Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System

Precise temperature control in high-temperature furnaces is challenged by nonlinearities, parameter drift, and high thermal inertia. This study proposes an adaptive control strategy combining a classical PID loop with real-time gain updates from a feed-forward artificial neural network (ANN). Implem...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Carlos Almachi, Ramiro Vicente, Edwin Bone, Jessica Montenegro, Edgar Cando, Salvatore Reina
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/12/3113
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433159054131200
author Juan Carlos Almachi
Ramiro Vicente
Edwin Bone
Jessica Montenegro
Edgar Cando
Salvatore Reina
author_facet Juan Carlos Almachi
Ramiro Vicente
Edwin Bone
Jessica Montenegro
Edgar Cando
Salvatore Reina
author_sort Juan Carlos Almachi
collection DOAJ
description Precise temperature control in high-temperature furnaces is challenged by nonlinearities, parameter drift, and high thermal inertia. This study proposes an adaptive control strategy combining a classical PID loop with real-time gain updates from a feed-forward artificial neural network (ANN). Implemented on an 18 kW retrofitted Blue-M furnace, the system was characterized by second-order transfer functions for heating and forced convection cooling. A dataset of 9702 samples was built from eight fixed PID configurations tested under a multi-ramp thermal profile. The selected 3-64-64-32-2 ANN, executed in Python and interfaced with LabVIEW, computes optimal gains in 0.054 ms while preserving real-time monitoring capabilities. Experimental results show that the ANN-assisted PID reduces the mean absolute error to 5.08 °C, limits overshoot to 41% (from 53%), and shortens settling time by 20% compared to the best fixed-gain loop. It also outperforms a fuzzy controller and remains stable under ±5% signal noise. Notably, gain reversals during cooling prevent temperature spikes, improving transient response. Relying on commodity hardware and open-source tools, this approach offers a cost-effective solution for legacy furnace upgrades and provides a replicable model for adaptive control in high-temperature, safety-critical environments like metal processing, battery cycling, and nuclear systems.
format Article
id doaj-art-3ff31ac7304749f49fff100ab9af9905
institution Kabale University
issn 1996-1073
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-3ff31ac7304749f49fff100ab9af99052025-08-20T03:27:10ZengMDPI AGEnergies1996-10732025-06-011812311310.3390/en18123113Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal SystemJuan Carlos Almachi0Ramiro Vicente1Edwin Bone2Jessica Montenegro3Edgar Cando4Salvatore Reina5Departamento de Ingeniería Mecánica (DIM), Escuela Politécnica Nacional (EPN), Quito 170517, EcuadorFaculty of Information Technology and Programming, ITMO University, Saint Petersburg 197101, RussiaDepartamento de Ingeniería Mecánica y Metalúrgica (DIMM), Pontificia Universidad Católica de Chile, Santiago 7820436, ChileDepartamento de Formación Básica (DFB), Escuela Politécnica Nacional (EPN), Quito 170517, EcuadorDepartamento de Ingeniería Mecánica (DIM), Escuela Politécnica Nacional (EPN), Quito 170517, EcuadorDepartamento de Ingeniería Mecánica (DIM), Escuela Politécnica Nacional (EPN), Quito 170517, EcuadorPrecise temperature control in high-temperature furnaces is challenged by nonlinearities, parameter drift, and high thermal inertia. This study proposes an adaptive control strategy combining a classical PID loop with real-time gain updates from a feed-forward artificial neural network (ANN). Implemented on an 18 kW retrofitted Blue-M furnace, the system was characterized by second-order transfer functions for heating and forced convection cooling. A dataset of 9702 samples was built from eight fixed PID configurations tested under a multi-ramp thermal profile. The selected 3-64-64-32-2 ANN, executed in Python and interfaced with LabVIEW, computes optimal gains in 0.054 ms while preserving real-time monitoring capabilities. Experimental results show that the ANN-assisted PID reduces the mean absolute error to 5.08 °C, limits overshoot to 41% (from 53%), and shortens settling time by 20% compared to the best fixed-gain loop. It also outperforms a fuzzy controller and remains stable under ±5% signal noise. Notably, gain reversals during cooling prevent temperature spikes, improving transient response. Relying on commodity hardware and open-source tools, this approach offers a cost-effective solution for legacy furnace upgrades and provides a replicable model for adaptive control in high-temperature, safety-critical environments like metal processing, battery cycling, and nuclear systems.https://www.mdpi.com/1996-1073/18/12/3113adaptive PID controlartificial neural networkthermal process controlhigh-temperature furnacereal-time control
spellingShingle Juan Carlos Almachi
Ramiro Vicente
Edwin Bone
Jessica Montenegro
Edgar Cando
Salvatore Reina
Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
Energies
adaptive PID control
artificial neural network
thermal process control
high-temperature furnace
real-time control
title Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
title_full Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
title_fullStr Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
title_full_unstemmed Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
title_short Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System
title_sort implementation of a neural network for adaptive pid tuning in a high temperature thermal system
topic adaptive PID control
artificial neural network
thermal process control
high-temperature furnace
real-time control
url https://www.mdpi.com/1996-1073/18/12/3113
work_keys_str_mv AT juancarlosalmachi implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem
AT ramirovicente implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem
AT edwinbone implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem
AT jessicamontenegro implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem
AT edgarcando implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem
AT salvatorereina implementationofaneuralnetworkforadaptivepidtuninginahightemperaturethermalsystem