An enhanced fault diagnosis method for rolling element bearings using a combination of time-varying filtering for empirical mode decomposition (TVF-EMD) and a high-order energy operator (HO-EO) is proposed in this paper. Empirical mode decomposition (EMD), as a classical mode decomposition technique, has been widely used in quite a few fields. However, the separation problem and the intermittent problem, which can give rise to mode mixing, still remain unresolved. TVF-EMD is capable of improving mode mixing in comparison with EMD. In addition, TVF-EMD is more robust to noise than EMD. These improvements ensure that the vibration signal is decomposed into multiple meaningful empirical modes precisely, known as intrinsic mode functions (IMFs). Then, the meaningful IMFs are selected to be processed by HO-EO. HO-EO is very suitable for bearing fault diagnosis as a demodulation algorithm. Moreover, compared with traditional energy operators, it is more robust to strong noise and vibration interference, so it has a higher accuracy. With this proposed method, the weak bearing fault signature can be distinguished precisely in the energy spectrum. In order to verify the proposed method, single-and dual-fault bearings are used. The experimental results reveal that the proposed method is a powerful and effective tool for bearings fault diagnosis.

The Teager–Kaiser energy operator (TKEO) and Hilbert transform (HT) are widely used as conventional demodulation methods in the signal processing field; however, it is well known that they are sensitive to vibration interference and noise, and these limitations hamper their applications, especially in the presence of strong noise. A vibrating screen is a kind of screening equipment in the field of vibrating machinery, which differs greatly from the rotating machinery in terms of structural characteristics and operational principles. The vibration signal extracted from the vibrating screen is not only comprised of multiple constituents but also a great deal of background noise. Thus, TKEO and HT have a large limitation on bearing fault diagnosis of the vibrating screen. To overcome these shortcomings, an alternative energy operator method named the envelope-derivative operator (EDO) is proposed. The results of simulation and bearing fault diagnosis of the vibrating screen indicate that EDO can effectively extract fault characteristic frequency, certifying its feasibility and superiority in comparison with TKEO and EDO.

No abstract

No abstract

Smoking in public places not only brings about some safety hazards, but also does harm to people’s lives, property and living environment. A smoking behavior detection model based on deep learning is trained for the concern of environment and safety. First, a vertical rotation data enhancement method is adopted in the preprocessing stage to extend the dataset and increase the objects of detection. Then, the channel attention module is introduced in backbone network to calibrate the feature response. Finally, added a small target detection layer to the YOLOv5 algorithm. This paper analyzes the network structure of the YOLOv5s, and the model is trained and tested by utilizing the YOLOv5s network. Experimental results show that the mAP value of the algorithm is improved by 5.3% over the original algorithm.