scholarly journals Artificial Intelligence in Electric Machine Drives: Advances and Trends

2021 ◽  
Author(s):  
Shen Zhang
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Domain Adaptation ◽  
Low Cost ◽  
Electric Machine ◽  
Widespread Application ◽  
Performance Control ◽  
Learning Capabilities ◽  
Machine Drives ◽  
Hardware Platforms

This review paper systematically summarizes the existing literature on applying classical AI techniques and advanced deep learning algorithms to electric machine drives. It is anticipated that with the rapid progress in deep learning models and embedded hardware platforms, AI-based data-driven approaches will become increasingly popular for the automated high-performance control of electric machines. Additionally, this paper also provides some outlook towards promoting its widespread application in the industry, such as implementing advanced RL algorithms with good domain adaptation and transfer learning capabilities and deploying them onto low-cost SoC FPGA devices.

scholarly journals Artificial Intelligence in Electric Machine Drives: Advances and Trends

2021 ◽  
Author(s):  
Shen Zhang
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Domain Adaptation ◽  
Low Cost ◽  
Electric Machine ◽  
Widespread Application ◽  
Performance Control ◽  
Learning Capabilities ◽  
Machine Drives ◽  
Hardware Platforms

This review paper systematically summarizes the existing literature on applying classical AI techniques and advanced deep learning algorithms to electric machine drives. It is anticipated that with the rapid progress in deep learning models and embedded hardware platforms, AI-based data-driven approaches will become increasingly popular for the automated high-performance control of electric machines. Additionally, this paper also provides some outlook towards promoting its widespread application in the industry, such as implementing advanced RL algorithms with good domain adaptation and transfer learning capabilities and deploying them onto low-cost SoC FPGA devices.

scholarly journals Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 223
Author(s):  
Yen-Ling Tai ◽  
Shin-Jhe Huang ◽  
Chien-Chang Chen ◽  
Henry Horng-Shing Lu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Computational Complexity ◽  
High Performance ◽  
Low Cost ◽  
Structural Complexity ◽  
Correction Function ◽  
Computational Time ◽  
Learning Methods ◽  
Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

Enabling high-performance room-temperature sodium/sulfur batteries with few-layer 2H-MoSe2 embellished nitrogen-doped hollow carbon spheres as polysulfide barrier

2021 ◽  
Author(s):  
Chunwei Dong ◽  
HongYu Zhou ◽  
Bo Jin ◽  
Wang Gao ◽  
Xingyou Lang ◽  
...  
Keyword(s):  
High Performance ◽  
Room Temperature ◽  
Electrode Materials ◽  
Low Cost ◽  
High Energy ◽  
High Energy Density ◽  
Widespread Application ◽  
Earth Abundant ◽  
Hollow Carbon ◽  
Sodium Sulfur

Room-temperature sodium/sulfur (RT-Na/S) batteries are of considerable interest for next-generation energy storage systems because of the earth-abundant electrode materials, low cost, and high energy density. However, the widespread application of...

Comparison of UV- and Derivative-Spectrophotometric and HPTLC UVDensitometric Methods for the Determination of Amrinone and Milrinone in Bulk Drugs

2020 ◽  
Vol 16 (3) ◽  
pp. 246-253
Author(s):  
Marcin Gackowski ◽  
Marcin Koba ◽  
Stefan Kruszewski
Keyword(s):  
Thin Layer ◽  
Thin Layer Chromatography ◽  
High Performance ◽  
Low Cost ◽  
Uv Spectra ◽  
Derivative Spectrophotometry ◽  
Therapeutic Monitoring ◽  
Bulk Drug ◽  
Layer Chromatography ◽  
Standard Solutions

Background: Spectrophotometry and thin layer chromatography have been commonly applied in pharmaceutical analysis for many years due to low cost, simplicity and short time of execution. Moreover, the latest modifications including automation of those methods have made them very effective and easy to perform, therefore, the new UV- and derivative spectrophotometry as well as high performance thin layer chromatography UV-densitometric (HPTLC) methods for the routine estimation of amrinone and milrinone in pharmaceutical formulation have been developed and compared in this work since European Pharmacopoeia 9.0 has yet incorporated in an analytical monograph a method for quantification of those compounds. Methods: For the first method the best conditions for quantification were achieved by measuring the lengths between two extrema (peak-to-peak amplitudes) 252 and 277 nm in UV spectra of standard solutions of amrinone and a signal at 288 nm of the first derivative spectra of standard solutions of milrinone. The linearity between D252-277 signal and concentration of amironone and 1D288 signal of milrinone in the same range of 5.0-25.0 μg ml/ml in DMSO:methanol (1:3 v/v) solutions presents the square correlation coefficient (r2) of 0,9997 and 0.9991, respectively. The second method was founded on HPTLC on silica plates, 1,4-dioxane:hexane (100:1.5) as a mobile phase and densitometric scanning at 252 nm for amrinone and at 271 nm for milrinone. Results: The assays were linear over the concentration range of 0,25-5.0 μg per spot (r2=0,9959) and 0,25-10.0 μg per spot (r2=0,9970) for amrinone and milrinone, respectively. The mean recoveries percentage were 99.81 and 100,34 for amrinone as well as 99,58 and 99.46 for milrinone, obtained with spectrophotometry and HPTLC, respectively. Conclusion: The comparison between two elaborated methods leads to the conclusion that UV and derivative spectrophotometry is more precise and gives better recovery, and that is why it should be applied for routine estimation of amrinone and milrinone in bulk drug, pharmaceutical forms and for therapeutic monitoring of the drug.

Sign in / Sign up

Export Citation Format

Share Document