<p>The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) is revolutionizing industries, particularly manufacturing, by enabling intelligent, data-driven decision-making. However, traditional AI models face limitations when applied to resource-constrained IoT environments, which impact efficiency and scalability. This research aims to develop and test an AI model, the Quantized Deep Convolute NeuroNet (QDCN), optimized for IoT systems to enhance manufacturing efficiency, reduce costs, and support broader digital transformation. The QDCN model overcomes the shortcomings of conventional AI models by improving energy efficiency, prediction accuracy, and processing speed. It is evaluated using a dataset derived from real-world manufacturing operations, comprising sensor data from IoT-enabled devices, such as temperature, machine speed, and production quality metrics. Data preprocessing includes Z-score normalization and outlier detection to ensure data quality and consistency. Feature extraction is performed using the Fourier Transform for frequency analysis and Principal Component Analysis (PCA) for dimensionality reduction. Feature selection is handled using the Intelligent Genetic Algorithm (IGA) to identify and optimize relevant features, enhancing the model's predictive accuracy and computational efficiency. The model achieves a high level of predictive performance, with accuracy and recall values ranging from 94 to 98%. Model simulation and optimization are conducted using Python and appropriate libraries. In conclusion, the proposed QDCN model significantly improves manufacturing operations by boosting efficiency, reducing operational costs, and enhancing product quality. It offers a promising framework for scalable, real-time AI-IoT integration in modern smart manufacturing environments and the evolving digital economy.</p>