Artificial stingless bee hive design utilizing embedded fuzzy-IoT based determining hive condition and honey volume

Stingless bee beekeeping presents both opportunities and challenges, with hive vulnerabilities and surrounding temperature posing significant threats to colony growth and honey production. This research addresses these challenges by developing an innovative artificial hive design incorporating IoT technology and fuzzy logic to optimize hive conditions and honey production. The research begins with the design of artificial hives on mitigating these threats through. Utilizing materials like Polyethylene Terephthalate Glycol (PET-G), 3D-printed components, and Polyvinyl Chloride (PVC), the artificial hive aims to provide a safe and conducive environment for stingless bee colonies. A total of five insulation techniques were implemented at artificial hives to achieve the maximum temperature ever recorded, which was 39.4°C. The clay-insulated artificial colonies exhibited the smallest standard deviation of humidity, measuring 0.46. However, given the greater relationship between temperature and bee survival, the bubble aluminium artificial hive emerges as the more favourable choice, due to its highest average temperature differential of 6.4°C between the interior and exterior. Furthermore, the integration of IoT (Cayenne myDevice and ThingSpeak) systems facilitate real-time monitoring of hive parameters such as temperature, humidity, and weight of honey compartment. Validation of sensors ensures accuracy and reliability in data collection, while heat insulation experiments aim to maintain optimal hive conditions, crucial for colony health and honey production. The implementation of fuzzy logic enables the collected data to forecast hive conditions and honey volumes. Following the successful execution of Embedded Fuzzy Logic on NodeMCU ESP8266, a comparison was made with Fuzzy Logic using MATLAB. Standard deviations for hive condition and honey volume are both less than 0.5, and average percentage errors are below 1%. As a result, the system exhibits minimal dispersion and it’s good to use in this study. In order to assess the effectiveness of the fuzzy logic system, which utilised two outputs (Hive Condition and Honey Volume) and three inputs (Weight, Temperature, and Humidity), ANOVA tests and box plots were implemented. Significant variations in internal humidity can be observed in relation to both the condition of the hive and the volume of honey. On the contrary, compartment temperature varies substantially only with honey volume, while internal temperature varies substantially only with hive condition. Overall, this research contributes to the advancement of stingless beekeeping practices by providing beekeepers with tools and technologies to enhance hive management and optimize honey production. By leveraging IoT and fuzzy logic, beekeepers can make informed decisions and maximize honey yields, ultimately ensuring the sustainability and growth of stingless bee colonies.