Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Biblos-e Archivo
Doctoral thesis . 2017
Data sources: Biblos-e Archivo
versions View all 4 versions
addClaim

Artificial cognitive architecture with self-learning and self-optimization capabilities. Case studies in micromachining processes

Authors: Beruvides López, Gerardo;

Artificial cognitive architecture with self-learning and self-optimization capabilities. Case studies in micromachining processes

Abstract

[ES] Esta Tesis Doctoral está enfocada hacia el diseño e implementación de una arquitectura cognitiva artificial, de inspiración biológica, dotada de estrategias de autoaprendizaje y autooptimización para realizar tareas de monitorización y control. En primer lugar, el fundamento nace en el nexo entre el paradigma del control por modelo interno y la conectividad cerebrocerebelo como base de la inteligencia humana. La principal hipótesis radica precisamente en que el control por modelo interno a través de la conectividad cerebro-cerebelo es un componente único de la inteligencia humana. El segundo principio está basado en el modelo de los circuitos compartidos y la emulación de las capacidades y experiencias socio-cognitivas de los seres humanos. Tres cuestiones esenciales han sido el desarrollo y perfeccionamiento de un método libre de gradiente para permitir la auto-optimización multiobjetivo, el desarrollo de una estrategia de aprendizaje por refuerzo para el autoaprendizaje, y finalmente la evaluación experimental y validación en dos procesos esenciales en la micro-escala (microfresado y microtaladrado). De forma resumida, la contribución técnica fundamental de esta Tesis Doctoral es que a partir de la mínima información sensorial posible (señales de aceleración y señales de fuerzas) y de la mínima cantidad de información sobre las condiciones de corte (velocidad de corte, avance por diente y penetración axial), se puede monitorizar en tiempo real el estado del proceso de corte en la micro-escala y realizar acciones de control para garantizar buenos acabados superficiales y alargar la vida útil de la herramienta. Este resultado técnico supone un salto cualitativo importante sin precedentes en la investigación industrial en el campo de la microfabricación.

[EN] This Doctoral Thesis is focused on the design and implementation of an artificial cognitive architecture, biologically inspired with strategies of self-learning and self-optimization to carry out monitoring and control tasks. Firstly, the foundations rely on the nexus between the paradigm of internal model control and the cerebellum-brain connectivity as the pillar of human intelligence. The main hypothesis is precisely that internal model control through the braincerebellum connectivity is a unique component of human intelligence. The second principle is based on the shared circuits model and the capacities to emulate socio-cognitive skills of human beings. Three key issues have been addressed in this Thesis, as follows: the development and refinement of a gradient-free method to enable multi-objective self-optimization, the development of a reinforcement learning strategy to carry out self-learning and finally, the experimental evaluation and validation in two manufacturing processes at the micro-scale (i.e., micro-milling and micro-drilling). In summary, the fundamental technical contribution from this Doctoral Thesis is the use of the minimum possible sensory information (force and vibration signals) and the minimum cutting conditions information (cutting speed, feed rate per tooth and axial cutting deep) in order to monitor and to perform control actions to guarantee high surface finish quality and to extend the useful life of the tool in micromachining process. This technical result represents an unprecedented qualitative leap in micromachining industrial research.

El trabajo desarrollado y presentado en esta Tesis Doctoral ha sido posible gracias a una beca de formación de personal investigador (FPI), concedida en el proyecto del plan nacional de I+D DPI2012-35504 CONTROL COGNITIVO ARTIFICIAL EN PROCESOS DE MICROMECANIZADO MECÁNICO. MÉTODO Y APLICACIÓN (CONMICRO).

Peer reviewed

Country
Spain
Related Organizations
Keywords

Informática, Manufacturas, Inteligencia artificial - Tesis doctorales, Aprendizaje automático - Tesis doctorales, Procesos cognitivos, Inteligencia artificial, Problemas de aprendizaje

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 76
    download downloads 202
  • 76
    views
    202
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
76
202
Green
Related to Research communities