Search

The complex and changeable working conditions of mechanical equipment in industrial field lead to uneven distribution of fault samples, which brings great trouble to traditional machine learning. In order to solve this problem, proposes a bearing fault transfer diagnosis method based on domain adaptive neural network and balanced dynamic distribution adaptive. Firstly, According to the characteristics of bearing vibration fault samples, the convolution layer of convolutional neural network is improved by wavelet transform, and the characteristics of bearing samples are extracted adaptively. Then, Maximum Mean Discrepancy measure and weight regularization are used to process the generated features in the loss function to reduce the difference in sample distribution and obtain the domain adaptive neural network model. Finally, A-distance is used to improve the equilibrium distribution adaptive to make it have dynamic characteristics, further improve the difference of sample distribution, and realize bearing transfer diagnosis by KNN classifier. Through experimental verification, the proposed method can accurately migrate the bearing fault state in the same bench rig cases and cross bench rig cases, proving that the method can effectively solve the problem of uneven distribution of unlabeled samples under variable working conditions, and has the effectiveness and robustness.

Here we introduce a metal‐free, catalytic and enantioselective strategy from α,β‐unsaturated 2‐acyl imidazoles to the chiral phosphorous 2‐acyl imidazoles. Interestingly, this methodology was catalyzed by the classical and commercial oxazaborolidine under mild conditions. This strategy features a wide range of substrates scope with good yields and excellent enantioselectivities. The possible mechanism further suggests the key of this reaction through the cleavage of diarylphosphine oxides using Frustrated Lewis Pairs theory. [ABSTRACT FROM AUTHOR]

In order to solve the back corona phenomenon caused by high specific resistance dust in electrostatic precipitation process, the circuit topology of DC base voltage superimposed pulse voltage is adopted. Firstly, for the DC base voltage part, a three-phase AC voltage regulator circuit and a subsequent filter circuit are established, and the average values generated by the circuit at different firing angles are analyzed. Secondly, in the pulse generation part, the LCC resonance is discussed according to the mathematical model. Finally, according to the design requirements, the whole circuit is simulated with Simulink module in MATLAB, and compared with the calculated data, it has a high consistency, which verifies the correctness of the design idea.

In order to address the challenge of accurately predicting nitrogen oxide (NOx) emission from diesel engines in transient operation using traditional neural network models, this study proposes a NOx emission forecasting model based on a hybrid neural network architecture combining the convolutional neural network (CNN) and long short-term memory (LSTM) neural network. The objective is to enhance calibration efficiency and reduce diesel engine emissions. The proposed model utilizes data collected under the thermal cycle according to the world harmonized transient cycle (WHTC) emission test standard for training and verifying the prediction model. The CNN is employed to extract features from the training data, while LSTM networks are used to fit the data, resulting in the precise prediction of training NOx emissions from diesel engines. Experimental verification was conducted and the results demonstrate that the fitting coefficient (R2) of the CNN-LSTM network model in predicting transient NOx emissions from diesel engines is 0.977 with a root mean square error of 33.495. Compared to predictions made by a single LSTM neural network, CNN neural network predictions, and back-propagation (BP) neural network predictions, the root mean square error (RMSE) decreases by 35.6%, 50.8%, and 62.9%, respectively, while the fitting degree R2 increases by 2.5%, 4.4%, and 6.6%. These results demonstrate that the CNN-LSTM network prediction model has higher accuracy, good convergence, and robustness. [ABSTRACT FROM AUTHOR]

With YN30 electronically-controlled diesel engine as the object of study, a detection method for the unevenness between different cylinders is proposed based on band-pass filtering. Firstly the instantaneous rotation speed signal of engine is picked up by crankshaft signal sensors. It is then processed by low-pass filtering and re-sampling, and the curves of unevenness between cylinders are obtained in the form of band-pass filtering. Finally the unevenness is quantified by PI algorithm to get the specific fuel correction required for each cylinder. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the control performance of permanent magnet synchronous motor is easily affected by load disturbance during operation, a fractional‐order sliding mode control method combining fractal‐order sliding mode controller (FOSMC) and fractional‐order sliding mode load torque observer (FOSMO) is proposed. The parameters of this method are tuned using the improved salp swarm algorithm (ISSA). Initially, the fractional‐order sliding mode controller is designed by applying fractional‐order calculus theory to enhance the system's response speed. Subsequently, a fractional‐order sliding mode load torque observer is developed to improve the system's anti‐interference capability and robustness due to the slow response and low identification accuracy of traditional load torque observers. Lastly, the control parameters are self‐tuned using the improved salp swarm algorithm due to the difficulty of adjusting them manually. Simulation and experimental results demonstrate that the proposed control method exhibits good convergence, no overshoot, minimal buffeting, and strong robustness against uncertain factors like load disturbances. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]