Research on Intelligent Safety Management Innovation Enabled by Artificial Intelligence and Forklift Internet of Things: A Data-Driven Risk Prediction Perspective
Abstract
To address the prominent pain points of high accident frequency, lagging hazard early warning, and extensive empirical management in traditional forklift operation safety management, this paper proposes a full-process intelligent safety management innovation framework enabled by artificial intelligence (AI) and forklift Internet of Things (IoT), from the perspective of data-driven risk prediction. Against the background of deep integration of Industry 4.0 and intelligent logistics, the framework takes industrial safety governance theory and systems engineering methodology as theoretical guidance, and realizes deep integration of multi-source forklift IoT perception data, standardized full-link data governance, and AI-driven quantitative risk prediction models through a four-layer edge-cloud collaborative architecture. On the basis of data standardization and quality control, it constructs four core mathematical models: multi-dimensional operation risk assessment, improved XGBoost collision risk prediction, dynamic early warning resource scheduling optimization, and comprehensive safety performance evaluation, and builds a closed-loop management mechanism of "perception-analysis-warning-disposal-evaluation". Experimental validation based on real large-scale warehouse logistics scenarios shows that the framework significantly improves data integrity and consistency, reduces the overall accident rate of forklift operations by more than 65%, shortens the response time of safety incidents by over 80%, and enhances the scientificity and foresight of safety management decisions. The research results provide a feasible technical implementation path for the digital and intelligent transformation of industrial site safety management, and have important reference value for promoting the application of AI and IoT technologies in the field of industrial safety.