Comparison of the Artificial Data Generation Methods for Deep Training of Monitoring System
MAGAZINE №3(86) June 2018
AUTHORS
SOBOLEVSKIY V.A. - Graduate student, Russian Academy of Sciences, Laboratory of Information Technologies in System Analysis and Modeling, St. Petersburg Institute of Informatics and Automation (St. Petersburg, Russia)
CATEGORY Analysis in logistics and SCM Simulation modelling
ABSTRACT
This article deals with the problem of input data generated for the creation and training of an artificial neural network which is the basis of the classification module of a dynamic monitoring system of the manufacture performance indexes. The input data that was used to train the neural network was divided into the following categories: real data, generated data for a given distribution, and data obtained using the simulation approach. The simulation model was created using the apparatus of Petri nets. Further, for the data used in the work, classification rules were set, after which the artificial neural network was trained on each data set. At the next stage, real data was submitted to the monitoring system which are previously did not appear in the training and validation of neural networks. The final step of this study was to compare the results of the classification of the described approaches of artificial generation of values of enterprise input parameters with respect to the control data set.
Keywords:
Introduction to Logistics Systems Analysis Using Petri Nets
MAGAZINE №5 (82) October 2017
AUTHORS PETROVSKIY D.V.
CATEGORY Analysis in logistics and SCM Simulation modelling
ABSTRACT
The purpose of this article is to show the possibilities of using stochastic Petri nets for the logistic systems analysis in order to optimize their operation. This article deals with the mathematical apparatus of Petri nets, moreover, it also shows an algorithm for making performance analysis. As an example, the simplest model of unloading a vehicle was developed and analysed to determine the main characteristics of a given model. In order to perform the performance analysis of given Petri net, the state space of this network was constructed and a state space stationary distribution of the system was found analytically. That allowed to determine the key parameters of the model; Performance analysis was performed without using third-party software. As a result, it has been shown that Petri nets are a simple and convenient tool for logistics systems optimization and design. Therefore, Petri nets can be used as a support mechanism for decisions making at various levels of supply chains.
Keywords:
Using Apparatus of Stochastic Petri Nets when Controlling Logistics Systems Parameters
MAGAZINE №6 (83) December 2017
AUTHORS PETROVSKIY D.V., KOKURIN D.I.
CATEGORY Analysis in logistics and SCM Simulation modelling
ABSTRACT
The article considers the use of the apparatus of stochastic Petri networks during supply chain analysis. The main object of the analysis is the storage and production modules and their interaction with other elements of the system. First, the logistical system under consideration was represented in the form of a stochastic Petri network, then two models of one system with different initial conditions were created with the purpose of their behavior analysis and comparison. Analysis of the results of the models was carried out by two methods: the construction of an analytical model of the Petri net; simulation of the model work during a specified period. In addition, the paper deals with the problem of exponential explosion; the dependence of the number of the system possible conditions on the change of its parameters is shown. As a result, it was shown how the behavior of the system depends on the change in the product delivery time and what period is critical for the production deficit.
Keywords:
