Fault Frequency Identification of Rolling Bearing Using Reinforced Ensemble Local Mean Decomposition

The vibration signal of rolling bearing exhibits the characteristics of energy attenuation and complex time-varying modulation caused by the transmission with multiple interfaces and complex paths. In view of this, strong ambient noise easily masks faulty signs of rolling bearings, resulting in inaccurate identification or even totally missing the real fault frequencies. To overcome this problem, we propose a reinforced ensemble local mean decomposition method to capture and screen the essential faulty frequencies of rolling bearing, further boosting fault diagnosis accuracy. Firstly, the vibration signal is decomposed into a series of preliminary features through ensemble local mean decomposition, and then the frequency components above the average level are energy-enhanced. In this way, principal frequency components related to rolling bearing failure can be identified with the fast spectral kurtosis algorithm. Finally, the efficacy of the proposed approach is verified through both a benchmark case and a practical platform. The results show that the selected fault characteristic components are accurate, and the identification and diagnosis of rolling bearing status are improved. Especially for the signals with strong noise, the proposed method still could accurately diagnose fault frequency.

Enhancement of the Moving Horizon Estimation Performance Based on an Adaptive Estimation Algorithm

Although moving horizon estimation (MHE) is a very efficient technique for estimating parameters and states of constrained dynamical systems, however, the approximation of the arrival cost remains a major challenge and therefore a popular research topic. The importance of the arrival cost is such that it allows information from past measurements to be introduced into current estimates. In this paper, using an adaptive estimation algorithm, we approximate and update the parameters of the arrival cost of the moving horizon estimator. The proposed method is based on the least-squares algorithm but includes a variable forgetting factor which is based on the constant information principle and a dead zone which ensures robustness. We show by this method that a fairly good approximation of the arrival cost guarantees the convergence and stability of estimates. Some simulations are made to show and demonstrate the effectiveness of the proposed method and to compare it with the classical MHE.

Distributed Finite-Time Consensus Control of Second-Order Multiagent Systems Subject to Communication Time Delay

This paper studies the consensus problem of a second-order multiagent system (MAS) with fixed communication delay under the structure of leaderless and leader-following systems. By using graph theory and finite-time control scheme, a distributed control protocol is proposed for each agent to reach consensus in a finite time. In practical application, the time delay of states is unavoidable, and for this, the consensus method is supposed to be extended to solve the time-delay problem. Thus, a finite-time consensus protocol with communication time delay is proposed in this paper. Compared with the general consensus method, the reliability and convergence speed of the system are increased by using the finite-time control. In addition, the protocol is distributed, and all agents have only local interactions. Finally, the effectiveness of the proposed protocol is verified by two numerical simulations.

Deep Transfer Learning for Biology Cross-Domain Image Classification

Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning.

A Hybrid Method for SOC Estimation of Power Battery

The accuracy of battery state of charge (SOC) is crucial for solving the problems such as overcharge, overdischarge, and mileage anxiety of electric vehicle power battery. In this study, an SOC estimation method using a hybrid method (HM) based on threshold switching is proposed, which combines the advantages of the extended Kalman filter (EKF) and the ampere hour integration (AHI) to improve the estimation accuracy and convergence speed. First, the parameters of the second-order RC equivalent model are identified using the least square. Then, the equation of EKF for updating the state variable is reconstructed by using the identified parameters to solve the problem of multiple iterations caused by the uncertainty of the initial value. Finally, the difference between the estimated voltage and the sampling voltage is used as the threshold value for switching between the AHI and the EKF to estimate the SOC of the battery. Simulation results show that the estimated SOC error of the proposed algorithm is less than 1.6% and the convergence time is within 70 s. Experiments under different SOC initial values are carried out to prove the advantages of the proposed method.

Obstacle Avoidance Control for Multisteering Mode of Multiaxle Wheeled Robot Based on Trajectory Prediction Strategy

A multiaxle wheeled robot is difficult to be controlled due to its long body and a large number of axles, especially for obstacle avoidance and steering in narrow space. To solve this problem, a multisteering mode control strategy based on front and rear virtual wheels is proposed, and the driving trajectory prediction of the multiaxle wheeled robot is analyzed. On this basis, an obstacle avoidance control strategy based on trajectory prediction is proposed. By calculating the relationship between the lidar points of the obstacle and the trajectory coverage area, the iterative calculation of the obstacle avoidance scheme for the proposed steering is carried out, and the feasible obstacle avoidance scheme is obtained. The mechanical structure, hardware, and software control system of a five-axle wheeled robot are designed. Finally, to verify the effectiveness of the obstacle avoidance strategy, a Z-shaped obstacle avoidance experiment was carried out. The results confirm the effectiveness of the proposed control strategy.

Robust Synchronization Control of Uncertain Fractional-Order Chaotic Systems via Disturbance Observer

This paper studies the synchronization of two different fractional-order chaotic systems through the fractional-order control method, which can ensure that the synchronization error converges to a sufficiently small compact set. Afterwards, the disturbance observer of the synchronization control scheme based on adaptive parameters is designed to predict unknown disturbances. The Lyapunov function method is used to verify the appropriateness of the disturbance observer design and the convergence of the synchronization error, and then the feasibility of the control scheme is obtained. Finally, our simulation studies verify and clarify the proposed method.

Embedding Tangent Space Extreme Learning Machine for EEG Decoding in Brain Computer Interface Systems

In motor imagery brain computer interface system, the spatial covariance matrices of EEG signals which carried important discriminative information have been well used to improve the decoding performance of motor imagery. However, the covariance matrices often suffer from the problem of high dimensionality, which leads to a high computational cost and overfitting. These problems directly limit the application ability and work efficiency of the BCI system. To improve these problems and enhance the performance of the BCI system, in this study, we propose a novel semisupervised locality-preserving graph embedding model to learn a low-dimensional embedding. This approach enables a low-dimensional embedding to capture more discriminant information for classification by efficiently incorporating information from testing and training data into a Riemannian graph. Furthermore, we obtain an efficient classification algorithm using an extreme learning machine (ELM) classifier developed on the tangent space of a learned embedding. Experimental results show that our proposed approach achieves higher classification performance than benchmark methods on various datasets, including the BCI Competition IIa dataset and in-house BCI datasets.

COVID-19 Pandemic Forecasting Using CNN-LSTM: A Hybrid Approach

COVID-19 has sparked a worldwide pandemic, with the number of infected cases and deaths rising on a regular basis. Along with recent advances in soft computing technology, researchers are now actively developing and enhancing different mathematical and machine-learning algorithms to forecast the future trend of this pandemic. Thus, if we can accurately forecast the trend of cases globally, the spread of the pandemic can be controlled. In this study, a hybrid CNN-LSTM model was developed on a time-series dataset to forecast the number of confirmed cases of COVID-19. The proposed model was evaluated and compared with 17 baseline models on test and forecast data. The primary finding of this research is that the proposed CNN-LSTM model outperformed them all, with the lowest average MAPE, RMSE, and RRMSE values on both test and forecast data. Conclusively, our experimental results show that, while standalone CNN and LSTM models provide acceptable and efficient forecasting performance for the confirmed COVID-19 cases time series, combining both models in the proposed CNN-LSTM encoder-decoder structure provides a significant boost in forecasting performance. Furthermore, we demonstrated that the suggested model produced satisfactory predicting results even with a small amount of data.

Prescribed Performance Synchronization Control of Chaotic Systems with Unknown Control Gain Signs

For a class of uncertain nonlinear chaotic systems with unknown control gain signs and saturated input, by means of Nussbaum function, a scheme of finite-time prescribed performance synchronization control is proposed. Here, Nussbaum function is used to eliminate the influence of unknown control gain signs, and fuzzy logic systems are used to estimate unknown functions. Lyapunov theory is used to prove that all synchronization errors converge to a predefined small performance range under the designed control method. Finally, simulation results are provided to illustrate the feasibility of the proposed method.