Raimundo Fernández Gassó

Vertical Roller Mills (VRMs) are extensively used in the cement industry for their high energy efficiency. Nonetheless, the start-up phase remains a critical operational challenge due to its pronounced sensitivity to changing process conditions. Such variations frequently induce excessive vibrations, which can trigger unplanned shutdowns, mechanical damage, and diminished throughput. The underlying cause lies in the intrinsic variability of raw materials, particularly in parameters such as moisture, particle size distribution, and hardness, which exert a direct influence on the mill’s dynamic response during the transition to steady-state operation. This study presents the real-world implementation of an Expert System designed to automate the start-up sequence. By applying logical reasoning to key process setpoints, the system enables a controlled and gradual ramp-up, minimizing transient instabilities. Seamlessly integrated into the plant’s control infrastructure, it facilitates remote unattended operation, enhancing process reliability and operational efficiency. The proposed architecture addresses a key challenge in cement production and enables advanced control and intelligent optimization.

The cement industry, responsible for 26% of industrial CO₂ emissions and 8% of global emissions, is under growing pressure to reduce its environmental footprint while maintaining profitability. In this context, optimizing grinding processes is essential to enhance both the efficiency and sustainability of cement production. This study presents the development of a self-adaptive expert system for closed-loop control, integrating symbolic Artificial Intelligence (AI) and Advanced Process Control (APC) techniques. The system dynamically adjusts operational parameters in real time to minimize the specific energy consumption of cement grinding while meeting quality targets. Notably, it enables autonomous plant operation without direct human supervision, thereby reallocating personnel to higher-value tasks and maintaining optimal performance continuously. The benefits observed following industrial implementation are discussed, alongside an analysis of the key factors influencing grinding performance and productivity. Furthermore, the integration of Artificial Neural Networks (ANNs) and genetic algorithms is proposed as a future enhancement, complementing the expert system through neuro-symbolic approaches. This fusion represents a significant step toward the digital transformation of industrial operations.