Anomaly detection without a pre-existing formal model: Application to an industrial manufacturing system

Author(s):  
J. A. Broderick ◽  
L. V. Allen ◽  
D. M. Tilbury
2013 ◽  
Vol 300-301 ◽  
pp. 85-88
Author(s):  
Hwa Young Jeong ◽  
Jong Hyuk Park ◽  
Hae Gill Choi

Industrial technology and its engineering depend on the integration of new technical trend, devices, its application and their business management processes. It also needs to consider the various situations in their working environment. Therefore, the system software engineer has to design the manufacturing system software considering accurate user need, system software requirement and matching their process to the machine in the design level when they make or develop the system software. In this paper, we discuss and make a process model for manufacturing system software. The software process model can be dynamical arrange their module when it needs re-arrange the sub module.


2012 ◽  
Vol 252 ◽  
pp. 364-367
Author(s):  
Yan Na Zhao

This article puts forward the new research methodology during establishing evaluation index system of industrial manufacturing system competence in He Bei .Firstly, we establish a set of the primary evaluating Index system. Secondly,we assess and screen these Indexes. At lastly ,we determine the final evaluating Index system.The Index system is more objective in this way.


Author(s):  
Matthieu Rauch ◽  
Jean-Yves Hascoet

Companies have to propose flexibility and interoperability in addition to robustness and efficiency to meet today demand of high customized products. The rise of high level object-oriented data models such as ISO 14649 — know as STEP-NC — enables manufacturing engineers to meet these requirements. In parallel, new manufacturing processes are now available. Theses processes, such as incremental sheet forming or cladding, are mature enough to be used in the industry. In addition to that, they are CNC controlled. They can be totally integrated into manufacturing data chains. It is consequently possible to use several processes on the same part and develop multi-process manufacturing approaches. Their success lies mainly upon the ability to select the best process with the best parameterization. The use of intelligent manufacturing systems is of great help to achieve this goal. The objective of this paper is to propose an intelligent manufacturing environment for multi-process manufacturing. Simulation and optimization approaches, advanced CNC programming methods are implemented in a coordinate way. Current CAD/CAM/CNC data chains limitations are overtaken by using STEP-NC. Finally, a practical implementation of such system is introduced. This experimental platform enables multi-process manufacturing with the industrial manufacturing equipment of the laboratory.


Author(s):  
Borja Ramis Ferrer ◽  
Wael M. Mohammed ◽  
Mussawar Ahmad ◽  
Sergii Iarovyi ◽  
Jiayi Zhang ◽  
...  

AbstractThe literature on the modeling and management of data generated through the lifecycle of a manufacturing system is split into two main paradigms: product lifecycle management (PLM) and product, process, resource (PPR) modeling. These paradigms are complementary, and the latter could be considered a more neutral version of the former. There are two main technologies associated with these paradigms: ontologies and databases. Database technology is widespread in industry and is well established. Ontologies remain largely a plaything of the academic community which, despite numerous projects and publications, have seen limited implementations in industrial manufacturing applications. The main objective of this paper is to provide a comparison between ontologies and databases, offering both qualitative and quantitative analyses in the context of PLM and PPR. To achieve this, the article presents (1) a literature review within the context of manufacturing systems that use databases and ontologies, identifying their respective strengths and weaknesses, and (2) an implementation in a real industrial scenario that demonstrates how different modeling approaches can be used for the same purpose. This experiment is used to enable discussion and comparative analysis of both modeling strategies.


2018 ◽  
Vol 24 (2) ◽  
pp. 170-184 ◽  
Author(s):  
Guy Richard Kibouka ◽  
Donatien Nganga-Kouya ◽  
Jean-Pierre Kenné ◽  
Vladimir Polotski ◽  
Victor Songmene

PurposeThe purpose of this paper is to find the optimal production and setup policies for a manufacturing system that produces two different types of parts. The manufacturing system consists of one machine subject to random failures and repairs. Reconfiguring the machine to switch production from one type of product to another generates a non-production time and a significant cost.Design/methodology/approachThis paper proposes an approach based on the development of optimal production and setup policies, taking into account the possibilities of undertaking the setup for all modes of the machine, and covering them at the end of setup. New optimality conditions are developed in terms of modified Hamilton-Jacobi-Bellman (HJB) equations and recursive numerical methods are applied to solve such equations.FindingsThe proposed approach led to determine more realistic production rates of both parts and setup sequences for the different modes of the machine that significantly influence the inventory and the system capacity. A numerical example and sensitivity analysis are used to determine the structure of the optimal policies and to show the helpfulness and robustness of the results obtained.Practical implicationsFollowing the steps of the proposed approach will provide the control policies for industrial manufacturing systems with setup permitted at all modes of the machine, and when the setup does not necessarily restore the machine to its operational mode. The proposed optimal policy takes into account the stochastic nature of the machine mode at the end of setup and we show that ignoring it leads to non-natural policies and underestimates significantly the safety stock thresholds.Originality/valueConsidering the assumptions presented in this paper leads to a new structure of the control laws for the production planning of manufacturing systems with setup.


Sign in / Sign up

Export Citation Format

Share Document