Recurrent-neural-network-based unscented Kalman filter for estimating and compensating the random drift of MEMS gyroscopes in real time

2021 ◽  
Vol 147 ◽  
pp. 107057 ◽  
Author(s):  
Dinghua Li ◽  
Jun Zhou ◽  
Yingying Liu
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Real Time ◽  
Recurrent Neural Network ◽  
Unscented Kalman Filter ◽  
Random Drift ◽  
Mems Gyroscopes

scholarly journals Improving the Reliability of Probabilistic Multi-Step-Ahead Flood Forecasting by Fusing Unscented Kalman Filter with Recurrent Neural Network

Water ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 578 ◽  
Author(s):  
Yanlai Zhou ◽  
Shenglian Guo ◽  
Chong-Yu Xu ◽  
Fi-John Chang ◽  
Jiabo Yin
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Recurrent Neural Network ◽  
Unscented Kalman Filter ◽  
Forecast Accuracy ◽  
Flood Forecasting ◽  
Processing Technique ◽  
Data Driven ◽  
Dependence Structure ◽  
Neural Network Approach

It is fundamentally challenging to quantify the uncertainty of data-driven flood forecasting. This study introduces a general framework for probabilistic flood forecasting conditional on point forecasts. We adopt an unscented Kalman filter (UKF) post-processing technique to model the point forecasts made by a recurrent neural network and their corresponding observations. The methodology is tested by using a long-term 6-h timescale inflow series of the Three Gorges Reservoir in China. The main merits of the proposed approach lie in: first, overcoming the under-prediction phenomena in data-driven flood forecasting; second, alleviating the uncertainty encountered in data-driven flood forecasting. Two commonly used artificial neural networks, a recurrent and a static neural network, were used to make the point forecasts. Then the UKF approach driven by the point forecasts demonstrated its competency in increasing the reliability of probabilistic flood forecasts significantly, where predictive distributions encountered in multi-step-ahead flood forecasts were effectively reduced to small ranges. The results demonstrated that the UKF plus recurrent neural network approach could suitably extract the complex non-linear dependence structure between the model’s outputs and observed inflows and overcome the systematic error so that model reliability as well as forecast accuracy for future horizons could be significantly improved.

scholarly journals Huber-Based Robust Unscented Kalman Filter Distributed Drive Electric Vehicle State Observation

Energies ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 750
Author(s):  
Wenkang Wan ◽  
Jingan Feng ◽  
Bao Song ◽  
Xinxin Li
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Degrees Of Freedom ◽  
Unscented Kalman Filter ◽  
State Parameter ◽  
State Observation ◽  
Straight Line ◽  
Distributed Drive Electric Vehicle ◽  
Huber Method ◽  
Yaw Moment

Accurate and real-time acquisition of vehicle state parameters is key to improving the performance of vehicle control systems. To improve the accuracy of state parameter estimation for distributed drive electric vehicles, an unscented Kalman filter (UKF) algorithm combined with the Huber method is proposed. In this paper, we introduce the nonlinear modified Dugoff tire model, build a nonlinear three-degrees-of-freedom time-varying parametric vehicle dynamics model, and extend the vehicle mass, the height of the center of gravity, and the yaw moment of inertia, which are significantly influenced by the driving state, into the vehicle state vector. The vehicle state parameter observer was designed using an unscented Kalman filter framework. The Huber cost function was introduced to correct the measured noise and state covariance in real-time to improve the robustness of the observer. The simulation verification of a double-lane change and straight-line driving conditions at constant speed was carried out using the Simulink/Carsim platform. The results show that observation using the Huber-based robust unscented Kalman filter (HRUKF) more realistically reflects the vehicle state in real-time, effectively suppresses the influence of abnormal error and noise, and obtains high observation accuracy.

Real-Time Signal Denoising Algorithm in Wheel Force Transducer

2014 ◽  
Vol 615 ◽  
pp. 244-247
Author(s):  
Dong Wang ◽  
Guo Yu Lin ◽  
Wei Gong Zhang
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Extended Kalman Filter ◽  
Unscented Kalman Filter ◽  
Force Transducer ◽  
Time Signal ◽  
Signal Denoising ◽  
Observation Function ◽  
Simulation Results ◽  
Wheel Force Transducer

The wheel force transducer (WFT) is used to measure dynamic wheel loads. Unlike other force sensors, WFT is rotating with the wheel. For this reason, the outputs and the inputs of the transducer are nonlinearly related, and traditional Kalman Filter is not suitable. In this paper, a new real-time filter algorithm utilizing Quadrature Kalman Filter (QKF) is proposed to solve this problem. In Quadrature Kalman Filter, Singer model is introduced to track the wheel force, and the observation function is established for WFT. The simulation results illustrate that the new filter outperforms the traditional Unscented Kalman Filter (UKF) and Extended Kalman Filter (EKF).

An FPGA-Based Residual Recurrent Neural Network for Real-Time Video Super-Resolution

2021 ◽  
pp. 1-1
Author(s):  
Kaicong Sun ◽  
Maurice Koch ◽  
Zhe Wang ◽  
Slavisa Jovanovic ◽  
Hassan Rabah ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recurrent Neural Network ◽  
Super Resolution
Sign in / Sign up

Export Citation Format

Share Document