An integrated visual monitoring system to determine trajectory and duration on each vibrating motion of vibrator during concrete placed on construction site was introduced, which could graphically display vibrating status of fresh concrete. Defects on concrete placing process such as missed vibration, insufficient vibration, or excess vibration could be quantifiably assessed, and therefore, precise and suitable remedy could be offered timely. The system consisted of four functional parts, namely, vibrating trajectory spatial coordinate collected subsystem, vibrating duration-collected subsystem, data process subsystem, and real-time display and assesses subsystem of vibrating status. The principle of operation was explained in this article. Firstly, accurate signals combined spatial coordinates were achieved by dual-satellite systems, e.g., GPS (Global Position System) and GLONASS (Global Navigation Satellite System), with RTK (Real Time Kinematics) mode and, duration of each vibration from start to end was determined by electrode device, respectively. Secondly, the wireless signals were sent to the terminal computer via MCC (Mono-Chip Computer) integrated. Finally, the worked status of vibrator on terminal was displayed simultaneously supported by assessment programm on compacting concrete. Tests results from outdoor and application in-situ proved that the system could monitor the vibration process in real-time reliably and quantifiably while fresh concrete was placed, and an innovative informationaized method might be realized.

The vibration process applied to fresh concrete is an important link in the construction process, but the lack of effective monitoring and evaluation methods results in the quality of the vibration process being difficult to control and, therefore, the structural quality of the resulting concrete structures difficult to guarantee. In this paper, according to the sensitivity of internal vibrators to vibration acceleration changes under different vibration media, the vibration signals of vibrators in air, concrete mixtures, and reinforced concrete mixtures were collected experimentally. Based on a deep learning algorithm for load recognition of rotating machinery, a multi-scale convolution neural network combined with a self-attention feature fusion mechanism (SE-MCNN) was proposed for medium attribute recognition of concrete vibrators. The model can accurately classify and identify vibrator vibration signals under different working conditions with a recognition accuracy of up to 97%. According to the classification results of the model, the continuous working times of vibrators in different media can be further statistically divided, which provides a new method for accurate quantitative evaluation of the quality of the concrete vibration process.