... of lost production, the cost of repair persons and the cost of standby machines. The developed design procedure integrates simulation, metamodel and genetic algorithms. Neural networks are able to approximate functions based on a set of sample data, i.e. construct metamodels from simulation results...

.... “Backpropagation neural networks”, or multilayer perceptron (Rumelhart et al., 1986), which will be applied in this work, figure among those networks that are most well‐know and most widely used as pattern classifiers or function approximators (Freeman and Skapura, 1991; Lippman, 1987). An overview...

... to integrate both these aspects into a seamless design process, using multiple layers of neural networks to characterise the cushioning curve patterns of EPS materials, determine cushioning configurations and arrangements based on package‐to‐product characteristics, and size the buffer features. The favourable...

... neural networks (ANNs) and classification and regression trees (CARTs) represent two practical approaches with special capabilities for operationalizing the kanban setting problem. This paper provides a comparison of ANNs with CART for setting the number of kanbans in a dynamically...

... 1. 1 Fast inference and high working efficiency. 2. 2 Its ability to perform the new inference procedure by training neural networks with new examples. 3. 3 Its adaptability to the dynamic manufacturing environment, owing to efficient knowledge acquisition capability. However...

...‐based and AI‐based. Presents a hybrid approach using simulation‐based scheduling and a neural network to solve the detailed scheduling problem. Develops the neural network to analyse the complex information as well as orders coming on the shopfloor, and suggests candidate scheduling rules...

...Siang Kok Sim; Ming Yeong Teo Describes work based on the hypothesis that the use of artificial neural networks can imbue vision‐based robots with the ability to learn about their environment and hence enhance their competence and flexibility. The Neocognitron neural network provides the vision...

... part routings among alternate routings to minimize the operating cost. At the second stage, a specific number of cells is obtained by using an ART1 neural network‐based cell formation module in approach A and a fuzzy rank order clustering (fuzzy ROC) module in approach B. At the third stage, production...