On the Use of Artificial Neural Networks for the Automated High-Level Design of ΣΔ Modulators

This paper presents a high-level synthesis methodology for Sigma-Delta Modulators (Sigma Delta Ms) that combines behavioral modeling and simulation for performance evaluation, and Artificial Neural Networks (ANNs) to generate high-level designs variables for the required specifications. To this end,...

Descripción completa

Detalles Bibliográficos
Autores: Díaz-Lobo, Pablo, Liñán-Cembrano, Gustavo, Rosa, José M. de la
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2024
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/385837
Acceso en línea:http://hdl.handle.net/10261/385837
https://api.elsevier.com/content/abstract/scopus_id/85179816067
Access Level:acceso abierto
Palabra clave:Analog-to-digital converters
Design automation
Neural networks
Optimization
Sigma-delta modulation
Descripción
Sumario:This paper presents a high-level synthesis methodology for Sigma-Delta Modulators (Sigma Delta Ms) that combines behavioral modeling and simulation for performance evaluation, and Artificial Neural Networks (ANNs) to generate high-level designs variables for the required specifications. To this end, comprehensive datasets made up of design variables and performance metrics, generated from accurate behavioral simulations of different kinds of Sigma Delta Ms, are used to allow the ANN to learn the complex relationships between design-variables and specifications. Several representative case studies are considered, including single-loop and cascade architectures with single-bit and multi-bit quantization, as well as both Switched-Capacitor (SC) and Continuous-Time (CT) circuit techniques. The proposed solution works in two steps. First, for a given set of specifications, a trained classifier proposes one of the available Sigma Delta text{M} architectures in the dataset. Second, for the proposed architecture, a Regression-type Neural Network (RNN) infers the design variables required to produce the requested specifications. A comparison with other optimization methods - such as genetic algorithms and gradient descent - is discussed, demonstrating that the presented approach yields to more efficient design solutions in terms of performance metrics and CPU time.