No abstract

One metaheuristic algorithm recently introduced is atom search optimization (ASO), inspired by the physical movement of atoms based on the molecular dynamics in nature. ASO displays a unique search ability by employing the interaction force from the potential energy and the constraint force. Despite some successful applications, it still suffers from a local optima stagnation and a low search efficiency. To alleviate these disadvantages, a new adaptive hybridized optimizer named AASOPSO is proposed. In this study, the individual and group cognitive components in particle swarm optimization (PSO) are integrated into ASO to accelerate the exploitation phase, and the acceleration coefficients are introduced to adaptively achieve a good balance between exploration and exploitation. Meanwhile, to improve the search performance of the algorithm, each individual atom possesses its own force constant, which is effectively and adaptively adjusted based on the feedback of the fitness of the atom in some sequential steps. The performance of AASOPSO is evaluated on two sets of benchmark functions compared to the other population-based optimizers to show its effectiveness. Additionally, AASOPSO is applied to the optimal no-load PID design of the hydro-turbine governor. The simulation results reveal that AASOPSO is more successful than its competitors in searching the global optimal PID parameters.

Combined with wavelet threshold denoising and Ensemble Empirical Mode Decomposition (EEMD) decomposition, an identification method based on Manta Ray Foraging Optimization-BP (MRFO-BP) neural network for vibration signals of residual pressure utilization hydraulic units is proposed to distinguish the vibration signal of each unit. The feature vectors of vibration signals are extracted by wavelet denoising and EEMD decomposition. The weights and thresholds in BP neural network are optimized by the MRFO algorithm. The feature vectors are input into the optimized BP neural network to realize the identification and classification of vibration signals. Compared with Particle Swarm Optimization-BP (PSO-BP) neural network, Bat Algorithm-BP (BA-BP) neural network, and BP neural network, the results show that the identification rate of each measuring point from the MRFO-BP neural network is greatly improved. The average identification rate of other measuring points is 98.514%, except the identification rate of the generator, which is 85.389%. Therefore, the MRFO-BP neural network has better stability and higher identification accuracy and can identify and classify vibration signals more accurately. The conclusions can provide theoretical basis for vibration signals identification of residual pressure utilization hydraulic unit. When the vibration signal of each unit cannot be clearly distinguished, the vibration signals of the units are identified by the method proposed in this paper. According to the obtained results, a feasible classification method can be provided for the vibration signals belonging to different units.

Deep learning algorithms have shown superior performance than traditional algorithms when dealing with computationally intensive tasks in many fields. The algorithm model based on deep learning has good performance and can improve the recognition accuracy in relevant applications in the field of computer vision. TensorFlow is a flexible opensource machine learning platform proposed by Google, which can run on a variety of platforms, such as CPU, GPU, and mobile devices. TensorFlow platform can also support current popular deep learning models. In this paper, an image recognition toolkit based on TensorFlow is designed and developed to simplify the development process of more and more image recognition applications. The toolkit uses convolutional neural networks to build a training model, which consists of two convolutional layers: one batch normalization layer before each convolutional layer, and the other pooling layer after each convolutional layer. The last two layers of the model use the full connection layer to output recognition results. Batch gradient descent algorithm is adopted in the optimization algorithm, and it integrates the advantages of both the gradient descent algorithm and the stochastic gradient descent algorithm, which greatly reduces the number of convergence iterations and has little influence on the convergence effect. The total training parameters of the toolkit model reach 1.7 million. In order to prevent overfitting problems, the dropout layer before each full connection layer is added and the threshold of 0.5 is set in the design. The convolution neural network model is trained and tested by the MNIST set on TensorFlow. The experimental result shows that the toolkit achieves the recognition accuracy of 99% on the MNIST test set. The development of the toolkit provides powerful technical support for the development of various image recognition applications, reduces its difficulty, and improves the efficiency of resource utilization.

No abstract