Mission of the Agrimechatronics Research Group
Embedded Files
Our Current Research Focuses on Four Areas
IoT and WSN development for honey bees
IoT and WSN development for honey bees
Supported by: USDA-ARS
The Honeybee Sensing Project is an innovative initiative that combines biology, technology, and environmental science to monitor and protect honeybee colonies, which are critical for pollination, biodiversity, and agriculture. By utilizing advanced sensors, the project tracks hive conditions such as temperature, humidity, CO2 levels, and stress indicators, providing real-time insights into colony health. It also examines bee behavior and environmental factors to identify biotic and abiotic stressors impacting their well-being. Cutting-edge technologies like GPS, RFID, wireless communication, machine learning, and data analytics play a pivotal role in analyzing data and identifying patterns.Honey bees contribute significantly to agriculture, with 2.5 million colonies pollinating over $15 billion worth of crops annually in the USA, according to USDA statistics. However, transporting approximately 600,000 beehives from North Dakota to the West Coast for pollination exposes them to stress from vibrations, noise, and altitude changes, leading to a 5–10% mortality rate and reduced productivity for days after the journey. To address these challenges, the project developed a wireless sensor network using NDIR SCD30 sensors, Adafruit I2S MEMS microphones, and Particle Argon™ microprocessors for Wi-Fi communication. These components are integrated into a custom-designed two-layer Printed Circuit Board (PCB) housed in a 3D-printed enclosure. Preliminary data from the system demonstrates its reliability and potential to revolutionize bee health monitoring, enhancing beekeeping practices and ensuring pollinator sustainability.
Autonomous UGV
Autonomous UGV
Supported by: USDA-NIFA-AFRI
Autonomous all-terrain-vehicles (ATVs) in agriculture merge the versatility of traditional unmanned vehicles with advanced autonomous technology, offering a range of benefits including self-navigation, task automation, accuracy, and environmental sensing. These vehicles can perform various farming operations efficiently, function continuously, and provide valuable data for precision farming. Benefits include reduced labor costs, increased productivity, enhanced safety, and data-driven insights. However, challenges such as the initial investment, the need for technical know-how, and regulatory concerns exist. Despite these challenges, autonomous ATVs represent a promising advancement in agricultural technology, poised to improve farming practices and productivity.
IoT and WSN development for Sugarbeet storage
IoT and WSN development for Sugarbeet storage
Supported by: USDA-ARS
Sugar beet sensing technology is crucial for reducing the spoilage of sugar beet piles during storage. It involves using advanced sensors to monitor gas emissions, temperature, humidity, pH, and sugar content within beet piles. This technology enables early detection of spoilage signs, allowing for timely interventions to adjust storage conditions or remove affected beets. By optimizing storage conditions and facilitating data-driven decision-making, this approach significantly enhances the management of sugar beet storage. Future advancements may include the integration of a wireless sensor network, the internet of things, and AI data analytics, further improving spoilage prevention, real-time condition adjustments, and ensuring the traceability and quality of the crop from field to processing facility.
AI Machine Learning applications for CEA
AI Machine Learning applications for CEA
Supported by: AES
Automation: The project will focus on designing, constructing, and testing an automatic control system for drip irrigation in the lettuce production system. A modified soil potential sensor will be used to automatically control the irrigation and nutrient delivery to conserve water and nutrients while maintaining plant health. The system will be tested and compared with measured water quantity and quality data, as well as imagery data. Machine learning algorithms will be applied to model and evaluate the system's performance. This objective will be led by Dr. Eshkabilov and assisted by Drs. Jia and Lee.
Water Management: Water and nutrient balances will be quantified to enhance water conservation in CEA production. This objective will be led by Dr. Jia and assisted by Drs. Eshkabilov and Lee.
Energy Efficiency: In this project, the team will evaluate using a newly developed innovative solar module for a greenhouse so that without additional energy supply, the system can maximize solar radiation, generate electricity, and increase crop yield. This objective will be led by Dr. Feng and assisted by all others. In addition, the NDSU team will conduct outreach activities to extend the CEA knowledge to the public, educational activities to train graduate and undergraduate students through classroom instructions, course and senior design projects, e.g., ABEN 286, ABEN 452, ABEN 482; ABEN 486/487, PLSC 210, PLSC 368, and PLSC 422.
Questions?
Questions?
Contact sulaymon.eshkabilov@ndsu.edu to get more information on the project
Page updated
Report abuse