• Energy Research
• CN close
• Sensors close

This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.

This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.

Ethanol sensors have found extensive applications across various industries, including the chemical, environmental, transportation, and healthcare sectors. With increasing demands for enhanced performance and reduced energy consumption, there is a growing need for developing new ethanol sensors. Micro-electromechanical system (MEMS) devices offer promising prospects in gas sensor applications due to their compact size, low power requirements, and seamless integration capabilities. In this study, SnO2-TiO2 nanocomposites with varying molar ratios of SnO2 and TiO2 were synthesized via ball milling and then printed on MEMS chips for ethanol sensing using electrohydrodynamic (EHD) printing. The study indicates that the two metal oxides dispersed evenly, resulting in a well-formed gas-sensitive film. The SnO2-TiO2 composite exhibits the best performance at a molar ratio of 1:1, with a response value of 25.6 to 50 ppm ethanol at 288 °C. This value is 7.2 times and 1.8 times higher than that of single SnO2 and TiO2 gas sensors, respectively. The enhanced gas sensitivity can be attributed to the increased surface reactive oxygen species and optimized material resistance resulting from the chemical and electronic effects of the composite.

Ethanol sensors have found extensive applications across various industries, including the chemical, environmental, transportation, and healthcare sectors. With increasing demands for enhanced performance and reduced energy consumption, there is a growing need for developing new ethanol sensors. Micro-electromechanical system (MEMS) devices offer promising prospects in gas sensor applications due to their compact size, low power requirements, and seamless integration capabilities. In this study, SnO2-TiO2 nanocomposites with varying molar ratios of SnO2 and TiO2 were synthesized via ball milling and then printed on MEMS chips for ethanol sensing using electrohydrodynamic (EHD) printing. The study indicates that the two metal oxides dispersed evenly, resulting in a well-formed gas-sensitive film. The SnO2-TiO2 composite exhibits the best performance at a molar ratio of 1:1, with a response value of 25.6 to 50 ppm ethanol at 288 °C. This value is 7.2 times and 1.8 times higher than that of single SnO2 and TiO2 gas sensors, respectively. The enhanced gas sensitivity can be attributed to the increased surface reactive oxygen species and optimized material resistance resulting from the chemical and electronic effects of the composite.

Fatigue of miners is caused by intensive workloads, long working hours, and shift-work schedules. It is one of the major factors increasing the risk of safety problems and work mistakes. Examining the detection of miner fatigue is important because it can potentially prevent work accidents and improve working efficiency in underground coal mines. Many previous studies have introduced feature-based machine-learning methods to estimate miner fatigue. This work proposes a method that uses electroencephalogram (EEG) signals to generate topographic maps containing frequency and spatial information. It utilizes a convolutional neural network (CNN) to classify the normal state, critical state, and fatigue state of miners. The topographic maps are generated from the EEG signals and contrasted using power spectral density (PSD) and relative power spectral density (RPSD). These two feature extraction methods were applied to feature recognition and four representative deep-learning methods. The results showthat RPSD achieves better performance than PSD in classification accuracy with all deep-learning methods. The CNN achieved superior results to the other deep-learning methods, with an accuracy of 94.5%, precision of 97.0%, sensitivity of 94.8%, and F1 score of 96.3%. Our results also show that the RPSD–CNN method outperforms the current state of the art. Thus, this method might be a useful and effective miner fatigue detection tool for coal companies in the near future.

Fatigue of miners is caused by intensive workloads, long working hours, and shift-work schedules. It is one of the major factors increasing the risk of safety problems and work mistakes. Examining the detection of miner fatigue is important because it can potentially prevent work accidents and improve working efficiency in underground coal mines. Many previous studies have introduced feature-based machine-learning methods to estimate miner fatigue. This work proposes a method that uses electroencephalogram (EEG) signals to generate topographic maps containing frequency and spatial information. It utilizes a convolutional neural network (CNN) to classify the normal state, critical state, and fatigue state of miners. The topographic maps are generated from the EEG signals and contrasted using power spectral density (PSD) and relative power spectral density (RPSD). These two feature extraction methods were applied to feature recognition and four representative deep-learning methods. The results showthat RPSD achieves better performance than PSD in classification accuracy with all deep-learning methods. The CNN achieved superior results to the other deep-learning methods, with an accuracy of 94.5%, precision of 97.0%, sensitivity of 94.8%, and F1 score of 96.3%. Our results also show that the RPSD–CNN method outperforms the current state of the art. Thus, this method might be a useful and effective miner fatigue detection tool for coal companies in the near future.

For the optimization of three-phase hybrid stepper motors with complex electromagnetic structures, an optimization method is presented in this paper. The method is a combination of 3D-FEM and the Taguchi optimization method intended to reduce the dependence on FEM results during the optimization calculation. In this paper, the optimization method is used in the optimization of the tooth shape of the three-phase hybrid stepper motor, and the objective is to reduce the noise caused by harmonics in the “torque-angle characteristic” of the motor. It is clear that traditional optimization methods make it very difficult to carry out such an optimization calculation as a large number of finite element calculations have to be used in the optimization process, and the required computation time is extremely long. Using the optimization method presented in the paper, the optimization becomes feasible because the number of finite element calculations is greatly reduced and the computation time is thus greatly reduced. In order to check the effectiveness of the optimization, the waterfall diagram for noise analysis and its application to check torque ripple are also presented in the paper. Both simulation and test results show that the optimized structure can significantly reduce the motor noise caused by torque ripple. Therefore, the optimization method proposed in this paper can be an effective tool for the optimal design of high-performance motors, including stepper motors.