<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>With the development of informatization and digitalization, the transformation of intelligent manufacturing has become the focus. This paper builds an evaluation system based on the scientific evaluation method of the development level of smart manufacturing and the real demand situation. It establishes an evaluation model of intelligent manufacturing MES systems by combining the GA-BP algorithm. Then, a SeqGAN generative adversarial network is used to expand the real samples. The evaluation model was trained and validated by constructing a training model through the BP neural network, taking the sample data of evaluation indexes as the network input and the seven labels from Industry 1.0 to Industry 4.0 as the network output. The results show that the classification accuracy of the model is above 98%, and all of them have achieved good results. In the actual case evaluation, it is judged that the intelligent manufacturing MES system of Company Z is in the range of industry 3.0 to 3.5, and this result is very close to the manual evaluation of the factory field survey. The synthesis shows that the model is reasonable and effective and has important guiding significance for the evaluation of enterprise intelligent manufacturing MES systems.</p>
</abstract>

With the development of informatization and digitalization, the transformation of intelligent manufacturing has become the focus. This paper builds an evaluation system based on the scientific evaluation method of the development level of smart manufacturing and the real demand situation. It establishes an evaluation model of intelligent manufacturing MES systems by combining the GA-BP algorithm. Then, a SeqGAN generative adversarial network is used to expand the real samples. The evaluation model was trained and validated by constructing a training model through the BP neural network, taking the sample data of evaluation indexes as the network input and the seven labels from Industry 1.0 to Industry 4.0 as the network output. The results show that the classification accuracy of the model is above 98%, and all of them have achieved good results. In the actual case evaluation, it is judged that the intelligent manufacturing MES system of Company Z is in the range of industry 3.0 to 3.5, and this result is very close to the manual evaluation of the factory field survey. The synthesis shows that the model is reasonable and effective and has important guiding significance for the evaluation of enterprise intelligent manufacturing MES systems.

Research on evaluation system and method of MES system for intelligent manufacturing

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

With the development of informatization and digitalization, the transformation of intelligent manufacturing has become the focus. This paper builds an...

Research on evaluation system and method of MES system for intelligent manufacturing

Publié en ligne: 10 juin 2024

Pages: -

Reçu: 09 mars 2024

Accepté: 12 mai 2024

DOI: https://doi.org/10.2478/amns-2024-1469

Mots clés
Intelligent manufacturing, MES system, SeqGAN, BP neural network, Evaluation model

© 2024 Muhan Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on evaluation system and method of MES system for intelligent manufacturing

Publié en ligne: 10 juin 2024

Pages: -

Reçu: 09 mars 2024

Accepté: 12 mai 2024

DOI: https://doi.org/10.2478/amns-2024-1469

Mots clésIntelligent manufacturing, MES system, SeqGAN, BP neural network, Evaluation model

© 2024 Muhan Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Intelligent manufacturing, MES system, SeqGAN, BP neural network, Evaluation model