Fault Detection and Control in Coal Milling Systems

Coal milling systems, integral to thermal power generation, pulverise raw coal into fine particles for efficient combustion. Their complex dynamics—characterised by nonlinear interactions among primary air flow, mill load, and mechanical wear—pose significant challenges for continuous, safe operation. Fault detection and control aim to identify abnormal conditions such as coal blockage, coal interruption or component wear before they escalate into system downtime or safety hazards. Modern approaches combine first-principles modelling with data-driven analytics, employing inferential “soft sensors” to estimate unmeasurable variables and predictive controls to maintain stable pulverised coal flow. Advanced signal-processing techniques extract fault signatures from vibration, acoustic or temperature signals, while machine-learning algorithms monitor deviations from expected patterns. Together, these methods enhance reliability, reduce maintenance costs and support adaptive responses to varying coal quality and load demands.

Research from Nature Portfolio

Recent studies have extended transient shock modelling and foundation reinforcement principles to industrial milling equipment, highlighting the importance of structural stability for reliable fault management. A transient mill-foundation dynamic model was developed to characterise the effects of shock forces, impact angles and concrete grade on foundation displacement and stress. This work demonstrated that targeted reinforcement schemes, informed by model predictions and validated against experimental data, can significantly reduce vibration amplitudes and prolong the service life of mill components. Such insights underscore the role of integrated mechanical and control strategies in mitigating fatigue-induced faults at the system level.

Fault Detection and Control in Coal Milling Systems publication trend

The graph below shows the total number of articles in fault detection and control in coal milling systems across all publications each year (not limited to Nature Index journals).

Technical terms

Coal mill: Equipment that grinds raw coal into fine particles for combustion in power plants.

Fault detection: Techniques to identify abnormal system states before they lead to failures.

Model-based monitoring: Use of mathematical models to predict system behaviour and detect discrepancies.

Soft sensor: An inferential estimator that computes process variables indirectly from available measurements.

Variational mode decomposition: Signal-processing method that decomposes complex signals into intrinsic mode functions for feature extraction.

References

1. Study on shock vibration analysis and foundation reinforcement of large ball mill. Scientific Reports (2023).
2. A new model-based approach for power plant Tube-ball mill condition monitoring and fault detection. Energy Conversion and Management (2014).
3. Abnormal Condition Monitoring and Diagnosis for Coal Mills Based on Support Vector Regression. IEEE Access (2019).
4. Fault Diagnosis of Coal Mill Based on Kernel Extreme Learning Machine with Variational Model Feature Extraction. Energies (2022).
5. Nonlinear Modeling and Inferential Multi-Model Predictive Control of a Pulverizing System in a Coal-Fired Power Plant Based on Moving Horizon Estimation. Energies (2018).