A calculation method of transmission efficiency for RV reducer

RV reducer is the core component of industrial robot. It is of great significance to raise the transmission efficiency of RV reducer for improving the transmission performance of industrial robot. RV reducer belongs to the 2K-V type planetary gear train and consists of an equal speed ratio mechanism. Therefore, according to the structural characteristics of RV reducer, the virtual power theory and split power theory are adopted, and a calculation method of transmission efficiency for RV reducer is proposed. Firstly, the structure of a common RV reducer is introduced. Related structural analysis, kinematic analysis, and loaded analysis are given. Secondly, RV reducer is represented by the method of graph theory. By the virtual power theory and split power theory, the power flow direction is determined, and the values of split powers are calculated. Finally, according to the graph representation for RV reducer and the calculation principle of meshing power loss of planetary gear, the power losses of meshing gear pairs are calculated, respectively. According to the input and output values described in graph representation of RV reducer, the formula of transmission efficiency for RV reducer is derived. The calculation of transmission efficiency for RV-40E reducer is considered as an example. The result is compared with previous work on the subject, and the relations between design parameters and transmission efficiency of RV reducer are discussed.

Analysis of Coaxiality-Transmission Efficiency Vector Model of RV Reducer Based on ADAMS

Aiming at the influence of the coaxiality error of the transmission system on the detection accuracy of the RV reducer performance test device, taking RV-20E reducer is used as the research object, combined with the ADAMS dynamic simulation software, the RV reducer dynamic transmission coaxiality and transmission efficiency vector model is established, and the coaxiality of the transmission system of this model is simulated under different error ranges and no load. The transmission efficiency is 32.94% when coaxiality is within the allowable error range. The results verify the accuracy of the model. At the same time, when the concentricity exceeds the allowable range of error, it will have a great impact on the transmission efficiency. The design of the coaxiality adjustment mechanism of the RV reducer performance detection device has certain theoretical significance and practical value.

Exploiting graph neural network with one-shot learning for fault diagnosis of mechanical equipment

For the classification of mechanical fault diagnosis, a graph neural network (GNN) method with one-shot learning is proposed. Convolutional Neural Network (CNN) is used to extract the feature vectors and One-Hot coding from images of Fault diagnosis of mechanical equipment. Inputting feature vectors and One-Hot coding into GNN, according to the Adjacency Matrix between vertices in the Graph, and is used for classification and inference. The method with one-shot learning is used for fault diagnosis classification. Through the fault classification for the industrial robot RV reducer and public data set CWRU pictures, the effectiveness of the method is verified. Five categories are used for fault diagnosis and classification in RV Reducer of the industrial robots. 80 categories are used in the public data set CWRU, and 55 categories are used as the training set. GNN is employed to spread the label information from the supervised sample of the unlabeled query data. The large-scale dataset can then be used as baseline classes to learn transferable knowledge for classifying novelties with one-shot samples. The one-shot learning with graph neural network GNN significantly improves the classification accuracy. The results show that the proposed method is superior to other similar methods and has a substantial potential for improvement in Fault diagnosis of mechanical equipment.

Error Analysis of Cycloid Gear Based on Ellipse Fitting Based on Least Square Approach

In this paper, under the condition of the existing processing and detecting technology, we used coordinate measuring machine (CMM) to measure the contour of cycloid gear. In order to improve the accuracy of measured data, we used Euclidean distance and Laida criterion to preprocess measured data. After preprocessing the measured data of the cycloid gear, we used ellipse fitting based on least square approach to fit the contour data points of the cycloid gear, and used the determination coefficient method to evaluate the goodness of fitting. According to the result of the curve fitting of cycloid gear, we used Matlab to analyse and calculate the pitch errors of cycloid gear, which provides data for the subsequent matching of parts combination of the best RV reducer with genetic algorithm.

Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network

As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.

RV reducer Design Using Resnet-based model and integration of Discretized OPtimization

A new type of mechanical system structure design model is proposed, which uses a small number of system feature samples to generate a new structure model. In this model, (1) the theory of limited sample recommendation algorithm is used to study the external dimensions recommendation of the reducer, an SG-Resnet network suitable for the generation of reducer structure parameters is established, the main factors affecting the promotion ability and learning rate of the SG-Resnet network structure are analyzed through hyperparameters, and in-depth study of the mechanism of each influencing factor. (2) Establish an optimization design method for the internal dimensions of the reducer, and initially calculate the structural parameters according to the basic performance parameters of the reducer, combine the objective function and constraint conditions to establish the corresponding multi-objective optimization model, and establish the Kriging proxy model. The mixed population NSGA-II algorithm is proposed, the MP-NSGA-II algorithm is used to obtain multiple sets of Pareto optimal solutions, and the multi-objective evaluation method is used to select the optimal solution from the non-dominated solution set. Experiments were carried out to verify the positive enhancement effect of the structural design model on the stiffness of the reducer. The experiment showed the reliability and generalizability of the model. This research provides a new solution for reducer design and lays a solid foundation for the development of integrated RV reducer forward design software.