scholarly journals On the Equivalence of Real Dynamic Process and Its Neural Network Quadratic Models

2021 ◽  
Vol 29 (2) ◽  
pp. 76
Author(s):  
Vasiliy Ye. Belozyorov ◽  
Danylo V. Dantsev ◽  
Yevhen V. Koshel
Keyword(s):  
Neural Network ◽  
Dynamic Process ◽  
Quadratic Models

Antioxidant increase by response surface optimization and Bayesian neural network modelling of pumpkin (Cucurbita moschata Duch) freezing

Food Research ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 73-82
Author(s):  
Y. Kristianto ◽  
W. Wignyanto ◽  
B.D. Argo ◽  
I. Santoso
Keyword(s):  
Neural Network ◽  
Response Surface ◽  
Feedforward Neural Networks ◽  
Slow Freezing ◽  
Total Phenolic ◽  
Bayesian Neural Network ◽  
Network Modelling ◽  
Response Surface Optimization ◽  
Response Change ◽  
Quadratic Models

Pumpkin antioxidants have been found to benefit diabetics. This current study was attempted to optimize slow freezing treatment for a pumpkin to obtain maximum antioxidant gain using response surface methodology (RSM) and Bayesian regularized neural network (BRANN) approaches. A central composite design was used to generate the freezing experiment and to examine response change as a function of temperature and freezing time. Feedforward neural networks with a 2-15-1 structure were developed and trained using the Bayesian regularization algorithm. The results showed that the freezing data were well fitted to quadratic models generating R2 for total phenolic compounds (TPC), flavonoid of 0.850 and 0.857 respectively. The RSM optimized freezing of -20oC for 9 hrs were well confirmed to produce an increase in TPC and flavonoid by 54.44% and 60.4% respectively. The BRANN performances were found to be similar to that of RSM. While overfitting was mitigated during the supervised training, the BRANN model served excellent predictive and confirmatory tool for the optimization. In conclusion, slow freezing at -20oC for 9 hrs significantly increases TPC and flavonoid of pumpkin. This novel process may be adopted to provide healthier pumpkins food products for targeted consumers.

Design of Neural Network Controller Based on FPGA Distillation Column

2013 ◽  
Vol 385-386 ◽  
pp. 956-959
Author(s):  
Jin Biao Yang ◽  
Mo Yi Jia ◽  
Li Hu Su ◽  
Le Le Yao
Keyword(s):  
Neural Network ◽  
Dynamic Process ◽  
Distillation Column ◽  
Control Mechanism ◽  
Mathematics Model ◽  
Distillation Process ◽  
Process Variables ◽  
Neural Network Controller ◽  
Network Controller ◽  
Complex Process

A study based on FPGA controller, is used to solve the problems of control mechanism of this kind of dynamic process of coal chemical distillation process complex, process variables, controlled variables, it is difficult to establish mathematics model.

Improved Dynamic Process Neural Network and its Application

2010 ◽  
Vol 458 ◽  
pp. 143-148
Author(s):  
Pei Yin Zhang ◽  
G.B. Yu ◽  
B. Dai ◽  
Ying Jie Ao
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Particle Swarm Optimization ◽  
Dynamic Process ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Test Results ◽  
Tourism Demand ◽  
Swarm Optimization ◽  
Proposed Model

The tourism demand is essential in terms of national economy and the improvement of people’ income. But it is difficult for traditional methods to predict the tendency of the tourism demand. In this paper, a time series prediction method based on dynamic process neural network (DPNN) is proposed to solve this problem. An improved particle swarm optimization (IPSO) is developed. By tuning the structure and improving the connection weights of PNN simultaneously, a partially connected DPNN can be obtained. The effectiveness of the proposed DPNN is proved by Henon system. Finally, the proposed DPNN is utilized to predict the tourism demand, and the test results indicate that the proposed model seems to perform well and appears suitable for using as a predictive maintenance tool.

Sign in / Sign up

Export Citation Format

Share Document