Fault Diagnosis of Balancing Machine Based on ISSA-ELM

Area of Science:

• Mechanical Engineering
• Artificial Intelligence
• Machine Learning

Background:

• Balancing machines are critical for verifying the dynamic balance of rotating parts.
• Current methods often lack sufficient accuracy in diagnosing balancing machine faults.
• Accurate fault diagnosis is essential for ensuring the reliability and performance of balancing equipment.

Purpose of the Study:

• To develop a highly accurate fault diagnosis method for balancing machines.
• To improve the prediction accuracy of the operational status of balancing machines.
• To address the limitations of existing fault diagnosis techniques in terms of accuracy.

Main Methods:

• Proposed a novel fault diagnosis approach combining an Improved Sparrow Search Algorithm (ISSA) with an Extreme Learning Machine (ELM).
• Introduced iterative chaos mapping and Fuch chaos mapping for population initialization and diversity enhancement.
• Incorporated an adaptive dynamic factor and Levy flight strategy to optimize individual positions and accelerate model convergence.

Main Results:

• The proposed ISSA-ELM model achieved a fault diagnosis accuracy of 99.17%.
• This represents a significant improvement over existing methods: 1.67% higher than SSA-ELM, 2.50% higher than HHO-ELM, 7.50% higher than PSO-ELM, and 17.50% higher than standard ELM.
• The method effectively improved the prediction accuracy of the balancing machine's operational state.

Conclusions:

• The ISSA-ELM fault diagnosis method offers superior accuracy and performance for balancing machines.
• The integration of chaos mapping and Levy flight strategies enhances the optimization capabilities of the Sparrow Search Algorithm.
• This research provides a robust solution for improving the reliability and maintenance of dynamic balancing equipment.