Corn Stalk Characteristics Effect on Performance of Baler Machine Cutting System

( Anil Bhujel ),( Frank Gyan Okyere ),( Jayanta Kumar Basak ),( Elanchezhian Arulmozhi ),( Jihoon Park ),( Fawad Khan ),( Yongjin Lee ),( Deoghyon Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

Corn stalks used as a biomass may have some physical characteristics that may influence the working efficiency of the cutting machine used for reducing the size. This may as well affect the overall cost of the biomass production. For instance, the cutting force required to cut the biomass to little sizes may be affected by the moisture content and circumferential size of the biomass. The aim of this research is to analyze the characteristics (physical and mechanical) of corn stalk effect on the working efficiency of a Baler cutting machine. The moisture content, % (wet base) and the mechanical properties of the corn stalk were determined using a weighing machine and dry oven. The mechanical strength (stress and strain) required to cut or break the corn stalk was determined using an EZ 632 UMT machine. The mechanical strength and moisture content of the corn stalk were marked against the cutting depth to establish the relationship between these variables. Six different moisture content (23.4%, 36.8%, 39.3%, 45.0%, 52.1% and 70.3%) were used. A Baler machine with a cutting system oriented at 45° angle to the horizontal was used to cut the corn stalks at cross- section perpendicular to the cutters. The machine was operated at three rotor speeds; 1200 rpm, 1773 rpm and 2485 rpm. The tensional strength were higher than the compressional strength in all moisture content except in the 23.4% moisture content. The highest cutting length was achieved in the high moisture content above 60%. The 70.29% moisture content corn stalks had the highest tensional strength (334.6 N) with 23.4% moisture content recording the lowest (13.8 N). The compressional strength varied with increasing moisture content. It was observed that the tensional force was highly correlated to the moisture content with correlation coefficient r = 0.98 and R² value of 0.96.

Sensor Systems for Greenhouse Microclimate Monitoring and Control: a Review

Bhujel Anil,Basak Jayanta Kumar,Khan Fawad,Arulmozhi Elanchezhian,Jaihuni Mustafa,Sihalath Thavisack,이덕현,박재성,김현태 한국농업기계학회 2020 바이오시스템공학 Vol.45 No.4

Purpose Sensors are the primary component of a monitoring and control system. Effective monitoring and control of the microclimatic environment in a greenhouse is the key necessity for protecting crops from adverse environments. Moreover,the greenhouse microclimate is influenced by various factors. In the large-scale greenhouse facilities, several sensors and actuators are needed to control the system. Manual monitoring and control of such a large and complex system is labor-intensive and impractical. Therefore, an automatic monitoring and control system in the greenhouse becomes indispensable. In addition, microclimatic parameters such as temperature, humidity, and solar irradiance in the greenhouse are non-linearly interlinked, thereby forming a non-linear multivariate system. Thus, an appropriately designed sensor system is needed for monitoring and controlling the greenhouse microclimate. Methods Research articles on greenhouse microclimate monitoring and control published in the last 6 years were considered. The sensor devices and technologies applied to control particular environmental parameters in the greenhouse and their key achievements were systematically reviewed. In addition, different approaches to determine the optimum number of sensors and their placement inside the greenhouse were investigated. Results It was found that spatially installed sensor devices above the plant height reflect the actual information of the environment getting by plant. Furthermore, both hardware and software-based sensing techniques control the greenhouse microclimate optimally. The proper positioning of sensors and their protection from harsh environmental factors is also essential. Conclusions It can be concluded that modern sensor devices and systems are driving the greenhouse monitoring and control system toward an intelligent, real-time, remotely accessible, and fully automatic system.

Design of a Programmable Greenhouse Environmental Data Collection System Using Raspberry Pi

( Anil Bhujel ),( Elanchezhian Arulmozhi ),( Byeong Eun Moon ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

Recently, greenhouse farming is gaining popularity because of the controlled environments due to which the quality and quantity production of crops improves significantly. To maintain a suitable environment for the plant, continuous monitoring of greenhouse inside environmental conditions is indispensable. However, manual monitoring of such parameters is impractical. A sensor-based data collection system is inherently implemented in the greenhouse monitoring system. In this experiment, a Raspberry Pi-based programmable data collection system was designed to collect the greenhouse indoor temperature and humidity using two DHT22 sensors. The DHT22 sensors spatially hung on two locations inside a greenhouse were connected to a Raspberry Pi via cables. A Python script is run in the Raspberry Pi to acquire the sensing digital data from the sensors and logged it into the micro SD card. Raspberry Pi is a miniature version of a computer, which offers a high-level language platform. Therefore, a user-interactive program written in Python language was implemented that allows configuring parameters like sensor numbers and sensing intervals in every time while restarting the program. The system was tested by installing it in a greenhouse with a user-defined logging interval. It concludes that a flexible data collection system can be designed by using Raspberry Pi.

Effect of Moisture Contents in the Mechanical Strength of Corn Stalk

( Anil Bhujel ),( Jayanta Kumar Basak ),( Fawad Khan ),( Byeong Eun Moon ),( Deog Hyun Lee ),( Jae Sung Park ),( Hyeon Tae Kim ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.2

Corn stalks used as a biomass have some physical characteristics that may influence the working efficiency of the cutting machine used for reducing the size. This may as well affect the over all cost of the biomass production. For instance, the cutting force required to cut the biomass to shorten the sizes may be affected by the moisture content and circumferential size of the biomass as the moisture content affect the mechanical strength of corn stalk. The aim of this research is to analyze the effects of moisture content of corn stalk on its characteristics (physical and mechanical). The moisture content, % (wet base) and the mechanical properties of the corn stalk were determined using a weighing machine and dry oven. The mechanical strength (stress and strain) required to cut or break the corn stalk was determined using an EZ 632 UMT machine. The mechanical strength and moisture content of the corn stalk were marked against the cutting depth to establish the relationship between these variables. Six different moisture content (23.4%, 36.8%, 39.3%, 45.0%, 52.1% and 70.3%) were used and a Baler machine with a cutting system oriented at 45° angle to the horizontal was used to make a piece of corn stalk. The tensional strength were higher than the compressional strength in all moisture content except in the 23.4% moisture content. The tensional strength is increasing with the increase of moisture content, where as, the compression strength did not follow the same pattern of tensional strength. The 70.29% moisture content corn stalks had the highest tensional strength (489N) with 23.4% moisture content recording the lowest (13.8 N). The compressional strength varied with increasing moisture content. It was observed that the tensional force was highly correlated to the moisture content with correlation coefficient r = 0.98 and R2 value of 0.96.

Semantic Segmentation of Strawberry Gray Mold Disease using Deep UNet

( Anil Bhujel ),( Jayanta Kumar Basak ),( Elanchezhian Arulmozhi ),( Thavisack Sihalath ),( Fawad Khan ),( Byeong Eun Moon ),( Mustafa Jaihuni ),( Deog Hyun Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.1

Gray mold is a common disease in strawberry, causing a devastating loss. Therefore, it is very important to identify the gray mold disease as early as possible and check the severity of the disease. The gray mold disease on strawberry plants was produced experimentally in a greenhouse located at Gyeongsang National University. The fungus “Botrytis cinerea” is the causal agent of gray mold disease, which was inoculated in the strawberry plants with three different concentrations (103, 105, and 107 MPN per 50 ml). The images of strawberry leaves infected by the disease were captured by the smartphone and pre-processed. In image pre-processing, removed the background of the image, created a mask of the lesion area of each image, and labeled them. A pair of the original image and its annotated mask were manually prepared and split into training and testing sets. A deep learning convolutional neural network-based UNet model was designed and trained by 45 sets of original and annotated pairs of images using heavy data augmentation. The model was trained for 10 epochs with 1000 steps per epoch, and the training accuracy achieved was 98.92%. Then the model was tested by 10 sets of original and annotated images, which gave the highest pixel accuracy of 98.21%. It was also tested by other segmentation metrics like the intersection of union (iu) and dice accuracy. The model provided the highest iu of 87.91% and dice accuracy of 92.91%. From the results, it can be concluded that the deep learning UNet can successfully segment the gray mold disease that occurred in strawberry, helping to identify the disease severity.

Automatic Environmental Sensor Data Collection System Using Raspberry Pi

( Bhola Paudel ),( Anil Bhujel ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.2

Precision agriculture is gaining its popularity because of the controlled environments which significantly improves the quality and quantity production of crops. To maintain a suitable environment for the plant, continuous monitoring of greenhouse inside environmental conditions is indispensable. However, manual monitoring of such parameters is impractical. A sensor-based data collection system is inherently implemented in the greenhouse monitoring system. In this experiment, a Raspberry Pi-based programmable data collection system was designed to collect the greenhouse indoor temperature, humidity and CO2 using two DHT22 sensors. The DHT22 and MH-Z19 sensors spatially hung on two locations inside a greenhouse were connected to a Raspberry Pi via cables. A Python script is run in the Raspberry Pi to acquire the sensing digital data from the sensors and logged it into the micro SD card. Raspberry Pi is a miniature version of a computer, which offers a high-level language platform. Therefore, a user-interactive program written in Python language was implemented that allows configuring parameters like sensor numbers and sensing intervals in every time while restarting the program. The system was tested by installing it in a greenhouse with a user-defined logging interval. It concludes that a flexible data collection system can be designed by using Raspberry Pi.

Prediction of overlapping leaf area of ice plants using digital image processing technique

( Bolappa Gamage Kaushalya Madhavi ),( Anil Bhujel ),( Jihoon Park ),( Na Eun Kim ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.2

Non-destructive, fast, and accurate leaf area estimation is critical in many plant physiological and ecological experiments. In modern agriculture, ubiquitous digital cameras and scanners are primarily replaced the traditional leaf area measurements. Thus, measuring the leaflet’s dimension is integral in analysing plant photosynthesis and growth. Moreover, leaf dimension assessment with image processing is widely used for presenting. This investigation proposed a new image segmentation algorithm to classify the ice plant (Mesembryanthemum crystallinum L.) canopy image with a threshold segmentation technique by grey colour model and calculating the degree of green colour in the HSV (hue saturation value) model. Notably, the segmentation technique is used to separate suitable surfaces from a defective noisy background. Eventually, the canopy area was measured by pixel number statistics. Furthermore, this paper proposed total leaf area estimation by a computer coordinating area curvimeter and lastly evaluated the overlapping percentage using the total leaf area and canopy area measurements. To verify the effectiveness of the proposed algorithm, a segmentation experiment was performed on 24 images of ice plants. The obtained results show the algorithm’s accuracy is above 90%, which is confirmed by comparing the results of the proposed algorithm with the curvimeter leaf area method. This system gives a vital contribution to crop evolution by computational tools, making easier the monitoring work.

Assessment of Combined Trichoderma-Enriched Biofertilizer and Nutrients Solutions on the Growth and Yield of Strawberry Plants

Khan Fawad,김나은,Bhujel Anil,Jaihuni Mustafa,이덕현,Basak Jayanta Kumar,김현태 한국농업기계학회 2021 바이오시스템공학 Vol.46 No.3

Purpose The use of biofertilizers not only decreases the level of a nutrient solution but also improves the growth of plants and reduces the risk of environmental pollution. In this study, the impact of Trichoderma-enriched biofertilizer (poultry manure composted and Trichoderma harzianum YC459 (TEB), standard nutrient solution (SNS), and the combination of both (TEB + SNS) were utilized to evaluate the growth, yield, and nutritional quality of strawberry plants (Fragaria × ananassa Duch.). Method The strawberry plants were planted in four treatments—control soil (CS, without TEB and SNS), T1 (SNS), T2 (TEB), and T3 (50% SNS + 50% TEB) — in a controlled greenhouse. Several scientific instruments such as a ubiquitous broadcast network (UBN) farm link control management system, sensor nodes, nutrient controller, composting reactor, digital refractor meter, dry oven, digital balance, and different chemical techniques were used for a particular purpose. Results Consequently, analysis of variance was performed, and a significant increase in yield values (123.07–145.83% and 88.46–100.00%) was recorded over control by T3 and T1, respectively. Also, the vegetative growth parameters, total soluble solids, ascorbic acid, and total sugar content were observed higher in T3. Conclusion It was observed that the combined use of Trichoderma-enriched biofertilizer with the standard nutrient solution could improve the growth, yield, and quality of the strawberry plant.

Performance Analysis of Different Optimizers, Batch Sizes, and Epochs on Convolutional Neural Network for Image Classification

Thavisack Sihalath,Jayanta Kumar Basak,Anil Bhujel,Elanchezhian Arulmozhi,Byeong-Eun Moon,Na-Eun Kim,Doeg-Hyun Lee,Hyeon-Tae Kim 경상대학교 농업생명과학연구원 2021 농업생명과학연구 Vol.55 No.2

The important thing in the field of deep learning is to find out the appropriate hyper-parameter for image classification. In this study, the main objective is to investigate the performance of various hyper-parameters in a convolutional neural network model based on the image classification problem. The dataset was obtained from the Kaggle dataset. The experiment was conducted through different hyper-parameters. For this proposal, Stochastic Gradient Descent without momentum (SGD), Adaptive Moment Estimation (Adam), Adagrad, Adamax optimizer, and the number of batch sizes (16, 32, 64, 120), and the number of epochs (50, 100, 150) were considered as hyper-parameters to determine the losses and accuracy of a model. In addition, Binary Cross-entropy Loss Function (BCLF) was used for evaluating the performance of a model. In this study, the VGG16 convolutional neural network was used for image classification. Empirical results demonstrated that a model had minimum losses obtain by Adagrad optimizer in the case of 16 batch sizes and 50 epochs. In addition, the SGD with a 32 batch sizes and 150 epochs and the Adam with a 64 batch sizes and 50 epochs had the best performance based on the loss value during the training process. Interestingly, the accuracy was higher while performing the Adagrad and Adamax optimizer with a 120 batch sizes and 150 epochs. In this study, the Adagrad optimizer with a 120 batch sizes and 150 epochs performed slightly better among those optimizers. In addition, an increasing number of epochs can improve the performance of accuracy. It can help to create a broader scope for further experiments on several datasets to perceive the suitable hyper-parameters for the convolutional neural network. Dataset: https://www.kaggle.com/c/dogs-vs-cats/data

Analysis of Blade Oblique Angles Effect on Cutting Properties of Corn Stalks

( Frank Gyan Okyere ),( Jayanta Kumar Basak ),( Anil Bhujel ),( Fawad Khan ),( Dougheon Lee ),( Junbeon Cho ),( Hyeon Tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.2

Biomass is produced by green plants that converts sunlight into plant materials through phot osysnthesis and it includes land- and - water based vegetation as well as all organic waste. C orn stover is a good source of biomass for feedstock, bioproducts. On a large scale, commerci al large square or round balers for harvesting corn stalks which are made of the cut and pick up, pre- compression chamber, and bale chamber. The cut and pick up system is critical in d etermining the size cut, the length of stalk in soil after cut and eventually the volume of bale produced. Hence knowledge of cutting blades size, its geometric design and other features re lative to the cutting material is required. The aim of this research is to analyze the effect of bl ade oblique angles on the cutting properties of corn stalks of various moisture content and siz es using a prototype cutting system of a baler machine. Three oblique angle cutting blades- 30 o,45o and 60o, three rotor speeds (1100rpm, 1750rpm and 2230rpm) and three ground speeds (2.5km/h, 5.0km/h and 7.5km/h) were used as the machine variable access its impact on the l ength of cut and length in soil using four different sets of corn stalk moisture content -70.05 ± 2.42%, 48.12± 1.19%, 28.14 ± 2.02% and 18.14 ± 2.22%. Also the effect of the oblique angl es and corn stalk physical properties (size) relative to their mechanical cutting properties (spec ific energy, peak load etc) were also analyzed. The optimum oblique angle of choppers requir ement to achieve a low length of cut, cut in soil, energy requirement et al was 45o followed by 60o. The ultimate shear strength was insignificantly affected by change in oblique angle, siz e and moisture content of corn stalk.