification for a 3 dof industrial robot |
| topic | collisions classification industrial robot neural network pattern recognition evaluation comparison |
| url | https://www.mdpi.com/2673-4052/5/1/2 |
| work_keys_str_mv | AT khaledhmahmoud neuralnetworkbasedclassifierforcollisionclassificationandidentificationfora3dofindustrialrobot AT gtabdeljaber neuralnetworkbasedclassifierforcollisionclassificationandidentificationfora3dofindustrialrobot AT abdelnassersharkawy neuralnetworkbasedclassifierforcollisionclassificationandidentificationfora3dofindustrialrobot |