论文部分内容阅读
针对采煤机截割路径的规划问题,提出了一种基于煤层分布预测的采煤机截割路径规划方法.建立了多输入、单输出的最小二乘支持向量机(LS-SVM)滚动预测模型,并将混沌粒子群算法用于LS-SVM参数的优化,以提高LS-SVM的预测性能.采用一种3次B样条对煤层分布的LS-SVM预测值进行拟合优化,从而得到足够平滑的曲线作为采煤机截割路径.结果表明:LS-SVM预测结果的最大相对误差为4.52%,平均误差为2.36%,满足工程要求;以3次B样条优化后的煤层分布曲线作为截割路径,可以及时调节滚筒高度,其截割电流最大为76.27A,比人工控制方法降低了10.27%,且持续时间较短.通过在中平能化集团十三矿11070工作面的试验验证,提出的方法能够用于采煤机截割路径的规划,对促进综采工作面自动化生产具有十分重要的意义.
In order to solve the planning problem of shearer’s cutting path, a cut-path planning method based on coal seam distribution prediction is proposed, and a LS-SVM rolling forecasting method with multi-input and single-output is established. Model, and the chaos particle swarm optimization algorithm is used to optimize the parameters of LS-SVM to improve the prediction performance of LS-SVM. A cubic B-spline is used to fit and predict LS-SVM predicted values of coal seam distribution, The results show that the maximum relative error of LS-SVM prediction is 4.52% and the average error is 2.36%, which meets the engineering requirements. The coal seam distribution curve optimized by 3 times B-spline As the cutting path, the height of the drum can be adjusted in time, the maximum cutting current is 76.27A, which is 10.27% lower than the manual control method, and the duration is short.According to the experiment of 11070 working face of Zhongming Nengping Group 13 Mine, The proposed method can be used for the planning of shearer cutting path, which is of great significance to the automated production of fully mechanized mining face.