234 1. INTRODUCTION China currently maintains a coal-dominant energy structure, with coal continuing to serve as a cornerstone in both the national energy mix and the economy [1,2]. Steeply dipping and acutely inclined coal seams are internationally recognized as challenging mining conditions and are extensively distributed in provinces such as Sichuan, Guizhou, Xinjiang, and Gansu. The safe and efficient extraction of these coal seams is of significant importance for ensuring high-quality regional socioeconomic development. Intelligent mining serves as the core technological driver for the high-quality advancement of the coal industry. Consequently, enhancing the automation and intelligence of mining equipment represents an inevitable pathway for the future development of extracting such geologically complex coal seams in China [3,4]. Digital twin technology refers to the use of data to drive virtual models in a digital space to replicate the behavior of corresponding physical entities, thereby enabling the observation, prediction, and optimization of these entities [5,6]. Today, digital twin technology has been widely applied in fields such as industry and manufacturing and is expanding into the mining sector. For example, in the context of intelligent mine construction, MARARCO developed a virtual reality design and analysis system for mining engineering using real mine data to simulate the design, construction, and extraction phases of mining projects [7]. A design and operational model for fully mechanized mining face production systems based on digital twin technology has been proposed, which can optimize system design and operational efficiency while enabling collaborative operation among equipment [8,9]. Subsequently, the concept, architecture, and implementation methods of digital twin-based intelligent mining face systems were introduced, further extending the application of digital twins in intelligent mining [10-13]. By integrating digital twin technology with deep learning, a method for predicting shearer health status was developed through the construction of a digital twin body, enabling virtual visualization and predictive analysis of the shearer’s condition [14-16]. Virtual simulation of fully mechanized mining face production systems based on digital twin technology has taken initial shape, allowing for the optimization of shearer cutting paths and the pre-evaluation of various mining processes [17,18]. Additionally, a laboratory "supportsurrounding rock" digital twin simulation test platform was developed and tested. This platform can simulate the "support-surrounding rock" environment under varying inclination angles in a laboratory setting, dynamically monitor the posture and status of hydraulic supports, simulate periodic and dynamic roof pressure, and support the development of new hydraulic support designs [19]. Due to the steep inclination of steeply dipping coal seam faces and the complexity of equipment stability control processes, higher demands are placed on support anti-toppling, anti-skidding, and steady-state control. Therefore, this study integrates digital twin technology in a laboratory environment to conduct a physical similarity simulation experiment on hydraulic supports in steeply dipping conditions. This enables the perception of the
RkJQdWJsaXNoZXIy MTM0Mzk2