Diagnosis of Discrete Event Systems under Temporal Constraints Using Neural Network

2020 ◽  
Vol 49 ◽  
pp. 198-205
Author(s):  
Mohammed Msaaf ◽  
Fouad Belmajdoub
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Statistical Model ◽  
Discrete Event Systems ◽  
Discrete Event ◽  
Temporal Constraints ◽  
Temporal Constraint ◽  
New Approach ◽  
Constraint Checking ◽  
Event System

The good functioning of a discrete event system is related to how much the temporal constraints are respected. This paper gives a new approach, based on a statistical model and neural network, that allows the verification of temporal constraints in DES. We will perform an online temporal constraint checking which can detect in real time any abnormal functioning related to the violation of a temporal constraint. In the first phase, the construction of temporal constraints from statistical model is shown and after that neural networks are involved in dealing with the online temporal constraint checking.

scholarly journals Discrete Event Systems Fault’s Diagnosis and Prognosis Using Feed-Forward Neural Networks

2021 ◽  
Vol 54 (6) ◽  
pp. 853-863
Author(s):  
Amri Omar ◽  
Fri Mohamed ◽  
Msaaf Mohammed ◽  
Belmajdoub Fouad
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Discrete Event Systems ◽  
Discrete Event ◽  
Modeling Tools ◽  
Feed Forward ◽  
Industrial Systems ◽  
Diagnosis And Prognosis ◽  
Event Systems ◽  
Fault Diagnosis And Prognosis

The elaboration and development of monitoring (diagnostic and prognostic) tools for industrial systems has been one of the main concerns of the researchers for many years, so that many researches and studies have been developed and proposed, especially concerning discrete event systems (DES), which occupy an important class of industrial systems. However, the use of modeling tools to ensure these operations become a complex and exhausting task, while the complexity of industrial systems has been increasing incessantly. Therefore, the development of more and more sophisticated techniques is required. In this context, the use of artificial neural networks (NN) seems interesting, because thanks to their automatics and intelligent algorithms, the NN could handle perfectly DES diagnosis and prognosis problems. For this purpose, in the following papers, we propose an intelligent approach based on feed-forward neural network, which will deal with fault diagnosis and prognosis in DES, so that the events generated by the DES, will be presented and analyzed by the neural network in real-time, in order to perform an online diagnosis and prognosis.

scholarly journals Specification of dynamic structure discrete event systems using single point encapsulated control functions

2014 ◽  
Vol 05 (03) ◽  
pp. 1450012 ◽  
Author(s):  
Alexandre Muzy ◽  
Bernard P. Zeigler
Keyword(s):  
Discrete Event Systems ◽  
Single Point ◽  
Discrete Event ◽  
Dynamic Structure ◽  
System Specification ◽  
Discrete Event System Specification ◽  
Usual Definition ◽  
Control Functions ◽  
Event System ◽  
Structure Changes

In Discrete Event System Specification (DEVS), the dynamics of a network is constituted only by the dynamics of its basic components. The state of each component is fully encapsulated. Control in the network is fully decentralized to each component. At dynamic structure level, DEVS should permit the same level of decentralization. However, it is hard to ensure structure consistency while letting all components achieve structure changes. Besides, this solution can be complex to implement. To avoid these difficulties, usual dynamic structure approaches ensure structure consistency allowing structure changes to be done only by the network having newly added dynamics change capabilities. This is a safe and simple way to achieve dynamic structure. However, it should be possible to simply allow components of a network to modify the structure of their network, other components and/or their own structure — without having to modify the usual definition a DEVS network. In this manuscript, it is shown that a simple fully decentralized approach is possible while ensuring full modularity and structure consistency.

scholarly journals Logic inference based construction of a supervisor for a discrete event system

2020 ◽  
Author(s):  
A. Davydov ◽  
A. Larionov ◽  
N. Nagul
Keyword(s):  
Supervisory Control ◽  
Discrete Event Systems ◽  
Autonomous Underwater Vehicle ◽  
Discrete Event ◽  
Discrete Event System ◽  
General View ◽  
Logical Inference ◽  
Event System ◽  
Logic Inference ◽  
Operational Modes

The paper provides a general view on the original logical inference based approach to dealing with discrete event systems as subject to supervisory control theory. The approach proposes a representation of automata-based discrete event system as a positively constructed formula and implementation of the calculus of positively constructed formulas. The stages of a supervisor construction are illustrated with a simplified model of an autonomous underwater vehicle operational modes switching. The supremal controllable sublanguage of the specification and the supervisor are constructed.

scholarly journals MODELING PREDICTIVE TRACKING CONTROL FOR MAX-PLUS LINEAR SYSTEMS IN MANUFACTURING

2020 ◽  
Vol 3 (2) ◽  
pp. 133-147
Author(s):  
Lathifatul Aulia ◽  
Widowati Widowati ◽  
R. Heru Tjahjana ◽  
Sutrisno Sutrisno
Keyword(s):  
Linear Systems ◽  
Production System ◽  
Tracking Control ◽  
Discrete Event Systems ◽  
Discrete Event ◽  
Process Flow ◽  
Sequence Of Events ◽  
Input And Output ◽  
Event System ◽  
Event Systems

Discrete event systems, also known as DES, are class of system that can be applied to systems having an event that occurred instantaneously and may change the state. It can also be said that a discrete event system occurs under certain conditions for a certain period because of the network that describes the process flow or sequence of events. Discrete event systems belong to class of nonlinear systems in classical algebra. Based on this situation, it is necessary to do some treatments, one of which is linearization process. In the other hand, a Max-Plus Linear system is known as a system that produces linear models. This system is a development of a discrete event system that contains synchronization when it is modeled in Max-Plus Algebra. This paper discusses the production system model in manufacturing industries where the model pays the attention into the process flow or sequence of events at each time step. In particular, Model Predictive Control (MPC) is a popular control design method used in many fields including manufacturing systems. MPC for Max-Plus-Linear Systems is used here as the approach that can be used to model the optimal input and output sequences of discrete event systems. The main advantage of MPC is its ability to provide certain constraints on the input and output control signals. While deciding the optimal control value, a cost criterion is minimized by determining the optimal time in the production system that modeled as a Max-Plus Linear (MPL) system. A numerical experiment is performed in the end of this paper for tracking control purposes of a production system. The results were good that is the controlled system showed a good performance.

Sign in / Sign up

Export Citation Format

Share Document