In order to improve the fault-tolerant performance of wheel angle sensor of steer-by-wire (SBW) vehicle, a fault diagnosis and fault-tolerant compensation (FDFTC) strategy for wheel angle sensor of SBW vehicle via extended Kalman filter (EKF) is proposed in this paper. Firstly, the steering motor model, rack and pinion model, vehicle dynamics model and variable transmission ratio model are established. Then, based on the analytical redundancy method, the EKF algorithm is adopted to obtain the wheel angle estimation signal. On this basis, a sensor FDFTC strategy with improved majority voting scheme is proposed, which is composed of fault diagnosis module and fault isolation compensation module. Finally, combined with Matlab/Simulink and Carsim, the estimation results are analyzed under sinusoidal condition and double lane change condition, and the performance of the proposed FDFTC strategy is further verified under the sensor stuck fault condition, deviation fault condition and noise interference condition. The results indicate that the proposed FDFTC strategy can not only accurately diagnose the fault signal, but also reconstruct the correct wheel angle signal, which is of great significance to improve the safety and reliability of SBW vehicle. 

Fault Diagnosis and Fault-Tolerant Compensation Strategy for Wheel Angle Sensor of Steer-by-Wire Vehicle via Extended Kalman Filter

Fault detection in heating, ventilation and air-conditioning (HVAC) systems can effectively prevent equipment damage and system energy loss, and enhance the stability and reliability of system operation. However, existing fault detection strategies have not realized high effectiveness, mainly due to the time-delay characteristics of HVAC system faults and the lack of system-fault operation data. Therefore, aiming at the time delay of system faults and the lack of actual system-fault operation data, this paper proposes a fault detection method that combines a system simulation model and an intelligent detection algorithm. The method first uses the Modelica modeling language to build a scalable simulation model of the system to obtain fault data that are not easily accessible in practice. The long short-term memory-support vector data description (LSTM-SVDD) algorithm is then applied to detect faults in real time by dynamically adjusting the fault residuals according to the absolute difference between the predicted and actual values. The experimental results show that the LSTM-SVDD method improves the average detection accuracy by 9.675% and 9.85% over the classical LSTM network and the extreme gradient boosting (XGBoost) method, respectively, under different fault levels.

/pdf/an-effective-fault-detection-method-for-hvac-systems-using-inz6mukj.pdf

An Effective Fault Detection Method for HVAC Systems Using the LSTM-SVDD Algorithm

Safe and efficient operation of the forced-oxidation system is of importance to the wet flue gas desulfurization (WFGD). However, equipment and system failures are commonly found due to the long-time running, frequent blower switching, and heavy workload etc., especially after the ultra-low emission (ULE) renovation to meet strict emission standard in China. This work develops a fault early detection method to improve the predictive maintenance of the forced-oxidation system including blowers, pipes, and the slurry tank. A model based on long short-term memory (LSTM) network and attention mechanism (AM) is constructed to predict real-time operation parameters and compare with the measured values. Then the sequence probability ratio test (SPRT) is utilized to analyze the prediction-measurement residual and provide automatic and dynamic warning. All the data for model training and prediction are from the build-in distributed control system (DCS) without additional sensors. The LSTM-AM model proves to accurately predict time-dependent and highly relevant parameters. SPRT can sensitively perceive the fault-caused residual deviation while alleviating the noises. Industrial application to the cases in a 50 MW combined heat and power generation plant is then carried out. Results show that the bearing failure of the oxidation blower and branch pipes (immersed in the slurry tank) blockage can be forecast in advance when the incipient degradation occurs. 

An integrated LSTM-AM and SPRT method for fault early detection of forced-oxidation system in wet flue gas desulfurization

A steering actuator is the core component of an autonomous vehicle. Because of noise interference, the extraction of useful fault features for an accurate fault diagnosis of steering actuator becomes an arduous task. This article proposes an adaptive denoising residual network (AD-ResNet) for fault diagnosis of steering actuator with reduced noise interference and improved accuracy. First, a high-complexity model based on long short-term memory (LSTM) is built to estimate redundant signals, and then, fault features are generated by comparing redundant signals with the measured sensor signals. Second, an attention unit is designed to determine the unique set of thresholds for each fault feature. Finally, hard thresholding is embedded in a deep network as a nonlinear transform layer to reduce noise. Simulation experiments were performed at different signal-to-noise ratios (SNRs), and the results confirmed that the proposed method could adaptively denoise the high-noise signals. The proposed method was then validated against a fault dataset that was built using road experiments with an autonomous vehicle, and it achieved an accuracy, a sensitivity, a specificity, and an F1-score of 91.66%, 91.66%, 97.22%, and 0.9159, respectively, averaged over all fault states. The proposed method outperformed the comparison methods in the experiments.

Steering Actuator Fault Diagnosis for Autonomous Vehicle With an Adaptive Denoising Residual Network

A steering actuator is the core component of an autonomous vehicle. Because of noise interference, the extraction of useful fault features for an accurate fault diagnosis of steering actuator becomes an arduous task. This paper proposes an adaptive de-noising residual network (AD-ResNet) for fault diagnosis of steering actuator with reduced noise interference and improved accuracy. First, a high-complexity model based on long short-term memory is built to estimate redundant signals, and then fault features are generated by comparing redundant signals with the measured sensor signals. Second, an attention unit is designed to determines the unique set of thresholds for each fault feature. Finally, hard thresholding is embedded in a deep network as a nonlinear transform layer to reduce noise. Simulation experiments were performed at different signal-to-noise ratios, and the results confirmed that the proposed method could adaptively de-noise the high-noise signals. The proposed method was then validated against a fault dataset that was built using road experiments with an autonomous vehicle, and it achieved an accuracy, a sensitivity, a specificity, and an F1-score of 91.66%, 91.66%, 97.22%, and 0.9159, respectively, averaged over all fault states. The proposed method outperformed the comparison methods in the experiments. 

In order to improve the accuracy of fault detection results, this paper proposes a novel fault detection strategy of vehicle wheel angle signal via long short-term memory network (LSTM) and improved sequential probability ratio test (SPRT). Firstly, a signal estimation method based on data-driven modeling is presented, which fuses the vehicle current status information and adopts the LSTM based on deep learning to estimate the vehicle wheel angle signal. Then, the signal residual sequence is obtained by comparing the estimated wheel angle signal with the measured wheel angle signal. Based on this, the improved SPRT method based on mathematical statistics is used to analyze the signal residual sequence, so as to detect the fault signal timely and accurately. Finally, the accuracy of the estimation results is analyzed under sinusoidal condition, double-lane change condition and sinusoidal sweep frequency condition, and the effectiveness of the fault detection strategy proposed in this paper is further verified under the stuck fault condition and drift fault condition. The results indicate the effectiveness of the proposed fault detection strategy, which is of great significance to improve the safety and reliability of the vehicle.

Feng Chen

Papers

Fault Detection Strategy of Vehicle Wheel Angle Signal via Long Short-Term Memory Network and Improved Sequential Probability Ratio Test