A centralized multi-objective model predictive control for a biventricular assist device: An in silico evaluation

Koh, Vivian Ci Ai; Ho, Yong Kuen; Stevens, Michael C.; Ng, Boon Chiang; Salamonsen, Robert F.; Lovell, Nigel H.; Lim, Einly

doi:10.1016/j.bspc.2018.10.021

Cited by 10 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These controllers generate a high computational burden and rely on accurate rules for different patient conditions, respectively. Other controllers such as model predictive control (MPC) and optimal control need a simplified state-space model that cannot be generalized and modified for different patient conditions [45].…”

Section: Discussionmentioning

confidence: 99%

A Sensorless Control System for an Implantable Heart Pump Using a Real-Time Deep Convolutional Neural Network

Fetanat

Stevens

Hayward

et al. 2021

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable longterm implantable sensors available. In this study, a novel realtime deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.Index Terms-Convolutional neural network, left ventricular assist devices, deep learning, model free adaptive control, physiological control, sensorless control.

show abstract

Section: Discussionmentioning

confidence: 99%

A Sensorless Control System for an Implantable Heart Pump Using a Real-Time Deep Convolutional Neural Network

Fetanat

Stevens

Hayward

et al. 2021

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…By implementing the algorithm proposed, the optimal control inputs and optimal states are obtained after solving the quadratic programming problem (13). Subsequently, the cost of the whole system can be calculated by (12). Additionally, the cost of the entire system is also calculated by adopting algorithm in [35].…”

Section: Numerical Examplementioning

confidence: 99%

“…If the controller fails, however, the entire system will not work properly [10], [11]. In addition, the load of online computing is increased by the huge scale of the system, and the performance of real-time is more difficult to guarantee [12], [13]. Later, the decentralized predictive control have been proposed by some research scholars.…”

Section: Introductionmentioning

confidence: 99%

Distributed Model Predictive Control for Linear Constrained Systems Based on Time-Varying Terminal Sets

Zhu

Xue

2021

IEEE Access

View full text Add to dashboard Cite

A novel distributed model predictive control (DMPC) strategy with time-varying terminal set for linear constrained systems is presented in this paper. To decrease the load of computation of DMPC while ensuring the global optimization, the nominal system is introduced by treating the influence of neighboring subsystems as a bounded disturbance. Then, under the distributed control structure, a distributed predictive control optimization problem containing the nominal state and input can be designed for each subsystem. Furthermore, different from most DMPC approaches, a novel approach to design a terminal constraint set that can be updated in every update time based on the predicted state of the system is proposed. Additionally, the analysis of feasibility and the stability of the proposed DMPC algorithm are described under kinds of the system constraints. Finally, experimental simulation is shown to prove validity by the control scheme in this paper.INDEX TERMS Distributed model predictive control, time-varying terminal constraint set, linear constrained system.

show abstract

A centralized multi-objective model predictive control for a biventricular assist device: An in vitro evaluation

Koh

Pauls

et al. 2020

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

A centralized multi-objective model predictive control for a biventricular assist device: An in silico evaluation

Cited by 10 publications

References 31 publications

A Sensorless Control System for an Implantable Heart Pump Using a Real-Time Deep Convolutional Neural Network

A Sensorless Control System for an Implantable Heart Pump Using a Real-Time Deep Convolutional Neural Network

Distributed Model Predictive Control for Linear Constrained Systems Based on Time-Varying Terminal Sets

A centralized multi-objective model predictive control for a biventricular assist device: An in vitro evaluation

Contact Info

Product

Resources

About