Integrated decision-support system for diagnosis, maintenance planning, and scheduling of manufacturing systems

Jeong, In-Jae; Leon, V. Jorge; Villalobos, J. René

doi:10.1080/00207540600678896

Cited by 47 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Yang & Lee [9] and Correa et al [10] made use of K2 [11] and Chow-Liu [12], algorithms respectively to generate trees from data. Jeong et al [13] extract the cause-effect relationship for the equipment that is diagnosed from the equipment's maintenance manual. Process data obtained from sensors and stored in manufacturing execution systems (MES) or maintenance databases are then used to generate the conditional probabilities of the network.…”

Section: Bayesian Networkmentioning

confidence: 99%

A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis

Ademujimi

Brundage

Prabhu

2017

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Artificial intelligence applications are increasing due to advances in data collection systems, algorithms, and affordability of computing power. Within the manufacturing industry, machine learning algorithms are often used for improving manufacturing system fault diagnosis. This study focuses on a review of recent fault diagnosis applications in manufacturing that are based on several prominent machine learning algorithms. Papers published from 2007 to 2017 were reviewed and keywords were used to identify 20 articles spanning the most prominent machine learning algorithms. Most articles reviewed consisted of training data obtained from sensors attached to the equipment. The training of the machine learning algorithm consisted of designed experiments to simulate different faulty and normal processing conditions. The areas of application varied from wear of cutting tool in computer numeric control (CNC) machine, surface roughness fault, to wafer etching process in semiconductor manufacturing. In all cases, high fault classification rates were obtained. As the interest in smart manufacturing increases, this review serves to address one of the cornerstones of emerging production systems.

show abstract

Section: Bayesian Networkmentioning

confidence: 99%

A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis

Ademujimi

Brundage

Prabhu

2017

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…Xu et al (2008) introduced and studied a parallel machine scheduling problem with almost periodic maintenance activities to minimise the completion time of the last finished maintenance. Jeong et al (2007) presented an integrated decision-support system for diagnosis, maintenance planning, and scheduling of electronics manufacturing systems to minimise makespan or total completion time. Cassady and Kutanoglu (2003) developed an integrated model for a single machine problem with an objective of minimising expected total weighted tardiness.…”

Section: Integrated Approaches To Production Scheduling and Maintenancementioning

confidence: 99%

Joint consideration of production scheduling, maintenance and quality policies: a review and conceptual framework

Pandey

Kulkarni

Vrat

2010

IJAOM

View full text Add to dashboard Cite

Performance of a manufacturing system depends on its ability to simultaneously meet several requirements such as: quick response to market demand, high product quality, low manufacturing costs and timely deliveries; which in turn strongly depend on performance at the shop floor level. In the past, the shop floor level operational policies in the context of scheduling, maintenance and quality have been examined in isolation. However, it is hypothesised that these three aspects of operations planning may also have some interaction effect and hence joint consideration of various policy options pertaining to quality, maintenance and scheduling on the performance of the manufacturing system is an important area for investigation. In this paper, a review of literature addressing the joint consideration of these three aspects is presented and research gaps are highlighted. As a preliminary work, some numerical investigations are also presented to highlight the importance of joint consideration of these three aspects. Finally, a conceptual methodology is presented that can lead to further developments in this field. Some potential research areas in this context are identified. ) of the Indian Institute of Technology, Roorkee (India) and the Director-in-Charge of IIT Delhi (July-December 2000). He has vast experience in teaching, research and consultancy spanning for more than 41 years. He is on the editorial board of several international journals. He has many awards and prizes to his credit. His areas of interest include productivity management, supply chain management, industrial engineering, operations research and operations management. 1 job-attributed criteria (e.g., job flow time) 2 shop-attributed criteria (e.g., machine utilisation) 3 completion-based criteria (e.g., makespan) 4 due-date-based criteria (e.g., tardiness) 5 financial criteria (e.g., job handling cost) 6 miscellaneous criteria (e.g., labour utilisation).In general, production scheduling models are often mathematical programming models designed to maximise or minimise one or more of the above measures. Solution methodologies for such models range from traditional integer programming

show abstract

“…The problems of modelling and optimisation of CBM have been widely investigated and successfully applied to single-component systems, see Grall, Dieulle, Bérenguer, and Roussignol (2002), Jardine et al (2006), Van Noortwijk (2009), Huynh, Barros Bérenguer, and Castro (2011), Huynh, Castro and Ahmad and Kamaruddin (2012) for an overview. In CBM, the maintenance decision-making can be based on fault diagnostic (the process of finding the cause of a fault (Jeong, Leon, & Villalobos, 2007)) and failure prognostic (the process of determining when a failure may occur in the future (Lewis & Edwards, 1997)) with two main types of degradation modelling (Wang, Chu, & Mao, 2008). For the first type, Markov chains are used to describe deterioration processes of components/system.…”

Section: Introductionmentioning

confidence: 99%

Condition-based maintenance for multi-component systems using importance measure and predictive information

Nguyen

Van

Grall

2014

International Journal of Systems Science: Operations & Logi

View full text Add to dashboard Cite

This paper presents a predictive condition-based maintenance strategy for multi-component systems whose structure may impact components deterioration process. To select components for preventive maintenance actions, a decision rule relying on both structural importance measure of components and their predictive reliability that can be estimated at inspection times is proposed. For corrective maintenance actions, an adaptive opportunistic maintenance decision rule taking into account both the criticality level of components and logistic support constraints is introduced. Moreover, both economic and structure dependencies between components are studied and integrated in maintenance model. A 12-component system is finally introduced to illustrate the use and the performance of the proposed predictive maintenance strategy. Indeed, the proposed strategy provides more flexibility in maintenance decision-making, hence leading to significant profits in terms of maintenance cost when compared to existing strategies.

show abstract

Integrated decision-support system for diagnosis, maintenance planning, and scheduling of manufacturing systems

Cited by 47 publications

References 19 publications

A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis

A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis

Joint consideration of production scheduling, maintenance and quality policies: a review and conceptual framework

Condition-based maintenance for multi-component systems using importance measure and predictive information

Contact Info

Product

Resources

About