ID 原文 译文
52917 在动态环境下，提出重规划策略使机器人拥有动态避障能力。 In dynamic environment, the reprogramming strategy is proposed to enable the robot to have dynamic obstacle avoidance ability.
52918 最后，在树莓派智能小车上进行了实验测试，结果验证了该算法的有效性。 Finally, the experiment is carried out on the Raspberry Pi smart car. The results show that the algorithm is effective.
52919 为了在全负载范围下高效率地驱动规则及不规则LED阵列，基于能馈式LED阵列驱动接口电路提出一种可最高效率点跟踪的控制策略，使能馈式LED阵列驱动接口电路在负载发生变化的情况下仍可工作在最高效率点。 In order to efficiently drive the regular and irregular LED arrays under the full load range, a control strategy based on the energy recycle LED matrix driving circuit that can track the maximum-efficiency operation point is proposed to enable the driving circuit work at the maximum-efficiency point at the load under changing circumstances.
52920 在负载组合已知的前提下基于RGBLED负载切换可实现调光调色，建立了反向传播(BP)神经网络负载控制的调光调色模型。 The brightness and color control can be achieved based on RGBLED load switching, and a load-controlled brightness and color control model of back propagation(BP) neural network is established.
52921 制作了 24 V输入、3通道输出、开关频率为100 kHz的能馈式RGBLED通道电路样机并搭建了相应的取色平台。 A RGBLED channle circuit prototype with 24 V input, 3 channel output, and a switching frequency of 100 kHz is made and the corresponding color extraction platform is built.
52922 实验结果表明，最高效率点跟踪的能馈式LED阵列驱动接口电路可利用神经网络负载控制模型实现有限空间下的调光调色。 The experimental results show that the energy-recycle interface circuit for LED matrix driving under maximum-efficiency operation point tracking control can realize the brightness and color control in limited space by using the neural network load control model.
52923 地质分层是指对某一个地区的地层剖面中的岩层进行划分，可用于指导相应的地质找矿工作。 Geological stratification aims to divide the rock layers in the stratum section of a certain area, which is of great significant to the problem of geological prospecting.
52924 传统的地质分层主要依靠专家根据经验进行人工判断，然而由于地质层位类别繁多，需要消耗大量的时间和人力成本。 However, considering that there exists a variety of geological horizons, and traditional geological stratification relies heavily on subjective judgment of the expert, performing geological stratification is time-consuming and knowledge-intensive work.
52925 现有的地质层位自动识别方法，由于没能考虑到测井数据的序列关系以及地质层位分布的特点，导致识别效果较差。 Existing automatic geological stratification methods fail to consider the sequence relationship of well logging data and the characteristics of geological horizon distribution, thus making classification accuracy unable to reach the state-of-the-art level.
52926 基于此，本文提出了一种改进的双向长短期记忆神经网络(BiLSTM)的地质片段层位预测方法，可以根据测井数据自动快速地进行地质分层预测。 Based on the above background, an improved bidirectional long-short memory neural network(BiLSTM) for geological horizon prediction is proposed.