The accuracy of high-precision optical processing robots is influenced by various factors, including static error factors and dynamic error factors. These factors pose significant challenges to the deterministic processing of precision optics. This article proposes a pose residual prediction model for optical processing hybrid robots based on deep spatio-temporal graph convolutional neural networks. In this study, we establish a geometric error model for hybrid robots and calibrate the geometric error parameters using an extended Kalman filter to obtain the pose residuals component. To address the complex spatio-temporal interactions between multiple sensor variables in joint space during robot motion, we introduce the non-Euclidean spatio-temporal graph convolutional neural network. This model effectively extracts advanced spatio-temporal interaction features based on a spatio-temporal attention mechanism. Finally, the performance of the proposed method in pose residual prediction was validated through real experiments, and the results demonstrated its advantages over other state-of-the-art methods.

@en

Autonomous navigation of Micro Aerial Vehicles (MAVs) in dynamic and unknown environments is a complex and challenging task. Current works rely on assumptions to solve the problem. The MAV's pose is precisely known, the dynamic obstacles can be explicitly segmented from static ones, their number is known and fixed, or they can be modeled with given shapes. In this paper, we present a method for MAV navigation in dynamic uncertain environments without making any of these assumptions. The method employs a particle-based dynamic map to represent the local environment and predicts it to the near future. Collision risk is defined based on the predicted maps and a series of risk-aware spatio-temporal (RAST) safety corridors are constructed, which are finally used to optimize a dynamically-feasible collision-free trajectory for the MAV. We compared our method with several state-of-the-art works in 12000 simulation tests in Gazebo with the physical engine enabled. The results show that our method has the highest success rate at different uncertainty levels. Finally, we validated the proposed method in real experiments.@en

To overcome the bearing capacity deficiencies of traditional serial hip joint simulators, complex trajectory simulation, among others, as well as a parallel manipulator with two pairs of artificial hip joints and two moving platforms are proposed. The movements and driving forces of the parallel manipulator under the required motion and loading are studied to provide a basis for further research. In this study, the modeling and analysis of inverse kinematics and dynamics for a parallel manipulator with joint friction are derived. In the inverse kinematic model, kinematic relationships between the linear module slider and the moving platform are established, and expressions for the slider are deduced. Subsequently, by analyzing the frictional forces of the artificial hip joint and thrust ball bearing, a rigid body dynamics model of the parallel manipulator with joint friction is established, which is subsequently decomposed into four driving torques associated with the moving platform, joint lever, slider, and screw. Finally, the difference in the kinematic performance between the two moving platforms is analyzed using numerical simulations and experiments, and the accuracy of the established model is verified@en

The most common failures of belt conveyors are runout, coal piles and longitudinal tears. The detection methods for longitudinal tearing are currently not particularly effective. A key study area for minimizing longitudinal belt tears with the advancement of machine learning is how to use machine vision technology to detect foreign items on the belt. In this study, the real-time detection of foreign items on belt conveyors is accomplished using a machine vision method. Firstly, the KinD++ low-light image enhancement algorithm is used to improve the quality of the captured low-quality images through feature processing. Then, the GridMask method partially masks the foreign objects in the training images, thus extending the data set. Finally, the YOLOv4 algorithm with optimized anchor boxes is combined to achieve efficient detection of foreign objects in belt conveyors, and the method is verified as effective.

@en

Aiming at a 5-DOF hybrid optical mirror polishing robot, the explicit dynamic model considering the joint friction is established and the inertia coupling distribution is studied. Firstly, the kinematics of the manipulator is solved based on closed-loop vector method, and the dynamic model is established with Newton-Euler method based on the force analysis of manipulator components. Secondly, the kinematic parameters of the reference point of the moving platform are selected as the intermediate variables, and the explicit dynamic model of the parallel manipulator is obtained by parameters substitution considering the friction effects of spherical joints, universal joints and ball screws. Finally, on the basis of the dynamic model, the inertia coupling strength evaluation index for active branched-chains is proposed, and the distribution law of the coupling strength in a certain trajectory and workspace is studied. The results show that the inertia coupling strength indices between active branched-chains vary with the manipulator position and are symmetrically distributed in the workspace. This paper provides a theoretical basis for the joint controller design and structural parameter optimization of the polishing robot.

@en

Real-time and accurate longitudinal rip detection of a conveyor belt is crucial for the safety and efficiency of an industrial haulage system. However, the existing longitudinal detection methods possess drawbacks, often resulting in false alarms caused by tiny scratches on the belt surface. A method of identifying the longitudinal rip through three-dimensional (3D) point cloud processing is proposed to solve this issue. Specifically, the spatial point data of the belt surface are acquired by a binocular line laser stereo vision camera. Within these data, the suspected points induced by the rips and scratches were extracted. Subsequently, a clustering and discrimination mechanism was employed to distinguish the rips and scratches, and only the rip information was used as alarm criterion. Finally, the direction and maximum width of the rip can be effectively characterized in 3D space using the principal component analysis (PCA) method. This method was tested in practical experiments, and the experimental results indicate that this method can identify the longitudinal rip accurately in real time and simultaneously characterize it. Thus, applying this method can provide a more effective and appropriate solution to the identification scenes of longitudinal rip and other similar defects. @en

During the processing of an optical mirror, the performance parameters of the bottom support system would affect the surface forming accuracy of the mirror. The traditional bottom support system has a large unadjustable support stiffness, which increases the difficulty of unloading the impact force generated by the grinding disc. In response to this scenario, a flexible support system (FSS) consisting of 36 support cylinders with beryllium bronze reeds (BBRs) and rolling diaphragms (RDs) as key components is designed. It is necessary to analyze the key components of the support cylinder to reduce its axial movement resistance, ensure a consistent force output of each support point. First, the internal resistance model of a flexible support cylinder is established, and the main factors of internal resistance are then analyzed. Thereafter, the multi-objective structural parameters of the BBR and RD are simulated in ANSYS using the control variable method. The optimal structural parameters of BBR and RD are determined by simulation. Finally, experiments are performed on the RD ultimate pressure, internal resistance of the support cylinder, and consistency of the force output of the FSS. The experimental results show that the support cylinder with the optimized design has good force output consistency, which provides a theoretical basis for the application of FSS in optical mirror processing. @en

As the supporting unit of rotating machinery, bearing can ensure efficient operation of the equipment. Therefore, it is very important to monitor the status of bearings accurately. A bearing fault diagnosis mothed based on Multipoint Optimal Minimum Local Mean Entropy Deconvolution Adjusted (MOMLMEDA) and Long Short-Term Memory (LSTM) is proposed. MOMLMEDA is an improved algorithm based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). By setting the local kurtosis mean as a new selection criterion, it can effectively avoid the interference of false kurtosis caused by noise and improve the accuracy of optimal kurtosis position. The optimal filter designed by optimal kurtosis position has periodic and amplitude characteristics, which are used as the fault feature in this paper. However, this feature has temporal characteristics and cannot be used as input of general neural network directly. LSTM is selected as the classification network in this paper. It can effectively avoid the influence of the temporal problem existing in feature vectors. Accurate diagnosis of bearing faults is realized by training classification neural network with samples. The overall recognition rate is up to 93.50%.@en

Given local weak feature information, a novel feature extraction and fault diagnosis method for planetary gears based on variational mode decomposition (VMD), singular value decomposition (SVD), and convolutional neural network (CNN) is proposed. VMD was used to decompose the original vibration signal to mode components. The mode matrix was partitioned into a number of submatrices and local feature information contained in each submatrix was extracted as a singular value vector using SVD. The singular value vector matrix corresponding to the current fault state was constructed according to the location of each submatrix. Finally, by training a CNN using singular value vector matrices as inputs, planetary gear fault state identification and classification was achieved. The experimental results confirm that the proposed method can successfully extract local weak feature information and accurately identify different faults. The singular value vector matrices of different fault states have a distinct difference in element size and waveform. The VMD-based partition extraction method is better than ensemble empirical mode decomposition (EEMD), resulting in a higher CNN total recognition rate of 100% with fewer training times (14 times). Further analysis demonstrated that the method can also be applied to the degradation recognition of planetary gears. Thus, the proposed method is an effective feature extraction and fault diagnosis technique for planetary gears.

@en

For planetary gear has the characteristics of small volume, light weight and large transmission ratio, it is widely used in high speed and high power mechanical system. Poor working conditions result in frequent failures of planetary gear. A method is proposed for diagnosing faults in planetary gear based on permutation entropy of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) Adaptive Neuro-fuzzy Inference System (ANFIS) in this paper. The original signal is decomposed into 6 intrinsic mode functions (IMF) and residual components by CEEMDAN. Since the IMF contains the main characteristic information of planetary gear faults, time complexity of IMFs are reflected by permutation entropies to quantify the fault features. The permutation entropies of each IMF component are defined as the input of ANFIS, and its parameters and membership functions are adaptively adjusted according to training samples. Finally, the fuzzy inference rules are determined, and the optimal ANFIS is obtained. The overall recognition rate of the test sample used for ANFIS is 90%, and the recognition rate of gear with one missing tooth is relatively high. The recognition rates of different fault gears based on the method can also achieve better results. Therefore, the proposed method can be applied to planetary gear fault diagnosis effectively.@en

The singularities of parallel manipulators are usually identified by geometrical methods or by the kinematic principles based on the pose parameters. The methods have limitations in applications that involve singularity avoidance, such as motion planning from input parameters. To identify a singularity from an input parameter point of view, which would make the singularity avoidance strategy more direct and more effective in practical applications, this paper focuses on the relationship between the singularities, the configuration spaces and the input parameters with a 3SPS+1PS parallel hip joint simulator selected to implement this approach. A univariate-form polynomial equation of the forward kinematics is obtained with the aid of the Sylvester dialytic method of elimination, therefore proving that the manipulator has at most eight configurations for a single input. The configurations are then divided into two types of spaces according to their distributions. It is discovered that in practice, we only need concern ourselves with the basic configuration spaces, where the singular loci degenerate into a single surface. Finally, the singular condition is proved to be equivalent to that when the univariate-form input–output equation has a repeated root in the real number field. Therefore, the singular condition equation of the input parameters and the singular loci of the input parameters in the basic configuration spaces are obtained. This study provides new insight into the singularity avoidance of a parallel manipulator, especially for the singularity-free design in the motion planning from input parameters.@en