Supervisory Algorithm for Autonomous Hemodynamic Management Systems

Future military conflicts will require new solutions to manage combat casualties. The use of automated medical systems can potentially address this need by streamlining and augmenting the delivery of medical care in both emergency and combat trauma environments. However, in many situations, these systems may need to operate in conjunction with other autonomous and semi-autonomous devices. Management of complex patients may require multiple automated systems operating simultaneously and potentially competing with each other. Supervisory controllers capable of harmonizing multiple closed-loop systems are thus essential before multiple automated medical systems can be deployed in managing complex medical situations. The objective for this study was to develop a Supervisory Algorithm for Casualty Management (SACM) that manages decisions and interplay between two automated systems designed for management of hemorrhage control and resuscitation: an automatic extremity tourniquet system and an adaptive resuscitation controller. SACM monitors the required physiological inputs for both systems and synchronizes each respective system as needed. We present a series of trauma experiments carried out in a physiologically relevant benchtop circulatory system in which SACM must recognize extremity or internal hemorrhage, activate the corresponding algorithm to apply a tourniquet, and then resuscitate back to the target pressure setpoint. SACM continues monitoring after the initial stabilization so that additional medical changes can be quickly identified and addressed, essential to extending automation algorithms past initial trauma resuscitation into extended monitoring. Overall, SACM is an important step in transitioning automated medical systems into emergency and combat trauma situations. Future work will address further interplay between these systems and integrate additional medical systems.

Inverse Design of Airfoils Using Convolutional Neural Network and Deep Neural Network

In this paper, we compare the efficacy of two neural network based models: Convolutional Neural Network (CNN) and Deep Neural Networks (DNN) to inverse design the airfoil shapes. Given the pressure distribution over the airfoil in pictorial (for CNN) or numerical form (for DNN), the trained neural networks predict the airfoil shapes. During the training phase, the critical hyper-parameters of both the models, namely — learning rate, number of epochs and batch size, are tuned to reduce the mean squared error (MSE) and increase the prediction accuracy. The training parameters in DNN are an order of magnitude lower than that of CNN and hence the DNN model is found to be ≈ 7× faster than the CNN. In addition, the accuracy of DNN is also observed to be superior to that of CNN. After processing the raw airfoil shapes, the smoothed airfoils are shown to yield the target pressure distribution thereby validating the framework.

Design of V-Substituted TiFe-Based Alloy for Target Pressure Range and Easy Activation

Titanium iron (TiFe) alloy is a room-temperature hydrogen-storage material, and it absorbs hydrogen via a two-step process to form TiFeH and then TiFeH2. The effect of V addition in TiFe alloy was recently elucidated. The V substitution for Ti sublattice lowers P2/P1 ratio, where P1 and P2 are the equilibrium plateau pressure for TiFe/TiFeH and TiFeH/TiFeH2, respectively, and thus restricts the two-step hydrogenation within a narrow pressure range. The focus of the present investigation was to optimize the V content such that maximum usable storage capacity can be achieved for the target pressure range: 1 MPa for absorption and 0.1 MPa for desorption. The effect of V substitution at selective Ti or Fe sublattices was closely analyzed, and the alloy composition Ti46Fe47.5V6.5 displayed the best performance with ca. 1.5 wt.% of usable capacity within the target pressure range. At the same time, another issue in TiFe-based alloys, which is a difficulty in activation at room temperature, was solved by Ce addition. It was shown that 3 wt.% Ce dispersion in TiFe alloy imparted to it easy room-temperature (RT) activation properties.

Grasp Point Optimization and Leakage-Compliant Dimensioning of Energy-Efficient Vacuum-Based Gripping Systems

Vacuum-based handling, used in many applications and industries, offers great flexibility and fast handling processes. However, due to significant energy conversion losses from electrical energy to the useable suction flow, vacuum-based handling is highly energy-inefficient. In preliminary work, we showed that our grasp optimization method offers the potential to save at least 50% of energy by a targeted placement of individual suction cups on the part to be handled. By considering the leakage between gripper and object, this paper aims to extend the grasp optimization method by predicting the effective compressed air consumption depending on object surface roughness, gripper diameter and gripper count. Through balancing of the target pressure difference and the leakage tolerance in combination with the gripper count and gripper diameter, significant reductions of the compressed air, use and therefore the overall energy consumption, can be achieved. With knowledge about the gripper-specific leakage behavior, in the future it will be straightforward for system integrators to minimize the need for oversizing due to process-related uncertainties and therefore to provide application-specific and energy-optimized handling solutions to their customers.

Improving Comfort and Air Conditioner Performance by Optimizing Controllers under Actual Usage Conditions

This study is to increase the efficiency of the air conditioning system under actual conditions of use. In order to improve the increase in energy consumption due to control without considering indoor cooling load fluctuations, we review it compared to conventional control methods in two respects. First, we examined the control method to reduce energy consumption by varying the evaporative pressure of the system according to the cooling load, and secondly, further reducing energy consumption by controlling the revolutions per minute (RPM) of the fan of the indoor unit at the same time as the pressure fluctuation under the cooling load. We found that changing the target pressure depending on the difference between the target temperature and room temperature can control temperature more efficiently and save energy than using fixed target pressure, and that the effect increases when applying the control of the air volume of the indoor air. Cleaning up the resulting values, the fan-load-control condition of the cooling-load-estimation control method showed an energy savings effect of 16.1%–48.7% compared with the fixed-pressure control method and 1.2%–37.7% compared with the cooling-load-estimation control method.

Machine Learning for Mechanical Ventilation Control

We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patient's lungs according to a trajectory of airway pressures specified by a clinician. Hand-tuned PID controllers and similar variants have comprised the industry standard for decades, yet can behave poorly by over- or under-shooting their target or oscillating rapidly. We consider a data-driven machine learning approach: First, we train a simulator based on data we collect from an artificial lung. Then, we train deep neural network controllers on these simulators.We show that our controllers are able to track target pressure waveforms significantly better than PID controllers. We further show that a learned controller generalizes across lungs with varying characteristics much more readily than PID controllers do.

Nanoscale disintegration kinetics of mesoglobules in aqueous poly(N-isopropylacrylamide) solutions revealed by small-angle neutron scattering and pressure jumps

Two types of disintegration processes are revealed for polymeric nanoparticles using rapid pressure jumps and kinetic small-angle neutron scattering, namely chain release or swelling of the nanoparticle, depending on the target pressure.

How reliable are the current Blood Pressure Measuring devices in Health Facilities of Bhutan?

Background: Accurate blood pressure measurement is vital before any inferences are made on the reading. Since device error is one of the potential causes of inaccurate results, blood pressure measuring (BPM) devices should be periodically assessed for its accuracy. This paper describes the types of BPM devices used in health facilities of Bhutan and the results of their performance verifications. Method: This study assessed the pressure accuracy and leak rates of BPM devices in use at two regional referral hospitals, district hospitals and BHU I using calibrated Vital Signs Simulator (ProSimTM 8) from Fluke Biomedical as reference device. For pressure accuracy assessment, static pressures were simulated against which simultaneous readings of each of the devices were recorded (n=3). For the leak rate assessment, the simulator was set to a target pressure and leak rate (n=3) were recorded over 1 minute. Result: A total of 395 devices of three types, viz., 135 aneroid, 125 electronic and 135 mercury were assessed. Deviations in readings of 64.72% of devices were found to be within acceptable range of ± 3 mmHg. The device-type specific pass percentages for pressure accuracy were 6.40 % for electronic, 88.81 % for aneroid and 94.81 % for mercury. A total of 71.85% of devices (aneroid and mercury) had acceptable leak rates of 15 mmHg per minute. Conclusion: The study shows that not all the blood pressure measuring devices currently being used in the health facilities of Bhutan are accurate. Besides ensuring that only validated BPM devices enter the country, these devices should be verified for its performance periodically once they are in use.

Establishment of a Two-Stage Turbocharging System Model and Analysis on Influence Rules of Key Parameters

This paper took a two-stage turbocharged heavy-duty six-cylinder diesel engine as the research object and established a two-stage turbocharging system matching model. The influence rules between the two-stage turbocharging key parameters were analyzed, while summarizing an optimization method of key parameters of a two-stage turbocharger. The constraint equations for the optimal distribution principle of the two-stage turbocharger’s pressure ratio and expansion ratio were proposed. The results show that when the pressure ratio constraint equation and expansion ratio constraint equation are satisfied, the diesel engine can achieve the target pressure ratio, while the total energy consumption of the turbocharger is the lowest.