Modeling of Potato Slice Drying Process in a Microwave Dryer using Artificial Neural Network and Machine Vision
Journal Title: Journal of Agricultural Machinery - Year 2021, Vol 11, Issue 2
Abstract
IntroductionMicrowave drying compared to conventional hot air drying has many benefits to apply in food drying processes such as volumetric heating, high thermal efficiency, shorter drying time and improved product quality. In conventional microwave drying method, a fixed microwave power was used during the drying process. However, the water of the product evaporated and mass of product decreased over the time that resulted in microwave power density (MPD) increasing during the drying process. Increasing the power density, especially at the end of the process, sharply increased the product temperature. High temperature of products led to the deterioration of the product quality. Most research used variable microwave power program for preventing the risk of overheating and charring of product. The evaporation of the water causes the shrinkage of product. Therefore, many studies have used machine vision for measuring the shrinkage and this technology has been used in modeling and predicting the MC.Materials and MethodsThe fresh potato samples (Solanum tuberosum cv. Santana) with 83% (w.b.) of initial MC were sliced into the chips of 5mm thickness. The developed drying systems consisted of microwave oven, lighting unit and imaging unit, temperature sensor, microwave power adjusting unit and a data acquisition unit (DAQ). A LabVIEW (V17.6, 2017) program was developed to integrate all measurements and adjusting the microwave power during the drying process. In this study, two sets of experiment with different aims have done. The first set of experiments was used for calculating the shrinkage by developed image processing algorithm and MC by offline mass measurement and then data sets were used to investigate the artificial neural networks (ANNs). The second set was used for evaluating the reliability of investigating models. The experiments, in the first set, were done with 8, 4 and 2.67 W g-1. In the variable mode, the power varied in two/three steps with respect to the MC of samples during the drying process. Second set of experiments was done in two variable and constant power modes with 5 and 3 W g-1. An image processing algorithm was developed to measure the shrinkage of potato slice during the drying process. In this study the feed forward ANN with back propagation algorithm was used. Two structures of ANN were used for modeling of MC. In the first model time and power density and the second model shrinkage and power density were used as input. Also moisture ratio was used as an output parameter in two models.Results and DiscussionThe obtained results indicated that for the first model the ANN with 2-3-1 structure had better results than others structures. This structure had 0.0713, 0.0337 and 0.0640 of RMSE and 0.9764, 0.9973 and 0.9800 of R for train, validation and test, respectively. For the second model, the 2-2-2-1 structure of ANN with 0.0780, 0.0816 and 0.0908 of RMSE and 0.9598, 0.9799 and 0.9746 of R for train, validation and test, respectively had better results than other structures. The evaluation of these models with a second data set showed that the second model with shrinkage and power density as input with 0.067 of RMSE and 0.994 of R had better results than the first model with 0.173 of RMSE and 0.961 of R. These consequences expressed that the second model had higher reliability for prediction of MC based on shrinkage and power density during drying process.ConclusionIn this study, a microwave dryer was developed with a real-time image recording system and a microwave power level program during the drying process. Two ANN models were used for modeling of drying kinetics of the potato slices. Also image processing algorithm was investigated by measuring the shrinkage of potato slice during the drying process. The outcomes revealed that shrinkage as input in the ANN had great effect on MC prediction during the drying process.
Authors and Affiliations
S. Rezaei,N. Behroozi-Khazaei,H. Darvishi,
Keywords
Related Articles
- EP ID EP718011
- DOI https://doi.org/10.22067/jam.v11i2.78709
- Views 33
- Downloads 0
Modeling of Soil Compaction Beneath the Tractor Tire using Multilayer Perceptron Neural Networks
Introduction Soil compaction is one of the most destructive effects of machine traffic. Compaction increases soil mechanical strength and reduces its porosity, plant rooting and ultimately the yield. Nowadays, agricultur...
Evaluating the Mechanical Properties of Tomato Based on Electrical Conductivity
Evaluation of mechanical and electrical properties of agricultural products plays an important role in equipment design and optimizing post-harvest operations. Among the crops, tomato and its products are the major proce...
Modeling Soil Pressure-Sinkage Characteristic as Affected by Sinkage rate using Deep Learning Optimized by Grey Wolf Algorithm
Due to the numerous variables that may influence the soil-machine interaction systems, predicting the mechanical response of soil interacting with off-road traction equipment is challenging. In this study, deep neural ne...
Predicting Whole-body Vibration-based on Linear Regression Models and Determining Permissible Exposure Time of Tractor Operator
IntroductionThe permissible exposure time to vibration for the operator is one of the key factors in maintaining the operator's health while optimizing machinery and equipment. The tractor studied was the ITM475, manufac...
Modeling the Effective Parameters on Accuracy of Soil Electrical Conductivity Measurement Systems Using RBF Neural Network
Introduction Presently, the loss of ground water levels and the increase in dissolved salts have given importance to the determination of salinity and the management of their variations in irrigated farms. Soil electrica...