As the two classical power allocation methods in battery-supercapacitor hybrid energy storage systems, split-frequency methods and power-level methods have been developed separately for many years. In this article, we made an attempt to integrate the advantages of the two methods and proposed an adaptive frequency-split-based quantitative power allocation strategy. First, an adaptive power preallocation is quantitatively determined according to the state of charge (SoC) of batteries and supercapacitors. Then, a windowed fast Fourier transform (FFT)-based power spectrum calculation algorithm is designed to derive the power level corresponding to each sampling frequency. By mapping the preallocated power to the power spectrum, the split frequency is adaptively computed. Finally, the power allocation is implemented through a low-pass filter (LPF) with the derived split frequency. Extensive experiments verify that the proposed method provides an improved performance in suppressing the dc bus voltage fluctuations and protecting batteries when compared with existing methods.

Driving style recognition plays a key role in ensuring driving safety and improving vehicle traffic efficiency. With the development of sensing technology, data-driven methods are more widely uesd to recognize driving style. However, adequately labeling data is difficult for supervised learning methods, while the classification accuracy is not sufficiently approved for unsupervised learning methods. This paper proposes a new driving style recognition method based on Tri-CatBoost, which takes CatBoost as base classifier and effectively utilizes the semi-supervised learning mechanism to reduce the dependency on data labels and improve the recognition ability. First, statistical features were extracted from the velocity, acceleration and jerk signals to fully characterize the driving style. The kernel principal component analysis was used to perform nonlinear feature dimension reduction to eliminate feature coupling. CatBoost is an ensemble of symmetric decision trees whose symmetry structure endows it fewer parameters, faster training and testing, and a higher accuracy. Then, a Tri-Training strategy is employed to integrate the base CatBoost classifiers and fully exploit the unlabeled data to generate pseudo-labels, by which the base CatBoost classifiers are optimized. To verify the effectiveness of the proposed method, a large number of experiments are performed on the UAH DriveSet. When the labeling ratio is 50%, the macro precision of Tri-CatBoost is 0.721, which is 15.7% higher than that of unsupervised K-means, 1.6% higher than that of supervised GBDT, 3.7% higher than that of Self-Training, 0.7% higher than that of Co-training, 1.5% higher than that of random forest, 6.7% higher than that of decision tree, and 4.0% higher than that of multilayer perceptron. The macro recall of Tri-CatBoost is 0.744, which is also higher than other methods. The experimental results fully demonstrate the superiority of this work in reducing label dependency and improving recognition performance, which indicates that the proposed method has broad application prospects.

The remaining useful life estimation has been widely studied for engineering systems. A system commonly works under varying operating conditions, which may affect the system degradation trajectory differently and consequently reduce the accuracy of remaining useful life estimation. In this paper, we propose CNN-XGB with extended time window to tackle this issue. Firstly, the extended time window is created by feature extension and time window processing in data preprocessing. In feature extension, multiple degradation features are extracted by an improved differential method, and these features are appended to the raw data as additional features. To make the time window cover more information for better prognostic accuracy, a time window padding method is used considering the problem of missing data in some samples. Secondly, a convolutional neural network architecture with multichannel 1*1 filter kernel is proposed considering the effect of varying operating conditions. Furthermore, to improve the prognostic robustness and avoid the sensitivity to the abnormal data, convolutional neural network and extreme gradient boosting are fused by model averaging (CNN-XGB). The validity of the proposed method is verified using aero-engine datasets from NASA.

For periodical beacon broadcasting in cellular vehicle-to-everything (C-V2X) networks, a distributed reservation media access control (MAC) protocol, the sensing-based semi-persistent scheduling (SPS), is adopted. However, how to quantify the communication reliability and latency is an open issue, which is critical for low-latency and high-reliability services. In this paper, an analytical model for SPS is presented, based on which the impacts of beacon rate, range settings and system configuration on access collision probability and delay outage probability are quantified. The analytical model provides important insights and guideline to adapt and optimize protocol parameters including the sensing range, transmit power and resource reservation. The enhanced MAC protocol can maintain high-reliability and low-latency services with a wide range of vehicle density. Simulations are conducted to validate the analysis and the results demonstrate that the proposed MAC enhancement solution can reduce collision probability while ensuring the delay outage probability based on service requirements.