To facilitate the ongoing transition to fourth-generation district heating systems, it is necessary to find resource-efficient methods to model the differential pressure in a district heating network ...accurately. This paper has developed, tested, and compared data-driven methods to create a soft sensor for a pressure transmitter in the district heating network. The sensor is used to control the district heating load and therefore, is the most critical spot of the sensor network. The data-based modelling approaches chosen were transfer functions and neural networks. The data set was collected from Hafslund Oslo Celsio’s historical database for January–March 2021, when the heating demand is highest. The best convolutional neural network and a first-order transfer function give acceptable results in estimating the pressure transmitter signal. Both models have the simplest architectures within their model type, suggesting that the need for complex models in either approach is redundant.
Display omitted
•Modelling approaches in deriving a soft sensor for the differential pressure in a district heating system.•Full description of the process of deriving a purely data-driven model for a pressure transmitter soft sensor.•Presents a soft sensor for a pressure transmitter with an accuracy of 0.018 (Convolutional Neural Network) and 0.021 (System Identification).
Environmental Data Science Gibert, Karina; Horsburgh, Jeffery S.; Athanasiadis, Ioannis N. ...
Environmental modelling & software : with environment data news,
08/2018, Letnik:
106
Journal Article
Recenzirano
Environmental data are growing in complexity, size, and resolution. Addressing the types of large, multidisciplinary problems faced by today's environmental scientists requires the ability to ...leverage available data and information to inform decision making. Successfully synthesizing heterogeneous data from multiple sources to support holistic analyses and extraction of new knowledge requires application of Data Science. In this paper, we present the origins and a brief history of Data Science. We revisit prior efforts to define Data Science and provide a more modern, working definition. We describe the new professional profile of a data scientist and new and emerging applications of Data Science within Environmental Sciences. We conclude with a discussion of current challenges for Environmental Data Science and suggest a path forward.
•Data Science connects data with decisions by producing actionable knowledge from data and bridging the Hammond’s Fact Gap.•Environmental Sciences can benefit from the added value given by Data Science, which is strategic in complex systems.•Historical and contemporary views of Environmental Data Science and emerging environmental applications are given.•Data Science requires new professional skills. Multidisciplinary working teams are very convenient.•Environmental Data Science involve signifficant challenges, making a promising research field in short, mid and long term.
Linear power flow model is advantageous for the fast operational analysis and the efficient optimization of the power systems. In this letter, we propose a hybrid physical model-driven and ...data-driven approach for linearizing power flow model. In this proposed approach, the linear power flow model contains two parts, i.e., the existing physical-equation-based linear power flow model and the linearized error model. The linearized errors are obtained by the partial least squares regression based data-driven approach. The proposed linear power flow model can retain the useful inherent information from the physical model and utilize the ability of data analysis to extract the inexplicit linear relationship. Simulations on the four test systems have validated that the proposed hybrid linear model exhibits a much better performance on the branch power flow calculation than other linear power flow models.
With the rapid development of computational techniques and scientific tools, great progress of data-driven analysis has been made to extract governing laws of dynamical systems from data. Despite the ...wide occurrences of non-Gaussian fluctuations, the effective data-driven methods to identify stochastic differential equations with non-Gaussian Lévy noise are relatively few so far. In this work, we propose a data-driven approach to extract stochastic governing laws with both (Gaussian) Brownian motion and (non-Gaussian) Lévy motion, from short bursts of simulation data. Specifically, we use the normalizing flows technology to estimate the transition probability density function (solution of non-local Fokker–Planck equations) from data, and then substitute it into the recently proposed non-local Kramers–Moyal formulae to approximate Lévy jump measure, drift coefficient and diffusion coefficient. We demonstrate that this approach can learn the stochastic differential equation with Lévy motion. We present examples with one- and two-dimensional decoupled and coupled systems to illustrate our method. This approach will become an effective tool for discovering stochastic governing laws and understanding complex dynamical behaviours.
This article is part of the theme issue ‘Data-driven prediction in dynamical systems’.
Inverse dynamics is a common tool for determining human joint torques during walking. The traditional approaches rely on ground reaction force and kinematics measurements prior to analysis. A novel ...real-time hybrid method is proposed in this work by integrating a neural network and dynamic model that only requires kinematic data. An end-to-end neural network for direct joint torque estimation is also developed based on kinematic data. The neural networks are trained on a variety of walking conditions, including starting and stopping, sudden speed changes, and asymmetrical walking. The hybrid model is first tested in a detailed dynamic gait simulation (OpenSim) which results in root mean square errors less than 5 N.m and a correlation coefficient of greater than 0.95 for all the joints. Experiments demonstrate that the end-to-end model on average outperforms the hybrid model across the whole test when compared to the gold standard approach which requires both kinetic and kinematic information. The two torque estimators are also tested on one participant wearing a lower limb exoskeleton. In this case, the hybrid model (R>0.84) has significantly better performance than the end-to-end neural network (R>0.59). This indicates that the hybrid model is better applicable to scenarios which differ from the training data.
Poorly assembled or faulty rotors often behave nonlinearly. The accurate extraction of weak nonlinear features is a vital issue. This paper proposes to extract the partial dynamic properties of ...concern for nonlinear feature based rotor condition monitoring. The realization of this concept relies on a novel tailored data-driven NARX (Nonlinear Auto Regressive with eXogenous input) modelling approach. The tailored NARX model represents part of the system’s dynamic properties of concern. The details are first to use the harmonic product spectrum to determine the rotational speed of the inspected rotor system. After that, the least mean squares method is used to extract the harmonic components from the measured vibration signal. The low-order harmonics of concern are then reconstructed for the tailored NARX modelling. Then the Nonlinear Output Frequency Response Functions are evaluated from the tailored NARX model as features for rotor condition monitoring. Finally, the proposed method is validated by simulation and experiment cases. The results show that the obtained features based on the proposed tailored NARX modelling approach are more robust and more accurate than conventional methods when assessing rotor faults. The proposed approach provides a reference for the inspection of the assembly quality of components such as bearings and the on-line health monitoring of rotating machinery.
Data assimilation, i.e., upgrading a numerical model by using experimental observations, is applied to adapt the performances of a simulation-based digital twin (DT) of a semi-industrial combustion ...furnace, based on available experimental data. More specifically, we rely on Kalman filter (KF) to adjust the prediction of our model by accounting for the underlying uncertainties. The DT is obtained by combining dimensionality reduction (through Proper Orthogonal Decomposition, POD) and regression (using Kriging) applied to Reynolds-averaged Navier–Stokes simulations of the furnace covering a three-dimensional design space, including both geometric and operational parameters. The experimental campaign concerns the measurement of the axial and radial profile of temperature inside the chamber and the NO concentrations at the outlet of the furnace, for a fuel mixture ranging from pure methane to pure hydrogen. Two types of KF algorithms are analyzed, i.e. the steady-state and the recursive ones. Both methodologies demonstrate improved DT performances, highlighting the significance of the Kalman gain in weighing the model’s prediction and measurement uncertainties. We also conduct a sensitivity analysis of data errors to reinforce this concept. The results of our study demonstrate the potential of data assimilation to build accurate and adaptive reduced-order models of realistic combustion systems.
•Data assimilation approach is discussed for a combustion furnace.•A digital twin model and experiments have been performed for the furnace.•Steady-state and recursive Kalman filter algorithms are discussed.•Temperature field and NO emissions are the updated variables by the Kalman filter.•The impact of uncertainties in the data assimilation framework is assessed.
•This work provides a data-driven modelling framework for the research of contact/impact process between complex contacting surfaces.•Indoor experiment rig between complex contacting surfaces is ...manufactured and displayed.•A neural-network-based contact force model between barrel and bourrelet is established.•Results obtained confirm that the proposed model can achieve high accuracy and also present excellent generalization ability.
Proper modelling of contact/impact phenomenon is critical to ensure reliable description of the overall dynamic behaviors of mechanical systems. The past few decades witnessed substantial developments on contact/impact dynamics modelling, especially for the smooth contacting surfaces, like spheres or cylinders. Contrastingly, less attention has been paid to the urgent modelling demand for complex contacting bodies. By utilizing the data-driven modelling framework based on artificial neural network, this paper aims to provide a new and feasible scheme for the research of contact/impact process between complex contacting surfaces. Taking the contact/impact process between barrel and bourrelet as our research object, the indoor experiment rig is manufactured and displayed for the first time. Measurement results collected under different initial indentation velocities serve as the training datasets of the learning process for the data-driven normal contact force model. After that, the optimum hyper-parameters of the neural network, mainly including the performance index, activation function, structure of network, and learning algorithms, are tuned for the contact/impact process between barrel and bourrelet through trail-and-error method. Eventually, the neural-network-based normal contact force model can be established, of which the prediction performance for interaction modelling is further analyzed and verified. Simulation results confirm that the proposed data-driven normal contact force model can achieve high accuracy and also present excellent generalization ability. Great agreements with the experimental results under the chosen network structure demonstrate the effectiveness of data-driven interaction modelling methodology presented for complex contacting geometries.