基于传统支持向量机(sVM)训练速度慢、参数选择难等问题，提出了基于极限学习机(ELM)的岩性识别。该算法是一种新的单隐层前馈神经网络(sLFNs)学习算法，不但可以简化参数选择过程，而且可以提高网络的训练速度。-Based on the traditional support vector machine (sVM) training is slow, difficult issues such as parameter selection, extreme learning machine is proposed based on (ELM) of lithology identification. The algorithm is a new single hidden layer feedforward neural network (sLFNs) learning algorithm, not only can simplify the parameter selection process, and can improve the network training speed.