Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/201708
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Curcó Cantarell, David | - |
dc.contributor.author | Gómez Cáceres, Max | - |
dc.date.accessioned | 2023-09-04T15:22:11Z | - |
dc.date.available | 2023-09-04T15:22:11Z | - |
dc.date.issued | 2023-06 | - |
dc.identifier.uri | http://hdl.handle.net/2445/201708 | - |
dc.description | Treballs Finals de Grau d'Enginyeria Química, Facultat de Química, Universitat de Barcelona, Curs: 2022-2023, Tutor: David Curcó Cantarell | ca |
dc.description.abstract | Artificial Intelligence is experiencing dramatic growth in recent times. AI models such as ChatGPT have become controversial topics as they continously transform our world. Nevertheless, the true nature of AI is still widely not yet understood by society. Nowadays, Artificial Intelligence is still seen by many as an obscure and foreign concept, even mysterious and threatening. However, this couldn’t be further from the truth. At their essence, they are just mathematical tools which rely on centuries-old knowledge: algebra and calculus. In this project, a neural network model has been created to solve a chemical engineering problem, the predictive model of a double tube heat exchanger. This model is a neural network that predicts future system outputs (inner stream output temperature) from the past values of the input variables of the system (inner and outer streams input temperatures and outer stream flow rate). The data used to train the model was obtained in a simulation written in the Python programming language. Afterwards, the optimal design parameters of the neural network were found experimentally by training different models and testing their performance. This was done in three stages: a proof of concept, a general design stage and a detailed design stage. The model has been successful in predicting the future state of the system with high exactitude while being circa. 3000 times faster than a conventional simulation. | ca |
dc.format.extent | 75 p. | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | ca |
dc.rights | cc-by-nc-nd (c) Gómez, 2023 | - |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.source | Treballs Finals de Grau (TFG) - Enginyeria Química | - |
dc.subject.classification | Intel·ligència artificial | cat |
dc.subject.classification | Xarxes neuronals (Informàtica) | cat |
dc.subject.classification | Treballs de fi de grau | cat |
dc.subject.other | Artificial intelligence | eng |
dc.subject.other | Neural networks (Computer science) | eng |
dc.subject.other | Bachelor's theses | eng |
dc.title | Application of neural networks to model double tube heat exchangers | eng |
dc.type | info:eu-repo/semantics/bachelorThesis | ca |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | ca |
Appears in Collections: | Treballs Finals de Grau (TFG) - Enginyeria Química |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
TFG GÓMEZ CÁCERES MAX 2022-23 P.pdf | 1.54 MB | Adobe PDF | View/Open |
This item is licensed under a
Creative Commons License