Transportation-cyber-physical-systems-oriented engine cylinder pressure estimation using high gain observer

In transportation cyber-physical-systems （T-CPS）, vehicle-to-vehicle （V2V） communications play an important role in the coordination between individual vehicles as well as between vehicles and the roadside infrastructures, and engine cylinder pressure is significant for engine diagnosis on-line and torque control within the information exchange process under V2V communications. However, the parametric uncertainties caused from measurement noise in T-CPS lead to the dynamic performance deterioration of the engine cylinder pressure estimation. Considering the high accuracy requirement under V2V communications, a high gain observer based on the engine dynamic model is designed to improve the accuracy of pressure estimation. Then, the analyses about convergence, converge speed and stability of the corresponding error model are conducted using the Laplace and Lyapunov method. Finally, results from combination of Simulink with GT- Power based numerical experiments and comparisons demonstrate the effectiveness of the proposed approach with respect to robustness and accuracy.

Subharmonic aided pressure estimation in portal hypertension:A noninvasive ultrasound-based technique to assess portal pressure gradient

Portal hypertension(PH)is a clinical syndrome,characterized by elevated pressure gradient between portal vein and inferior vena cava.These elevated pressures gradient due to increased vascular resistance and/or increased volume of blood flowing through the portal vein circulation,results in blood outflow difficulty from portal vein to hepatic veins and inferior vena cava.

Cuffless Blood Pressure Estimation Based on Both Artificial and Data-Driven Features from Plethysmography

Blood pressure(BP)is an important indicator of individuals’health conditions for the prevention or treatment of cardiovascular disease.However,conventional measurements require inconvenient cuffbased instruments and are not able to detect continuous blood pressure.Advanced methods utilize machine learning to estimate BP by constructing artificial features in plethysmography(PPG)or using an end-to-end deep learning framework to estimate BP directly.Empirical features are limited by current research on cardiovascular disease and are not sufficient to express BP variability,while data-driven approaches neglect expert knowledge and lack interpretability.To address this issue,in this paper we propose a method for continuous BP estimation that extracts both artificial and data-driven features from PPG to take advantage of expert knowledge and deep learning at the same time.Then a deep residual neural network is designed to reduce information redundancy in the gathered features and refine high-level features for BP estimation.The results show that our proposed methods outperforms the compared methods in three commonly used metrics.

Qualitative estimation of pulmonary artery systolic pressure:could right heart catheterization be replaced by transthoracic Doppler echocardiography?

Background Transthoracic Doppler echocardiography is recommended for screening the presence of pulmonary hypertension(PH).However,the accuracy of pulmonary artery systolic pressure(PASP) estimated by Doppler echocardiographic is still unknown.Methods We conducted a retrospective study on 102 patients with idiopathic pulmonary arterial hypertension who underwent Doppler echocar-diography within 72 hours before right heart catheterization. During this time,all patients were stable without any specific drug therapy.Results There was moderate correlation between Doppler echocardiographic and right heart catheteriza- tion measurements of PASP(r =0.642,P【0.001).Using Bland-Altman analytic methods,the bias for the echocardio-graphic estimates of PASP was 6.65 mm Hg with 95%limits of agreement ranging from -47.62 to 34.30 mm Hg.There were 58.8%cases with absolute differences over 10 mm Hg between the two methods.Overestimation and underestimation of PASP by Doppler echocardiography occurred in 15.7% (16/102) and 43.1%(44),respectively.The magnitude of pressure underestimation and overestimation was insignificant (24.52±12.15 vs.25.69±16.09,P=0.765),while the corresponding diagnostic categories of severity that each subject would fall into for each technique are not in good agreement. The diagnostic categories of 16 overestimated patients were in accordance.During 44 underestimated patients,20.5%of patients had their pressure underestimated within one diagnostic category(minor error);4.5%of the underestimates were with two diagnostic categories(major error).Conclusions Transthoracic Doppler echocardiography may frequently be inaccurate in estimating PASP and could not replace the right heart catheterization.

Advocating for the implementation of SonoVue microbubbles as pressure sensors: a call to action for clinical noninvasive pressure estimation

Pressure measurement within the body is of pivotal significance in the diagnosis of vascular and organ-related diseases associated with hydrostatic pressure.At present,the most commonly used clinical method is to insert a catheter along with a pressure sensor and then guide it to the area of interest through vessels such as central venous pressure(CVP).However,the presence of sensors within the vessel of interest will inevitably cause alterations to the circulation and thus affect blood pressure.Moreover,the use of invasive methods does not allow monitoring of every area inside the body.

Estimating Average Reservoir Pressure： A Neural Network Approach with Limited Data

Insight into average oil pressure in gas reservoirs and changes in production （time）, play a critical role in reservoir and production performance, economic evaluation and reservoir management. In all practicality, average reservoir pressure can be conducted only when producing wells are shut in. This is regarded as a pressure build-up test. During the test, the wellbore pressure is recorded as a function of time. Currently, the only available method with which to obtain average reservoir pressure is to conduct an extended build-up test. It must then be evaluated using Homer or MDH （Miller, Dyes and Huchinson） valuation procedures. During production, average reservoir pressure declines due to fluid withdrawal from the wells and therefore, the average reservoirpressure is updated, periodically. A significant economic loss occurs during the entire pressure build-up test when producing wells are shut in. In this study, a neural network model has been established to map a nonlinear time-varying relationship which controls reservoir production history in order to predict and interpolate average reservoir pressure without closing the producing wells. This technique is suitable for constant and variable flow rates.

A Sensorless State Estimation for A Safety-Oriented Cyber-Physical System in Urban Driving:Deep Learning Approach

In today's modern electric vehicles,enhancing the safety-critical cyber-physical system(CPS)'s performance is necessary for the safe maneuverability of the vehicle.As a typical CPS,the braking system is crucial for the vehicle design and safe control.However,precise state estimation of the brake pressure is desired to perform safe driving with a high degree of autonomy.In this paper,a sensorless state estimation technique of the vehicle's brake pressure is developed using a deep-learning approach.A deep neural network(DNN)is structured and trained using deep-learning training techniques,such as,dropout and rectified units.These techniques are utilized to obtain more accurate model for brake pressure state estimation applications.The proposed model is trained using real experimental training data which were collected via conducting real vehicle testing.The vehicle was attached to a chassis dynamometer while the brake pressure data were collected under random driving cycles.Based on these experimental data,the DNN is trained and the performance of the proposed state estimation approach is validated accordingly.The results demonstrate high-accuracy brake pressure state estimation with RMSE of 0.048 MPa.

A Novel Particle Filtering Method for Estimation of Pulse Pressure Variation during Spontaneous Breathing

The first automatic algorithm was designed to estimate the pulse pressure variation (PPVPPV) from arterial blood pressure (ABP) signals under spontaneous breathing conditions. While currently there are a few publicly available algorithms to automatically estimate PPVPPV accurately and reliably in mechani-cally ventilated subjects, at the moment there is no automatic algorithm for estimating PPVPPV on sponta-neously breathing subjects. The algorithm utilizes our recently developed sequential Monte Carlo method (SMCM), which is called a maximum a-posteriori adaptive marginalized particle filter (MAM-PF). The performance assessment results of the proposed algorithm on real ABP signals from spontaneously breath-ing subjects were reported.