Damage Detection and Localization under Variable Environmental Conditions Using Compressed and Reconstructed Bayesian Virtual Sensor Data

Structural health monitoring (SHM) with a dense sensor network and repeated vibration measurements produces lots of data that have to be stored. If the sensor network is redundant, data compression is possible by storing the signals of selected Bayesian virtual sensors only, from which the omitted signals can be reconstructed with higher accuracy than the actual measurement. The selection of the virtual sensors for storage is done individually for each measurement based on the reconstruction accuracy. Data compression and reconstruction for SHM is the main novelty of this paper. The stored and reconstructed signals are used for damage detection and localization in the time domain using spatial or spatiotemporal correlation. Whitening transformation is applied to the training data to take the environmental or operational influences into account. The first principal component of the residuals is used to localize damage and also to design the extreme value statistics control chart for damage detection. The proposed method was studied with a numerical model of a frame structure with a dense accelerometer or strain sensor network. Only five acceleration or three strain signals out of the total 59 signals were stored. The stored and reconstructed data outperformed the raw measurement data in damage detection and localization.

An Innovative Modelling Approach Based on Building Physics and Machine Learning for the Prediction of Indoor Thermal Comfort in an Office Building

In this paper, an innovative hybrid modelling technique based on machine learning and building dynamic simulation is presented for the prediction of indoor thermal comfort feedback from occupants in an office building in Le Bourget-du-Lac, Chambéry, France. The office was equipped with Internet of Things (IoT) environmental sensors. A calibrated building energy model was created for the building using optimisation tools. Thermal comfort was collected using a portable device. A machine learning (ML) model was trained using collected feedback, environmental data from IoT devices and synthetic datasets (virtual sensors) extracted from a physics-based model. A calibrated energy model was used in co-simulation with the predictive method to estimate comfort levels for the building. The results show the ability of the method to improve the prediction of occupant feedback when compared to traditional thermal comfort approaches of about 25%, the importance of information extracted from the physics-based model and the possibility of leveraging scenario evaluation capabilities of the dynamic simulation model for control purposes.

Increasing the efficiency of electric submersible pumps by using big data processing and machine learning technologies

The current coverage of oil wells with telemetry does not allow timely determination of deviations in the operation of about 40% of electric submersible pumps. To solve this problem, a model of virtual sensors has been developed that allows the prediction of temperature and pressure growth at the pump intake in the absence of submersible sensors based on modern big data processing and machine learning technologies. The developed models of virtual sensors are embedded directly into the process control system, which allows notifying the technologists and operators about a possible reduction in the planned average pump operating time and their possible failures for various reasons.

A field-oriented control (FOC) method using the virtual currents for the induction motor drive

<span lang="EN-US">An improving field-oriented control technique without current sensors is proposed to control rotor speed for an induction motor drive. The estimated stator currents based on the slip frequency are used instead of feedback current signals in the FOC loop. The reference signals and the estimated currents through computation steps are used to generate the control voltage for the switching inverter. Simulations were performed in Matlab/Simulink environment at rated speed and low-speed range to demonstrate the method's feasibility. Through simulation results, the FOC method using virtual sensors has proved its effectiveness in ensuring the stable operation of the IMD over a wide speed range.</span>

Orchestrating Heterogeneous Devices and AI Services as Virtual Sensors for Secure Cloud-Based IoT Applications

The concept of the cloud-to-thing continuum addresses advancements made possible by the widespread adoption of cloud, edge, and IoT resources. It opens the possibility of combining classical symbolic AI with advanced machine learning approaches in a meaningful way. In this paper, we present a thing registry and an agent-based orchestration framework, which we combine to support semantic orchestration of IoT use cases across several federated cloud environments. We use the concept of virtual sensors based on machine learning (ML) services as abstraction, mediating between the instance level and the semantic level. We present examples of virtual sensors based on ML models for activity recognition and describe an approach to remedy the problem of missing or scarce training data. We illustrate the approach with a use case from an assisted living scenario.

Feasibility of A Neural Network-Based Virtual Sensor for Vehicle Unsprung Mass Relative Velocity Estimation

With the automotive industry moving towards automated driving, sensing is increasingly important in enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long–Short Term Memory (BiLSTM) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which were used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors to estimate vehicle unsprung mass relative velocity.

SIMULATION MODEL OF THE BRUSH CUTTER ROTOR WITH SIX BLADES

Brush cutters are used in forestry for the care of forest plantations in operations for cutting unwanted tree and shrub vegetation (TSV). Rotors can be used as working bodies. The rotor we are considering is a flywheel, on the outer sides of which the blades are hinged. When cutting DKR with blades, a cutting moment arises, which is transmitted through the knife to the axis of its rotation and then to the shaft driving the flywheel. When designing a brush cutter structure, the impact from the cutting forces of the DKR is decisive for the choice of drive power and rotor parameters. We designed the brush cutter rotor in CAD Solidworks to study the cutting process of the DKR. Its geometric and mass parameters were set; the kinematic links of the links were established. The input motion characteristics were set in the Motion Solidworks module and the cutting moment was applied to the knives. Virtual sensors were installed on the model to record movement characteristics. As a result of a computer experiment for three options, which differ in cutting force and the presence of a damper, the trajectories of the knives and the power consumption of the drive were established