A framework for determining MIMO process parameters by a neuro-DM&ACO approach

• Published in: International journal of production research Vol. 45; no. 15; pp. 3505 - 3520
• Main Authors: Wong, J.-T., Su, C.-T., Hsieh, H.-T.
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis Group 01.08.2007; Washington, DC Taylor & Francis; Taylor & Francis LLC
• Subjects: Ant colony optimisation (ACO); Applied sciences; Artificial neural network (ANN); Chemical-mechanical planarisation (CMP); Computer science; control theory; systems; Data mining; Data processing. List processing. Character string processing; Electronics; Exact sciences and technology; Inventory control, production control. Distribution; Memory organisation. Data processing; Microelectronic fabrication (materials and surfaces technology); Neural networks; Operational research and scientific management; Operational research. Management science; Optimization algorithms; Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices; Semiconductors; Simulation; Software; Studies; Capability index; MIMO system; Data analysis; Mechanical polishing; Decision making; Chemical polishing; Data processing; Information extraction; Artificial neural network (ANN); Neural network; Data mining; Ant colony optimisation (ACO); Operating conditions; Microelectronic fabrication; Planarization; Manufacturing process; Chemical-mechanical planarisation (CMP); Swarm intelligence; Production process
• ISSN: 0020-7543; 1366-588X
• DOI: 10.1080/00207540500471814

A framework combining artificial neural network (ANN) modelling technique, data mining and ant colony optimisation (ACO) algorithm is proposed for determining multiple-input multiple-output (MIMO) process parameters from the initial chemical-mechanical planarisation (CMP) processes used in semiconductor manufacturing. Owing to the invisibility of the ANN in the solution procedures, the decision tree approach of data mining is adopted to provide the necessary information for a real-valued ACO. The simulation result demonstrates that the proposed method can be an efficient tool for selecting properly defined parameter combination with the CMP process.