Increasing climate change concerns call for the manufacturing sector to decarbonize its process by introducing a mitigation strategy. Energy efficiency concepts within the manufacturing process value chain are proportional to the emission reductions, prompting decision makers to require predictive tools to execute decarbonization solutions. Accurate forecasting requires techniques with a strong capability for predicting automotive component manufacturing energy consumption and carbon emission data. In this paper we introduce a hybrid autoregressive moving average (ARIMA)-long short-term memory network (LSTM) model for energy consumption forecasting and prediction of carbon emission within the manufacturing facility using the 4IR concept. The method could capture linear features (ARIMA) and LSTM captures the long dependencies in the data from the nonlinear time series data patterns, Root means square error (RMSE) is used for data analysis comparing the performance of ARIMA which is 448.89 as a single model with ARIMA-LSTM hybrid model as actual (trained) and predicted (test) 59.52 and 58.41 respectively. The results depicted RMSE values of ARIMA-LSTM being extremely smaller than ARIMA, which proves that hybrid ARIMA-LSTM is more suitable for prediction than ARIMA.
Application of ARIMA-LSTM for Manufacturing Decarbonization Using 4IR Concepts
Lect.Notes Mechanical Engineering
International Conference on Flexible Automation and Intelligent Manufacturing ; 2022 ; Detroit, MI, USA June 19, 2022 - June 23, 2022
Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus ; Kapitel : 12 ; 115-123
2022-10-13
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Prediction of ship track based on ARIMA-LSTM
British Library Conference Proceedings | 2022
|Prediction of ship track based on ARIMA-LSTM
SPIE | 2022
|Short traffic flow prediction method based on ARIMA and LSTM hybrid neural network
Europäisches Patentamt | 2021
|