[Purposes] To address the issues of outlier detection and environmental noise interference in bridge monitoring signals, this study proposes an outlier detection algorithm based on a least squares-improved boxplot and a denoising method combining fast ensemble empirical mode decomposition (FEEMD) with wavelet thresholding. [Methods] First, an improved boxplot algorithm was employed to identify and replace outliers. Subsequently, the FEEMD method was utilized to decompose the bridge monitoring signals after outlier processing. The variance contribution rates of the decomposed components were calculated, and the modal components with small variance contribution rates were removed. The remaining signals were subjected to wavelet thresholding. Finally, the signals were reconstructed to obtain the denoised signals. [Findings] Analysis of both simulated and actual measured signals reveals that the boxplot algorithm improved upon the least squares method achieves a recall rate of 100% for identifying anomalous data. Meanwhile, the denoising method combining the fast ensemble empirical mode decomposition with wavelet thresholding can effectively filter out interfering noise signals. By analyzing simulated signals contaminated with various types of noise, it is found that compared to methods such as wavelet thresholding, FEEMD alone, and the combination of empirical mode decomposition (EMD) with wavelet thresholding, the monitoring data denoised using the proposed method exhibits a minimum root mean square error. Results from processing actual measured signals demonstrate that the smoothness index and noise mode after denoising are superior to those obtained from other schemes. [Conclusions] The improved boxplot algorithm based on the least squares method and the denoising method combining FEEMD with wavelet thresholding can effectively address the issues of outlier recognition and noise in bridge monitoring signals. The research findings can serve as a reference for the preprocessing of bridge signals.