In recent years, more and more deep learning methods for fault diagnosis of rolling element bearings (REBS) have been proposed. However, in industry, the scarcity of available data to monitor the health condition of REBS leads to a low recognition accuracy of the trained intelligent diagnostic models. To solve this problem, we propose a simulation data driven subdomain adaption adversarial transfer learning network (SAATLN). Firstly, a defect vibration model is introduced to simulate vibration signals of different types of REBS faults. And the real signal and simulated signal are used as the target domain and source domain of the transfer learning fault diagnosis methods, respectively. Secondly, SAATLN uses the designed residual Squeeze-and-Excitation (Re-SE) blocks to extract transfer features between different domains. Meanwhile, it combines adversarial learning and subdomain adaptation to adapt the marginal distribution and conditional distribution discrepancy of high-level features. And the local maximum mean discrepancy (LMMD) is introduced as the subdomain adaptation metric criterion. Finally, different transfer tasks are performed on the artificially damaged and run-to-failure REBS data sets. The results demonstrate the effectiveness and superiority of the SAATLN in the simulation data driven REBS fault diagnosis.

This paper presents a novel modulated Model-Predictive Control (MMPC) scheme for Modular Multilevel Cascaded Converter-based STATCOMs (MMCC-STATCOM) to compensate unbalanced load current and regulate reactive power flow. By adding a common mode voltage (CMV) to the phasevoltages of the star-connected MMCC current model, the method allows natural injection of a non-sinusoidal voltage to the neutral point of the converter, hence achieving inter-phase cluster voltage balance. Moreover the imposed CMV is shown to extend the operating ranges of MMCC STATCOMs when used for negative sequence current compensation. The proposed MMPC method incorporates a modified branch and bound (B&B) algorithm to optimize the per-phase switch duty ratios. It is shown to be computationally more efficient compared to model-predictive control schemes using optimal voltage level method combined with voltage sorting schemes. Experimental results with different weighting factors confirm the effectiveness of this control scheme, and compared favorably with the conventional scheme of injecting only a sinusoidal zero sequence voltage.Index Terms-Modulated model predictive control (MMPC), Branch and bound method (B&B), Multilevel modular cascaded converter-based STATCOM (MMCC-STATCOM).

It is difficult to evaluate the degradation performance and the degradation state of the rolling bearing in noisy environment. A new method is proposed to solve the problem based on singular value decomposition (SVD)-sliding window linear regression and ResNeXt - multi-attention mechanism's deep neural network (RMADNN). Firstly, the root mean square(RMS) gradient value is calculated on the basis of RMS based on SVD and linear regression of sliding window, which is used as the rolling bearing performance degradation indicator in noisy environment. Secondly, the degradation state of rolling bearing is divided by the RMS gradient. Thirdly, for the part of the deep learning network model, the soft attention mechanism is introduced into the bidirectional long short-term memory network (BiLSTM) to extract more important and deep fault features. At the same time, the ResNeXt layer is added into the convolutional neural network (CNN) to extract more fault features and merge them through multi-scale grouped convolution. Then, the hybrid domain attention mechanism (HDAM) was introduced after the ResNext layer. The HDAM can screen out more important features from the output features of the ResNext in the two dimensions of channel and spatial. Therefore, the improved deep learning network of the ResNeXt - multi-attention mechanism's deep neural network (RMADNN) in this research is established. Finally, the labeled data set is input into the improved model for training, and the Softmax classifier is used to identify the life decline state of the rolling bearing. The result shows that the indicator of RMS gradient proposed has a better characterization, and the RMADNN model can distinguish the life degradation state of rolling bearing better.

The Static Synchronous Series Compensator, performing power control and reactive power compensation, is an important aid to stable and flexible operation of recent electrical power distribution networks. The paper describes a compensator based on a bidirectional Z-source inverter with PWM technology. This inverter has a wide control range and does not require a switching dead time. Its design using small signal theory to obtain suitable L-C network parameters for desired time response is described. Model predictive current control and direct current control schemes are analysed and compared, and satisfactory performance of the whole compensator is demonstrated.

No abstract