基于稀疏分解的航空装备机电故障检修仿真

Sparse Decomposition Based Maintenance Simulation of Mechanical and Electrical Faults of Aviation Equipment

航空装备在巡航、物资运输、军事作战等领域具有重要作用,因此一旦发生故障,造成的损失也是巨大的。在航空装备故障中,机电故障是最难以诊断和修复的。以往在故障检修的故障信号处理环节中,多采用小波变换、盲源分离以及奇异值分解等三种方法,信号去噪能力不足,影响了整体方法的检修效果。针对上述情况,提出一种基于稀疏分解的航空装备机电故障检修方法。该方法首先利用采集装置对航空装备机电故障信号进行采集,然后利用稀疏分解对故障信号进行分解去噪处理,接着利用免疫聚类算法对去噪后的信号进行故障识别,最后对不同类型的故障进行故障修复。结果表明:稀疏分解去噪后,信号信噪比提高1.4dB、5.3dB、9.8dB,去噪效果有明显改善;使得所提方法的漏检率与误检率降低,提高了整体检修质量。

Aviation equipment plays an important role in the fields of cruise,material transportation,and military action.In the aviation equipment failure,electromechanical failure is the most difficult to diagnose and repair.In the past,wavelet transform,blind source separation and singular value decomposition were often adopted,but the denoising ability was insufficient,influencing the overall effect.Therefore,an electromechanical troubleshooting method for aviation equipment based on sparse decomposition was proposed.Firstly,this method used the acquisition device to collect the electromechanical fault signal from the aviation equipment,and then decomposed the fault signal by sparse decomposition.Moreover,the method used the immune clustering algorithm to identify the breakdowns of signal after the noise reduction.Finally,we repaired the different types of faults.The results prove that after sparse decomposition and noise reduction,the signal-to-noise ratio is improved by 1.4 dB,5.3 dB and 9.8 dB,respectively.The denoising effect is obviously improved.The missed detection rate and false detection rate of the proposed method are reduced,so that the overall quality is improved.