Optimal Sensor Location Research Articles

Deep Transferable Intelligence for Spatial Variability Characterization and Data-Efficient Learning in Biomechanical Measurement

Biomechanical measurement is of promising value for rehabilitation, assisted-living, and lifestyle management applications. Nevertheless, the understanding is still limited on the spatial variability of biomechanical dynamics that is essential for optimal motion sensor configuration. Besides, training physical activity detectors is usually data-heavy and time-consuming. Targeting these two challenges, in this study, we propose a novel deep transfer intelligence framework, which leverages deep learning to characterize spatial variability of different motion sensors on diverse body locations, and further leverages inter-subject transfer learning to maximize data-efficiency in challenging scarce data learning. More specifically, to characterize the spatial variability, we propose deep convolutional neural networks to investigate capabilities of both different sensor locations and channels, on physical activity measurement. The characterization determines both optimal sensor configuration and optimal channel configuration. Further, we propose a transfer learning approach to mine inter-subject similarity and then share learned knowledge among subjects, thereby minimizing the training effort and maximizing the data-efficiency in the wearable scarce data learning scenario. Our evaluation experiments have determined the optimal sensor location from seven options as thigh, and the optimal sensor&channel configuration from 42 options as thigh-accelerometer-axis-Y. Our experiments have further demonstrated that, with transfer learning under the optimal sensor&channel configuration, only 10% of data from the target subject for model fine-tuning can yield a physical activity detection accuracy up to 91.6%, with a performance boosting of 9% compared with direct learning without transfer learning. Therefore, the deep transferable learning framework will greatly advance spatial variability characterization for optimal sensor and channel configuration, and efficient scarce data learning in biomedical measurement.

Optimal Geometries for AOA Localization in the Bayesian Sense

This paper considers the optimal sensor placement problem for angle-of-arrival (AOA) target localization in the 2D plane with a Gaussian prior. Optimal sensor locations are analytically determined for a single AOA sensor using the D- and A-optimality criteria and an approximation of the Bayesian Fisher information matrix (BFIM). Optimal sensor placement is shown to align with the minor axis of the prior covariance error ellipse for both optimality criteria. The approximate BFIM is argued to be valid for a sufficiently small prior covariance compared with the target range. Optimal sensor placement results obtained for Bayesian target localization are extended to manoeuvring target tracking. For sensor trajectory optimization subject to turn-rate constraints, numerical search methods based on the D- and A-optimality criteria as well as a new closed-form projection algorithm that aims to achieve alignment with the minor axis of the prior error ellipse are proposed. It is observed that the two optimality criteria generate significantly different optimal sensor trajectories despite having the same optimal sensor placement for the localization of a stationary target. Analysis results and the performance of the sensor trajectory optimization methods are demonstrated with simulation examples. It is observed that the new closed-form projection algorithm achieves superior tracking performance compared with the two numerical search methods.

Reduced order model-based observer design for online temperature distribution estimation in lithium-ion batteries

Time/space separation-based modeling methods have been widely researched for estimating lithium-ion battery (LIB) thermal dynamics. However, these methods have been developed in an offline environment and may not perform well in real-time application since the battery systems in electric vehicles (EVs) are usually subject to external disturbances. Furthermore, the onboard measurements of temperature are often corrupted by significant error. To address these problems, we present a reduced model-based observer design for online temperature distribution estimation in LIBs. First, an extreme learning machine (ELM)-based offline spatiotemporal model is constructed to approximate the thermal dynamics of LIB. Second, an adaptive reduced order observer is designed based on the offline model developed in the previous step. The offline model is then updated with the estimation results of the observer. As the performance of the estimator is highly related to the placement of sensors, a genetic algorithm (GA)-based integrated optimization strategy is also developed to determine the optimal sensor location for online estimation. Finally, the whole temperature distribution is estimated in real time using the observer, the measured voltage, current and the limited available temperature data. Two experiments on different batteries with different input currents verify the effectiveness of this developed model.

Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation

AbstractThere is a growing interest in developing data‐driven reduced‐order models for atmospheric and oceanic flows that are trained on data obtained either from high‐resolution simulations or satellite observations. The data‐driven models are non‐intrusive in nature and offer significant computational savings compared to large‐scale numerical models. These low‐dimensional models can be utilized to reduce the computational burden of generating forecasts and estimating model uncertainty without losing the key information needed for data assimilation (DA) to produce accurate state estimates. This paper aims at exploring an equation‐free surrogate modeling approach at the intersection of machine learning and DA in Earth system modeling. With this objective, we introduce an end‐to‐end non‐intrusive reduced‐order modeling (NIROM) framework equipped with contributions in modal decomposition, time series prediction, optimal sensor placement, and sequential DA. Specifically, we use proper orthogonal decomposition (POD) to identify the dominant structures of the flow, and a long short‐term memory network to model the dynamics of the POD modes. The NIROM is integrated within the deterministic ensemble Kalman filter (DEnKF) to incorporate sparse and noisy observations at optimal sensor locations obtained through QR pivoting. The feasibility and the benefit of the proposed framework are demonstrated for the NOAA Optimum Interpolation Sea Surface Temperature (SST) V2 data set. Our results indicate that the NIROM is stable for long‐term forecasting and can model dynamics of SST with a reasonable level of accuracy. Furthermore, the prediction accuracy of the NIROM gets improved by almost one order of magnitude by the DEnKF algorithm.

Optimization of multi-type sensor locations for simultaneous estimation of origin-destination demands and link travel times with covariance effects

This paper investigates the multi-type traffic sensor location problem for simultaneous estimation of origin-destination (OD) demands and link travel times while also considering the two sources of spatial covariance effects on a road network with uncertainties. The first source is the statistical correlation of the vehicular traffic demands for different OD pairs in a typical hourly period (e.g., morning peak hour) on a daily scale, as the travel demand patterns vary daily, weekly, and seasonally over the year. The second source is the stochastic nature of the link travel times on different road links during the peak hour period and their correlation with adjacent links in congested conditions. By considering these aspects, a novel model is formulated to optimize the number and locations of multi-type traffic sensors for simultaneous estimation of stochastic OD demands and link travel times during the same peak-hour period over a year. This estimation is supported by the data recorded by multi-type traffic sensors such as point sensors and automatic vehicle identification sensors, which yield the link speed/flow and path travel time information, respectively. Based on the integrated observations from multi-type traffic sensors, a novel Kullback–Leibler divergence-based model is developed to accommodate different probability distributions of OD demands and link travel times in different traffic conditions. Moreover, an improved firefly algorithm is developed to solve the multi-type sensor location problem. Specifically, the search strategy of this algorithm is enhanced by considering the mean and covariance of the OD demands and link travel times. Numerical examples of synthetic and real-world road networks are used to illustrate the applications and merits of the developed multi-type sensor location model for simultaneously estimating the OD demands and link travel times while also considering covariance effects.

Optimal numbers and locations of wearable sensors to enhance the performance of classification models that differentiate injurious versus non-injurious transfers

Optimal numbers and locations of wearable sensors to enhance the performance of classification models that differentiate injurious versus non-injurious transfers

Optimal location of acoustic emission sensors for detecting rail damage

To detect cracks in rail sections, various experiments using the acoustic emission technique have been carried out by earlier researchers. However, the literature suggests that studies investigating the optimum location of acoustic emission sensors for the detection of cracks in railway tracks are rare. It is difficult to detect defects without the optimal placement of the sensor, owing to the complex geometry of the rail section as well as the high cost of sensors. Hence an attempt was made to find the optimum placement of a single sensor on a rail section to detect cracks precisely. A pencil lead break, which simulates a crack, was applied in the rail section to initiate such a crack. The obtained signal was analysed using wavelet transformation to establish a relationship with the group velocity to localise the simulated crack. From the investigation, it was found that the optimum placement of the sensor was between 75 mm to 375 mm for a 1.9 m length of rail section in laboratory conditions.

Optimization of multi-type traffic sensor locations for network-wide link travel time estimation with consideration of their covariance

Due to the propagation of traffic congestion from upstream to downstream links and the uncertainty of path choice behaviours, travel times between different links, particularly adjacent links, are highly correlated in a typical period from day to day. To improve the estimation accuracy of both the mean and covariance of link travel times, a novel measurement is proposed to optimize the locations of multi-type traffic sensors for link travel time estimation. Multi-source data from different types of traffic sensors can be integrated to better estimate link travel time in an entire road network. In practice, the allocation of multi-type traffic sensors is constrained by the total financial budget and should be optimized in accordance with measurement errors and the cost ratio. Numerical examples of synthetic and real road networks are conducted to demonstrate the applications and merits of the proposed multi-type sensor location model with covariance effects.

Comparative Analysis between Genetic Algorithm and Simulated Annealing-Based Frameworks for Optimal Sensor Placement and Structural Health Monitoring Purposes

The arbitrary placement of sensors in concrete structures measures a considerable amount of unnecessary data. Optimal sensor placement methods are used to provide informative data with the least cost and maximum efficiency. In this study, a robust optimal sensor placement framework that combines an optimization-based algorithm, the simulated annealing (SA) algorithm, and the ensemble Kalman filter (EnKF) are presented for structural health monitoring and system identification. The SA algorithm randomly generates an initial population of sensor locations, while the framework undergoes a minimization process. The objective function used is the difference between the actual measured data and their corresponding EnKF predicted values. A comparative analysis between the genetic algorithm–ensemble Kalman filter (GA-EnKF) and the simulated annealing–ensemble Kalman filter (SA-EnKF) approaches is presented. The performance and computational burden of both algorithms, which converge to the best sensor locations for damage detection purposes, are tested on a 10-story building subjected to a seismic excitation. The results are compared to the optimal sensor locations of the brute-force search methodology. The GA-EnKF outperforms the SA-EnKF in terms of accuracy in converging to the optimal results, yet the computational cost of the SA-EnKF is considerably lower.

Multi-criteria sensor placement determination in prognostics and health management using combined fault diagnosis, fault detection, and risk indexes

In framework of a prognostics and health management (PHM), a stochastic method is proposed for optimal sensor locations determination using three independent criteria indexes, reflecting the efficiency of sensor network: (i) the uncertainty of sensor information, the ability of fault diagnosis of a sensor network, (ii) the reliability of sensors, reflecting the fault detectability in sensor networks, (iii) risk of sensor failure including the consequence of sensor failure scenarios. The dynamic system failure model is developed and analyzed to consider the variation of environmental factors and their related failure threshold characterization along with statistical variance estimation as the information value that each possible sensor placement scenario provides through sensor information. A dynamic failure model is developed to incorporate the interaction of sensors and their corresponding components. It is demonstrated here that considering each criterion independently will not comprehensively determine the optimal placement scenario. An augmented index is formulated through Shannon Entropy theory, ranking all sensor placement scenarios based on proposed combined index. Optimization of sensor placement is demonstrated on a typical steam turbine. As shown in detail, the ranking based on each criterion provides different inconsistent rank for the location of the sensors. The combined index is found practically proper and recommended for rank and selection process.

Grid Search for Lowest Root Mean Squared Error in Predicting Optimal Sensor Location in Protected Cultivation Systems.

Irregular changes in the internal climates of protected cultivation systems can prevent attainment of optimal yield when the environmental conditions are not adequately monitored and controlled. Key to indoor environment monitoring and control and potentially reducing operational costs are the strategic placement of an optimal number of sensors using a robust method. A multi-objective approach based on supervised machine learning was used to determine the optimal number of sensors and installation positions in a protected cultivation system. Specifically, a gradient boosting algorithm, a form of a tree-based model, was fitted to measured (temperature and humidity) and derived conditions (dew point temperature, humidity ratio, enthalpy, and specific volume). Feature variables were forecasted in a time-series manner. Training and validation data were categorized without randomizing the observations to ensure the features remained time-dependent. Evaluations of the variations in the number and location of sensors by day, week, and month were done to observe the impact of environmental fluctuations on the optimal number and location of placement of sensors. Results showed that less than 32% of the 56 sensors considered in this study were needed to optimally monitor the protected cultivation system’s internal environment with the highest occurring in May. In May, an average change of −0.041% in consecutive RMSE values ranged from the 1st sensor location (0.027°C) to the 17th sensor location (0.013°C). The derived properties better described the ambient condition of the indoor air than the directly measured, leading to a better performing machine learning model. A machine learning model was developed and proposed to determine the optimal sensors number and positions in a protected cultivation system.

An online machine learning-based sensors clustering system for efficient and cost-effective environmental monitoring in controlled environment agriculture

Sensors are vital in controlled environment agriculture for measuring parameters for effective decision-making. Currently, most growers randomly install a limited number of sensors due to economic implications and data management issues. The microclimate within a protected cultivation system is continuously affected by the macroclimate (ambient), which further complicates decision-making around optimal sensor placement. The ambient weather's effect on the indoor microclimate makes it challenging to predict or acquire the ideal condition of the systems through using sensors. This study proposed and implemented a machine learning (K-Means++) algorithm to select optimal sensor locations through clustering. Temperature and relative humidity data were collected from 56 different locations within the greenhouse for over a year covering and these covered four major seasons (spring, summer, autumn, and winter). The data was processed to remove outliers or noise interference using interquartile. The original temperature and relative humidity data were transformed to other air properties (dew point temperature, enthalpy, humid ratio, and specific volume) and used in simulations. The results obtained showed that the number of optimal sensor locations ranged between 3 and 5, and there were similar sensor locations among the air properties. An online machine learning web-based system was developed to systematically determine the optimal number of sensors and location.

Optimal Sensor Placement Using Learning Models—A Mediterranean Case Study

In this paper, we discuss different approaches to optimal sensor placement and propose that an optimal sensor location can be selected using unsupervised learning methods such as self-organising maps, neural gas or the K-means algorithm. We show how each of the algorithms can be used for this purpose and that additional constraints such as distance from shore, which is presumed to be related to deployment and maintenance costs, can be considered. The study uses wind data over the Mediterranean Sea and uses the reconstruction error to evaluate sensor location selection. The reconstruction error shows that results deteriorate when additional constraints are added to the equation. However, it is also shown that a small fraction of the data is sufficient to reconstruct wind data over a larger geographic area with an error comparable to that of a meteorological model. The results are confirmed by several experiments and are consistent with the results of previous studies.

Fisher information‐based optimal sensor locations for output‐only structural identification under base excitation

Fisher information‐based optimal sensor locations for output‐only structural identification under base excitation

Evaluation of surgical skill using machine learning with optimal wearable sensor locations.

Evaluation of surgical skills during minimally invasive surgeries is needed when recruiting new surgeons. Although surgeons’ differentiation by skill level is highly complex, performance in specific clinical tasks such as pegboard transfer and knot tying could be determined using wearable EMG and accelerometer sensors. A wireless wearable platform has made it feasible to collect movement and muscle activation signals for quick skill evaluation during surgical tasks. However, it is challenging since the placement of multiple wireless wearable sensors may interfere with their performance in the assessment. This study utilizes machine learning techniques to identify optimal muscles and features critical for accurate skill evaluation. This study enrolled a total of twenty-six surgeons of different skill levels: novice (n = 11), intermediaries (n = 12), and experts (n = 3). Twelve wireless wearable sensors consisting of surface EMGs and accelerometers were placed bilaterally on bicep brachii, tricep brachii, anterior deltoid, flexor carpi ulnaris (FCU), extensor carpi ulnaris (ECU), and thenar eminence (TE) muscles to assess muscle activations and movement variability profiles. We found features related to movement complexity such as approximate entropy, sample entropy, and multiscale entropy played a critical role in skill level identification. We found that skill level was classified with highest accuracy by i) ECU for Random Forest Classifier (RFC), ii) deltoid for Support Vector Machines (SVM) and iii) biceps for Naïve Bayes Classifier with classification accuracies 61%, 57% and 47%. We found RFC classifier performed best with highest classification accuracy when muscles are combined i) ECU and deltoid (58%), ii) ECU and biceps (53%), and iii) ECU, biceps and deltoid (52%). Our findings suggest that quick surgical skill evaluation is possible using wearables sensors, and features from ECU, deltoid, and biceps muscles contribute an important role in surgical skill evaluation.

An optimal sensor location based protection scheme for DER-integrated hybrid AC/DC microgrid with reduced communication delay

In spite of the advantages, the acceptance of hybrid microgrid has been hindered due to the complexity of the protection task. With increased number of DERs (Distributed Energy Resources) and loads in the network, the placement of sensors in every bus for proper monitoring and protection is often not economical both in terms of sensor installation cost and the cost associated with communication infrastructure. Transmission of high volume of sensor information through the communication network demands high bandwidth for reduced communication delay. In this regard, a low-cost protection scheme for hybrid microgrid with optimal sensor placement and immunity against converter faults has been proposed. The issues related to sensor placement and increased impact of communication delay of the reported techniques has been addressed by identifying a set of optimal sensor locations for network observability. The scheme based on Wavelet Packet Decomposition (WPD) and ensemble classifier has been extensively validated in terms of the optimality of identified sensor locations, minimization of communication delay and accuracy of the protection scheme.

Sensor Screening Methodology for Virtually Sensing Transmission Input Loads of a Wind Turbine Using Machine Learning Techniques and Drivetrain Simulations

The ongoing trend of building larger wind turbines (WT) to reach greater economies of scale is contributing to the reduction in cost of wind energy, as well as the increase in WT drivetrain input loads into uncharted territories. The resulting intensification of the load situation within the WT gearbox motivates the need to monitor WT transmission input loads. However, due to the high costs of direct measurement solutions, more economical solutions, such as virtual sensing of transmission input loads using stationary sensors mounted on the gearbox housing or other drivetrain locations, are of interest. As the number, type, and location of sensors needed for a virtual sensing solutions can vary considerably in cost, in this investigation, we aimed to identify optimal sensor locations for virtually sensing WT 6-degree of freedom (6-DOF) transmission input loads. Random forest (RF) models were designed and applied to a dataset containing simulated operational data of a Vestas V52 WT multibody simulation model undergoing simulated wind fields. The dataset contained the 6-DOF transmission input loads and signals from potential sensor locations covering deformations, misalignments, and rotational speeds at various drivetrain locations. The RF models were used to identify the sensor locations with the highest impact on accuracy of virtual load sensing following a known statistical test in order to prioritize and reduce the number of needed input signals. The performance of the models was assessed before and after reducing the number of input signals required. By allowing for a screening of sensors prior to real-world tests, the results demonstrate the high promise of the proposed method for optimizing the cost of future virtual WT transmission load sensors.

Optimal Number and Location of Sensors for Structural Damage Detection using the Theory of Geometrical Viewpoint and Parameter Subset Selection Method

The recorded responses at predefined sensor placements are used as input to solve an inverse structural damage detection problem. The error rate that noise causes from the recorded responses of the sensors is a significant issue in damage detection methods. Therefore, an optimal number and location of sensors is a goal to achieve the lowest error rate in structural damage detection. To overcome this problem, an algorithm (GVPSS) based on a Geometrical Viewpoint (GV) of optimal sensor placement and Parameter Subset Selection (PSS) method is proposed. The goal of the GVPSS algorithm is to minimize the effect of noise on damage detection problem. Therefore, the fitness function based on error in damage detection is minimized by GVPSS. In this method, the degrees of freedom are arranged to place sensors using a fitness function based on GV theory. Then, the optimal number and location of sensors are found on these arranged the degrees of freedom using the objective function. The efficiency of the proposed method is studied in a 52-bar dome structure under static and dynamic loadings. In the examples, damages are detected in two states: 1) using responses recorded at all DOFs, 2) using responses recorded at the optimal number and location of sensors obtained by GVPSS. The results showed that the damage detection error in state 2 is approximately equal to the error in state 1. Therefore, the GVPSS have the high performance to find the optimal number and location of sensors for structural damage detection.

Multi-objective optimization of pressure sensor location for burst detection and network calibration

This paper proposes a methodology to determine the optimal location of pressure sensors for the simultaneous calibration of the hydraulic network model and the detection of pipe bursts. The methodology considers a search space reduction process and aims at maximizing nodal pressure sensitivities to both pipe roughness coefficients and pipe burst sizes. A multi-objective optimization problem is formulated for a given number of sensors and multiple optimal configurations of pressure sensors are obtained. Three different optimal configurations are selected and compared: one solution that individually maximizes each objective function (two solutions) and one trade-off solution. The methodology is applied to a real water distribution network with hourly consumption data. Results demonstrate that (i) the optimal location of pressure sensors hardly changes with the perturbation values used to numerically compute the sensitivities and (ii) minor differences can be found in the performance of pipe roughness calibration and pipe burst location by using either a solution that individually maximizes each objective function or the trade-off solution considering the high number of pressure sensors (26) and the oversized pipe diameters to comply with firefighting conditions, being pressure less sensitive to friction and flow rate changes.

A simulation-based evaluation of fan coil unit fault effects

Faults in heating, ventilation and air conditioning (HVAC) systems cause increased energy consumption, degrading thermal comforts, growing operational cost and reduced system lifespan. An effective evaluation of fault effects is critical to the development of various fault diagnostics solutions, the improvement of operation maintenance and the optimization of monitoring systems. In the HVAC area, a majority of research work in evaluating fault effects was to analyze energy consumption impacts or thermal comfort impacts. However, a handful of research has been conducted on evaluating fault effects on various measurements, which are increasingly employed to monitor equipment's operation. Fault effects on various measurements may display different symptom patterns and present changed sensitivities when the equipment operates under various faults, severity levels, as well as operation conditions. However, a long-term observation of fault symptoms under various operation conditions, different fault types and severity levels to evaluate fault effects is extremely challenging. In this paper, a simulation-based framework was proposed to evaluate fault effects in fan coil units (FCUs). Two metrics namely fault symptom occurrence probability (SOP) and fault symptom daily continuous duration (SDCD) were developed to quantify fault symptoms under various FCU faults. A total of 18 common FCU faults at different severity levels were implemented on the developed HVACSIM+ simulation platform to obtain a full year fault inclusive data set for 48 fault simulation cases. The framework, as well as obtained SOP and SDCD distributions will benefit multiple folds such as the development of probability-based fault diagnostics inference approaches, optimization of sensor location, and fault prioritization.