Shin Hakjong, Kwak Younghoon, Huh Jung-Ho
Department of Architectural Engineering, University of Seoul, Seoul, South Korea.
Department of Architecture, University of Seoul, Seoul, South Korea.
Heliyon. 2023 Aug 12;9(8):e19093. doi: 10.1016/j.heliyon.2023.e19093. eCollection 2023 Aug.
Livestock facilities commonly generate NH, a hazardous substance that may also harm livestock. Therefore, monitoring of NH concentrations in livestock facilities is necessary to ensure proper control. However, NH is alkaline and toxic, causing corrosion inside detection sensors and making monitoring difficult. This study proposes a virtual sensor concept to complement the durability of NH physical sensors. The study also conducts a long-term performance validation of a data-driven NH concentration prediction model. Results indicate that the model's prediction performance declines sharply when the data generation pattern inside the livestock facility changes due to changes in outdoor conditions and facility operation. Furthermore, the prediction performance of the model differed depending on the training data period settings when updating the model. Hence, the model needs versioning and update management to respond to the data generation pattern in the livestock facility when operating the NH concentration virtual sensor. The virtual sensor is expected to enhance monitoring and reduce sensor management costs in livestock facilities.
畜牧设施通常会产生氨气（NH），这是一种有害物质，也可能对牲畜造成伤害。因此，监测畜牧设施中的氨气浓度对于确保适当控制是必要的。然而，氨气呈碱性且有毒，会导致检测传感器内部腐蚀，从而使监测变得困难。本研究提出了一种虚拟传感器概念，以补充氨气物理传感器的耐用性。该研究还对数据驱动的氨气浓度预测模型进行了长期性能验证。结果表明，当畜牧设施内的数据生成模式因室外条件和设施运行的变化而改变时，该模型的预测性能会急剧下降。此外，在更新模型时，模型的预测性能因训练数据期设置而异。因此，在运行氨气浓度虚拟传感器时，该模型需要进行版本控制和更新管理，以应对畜牧设施中的数据生成模式。预计该虚拟传感器将加强监测并降低畜牧设施中的传感器管理成本。
