An accurate state of charge (SOC) estimation depends on an accurate battery model. The influence of nonlinear and unstable interference factors makes the accurate SOC estimation difficult. To obtain an accurate battery model, a method based on the NARX (nonlinear autoregressive network with exogenous inputs) recurrent neural network and moving window method is proposed. This paper improves the accuracy, modelling speed and robustness of SOC estimation from the following three aspects. First, to overcome the excessive reliance on the amount of data in the model training process, the NARX recurrent neural network is used to establish the battery model. NARX (nonlinear autoregressive with external input) recurrent neural network with the delay and feedback functions can keep the input and output of a previous moment and add it to the calculation of the next moment. Therefore, better estimation results are achieved using a small amount of data; second, the moving window method is used against the gradient explosion and the gradient vanishing that may occur in the NARX model training process. Third, by comparing it with other methods under different working conditions and different temperatures, the validity of the proposed model is verified. The results indicate that the proposed model has a higher accuracy and speed of the SOC estimation. The RMSE performance of the proposed model is reduced by approximately 65%, and the execution time is shortened by approximately 50%.

Force measurement is widely applied in many applications. Resonant force sensors are featured with high accuracies, high resolutions, and long-term stabilities. In this paper, we report a probe-type high-precision force sensor based on a quartz resonator. The scale factor of our sensor is 161.5 mHz μN ⁻¹ and the bias stability of the sensor is 20 ppb (parts per billion) for an averaging time of 0.2 s. A comprehensive test showed that the nominal theoretical resolution of our sensor was 5 nN, and the repeated stability of our sensor has been proven by several controlled tests. With its large measurement range of 50 mN, the dynamic range of the sensor is up to 140 dB.

Hot in-place recycling allows the rehabilitation of worn asphalt pavement with minimal resources. However, it is limited by the heating rate of asphalt pavement. Temperature field distribution was calculated and analyzed in traditional single-stage heating technology (SHT) with constant temperature heating mode. Multi-stage heating technology (MHT) was proposed to improve the heating rate by decreasing the depth to which the asphalt pavement was heated at a given time. The asphalt pavement temperature fields were calculated for SHT and MHT. The calculation results accurately described the temperature field of the asphalt pavement, and the heating rate of MHT was over half that of SHT.