On Adam Trained Models and a Parallel Method to Improve the Generalization Performance

Fault diagnosis is of great significance to improve the production efficiency and accuracy of industrial robots. Compared with the traditional gradient descent algorithm, the extreme learning machine (ELM) has the advantage of fast computing speed, but the input weights and the hidden node biases that are obtained at random affects the accuracy and generalization performance of ELM. However, the level-based learning swarm optimizer algorithm (LLSO) can quickly and effectively find the global optimal solution of large-scale problems, and can be used to solve the optimal combination of large-scale input weights and hidden biases in ELM. This paper proposes an extreme learning machine with a level-based learning swarm optimizer (LLSO-ELM) for fault diagnosis of industrial robot RV reducer. The model is tested by combining the attitude data of reducer gear under different fault modes. Compared with ELM, the experimental results show that this method has good stability and generalization performance.

Download Full-text

A gain perturbation method to improve the generalization performance for the recurrent neural network misfire detector

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339) ◽

10.1109/ijcnn.1999.832599 ◽

2003 ◽

Author(s):

P. Sun ◽

K. Marko

Keyword(s):

Neural Network ◽

Perturbation Method ◽

Recurrent Neural Network ◽

Generalization Performance

Download Full-text

Large-Scale Parallel Method of Moments on CPU/MIC Heterogeneous Clusters

IEEE Transactions on Antennas and Propagation ◽

10.1109/tap.2017.2700871 ◽

2017 ◽

Vol 65 (7) ◽

pp. 3782-3787 ◽

Cited By ~ 2

Author(s):

Yan Chen ◽

Sheng Zuo ◽

Yu Zhang ◽

Xunwang Zhao ◽

Huanhuan Zhang

Keyword(s):

Method Of Moments ◽

Large Scale ◽

Parallel Method ◽

Heterogeneous Clusters

Download Full-text

A Parallel Method for Generating Pseudorandom Binary I.I.D. Sequences

2008 IEEE 10th International Symposium on Spread Spectrum Techniques and Applications ◽

10.1109/isssta.2008.144 ◽

2008 ◽

Author(s):

S. Soga ◽

H. Fujisaka ◽

K. Furuta

Keyword(s):

Parallel Method

Download Full-text

Comparison of Three Different Parallel Computation Methods for a Two-Dimensional Dam-Break Model

Mathematical Problems in Engineering ◽

10.1155/2017/1970628 ◽

2017 ◽

Vol 2017 ◽

pp. 1-12 ◽

Cited By ~ 1

Author(s):

Shanghong Zhang ◽

Wenda Li ◽

Zhu Jing ◽

Yujun Yi ◽

Yong Zhao

Keyword(s):

Parallel Computation ◽

Data Exchange ◽

Large Scale ◽

Good Choice ◽

Dam Break ◽

Two Dimensional ◽

Parallel Method ◽

Parallel Methods ◽

Storage Area ◽

Speedup Factor

Three parallel methods (OpenMP, MPI, and OpenACC) are evaluated for the computation of a two-dimensional dam-break model using the explicit finite volume method. A dam-break event in the Pangtoupao flood storage area in China is selected as a case study to demonstrate the key technologies for implementing parallel computation. The subsequent acceleration of the methods is also evaluated. The simulation results show that the OpenMP and MPI parallel methods achieve a speedup factor of 9.8× and 5.1×, respectively, on a 32-core computer, whereas the OpenACC parallel method achieves a speedup factor of 20.7× on NVIDIA Tesla K20c graphics card. The results show that if the memory required by the dam-break simulation does not exceed the memory capacity of a single computer, the OpenMP parallel method is a good choice. Moreover, if GPU acceleration is used, the acceleration of the OpenACC parallel method is the best. Finally, the MPI parallel method is suitable for a model that requires little data exchange and large-scale calculation. This study compares the efficiency and methodology of accelerating algorithms for a dam-break model and can also be used as a reference for selecting the best acceleration method for a similar hydrodynamic model.

Download Full-text

A parallel in time/spectral collocation combined with finite difference method for the time fractional differential equations

Journal of Algorithms & Computational Technology ◽

10.1177/17483026211008409 ◽

2021 ◽

Vol 15 ◽

pp. 174830262110084

Author(s):

Xianjuan Li ◽

Yanhui Su

Keyword(s):

Finite Difference ◽

Finite Difference Method ◽

Differential Equations ◽

Spectral Method ◽

Fractional Differential Equations ◽

Difference Method ◽

Spectral Collocation ◽

Parallel Method ◽

Fractional Differential ◽

Time Fractional Differential Equations

In this article, we consider the numerical solution for the time fractional differential equations (TFDEs). We propose a parallel in time method, combined with a spectral collocation scheme and the finite difference scheme for the TFDEs. The parallel in time method follows the same sprit as the domain decomposition that consists in breaking the domain of computation into subdomains and solving iteratively the sub-problems over each subdomain in a parallel way. Concretely, the iterative scheme falls in the category of the predictor-corrector scheme, where the predictor is solved by finite difference method in a sequential way, while the corrector is solved by computing the difference between spectral collocation and finite difference method in a parallel way. The solution of the iterative method converges to the solution of the spectral method with high accuracy. Some numerical tests are performed to confirm the efficiency of the method in three areas: (i) convergence behaviors with respect to the discretization parameters are tested; (ii) the overall CPU time in parallel machine is compared with that for solving the original problem by spectral method in a single processor; (iii) for the fixed precision, while the parallel elements grow larger, the iteration number of the parallel method always keep constant, which plays the key role in the efficiency of the time parallel method.

Download Full-text

An efficient and accurate method for obtaining regional scale rice growth conditions based on WOFOST model and satellite images

10.5194/egusphere-egu21-10688 ◽

2021 ◽

Author(s):

Bingyu Zhao ◽

Meiling Liu ◽

Jiianjun Wu ◽

Xiangnan Liu ◽

Mengxue Liu ◽

...

Keyword(s):

Remote Sensing ◽

Data Assimilation ◽

Growth Model ◽

Growth Parameters ◽

Remote Sensing Data ◽

Growth Conditions ◽

Crop Growth ◽

Crop Growth Model ◽

Parallel Method ◽

Rice Growth

<p>It is very important to obtain regional crop growth conditions efficiently and accurately in the agricultural field. The data assimilation between crop growth model and remote sensing data is a widely used method for obtaining vegetation growth information. This study aims to present a parallel method based on graphic processing unit (GPU) to improve the efficiency of the assimilation between RS data and crop growth model to estimate rice growth parameters. Remote sensing data, Landsat and HJ-1 images were collected and the World Food Studies (WOFOST) crop growth model which has a strong flexibility was employed. To acquire continuous regional crop parameters in temporal-spatial scale, particle swarm optimization (PSO) data assimilation method was used to combine remote sensing images and WOFOST and this process is accompanied by a parallel method based on the Compute Unified Device Architecture (CUDA) platform of NVIDIA GPU. With these methods, we obtained daily rice growth parameters of Zhuzhou City, Hunan, China and compared the efficiency and precision of parallel method and non-parallel method. Results showed that the parallel program has a remarkable speedup (reaching 240 times) compared with the non-parallel program with a similar accuracy. This study indicated that the parallel implementation based on GPU was successful in improving the efficiency of the assimilation between RS data and the WOFOST model and was conducive to obtaining regional crop growth conditions efficiently and accurately.</p>

Download Full-text