Inquiry into Wavelet Packet Denoising, Real-Time Optimization and Visualization for AI-Enabled Smart Software in Construction Engineering Deformation Monitoring

In construction engineering, deformation monitoring is crucial for ensuring structural safety. Traditional methods have limitations in data processing and real-time presentation. This paper explores an AI-enabled smart software for deformation monitoring in construction engineering, which applies wavelet packet denoising technology to optimize real-time performance and achieve visualization. Leveraging AI’s powerful computing capability, the software can quickly process complex deformation monitoring data. The improved wavelet packet threshold method can effectively remove noise and enhance data accuracy. The denoised and optimized data is intuitively presented through innovative visualization designs, helping workers grasp deformation conditions in a timely manner. Experimental studies show that: (1) The root mean square error of the improved wavelet packet threshold function is about a quarter less than that of the hard threshold, and the signal-to-noise ratio is about 1.11 times higher. (2) Compared with the soft threshold, the root mean square error of the improved function is about one-tenth less, and the signal-to-noise ratio is about 1.25 times higher. Among the three selected denoising methods, the improved wavelet packet threshold function has the smallest root mean square error and the largest signal-to-noise ratio, confirming that it can significantly improve the efficiency and accuracy of deformation monitoring, providing strong support for the safety of construction projects.