Enhancement of Throughput Simulation Accuracy Using AI
G. Jehovah Jerone1, R. Pugazhenthi2, C. Dhanasekaran3, M. Chandrasekaran4
1G. Jehovah Jerone, P.G. Student, Department of Mechanical Engineering, Vels Institute of Science, Technology & Advanced Studies, Chennai (Tamil Nadu), India.
2C. Dhanasekaran, Professor, Department of Mechanical Engineering, Vels Institute of Science, Technology & Advanced Studies, Chennai (Tamil Nadu), India.
3R. Pugazhenthi, Professor, Department of Mechanical Engineering, Vels Institute of Science, Technology & Advanced Studies, Chennai (Tamil Nadu), India.
4M. Chandrasekaran, Professor, Department of Mechanical Engineering, Vels Institute of Science, Technology & Advanced Studies, Chennai (Tamil Nadu), India.
Manuscript received on 19 May 2019 | Revised Manuscript received on 05 June 2019 | Manuscript Published on 15 June 2019 | PP: 69-74 | Volume-8 Issue-1S2 May 2019 | Retrieval Number: A00140581S219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This research article study and analyze the feasibility of deploying the time study analysis, which has been created by using Artificial Intelligence (AI). Artificial Intelligence is used to reach accurate results by a throughput simulation study and which is also used to reduce the percentage of variability in the pre-production study versus the physical implementation. The modern manufacturing facility is very keen in implementing the optimized production system to avoid the unwanted cost investment and smooth running without stoppage like starving and blocking prior to the physical implementation. But the level of output accuracy differs in Throughput study when we use the designed cycle time instead of the real physical time studies. Deriving the physical time study is possible only when the facility is implemented in the manufacturing area. In this study, the correlation between the AI and physical time would be validated and Throughput simulation result will be compared to improve the accuracy and difference. Usual data usage for the Throughput study are designed to cycle time, Mean Time To Repair (MTTR), Mean Time Between Failures (MTBF). This feasibility study will replace the designed cycle time by Artificial Intelligence (AI) time. Expected results from this study are to find the benefits by using the AI time studies from the Throughput simulation when compared to the designed cycle time.
Keywords: Artificial Intelligence, Automod, MTBF, Simulation.
Scope of the Article: Artificial Intelligence