Scholarlink

A customized data acquisition (DAq) device is presented for Industrial Internet of Things (IIoT) applications. Referred to as 2S Tools Flex DAq, the multivariable wireless DAq supports advanced connectivity options such as LoRaWAN, LTE, and ZigBee, accommodating a wide range of sensors with low power consumption. To demonstrate the potential of integrating Artificial Intelligence (AI) into a system involving sensors, the 2S Tools Flex DAq, and the cloud, we applied Long Short-Term Memory (LSTM) neural networks for predictive analytics for water quality parameters collected by the device. Specifically, we forecast pH, water level, and temperature using real-time data collected by the 2S Tools Flex DAq in a remote monitoring system. The LSTM model achieved high accuracy in predicting pH and temperature, with R \(^{2}\) values of 0.97 and 0.99, respectively. These experimental results highlight the feasibility of embedding AI capabilities into the DAq device we built for enhanced predictive maintenance and process optimization in IIoT settings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Developing a LoRaWAN-Based Data Acquisition Device Empowered by AI

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Menno J. Faber,
  • Helder R. de O. Rocha,
  • Marcelo E. V. Segatto,
  • Jair A. Lima Silva

摘要

A customized data acquisition (DAq) device is presented for Industrial Internet of Things (IIoT) applications. Referred to as 2S Tools Flex DAq, the multivariable wireless DAq supports advanced connectivity options such as LoRaWAN, LTE, and ZigBee, accommodating a wide range of sensors with low power consumption. To demonstrate the potential of integrating Artificial Intelligence (AI) into a system involving sensors, the 2S Tools Flex DAq, and the cloud, we applied Long Short-Term Memory (LSTM) neural networks for predictive analytics for water quality parameters collected by the device. Specifically, we forecast pH, water level, and temperature using real-time data collected by the 2S Tools Flex DAq in a remote monitoring system. The LSTM model achieved high accuracy in predicting pH and temperature, with R \(^{2}\) values of 0.97 and 0.99, respectively. These experimental results highlight the feasibility of embedding AI capabilities into the DAq device we built for enhanced predictive maintenance and process optimization in IIoT settings.