A Blended System Dynamics-Discrete Event Physics-Based Model for Anomaly Detection in Cyber-Physical Manufacturing Systems

2021 ◽  
Author(s):  
HONG YU ◽  
Ajay Raghavan ◽  
Deokwoo Jung ◽  
Saman Mostafavi ◽  
Yukinori Sasaki ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
System Dynamics ◽  
Manufacturing Systems ◽  
Discrete Event

A Blended System Dynamics-Discrete Event Physics-Based Model for Anomaly Detection in Cyber-Physical Manufacturing Systems

2020 ◽  
Author(s):  
Hong Yu ◽  
Ajay Raghavan ◽  
Saman Mostafavi ◽  
Deokwoo Jung ◽  
Yukinori Sasaki ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
System Dynamics ◽  
Discrete Event Simulation ◽  
Manufacturing Systems ◽  
Discrete Event ◽  
Continuous Variables ◽  
Event Simulation ◽  
Computational Overhead ◽  
Discrete Manufacturing System ◽  
Discrete Manufacturing

Abstract Being able to quickly detect anomalies and reason about their root causes in critical manufacturing systems can significantly reduce the analysis time to bring operations back online, thus reducing expensive unplanned downtime. Machine learning-based anomaly detection approaches often need significant amounts of labeled data for training and are challenging to scale for manufacturing deployments. A robust blended system dynamics and discrete event simulation physics-based modeling methodology is proposed for the task of automated anomaly detection. The blended model consists of discrete event simulation (DES) components for the discrete manufacturing process modeling, and system dynamics (SD) components for continuous variables. The methodology strikes a balance between the computational overhead for online monitoring and the level of details required to perform anomaly detection tasks. The implementation of models takes an object-oriented approach, allowing multiple components of a smart factory to be robustly described in a modular, extendable and reconfigurable manner. The proposed methodology is applied to and validated by data collected from a real commercial manufacturing plant. A production line is modeled with DES components and heat transfer is modeled with SD. The blended model is then utilized for anomaly detection. It is demonstrated that the model-based approach is effective not only for detecting but also explaining particular types of anomalies in a commercial discrete manufacturing system.

MANUFACTURING SYSTEMS MODELLING USING SYSTEM DYNAMICS: FORMING A DEDICATED MODELLING TOOL

2003 ◽  
Vol 02 (01) ◽  
pp. 71-87 ◽  
Author(s):  
A. OYARBIDE ◽  
T. S. BAINES ◽  
J. M. KAY ◽  
J. LADBROOK
Keyword(s):  
System Dynamics ◽  
System Design ◽  
Discrete Event Simulation ◽  
Manufacturing Systems ◽  
Manufacturing System ◽  
Computer Modelling ◽  
Discrete Event ◽  
Event Simulation ◽  
Manufacturing System Design ◽  
Computer Based

Discrete event simulation is a popular aid for manufacturing system design; however in application this technique can sometimes be unnecessarily complex. This paper is concerned with applying an alternative technique to manufacturing system design which may well provide an efficient form of rough-cut analysis. This technique is System Dynamics, and the work described in this paper has set about incorporating the principles of this technique into a computer based modelling tool that is tailored to manufacturing system design. This paper is structured to first explore the principles of System Dynamics and how they differ from Discrete Event Simulation. The opportunity for System Dynamics is then explored, and this leads to defining the capabilities that a suitable tool would need. This specification is then transformed into a computer modelling tool, which is then assessed by applying this tool to model an engine production facility.

scholarly journals Anomaly Detection in Discrete Manufacturing Systems by Pattern Relation Table Approaches

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5766
Author(s):  
Xinmiao Sun ◽  
Ruiqi Li ◽  
Zhen Yuan
Keyword(s):  
Anomaly Detection ◽  
Manufacturing Systems ◽  
Sequence Data ◽  
Discrete Event ◽  
Intelligent Manufacturing ◽  
System Structure ◽  
Data Set ◽  
Structure Information ◽  
Discrete Manufacturing ◽  
Repeated Events

Anomaly detection for discrete manufacturing systems is important in intelligent manufacturing. In this paper, we address the problem of anomaly detection for the discrete manufacturing systems with complicated processes, including parallel processes, loop processes, and/or parallel with nested loop sub-processes. Such systems can generate a series of discrete event data during normal operations. Existing methods that deal with the discrete sequence data may not be efficient for the discrete manufacturing systems or methods that are dealing with manufacturing systems only focus on some specific systems. In this paper, we take the middle way and seek to propose an efficient algorithm by applying only the system structure information. Motivated by the system structure information that the loop processes may result in repeated events, we propose two algorithms—centralized pattern relation table algorithm and parallel pattern relation table algorithm—to build one or multiple relation tables between loop pattern elements and individual events. The effectiveness of the proposed algorithms is tested by two artificial data sets that are generated by Timed Petri Nets. The experimental results show that the proposed algorithms can achieve higher AUC and F1-score, even with smaller sized data set compared to the other algorithms and that the parallel algorithm achieves the highest performance with the smallest data set.

scholarly journals Hybrid simulation modelling of the human-production process interface in lean manufacturing systems

2019 ◽  
Vol 10 (2) ◽  
pp. 665-690 ◽  
Author(s):  
Omogbai Oleghe ◽  
Konstantinos Salonitis
Keyword(s):  
System Dynamics ◽  
Continuous Improvement ◽  
Lean Manufacturing ◽  
Manufacturing Systems ◽  
Discrete Event ◽  
Hybrid Simulation ◽  
Simulation Modelling ◽  
Problem Situation ◽  
Hybrid Modelling ◽  
Content Type

Purpose This study aims to seek to advance a system dynamics-discrete event hybrid simulation modelling concept useful for taking improvement decisions where one needs to consider the interactions between human factors and process flow elements in lean manufacturing systems. Design/methodology/approach A unique approach is taken to hybrid simulation modelling where the whole problem situation is first conceptualized using a causal loop diagram and stock and flow diagram, before transmitting to a hybrid simulation model. The concept is intended to simplify the simulation modelling process and make the concept pliable for use in various types of lean manufacturing problem situations. Findings The hybrid simulation modelling concept was applied to a lean manufacturing case where quality performance was sporadic mainly because of production pressures. The hybrid modelling concept revealed a solution that advanced full compliance with lean and one that required changes in job scheduling policies to promote both continuous improvement and throughput increases. Research limitations/implications Because non-tangible aspects of lean were objectively assessed using the hybrid modelling concept, the study is an advancement towards establishing a credible link between human resource aspects of lean and the performance of an organization. Practical implications The applied hybrid model enabled managers in the plant navigate the trade-off decision they often face when choosing to advance production output ahead of continuous improvement practices. Originality/value System dynamics-discrete event hybrid simulation modelling is a rarity in lean manufacturing systems.

scholarly journals Discrete Event System Control in Max-Plus Algebra: Application to Manufacturing Systems

2020 ◽  
Vol 53 (4) ◽  
pp. 143-150
Author(s):  
Gabriel Freitas Oliveira ◽  
Renato Markele Ferreira Candido ◽  
Vinicius Mariano Gonçalves ◽  
Carlos Andrey Maia ◽  
Bertrand Cottenceau ◽  
...  
Keyword(s):  
Manufacturing Systems ◽  
Discrete Event ◽  
Discrete Event System ◽  
System Control ◽  
Event System

Discrete-event modeling by system dynamics method

2021 ◽  
Author(s):  
A. N. Medvedev ◽  
V. N. Timokhin ◽  
Yu. A. Nelyubina
Keyword(s):  
System Dynamics ◽  
Discrete Event ◽  
Event Modeling ◽  
Dynamics Method

Knowledge Application Model for Manufacturing Process

2011 ◽  
Vol 467-469 ◽  
pp. 1218-1224
Author(s):  
Hong Feng Lai ◽  
Kuang Yao Wu
Keyword(s):  
Manufacturing Systems ◽  
Discrete Event ◽  
Static Structure ◽  
Knowledge Application ◽  
Flexible Assembly ◽  
Mathematical Properties ◽  
Traditional Function ◽  
Manufacturing Knowledge ◽  
Function Models ◽  
Distributed Manufacturing Systems

This paper proposes a categorical foundation for integrating various types of manufacturing knowledge in manufacturing systems. The composing procedures of overall system can be explained by pushout of category theory. The purpose of this paper is to resolve the issue involves in sharing and coordination for modeling knowledge application in distributed manufacturing systems. We will propose a method for modeling discrete event system. The mathematical foundation lies in assuring that the constructed models have mathematical properties, e.g. consistency and completeness, and overcome the drawbacks of traditional function models, since it can show not only the static structure but also the dynamic semantics. The categorical notations and properties are expressed by an example of flexible assembly workcell.

Sign in / Sign up

Export Citation Format

Share Document