基于极点配置的推力矢量伺服系统控制策略研究

针对推力矢量伺服系统提出了一种采用状态反馈对系统极点进行配置的方法,同时采用该方法设计了Luenberger状态观测器,在此基础上实现了伺服系统的稳态控制。通过仿真和实验表明,采用该方法设计的推力矢量伺服系统的性能优于基于输出反馈的PI-陷波滤波控制的系统性能。     

Adaptive neuro-fuzzy algorithm applied to predict and control multi-phase flow rates through wellhead chokes

A Takagi-Sugeno adaptive neuro-fuzzy inference system (TSFIS) model is developed and applied to a dataset of wellhead flow-test data for the Resalat oil field located offshore southern Iran, the objective is to assist in the prediction and control of multi-phase flow rates of oil and gas through the wellhead chokes. For this purpose, 182 test data points (Appendix 1) related to the Resalat field are evaluated. In order to predict production flow rate (Q_L) expressed as stock-tank barrels per day (STB/D), this dataset includes four selected input variables: upstream pressure (Pwh); wellhead choke sizes (D64); gas to liquid ratio (GLR); and, base solids and water including some water-soluble oil emulsion (BS&W). The test data points evaluated include a wide range of oil flow rate conditions and values for the four input variables recorded. The TSFIS algorithm applied involves five data processing steps: a) pre-processing, b) fuzzification, c) rules base and adaptive neuro-fuzzy inference engine, d) defuzzification, and e) post-processing of the fuzzy model. The developed TSFIS model for the Resalat oil field database predicted oil flow rate to a high degree of accuracy (root mean square error = 247 STB/D, correlation coefficient = 0.9987), which improves substantially on the commonly used empirical algorithms used for such predictions. TSFIS can potentially be applied in wellhead choke fuzzy controllers to stabilize flow in specific wells based on real-time input data records.     

基于机器视觉的运煤车车号识别技术研究

在铁路运煤装车过程中为了快速、准确地识别车号,提出一种基于机器视觉的运煤车车号识别技术。将连通区域提取与投影分割法结合,实现车号的粗定位、细分割,并对图像中的断裂字符进行二次分割,构建了基于BP神经网络的分类模型进行车号识别,提升了煤炭装车的效率和精度。     

二层沟槽织构对机床导轨表面润滑特性的影响

通过构建二层沟槽织构模型，仿真研究沟槽织构表面的流体动力效应。结果表明：沟槽容积相同时，与单层沟槽相比，二层沟槽的平均油膜压力可以达到单层沟槽的2.31倍；保持二层沟槽的量纲一总深度[β]1、第一层沟槽量纲一宽度[α]1不变时，随着第二层量纲一深度[β]2的增大，平均油膜压力先增大后减小，[β]2为4.4时，平均油膜压力达到最大值；第二层沟槽的量纲一宽度[α]2从0.25增大到0.45时，沟槽内的旋涡区也随之增大，平均油膜压力逐渐减小。     

三维增材鞋面印花机对位平台的冗余驱动控制策略

针对自动鞋面印花机在进行对版时定位精度低,影响鞋面印刷质量的问题,提出了基于冗余驱动的印花机对位平台。在原有的三轴并联机构对位平台的基础上通过增加1个Y轴,有效地提高了对位平台Y向的刚度和承载能力,从而提高了印花机对位平台的定位精度。由于冗余驱动机构运动过程中存在机构运动耦合,利用几何法进行解耦,提出了基于电子凸轮的控制策略。同时提出了对机构换向间隙补偿的控制策略,进一步提高对位平台的定位精度,保证了鞋面的印刷质量。经过实验验证,改进后的印花机对位平台Y向定位精度提高了85.7%,Z向旋转定位精度提高了72.9%,X向和Y向换向间隙分别提高了50% 和75%,Z向旋转换向间隙提高了42.86%。     

神经网络全局势函数在多相催化中的应用

当今的多相催化研究需要新的技术和方法从原子尺度上表征活性中心结构和反应中间体。本文作者课题组近期开发了理论模拟新技术来探索催化剂活性位点结构，即基于神经网络势函数的大规模原子模拟（LASP）软件中实现的全局神经网络势函数计算方法。本文介绍了该方法可以显著降低催化体系的计算代价，而维持与密度泛函理论同一级别的计算精度，从而解决多相催化中的许多复杂问题。本文对神经网络势函数方法的实现细节和目前已实现的应用场景进行了详细介绍。神经网络势函数可以用来预测材料晶体结构，理解高压氢化条件下TiO₂表面的结构演化和确定三元氧化物ZnCrO晶相中合成气制甲醇活性位点。最后文章分析了神经网络势函数的局限性和今后可能的三个研究方向，即材料性质预测、多元素体系神经网络势函数构造和化学反应拟合。     

Design of delayed reconfigurable manufacturing system based on part family grouping and machine selection

To improve the convertibility of reconfigurable manufacturing system (RMS), the concept of delayed reconfigurable manufacturing system (D-RMS) was proposed. RMS and D-RMS are both constructed around part family. However, D-RMS may suffer from ultra-long system problem with unacceptable idle machines using generic RMS part families. Besides, considering the complex basic system structure of D-RMS, machine selection of D-RMS should be addressed, including dedicated machine, flexible machine, and reconfigurable machine. Therefore, a system design method for D-RMS based on part family grouping and machine selection is proposed. Firstly, a part family grouping method is proposed for D-RMS that groups the parts with more former common operations into the same part family. The concept of longest relative position common operation subsequence (LPCS) is proposed. The similarity coefficient among the parts is calculated based on LPCS. The reciprocal value of the operation position of LPCS is adopted as the characteristic value. The average linkage clustering (ALC) algorithm is used to cluster the parts. Secondly, a machine selection method is proposed to complete the system design of D-RMS, including machine selection rules and the dividing point decision model. Finally, a case study is given to implement and verify the proposed system design method for D-RMS. The results show that the proposed system design method is effective, which can group parts with more former common operations into the same part family and select appropriate machine types.     

[可靠性建模及试验技术]重型机床液压元件油液污染退化量分布剖面可靠性建模

针对重型机床液压系统故障频繁且多与油液中的固态颗粒污染物相关的问题，进行了油液污染趋势变化试验。通过时域分析获得了油样颗粒数的有量纲和量纲一参数，通过Q-Q图和K-S检验分析有量纲参数，污染颗粒数是退化量服从正态分布的退化数据。进行了油液污染与环境相关性分析试验，采用相关系数法分析得到，颗粒数变化量与一定范围内的温度、流量、压力的相关性小；将液压元件分为管路、阀、过滤器三类，用直径5 μm左右的颗粒和直径大于15 μm的颗粒分别研究管路及阀件的堵塞和磨损情况，以过滤器过滤精度大小的颗粒研究过滤器的堵塞情况，设定ISO4406标准20/17级对应的颗粒数为阈值，利用退化量分布建立了液压元件单一故障模式的可靠性模型；利用竞争失效模型将上述模型融合为多故障模式下的可靠性模型。     

结合深度学习与支持向量机的金属零件识别

目的 在视觉引导的工业机器人自动拾取研究中，关键技术难点之一是机器人抓取目标区域的识别问题。特别是金属零件，其表面的反光、随意摆放时相互遮挡等非结构化因素都给抓取区域的识别带来巨大的挑战。因此，本文提出一种结合深度学习和支持向量机的抓取区域识别方法。方法 分别提取抓取区域的方向梯度直方图（HOG）和局部二进制模式（LBP）特征，利用主成分分析法（PCA）对融合后的特征进行降维，以此来训练支持向量机（SVM）分类器。通过训练Mask R-CNN（regions with convolutional neural network）神经网络完成抓取区域的初步分割。然后利用SVM对Mask R-CNN识别的抓取区域进行二次分类，完成对干扰区域的剔除。最后计算掩码完成实例分割，以此达到对抓取区域的精确识别。结果 对于随机摆放的铜质金属零件，本文算法与单一的Mask R-CNN及多特征融合的SVM算法就识别准确率、错检率、漏检率3个指标进行了比较，结果表明本文算法在识别准确率上较Mask R-CNN和SVM算法分别提高了7%和25%，同时有效降低了错检率与漏检率。结论 本文算法结合了Mask R-CNN与SVM两种方法，对于反光和遮挡情况具有一定的鲁棒性，同时有效地提升了目标识别的准确率。