Parallel fusion model for complex multi-source vibration time-series prediction
Authors:
Open Access
- 19 May 2026
- journal article
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Abstract
Aiming at the insufficient prediction accuracy caused by the non-stationary and multi-frequency coupling characteristics of complex multi-source vibration signals, this study proposes a parallel fusion prediction model that takes hyperparameter optimization as the core preprocessing step and integrates multivariate variational mode decomposition (MVMD) with parallel weighted KNN-XGBoost. Firstly, a "training-validation-test" three-set data separation framework is constructed, and a stepwise grid search strategy is adopted to optimize key hyperparameters. With the error validation set as the objective function, the number of neighbors for K-Nearest Neighbors (KNN), the tree depth and learning rate for eXtreme Gradient Boosting (XGBoost), and the optimal fusion weights of KNN and XGBoost are determined sequentially. This fundamentally avoids the subjective bias inherent in manual parameter tuning. Secondly, MVMD is employed to decompose complex multi-source vibration signals into 8 intrinsic mode functions (IMFs) with different frequency scales. This addresses the mode mixing issue of traditional decomposition methods, reduces the complexity of vibration signals, and retains the multi-source coupling features. Thirdly, a parallel weighted KNN-XGBoost structure is built based on the optimized parameters. Through independent prediction and weighted fusion, error propagation in serial structures is avoided, enabling the synergy of "local correction-global fitting". Multiple comparative and ablation experiments demonstrate that, compared with other models, the MVMD-parallel-KNN-XGBoost model achieves the optimal balanced performance. This study provides a parallel fusion technical pathway of "parameter optimization-modal separation-model fusion" for complex multi-source vibration time-series prediction, which can meet the high-precision prediction requirements of complex multi-source vibration in fields such as aerospace, rail transit, and industrial engineering etc.Keywords
Funding Information
- Key Technologies Research and Development Program (2024YFF0508104)
- Key Technologies Research and Development Program (2024YFF0508104)
- Research and application of key technologies for micro-nano environmental vibration control of Chinese major science and technology infrastructures (QNJJZD – 2022 - 04)
- Research and application of key technologies for micro-nano environmental vibration control of Chinese major science and technology infrastructures (QNJJZD – 2022 - 04)
- Research on key technologies for industrial upstairs engineering designs (ZDZX2025-07)
- Research on key technologies for industrial upstairs engineering designs (ZDZX2025-07)
This publication has 20 references indexed in Scilit:
- Digital twin-inspired methods for rotating machinery intelligent fault diagnosis and remaining useful life prediction: A state-of-the-art review and future challengesMechanical Systems and Signal Processing, 2025
- A novel lightweight DDPM-based data augmentation method for rotating machinery fault diagnosis with small sampleMechanical Systems and Signal Processing, 2025
- Time Series Prediction Based on LSTM-Attention-LSTM ModelIEEE Access, 2023
- Vibration-based anomaly detection using LSTM/SVM approachesMechanical Systems and Signal Processing, 2022
- Approximating XGBoost with an interpretable decision treeInformation Sciences, 2021
- A kNN algorithm for locating and quantifying stiffness loss in a bridge from the forced vibration due to a truck crossing at low speedMechanical Systems and Signal Processing, 2021
- Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibrationEngineering with Computers, 2021
- Prediction of mechanical equipment vibration trend using autoregressive integrated moving average model2017
- K-Nearest Neighbors2013
- Random ForestsMachine Learning, 2001