The current research investigates using artificial intelligence to improve manufacturing quality control and maintenance management by analyzing sensor data from production machinery. Leveraging advanced predictive models such as Stacked LSTM, RNNs, Random Forest, Gradient Boosting, SVM, ARIMA, and SARIMA, the study predicts potential equipment failures and enables preemptive maintenance to avoid breakdowns. Key findings show that AI-driven insights, displayed through intuitive dashboards and detailed reports, enhance regulatory compliance, improve operational reliability, and reduce downtime through effective anomaly detection in rotating machinery. These innovations not only increase productivity and operational efficiency but also align with several United Nations Sustainable Development Goals, including Goal 8 (Resilient Industrial Infrastructure), Goal 9 (Responsible Consumption and Production), Goal 12 (Lower Greenhouse Gas Emissions), Goal 13 (Fostering Sustainable Practices), and Goal 17 (Strengthening Partnerships). The research highlights the transformative potential of predictive modeling and advanced sensing technologies in driving creativity, improving production asset oversight, and promoting sustainability across industries.