Virtual Sensor Research Articles

Frequency domain adaptation of multichannel active road-noise sound control system with virtual sensing

The convergence speed of multichannel adaptive active noise control algorithms can be improved by pre-whitening the reference signals and reducing their cross-correlations. When considering nonstationary processes, like road noise, it proves advantageous to use a short time-based cross-correlation estimation of the reference signal, which can be obtained as part of the bin-normalised frequency domain least-means-squares algorithm. However, the regularisation of such an algorithm is crucial to its success and can further improve the convergence rate. In addition, virtual sensors can be employed by using the additional filter method, which provides targets for the measured error signals to follow, generated from the reference signals. Still, the performance of this virtual sensing is known to be degraded if the properties of the reference signals change, so special consideration should be taken when the reference signals are nonstationary.

Tri-axial rubidium and helium optically pumped magnetometers for on-scalp magnetoencephalography recording of interictal epileptiform discharges: a case study

Cryogenic magnetoencephalography (MEG) enhances the presurgical assessment of refractory focal epilepsy (RFE). Optically pumped magnetometers (OPMs) are cryogen-free sensors that enable on-scalp MEG recordings. Here, we investigate the application of tri-axial OPMs [87Rb (Rb-OPM) and 4He gas (He-OPM)] for the detection of interictal epileptiform discharges (IEDs). IEDs were recorded simultaneously with 4 tri-axial Rb- and 4 tri-axial He-OPMs in a child with RFE. IEDs were identified visually, isolated from magnetic background noise using independent component analysis (ICA) and were studied following their optimal magnetic field orientation thanks to virtual sensors. Most IEDs (>1,000) were detectable by both He- and Rb-OPM recordings. IEDs were isolated by ICA and the resulting magnetic field oriented mostly tangential to the scalp in Rb-OPMs and radial in He-OPMs. Likely due to differences in sensor locations, the IED amplitude was higher with Rb-OPMs. This case study shows comparable ability of Rb-OPMs and He-OPMs to detect IEDs and the substantial benefits of triaxial OPMs to detect IEDs from different sensor locations. Tri-axial OPMs allow to maximize spatial brain sampling for IEDs detection with a limited number of sensors.

Regulatory Framework for Ensuring Safe Operation of Railway Equipment Based on the Service Life of Load-Bearing Structures

Switching the operation of railway equipment to life cycle contracts and confirming its safety compliance with industry technical regulations in the absence of a legislative framework for the recall of substandard products entails the need for a more thorough analysis of resource indicators of structural components of rolling stock and track superstructure. From this point of view, the state of the existing regulatory framework for confirming the strength and service life criteria of load­bearing elements of rolling stock and track, the influence of the regulatory «guillotine» and the general transition from the system of Soviet state standards GOSTs and strength rules to modern approaches of certification and differentiation of such concepts as «standard» and «supporting standard».Trends in moving away from classical bench testing methods towards introduction of a resource-based approach with defectiveness assessment are shown using examples of previously carried out research on safe operation of ER200 bogie frame and on the transition to domestic cassette bearings as part of import substitution, currently carried out for different types of rolling stock.Based on the new methods and approaches, it is possible to consider longer periods of operation, reasonably assess the extension of service life, or introduce resource-restoring technology, ensuring further safe operation. As part of these new trends, a transition is being made to modern modelling methods for assessing product safety, concepts such as «virtual sensor» and «virtual train-track system» are being introduced. It is shown that a reasonable combination of full-scale operational tests and virtual digital modelling makes it possible to offer reliable estimates of service life and safety indicators at the design and operation stages in a short time.

NON-QUALITY RISK EVALUATION FROM TOOL WEAR ASSESSMENT

The development of part quality virtual sensors requires knowledge and observability of cutting conditions and in particular tool wear as tool are consumables. This paper presents an unsupervised anomalies detection approach to assess tool wear from standard machine load sensors in order to evaluate a non-quality risk metric. The developed methodology combines physics and business rules with density estimators to analyse the behaviour of axes and spindle loads. Industrial data from an automotive production line are used to illustrate the methodology application.

Network Optimization of Carbon Monoxide Sensor Nodes in the Metropolitan Region of São Paulo

Air pollution is one of the biggest problems affecting large urban areas. Better monitoring of regions suffering from this type of pollution is in the interest of public health. Although many cities employ sensors to monitor air pollution, a current concern is how to establish the ideal number of sensors to monitor a given geographical region. To address this concern, this research proposes a method to optimize the number of sensors in an air pollution monitoring network to cover a given region efficiently and precisely and uses the metropolitan region of São Paulo, Brazil, and CO sensors as an example. The model of Fragmentation into Groups via Routes is proposed to distribute sensors within micro-regions that display similar air pollution characteristics. A network of virtual sensors is created, and the output of each sensor is established using a method of spatial interpolation called IDW. To identify the optimum sensor configuration, a genetic algorithm is used to assess the topology with the lowest variance of data spread. A lesser number of sensor stations to be treated leads to faster responses to sudden changes in urban conditions. Therefore, municipality authorities can take quick measures to improve the population’s wellness.

Simultaneous in-situ calibration for physical and virtual sensors towards digital twin-enabled building operations

Digital twin-enabled building operations heavily rely on a building sensor network to collect operational data. Virtual sensing, in combination with physical sensors, has great potential in establishing a reliable and informative sensing environment. However, physical sensors can experience hardware errors or systematic errors due to the working environment within building systems. Virtual sensors are also subject to their model uncertainties arising from input physical sensor errors and changes in system operations. These virtual sensor errors have a negative effect on the in-situ calibration accuracy of corresponding physical sensors. To address these issues, this study proposes a simultaneous in-situ calibration (SIC) method designed to calibrate multiple physical and virtual sensors with varying errors in the context of digital twins. The SIC problem is mathematically formulated, including two types of distance functions (direct and indirect) and defining correction functions to calibrate various types of virtual sensors (such as backup, validation, replacement/virtualization, and observation sensors). Importantly, the proposed method tackles the challenges posed by the unknown calibration environment in operational systems. A field application study was conducted for two physical sensors and three different virtual sensors operating in a district heating substation serving real residential buildings in Korea. The case study shows how the different calibration accuracies for each sensor depend on the calibration approaches, such as physical-targeted (existing Case 1), virtual-targeted (existing Case 2), and simultaneous calibration (novel Case 3). Under the simultaneous errors, only Case 3 satisfied the reference accuracy for all sensors. Specifically, the average MAEs in Case 3 were improved by approximately 79.3%, 75.3%, 63.9%, and 87.5% for the target physical sensor, backup virtual sensor, virtualized sensor, and validation virtual sensor, respectively, compared to the accuracies before calibration. These results demonstrate the importance and effectiveness of simultaneous in-situ calibration of physical and virtual sensors in digital twin-enabled building operations. The proposed calibration can contribute to the synchronization of physical and virtual building systems, thus achieving reliable and informative virtual sensing-driven digital twins.

A Sparse-Array Design Method Using Q Uniform Linear Arrays for Direction-of-Arrival Estimation.

Nowadays, sparse arrays have been a hotspot for research in the direction of arrival (DOA). In order to achieve a big value for degrees of freedom (DOFs) using spatial smoothing methods, researchers try to use multiple uniform linear arrays (ULAs) to construct sparse arrays. But, with the number of subarrays increasing, the complexity also increases. Hence, in this paper, a design method, named as the cross-coarray consecutive-connected (4C) criterion, and the sparse array using Q ULAs (SA-UQ) are proposed. We first analyze the virtual sensor distribution of SA-U2 and extend the conclusions to SA-UQ, which is the 4C criterion. Then, we give an algorithm to solve the displacement between subarrays under the given Q ULAs. At last, we consider a special case, SA-U3. Through the analysis of DOFs, SA-UQ can find underdetermined signals. Moreover, SA-U3 can obtain DOFs close to other sparse arrays using three ULAs. The simulation experiments prove the performance of SA-UQ.

A virtual sensor network for pressure distribution inside a multi-zone building based on spatial adjacency relationships and multivariate adaptive regression spline

Airflows within multi-zone buildings cause variations in environmental parameters both vertically and horizontally. Although it is difficult to monitor the airflows through existing sensors, pressure monitoring allows the identification of airflows, since airflows across zones are induced by pressure differences. This study proposes a data-driven method for establishing a virtual pressure sensor network within a multi-zone building. Three scenarios with various sample sizes are applied to evaluate their impacts on the analyzed results, and scenario 3 is identified as the most suitable database for creating a virtual sensor network. The single-sided or multi-sided spatial adjacency relationships are determined for each zone, and the MARS model is then applied to develop the relationships among the variables, with key physical sensors designated by the frequency analysis of independent variables. The final sensor network comprises four key physical sensors, thirteen direct virtual sensors, and five indirect virtual sensors. All virtual sensors can achieve excellent predicted results with high R2 values and low MAE and RMSE, with mean values of 0.997 Pa and 1.269 Pa, respectively. Notably, the difference in accuracy between direct and indirect virtual sensors is influenced by spatial adjacency relationships. This study demonstrates a reliable virtual sensor network for predicting pressure variations and provides a reference for the identification of airflows and the efficient adjustment of HVAC systems.

Dynamic simulation based on feature transfer learning with source domain adaptive optimization: Application of data-driven model for aero-engines

Sensors are difficult to arrange inside complex aero-engine systems because of harsh operating environment. Aero-engine thermodynamic models can be used as virtual sensors to provide the basis for diagnosis and control. The modeling based on mechanism equations can be well explained, but its over-reliance on component characteristics lead to poor handling of strong dynamic. This paper proposed a novel source-domain-adaptive dynamic modeling framework of Feature Similarity-based Transfer Learning (FSTL) based on Deep Deterministic Policy Gradients (DDPG), which can mitigate for these shortcomings to a certain extent through little measurement data. The field startup signals are used to form the target domain, and the reward function is constructed by utilizing the domain similarity of feature fusion through FSTL. A dynamic model of a gas engine with a rated speed of 9000 rpm is carried out using the proposed learn-to-learn framework. The verification results of the startup process indicate that FSTL-DDPG has the most outstanding performance of 0.9536 regression coefficient and 0.46 % mean square error, which are improved by about 16.9 % and 62.0 % compared with FSTL and Dynamic Mode Decomposition combined with Long Short-Term Memory (DMD-LSTM). Qualitative and quantitative analysis revealed that FSTL-DDPG has better simulation performance and matching degree of physical laws.

Virtual PMV sensor towards smart thermostats: Comparison of modeling approaches using intrusive data

Smart thermostats are considered an effective digital technology for building energy efficiency. This study proposes a virtual predicted mean vote (PMV) sensor for smart thermostats for indoor thermal comfort and energy-efficient building operation and control. The proposed virtual sensor can observe the representative PMV for the occupied zone, considering the systematic errors caused by the spatial difference between the wall-mounted thermostat and the occupied zone. Virtual PMV sensor-based smart thermostat has the potential to improve energy efficiency and thermal comfort by observing unmeasured thermal comfort within the occupied zone based on variables obtained from an existing wall-installed thermostat. To cover systematic errors for general applications, intrusive measurements using a commissioning period are necessary, even in the short term. Thus, conventional modeling approaches can be used with limited intrusive data to develop an accurate in-situ virtual PMV sensor during operation. In the application into a small-sized office building, the real systematic errors showed up to −2.4 °C among ten different thermostat locations in the target office zone. The in-situ virtual sensor could accurately observe the PMV for an occupied zone for different air-conditioning periods (air-conditioned working hours, non-air-conditioned working hours, and closing hours) with the best accuracy of 0.05 mean absolute error (MAE) using one-day intrusive dataset. Based on comparing white-box, black-box, and gray-box virtual sensors in the application, this study recommends using the gray-box modeling approach to leverage the synergetic effect between data and knowledge for better in-situ virtual sensor modeling under a limited intrusive dataset.

Wear dependent virtual flow rate sensor for progressing cavity pumps with deformable stator

Wear dependent virtual flow rate sensor for progressing cavity pumps with deformable stator

A Virtual System and Method for Autonomous Navigation Performance Testing of Unmanned Surface Vehicles

An overall framework of the virtual testing system has been established based on the analysis of the virtual testing requirements for autonomous navigation performance of unmanned surface vehicles (USVs). This system consists of several modules, including the environment module, motion module, sensor module, and 3D visualization module. Firstly, within the robot operating system (ROS) environment, a three-dimensional navigation environment was generated by combining actual wave spectra with Gerstner waves. By designing a power plugin for USV navigation, the system was made to reflects the coupled motion model of USVs in wind, waves and currents, along with predictive results. Regarding the four typical sensor information on USVs, the actual sensors were virtualized, and a simulation approach for virtual sensor information is provided. The three-dimensional visualization of USV’s motion enables the intuitive display and analysis of the virtual testing process. Based on the prediction of coupled motion characteristics in wind, waves and currents, the interaction between USVs and the virtual testing system has been realized. A platform for virtual testing experiments to determine the autonomous navigation performance of USVs was established, and the effectiveness of the platform was verified in terms of perception and environmental interference. In virtual environmental interference validation, the average amplitude deviation of the heave motion of USVs under sea state 3 reaches 0.74 m, and the average amplitude deviation of the pitch motion reaches 0.25 rad, showing the gradually increasing disturbance of the sea state. Finally, virtual testing experiments were conducted on a specific USV to evaluate its autonomous navigation perception performance, trajectory tracking performance, and autonomous obstacle avoidance. The evaluation results indicate that the platform can achieve the functionality of virtual testing for the autonomous navigation performance of USVs from the perspective of cost function, taking the reaction distance, regression distance, and obstacle avoidance time into consideration. A representative example is that the cost function deviation rates of overtaking obstacle avoidance between static and dynamic seas reach 5.11%, 8.98% and 18.43%, respectively. The gradually increasing data shows that the virtual simulating method matches the drifting-off-course tendency of boats in rough seas. This includes acquiring perception information of navigation and simulating the motion and navigation processes for visualization. The platform provides new means for testing and evaluating the autonomous navigation performance of USVs.

Digital twin connection model based on virtual sensor

Digital twin connection model based on virtual sensor

Predicting geogenic groundwater arsenic contamination risk in floodplains using interpretable machine-learning model

Long-term exposure to geogenic arsenic (As)-contaminated groundwater poses a severe threat to public health problems. Generally, elevated As concentrations have been observed with high amounts of ammonium in groundwater of floodplains. An extreme gradient boosting algorithm was conducted to develop a probability model based on hydrogeochemical data, which predicted the occurrence rates of groundwater As on a regional scale. Results showed that concentrations of NH4+, Eh, K, Cl−, SO42−, and NO3− were powerful predictive variables of As exposure. The model revealed the co-enrichment of As with NH4+, suggesting that the mineralization of nitrogen-containing organic matter promoted the reduction of As-bearing iron-oxides. The predicted distribution of high-As groundwater showed high consistency with known spatial distribution of As contamination, and the model also accurately predicted As concentrations in Jiangbei Plain of China and typical As-affected floodplains of Southeast Asia. The model can serve as a low-cost and rapid virtual sensor for detecting As concentrations in private or newly drilled wells, thereby providing critical information for informed management decisions, environmental protection and public health safety.

Active control of impulsive scattered sound based on virtual sensing

Active control method is an important way to reduce the scattered radiation of 3D objects and render them acoustically invisible. Traditional active control requires the error sensor to be sufficiently close to the target area because the zone of quiet (ZoQ) is generated around the sensor; thus, the scattered noise cannot be eliminated at the remote position in situations wherein the microphone can only be placed near the scatterer. To solve this dilemma, this study proposed two methods of predicting and controlling the scattered sound, combined with adaptations of two commonly used virtual sensing (VS) methods: the auxiliary-filter-based virtual-sensing (AF-VS) and the remote microphone technique (RMT). Both methods are based on the correlation between signals to predict the scattered noise; therefore, ZoQ can be transferred to the non-near-field target position with fewer physical microphones. Further, the causal constraints need not be satisfied in the former method, which uses pre-trained auxiliary filters to implicitly estimate and control the scattered pressure at the target point. Whereas, the latter explicitly estimates the scattered component instead of the total sound pressure with the pre-modeled observation matrix, thereby avoiding the causality limitation of the RMT and reducing one estimation process. Experiments were conducted to suppress impulsive scattered sound using a dual-channel feedforward adaptive ANC system, and the attenuation performances of the two proposed methods were compared with those of the direct control of the desired noise with the optimal Wiener solution and the method without combining the VS. The results demonstrated the feasibility and effectiveness of the two active control methods for scattered sound using virtual sensors. Moreover, in the impulsive scattered sound control with a 300 Hz-1000 Hz carrier, the average noise reduction (NR) at the observation points reached approximately 18 dB, and a more stable and excellent performance was obtained using the latter method based on RMT. Therefore, this research provides a solution for the case of limited error sensor placement in scattered sound active control systems; and in addition, can be used to guide the choice of VS methods in scattered sound control applications.

A Semisupervised Just-In-Time Learning Framework Based on Local Label Propagation and Its Application to Industrial Virtual Sensing

A Semisupervised Just-In-Time Learning Framework Based on Local Label Propagation and Its Application to Industrial Virtual Sensing

Method of Virtual Sensor Design for Faulty Physical Sensor Replacement

The paper considers the problem of virtual sensor design for nonlinear dynamic systems with non-smooth nonlinearities described by continuous-time models for faulty physical sensor replacement. The main purpose of virtual sensors is generating the estimates of the unmeasured components of the considered system to provide additional information for effective control and fault diagnosis. Besides, virtual sensors can be used for faulty physical sensor replacement. The methods of virtual sensor design for solving this problem differ from standard procedure since information from faulty physical sensor does not use to design the virtual sensor replacing this sensor. It is assumed that to solve the problem, the system is equipped by diagnostic system allowing detecting faulty sensor. For every such a sensor, the virtual sensor generating estimate replacing the faulty sensor is designed. To solve the problem, so-called logic-dynamic approach is used which does not guarantee optimal solution but uses only methods of linear algebra to solve the problem for systems with non-smooth nonlinearities. This approach contains three steps. Initially, the nonlinear term is removed from system and linear model is designed. Then, a possibility to estimate the faulty sensor and to insert in the model the transformed nonlinear term is checked. Finally, stability of sensor is provided. The virtual sensor can be designed in identification canonical form or Jordan canonical form. The advantage of the first form is a standard procedure of the virtual sensor design while Jordan form allows obtaining simpler solution. The relations allowing designing the virtual sensor as in identification canonical as Jordan canonical form are derived.

In situ virtual sensors in building digital twins: framework and methodology

A novel sensing system is essential for intelligent building operations and digitalization of the building life cycle. Therefore, this study introduces the concept and framework of in situ virtual sensing in building operations, proposes modeling methodologies for in situ virtual sensors, and shows the applications of representative virtual sensors in a real operational system. The concept of in situ virtual sensing involves virtual sensors that are built, operated, verified/validated, and calibrated in operational buildings and the digital twins. Considering the virtual sensor purposes and available modeling resources, modeling methodologies are proposed to achieve the virtual sensing under limited modeling environments in the target building operation. Case studies showed an RMSE of approximately 0.5 °C during the winter season in the real buildings without experimental modeling environments (such as laboratory and manufacturing facilities). According to the findings and results, this study can contribute by providing in-depth insight into virtual sensing-driven building operations, digitalization, and intelligence.

Economic fatigue damage monitoring for vehicle fleets using the scattering transform

AbstractVehicle monitoring is an important prequisite for predictive maintenance applications. Virtual sensors can be deployed to establish relationships between fatigue related quantities of interest and readily available measurement data, which reduces the costs of monitoring for vehicle fleets. This work describes a data‐driven virtual sensing approach using the scattering transform and principal component analysis. These data transformations are used to obtain a reduced representation of acceleration data, which is suitable for the identification of fatigue critical events during vehicle operation. Results of a previous study using an eBike demonstrator are summarized and the methodology is applied to experimental data of a sensor equipped light rail vehicle. In both applications, fictitious fatigue damage contributions are estimated accurately and physical interpretations of the reduced representation are found.

Application of External Torque Observer and Virtual Force Sensor for a 6-DOF Robot

Application of External Torque Observer and Virtual Force Sensor for a 6-DOF Robot