EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY
The design and training scheme for the artificial neural network is considered. An expert system of evaluating a craftsman’s motor skills stability while working on the welder simulator is based on this technique. It is assumed that the weld joint quality depends directly on the welding behavior sta...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Don State Technical University
2014-12-01
|
| Series: | Advanced Engineering Research |
| Subjects: | |
| Online Access: | https://www.vestnik-donstu.ru/jour/article/view/355 |
| _version_ | 1797881377749729280 |
|---|---|
| author | Vitaliy Fedorovich Lukianov Igor Vladimirovich Kuzmenko |
| author_facet | Vitaliy Fedorovich Lukianov Igor Vladimirovich Kuzmenko |
| author_sort | Vitaliy Fedorovich Lukianov |
| collection | DOAJ |
| description | The design and training scheme for the artificial neural network is considered. An expert system of evaluating a craftsman’s motor skills stability while working on the welder simulator is based on this technique. It is assumed that the weld joint quality depends directly on the welding behavior stability. While the stability of the manual arc and mechanized welding depends on the welder’s motor skills. It is proposed to use an expert system to determine the stability criterion of the welding process. A step by step design of the artificial neural network architecture considering the specific weld formation is described. It is shown that the application of artificial neural networks based on the expert system allows evaluating the welder’s job stability. A training technique which shortens the time and reduces the number of experiments without loss of the data adequacy and the expert system training quality is described. When creating a database, the experimental results presented as "Quality domain" that connects the welder’s motor actions and the fillet joints defects are used. |
| first_indexed | 2024-04-10T03:19:10Z |
| format | Article |
| id | doaj.art-93d67c51744b4b63bbb561120f202cda |
| institution | Directory Open Access Journal |
| issn | 2687-1653 |
| language | Russian |
| last_indexed | 2024-04-10T03:19:10Z |
| publishDate | 2014-12-01 |
| publisher | Don State Technical University |
| record_format | Article |
| series | Advanced Engineering Research |
| spelling | doaj.art-93d67c51744b4b63bbb561120f202cda2023-03-13T07:31:25ZrusDon State Technical UniversityAdvanced Engineering Research2687-16532014-12-0114411712410.12737/6899348EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITYVitaliy Fedorovich Lukianov0Igor Vladimirovich Kuzmenko1Донской государственный технический университет, РоссияДонской государственный технический университет, РоссияThe design and training scheme for the artificial neural network is considered. An expert system of evaluating a craftsman’s motor skills stability while working on the welder simulator is based on this technique. It is assumed that the weld joint quality depends directly on the welding behavior stability. While the stability of the manual arc and mechanized welding depends on the welder’s motor skills. It is proposed to use an expert system to determine the stability criterion of the welding process. A step by step design of the artificial neural network architecture considering the specific weld formation is described. It is shown that the application of artificial neural networks based on the expert system allows evaluating the welder’s job stability. A training technique which shortens the time and reduces the number of experiments without loss of the data adequacy and the expert system training quality is described. When creating a database, the experimental results presented as "Quality domain" that connects the welder’s motor actions and the fillet joints defects are used.https://www.vestnik-donstu.ru/jour/article/view/355сварное соединение, искусственные нейронные сети, обучение искусственной нейронной сети, дефекты сварного шва, экспертная система, стабильность процесса сварки, аналитические методы. |
| spellingShingle | Vitaliy Fedorovich Lukianov Igor Vladimirovich Kuzmenko EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY Advanced Engineering Research сварное соединение, искусственные нейронные сети, обучение искусственной нейронной сети, дефекты сварного шва, экспертная система, стабильность процесса сварки, аналитические методы. |
| title | EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY |
| title_full | EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY |
| title_fullStr | EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY |
| title_full_unstemmed | EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY |
| title_short | EXPERT SYSTEM TRAINING TECHNIQUE TO EVALUATE WELDER’S JOB STABILITY |
| title_sort | expert system training technique to evaluate welder s job stability |
| topic | сварное соединение, искусственные нейронные сети, обучение искусственной нейронной сети, дефекты сварного шва, экспертная система, стабильность процесса сварки, аналитические методы. |
| url | https://www.vestnik-donstu.ru/jour/article/view/355 |
| work_keys_str_mv | AT vitaliyfedorovichlukianov expertsystemtrainingtechniquetoevaluateweldersjobstability AT igorvladimirovichkuzmenko expertsystemtrainingtechniquetoevaluateweldersjobstability |