Observer-based fault estimation in steer-by-wire vehicle

Đorđević, Vladimir; Stojanović, Vladimir; Prsic, Dragan; Dubonjić, Ljubiśa; Menezes, Morato

doi:10.5937/engtoday2201007d

Cited by 13 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method is very simple and easy to implement in industrial practice. This gives it a huge advantage compared to modern methods that require the order of the controller to be at least equal to the order of the process [4][5][6]12]. This makes these methods…”

Section: Introductionmentioning

confidence: 99%

PD controller design for a system of a valve controlled hydromotor

Dubonjić,

Prodanović,

Stojanović

et al. 2023

Engineering Today

Self Cite

View full text Add to dashboard Cite

PD controller design methodology based on D-decomposition is considered in this paper. The method consists in tuning two parameters of a controller: proportional (P) and differential (D). The method was applied to a hydromotor controlled by a valve according to the position of the valve's piston. The results obtained in this paper show the good performance of the automatic control system in comparison with other methods of controller design and other controllers designed with the same method on the valve controlled hydromotor system.

show abstract

Section: Introductionmentioning

confidence: 99%

PD controller design for a system of a valve controlled hydromotor

Dubonjić,

Prodanović,

Stojanović

et al. 2023

Engineering Today

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to handle such events in future, we can find several approaches in literature. Some of the methods include observer fault estimation based on sensors [ 8 ] , nature optimal control systems [ 9 ] and predictive control models [ 10 ] . All the approaches add a layer to the system that is supposed to detect any faulty behavior of the system.…”

Section: Introductionmentioning

confidence: 99%

Interpretable AI for bio-medical applications

Sathyan¹,

Weinberg²,

Cohen³

2022

Complex Eng Syst

View full text Add to dashboard Cite

This paper presents the use of two popular explainability tools called Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) to explain the predictions made by a trained deep neural network. The deep neural network used in this work is trained on the UCI Breast Cancer Wisconsin dataset. The neural network is used to classify the masses found in patients as benign or malignant based on 30 features that describe the mass. LIME and SHAP are then used to explain the individual predictions made by the trained neural network model. The explanations provide further insights into the relationship between the input features and the predictions. SHAP methodology additionally provides a more holistic view of the effect of the inputs on the output predictions. The results also present the commonalities between the insights gained using LIME and SHAP. Although this paper focuses on the use of deep neural networks trained on UCI Breast Cancer Wisconsin dataset, the methodology can be applied to other neural networks and architectures trained on other applications. The deep neural network trained in this work provides a high level of accuracy. Analyzing the model using LIME and SHAP adds the much desired benefit of providing explanations for the recommendations made by the trained model.

show abstract