Advanced power and energy system pnn

Can a probabilistic neural network optimize of PNN?

In this paper, a fault diagnosis method for power transformer is proposed using probabilistic neural network and bat algorithm to optimize uncertain parameter smooth factor ( σ) of PNN. In the proposed approach, BA can enhance the global convergence of network when optimizing PNN and outperformed other optimization algorithms.

Is PNN a good radial basis function feedforward neural network?

PNN is a radial basis function feedforward neural network based on Bayesian decision theory, which has a strong fault tolerance and significant advantages in pattern classification. However, one challenge still remains: the performance of PNN is greatly affected by its hidden layer element smooth factor which impacts the classification performance.

Can BA improve the global convergence of network when optimizing PNN?

In the proposed approach, BA can enhance the global convergence of network when optimizing PNN and outperformed other optimization algorithms. We conducted the experiments using the collected fault data from a practical transformer system to evaluate the performance of the developed models.

Is L-pnpu energy-efficient 3D PNN segmentation processor based on lidar?

Therefore, the entire system, from sensing to processing, must be taken into account for 3D PNN processor implementation. This paper proposes L-PNPU, an energy-efficient 3D PNN segmentation processor optimized with the unique mechanical characteristics of LiDAR.

Can artificial neural networks improve power transformer fault diagnosis?

Particularly, the application of artificial neural networks (ANN) , , makes progressively the power transformer fault diagnosis more efficient and effective. However, there still reminds some challenges while developing ANN for domain applications, including local minimum and over-fitting .

How efficient is L-pnpu at 250 MHz and 1.0V?

At 250 MHz and 1.0V, L-PNPU achieves 1.27M points/s of throughput and 0.51 μJ/point of energy efficiency. Y. Guo, H. Wang, Q. Hu, H. Liu, L. Liu and M. Bennamoun. 2021.