Parameters Predictions of Paddy Grain Drying Based on Machine Learning
1
Citation
25
Reference
10
Related Paper
Citation Trend
Abstract:
In order to improve the drying efficiency and guarantee the grain quality after drying, this paper proposed to use artificial intelligence modelling to predict the grain quality indexes after drying. With air temperature, air relative humidity, initial moisture content, air velocity and tempering rate as control parameters, three models were established, and the prediction performance of these three models was tested. The three models were regression model, Back-propagation Neural Network (BPNN) and Deep Neural Network (DNN). The results showed that the machine learning techniques, in particular DNN had the best performance, especially for predicting germination rate ratio. The contribution of this paper is to demonstrate the ability of machine learning techniques in fitting grain drying characteristics with different control parameters. This paper proved the applicability of machine learning technology in grain drying field, and established the corresponding models.Keywords:
Grain drying
Tempering
Backpropagation
In this paper,five neural network models,such as back-propagation neural network(BPNN),radial basis neural network(RBFNN),generalized regression neural network(GRNN),cascade forward backpropagation neural network(CFNN) and Elman backpropagation neural network(ELMNN),have been evaluated in predicting protein secondary structures.The prediction accuracy of GRNN is better than the others.In addition,some affecting factors(the training sets and the parameters of network) are also discussed.
Backpropagation
Rprop
Cite
Citations (0)
The purpose of the study is to forecast the price of rice in the city of Denpasar in 2017 using backpropagation neural network method. Backpropagation neural network is a model of artificial neural network by finding the optimal weight value. Artificial neural networks are information processing systems that have certain performance characteristics similar to that of human neural networks. This analysis uses time series data of rice prices in the city of Denpasar from January 2001 until December 2016. The results of this research, concludes that the lowest rice price is predicted in July 2017 at Rp9791.5 while the highest rice price in April 2017 for Rp9839.4.
Backpropagation
Value (mathematics)
Cite
Citations (14)
This paper presents a method of next day peak load forecasting using an artificial neural network (ANN). The author combines the DSC search method (Davis, Swann, Campey search method) with the backpropagation learning algorithm (Bp) to reduce the training times and avoid converging at local minima as much as possible. The forecasting results by ANN is as good as human experts results and is better than the forecasting results by the regression model. The training times by the author's approach are less than that by the pure backpropagation in some cases.
Backpropagation
Maxima and minima
Cite
Citations (5)
In this study, multi-stage intermittent drying (MSID) of rough rice is considered based on stress cracking index (SCI), tempering index (TI), and total drying/tempering duration for Hashemi and Koohsar varieties experimentally and theoretically. The samples were dried at 60°C for 20, 40, and 60 min and tempered at 60°C for 40, 80, 120, 160, 200, and 240 min after each drying stage. Afterward, the completion of the tempering process was assessed using the TI along with analysis of moisture content kinetics by a simplified drying model. For both varieties, the SCI decreased significantly until continuing the tempering operation to certain durations and increased for longer drying durations in each drying stage. Considering the SCI and the total drying/tempering duration, the tempering durations of 200 and 160 min after 40 min drying in each stage were determined as the best performed conditions for MSID of Hashemi and Koohsar varieties, respectively. The results achieved by the TI were in conformity with those obtained by the mathematical model. It was concluded that the TI and simulation of surface moisture content on a kernel could be applied for estimating the time required for supplementation of the tempering process to eliminate moisture content gradients created inside the kernels during the drying process.
Tempering
Grain drying
Cite
Citations (44)
Parboiled paddy dried in the shade had excelle'Dt milling quality, but rapid
drying with hot air (40°_80°C.) or in the sun gave high breakage. The damage
started as the moisure content reached 15% and increased sharply with
further drying. Milling at different time intervals after drying demonstrated
further that damage to the paddy occurred gradually only subsequent to its removal
from the dryer. From this it was found that keeping the paddy hot after
drying (conditioning) for about 2 hr. prevented the milling breakage. Dryinr
in two stages with a tempering (2 hr. if hot, 8 hr. if at room temperature) jus
before attainment of the critical moisture content (at 15.5-16,5%) also pre
served milling quality, Tempering at higber moisture contents was less beneficial,
and multiple tempering gave no additional benefit Drying in two passes
witb a tempering in the moisture range of 15 to 19%, followed by hot-conditioning
after tbe final drying; was convenient in practice and satisfactory; a
drying temperature up to 80~C. could be used. After parboiled paddy was
dried in this way, milling breakage would not exceed 1-2%,
Tempering
Breakage
Grain drying
Cite
Citations (54)
Tempering
Grain drying
Cite
Citations (66)
The authors introduce a novel patient severity measurement model using neural networks. A three layer, fully connected backpropagation neural network was used in the pilot experiment. The results are promising and demonstrate that the backpropagation neural network technique is capable of assessing the severity value by learning from raw data. The neural network is easy to improve and of relatively low cost. It saves the expert's valuable time used in assigning numerical values to variables.< >
Backpropagation
Value (mathematics)
Cite
Citations (0)
This article deals with grains' drying features and techniques.Experiments were conducted to determine the technical parameters of the drying system.Experimental analysis was made in terms of drying temperature,grain thickness,drying periods,hot wind velocity and tempering time.The findings show that when the moisture is at a low level at the initial stage,the drying time has a large effect on the reduction in moisture while the wind temperature has little effect.With the rise of initial moisture,the influence of relatively hot wind on the reduction of moisture rises while the wind temperature and tempering time have little effect.The tempering time plays a subsidiary role in the grain drying and it can improve the drying quality.
Tempering
Grain drying
Cite
Citations (0)
Artificial Neural Network (Artificial Neural Network) is an information processing paradigm inspired by the workings of biological nervous systems, such as the performance of the brain, which processes information. Toko Anugerah Jaya Pancing 99 faces challenges in predicting product sales that fluctuate according to customer demand, and external factors can also affect sales of their products. To determine store sales predictions using the backpropagation method. From the research results with data training experiments it was found that the iterations process stopped when the epoch reached 6, time 0.00.01, performance 0.317, Gradient 0.359, and Validation Checks 6. Keywords: Prediction, Backpropagation, Neural Networks, Sales
Backpropagation
Cite
Citations (0)
A true understanding of rice kernel fissuring and breakage, as a result of drying and tempering, must includeboth engineering and cereal science principles. Particular emphasis must be placed on the change of states of starchoccurring at the glass transition temperature (T g ). This transition from a glassy to rubbery state, or vice versa, has beenidentified to play an important role in rice fissuring and breakage. A hypothesis has been developed explaining rice kernelfissuring during drying and tempering. The objectives of this research were to determine the effect of the T g during ricedrying and tempering on milling quality. Additionally, the minimum tempering time required for various dryingconditions, to optimize milling quality, was determined. Rice was dried under three conditions, two with a drying airtemperature above T g and one below T g , for four durations and then tempered for 0 to 240 min. The experimentalprocedure was designed to directly test the T g hypothesis by cooling rice to a temperature below the T g after eachtempering duration. Results for both medium-grain rice and long-grain rice at 19.6 to 23.7% harvest moisture content(MC) * show that 5 to 6 percentage points MC can be removed per drying pass without damaging the rice kernel, as longas sufficient tempering is allowed. Required tempering durations were shorter for long-grain rice as compared tomedium-grain.
Tempering
Breakage
Grain drying
Cite
Citations (192)