Applications of neural networks in manufacturing: a state-of-the-art survey

Zhang, Hongchao; Huang, Samuel H.

doi:10.1080/00207549508930175

Cited by 164 publications

(66 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zhang and Huang (1995) discussed the applications of neural networks in general. Burke and Ignozio (1992) reviewed the application of neural networks in operations research.…”

Section: Research Backgroundmentioning

confidence: 99%

Simulation metamodelling with neural networks: An experimental investigation

Sabuncuoğlu¹,

Touhami²

2002

International Journal of Production Research

View full text Add to dashboard Cite

Arti®cial neural networks are often proposed as an alternative approach for formalizing various quantitative and qualitative aspects of complex systems. This paper examines the robustness of using neural networks as a simulation metamodel to estimate manufacturing system performances. Simulation models of a job shop system are developed for various con®gurations to train neural network metamodels. Extensive computational tests are carried out with the proposed models at various factor levels (study horizon, system load, initial system status, stochasticity, system size and error assessment methods) to see the metamodel accuracy. The results indicate that simulation metamodels with neural networks can be e ectively used to estimate the system performances. IntroductionSimulation has been widely accepted by the scienti®c community and practitioners as a¯exible tool in modelling and analysis of complex systems. It reduces the cost, time and risks associated with the implementations of new designs. However, due to its lengthy computational requirements and the trail-and-error nature of the development process, simulation may not be always the ®rst preferred tool in solving real-life problems. This issue is particularly important for problems where the solution space is very large and when the time available for decisionmaking is too limited for extensive analysis to be performed (i.e. on-line applications). Harmonosky and Robohn (1995) stated that CPU requirements appeared to be a major obstacle for the on-line applications of simulation. Time considerations are still an important issue, even with the o -line use of simulation due to the increasing complexity of the modern production systems. In this paper, it is argued that the use of simulation metamodels may help alleviate these problems.A simulation metamodel is a simpler model of the real system. The simulation model is an abstraction of the real system in which a selected subset of inputs is considered. The e ect of the excluded inputs is represented in the model in the form of the randomness to which the system is subject. As illustrated in ®gure 1, a metamodel is a further abstraction of the simulation model. Simulation is used to generate data sets, which in turn are used to build the metamodel. A simulation metamodel with neural networks is a neural network whose training is provided by a simulation model. In general, a metamodel takes a fewer number of inputs

show abstract

“…Zhang and Huang (1995) discussed the applications of neural networks in general. Burke and Ignozio (1992) reviewed the application of neural networks in operations research.…”

Section: Research Backgroundmentioning

confidence: 99%

Simulation metamodelling with neural networks: An experimental investigation

Sabuncuoğlu¹,

Touhami²

2002

International Journal of Production Research

View full text Add to dashboard Cite

show abstract

“…Kim et al (1995) combine the BPNN with the apparent tardiness cost rule, and report a significant improvement of 8% on average. For a complete survey of neural network scheduling applications in manufacturing, we refer the readers to Sabuncuoglu (1998) and Zhang and Huang (1995). It is noteworthy that Philipoom and Rees (1997) conclude that neural networks far outperformes the traditional approcahes for job shop scheduling and are statistically better.…”

Section: Literature Reviewmentioning

confidence: 99%

A neuro-genetic approach to design and planning of a manufacturing cell

2005

View full text Add to dashboard Cite

_________________________________________________________________ Recommended citationCaker, Tarik., Yildirim, Mehmet Bayram. and Mehmet Barut. 2005 In this paper, we propose a neuro-genetic decision support system coupled with simulation to design a job shop manufacturing system by achieving predetermined values of targeted performance measures such as flow time, number of tardy jobs, total tardiness and machine utilization at each work center. When a manufacturing system is designed, the management has to make decisions on the availability of resources or capacity, in our setting, the number of identical machines in each work station and the dispatching rule to be utilized in the shop floor to achieve performance values desired. Four different priority rules are used as Earliest due date (EDD), Shortest Processing Time (SPT), Critical ratio (CR) and First Come First Serve (FCFS). In reaching the final decision, design alternatives obtained from the proposed system are evaluated in terms of performance measures. An illustrative example is provided to explain the procedure.

show abstract

“…These range from sophisticated aerospace applications such as the IPCS, to various mobility support systems such as anti-lock breaking systems in automobiles, to thermostats that adapt to environmental conditions. Neural networks are not only embedded in many robotics systems in manufacturing, they are often involved in other areas of process control, for example, shop floor planning [Jain 1998] and diagnosis [Zhang 1995].…”

Section: Roboticsmentioning

confidence: 99%

Methods and Procedures for the Verification and Validation of Artificial Neural Networks

Taylor¹

2006

View full text Add to dashboard Cite

Applications of neural networks in manufacturing: a state-of-the-art survey

Cited by 164 publications

References 62 publications

Simulation metamodelling with neural networks: An experimental investigation

Simulation metamodelling with neural networks: An experimental investigation

A neuro-genetic approach to design and planning of a manufacturing cell

Methods and Procedures for the Verification and Validation of Artificial Neural Networks

Contact Info

Product

Resources

About