【标题】Knowledge and data dual-driven transfer network for industrial robot fault diagnosis
【参考中译】用于工业机器人故障诊断的知识和数据双驱动传输网络
【类型】 期刊
【关键词】 Knowledge driven; Data driven; Industrial robot; Fault diagnosis; Transfer learning
【参考中译】 知识驱动；数据驱动；工业机器人；故障诊断；迁移学习
【作者】 Tao Yin; Na Lu; Guangshuai Guo; Yaguo Lei; Shuhui Wang; Xiaohong Guan
【摘要】 Various deep transfer learning solutions have been developed for machine fault diagnosis, which are purely data driven. Plenty of prior knowledge on the fault of different machinery parts has been summarized in previous research. The value of these prior knowledge has not been ever deeply explored in the existing deep transfer solutions, which might greatly facilitate the training progress and improve the diagnosis performance of network models. However, how to represent and incorporate prior knowledge into deep models remains a challenge. To address this problem, a knowledge and data dual-driven transfer network for fault diagnosis is developed in this paper. The prior frequency knowledge of fault signal is extracted by envelope analysis and pass band selection. Based on which, a band-pass filter based embedding method is proposed to incorporate the prior knowledge by imprinting the convolutional kernels with the designed filters. A dual channel weight shared deep adaptation network is constructed to perform the prior knowledge embedding and knowledge transfer across domains. Multi-kernel maximum mean discrepancy (MK-MMD) is adopted for domain adaption. A symmetry constraint is used to reserve the linear phase property of the band-pass kernels. The constructed network combines data driven and knowledge driven mechanism which is termed as Knowledge and Data Dual-driven Transfer Network (KDDT Network). Extensive experiments have been performed on an industrial robot rotate vector (RV) reducer dataset collected in our laboratory and some bearing benchmarks. Comparisons results with the state-of-the-art methods have shown the superiority of the proposed method.
【参考中译】 已有各种深度迁移学习解决方案被开发用于机器故障诊断，它们纯粹是数据驱动的。在以往的研究中，已经总结了大量关于不同机械部件故障的先验知识。这些先验知识的价值在现有的深度迁移解决方案中没有得到深入的挖掘，这可能会极大地促进网络模型的训练进度，提高网络模型的诊断性能。然而，如何将先验知识表示并结合到深层模型中仍然是一个挑战。针对这一问题，本文提出了一种知识和数据双驱动的故障诊断传输网络。通过包络分析和通带选择提取故障信号的先验频率知识。在此基础上，提出了一种基于带通滤波器的嵌入方法，通过在卷积核上嵌入所设计的滤波器来融合先验知识。构建了一个双通道权重共享深度适应网络，用于先验知识嵌入和跨域知识转移。域自适应采用多核最大均值差(MK-MMD)算法。对称约束被用来保留带通核的线性相位特性。构建的网络将数据驱动和知识驱动机制相结合，称为知识和数据双驱动传输网络(KDDT Network)。在实验室收集的工业机器人旋转矢量减速器数据集和一些轴承基准上进行了广泛的实验。与最新方法的比较结果表明了该方法的优越性。
【来源】 Mechanical Systems and Signal Processing 2023, vol.182
【入库时间】 2023/4/27
【标题】Discriminative feature learning using a multiscale convolutional capsule network from attitude data for fault diagnosis of industrial robots
【参考中译】用于工业机器人故障诊断的多尺度卷积胶囊网络鉴别特征学习
【关键词】 Fault diagnosis; Industrial robot; Attitude; Multiscale convolutional neural network; Capsule network
【参考中译】 故障诊断；工业机器人；姿态；多尺度卷积神经网络；胶囊网络
【作者】 Jianyu Long; Yaoxin Qin; Zhe Yang; Yunwei Huang; Chuan Li
【摘要】 Effective fault diagnosis is important to ensure the reliability, safety, and efficiency of industrial robots. This article proposes a simple yet effective data acquisition strategy based on transmission mechanism analysis, using only one attitude sensor mounted on an end effector or an output component to monitor the attitude of all transmission components. Unlike widely used vibration-monitoring signals, attitude signals can provide fault features reflecting spatial relationships. Using one attitude sensor facilitates the data collection, but weakens fault features and introduces strong background noise in attitude signals. To learn discriminative features from the attitude data collected by the attitude sensor, a multiscale convolutional capsule network (MCCN) is proposed. In MCCN, integrating low-level and high-level features in a convolutional neural network (CNN) as multiscale features is conductive to noise reduction and robust feature extraction, and a capsule network (CapsNet) is used to recognize the spatial relationships in attitude data. The extracted multiscale features in CNN and the spatial-relational features in CapsNet are fused for effective fault diagnosis of industrial robots. The performance of MCCN is evaluated by attaching a softmax-based classifier and integrating it into different transfer learning frameworks to diagnose faults in industrial robots under single and variable working conditions, respectively. Fault diagnosis experiments were conducted on a 6-axis series industrial robot and a parallel robot-driven 3D printer. The superiority of the proposed MCCN was demonstrated by comparing its performance with the other feature learning methods.
【参考中译】 有效的故障诊断对于保证工业机器人的可靠性、安全性和高效性具有重要意义。本文在分析传动机构的基础上，提出了一种简单而有效的数据采集策略，只需在末端执行器或输出部件上安装一个姿态传感器来监测所有传动部件的姿态。与广泛使用的振动监测信号不同，姿态信号可以提供反映空间关系的故障特征。使用一个姿态传感器便于数据采集，但削弱了故障特征，并在姿态信号中引入了较强的背景噪声。为了从姿态传感器采集的姿态数据中学习可区分的特征，提出了一种多尺度卷积胶囊网络。在MCCN中，将低层特征和高层特征集成在卷积神经网络(CNN)中作为多尺度特征有助于降噪和稳健的特征提取，而胶囊网络(CapsNet)用于识别姿态数据中的空间关系。将CNN中提取的多尺度特征与CapsNet中的空间关系特征进行融合，实现了工业机器人的有效故障诊断。通过加入基于Softmax的分类器并将其集成到不同的转移学习框架中来评估MCCN的性能，分别在单一和可变工作条件下诊断工业机器人的故障。在六轴串联工业机器人和并联机器人驱动的3D打印机上进行了故障诊断实验。通过与其他特征学习方法的性能比较，证明了MCCN的优越性。
【标题】Real-time path correction of industrial robots in machining of large-scale components based on model and data hybrid drive
【参考中译】基于模型和数据混合驱动的大型零件加工工业机器人实时路径修正
【关键词】 Link position estimation; Flexible dynamics; Data-driven prediction; Path correction; Industrial robots
【参考中译】 链接位置估计；柔性动力学；数据驱动预测；路径修正；工业机器人
【作者】 Yang Lin; Huan Zhao; Han Ding
【摘要】 Industrial robots are increasingly used in machining of large-scale components due to advantages of high repeatability, large workspace and low cost. Nevertheless, applying industrial robots to high-accuracy machining of large-scale components remains a challenge, where the major hurdle is the insufficient manipulator stiffness due to joint flexibility. When the robot is performing a machining task, joint flexibility-induced position errors between motor and link called joint position errors (JPEs), as the main source of robot deformations, make the robot deviate from the desired path. For most industrial robots, due to the lack of link-side encoders, it is difficult to obtain the JPEs by direct measurement and compensate them in the controller, which deteriorates the path accuracy of the robot during machining greatly. To address this problem, this paper presents a realtime path correction approach of industrial robots based on JPE estimation and compensation with requiring only motor-side measurements and external wrenches. The proposed approach is divided into three steps. First, to estimate the actual link position of the robot in real-time, the dynamics of a manipulator with joint flexibility called flexible dynamics (FD) is introduced. Second, by taking both FD and disturbance dynamics into account, a novel link state estimator called flexible-dynamics based disturbance Kalman filter (FDBDKF) is developed, and thus JPEs can be estimated in real-time. Third, a data-driven locally weighted projection regression (LWPR)-based JPE prediction and compensation method is developed to further improve the compensation accuracy of the JPEs. Simulation and experimental results, obtained on a 6-DOF industrial robot, demonstrate the feasibility and effectiveness of the proposed approach. Experimental results show significant improvement (>80%) in the path accuracy of a simple material removal process corrected using the proposed approach.
【参考中译】 工业机器人以其重复性高、工作空间大、成本低等优点被越来越多地应用于大型零件的加工。然而，将工业机器人应用于大型零部件的高精度加工仍然是一个挑战，其中的主要障碍是由于关节灵活性而导致的机械手刚度不足。当机器人执行加工任务时，关节柔性引起的电机和连杆之间的位置误差称为关节位置误差(JPEs)，它是机器人变形的主要来源，使机器人偏离预期路径。对于大多数工业机器人来说，由于缺乏链路端编码器，直接测量JPE并在控制器中进行补偿是困难的，这极大地恶化了机器人在加工过程中的路径精度。针对这一问题，本文提出了一种基于JPE估计和补偿的工业机器人实时路径修正方法，只需要电机侧测量和外部扳手。建议的方法分为三个步骤。首先，为了实时估计机器人的实际连杆位置，引入了具有关节柔性的机械手动力学，称为柔性动力学(FD)。其次，综合考虑故障检测和干扰动态，提出了一种新的链路状态估计器--基于柔性动力学的干扰卡尔曼滤波(FDBDKF)，实现了JPEs的实时估计。第三，提出了一种基于数据驱动局部加权投影回归(LWPR)的JPE预测与补偿方法，进一步提高了JPE的补偿精度。在六自由度工业机器人上的仿真和实验结果证明了该方法的可行性和有效性。实验结果表明，使用该方法修正的简单材料去除过程的路径精度有显著提高(>80%)。
【来源】 Robotics and Computer-Integrated Manufacturing 2023, vol.79