Study of the Scraper Conveyor Chain Tension Regulation Technique Utilizing Data Fusion

Addressing the insufficient monitoring accuracy and subpar control efficacy in tension management of chains in coal mine scraper conveyors, a novel dynamic and agile adjustment approach based on data fusion is introduced. This method integrates multisource sensory data to form an intelligent decision-making model that blends fuzzy logic with a probabilistic neural network, facilitating precise detection and optimal control of the chain tension states. Initially, sensors measuring force, displacement, and current are strategically placed at pivotal sections of the scraper conveyor to collect multifaceted data pertinent to chain tension. Subsequently, fuzzy logic is applied to perform feature extraction and synthesis of various data types, yielding a comprehensive tension assessment index. Building on this, probabilistic neural networks are utilized for intelligent recognition of chain tension conditions and prediction of future trends. Lastly, tension is dynamically adjusted based on predictive outcomes and real-time feedback, ensuring the chain consistently operates at peak efficiency. This method's data fusion control strategy profoundly taps into the inherent connections among multisource information, overcoming the constraints of a single-source signal. The fusion of complex data via fuzzy logic and the learning and predictive capacities endowed by the probabilistic neural network substantially enhance the precision of tension monitoring and the promptness of control adjustments.