https://hmjournals.com/ijaap/index.php/IJRISE <p><strong>International Journal of Research In Science &amp; Engineering (IJRISE)</strong> <strong>having</strong> <strong>E-ISSN: 2394-8299 P-ISSN: 2394-8280</strong> is Double Blind Peer reviewed, open access, online international journal published bimonthly. IJRISE is an international forum for scientists and engineers in all aspects of science and engineering publishing high quality papers. Papers of original research and innovatory applications from all parts of the world are welcome. This journal aims to cover the scientific research in a broader sense and not publishing a niche area of research facilitating researchers from various verticals to publish their papers. </p> HM Publishers en-US International Journal of Research in Science & Engineering 2394-8299 https://hmjournals.com/ijaap/index.php/IJRISE/article/view/6200 <p>The blistering development of Industry 4.0 has generated an increasing need to find smart systems that can handle sophisticated engineering processes with minimal human intervention. The given paper introduces the design and development of a Smart System of Efficient Engineering Applications (SSEEA) - the combination of deep learning-based fault detection, edge computing and real-time process optimization to optimize the performance of industrial operation. SSEEA relies on a hybrid neural network consisting of spatial and temporal pattern recognition neural networks which combine Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM). This system is built to have five functional layers, including data acquisition, edge pre-processing, AI inference, decision support and visualization, with low-latency high throughput behavior on resource-constrained industrial systems. It was tested on a benchmark dataset of 48,000 labeled operational cycles in one of a chemical process plant and demonstrated in an actual manufacturing environment. The SSEEA had an accuracy of 97.3% in fault detection, a precision of 96.9% and a recall of 97.1%, which is better than the baseline classifiers such as Support Vector Machines, Random Forest and standalone neural networks. SSEEA was found to have a 65.9% lower fault detection latency, 59.6% lower energy usage and eight times the prediction horizon than traditional threshold-based monitoring systems. ANOVA and Wilcoxon signed-rank tests were used to statistically prove all gains in performance. These findings substantiate the practicability and efficiency of SSEEA to be implemented in energy-intensive and safety-reliant industrial systems and provide a scalable and intelligible addition to the industrial digitalization process towards sustainable industrial digitalization.</p> Noor Alwan Malk Copyright (c) 2026 Authors https://creativecommons.org/licenses/by/4.0 2026-01-06 2026-01-06 6 1 1 10 10.55529/ijrise.61.1.10