Search

For substation secondary circuit terminal strip wiring, low efficiency, less easy fault detection and inspection, and a variety of other issues, this study proposes a text detection and identification model based on improved YOLOv7-tiny and MAH-CRNN+CTC terminal lines. First, the YOLOv7-tiny target detection model is improved by the introduction of the spatially invariant multi-attention mechanism (SimAM) and the weighted bidirectional feature pyramid network (BiFPN). This also improves the feature enhancements and feature fusion ability of the model, balances various scales of characteristic information, and increases the positioning accuracy of the text test box. Then, a multi-head attention hybrid (MAH) mechanism is implemented to optimize the convolutional recurrent neural network with connectionist temporal classification (CRNN+CTC) so that the model could learn data features with larger weights and increase the recognition accuracy of the model. The findings indicate that the enhanced YOLOv7-tiny model achieves 97.39%, 98.62%, and 95.07% of precision, recall, and mean average precision (mAP), respectively, on the detection dataset. The improved MAH-CRNN+CTC model achieves 91.2% character recognition accuracy in the recognition dataset. [ABSTRACT FROM AUTHOR]

An accurate NOx concentration prediction model plays an important role in low NOx emission control in power stations. Predicting NOx in advance is of great significance in satisfying stringent environmental policies. This study aims to accurately predict the NOx emission concentration at the outlet of boilers on different operating conditions to support the DeNOx procedure. Through mutual information analysis, suitable features are selected to build models. Long short-term memory (LSTM) models are utilized to predict NOx concentration at the boiler's outlet from selected input features and exhibit power in fitting multivariable coupling, nonlinear, and large time-delay systems. Moreover, a composite LSTM model composed of models on different operating conditions, like steady-state and transient-state condition, is prosed. Results of one whole day of typical operating data show that the accuracy of the NOx concentration and fluctuation trend prediction based on this composite model is superior to that using a single LSTM model and other non-time-sequence models. The root mean square error (RMSE) and R2 of the composite LSTM model are 3.53 mg/m3 and 0.89, respectively, which are better than those of a single LSTM (i.e., 5.50 mg/m3 and 0.78, respectively). [ABSTRACT FROM AUTHOR]

The behavior of aluminum particles during Al/AP propellant combustion is studied by 25 kHz high-speed digital off-axis holography and high-speed microscopic imaging. The advantage of off-axis holography is that the effects of the enveloping flame are suppressed, thereby, achieving better burning particle imaging. Three-dimensional dynamics of the aluminum particles from a series of time-resolved holograms are given in order to study the motion behaviors of particles during combustion. Typical processes, e.g., formation and change of the condensed phase products, micro-explosion behavior, and diameter ratio of enveloping flame and Al particle, are analyzed. This work provides a new 3D approach, that is, high-speed digital off-axis holographic imaging, for studying solid propellant combustion. [ABSTRACT FROM AUTHOR]