In the relentless pursuit of operational efficiency and safety, the energy sector faces a persistent challenge: detecting early faults in rolling bearings before they escalate into catastrophic failures. These components, crucial in machinery from wind turbines to power plants, often operate in noisy environments where subtle signs of wear can be easily missed. However, a groundbreaking study published in Jixie qiangdu (Journal of Mechanical Strength) offers a promising solution, potentially revolutionizing predictive maintenance strategies.
Lead author Sun Meng, affiliated with an undisclosed institution, has developed a novel method for early fault diagnosis in rolling bearings. The approach integrates several advanced algorithms to enhance the detection of weak fault characteristics that are often drowned out by operational noise. “The key is to optimize the signal processing techniques to make them more sensitive to early fault signs,” Sun explains.
At the heart of this innovation lies the improved artificial gorilla troops optimizer (IGTO) algorithm. This algorithm simultaneously optimizes multiple parameters of the resonance-based sparse signal decomposition (RSSD) method. By doing so, it achieves an optimal match between the wavelet basis function and the dissipation function, significantly improving the algorithm’s performance. “The IGTO algorithm has shown a marked improvement in optimization performance compared to existing methods,” Sun notes.
The process begins by using the squared envelope spectrum correlated kurtosis (SE-SCK) negative value of the low resonance component as the objective function. The IGTO algorithm then optimizes the quality factor, weight coefficient, and Lagrange multiplier of the RSSD. This optimized low resonance component is subsequently input into the sparse maximum harmonics-to-noise-ratio deconvolution (SMHD) method for filtering. Finally, envelope spectrum analysis is performed to extract the fault features.
The implications for the energy sector are profound. Early detection of bearing faults can prevent unplanned downtime, reduce maintenance costs, and enhance the overall safety and reliability of operations. For instance, in wind farms, where turbines operate in harsh conditions, this method could significantly extend the lifespan of critical components and improve energy production efficiency.
The study’s findings, validated through simulation and real-world tests using the XJTU-SY bearing full life cycle fault signal, demonstrate the method’s effectiveness in extracting early weak fault characteristics. This breakthrough could pave the way for more sophisticated predictive maintenance systems, not just in the energy sector but across various industries that rely on heavy machinery.
As the energy sector continues to evolve, driven by the need for sustainability and efficiency, innovations like Sun Meng’s method will play a pivotal role. By enabling earlier and more accurate fault detection, this research could shape the future of maintenance strategies, ensuring that machinery operates at peak performance for longer periods. The publication of this research in Jixie qiangdu, also known as the Journal of Mechanical Strength, underscores its significance and potential impact on the field.