Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging

Rotating machinery is widely applied in industrial applications. Fault diagnosis of rotating machinery is vital in manufacturing system, which can prevent catastrophic failure and reduce financial losses. Recently, Deep Learning (DL)-based fault diagnosis method becomes a hot topic. Convolutional Neural Network (CNN) is an effective DL method to extract the features of raw data automatically. This paper develops a fault diagnosis method using CNN for InfRared Thermal (IRT) image. First, IRT technique is utilized to capture the IRT images of rotating machinery. Second, the CNN is applied to extract fault features from the IRT images. In the end, the obtained features are fed into the Softmax Regression (SR) classifier for fault pattern identification. The effectiveness of the proposed method is validated using two different experimental data. Results show that the proposed method has a superior performance in identification various faults on rotor and bearings comparing with other deep learning models and traditional vibration-based method.     

月球表层采样样品智能确认方法

表层采样是月球采样探测的重要方式，样品智能确认有助于提升工作效率与复杂问题处理能力。结合月球表层采样铲挖工作过程，分析了铲挖过程中臂载相机图像的特点，模仿有人参与识别过程，提出了层次解耦的月球样品智能识别流程，利用深度学习方法构建了一类深度卷积识别网络，完整地描述了图像、特征、标记在网络中的正反传递关系，并在月球表层采样地面试验中进行了验证，结果表明该方法对不同光照、不同背景、不同过程、不同形态的样品，具有较好的泛化识别能力，误识别率优于8.1%，平均单幅识别时间约0.7 s。     

智能结构动力系统控制器设计和结构优化的综合分析

通过由两个压电作动器控制的空间桁架,将最优控制问题和结构中杆件截面积动态优化相结合,综合分析了二者的混合优化问题.计算结果表明,在结构动态响应特性不变的条件下,结构重量和控制需求均有显著下降.      

用于钻头刃磨的运动合成方法研究

提出一种六自由度机械手的运动合成方法应用于钻头的刃磨,该方法利用运动的合成形成了刃磨钻头后刀面所需的刃磨运动,从而使得刃磨的调整变得十分方便。刃磨参数可以根据钻尖几何参数对机械手运动方程进行求解得到,刃磨出钻尖的测量结果与理论值基本一致。     

双臂空间机器人可操作度分析及其构型优化

利用传统的操作度概念,分析多臂空间机器人的可操作度,特别是基座和辅助臂的耦合效应对任务机械臂的操作度的影响。进而利用基座姿态最小扰动和可操作度指标对多臂机器人机械臂的构型进行优化。最后对平面双臂空间机器人进行数值仿真,并分析耦合效应对可操作度的影响以及在多臂构型优化中的应用。仿真结果表明本文的研究方法及结果可指导在轨服务中的近距离双臂协调交会、软对接和抓捕操作,具有较强的工程应用价值。     

空间机器人神经网络自适应滑模目标操控轨迹跟踪控制

针对参数未知的空间目标操控问题,考虑空间机器人负载不确定性、系统动力学不确定性和环境扰动等因素,为实现操作过程的稳定控制及机器人轨迹的有效跟踪,提出一种基于径向基神经网络估计不确定项的自适应增益非奇异终端滑模变结构控制器。首先基于拉格朗日法建立空间机器人的刚体动力学模型。考虑空间机器人基座姿态主动控制模式,使用径向基神经网络对模型中的不确定项进行估计。进而提出基于神经网络估计的非奇异终端滑模控制器,并针对不确定性和扰动的估计误差设计自适应增益,以期实现空间机器人系统轨迹跟踪控制的收敛。仿真校验结果表明所设计的控制方法具有较好的误差收敛速度和控制精度。     

低温推进剂加注液位信号智能处理技术研究

低温加注系统是运载火箭发射场地面支持设备的重要组成部分,包括低温介质的储存、运输、供给、控制以及安全等内容。由于低温推进剂本身存在低温沸腾、易挥发的特性,其加注过程十分复杂,为满足新一代运载火箭推进剂精准的加注要求,需要实时准确监测加注过程中贮箱内的液位高度。本文针对火箭地面加注过程的液位信号数据,对其三角波电压和线性波电压的特征进行分析、提取,基于BP（Back Propagation,反向传播）神经网络算法完成对不同加注状态的识别检测,并应用于传感器节数判别,优化了液位计算算法,降低了节数人为干预需求,提高了液位测量准确性。经实验测试验证,该方法可有效识别低温加注状态,识别准确率达到90%以上,用于液位信号处理中可显著提升液位高度计算的准确性。     

管道喷涂机器人:结构与位姿调整

针对工业上大型管道内壁喷涂的需求,设计了用于喷涂管道的机器人,该机器人采用串并联结构形式,由支撑平台和串联机械手组成.支撑平台采用几何的方法建立数学模型,串联机械手采用D-H参数法建模;并在数学模型基础上给出了逆解方程.位姿调整时,对机器人进行初定位,利用激光跟踪仪测量出管道和机器人的位姿,求解出调整量,对机器人进行位姿调整,使喷枪旋转轴和管道轴线重合.管道喷涂机器人在工厂进行试验测试,测试结果表明该装备可以很好地实现管道的喷涂,提高喷涂质量和效率.      

High-adaption locomotion with stable robot body for planetary exploration robot carrying potential instruments on unstructured terrain

There is a strong demand for Planetary Exploration Mobile robots (PEMRs) that have the capability of the traversability, stability, efficiency and high load while tackling the specialized tasks on planet surface. In this paper, an electric parallel wheel-legged hexapod robot which has high-adaption locomotion on the unstructured terrain is presented. Also, the hybrid control framework, which enables robot to stably carry the heavy loads as well as to traverse the uneven terrain by utilizing both legged and wheeled locomotion, is also proposed. Based on this framework, robot controls the multiple DOF leg for performing high-adaption locomotion to negotiate obstacles via Gait Generator (GG). Additionally, by using Whole-Body Control (WBC) of framework, robot has the capability of flexibly accommodating the uneven terrain by Attitude Control (AC) kinematically adjusting the length of legs like an active suspension system, and by Force/torque Balance Control (FBC) equally distributing the Ground Reaction Force (GRF) to maintain a stable body. The simulation and experiment are employed to validate the proposed framework with the physical system in the planetary analog environments. Particularly, to smoothly demonstrate the performance of robot transporting heavy loads, the experiment of carrying 3-person load of about 240 kg is deployed.