A deep learning-based operation optimization strategy for BFG/coal co-firing boiler

2017 ◽  
Author(s):  
Jian-Guo Wang ◽  
Jin-Qiu Min ◽  
Li-Lan Liu ◽  
Bang-Hua Yang ◽  
Shi-Wei Ma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optimization Strategy ◽  
Operation Optimization

An MCFC operation optimization strategy based on PID auto-tuning control

2017 ◽  
Vol 42 (40) ◽  
pp. 25518-25530 ◽  
Author(s):  
Donghyeon Lee ◽  
Yujin Cheon ◽  
Jun-Hyung Ryu ◽  
In-Beum Lee
Keyword(s):  
Optimization Strategy ◽  
Operation Optimization ◽  
Auto Tuning

EXAMINATION OF MEDICAL IMAGE RECORDING ACCORDING TO THE CATEGORY OF RESEARCH PROGRESS AND TECHNICAL METHODS BASED ON DEEP LEARNING

2021 ◽  
Vol 03 (01) ◽  
pp. 22-31
Author(s):  
Elcin Nizami Huseyn ◽  
◽  
Mohammad Hoseini ◽  
Keyword(s):  
Deep Learning ◽  
Image Matching ◽  
Medical Image ◽  
Image Alignment ◽  
Research Progress ◽  
Optimization Strategy ◽  
Convolutional Network ◽  
Image Recording ◽  
Guided Surgery ◽  
Similarity Estimation

With the development of imaging-guided surgery and radiotherapy, the clinical demand for medical image matching research is stronger and the challenges are even greater. In recent years, deep learning, especially deep convolution neural networks, has made excellent achievements in medical image processing, and the research on medical image matching has developed rapidly. In this paper, the domestic and foreign research progress based on deep learning medical image alignment is summarized according to the classification of technical methods, including the similarity estimation based on optimization strategy, the transformation parameters of direct estimation of medical image alignment, etc. Then it analyses the challenge of the deep learning method in medical image matching and puts forward possible solutions and research directions. Key words: medical image recording, deep learning, CNN, full convolutional network

Review of Economic Operation Optimization Strategy of Photovoltaic Grid-Connected System

2013 ◽  
Vol 860-863 ◽  
pp. 75-80
Author(s):  
Yang Du ◽  
Wei Cao ◽  
Wan Xin Li
Keyword(s):  
Objective Function ◽  
Research Methods ◽  
Optimization Strategy ◽  
System Operation ◽  
Operation Optimization ◽  
Economic Operation ◽  
Key Issues ◽  
Main Factors

Economy is one of the main factors for the development of photovoltaic grid-connected system. From the view of economic operation in this article, four aspects of photovoltaic grid-connected system are reviewed, including the component modeling, the objective function, constraints and optimization strategies. Typical research methods used in economic operation are analyzed, and the key issues about photovoltaic grid-connected system operation are pointed out.

scholarly journals Gradient Descent Optimization in Deep Learning Model Training Based on Multistage and Method Combination Strategy

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Chuanlei Zhang ◽  
Minda Yao ◽  
Wei Chen ◽  
Shanwen Zhang ◽  
Dufeng Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Gradient Descent ◽  
Optimization Methods ◽  
Adaptive Methods ◽  
Learning Model ◽  
Optimization Strategy ◽  
Combination Strategy ◽  
Network Training ◽  
Model Training ◽  
Deep Learning Model

Gradient descent is the core and foundation of neural networks, and gradient descent optimization heuristics have greatly accelerated progress in deep learning. Although these methods are simple and effective, how they work remains unknown. Gradient descent optimization in deep learning has become a hot research topic. Some research efforts have tried to combine multiple methods to assist network training, but these methods seem to be more empirical, without theoretical guides. In this paper, a framework is proposed to illustrate the principle of combining different gradient descent optimization methods by analyzing several adaptive methods and other learning rate methods. Furthermore, inspired by the principle of warmup, CLR, and SGDR, the concept of multistage is introduced into the field of gradient descent optimization, and a gradient descent optimization strategy in deep learning model training based on multistage and method combination strategy is presented. The effectiveness of the proposed strategy is verified on the massive deep learning network training experiments.

scholarly journals Fast Inverse Design of Nanophotonics using Di fferential Evolutionn and Back-Propagation

2021 ◽  
Author(s):  
Cankun Qiu ◽  
Xia Wu ◽  
Zhi Luo ◽  
Huidong Yang ◽  
Bo Huang
Keyword(s):  
Deep Learning ◽  
Back Propagation ◽  
Bp Algorithm ◽  
Inverse Design ◽  
Training Dataset ◽  
Design Parameters ◽  
Optical Simulation ◽  
Learning Technology ◽  
Optimization Strategy ◽  
Initial Values

Abstract Deep learning technology have been used as a new approach for forward simulation and inverse design of nanophotonic structures. Deep learning technology greatly reduces the time of optical simulation and enables us to use back-propagation (BP) algorithm to optimize design parameters. But BP is very sensitive to the initial values and hard to converge to the optimal value for some initial values. In this research, we propose a hybrid optimization strategy that combined differential evolution (DE) with BP algorithm for the inverse design of multilayer nanofilms structures. The proposed method effectively utilizes the global parallel exploration capability of DE and the local exploitation capability of gradient descent based on BP. It can alleviate the sensitivity of the initial values for the BP algorithm and effectively compensates for the slower convergence properties of the DE. The results suggest that the hybrid DE-BP algorithm can greatly speeds up the inverse design process of multilayer nanofilms and can search in a larger parameter space that even exceeds the parameter range of the training dataset that are used to train the forward prediction neural networks.

Sign in / Sign up

Export Citation Format

Share Document