skip to main content


Title: Simultaneous Detection and Estimation of False Data Injection Attacks in Cyber-Physical Battery Systems using a Learning Observer
This work is to present a learning observer-based method for simultaneous detection and estimation of false data injection attacks (FDIAs) to the cyber-physical battery systems. The original battery system in a state-space formulation is transformed into two separate subsystems: one contains both disturbances and the FDIAs and the second one is free from disturbances but subject to FDIAs. A learning observer is then designed for the second subsystem such that the FDIA signals can be estimated and further detected without being affected by the disturbances. This makes the proposed learning observer-based detection and estimation method is robust to disturbances and false declaration of FDIAs can be avoided. Another advantage of the proposed method is that the computing load is low because of the design of a reduced-order learning observer. With a three-cell battery string, a simulation study is employed to verify the effectiveness of proposed detection and estimation method for the FDIAs.  more » « less
Award ID(s):
2153858
NSF-PAR ID:
10490766
Author(s) / Creator(s):
; ;
Publisher / Repository:
IEEE
Date Published:
Page Range / eLocation ID:
1 to 5
Format(s):
Medium: X
Location:
Rome, Italy
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Accurate tracking of the internal electrochemical states of lithium-ion battery during cycling enables advanced battery management systems to operate the battery safely and maintain high performance while minimizing battery degradation. To this end, techniques based on voltage measurement have shown promise for estimating the lithium surface concentration of active material particles, which is an important state for avoiding aging mechanisms such as lithium plating. However, methods relying on voltage often lead to large estimation errors when the model parameters change during aging. In this paper, we utilize the in-situ measurement of the battery expansion to augment the voltage and develop an observer to estimate the lithium surface concentration distribution in each electrode particle. We demonstrate that the addition of the expansion signal enables us to correct the negative electrode concentration states in addition to the positive electrode. As a result, compared to a voltage only observer, the proposed observer can successfully recover the surface concentration when the electrodes' stoichiometric window changes, which is a common occurrence under aging by loss of lithium inventory. With a 5% shift in the electrodes' stoichiometric window, the results indicate a reduction in state estimation error for the negative electrode surface concentration. Under this simulated aged condition, the voltage based observer had 9.3% error as compared to the proposed voltage and expansion observer which had 0.1% error in negative electrode surface concentration. 
    more » « less
  2. The problem of sensor placement for second order infinite dimensional systems is examined within the context of a disturbance-decoupling observer. Such an observer takes advantage of the knowledge of the spatial distribution of disturbances to ensure that the resulting estimation error dynamics are not affected by the temporal component of the disturbances. When such an observer is formulated in a second order setting, it results in a natural observer. Further, when the natural observer is combined with a disturbance decoupling observer, the necessary operator identities needed to ensure the well-posedness of the observer, are expressed in terms of the stiffness, damping, input and output operators. A further extension addresses the question of where to place sensors so that the resulting natural disturbance decoupling observer is optimal with respect to an appropriately selected performance measure. This paper proposes this performance measure which is linked to the mechanical energy of second order infinite dimensional systems. The proposed sensor optimization is demonstrated by a representative PDE in a second order setting. 
    more » « less
  3. Abstract Road profile information can be utilized to enhance vehicle control performance, passenger ride comfort, and route planning and optimization. Existing road-profile estimation algorithms are mainly based on one single vehicle, which are usually susceptible to modeling uncertainties and measurement noises. This technical brief proposes a new cascaded learning framework that utilizes multiple heterogeneous vehicles to achieve enhanced estimation. In this framework, each individual vehicle first performs a local estimation via a standard disturbance observer (DOB) while traversing a considered road segment. Then learning filters are designed to dynamically connect the vehicles, and the preliminary estimates from one vehicle are utilized to generate the learning signal for another. For each vehicle, a heterogeneous learning signal is produced and added to its estimation loop for estimating enhancement, through which the estimations are improved over multiple iterations. Extensive numerical studies are carried out to validate the effectiveness of the proposed method with promising results demonstrated. 
    more » « less
  4. Abstract Background

    Lung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin‐sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities.

    Purpose

    The standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error‐prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection.

    Methods

    A robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI) dataset are used for training, validation, and testing.

    Results

    Using only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre‐defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions.

    Conclusions

    A pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.

     
    more » « less
  5. The lithium iron phosphate (LFP) battery has more nonlinear characteristic than other battery type. For this reason, when we use electrical equivalent circuit model and the extended Kalman filter (EKF) for estimating the SOC, the estimation performance can be decreased in the nonlinear region. This paper proposes an advance estimation method of state of charge (SOC) for lithium iron phosphate (LFP) batteries. To improve the model accuracy, this paper utilizes the nonlinear observer for identifying the internal parameters of batteries. Furthermore, to reduce the nonlinear effect of the LFP batteries, this paper recast the Kalman process. Therefore, through the proposed method, the performance of SOC estimation can be more accurate and the computational burden is decreased when we apply the embedded system. 
    more » « less