An intelligent internet of things-based artificial intelligence framework for adaptive mechanical process control and real-time performance optimization

Proportional-Integral-Derivative (PID) and Model Predictive Control (MPC) are the conventional methods used for Industrial Process Control (IPC). But these methods often fail to maintain optimal performance when the operating environment is nonlinear and changes dynamically. Internet of Things (IoT) models help with connectivity and monitoring in industry. These models lack predictive decision-making for real-time adaptation, energy efficiency, and early fault detection. This study aims to develop an Artificial Intelligence-Enabled Control System (AI-ECS) that unifies real-time process management, predictive maintenance, and adaptive energy optimization for dynamic industrial environments. AI-ECS integrates IoT sensor networks with hybrid Random Forest (RF) and Long Short-Term Memory (LSTM) algorithms for predictive analytics. Further, real-time feedback control is achieved through dynamically tuned PID and MPC controllers running on an edge-computing platform. An experimental study was done on a continuous-flow industrial process testbed. The setup included multi-rate sensor sampling, Message Queuing Telemetry Transport (MQTT) communication, and containerized edge services. AI-ECS was compared with traditional PID, Advanced Process Control (APC), and IoT-only systems. AI-ECS reduced control error by \(\:73.3\%\) , measured as the relative reduction in Mean Absolute Percentage Error (MAPE) of the process variable relative to its setpoint. Energy Consumption (EC) decreased by \(\:9.1\%\) as well. Early Fault Detection (FD) also improved by a good margin. Anomalies were monitored over a \(\:48\) - hour pre-failure window, and the impending fault was detected up to \(\:36\) hours before failure. The system also presented faster disturbance rejection. Stability was verified across the \(\:24\) - hour and \(\:30\) - day operational windows of the testbed. The AI-ECS gives a reproducible, scalable, and energy-efficient model for intelligent industrial control. It provides a practical method for predictive, self-optimizing, and fault-tolerant manufacturing in accordance with the standards of Industry 4.0 by combining IoT-enabled sensing with adaptive decision-making driven by artificial intelligence (AI).