Rahul Priyadarshi, Akash Panigrahi, Srikanta Routroy and Girish Kant Garg
The purpose of this study is to select the appropriate forecasting model at the retail stage for selected vegetables on the basis of performance analysis.
Abstract
Purpose
The purpose of this study is to select the appropriate forecasting model at the retail stage for selected vegetables on the basis of performance analysis.
Design/methodology/approach
Various forecasting models such as the Box–Jenkins-based auto-regressive integrated moving average model and machine learning-based algorithms such as long short-term memory (LSTM) networks, support vector regression (SVR), random forest regression, gradient boosting regression (GBR) and extreme GBR (XGBoost/XGBR) were proposed and applied (i.e. modeling, training, testing and predicting) at the retail stage for selected vegetables to forecast demand. The performance analysis (i.e. forecasting error analysis) was carried out to select the appropriate forecasting model at the retail stage for selected vegetables.
Findings
From the obtained results for a case environment, it was observed that the machine learning algorithms, namely LSTM and SVR, produced the better results in comparison with other different demand forecasting models.
Research limitations/implications
The results obtained from the case environment cannot be generalized. However, it may be used for forecasting of different agriculture produces at the retail stage, capturing their demand environment.
Practical implications
The implementation of LSTM and SVR for the case situation at the retail stage will reduce the forecast error, daily retail inventory and fresh produce wastage and will increase the daily revenue.
Originality/value
The demand forecasting model selection for agriculture produce at the retail stage on the basis of performance analysis is a unique study where both traditional and non-traditional models were analyzed and compared.
Details
Keywords
Akash K. Gupta, Rahul Yadav, Malay K. Das and Pradipta K. Panigrahi
This paper aims to present the implementation of a multi-layer radiation propagation model in simulations of multi-phase flow and heat transfer, for a dissociating methane hydrate…
Abstract
Purpose
This paper aims to present the implementation of a multi-layer radiation propagation model in simulations of multi-phase flow and heat transfer, for a dissociating methane hydrate reservoir subjected to microwave heating.
Design/methodology/approach
To model the induced heterogeneity due to dissociation of hydrates in the reservoir, a multiple homogeneous layer approach, used in food processes modelling, is suggested. The multi-layer model is incorporated in an in-house, multi-phase, multi-component hydrate dissociation simulator based on the finite volume method. The modified simulator is validated with standard experimental results in the literature and subsequently applied to a hydrate reservoir to study the effect of water content and sand dielectric nature on radiation propagation and hydrate dissociation.
Findings
The comparison of the multi-layer model with experimental results show a maximum difference in temperature estimation to be less than 2.5 K. For reservoir scale simulations, three homogeneous layers are observed to be sufficient to model the induced heterogeneity. There is a significant contribution of dielectric properties of sediments and water content of the reservoir in microwave radiation attenuation and overall hydrate dissociation. A high saturation reservoir may not always provide high gas recovery by dissociation of hydrates in the case of microwave heating.
Originality/value
The multi-layer approach to model microwave radiation propagation is introduced and tested for the first time in dissociating hydrate reservoirs. The multi-layer model provides better control over reservoir heterogeneity and interface conditions compared to existing homogeneous models.
Details
Keywords
I. Aliyu, S.M. Sapuan, E.S. Zainudin, M.Y.M. Zuhri and Y. Ridwan
The conflicting results on the corrosion characteristics of aluminium matrix composites reinforced with agrarian waste have stimulated an investigation on the hardness and…
Abstract
Purpose
The conflicting results on the corrosion characteristics of aluminium matrix composites reinforced with agrarian waste have stimulated an investigation on the hardness and corrosion rate of sugar palm fibre ash (SPFA) reinforced LM26 Al/alloy composite by varying the SPFA from 0 to 10 wt% in an interval of 2 wt%. This paper aims to discuss the aforementioned issue.
Design/methodology/approach
The composites were produced via stir-casting and the hardness was determined using a Vickers hardness testing machine, corrosion rate was examined through the weight loss method by immersion in 0.5, 1.0 and 1.5 M hydrochloric acid (HCl) at temperatures of 303, 318, and 333 K for the maximum duration of 120 h. The morphological study was conducted using a scanning electron microscope (SEM) on the samples before and after immersion in HCl.
Findings
The incorporation of SPFA improved the hardness of the alloy from 58.22 to 93.62 VH after 10 wt% addition. The corrosion rate increases with increased content of SPFA, the concentration of HCl and temperature. The least corrosion rate of 0.0272 mpy was observed for the LM26 Al alloy in 0.5 M after 24 h while the highest corrosion rate of 0.8511 mpy was recorded for LM26 Al/10 wt% SPFA in 1.5 M HCl acid after 120 h. The SEM image of corroded samples revealed an increased number of pits with increased SPFA content.
Research limitations/implications
The work is limited to SPFA up to 10 wt% as reinforcement in LM26 Al alloy, the use of HCl as corrosion medium, temperatures in the range of 303–333 K, and a weight loss method were used to evaluate the corrosion rate.
Originality/value
The corrosion rate was determined for LM26 Al/SPFA composites with various amounts of SPFA in 0.5, 1.0 and 1.5 M HCl at 303, 318 and 333 K and compared with the matrix alloy.