Deep Neural Multi-Layer Perceptron Integrated Hybrid Engineering for IIoT Resource Management

The combination of both Deep Neural Multi-Layer Perceptron (DNMLP) and Model-Based Engineering (MBE) creates a novel hybrid engineering methodology for the resource management in IIoT applications. The DNMLP-MBE framework builds upon cloud-based IIoT architectures to improve the productivity, energy...

Full description

Saved in:
Bibliographic Details
Published in:2025 2nd International Conference On Multidisciplinary Research and Innovations in Engineering (MRIE) pp. 583 - 588
Main Authors: Uvaneshwari, M, Singh, Anil Pratap, Ambika, K., Parvathy, K, Bhatt, Nirav, Takkella, Radhika
Format: Conference Proceeding
Language:English
Published: IEEE 30.07.2025
Subjects:
Computational modeling
Computer architecture
Costs
Data models
Deep learning
DNMLP
IIoT
Industrial Internet of Things
Job shop scheduling
MBE
Multi - view modeling
Neural networks
Optimization
Processor scheduling
Pumping systems
Resource management
Task scheduling
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The combination of both Deep Neural Multi-Layer Perceptron (DNMLP) and Model-Based Engineering (MBE) creates a novel hybrid engineering methodology for the resource management in IIoT applications. The DNMLP-MBE framework builds upon cloud-based IIoT architectures to improve the productivity, energy, and automation of Dense Industrial domains. Thus, solving problems related to voltage optimization and possible tasks in pumping systems results in efficient and synchronized activity. The DNMLP-MBE algorithm can work out through multi-view modeling, each neuron imitating biological cells in order to process signals that are input and reach optimal output. Iterative testing for validation points to overall improvements on aspects like delayed computation time and costs to claims efficiency on other functions including milieu such as Model-in-the-Loop and Hardware-in-the-Loop. The proposed system also ensures a reasonable distribution of computational load and resources Implemented reference signal voltages exhibit enhanced performance relative to typical approaches. This promising paradigm shifts the resource management of IIoT to the next level by applying state-of-the-art deep learning into sound engineering processes in pursuit of better industrial automation, less breakdown time and cost optimization. The outcomes ensure the flexibility and the capability of DNMLP-MBE for contemporary industrial procedures.
DOI:10.1109/MRIE66930.2025.11156431