Optimization of acousto-ultrasonic sensor networks using genetic algorithms based on experimental and numerical data sets

The Second International Conference and Advanced School 'Turbulent Mixing and Beyond', TMB-2009, was held at the Abdus Salam International Centre for Theoretical Physics, (ICTP), Trieste, Italy on 27 July–7 August 2009. TMB-2009 united over 180 participants ranging from students to members of the National Academies of Sciences and Engineering, and including researchers at experienced and early stages of their carriers from leading scientific institutions in academia, national laboratories, corporations and industry worldwide. Responding to the community's inquiry and reaffirming the practices established at TMB-2007, two Round Tables were organized for the participants of TMB-2009 on 30 July 2009 and 6 August 2009 in the Oppenheimer Room at the Centre. The goals of the Round Tables were to encourage the information exchange among the members of the interdisciplinary and international TMB community, promote discussions regarding the state-of-the-art in TMB-related scientific areas, identify directions for frontier research, and articulate recommendations for future developments.

Influence of the characteristics of the experimental data set used to identify anisotropy parameters

In this paper, a 2D least square FIR differentiation filter method is proposed in the context of tensorial elastography. Displacements are estimated from ultrasonic images obtained during freehand compression. Two 2D filters are used for providing all partial derivative maps according to the estimated motion obtained with a Bilinear Deformable Block Matching method. From these results, several strain tensor images are built, revealing the tissue's elasticity properties. Among these tensors, the infinitesimal strains, the rigid rotation and principal strains tensors are retained, thus improving the contrast between the tumor and the background tissue. The 2D filters were first applied to displacement maps estimated from simulated data and two experimental RF data sets and then compared to the 1D differentiation filter LSQSE used in elastography. The first experimental data set was collected from a homogeneous phantom with a cylindrical hard inclusion and the second data set was collected from a thyroid gland with a malignant tumor. For all studied RF data sets, the contrast between the tumor and the background tissue calculated on strain tensor maps was increased up to a factor of 3 with our method compared to the LSQSE method. We also observed that the rigid rotation tensor and principal strains tensor were well adapted to thyroid elastography.

This report summarizes the achievements and final results of this program. The objective of this program is to develop a general model-based sensor network design methodology and tools to address key issues in the design of an optimal sensor network configuration: the type, location and number of sensors used in a network, for online condition monitoring. In particular, the focus in this work is to develop software tools for optimal sensor placement (OSP) and use these tools to design optimal sensor network configuration for online condition monitoring of gasifier refractory wear and radiant syngas cooler (RSC) fouling. The methodology developed will be applicable to sensing system design for online condition monitoring for broad range of applications. The overall approach consists of (i) defining condition monitoring requirement in terms of OSP and mapping these requirements in mathematical terms for OSP algorithm, (ii) analyzing trade-off of alternate OSP algorithms, down selecting the most relevant ones and developing them for IGCC applications (iii) enhancing the gasifier and RSC models as required by OSP algorithms, (iv) applying the developed OSP algorithm to design the optimal sensor network required for the condition monitoring of an IGCC gasifier refractory and RSC fouling. Two key requirements for OSP for condition monitoring are desired precision for the monitoring variables (e.g. refractory wear) and reliability of the proposed sensor network in the presence of expected sensor failures. The OSP problem is naturally posed within a Kalman filtering approach as an integer programming problem where the key requirements of precision and reliability are imposed as constraints. The optimization is performed over the overall network cost. Based on extensive literature survey two formulations were identified as being relevant to OSP for condition monitoring; one based on LMI formulation and the other being standard INLP formulation. Various algorithms to solve these two formulations were developed and validated. For a given OSP problem the computation efficiency largely depends on the “size” of the problem. Initially a simplified 1-D gasifier model assuming axial and azimuthal symmetry was used to test out various OSP algorithms. Finally these algorithms were used to design the optimal sensor network for condition monitoring of IGCC gasifier refractory wear and RSC fouling. The sensors type and locations obtained as solution to the OSP problem were validated using model based sensing approach. The OSP algorithm has been developed in a modular form and has been packaged as a software tool for OSP design where a designer can explore various OSP design algorithm is a user friendly way. The OSP software tool is implemented in Matlab/Simulink© in-house. The tool also uses few optimization routines that are freely available on World Wide Web. In addition a modular Extended Kalman Filter (EKF) block has also been developed in Matlab/Simulink© which can be utilized for model based sensing of important process variables that are not directly measured through combining the online sensors with model based estimation once the hardware sensor and their locations has been finalized. The OSP algorithm details and the results of applying these algorithms to obtain optimal sensor location for condition monitoring of gasifier refractory wear and RSC fouling profile are summarized in this final report.

10 - Design of Sensor Networks

Failure in achieving a function-based resection related to the insufficient patient's participation is a drawback of awake surgery. To assess preoperative parameters predicting the risk of patient insufficient intraoperative cooperation leading to the arrest of the awake resection. Observational, retrospective, multicentric cohort analysis enrolling 384 (experimental dataset) and 100 (external validation dataset) awake surgeries. In the experimental data set, an insufficient intraoperative cooperation occurred in 20/384 patients (5.2%), leading to awake surgery failure in 3/384 patients (ie, no resection, 0.8%), and precluded the achievement of the function-based resection in 17/384 patients (ie, resection limitation, 4.4%). The insufficient intraoperative cooperation significantly reduced the resection rates (55.0% vs 94.0%, P < .001) and precluded a supratotal resection (0% vs 11.3%, P = .017). Seventy years or older, uncontrolled epileptic seizures, previous oncological treatment, hyperperfusion on MRI, and mass effect on midline were independent predictors of insufficient cooperation during awake surgery ( P < .05). An Awake Surgery Insufficient Cooperation score was then assessed: 96.9% of patients (n = 343/354) with a score ≤2 presented a good intraoperative cooperation, while only 70.0% of patients (n = 21/30) with a score >2 presented a good intraoperative cooperation. In the experimental data set, similar date were found: 98.9% of patients (n = 98/99) with a score ≤2 presented a good cooperation, while 0% of patients (n = 0/1) with a score >2 presented a good cooperation. Function-based resection under awake conditions can be safely performed with a low rate of insufficient patient intraoperative cooperation. The risk can be assessed preoperatively by a careful patient selection.

Transmission power control has paramount importance in the design of energy-efficient wireless sensor networks (WSNs). In this paper, we systematically explore the effects of various transmission power control strategies on WSN lifetime with an emphasis on discretization of power levels and strategies for transmission power assignment. We investigate the effects of the granularity of power levels on energy dissipation characteristics through a linear programming framework by modifying a well known and heavily utilized continuous transmission power model (HCB model). We also investigate various transmission power assignment strategies by using two sets of experimental data on Mica motes. A novel family of mathematical programming models are developed to analyze the performance of these strategies. Bandwidth requirements of the proposed transmission power assignment strategies are also investigated. Numerical analysis of our models are performed to characterize the effects of various design parameters and to comparethe relative performance of transmission power assignment strategies. Our results show that the granularity of discrete energy consumption has a profound impact on WSN lifetime, furthermore, more fine-grained control of transmission power (i.e., link level control) can extend network lifetime up to 20% in comparison to optimally-assigned network-level single transmission power.

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

A perturbative formalism for the treatment of the acoustoelastic effect in material plates with a stress profile in the thickness direction is proposed and compared with a numerical method. The latter consists of an application of the local interaction simulation approach (LISA). The reliability of both the analytical treatment and the numerical approach is tested by comparing the respective results for several cases of propagation of Rayleigh waves in specimens with various kinds of stress fields, including welded steel plates. Finally, the linearization obtained from the perturbation treatment is exploited for the solution of the “inverse problem,” i.e., the determination of the stress field from a set of RW times of flight with different wavelengths. A numerical example is provided to illustrate the applicability of the method, starting from a set of synthetic data obtained with LISA.

A comparison of turbine mass flow models based on pragmatic identification data sets for turbogenerator model development

Noise radiated from flow past different configurations of the half-round mirror (HRM) mounted on a plate has been investigated using computational aeroacoustics (CAA). The stress-blended eddy simulation (SBES), together with the Ffowcs Williams–Hawkings (FW–H) acoustic analogy, was employed to predict near-field flow and far-field noise, respectively. The numerical methodology was verified and validated for the standard HRM case against several previously published numerical and experimental data sets, which provides good agreement. Further, (i) the choice of different type of grids for CAA and (ii) the applicability of methods such as the Kirchhoff integral and the FW–H using near field inputs computed from the SBES were assessed. As a next step, the effect of induced noise from the HRM for different (a) aspect ratios (AR) ranging from 1 to 2.5 and (b) inclination of the mirror toward the plate (θ) ranging from 0° to 32° was investigated. For all the investigated cases, the distribution of the radiated noise exhibits a dipole-like structure closer to the plate and a monopole-like structure away from the plate. By inclining the mirror closer to the mounting plate, the emitted noise is reduced both in the vertical and lateral directions of the wake, whereas an increase in the AR of the mirror increases the induced noise considerably. The findings from the current study can provide a deeper understanding for effectively mitigating the induced aerodynamic noise from side-view mirrors.

Application of artificial neural networks to near-instant construction of short-term g-functions

Safety and optimality are crucial requirements in every industrial process. The success of any fault diagnosis technique depends critically on the sensors measuring the important process variables. Choosing an appropriate sensor network is a combinatorially difficult problem, especially when the number of potential measurements is large. There has been considerable amount of work that has been done on developing algorithms for sensor network design for fault diagnosis based on quantitative and qualitative models. Various objectives, such as cost, reliability and fault resolution have been used in the sensor network design. While these design algorithms can provide the best design locations for a given cost, the value of the sensor network for fault diagnosis or benefit accrued is usually not quantified in a manner that is transparent to the user. This is an important aspect that needs to be addressed if these algorithms have to be assimilated into industrial practice. An approach for characterizing the value of a sensor network from a fault diagnosis perspective is proposed. This notion of value can be used directly in sensor network design algorithms. The proposed concepts are explained through a simple example and numerical simulations of a CSTR. © 2007 American Institute of Chemical Engineers AIChE J, 2007

A digital computer program is described for the estimation of parameters in an open two compartment system distinguishing 3 models. The mathematical function to be fitted to a given set of experimental data is given initial estimates for the parameters of the function. The program uses an iterative procedure to adjust the parameters until the sum of squares of residuals has converged to a minimum. Assuming that a given substance is introduced into compartment 1, the function can be fitted to the set of experiment data of that compartment. A set of experimental data from compartment 2 can also be included in the minimizing function. Two optional weighting functions are presented. From the constants of the two-exponential functions the physiological parameters of the three models are determined. Experimental observations of compartment 1 only allow for calculation of physiological parameters of two of the models.

PurposeMany metal workpieces have the characteristics of less texture, symmetry and reflectivity, which presents a challenge to existing pose estimation methods. The purpose of this paper is to propose a pose estimation method for grasping metal workpieces by industrial robots.Design/methodology/approachDual-hypothesis robust point matching registration network (RPM-Net) is proposed to estimate pose from point cloud. The proposed method uses the Point Cloud Library (PCL) to segment workpiece point cloud from scenes and a trained-well robust point matching registration network to estimate pose through dual-hypothesis point cloud registration.FindingsIn the experiment section, an experimental platform is built, which contains a six-axis industrial robot, a binocular structured-light sensor. A data set that contains three subsets is set up on the experimental platform. After training with the emulation data set, the dual-hypothesis RPM-Net is tested on the experimental data set, and the success rates of the three real data sets are 94.0%, 92.0% and 96.0%, respectively.Originality/valueThe contributions are as follows: first, dual-hypothesis RPM-Net is proposed which can realize the pose estimation of discrete and less-textured metal workpieces from point cloud, and second, a method of making training data sets is proposed using only CAD models with the visualization algorithm of the PCL.