摘要
大部分采煤机采煤产量运用称重法来评估,该评估方式可随时调节采煤机姿态,实时控制采煤机。称重仅在生产过程完成后进行,对采煤机实时效率的监控起不到应有的作用。根据采煤机在采煤过程中牵引电机在行走过程中的电机电流、速度、温度以及截割电机的截割电流和温度等相关参数,运用多元统计理论及神经网络算法,建立相关数学模型,预测采煤产量,将模型潜入到采煤机控制过程,在线监测采煤机产量与其耗能的比例关系,以便使采煤机效率最大化。通过对井下采煤机产量参数测量,运用多元统计理论建立多元统计模型来预测和控制采煤机工作过程中的产量,使采煤机的产量测量走向机械化和智能化。
Gravimetric method was conducted to assess shearer mining production output, which could adjust shearer gesture anytime and get shearer under real time control, weighing only after the completion of the production process. But, it cannot monitor shearer real time effciency. According to the process of walking the shearer in the coal mining process, speed, temperature, cutting motor cutting current and temperature parameters combining the use of multivariate statistical theory, established mathematical model and predicted mining coal production model to the shearer control process, the online ratio between shearer production and its energy could be monitored, this assessment can optimize shearer efficiency and get more real time control of shearer. This thesis utilized the multivariate statistical theory to make a multivariate statistical mode, which was used to predicate and control the output of the mine shearer through measuring the output parameters of mine shearer, making mine shearer＇ s output become more mechanized and intellectualized.
出处
《煤炭与化工》
CAS
2013年第1期22-24,共3页
Coal and Chemical Industry
基金
河北省自然基金(E2010001030)
关键词
井下采煤机
多元统计理论
多元统计模型
控制过程
高产高效
机械化
mine shearer
multivariate statistical theory
multivariate statistical mode
control process
high output and efficiency
mechanization
