采场支架与顶板状态智能感知研究

It is of great importance to sense the roof weighting, roof caving and support crushing in advance and self-evaluating initial resistance, working resistance for promoting the safety, efficiency and intelligent mining level in longwall penal in our nation. In the present, the research on collecting massive data by the electro-hydraulic shield supports to reflect the supports-roof status is insufficient. Based on scientific issue of intelligent sensing of supports-roof status, this project using the massive data that is collected by the electro-hydraulic controlled two-leg shield supports, data mining and working cycle analysis technique to extract the characteristic parameters, including the increase rates of supporting resistance during different loading stages during a working cycle, the opening of safety valve, the lowering of legs. Then the supporting characteristics of a single support and the law of load transformation and distribution on the longwall panel considering time, geology and support shield itself can be analyzed. On the basis of in-depth explanation on the temporal-sequence curve of supporting resistance and the indicating relationship between support and surrounding rocks, the intelligent sensing model can be constructed based on the artificial neural network and the theory of decision tree.

超前感知综采工作面顶板来压及发生局部冒顶、压架等事故的风险，自主评价初撑力、工作阻力等支护参数的适应性，是提高综采工作面安全性、生产效率以及智能化开采水平的重要基础。当前国内外在通过挖掘电液控制液压支架海量监测数据以反映支架与顶板状态方面的研究仍然不足。项目围绕综采工作面支架与顶板状态智能感知的核心科学问题，基于两柱式电液控制液压支架采集的海量阻力监测数据，结合大数据挖掘及工作循环分析技术，提取包括支架工作循环各承载阶段增阻速率、安全阀开启及活柱下缩特征等在内的多因次工作循环特征参数；进而研究在时间、地质、支架自身特性等多种因素影响下的单台支架承载特征及支架群组载荷转移分布规律；在深入解读支架阻力及活柱下缩时序曲线所蕴含的支架与围岩相互作用关系的基础上，建立基于人工神经网络及决策树理论的支架与顶板状态智能感知模型，实现对支架与顶板状态的智能感知。

超前感知综采工作面顶板来压及发生局部冒顶等事故的风险，自主评价初撑力、工作阻力等支护参数的适应性，是提高综采工作面安全性、生产效率以及智能化开采水平的重要基础。项目围绕综采工作面支架与顶板状态智能感知的核心科学问题，基于综采工作面海量监测数据，开发了综采工作面支架与顶板状态智能感知系统（Status of Shield and Roof IntelliSense system, SSRI），结合大数据挖掘及工作循环分析技术，提出了包括支架工作循环各承载阶段增阻速率、安全阀开启及活柱下缩特征等在内的多因次工作循环特征参数；研究了在初撑力、安全阀开启、割煤及邻架移架、地质等多种因素影响下的单台支架承载特征及支架群组载荷转移分布规律；在深入解读支架阻力及活柱下缩时序曲线所蕴含的支架与围岩相互作用关系的基础上，建立了基于人工神经网络及决策树理论的支架与顶板状态智能感知模型，初步实现了对顶板来压预测、冒顶预警、支架适应性及支护质量评价等支架与顶板状态的智能感知。