Scope

Deadline Date: 31 March 2026

The integration of deep learning algorithms into predictive maintenance systems represents a significant advancement in the application of numerical methods for engineering design and decision-making. As industries increasingly adopt data-driven solutions to manage complex equipment and production processes, predictive maintenance has become a vital strategy for minimizing unexpected downtimes, reducing maintenance costs, and extending asset lifespans.

This research area is critically important in the context of modern engineering, where large-scale sensor data, real-time monitoring, and intelligent analysis converge to form the foundation of Industry 4.0. Deep learning models—especially those capable of handling time series data and anomaly detection—enable engineers to forecast failures and optimize repair schedules with high accuracy. These models leverage numerical techniques rooted in statistical learning, neural network training, and signal processing to extract actionable insights from complex, multi-dimensional datasets.

Given the growing demand for computationally efficient and scalable solutions, the development and validation of specialized algorithms for industrial predictive maintenance are of high relevance. This special issue seeks to highlight novel methodologies and practical implementations that bridge the gap between artificial intelligence, numerical modeling, and engineering maintenance systems—offering both theoretical advancements and real-world applications.

The primary aim of this Special Issue is to explore and disseminate recent developments in algorithm design for deep learning models applied to industrial predictive maintenance systems. As industries transition toward intelligent and data-driven operations, the need for robust computational approaches to forecast equipment failures has become increasingly critical. This Special Issue focuses on research that bridges deep learning methodologies with practical engineering applications, particularly in the optimization of system reliability, efficiency, and cost-effectiveness.

The scope encompasses innovative algorithmic strategies that utilize numerical and computational techniques to analyze sensor data, model degradation patterns, and predict faults within complex industrial environments. Topics of interest include the theoretical development of deep learning models, advanced signal processing for time series data, and the integration of industrial internet of things (IIoT) technologies to enable real-time predictive maintenance. The Special Issue also encourages submissions that provide comparative analysis of algorithms, discuss practical deployment challenges, or demonstrate real-world implementations in manufacturing and engineering systems.

By uniting contributions from academia and industry, this Special Issue aims to provide a comprehensive perspective on how deep learning and numerical methods can jointly enhance predictive maintenance, thus contributing to the advancement of smart, sustainable, and efficient industrial systems.

Suggested themes:

Predictive maintenance for induction motors using deep learning and machine learning techniques.

Industrial Internet of Things predictive maintenance facilitated by deep learning.

Industrial predictive maintenance using machine learning.

Predictive maintenance using machine learning for industry-wide sustainable smart manufacturing.

A systematic overview of the literature on machine learning techniques used in predictive maintenance.

Methods based on data that are used to estimate industrial equipment repair.

An analysis of cutting-edge machine learning algorithms for predictive maintenance in comparison.

Industrial production line predictive maintenance system.

Predictive maintenance using machine learning in the manufacturing sector.

Applications of data-driven predictive maintenance for temporal convolutional networks in industrial systems.

A study of unsupervised machine learning techniques for predictive maintenance's early fault identification.

Survey of future maintenance defect detection methods.