Refine
Document Type
- Article (3)
Language
- English (3)
Has Fulltext
- yes (3)
Keywords
- All-Wheel Drive (1)
- Autoclave (1)
- Autoklav (1)
- Automotive (1)
- Gaseous hydrogen (1)
- Hydrogen sorption curves (1)
- Hydrogen uptake (1)
- LSTM (1)
- Lithium-Ionen-Akkumulator (1)
- Martensitic stainless steel (1)
Remaining-useful-life (RUL) prediction of Li-ion batteries is used to provide an early indication of the expected lifetime of the battery, thereby reducing the risk of failure and increasing safety. In this paper, a detailed method is presented to make long-term predictions for the RUL based on a combination of gated recurrent unit neural network (GRU NN) and soft-sensing method. Firstly, an indirect health indicator (HI) was extracted from the charging processes using a soft-sensing method that can accurately describe power degradation instead of capacity. Then, a GRU NN with a sliding window was applied to learn the long-term performance development. The method also uses a dropout and early stopping method to prevent overfitting. To build the models and validate the effectiveness of the proposed method, a real-world NASA battery data set with various battery measurements was used. The results show that the method can produce a long-term and accurate RUL prediction at each position of the degradation progression based on several historical battery data sets.
Feasibility Study of Wheel Torque Prediction with a Recurrent Neural Network Using Vehicle Data
(2023)
In this paper, we present a feasibility study on predicting the torque signal of a passenger car with the help of a neural network. In addition, we analyze the possibility of using the proposed model structure for temperature prediction. This was carried out with a neural network, specifically a three-layer long short-term memory (LSTM) network. The data used were real road load data from a Jaguar Land Rover Evoque with a Twinster gearbox from GKN. The torque prediction generated good results with an accuracy of 55% and a root mean squared error (RMSE) of 49 Nm, considering that the data were not generated under laboratory conditions. However, the performance of predicting the temperature signal was not satisfying with a coefficient of determination (R2) score of −1.396 and an RMSE score of 69.4 °C. The prediction of the torque signal with the three-layer LSTM network was successful but the transferability of the network to another signal (temperature) was not proven. The knowledge gained from this investigation can be of importance for the development of virtual sensor technology.
Hydrogen is nowadays in focus as an energy carrier that is locally emission free. Especiallyin combination with fuel-cells, hydrogen offers the possibility of a CO2neutral mobility, providedthat the hydrogen is produced with renewable energy. Structural parts of automotive componentsare often made of steel, but unfortunately they may show degradation of the mechanical propertieswhen in contact with hydrogen. Under certain service conditions, hydrogen uptake into the appliedmaterial can occur. To ensure a safe operation of automotive components, it is therefore necessary toinvestigate the time, temperature and pressure dependent hydrogen uptake of certain steels, e.g., todeduct suitable testing concepts that also consider a long term service application. To investigate thematerial dependent hydrogen uptake, a tubular autoclave was set-up. The underlying paper describesthe set-up of this autoclave that can be pressurised up to 20 MPa at room temperature and can beheated up to a temperature of 250◦C, due to an externally applied heating sleeve. The second focusof the paper is the investigation of the pressure dependent hydrogen solubility of the martensiticstainless steel 1.4418. The autoclave offers a very fast insertion and exertion of samples and thereforehas significant advantages compared to commonly larger autoclaves. Results of hydrogen chargingexperiments are presented, that were conducted on the Nickel-martensitic stainless steel 1.4418.Cylindrical samples 3 mm in diameter and 10 mm in length were hydrogen charged within theautoclave and subsequently measured using thermal desorption spectroscopy (TDS). The resultsshow how hydrogen sorption curves can be effectively collected to investigate its dependence ontime, temperature and hydrogen pressure, thus enabling, e.g., the deduction of hydrogen diffusioncoefficients and hydrogen pre-charging concepts for material testing.