This study aims at determining the optimal material and process parameters that will maximize the quality characteristics of miscanthus fiber-reinforced polypropylene (MFRPP) composite. Taguchi L16 was utilized in the design of experiment and larger-the-better signal-to-noise ratio was used in the analysis of the impact strength of MFRPP. Optimal combination of material and process parameters and the main effects were determined, and the significant variables were identified using analysis of variance. Artificial neural network (ANN) and extreme learning machine (ELM) were utilized on the Taguchi experimental data and used in the prediction of the impact strength of MFRPP. The results showed the optimum impact strength occurred at 25 wt% miscanthus fiber loading. The results of the predictions made revealed that both ANN and ELM are very efficient in predicting the impact strength of MFRPP as shown by the relative errors when compared with the experimental data. Both the performance metrics assessments and the quality of prediction show that ELM is a better machine learning technique than ANN. The high impact strength of MFRPP composite is a confirmation that MFRPP is a very useful material for industrial applications.
This study focuses on solving the problem of overstocking and under stocking of production inventory in manufacturing sector. To ensure effective management of inventory in manufacturing sector, three years production data were gathered and properly analyzed using multiple linear regression analysis and time series forecasting methods. A multiple linear regression model was developed in MINITAB software to make prediction for inventory requirements. From the result, the coefficient of determination (R2) is 1.00, the adjusted R2 is 1.00, F-distribution is 4.212 x 107 which is greater than any value in F-distribution table, and all these show a very strong relationship between the dependent variable and the independent variables. Also, a Time series analysis was done to make forecast of monthly inventory requirements for both raw materials and finished products. Trend analysis and Moving Average method were used in Time series forecasting, and lower Mean Absolute Percent Error (MAPE) and Mean Absolute Deviation (MAD) were used as criteria for selecting the method that gives the best forecast. From the results obtained, Trend analysis gave MAPE 13% and MAD 2350, while Moving Average gave MAPE 14% and MAD 2574. This work adds to growing body of literatures on data driven inventory management by utilizing historical data in customized software for generation of models that can effectively make forecast of inventory requirements in manufacturing sector.
Nomenclature:
a = Value of yt at t = 0; b = Trend Value; MA= Moving Average; MAD = Mean Absolute Deviation MAPE =Mean Absolute Percentage Error; N = Number of periods;
t = Period Yt = Forecast for period t y = Monthly Quantity of Product Produced α=regression constant
β1-βk=Coefficients of the independent variables
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.