In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition is difficult and the amount of data is too small, with large data training methods to solve a certain degree of difficulty. Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network. It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning. The experiment shows that this method can detect the cloud computing abnormality and determine the fault more effectively and accurately than the traditional method in the case of the small amount of cloud fault feature data.

In order to improve the signal natural frequency of dynamic vibration absorber and eliminate the influence of nonlinear output force to the adaptive vibration absorption system. A new type of electromagnetic active vibration absorber is designed in this article. The internal magnetic circuit structure is changed through the electromagnet placed on the upper and lower, produce the electromagnetic force in two directions. Reaction force of upper mass is used to eliminate the target vibration. The effective frequency range of the vibration absorption increases, output force is basically linear. Aimed at multiple-point adaptive control strategy, a distributed multi-channel adaptive control algorithm is proposed, in which coupling between channels can be compensated on each control loop. Influence of secondary path on active control is analyzed, put forward the improved least mean square algorithm to identify the secondary. Active vibration control experiment platform is structured to verify the output force of absorber, and engineering application of the distributed multi-channel adaptive control algorithm. The results show that the distributed multi-channel adaptive control algorithm system has about 15 dB noise reduction, effect is obvious; new type of electromagnetic active vibration absorber is not limited to the natural frequency, output force can adaptive keep pace with the excitation frequency.

No abstract

Active vibration control (AVC) can solve many vibration problems. However, structural vibration in underwater vehicles often involves other factors such as complex excitation and path coupling, etc. At present, the traditional algorithm (e.g., multi Filtered-x Least Mean Square, M-FxLMS) usually cannot effectively process the multi-frequency excitation and the coupling effects of the multi-secondary path, which will affect its convergence and stability to a certain extent. Consequently, a novel strategy is presented in this paper, namely, the wavelet packet transformation decentralized decoupling M-FxLMS algorithm (WPTDDM-FxLMS), which can solve the structural vibration problems mentioned above. The multi-frequency control is converted into a single-frequency line spectrum control, and the feedback compensation factor is introduced in the identification of the secondary path, both of which can simplify the multi-path control system to the parallel single-path systems. Furthermore, the WPTDDM-FxLMS algorithm is applied to the AVC in a multi-input and multi-output system (MIMO) vibration platform. Finally, the simulation and experiments show that the wavelet packet can decompose the multi-frequency excitation into a line spectrum signal, and the improvement of the decentralized decoupling and the variable step-size can effectively reduce the computation amount and increase the convergence speed and accuracy. Overall, the novel algorithm is significant for multi-path coupling vibration control. It will have certain engineering application value in underwater vehicles.

Background:Neck pain is a common discomfort or more intense forms of pain in the cervical region. Neck pain has a large impact on individuals and their families, communities, healthcare systems, and businesses throughout the world. Therapeutic strategies are widely used for patients with neck pain in clinical practice, but the effectiveness of each therapeutic strategy is still unclear. The aim of this study is to assess the efficacy and safety of therapeutic strategies for neck pain.Method:Seven electronic databases will be searched regardless of publication date or language. Randomized controlled trials will be included if they recruited participants with neck pain for assessing the effect of each therapy. Primary outcomes will include pain score. The risk of bias will be assessed by 2 authors using the Cochrane tool of risk of bias. Network meta-analysis in random effects model will be conducted to estimate the indirect and mixed effects of therapeutic strategies for neck pain by R-3.5.1 software. The confidence in cumulative evidence will be assessed by grading of recommendations assessment, development, and evaluation.Results:This study will be to assess the effect and safety of therapeutic strategies for neck pain.Conclusions:This study will assess the effect of different therapeutic strategies for neck pain and provide reliable evidence for the choice of treatments.Systematic review registration:PROSPERO (CRD42019102385).