Hybrid State Estimation–A Contribution Towards Reliability Enhancement of Artificial Neural Network Estimators

Sieberg, Philipp Maximilian; Blume, Sebastian; Reicherts, Sebastian; Maas, Niko; Schramm, Dieter

doi:10.1109/tits.2021.3055800

Cited by 9 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KF can also generate a sufficiently large dataset from a relatively smaller set of accurate data points, eliminating any potential uncertainty associated with the rootkit's data collection abilities (which may affect training of the VDDM). The hybrid estimator -combining KF and ANN -improves prediction accuracy and convergence speed when compared with traditional KF/NN approaches [20], [21]. The steps involved in the generation of the training and test datasets for the ANN are described below.…”

Section: A Vddm: Target Identification and State Predictionmentioning

confidence: 99%

Behind Closed Doors: Process-Level Rootkit Attacks in Cyber-Physical Microgrid Systems

Rath¹,

Zografopoulos²,

Vergara³

et al. 2022

Preprint

View full text Add to dashboard Cite

Embedded controllers, sensors, actuators, advanced metering infrastructure, etc. are cornerstone components of cyber-physical energy systems such as microgrids (MGs). Harnessing their monitoring and control functionalities, sophisticated schemes enhancing MG stability can be deployed. However, the deployment of 'smart' assets increases the threat surface. Power systems possess mechanisms capable of detecting abnormal operations. Furthermore, the lack of sophistication in attack strategies can render them detectable since they blindly violate power system semantics. On the other hand, the recent increase of process-aware rootkits that can attain persistence and compromise operations in undetectable ways requires special attention. In this work, we investigate the steps followed by stealthy rootkits at the process level of control systems pre-and post-compromise. We investigate the rootkits' precompromise stage involving the deployment to multiple system locations and aggregation of system-specific information to build a neural network-based virtual data-driven model (VDDM) of the system. Then, during the weaponization phase, we demonstrate how the VDDM measurement predictions are paramount, first to orchestrate crippling attacks from multiple system standpoints, maximizing the impact, and second, impede detection blinding system operator situational awareness.

show abstract

Section: A Vddm: Target Identification and State Predictionmentioning

confidence: 99%

Behind Closed Doors: Process-Level Rootkit Attacks in Cyber-Physical Microgrid Systems

Rath¹,

Zografopoulos²,

Vergara³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to the central predictive control, this also includes the generation of reference trajectories representing the control targets, the simulation of the actuators with regard to a realistic mapping, as well as the implementation of state estimators, which estimate the states necessary for the control not determined by sensors. Examples for the implementation of these state estimators are presented in [19][20][21]. The implementation of all algorithms is done in MATLAB & Simulink.…”

Section: Simulation Frameworkmentioning

confidence: 99%

Central Non-Linear Model-Based Predictive Vehicle Dynamics Control

Sieberg

Schramm

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Considering automated driving, vehicle dynamics control systems are also a crucial aspect. Vehicle dynamics control systems serve as an important influence factor on safety and ride comfort. By reducing the driver’s responsibility through partially or fully automated driving functions, the occupants’ perception of safety and ride comfort changes. Both aspects are focused even more and have to be enhanced. In general, research on vehicle dynamics control systems is a field that has already been well researched. With regard to the mentioned aspects, however, a central control structure features sufficient potential by exploiting synergies. Furthermore, a predictive mode of operation can contribute to achieve these objectives, since the vehicle can act in a predictive manner instead of merely reacting. Consequently, this contribution presents a central predictive control system by means of a non-linear model-based predictive control algorithm. In this context, roll, self-steering and pitch behavior are considered as control objectives. The active roll stabilization demonstrates an excellent control quality with a root mean squared error of 7.6953×10−3 rad averaged over both validation maneuvers. Compared to a vehicle utilizing a conventional control approach combined with a skyhook damping, pitching movements are reduced by 19.75%. Furthermore, an understeering behavior is maintained, which corresponds to the self-steering behavior of the passive vehicle. In general, the central predictive control, thus, increases both ride comfort and safety in a holistic way.

show abstract

“…Unscented transformation [24,25] is a powerful tool to estimate the statistics of a random variable that undergoes a nonlinear transformation [26] and is used in many applications ranging from sensor fusion for state estimation [27] to an unscented Kalman observer [28]. Moreover, in recent studies, Sieberg et al combined an artificial neural network with confidence level adjustment and presented a hybrid state estimation structure using unscented transformation [29]. We borrowed this useful stochastic tool to make informed choices on initial conditions for the stochastic analysis simulations.…”

Section: Introductionmentioning

confidence: 99%

Stochastic stability analysis of legged locomotion using unscented transformation

Er,

Ankarali

2023

Bioinspir. Biomim.

View full text Add to dashboard Cite

In this manuscript, we present a novel method for estimating the stochastic stability characteristics of metastable legged systems using the unscented transformation. Prior methods for stability analysis in such systems often required high-dimensional state space discretization and a broad set of initial conditions, resulting in signiﬁcant computational complexity. Our approach aims to alleviate this issue by reducing the dimensionality of the system and utilizing the unscented transformation to estimate the output distribution. This technique allows us to account for multiple sources of uncertainty and high-dimensional system dynamics, while leveraging prior knowledge of noise statistics to inform the selection of initial conditions for experiments. As a result, our method enables the eﬃcient assessment of controller performance and analysis of parametric dependencies with fewer experiments. To demonstrate the eﬃcacy of our proposed method, we apply it to the analysis of a one-dimensional hopper and an underactuated bipedal walking simulation with a hybrid zero dynamics controller.

show abstract

Hybrid State Estimation–A Contribution Towards Reliability Enhancement of Artificial Neural Network Estimators

Cited by 9 publications

References 25 publications

Behind Closed Doors: Process-Level Rootkit Attacks in Cyber-Physical Microgrid Systems

Behind Closed Doors: Process-Level Rootkit Attacks in Cyber-Physical Microgrid Systems

Central Non-Linear Model-Based Predictive Vehicle Dynamics Control

Stochastic stability analysis of legged locomotion using unscented transformation

Contact Info

Product

Resources

About