State-of-charge (SoC) estimation is indispensable for battery management systems (BMSs). Accurate SoC estimation can improve the efficiency of battery utilization, especially for electric vehicles (EVs). Several kinds of battery SoC estimation approaches have been developed, but a simple and efficient method for battery SoC estimation that can adapt to a variety of lithium-ion batteries is worth exploring. To this end, a recurrent neural network (RNN) model based on a gated recurrent unit (GRU) is presented for battery SoC estimation. The GRU-RNN model can rapidly learn its own parameters by means of an ensemble optimization method based on the Nadam and AdaMax optimizers. The Nadam optimizer is used in the model pre-training phase to find the minimum optimized value as soon as possible, and then the AdaMax optimizer is used in the model fine-tuning phase to further determine the model parameters. To validate the effectiveness and robustness of the proposed method, the GRU-RNN model was trained and tested with three kinds of dynamic loading profiles, and compared with existing SoC estimation methods. The experimental results show that the proposed method dramatically reduces the model training time and increases estimation accuracy.

The state of health is an indicator of battery performance evaluation and service lifetime prediction, which is essential to ensure the reliability and safety of electric vehicles. Although a large number of capacity studies have emerged, there are few simple and effective methods suitable for engineering practice. Hence, a least square support vector regression model with polynomial kernel function is presented for battery capacity estimation. By the battery charging curve, the feature samples of battery health state are extracted. The grey relational analysis is employed for the feature selection, and the K-fold cross-validation is adopted to obtain hyper-parameters of the support vector regression estimation model. To validate this method, the support vector regression estimation model was trained and tested on the battery data sets provided by NASA Prognostics Center of Excellence. The experimental results show that the proposed method only needs some battery feature data, and can achieve high-precision capacity estimation, which indicates that the proposed method shows great efficiency and robustness.

Diesel-natural gas dual fuel engine has gained increasing interesting in recent years because of its excellent power and economy. However, the reliability of the dual fuel engine does not meet the requirements of practical application. The piston maximun temperature (PMT) of the dual fuel engine easily exceeds the security border. In view of this, this paper proposes a method based on the lasso regression to estimate the PMT of the dual fuel engine, so as to real-timely monitor the health state of the dual fuel engine. Specifically, PMTs under some working conditions were offline acquired by the finite element analysis with ANSYS. A model is presented to describe the relationship between the PMT and some indirect engine variables, including NOx emission, excess air coefficient, engine speed, and inlet pressure, and the model parameters are optimized using the lasso regression algorithm, which can be easily implemented by the electronic control unit (ECU). Finally, the model is employed to real-timely estimate the PMT of the dual fuel engine. Experiments reveal that the proposed model produces satisfying predictions with deviations less than 10 °C.

The burgeoning field of large language models (LLMs), exemplified by DALL-E and Stable Diffusion, has made image generation a reality. However, the computationally intensive GPU training these models necessitate incurs substantial financial burdens. Moreover, while a plethora of image datasets are accessible, specialized anime avatar datasets remain elusive and are often entangled in copyright disputes. This scarcity presents a significant research opportunity: developing a cost-effective, user-friendly anime avatar generation technique that circumvents these challenges. This paper introduces a novel method for creating animated avatars, leveraging the deep convolutional generative adversarial network(DCGAN) architecture and enhanced with Self-Attention (SA) and Spectral Normalization (SN), termed the SA+SN-DCGAN. The integration of the SA mechanism into the generator significantly elevates the quality of the output. Meanwhile, the application of SN to the discriminator effectively combats the notorious vanishing or exploding gradients, and thereby diminishing the likelihood of overfitting. Our methodology involved sourcing anime avatars from reputable public domains and standardizing them using OpenCV. A meticulous grid search was employed to fine-tune model hyperparameters. After 300 epochs of rigorous training, the generator and discriminator achieved stable error rates, with the synthesized images closely mirroring the fidelity of authentic avatars. Comparative evaluations against prevailing models underscore the SA+SN-DCGAN method’s superiority in producing highly realistic anime avatars, affirming its exceptional overall performance. This study not only contributes a novel solution to the domain of anime avatar generation but also paves the way for future research in the field.