Virtual Sensor Model Research Articles

Harnessing NOx emission management: A virtual sensor model for natural gas power generation engines with active pre-chamber

This paper presents a NOx Sensor machine learning model for a highly efficient 2MW power generation lean burn gas engine with an active pre-chamber. As gas power generation continues to evolve, engine efficiency and the accurate measurement of NOx emissions has taken on greater importance. However, the working life of existing NOx sensors pales in comparison to the lifecycle of an engine. This paper studies a series of machine learning NOx sensor models and carries out a comparative analysis. We introduce a predictive analytics model used for monitoring the emissions of active pre-chamber gas engines. This real deployment aims to detect the deviations in emissions across an entire fleet of gas engines, even when no physical sensors are installed in the engines. Finally, a model has been implemented that allows the prediction of NOx values, in engines that did not have them initially, with a 5–10 % precision. For example, with NOx at 120 ppm, the virtual sensor provides values close to +-10 ppm. It has been observed that such features as the setpoint value of the active pre-chamber gas pressure, in a lean burn gas engine with active pre-chamber, are among those parameters that have the greatest impact on the model estimation.

Virtual Sensing of Key Variables in the Hydrogen Production Process: A Comparative Study of Data-Driven Models.

Hydrogen is an ideal energy carrier manufactured mainly by the natural gas steam reforming hydrogen production process. The concentrations of CH4, CO, CO2, and H2 in this process are key variables related to product quality, which thus need to be controlled accurately in real-time. However, conventional measurement methods for these concentrations suffer from significant delays or huge acquisition and upkeep costs. Virtual sensors effectively compensate for these shortcomings. Unfortunately, previously developed virtual sensors have not fully considered the complex characteristics of the hydrogen production process. Therefore, a virtual sensor model, called "moving window-based dynamic variational Bayesian principal component analysis (MW-DVBPCA)" is developed for key gas concentration estimation. The MW-DVBPCA considers complicated characteristics of the hydrogen production process, involving dynamics, time variations, and transportation delays. Specifically, the dynamics are modeled by the finite impulse response paradigm, the transportation delays are automatically determined using the differential evolution algorithm, and the time variations are captured by the moving window method. Moreover, a comparative study of data-driven virtual sensors is carried out, which is sporadically discussed in the literature. Meanwhile, the performance of the developed MW-DVBPCA is verified by the real-life natural gas steam reforming hydrogen production process.

AI-Driven Virtual Sensors for Real-Time Dynamic Analysis of Mechanisms: A Feasibility Study

The measurement of the ground forces on a real structure or mechanism in operation can be time-consuming and expensive, particularly when production cannot be halted to install sensors. In cases in which disassembling the parts of the system to accommodate sensor installation is neither feasible nor desirable, observing the structure or mechanism in operation and quickly deducing its force trends would facilitate monitoring activities in industrial processes. This opportunity is gradually becoming a reality thanks to the coupling of artificial intelligence (AI) with design techniques such as the finite element and multi-body methods. Properly trained inferential models could make it possible to study the dynamic behavior of real systems and mechanisms in operation simply by observing them in real time through a camera, and they could become valuable tools for investigation during the operation of machinery and devices without the use of additional sensors, which are difficult to use and install. In this paper, the idea presented is developed and applied to a simple mechanism for which the reaction forces during operating conditions are to be determined. This paper explores the implementation of an innovative vision-based virtual sensor that, through data-driven training, is able to emulate traditional sensing solutions for the estimation of reaction forces. The virtual sensor and relative inferential model is validated in a scenario as close to the real world as possible, taking into account interfering inputs that add to the measurement uncertainty, as in a real-world measurement scenario. The results indicate that the proposed model has great robustness and accuracy, as evidenced by the low RMSE values in predicting the reaction forces. This demonstrates the model’s effectiveness in reproducing real-world scenarios, highlighting its potential in the real-time estimation of ground reaction forces in industrial settings. The success of this vision-based virtual sensor model opens new avenues for more robust, accurate, and cost-effective solutions for force estimation, addressing the challenges of uncertainty and the limitations of physical sensor deployment.

Design and simulation of a smart energy metering system

Power theft has been one of the main problems facing the power industry in Nigeria which had led to huge economic and infrastructural loss to the government and utility companies. Hence the need to proffer solution to this challenge, this research identified the various method of stealing energy which is meter by passing, connecting directly to the supply cable just before it gets to the meter terminal, resetting of meter reading, and deliberate non-payment of electricity bills, vandalism and unfaithful act of the utility employees. The causes and effect of energy theft where also identified to be customer taking electricity as part of social service from the government and also the inability of the utility companies to meter their customers. In finding solution to this problem, this thesis adopted the simulation of anti-tamper sensor (accelerometers, light, tilt, magnetic) using Proteus to create a virtual sensor model that can mimic the behavior of the physical sensors, SMS algorithm was programmed in such that it assumes the micro-controller (ADUINO) and a GSM module from the Proteus library was used, the connection was done using the appropriate serial communication pins. The result obtained shown that smart metering was successfully designed and simulation model accurately replicated the behavior of the energy meter, including measurements of voltage, current, and power consumption. The tampering energy meter seal using highly sensitive sensors to mitigate against energy theft by provide an additional layer of security against meter tampering with incorporated of sensor output information that can sent via by GSM Module to the cloud, which help to mitigate against meter tampering. The complete system software implementation and validation was done using Proteus and Arduino.

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring.

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation-including proper experimental settings or hyperparameter optimization-improved the root mean squared errors by 23-63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms' performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.

Improving Virtual Sensor Models by Censored Online Data

Digital twins are able to bridge the physical and the virtual world, which is especially useful in industrial environments. One small, but rather essential, kind of digital twin is the so called virtual sensor model. This type of model is used to enhance or replace a physical sensor in industrial settings to reduce costs or enable information retrieval from inaccessible locations within a machine or process. The virtual sensor model is usually trained once, whereat only a predefined amount of information without any adaptation possibilities on the clients side is provided. As manufacturers want to provide the possibility of custom adaptations for their clients, the virtual sensor models require to incorporate adaptive features, which also have to handle incomplete data recordings, e.g. uncensored data. Traditional offline machine learning approaches are often insufficient for such adaptive requirements, therefore the usage of online learning approaches is gaining increased attention, to avoid high computational, storage and temporal costs. This paper covers the continued training of such adaptive virtual sensor models, focusing on the handling and integration of censored online data. Different approaches to tackle the problems of catastrophic forgetting in online learning and correction of censored data are presented as well as the handling of censored data in online learning environments. The experiments sections compares various scenarios with and without censored data using an industrial dataset and demonstrates the positive influence of different online learning approaches.

Model based Verification and Validation of LiDAR sensor

This research paper presents the study of modelling and validating the results of simulation of LiDAR sensor with actual sensor data. The model can be further utilized for virtual testing of various ADAS functions. The virtual sensor is a physics-based sensor capable of emulating the real sensor. Initially an in-depth study of Velodyne VLP-16 sensor was carried out in order to parameterize the virtual sensor model. The sensor is modelled virtually in Gazebo simulation environment. Gazebo is used along with ROS (Robotic Operating Interface) in order to record the sensor data. Data conversion from sensor message format to Cartesian coordinates has been carried out. This was done in order to have a common format of actual and virtual data for validation. Four different objects were selected for validating the sensor data. The validation methodology is based on comparison of actual recorded data generated by Velodyne VLP-16 LiDAR and virtually generated data by the virtual LiDAR sensor model. The validation proves that the in case of static scenarios, the virtual lidar sensor model is 99 % accurate in measuring the range to the object. Although there is slight deviation from the actual value, it is in the acceptable limits.

Stereoscopic Camera-Sensor Model for the Development of Highly Automated Driving Functions within a Virtual Test Environment

The need for efficient and reproducible development processes for sensor and perception systems is growing with their increased use in modern vehicles. Such processes can be achieved by using virtual test environments and virtual sensor models. In the context of this, the present paper documents the development of a sensor model for depth estimation of virtual three-dimensional scenarios. For this purpose, the geometric and algorithmic principles of stereoscopic camera systems are recreated in a virtual form. The model is implemented as a subroutine in the Epic Games Unreal Engine, which is one of the most common Game Engines. Its architecture consists of several independent procedures that enable a local depth estimation, but also a reconstruction of a whole three-dimensional scenery. In addition, a separate programme for calibrating the model is presented. In addition to the basic principles, the architecture and the implementation, this work also documents the evaluation of the model created. It is shown that the model meets specifically defined requirements for real-time capability and the accuracy of the evaluation. Thus, it is suitable for the virtual testing of common algorithms and highly automated driving functions.

Evaluation of Perception Sensor Model Performance in Simulation based on Experimental Findings

The market introduction of automated driving functions poses a significant challenge in terms of safety validation, primarily due to the complexity of real traffic test cases. While virtual testing has emerged as a viable solution, the accurate replication of physical perception sensors in virtual environments remains a formidable task. This study presents an evaluation method for virtual perception sensors, specifically focusing on their performance in automated driving and real-driving behaviour scenarios. Real driving data from a proving ground is collected and integrated into a multi-body simulation software, employing a specialized toolbox for seamless conversion of recorded measurements into simulation-ready data. Virtual sensor models for LIDAR, Radar, and Camera, utilizing various machine learning approaches, are implemented within the simulation alongside commercial sensor models. The output of these models is compared to real measurement data using statistical metrics, including the Chebyshev Distance, Pearson Correlation Coefficient, and Cross-Correlation Coefficient. The evaluation highlights the accuracy and performance of the machine learning-based models and the importance of employing multiple metrics that consider both correlation and offset between simulated and measured data.

A Novel Virtual Sensor Modeling Method Based on Deep Learning and Its Application in Heating, Ventilation, and Air-Conditioning System

Realizing the dynamic redundancy of sensors is of great significance to ensure the energy saving and normal operation of the heating, ventilation, and air-conditioning (HVAC) system. Building a virtual sensor model is an effective method of redundancy and fault tolerance for hardware sensors. In this paper, a virtual sensor modeling method combining the maximum information coefficient (MIC) and the spatial–temporal attention long short-term memory (STA-LSTM) is proposed, which is named MIC-STALSTM, to achieve the dynamic and nonlinear modeling of the supply and return water temperature at both ends of the chiller. First, MIC can extract the influencing factors highly related to the target variables. Then, the extracted impact factors via MIC are used as the input variables of the STA-LSTM algorithm in order to construct an accurate virtual sensor model. The STA-LSTM algorithm not only makes full use of the LSTM algorithm’s advantages in handling historical data series information, but also achieves adaptive estimation of different input variable feature weights and different hidden layer temporal correlations through the attention mechanism. Finally, the effectiveness and feasibility of the proposed method are verified by establishing two virtual sensors for different temperature variables in the HVAC system.

A virtual sensor simulation system of a flower greenhouse coupled with a new temperature microclimate model using three-dimensional CFD

Greenhouse culture, as a high-yield and efficient production technology, has become an important means to increase crop yield and quality. Greenhouse environmental monitoring is a key practice affecting the yield and quality of greenhouse crops. Meeting the growth needs of crops while reducing the cost of environmental monitoring has become an urgent and difficult scientific problem. Sensor technology with the addition of computational fluid dynamics (CFD) technique is a new method for addressing this issue. However, this CFD approach generally cannot monitor the greenhouse environment in real time. This study aims to establish a virtual sensor system based on the external environment of a climate model to form a closed-loop network using a finite volume CFD code (ANSYS FLUENT 19.0). An experiment is conducted on a flower greenhouse, and a 3D transient CFD is implemented including a meshing and turbulence model in the MATLAB interface program. Furthermore, a temperature model based on the external greenhouse environment is established using a regression method from the model, and a virtual sensor model of greenhouse temperature is established using a feedback method. The results show that the simulation satisfied the temperature distribution law, revealing that virtual sensors and physical sensors can work together to monitor the greenhouse environment.

Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm

The Nitrogen Oxides (NOx) from engines aggravate natural environment and human health. Institutional regulations have attempted to protect the human body from them, while car manufacturers have tried to make NOx free vehicles. The formation of NOx emissions is highly dependent on the engine operating conditions and being able to predict NOx emissions would significantly help in enabling their reduction. This study investigates advanced method of predicting vehicle NOx emissions in pursuit of the sensorless engine. Sensors inside the engine are required to measure the operating condition. However, they can be removed or reduced if the sensing object such as the engine NOx emissions can be accurately predicted with a virtual model. This would result in cost reductions and overcome the sensor durability problem. To achieve such a goal, researchers have studied numerical analysis for the relationship between emissions and engine operating conditions. Also, a Deep Neural Network (DNN) is applied recently as a solution. However, the prediction accuracies were often not satisfactory where hyperparameter optimization was either overlooked or conducted manually. Therefore, this study proposes a virtual NOx sensor model based on the hyperparameter optimization. A Genetic Algorithm (GA) was adopted to establish a global optimum with DNN. Epoch size and learning rate are employed as the design variables, and R-squared based user defined function is adopted as the object function of GA. As a result, a more accurate and reliable virtual NOx sensor with the possibility of a sensorless engine could be developed and verified.

SOLVING THE PROBLEM OF INCOMPLETE INFORMATION ABOUT AN AUTOMATIC CONTROL OBJECT BASED ON REAL-TIME VIRTUAL SENSORS

Modern automatic control systems use built-in mathematical models for estimation of unmeasured by the direct methods parameters such as NOX emission in aeroengine low-emission combustion chamber. The two models of NOX emissions virtual sensor built into the controller are proposed. A stochastic nonlinear mathematical model is based on the Zeldovich equation. It applies the superposition principle of NOX production in diffusion and homogeneous flames. Probability density distribution functions of the air-fuel mixture concentration in these flames take into account both of a spatial non-uniformity of the mixture composition and a harmonic component of the acoustic waves generated by the heat release. The concept of integral relations models has been developed with the use of numerical modeling of spatial and temporal non-uniformities of the air-fuel mixture concentration (4D-metamodeling) and available experimental data. Another virtual sensor model is based on the neural network predicting NOX emission in gas turbine combustion chamber. The example of a neural network and results of its training on a real combustion chamber is presented. It is shown that the two or three-layer neural network having 20–30 neurons provides an acceptable error (not exceeding 10 %) of the NOX emission display and can be used as a virtual emission sensor in an engine control system. The normalized level of NOx emission per take-off and landing cycle is considered as a target function of the automatic control of low-emission combustion. To estimate the level of NOX emission a built-in virtual sensor is proposed.

Virtual NOx-emission sensors for robust aero engine automatic control system

Modern robust control systems use built-in mathematical models for estimation of unmeasured by the direct methods parameters such as NOx emission. The two models of NOx emissions virtual sensor built into the smart controller of an aero engine low-emission combustion chamber are proposed in this study. A stochastic nonlinear mathematical model is based on the Zeldovich equation. It applies the superposition principle of NOx production in diffusion and homogeneous flames. Probability density distribution functions of the air-fuel mixture concentration in these flames take into account both of a spatial non-uniformity of the mixture composition and a harmonic component of the acoustic waves generated by the heat release. The NOx generation rate is averaged over the fuel flow through diffusion and homogeneous flames based on the probability density distribution function. An exponentiality of a decrease in the generation rate along the length of the combustor space is proposed. The concept of integral relations models has been developed with the use of numerical modeling of spatial and temporal non-uniformities of the air-fuel mixture concentration (4D-metamodeling) and available experimental data. Another virtual sensor model is based on the neural network. A well-known approach of NOx emissions prediction used in monitoring systems of gas turbine power plants is applied. The example of a neural network and results of its training on a real combustion chamber is presented. It is shown that the two or three-layer neural network having 20… 30 neurons provides an acceptable error (not exceeding 10%) of the NOx emission display and can be used as a virtual emission sensor in an engine control system. The normalized level of NOx emission per take-off and landing cycle is considered as a target function of the automatic control of low-emission combustion. The estimation of the level of NOx emission by a built-in virtual sensor is proposed for robust aero engine automatic control.

Robust Fault Tolerant Control Design for Nonlinear Systems not Satisfying Matching and Minimum Phase Conditions

This paper proposes an adaptive sliding mode fault tolerant control design for lipschitz nonlinear system subject to simultaneous actuator and sensor faults. First, in order to estimate the system states, actuator and sensor faults, only one observer with an adaptive nonlinear gain is required where the minimum phase condition is relaxed to delectability and the matching condition is weakened to become a condition related to the system dimensions. Furthermore, our approach is applicable where there are faults greater than outputs. Next, a virtual sensor technique is developed to replace a failed, missing or corrupted sensor to provide a signal having the same effect of the nominal sensor. Then, this study provides an adaptive sliding mode fault tolerant control to achieve an optimal interaction between observer, virtual sensor and controller models. Thus, using the LMI technique with multiobjective optimization performance, sufficient conditions are derived to ensure the closed-loop Lipschitz nonlinear system stability and guarantee that the Lipschitz set of the adaptive sliding mode observer is a subset of the adaptive sliding mode control Lipschitz set. Two illustrative examples the first is the robotic manipulator model and the second is the longitudinal dynamics of the following vehicle system were performed to verify the effectiveness of the proposed approach.

A Virtual Pressure and Force Sensor for Safety Evaluation in Collaboration Robot Application.

Recent developments in robotics have resulted in implementations that have drastically increased collaborative interactions between robots and humans. As robots have the potential to collide intentionally and/or unexpectedly with a human during the collaboration, effective measures to ensure human safety must be devised. In order to estimate the collision safety of a robot, this study proposes a virtual sensor based on an analytical contact model that accurately estimates the peak collision force and pressure as the robot moves along a pre-defined path, even before the occurrence of a collision event, with a short computation time. The estimated physical interaction values that would be caused by the (hypothetical) collision were compared to the collision safety thresholds provided within ISO/TS 15066 to evaluate the safety of the operation. In this virtual collision sensor model, the nonlinear physical characteristics and the effect of the contact surface shape were included to assure the reliability of the prediction. To verify the effectiveness of the virtual sensor model, the force and pressure estimated by the model were compared with various experimental results and the numerical results obtained from a finite element simulation.

Nonlinear Dynamic Soft Sensor Modeling With Supervised Long Short-Term Memory Network

Soft sensor has been extensively utilized in industrial processes for prediction of key quality variables. To build an accurate virtual sensor model, it is very significant to model the dynamic and nonlinear behaviors of process sequential data properly. Recently, a long short-term memory (LSTM) network has shown great modeling ability on various time series, in which basic LSTM units can handle data nonlinearities and dynamics with a dynamic latent variable structure. However, the hidden variables in the basic LSTM unit mainly focus on describing the dynamics of input variables, which lack representation for the quality data. In this paper, a supervised LSTM (SLSTM) network is proposed to learn quality-relevant hidden dynamics for soft sensor application, which is composed of basic SLSTM unit at each sampling instant. In the basic SLSTM unit, the quality and input variables are simultaneously utilized to learn the dynamic hidden states, which are more relevant and useful for quality prediction. The effectiveness of the proposed SLSTM network is demonstrated on a penicillin fermentation process and an industrial debutanizer column.

Virtual Integration Platforms and Sensor Models in the Context of ADAS Functions Performance Testing & Validation

Virtual Integration Platforms and Sensor Models in the Context of ADAS Functions Performance Testing & Validation

Adaptive virtual sensors using SNPER for the localized construction and elastic net regularization in nonlinear processes

Traditional data-driven virtual sensors were constructed upon the macro-perspective of the manifold structure using generalized models. They did not focus on the local relationships among the data samples through micro-perspective of manifold proximity indicating the local relationships among the data samples. In the case with the quantity of data points fewer than the dimensions of the data variables, the virtual sensor model is likely to be unstable, ill-conditioned, and computationally expensive. And the real-world data often vary with time. It is difficult, in the long term, to sustain good performance by a single fixed model. This paper addresses the aforementioned issues by proposing three algorithms (NPER, SNPER, and LW-SNPER) to successively improve the virtual sensor modeling performance for nonlinear, high-dimensional and time-varying processes. It is shown through the numerical cases and a real semiconductor process that the proposed algorithms perform better than the other regular regression algorithms.

Virtual Sensor of Surface Electromyography in a New Extensive Fault-Tolerant Classification System.

A few prosthetic control systems in the scientific literature obtain pattern recognition algorithms adapted to changes that occur in the myoelectric signal over time and, frequently, such systems are not natural and intuitive. These are some of the several challenges for myoelectric prostheses for everyday use. The concept of the virtual sensor, which has as its fundamental objective to estimate unavailable measures based on other available measures, is being used in other fields of research. The virtual sensor technique applied to surface electromyography can help to minimize these problems, typically related to the degradation of the myoelectric signal that usually leads to a decrease in the classification accuracy of the movements characterized by computational intelligent systems. This paper presents a virtual sensor in a new extensive fault-tolerant classification system to maintain the classification accuracy after the occurrence of the following contaminants: ECG interference, electrode displacement, movement artifacts, power line interference, and saturation. The Time-Varying Autoregressive Moving Average (TVARMA) and Time-Varying Kalman filter (TVK) models are compared to define the most robust model for the virtual sensor. Results of movement classification were presented comparing the usual classification techniques with the method of the degraded signal replacement and classifier retraining. The experimental results were evaluated for these five noise types in 16 surface electromyography (sEMG) channel degradation case studies. The proposed system without using classifier retraining techniques recovered of mean classification accuracy was of 4% to 38% for electrode displacement, movement artifacts, and saturation noise. The best mean classification considering all signal contaminants and channel combinations evaluated was the classification using the retraining method, replacing the degraded channel by the virtual sensor TVARMA model. This method recovered the classification accuracy after the degradations, reaching an average of 5.7% below the classification of the clean signal, that is the signal without the contaminants or the original signal. Moreover, the proposed intelligent technique minimizes the impact of the motion classification caused by signal contamination related to degrading events over time. There are improvements in the virtual sensor model and in the algorithm optimization that need further development to provide an increase the clinical application of myoelectric prostheses but already presents robust results to enable research with virtual sensors on biological signs with stochastic behavior.