An Easy-to-Implement Hysteresis Model Identification Method Based on Support Vector Regression

Zhang, Shukuan; Wang, Mingqiao; Zheng, Ping; Qiao, Guofu; Liu, Faliang; Gan, Lei

doi:10.1109/tmag.2017.2702168

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SVR is an expansion of a classical Support Vector Machine (SVM) from pure classification to regression tasks. Similar to SVM it is designed for estimation of high dimensional, nonlinear problems when only a limited number of samples are available [26]. The SVR model implemented in this paper was based on [26].…”

Section: A Preliminary Evaluation Of the Lstmmentioning

confidence: 99%

“…Similar to SVM it is designed for estimation of high dimensional, nonlinear problems when only a limited number of samples are available [26]. The SVR model implemented in this paper was based on [26]. The hyperparameters of the SVR are chosen as follows: penalty C = 10, kernel = Radial Basis Function (RBF) kernel, kernel coefficient γ = 0.1, margin of tolerance = 0.1.…”

Section: A Preliminary Evaluation Of the Lstmmentioning

confidence: 99%

See 1 more Smart Citation

Hysteresis Modeling of Robotic Catheters Based on Long Short-Term Memory Network for Improved Environment Reconstruction

Zhang

Ourak

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Catheters are increasingly being used to tackle problems in the cardiovascular system. However, positioning precision of the catheter tip is negatively affected by hysteresis. To ensure tissue damage due to imprecise positioning is avoided, hysteresis is to be understood and compensated for. This work investigates the feasibility to model hysteresis with a Long Short-Term Memory (LSTM) network. A bench-top setup containing a catheter distal segment was developed for model evaluation. The LSTM was first tested using four groups of test datasets containing diverse patterns. To compare with the LSTM, a Deadband Rate-Dependent Prandtl-Ishlinskii (DRDPI) model and a Support Vector Regression (SVR) model were established. The results demonstrated that the LSTM is capable of predicting the tip bending angle with sub-degree precision. The LSTM outperformed the DRDPI model and the SVR model by 60.1% and 36.0%, respectively, in arbitrarily varying signals. Next, the LSTM was further validated in a 3D reconstruction experiment using Forward-Looking Optical Coherence Tomography (FL-OCT). The results revealed that the LSTM was able to accurately reconstruct the environment with a reconstruction error below 0.25 mm. Overall, the proposed LSTM enabled precise free-space control of a robotic catheter in the presence of severe hysteresis. The LSTM predicted the catheter tip response precisely based on proximal input pressure, minimizing the need to install sensors at the catheter tip for localization.

show abstract

Section: A Preliminary Evaluation Of the Lstmmentioning

confidence: 99%

Section: A Preliminary Evaluation Of the Lstmmentioning

confidence: 99%

Hysteresis Modeling of Robotic Catheters Based on Long Short-Term Memory Network for Improved Environment Reconstruction

Zhang

Ourak

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…10 . Weight vector w , insensitive loss function ε , penalty factor C to minimize training errors, and and are slack variables (Zhang et al 2017 ). …”

Section: Methodology and Thermodynamics Backgroundmentioning

confidence: 99%

Deep learning approach for prediction of exergy and emission parameters of commercial high by-pass turbofan engines

Dursun

Toraman

Aygün

2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

Aviation emissions originated from the fuel burn have been hot topics by engineers and policy-makers due to their harmful effects on the environment and thereby human health as well as sustainability. In this study, it is tried that several emission indexes (EIs) involving CO, HC and NOx as well as fuel flow of several commercial aircraft engines (CAEs) are predicted using support vector regression (SVR) and long short-term memory (LSTM) approaches for take-off phase. Moreover, exergo-environmental parameters involving exergy efficiency (ExEFF), wasted exergy ratio (WExR) and environmental effect factor (EEF) pertinent to CAEs are computed employing thermodynamics laws. While establishing the models, rated thrust, by-pass ratio, overall pressure ratio and combustion type of the CAEs are utilized as the model inputs. According to the findings of emission modelling, the coefficient of determination ( R 2 ) of EI NOx and EI CO of the CAEs is found as 0.929074 and 0.960277 with SVR, whereas their R 2 values are elevated to 0.954878 and 0.989283 with LSTM approach, respectively. However, R 2 of EI HC is determined lower with 0.632280 (by SVR) and 0.651749 (by LSTM). On the other hand, exergo-environmental parameters for the CAEs are estimated with high correctness at both models. Namely, R 2 of ExEFF and EEF regarding the CAEs are computed as 0.991748 and 0.989067 by SVR; however, these are calculated as 0.994785 and 0.992797 by LSTM method. To model these parameters with low error by using significant design variables as model inputs could help in predicting emission and environmental metrics for new engine designs.

show abstract

“…A quadratic programming method 32 is employed to solve Equation ( 3) to obtain the optimal Lagrange multipliers α i and α i Ã . Then the optimal weight vector can be expressed as follows:…”

Section: Svr Modelmentioning

confidence: 99%

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Wang

Liu

2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

An intelligent prediction model of rubber fatigue life considering strain ratios based on the support vector regression (SVR) and an improved sparrow search algorithm (ISSA) is proposed. In order to solve the problem that traditional methods may lead to unsatisfactory prediction results, we establish a prediction model based on SVR. To further improve the prediction accuracy, we utilize the ISSA algorithm to optimize various hyper‐parameters in the model. Fatigue tests of filled natural rubber on dumbbell‐type specimens are performed and applied to verify the effectiveness of the proposed model. The results show that the ISSA optimized SVR (ISSA‐SVR) model is superior in terms of prediction accuracy, convergence speed, and stability compared with SVR models using the grid search or some standard optimization algorithms. Furthermore, comparisons of some published related models demonstrate that the ISSA‐SVR has the most accurate predictive results, which gather within 1.5 times the dispersion lines.

show abstract

An Easy-to-Implement Hysteresis Model Identification Method Based on Support Vector Regression

Cited by 10 publications

References 10 publications

Hysteresis Modeling of Robotic Catheters Based on Long Short-Term Memory Network for Improved Environment Reconstruction

Hysteresis Modeling of Robotic Catheters Based on Long Short-Term Memory Network for Improved Environment Reconstruction

Deep learning approach for prediction of exergy and emission parameters of commercial high by-pass turbofan engines

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Contact Info

Product

Resources

About