scholarly journals Mathematical model for the evaluation of risk of emergency situations at a dangerous technical object based on artificial neural networks

2018 ◽  
Vol 44 ◽  
pp. 00069
Author(s):  
Nikolay Peganov ◽  
Aleksandr Tumanov ◽  
Vladimir Tumanov
Keyword(s):  
Neural Networks ◽  
Mathematical Model ◽  
Risk Assessment ◽  
Artificial Neural Networks ◽  
Fire Risk ◽  
Management Decision ◽  
Technical Object ◽  
Emergency Situations ◽  
Artificial Neural ◽  
The Mathematical Model

In the work performed adaptation of artificial neural networks in modern security systems potentially dangerous technical objects — high-rise buildings as tools for assessing and forecasting in management decision. The study obtained the main scientific results: the mathematical model of risk assessment of man-made emergencies based on artificial neural networks; the mathematical model, adapted to the cumulative model of development technogene emergency-fire; provided risk assessment technique manmade emergencies based on artificial neural networks; represented private man-made fire risk assessment methodology using artificial neural networks.

scholarly journals Integration of Classical Mathematical Modeling with an Artificial Neural Network for the Problems with Limited Dataset

Energies ◽  
2021 ◽  
Vol 14 (16) ◽  
pp. 5127
Author(s):  
Szymon Buchaniec ◽  
Marek Gnatowski ◽  
Grzegorz Brus
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mathematical Model ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Mathematical Models ◽  
Box Model ◽  
Advantages And Disadvantages ◽  
Artificial Neural ◽  
The Mathematical Model

One of the most common problems in science is to investigate a function describing a system. When the estimate is made based on a classical mathematical model (white-box), the function is obtained throughout solving a differential equation. Alternatively, the prediction can be made by an artificial neural network (black-box) based on trends found in past data. Both approaches have their advantages and disadvantages. Mathematical models were seen as more trustworthy as their prediction is based on the laws of physics expressed in the form of mathematical equations. However, the majority of existing mathematical models include different empirical parameters, and both approaches inherit inevitable experimental errors. Simultaneously, the approximation of neural networks can reproduce the solution exceptionally well if fed sufficient data. The difference is that an artificial neural network requires big data to build its accurate approximation, whereas a typical mathematical model needs several data points to estimate an empirical constant. Therefore, the common problem that developers meet is the inaccuracy of mathematical models and artificial neural networks. Another common challenge is the mathematical models’ computational complexity or lack of data for a sufficient precision of the artificial neural networks. Here we analyze a grey-box solution in which an artificial neural network predicts just a part of the mathematical model, and its weights are adjusted based on the mathematical model’s output using the evolutionary approach to avoid overfitting. The performance of the grey-box model is statistically compared to a Dense Neural Network on benchmarking functions. With the use of Shaffer procedure, it was shown that the grey-box approach performs exceptionally well when the overall complexity of a problem is properly distributed with the mathematical model and the Artificial Neural Network. The obtained calculation results indicate that such an approach could increase precision and limit the dataset required for learning. To show the applicability of the presented approach, it was employed in modeling of the electrochemical reaction in the Solid Oxide Fuel Cell’s anode. Implementation of a grey-box model improved the prediction in comparison to the typically used methodology.

scholarly journals Development of turning process digital twin based on machine learning

2021 ◽  
pp. 32-41
Author(s):  
D. A. Rastorguev ◽  
◽  
A. A. Sevastyanov ◽  
Keyword(s):  
Neural Networks ◽  
Mathematical Model ◽  
Artificial Neural Networks ◽  
Information Technologies ◽  
Cutting Process ◽  
Turning Process ◽  
Force Load ◽  
Cnc Machine ◽  
Digital Twin ◽  
Artificial Neural

Today, manufacturing technologies are developing within the Industry 4.0 concept, which is the information technologies introduction in manufacturing. One of the most promising digital technologies finding more and more application in manufacturing is a digital twin. A digital twin is an ensemble of mathematical models of technological process, which exchanges information with its physical prototype in real-time. The paper considers an example of the formation of several interconnected predictive modules, which are a part of the structure of the turning process digital twin and designed to predict the quality of processing, the chip formation nature, and the cutting force. The authors carried out a three-factor experiment on the hard turning of 105WCr6 steel hardened to 55 HRC. Used an example of the conducted experiment, the authors described the process of development of the digital twin diagnostic module based on artificial neural networks. When developing a mathematical model for predicting and diagnosing the cutting process, the authors revealed higher accuracy, adaptability, and versatility of artificial neural networks. The developed mathematical model of online diagnostics of the cutting process for determining the surface quality and chip type during processing uses the actual value of the cutting depth determined indirectly by the force load on the drive. In this case, the model uses only the signals of the sensors included in the diagnostic subsystem on the CNC machine. As an informative feature reflecting the force load on the machine’s main motion drive, the authors selected the value of the energy of the current signal of the spindle drive motor. The study identified that the development of a digital twin is possible due to the development of additional modules predicting the accuracy of dimensions, geometric profile, tool wear.

Artificial Neural Networks and other AI Applications for Business Management Decision Support

2016 ◽  
Vol 8 (4) ◽  
pp. 1-20 ◽  
Author(s):  
Steven Walczak
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Management Decision ◽  
Leadership Responsibilities ◽  
Managerial Decision ◽  
Managerial Leadership ◽  
Tremendous Amount ◽  
Artificial Neural ◽  
Manager Performance ◽  
Amount Of Knowledge

Artificial intelligence (AI) in general and artificial neural networks (ANN) in particular provide a tremendous amount of knowledge to improve managerial decision making. Additionally, these same ANN and AI techniques also serve as knowledge repositories and distribution schema for organizations that facilitate managerial leadership responsibilities. This article examines how various ANN and other AI applications may be adapted to facilitate managerial leadership, improve manager performance and in some cases perform management activities. Further research that classifies leadership styles and the desired qualities of leaders is reviewed.

Sign in / Sign up

Export Citation Format

Share Document