Development of a wireless smart sensor system and case study on lifting risk assessment

Abstract

With the widespread adoption of Industry 4.0 and smart manufacturing concepts across industries, sensor development, system integration, and data analysis have become important aspects of efficient manufacturing operations. In addition to monitoring the performance of machines, significant importance is given to human condition monitoring in factories, using body-worn sensors to ensure the well-being of workers and for injury prevention. This research presents the development of a body-worn sensor system capable of sampling acceleration and rotation data up to 400 Hz and wirelessly transmitting the data over Bluetooth Low Energy (BLE). Further, the communication protocols for data acquisition, data communication within the device, Real Time Operating System (RTOS) programming, and multi-threading are described. This system is designed in such a way that multiple devices can be connected to the Data acquisition (DAQ) system simultaneously, and data is collected from the sensors in a synchronized manner. This information is valuable for the wider adoption of sensor systems for human condition monitoring in industry. Lastly, to test the system’s capabilities, a case study of lifting risk assessment is presented, where data collected from the accelerometer and gyroscope are used to determine a relative estimate of the physical stress associated with a manual lifting task by using different machine learning (ML) algorithms. The case study highlights how sensor placement, feature extraction, and sensor types influence machine learning models. As the sensor system can perform computations on the edge, a framework to carry out real-time lifting risk assessment using lightweight algorithms and the most important data features is proposed.