During the manufacturing process of electronic equipment, objects such as tin beads and glue blocks may be left in the electronic equipment, causing failure of the electronic equipment. This paper uses experimental equipment to collect weak vibration signals on the surface of electronic equipment. In view of the nonlinear and non-stationary characteristics of the vibration signal and its easy to be masked by strong background noise, a fault diagnosis method of weak vibration signal based on improved variational mode decomposition (VMD) and maximum correlation kurtosis deconvolution (MCKD) is proposed. Cosine factors and adaptive weights are introduced to improve the convergence accuracy of the Whale Optimization Algorithm (WOA). The envelope spectrum peak factor is used as the adaptability function of the improved whale algorithm (IWOA) to optimize the parameters of VMD and MCKD. Firstly, based on the decomposition results of weak fault signals by IWOA-VMD, the optimal modal components are selected. Secondly, the fault impact component in the optimal modal component is enhanced based on the IWOA-MCKD algorithm. Finally, the fault characteristic frequency is extracted through the envelope spectrum. The feasibility and superiority of the proposed optimization method are verified through simulation signal analysis and actual case study.
11 March 2025 in IEEE Transactions on Instrumentation and Measurement
It is widely known that unexpected foreign objects, such as glue residues and plastic fragments, may be left inside electronic products during production and assembly. These foreign objects may cause electronic products to malfunction. This paper employs a vibration test bench to investigate electronic products and collect vibration signals of foreign objects inside them. These signals are typically weak fault vibration signals, often obscured by strong background noise. To recover the periodic pulses from this noise, we apply the maximum second-order cyclostationarity blind deconvolution (CYCBD) method. However, the selection of the key parameters of CYCBD, cyclic frequency and filter length, is very challenging. To address this issue, we propose an adaptive CYCBD (ACYCBD) method. The proposed method utilizes an improved envelope spectrum via candidate fault frequency optimization-gram (IESCFFOgram) to efficiently identify information frequency bands.The cyclic frequency is estimated from the enhanced harmonic product spectrum (EHPS) of these bands. The proposed power dispersion entropy (PSE-DE) is used to determine the optimal filter length, enhancing sensitivity to signal vibrations. The feasibility and superiority of the proposed method are validated through simulated signals and actual data analysis on a vibration test bench, and experimental results indicate its robustness and resistance to strong background noise.
Foreign body failure in electronic products refers to the presence of unintended foreign matter within key components, causing abnormal behavior. Traditional detection methods rely on shaking the product and human auditory perception to identify foreign objects. In contrast, this paper introduces a novel approach using a foreign object vibration device to induce vibrations in electronic products. Vibration signals are collected from an acceleration sensor on the product’s surface and analyzed to detect foreign objects. Since vibrations are random, the impact of foreign objects is hidden across multiple signal channels, making single-channel fault diagnosis limited. To address this, we propose a multi-channel enhanced convolutional neural network strategy. Multi-channel signals are preprocessed to amplify variations, and time-domain features and entropy values are extracted to generate a multi-channel feature fusion matrix. This matrix is fed into a multi-channel gated recurrent convolutional neural network, combining the benefits of convolutional neural network and gated recurrent unit to detect foreign objects and classify their types. Experimental results show that the proposed method achieves higher accuracy than traditional methods and effectively distinguishes different types of foreign objects.