Aiming at the problem that the vibration signals in train operation are complex and nonlinear, and the information of single channel signal is incomplete, a fault diagnosis method of yaw damper based on multi-channel signal fusion on car body and bogie was proposed. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was performed on the signals of multiple train channels, and the intrinsic mode function (IMF) was extracted to compose the feature set of refined composite multiscale dispersion entropy. Secondly, kernel principal component analysis (KPCA) was used to reduce the dimensionality of the extracted feature set. Finally, the optimal feature subset was inputted into the snake optimized kernel extreme learning machine (SO-KELM) to diagnose the yaw damper fault types. The experimental results show that the multi-channel fusion feature set optimized by kernel principal component analysis can accurately reflect the signal characteristics of different fault types of yaw damper, and realize the fault diagnosis of yaw damper. The superiority of this method is verified by comparing with other models.

Compressed air energy storage, as a new energy storage technology, plays an important role in peak shaving and valley filling. Based on the compressed air energy storage with abandoned oil wellbores, a pipeline-wellbore gas storage chamber, that is, the storage space was composed of above ground pipelines and underground wellbores, was proposed. Its inflation process was simulated, with a focus on analyzing the thermodynamics and flow characteristics of the internal gas. The results showed that with compressed gas flowed into the pipeline wellbore gas storage chamber, the gas temperature rapidly increased under the heating effect of the high-temperature wellbore wall. Subsequently, the temperature of the gas became slightly higher than that of the wall, at this point, a heat release of the gas to the wall. The gas temperature and heat dissipation tended to remain stable until the gas storage pressure rose to about 3 MPa. Due to the presence of geothermal gradient, there were significant differences in gas characteristics in different areas of the underground wellbore during the inflation process. As the depth of the wellbore increased, gas flow rate, density, and frictional resistance decreased. With the increase of the gas storage pressure, the differences in the gas flow rate and frictional resistance in different areas diminished. The results of this study provide significant theoretical insights that can effectively inform the practical application of compressed air energy storage systems, particularly those that employ underground wellbores as the repository for gas storage.

To address the issue that traditional fault diagnosis methods struggle to accurately diagnose faults in the nuclear reactor coolant system (RCS) of nuclear power plants under uncertain conditions, a dynamic fuzzy radial basis function neural network (DFRBFNN) model was established for RCS fault diagnosis following these steps. First, based on the fault types and sample data of the RCS, the initial structure of the DFRBFNN model was determined. Then, using the radial basis function neural network method, the initial DFRBFNN model for RCS fault diagnosis was constructed, and a random initialization method was applied to initialize the connection weights from the defuzzification layer to the output layer of the initial DFRBFNN model. Finally, the error reduction rate method was used to adjust the structure and parameters of the initial DFRBFNN model, resulting in the final DFRBFNN model for RCS fault diagnosis. The established model was applied to diagnose loss of coolant, flow loss, and steam generator tube rupture accidents, and its performance was compared with traditional fault diagnosis models to verify its effectiveness. The research shows that the constructed DFRBFNN model can accurately diagnose RCS faults under uncertain conditions.

In order to meet the requirements of high-voltage DC circuit breakers for rapidity actuation of their actuating mechanisms, a new electromagnetic repulsion mechanism was designed for 40.5 kV vacuum circuit breaker, which had high breaking and closing speeds and was suitable for quick disconnection. It consisted of a coil-plate and a double-coil mechanism connected in series.Firstly, the electromagnetic field simulation was carried out by the finite element method, the feasibility of the mechanism was initially verified by analyzing the electromagnetic repulsion,displacement/time characteristics and velocity/time characteristics. Then, the single-variable method was used to simulate and analyze its motion characteristics. the law of the influence of each parameter on the motion characteristics was obtained, and the optimization parameters were determined. Finally, in order to reduce the tripping bounce of the long-stroke fast electromagnetic repulsion mechanism, an electromagnetic buffer was designed. the effects of buffer current input time and buffer driving circuit parameters on buffer characteristics were analyzed. The results show that the new electromagnetic repulsion mechanism combines the advantages of the fast response of the coil-plate mechanism and the high drive efficiency of the double-coil mechanism,with its short response time, large motion speed and short full stroke time, and meet the need of quick disconnection. Under the parameter conditions of 3 500 μF capacitance and 1 200 V for the driving circuit and buffer circuit capacitance 3 500 μF capacitance and 1 300 V for the buffer circuit, the full travel time of the designedelectromagnetic repulsion mechanism is only 2.18 ms.

Aiming at obvious load fluctuation trend, strong randomness and low accuracy caused by unreasonable parameter values of the prediction model involved into the power load forecasting process, a combined prediction model composing of ALIF (adaptive local iterative filtering), VMD (variational mode decomposition), NGO (northern goshawk optimization) and CNN-LSTM (convolutional neural networks - long short-term memory) was established. Firstly, CCM (convergent cross-mapping) method was used to identify the key factors affecting the power load. Secondly, an innovative combination of ALIF, NGO-based VMD and FE (fuzzy entropy) was employed for combinatorial decomposition and necessary recombination of original load sequence. Next, based on the modal components generated after decomposition and recombination, combined with optimal hyperparameter combination of CNN-LSTM determined by NGO method, an NGO-CNN-LSTM day-ahead power load combination prediction model with the high prediction accuracy, short training time and fast convergence speed was formulated. Compared with other benchmark models, the obtained results demonstrated that the proposed model has the better adaptability and prediction accuracy, and can provide important technical support for the safe, reliable and economical operation of power system.

The estimation of the state of health (SOH) for lithium-ion batteries is considered crucial for ensuring the safe and stable operation of battery management system. However, the accurate estimation of SOH has been a challenge due to the capacity regeneration phenomenon during the discharge process of lithium-ion batteries. To improve estimation accuracy, a hybrid model based on variational mode decomposition (VMD) and bidirectional long short-term memory network with attention mechanism (BiLSTM-ATT) was proposed. First, the battery capacity was decomposed using the VMD algorithm, producing a set of stable sub-sequences. Then, permutation entropy was introduced to reconstruct the sub-sequences to reduce computational complexity. The reconstructed sequences were input into the BiLSTM-ATT model, and feature weights were assigned by the attention mechanism. The SOH values were trained and estimated by the BiLSTM model. Finally, the complete SOH estimation result was obtained by summing all estimated values. Validation was performed using the CS2_36, CS2_38, and CX2_35 datasets from the CALCE lithium battery dataset. The results show that the proposed algorithm maintains a root mean square error within 0.6% and a mean absolute error within 0.4%, which demonstrates higher accuracy and performance compared to other estimation models.

In order to solve the problems of the traditional interactive multiple model (IMM) algorithm in vehicle target tracking, such as the model probability change is not obvious and the tracking accuracy is insufficient, an improved adaptive IMM-UKF(unscented Kalman filter) algorithm was proposed. Firstly, the vehicle motion model was established by using uniform speed straight line, uniform acceleration straight line and uniform turning, and the vehicle target was tracked by unscented Kalman filter. Then, the probability change rate of sub model was used as the correction parameter of IMM algorithm, and different correction strategies were adopted for the main diagonal and non main diagonal elements of Markov matrix. Finally, the decision window was set to modify the main diagonal element of the normalized Markov matrix to expand the probability of matching model. The results show that the probability of the improved algorithm model changes more obviously, and the root mean square errors of position and velocity are less than the original algorithm, which effectively improves the tracking accuracy.

In view of the high cost of controlling all the nodes in the traffic network, a pinning control framework for urban traffic network analysis and control network in the case of limited resources were constructed by this paper, and a new pinning control algorithm for urban traffic network was proposed.By using the mutual coupling and containment relationship between nodes and controlling some key nodes in the road network, the expected behavior of the whole network was guaranteed, and the limitation that the system consumes too much computing and control resources were effectively solved.The control input was set as the variation of the duration of the green light, a new pinning controller was designed, and the conditions for effectively ensuring the stability of the urban road traffic network are proposed.Through the simulation analysis, the signal control method proposed can make the urban road traffic network achieve the desired state, and effectively improve the utilization of road resources in the case of limited infrastructure and control costs.

The high-precision fault diagnosis of cross modal high-dimensional fault data under unsupervised conditions is a challenging problem. To address this issue, a rotating machinery fault diagnosis method based on unsupervised cross-modal Euler discriminant space (UCEDS) was proposed. In this method, cross-modal fault data samples were mapped to Euler representations through cosine metrics to enhance the differences and separability between different types of fault samples. Then, an unsupervised cross modal Euler discriminant space learning model was constructed in this space, and the analytical solution of the model was theoretically derived. This model not only considered the local neighborhood structure of fault samples, but also effectively discovered the local structural information of complex and nonlinear fault feature samples. At the same time, on the basis of cross modal consistent discriminative fusion, it further improved the complementarity between low dimensional discriminative feature subsets. Targeted experiments on the Paderborn fault bearing dataseht showed that the proposed UCEDS method had superior fault diagnosis and classification performance.

To tackle the computational cost and registration time challenges in traditional point cloud registration methods like ICP (iterative closest point) such as LIO-SAM (tightly-coupled lidar inertial odometry via smoothing and mapping) and newer models utilizing deep neural networks such as HRegNet(hierarchical registration network), a lightweight and real-time HKRNet (hierarchical kcpstack registration network) network model was proposed. The model was developed by thoroughly studying the HRegNet neural network point cloud registration framework. Initially, a combined filtering approach involving point cloud voxelization and Gaussian threshold downsampling was used to remove redundant points from ground radar scans, reducing the point count from around 130 000 to about 70 000. Subsequently, the computationally intense KNN (K-nearest neighbors) point cloud clustering algorithm within the HRegNet model was enhanced by optimizing it to a KD-Tree (K-dimensional tree) algorithm, resulting in a 25% improvement in processing speed while upholding accuracy. Lastly, to address high memory usage and low computational efficiency of the convolutional modules in the model, a lightweight convolutional module leveraging tensor decomposition and a hierarchical singular value decomposition algorithm was introduced. This leaded to a compressed model size of 86.1% of the original and a decrease of 61.2% in computational cost. The outcomes indicate that the HKRNet network, in comparison to the HRegNet network, can reduce registration time by 40% with minimal loss of accuracy, achieving a single registration time not exceeding 84ms, thus meeting real-time registration requirements.