College of Computer Science and Technology, Xi'an University of Science and Technology
College of Mechanical Engineering, Xi'an University of Science and Technology

采煤机自适应截割技术是实现综采工作面智能化开采的关键技术。针对采煤机在复杂煤层下自动截割精度较低的问题，提出了一种基于改进门控循环神经网络（GRU）的采煤机滚筒调高量预测方法。鉴于截割轨迹纵向及横向相邻数据之间的相关性，采用定长滑动时间窗法对获取的采煤机滚筒高度数据进行预处理，将输入数据划分为连续、大小可调的子序列，同时处理横向、纵向的特征信息。为提高模型预测效率，满足循环截割的实时性要求，提出了一种用因果卷积改进的门控循环神经网络（CC−GRU），对输入数据进行双重特征提取和双重数据过滤。CC−GRU利用因果卷积提前聚焦序列纵向的局部时间特征，以减少计算成本，提高运算速度；利用门控机制对卷积得到的特征进行序列化建模，以捕捉元素之间的长期依赖关系。实验结果表明，采用CC−GRU模型对采煤机滚筒调高量进行预测，平均绝对误差（MAE）为43.80 mm，平均绝对百分比误差（MAPE）为1.90%，均方根误差（RMSE）为50.35 mm，决定系数为0.65，预测时间仅为0.17 s；相比于长短时记忆（LSTM）神经网络、GRU、时域卷积网络（TCN），CC−GRU模型的预测速度较快且预测精度较高，能够更准确地对采煤机调高轨迹进行实时预测，为工作面煤层模型的建立和采煤机调高轨迹的预测提供了依据。

The adaptive cutting technology of the shearer is a key technology for achieving intelligent mining in fully mechanized working faces. In order to solve the problem of low automatic cutting precision of the shearer in complex coal seams, a prediction method for the height adjustment of shearer drum based on improved gated recurrent neural network (GRU) is proposed. Considering the correlation between adjacent data in the longitudinal and transverse directions of the cutting trajectory, the fixed length sliding time window method is used to obtain the height data of the shearer drum. The input data is divided into continuous and adjustable subsequences, while processing the feature information in the transverse and longitudinal directions. To improve the prediction efficiency of the model and meet the real-time requirements of cyclic cutting, causal convolution gated recurrent unit(CC-GRU) is proposed to perform dual feature extraction and dual data filtering on input data. CC-GRU utilizes causal convolution to focus on the local temporal features in the longitudinal direction of the sequence in advance, in order to reduce computational costs and improve computational speed. CC-GRU uses gating mechanism to serialize and model the features obtained from convolution to capture long-term dependencies between elements. The experimental results show that using the CC-GRU model to predict the height adjustment of the shearer drum, the MAE is 43.80 mm, MAPE is 1.90%, RMSE is 50.35 mm, the determination coefficient is 0.65, and the prediction time is only 0.17 seconds. Compared to long short term memory (LSTM) neural networks, GRU, and temporal convolutional network (TCN), the CC-GRU model has a faster prediction speed and higher prediction precision. It can more accurately predict the height adjustment trajectory of the shearer in real time. This provides a basis for the establishment of coal seam models in the working face and the prediction of the height adjustment trajectory of the shearer.

国家自然科学基金资助项目(61674121)。

齐爱玲，王雨，马宏伟. 基于改进门控循环神经网络的采煤机滚筒调高量预测[J]. 工矿自动化，2024，50（2）：116-123.

QI Ailing, WANG Yu, MA Hongwei. Prediction of height adjustment of shearer drum based on improved gated recurrent neural network[J]. Journal of Mine Automation，2024，50（2）：116-123.