# A Hybrid Intelligent Fault Diagnosis Framework for Rolling Bearings and Gears Based on BAYES-ICEEMDAN-SNR Feature Enhancement and ITOC-LSSVM

## TL;DR

This paper introduces a new fault diagnosis framework for rolling bearings and gears that improves signal analysis and model optimization, achieving high accuracy in identifying faults.

## Contribution

The novel BAYES-ICEEMDAN-SNR method and ITOC-LSSVM model enhance feature extraction and optimization for fault diagnosis in noisy environments.

## Key findings

- The BAYES-ICEEMDAN-SNR method improves vibration signal decomposition stability and feature extraction robustness.
- The ITOC-LSSVM model achieves 97.67% classification accuracy on the Case Western Reserve University bearing dataset.
- The proposed framework outperforms existing methods in fault diagnosis for bearings and gears.

## Abstract

What are the main findings?
An enhanced ICEEMDAN method integrating Bayesian optimization and adaptive signal-to-noise ratio (BAYES-ICEEMDAN-SNR) is proposed, which significantly improves the stability of vibration signal decomposition and the robustness of feature extraction.An improved Tornado Optimizer with Coriolis force (ITOC) is designed by incorporating Chebyshev chaotic mapping, Cauchy mutation, and dynamic opposition-based learning strategies, effectively enhancing global search capability and convergence accuracy.

An enhanced ICEEMDAN method integrating Bayesian optimization and adaptive signal-to-noise ratio (BAYES-ICEEMDAN-SNR) is proposed, which significantly improves the stability of vibration signal decomposition and the robustness of feature extraction.

An improved Tornado Optimizer with Coriolis force (ITOC) is designed by incorporating Chebyshev chaotic mapping, Cauchy mutation, and dynamic opposition-based learning strategies, effectively enhancing global search capability and convergence accuracy.

What are the implications of the main findings?
The constructed ITOC-LSSVM fault diagnosis model achieves a classification accuracy of 97.67% on the Case Western Reserve University bearing dataset, outperforming several comparative methods.This method provides an efficient and adaptive solution for intelligent fault diagnosis of rolling bearings under strong noise environments, demonstrating considerable potential for engineering applications.

The constructed ITOC-LSSVM fault diagnosis model achieves a classification accuracy of 97.67% on the Case Western Reserve University bearing dataset, outperforming several comparative methods.

This method provides an efficient and adaptive solution for intelligent fault diagnosis of rolling bearings under strong noise environments, demonstrating considerable potential for engineering applications.

To address the challenges of difficult feature extraction for rolling bearing vibration signals, low efficiency in optimizing diagnostic model parameters, and the tendency to get trapped in local optima, this paper proposes an improved ICEEMDAN feature extraction method based on Bayesian optimization and adaptive noise signal ratio enhancement (BAYES-ICEEMDAN-SNR) and combines it with the improved Coriolis force optimization algorithm (ITOC) to optimize the least squares support vector machine (LSSVM) fault diagnosis model. Firstly, Bayesian optimization is used to adaptively determine the noise parameters and introduce a dynamic signal-to-noise ratio adjustment mechanism to enhance the robustness of feature extraction; secondly, Chebyshev chaotic mapping, Cauchy mutation, and dynamic reverse learning strategies are applied to enhance the global search and local escape capabilities of ITOC, thereby optimizing the hyperparameters of LSSVM; and finally, the Keesey-Chestnut University bearing dataset and Huazhong University of Science and Technology gear dataset are used for verification. The experimental results show that the average fault identification accuracy of the proposed method reaches over 97%, which is superior to that of the comparison models, and the effectiveness of each core improvement module of the proposed model is verified through ablation experiments, providing an effective solution for intelligent fault diagnosis of rolling bearings and gears.