To monitor the tool wear state of computerized numerical control (CNC) machining equipment in real time in a manufacturing workshop, this paper proposes a real-time monitoring method based on a fusion of a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network with an attention mechanism (CABLSTM). In this method, the CNN is used to extract deep features from the time-series signal as an input, and then the BiLSTM network with a symmetric structure is constructed to learn the time-series information between the feature vectors. The attention mechanism is introduced to self-adaptively perceive the network weights associated with the classification results of the wear state and distribute the weights reasonably. Finally, the signal features of different weights are sent to a Softmax classifier to classify the tool wear state. In addition, a data acquisition experiment platform is developed with a high-precision CNC milling machine and an acceleration sensor to collect the vibration signals generated during tool processing in real time. The original data are directly fed into the depth neural network of the model for analysis, which avoids the complexity and limitations caused by a manual feature extraction. The experimental results show that, compared with other deep learning neural networks and traditional machine learning network models, the model can predict the tool wear state accurately in real time from original data collected by sensors, and the recognition accuracy and generalization have been improved to a certain extent.
Aiming to build upon the slow convergence speed and low search efficiency of the potential function-based rapidly exploring random tree star (RRT*) algorithm (P_RRT*), this paper proposes a path planning method for manipulators with an improved P_RRT* algorithm (defined as improved P_RRT*), which is used to solve the path planning problem for manipulators in three-dimensional space. This method first adopts a random sampling method based on a potential function. Second, based on a probability value, the nearest neighbour node is selected by the nearest Euclidean distance to the random sampling point and the minimum cost function, and in the expansion of new nodes, twice expansion methods are used to accelerate the search efficiency of the algorithm. The first expansion adopts the goal-biased expansion strategy, and the second expansion adopts the strategy of random sampling in a rectangular area. Then, the parent node of the new node is reselected, and the path is rerouted to obtain a clear path from the initial point to the target point. Redundant node deletion and the maximum curvature constraint are used to remove redundant nodes and minimize the curvature on the generated path to reduce the tortuosity of the path. The Bezier curve is used to fit the processed path and obtain the trajectory planning curve for the manipulator. Finally, the improved P_RRT* algorithm is verified experimentally in Python and the Robot Operating System (ROS) and compared with other algorithms. The experimental results verify the effectiveness and superiority of the improved algorithm.
To improve the path planning efficiency of a robotic arm in three-dimensional space and improve the obstacle avoidance ability, this paper proposes an improved artificial potential field and rapid expansion random tree (APF-RRT) hybrid algorithm for the mechanical arm path planning method. The improved APF algorithm (I-APF) introduces a heuristic method based on the number of adjacent obstacles to escape from local minima, which solves the local minimum problem of the APF method and improves the search speed. The improved RRT algorithm (I-RRT) changes the selection method of the nearest neighbor node by introducing a triangular nearest neighbor node selection method, adopts an adaptive step and generates a virtual new node strategy to explore the path, and removes redundant path nodes generated by the RRT algorithm, which effectively improves the obstacle avoidance ability and efficiency of the algorithm. Bezier curves are used to fit the final generated path. Finally, an experimental analysis based on Python shows that the search time of the hybrid algorithm in a multi-obstacle environment is reduced to 2.8 s from 37.8 s (classic RRT algorithm), 10.1 s (RRT* algorithm), and 7.4 s (P_RRT* algorithm), and the success rate and efficiency of the search are both significantly improved. Furthermore, the hybrid algorithm is simulated in a robot operating system (ROS) using the UR5 mechanical arm, and the results prove the effectiveness and reliability of the hybrid algorithm.
In order to obtain the automatic simulation generation of traditional handmade batik patterns in a computer, this paper proposes the automatic generation method of batik flower patterns based on fractal geometry. Firstly, we analyze the fractal characteristics of batik flowers and design an automatic flower generation algorithm based on a two-dimensional iterated function system (IFS) and a curve function. The algorithm forms a complete flower pattern. Secondly, a nonlinear function is defined and the flower pattern is introduced into the nonlinear function to iterate and change. On this basis, we present an automatic generation method of different distribution patterns for flower patterns which obtains the most effective range of each parameter value for each function. Finally, in order to verify the feasibility of the automatic generation method of batik flower patterns, we develop an automatic generation experiment system for batik patterns via an interactive way of working. The results show that the user or designer can quickly and automatically simulate a series of flower patterns by changing the relevant parameter values, realizing the digitization and innovative design of the pattern and enriching the batik pattern base.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.