Search

Laser-assisted microcutting (LAMC) is a feasible technique for precision machining of amorphous alloys. However, due to the significant difference in deformation characteristics between amorphous and crystalline alloys, the research on LAMC of crystalline alloys cannot be directly used to explain the phenomenon of amorphous alloys. This paper studies the surface defect generation process in ultraprecision machining of Ni-P amorphous alloy by stepped microcutting. It is found that LAMC can greatly reduce the accumulation of elastic potential energy and the deformation zone, thus suppressing the generation of in-plane chipping and edge chipping. LAMC experiments of Ni-P amorphous alloy with different laser irradiation power show that the laser assisted temperature should be controlled around Tg.

NiP coating with an amorphous structure is a commonly used mold material for manufacturing resin optical components. However, due to the inhomogeneous deformation characteristics of amorphous alloys, chippings and burrs are easily produced at the edge of microstructures. Laser-assisted microcutting has proven to effectively inhibit the generation of these defects but the evolution of chip-deformation mechanisms with different laser power remains to be explored. In this study, a simulation of the temperature field under nanosecond laser irradiation was conducted and the laser-assisted cutting of NiP was considered, using the same irradiation parameters. Through the analysis of chip morphology under different conditions, it is found that the temperature in the deformation zone mainly affects the morphology of the secondary shear bands but has no effect on the number of nucleation in the primary and secondary shear bands. The proper temperature in the shear deformation zone can improve the deformation ability of the secondary shear band, thus making the shearing process more stable. This research will prove helpful to understand the material deformation mechanisms to guide the selection of laser parameters in the laser assisted cutting of amorphous alloy.

The accurate estimation of state of charge (SOC) and state of health (SOH) of lithium-ion battery is crucial to ensure the safe and stable operation of the battery. In this paper, a data-driven model framework based on deep learning for estimating SOC and SOH is proposed, which mainly consists of long short-term memory (LSTM) neural network and back propagation (BP) neural network. The switch between SOC estimation model and SOH estimation model can be realized by adjusting the output mode of LSTM. When estimating SOC, the LSTM is set to have corresponding output at each input. The model takes 10 consecutive voltage sampling points as input and the estimated value of SOC at the last sampling moment as output. When estimating SOH, the LSTM is set to have a corresponding output only at the last input. The model takes the sequence of 150 sampling points on the charging voltage curve as input and the SOH value at the current cycle as output. Experiments are carried out on the Oxford battery degradation dataset, and the results show that the proposed model framework can obtain accurate and reliable estimates of SOC and SOH.

State of charge (SOC) estimation of lithium-ion batteries is a problem of time series. In deep learning methods, both convolutional neural network (CNN) and recurrent neural network (RNN) can be used to solve such problems. In this paper, based on deep learning, a hybrid neural network model is proposed to estimate the SOC of lithium-ion batteries by taking the sequence of sampling points of voltage, current and temperature as input. The model is mainly composed of three modules, namely, convolutional module, ultra-lightweight subspace attention mechanism (ULSAM) module and the gated recurrent unit (GRU) module. Convolutional module and ULSAM module are responsible for extracting the feature information from the sequence of sampling points and outputting feature maps. GRU module is responsible for processing the sequences of the feature maps and outputting the value of SOC. The proposed model is tested on the public NASA Randomized Battery Usage dataset and Oxford Battery Degradation dataset. The experimental results show that the proposed model can obtain a relatively accurate SOC estimation at unknown aging state and complex operating conditions.