Variable Transformation Research Articles

Few-Shot Metering Anomaly Diagnosis with Variable Relation Mining

Metering anomalies not only mean huge economic losses but also indicate the faults of equipment and power lines, especially within the substation. As a result, metering anomaly diagnosis is becoming one of the most important missions in smart grids. However, due to the insufficient and imbalanced anomaly cases, identifying the anomalies in smart meter data accurately and efficiently remains challenging. Existing methods usually employ few-shot learning models in computer vision directly, which requires the rich experience of human experts and sufficient abnormal cases for training. It blocks model generalizing to various application scenarios. To address these shortcomings, we propose a novel framework for metering anomaly diagnosis based on few-shot learning, named FSMAD. Firstly, we design a fault data injection model to emulate anomalies, so that no abnormal samples are required in the training phase. Secondly, we provide a learnable variable transformation to reveal inherent relationships among various smart meter data and help FSMAD extract more efficient features. Finally, the deeper metric network is equipped to support FSMAD in obtaining powerful comparison capability. Extensive experiments on a real-world dataset demonstrate the advantages of our FSMAD over state-of-the-art methods.

A numerical study of thermal and diffusion effects on MHD Jeffrey fluid flow over a porous stretching sheet with activation energy

The primary aim of this research work is to develop a mathematical model for the two-dimensional steady incompressible flow of a Jeffrey fluid over a vertical stretching sheet immersed in a Darcy porous medium. The combined effects of Soret and Dufour numbers, activation energy, viscous dissipation, thermal radiation, mixed convection, and Joule heating are included in the energy and concentration equations within this model. Using appropriate similarity variable transformations, the governing partial differential equations were altered into nonlinear ordinary differential equations and then solved numerically using the Runge-Kutta-Fehlberg method along with the shooting technique. The impact of various physical parameters on concentration, velocity, and temperature profiles is deployed through graphs. The velocity increased with a gradual increment in the values of the viscous ratio, thermal, and solutal stratification parameters, whereas the reverse trend was noticed for the magnetic strength. The temperature diminishes as the Prandtl number increases, whereas the opposite scenario exists for Eckert and Dufor numbers and radiation. The fluid concentration rises for a monotonic increment of the Soret number, while it reduces as the Schmidt number, activation energy, and reaction constraint escalate. The amplification of skin friction is observed with an increase in magnetic field strength, while it decreases with an increasing viscous ratio factor. The Nusselt number decreases as radiation increases and the Eckert number rises, but the opposite scenario occurs with increases in the Prandtl number. The Sherwood number is heightened by an increase in the Schmidt number, reaction, and activation energy factors. Moreover, the numerical values of skin friction and the Nusselt number are compared with the previously published work, demonstrating excellent agreement between the results.

Fault current limiter principle by switching magnetic circuit

AbstractSeveral types of fault current limiters have been studied so far, including superconductor based one or nonsuperconductor based one. However, it is difficult to satisfy all requirements for cost, maintainability, and current limiting performance. This study proposes another type of fault current limiter, variable transformer based one. It is supposed to be less expensive and easier to be maintained since it is based on the conventional transformer, and to be expected better current limiting performance since the magnetic circuit of the transformer is drastically changed. The magnetic circuit of the transformer is switched to be opened and to produce another one by shifting a portion of its iron core mechanically, allowing the primary and secondary electric circuit to be magnetically isolated. In that way, the electromotive force of the secondary winding could be reduced so that the secondary current could be limited. The prototype based on this concept was designed and built up, and its stational performance has been investigated. As a result, it was confirmed that the prototype shows good current limiting performances identical to the results of the previous FE analysis. Furthermore, the prototype was connected to the operating mechanism to investigate the transient performances, and as a result, satisfying current limiting performances are confirmed

Grading diffuse glioma based on 2021 WHO grade using self-attention-base deep learning architecture: variable Vision Transformer (vViT)

Purpose:To evaluate the diagnostic performance of the self-attention-based model, termed variable Vision Transformer (vViT), in the task of predicting the grade of diffuse glioma based on the 2021 World Health Organization (WHO) central nervous system (CNS) tumor classification. Materials and Methods:This cross-sectional study analyzed adult patients with histopathologically confirmed diffuse glioma, following the 2021 WHO CNS tumor classification. We used age, sex, radiomic features, and four MRI sequences to predict the grade of gliomas. As binary classifications, we constructed three models: 2 vs. 3/4 (326 patients with 1575 grade 2 and 1574 grade 3/4 images), 3 vs. 2/4 (330 patients with 1726 grade 3 and 1726 grade 2/4 images), and 4 vs. 2/3 (333 patients with 3292 grade 4 and 3292 grade 2/3 images). As a multiclass classification, we constructed a 2 vs. 3 vs. 4 model (334 patients with 1575 grade 2, 1575 grade 3, and 1575 grade 4 images). Metrics including accuracy and area under the curve of the receiver operating characteristic (AUC-ROC) were calculated. Results:The highest accuracy and AUC-ROC were 0.84 (95% confidence interval; 0.75–0.93) in multiclass classification (2 vs. 3 vs. 4) and 0.94 (0.88–0.98) in 4 vs. 2/3, respectively. The highest Cohen’s κ coefficient between ground truth and the predicted value was 0.54 obtained in the multiclass classification (2 vs. 3 vs. 4). Conclusions:The vViT is a competent multi-modal deep-learning model that can predict the grade of gliomas which were classified based on the 2021 WHO CNS tumor classification.

Procedure for Determining the Upper Bound on Absolute Error for LVDT Sensors

This paper presents the procedure for determining the upper bound on absolute error (UBAE) for linear variable differential transformer (LVDT) sensors without inter-winding capacitance. This procedure is based on the results of a parametric identification of the sensor, from which the coefficient values of the corresponding transfer function are obtained. The UBAE is then determined by a simulation experiment using dedicated computational software. The error value and the shape of the input signal, which is constrained in magnitude, are determined. The calculations and additional validation of the procedure presented in this article are carried out using the MathCad 5.0 program. As the basis for the proposed procedure, we review issues related to the modelling of LVDT sensors without inter-winding capacitance. The solutions presented here can be used to determine the UBAE, which can then be used to assess the accuracy of these types of sensor and their mutual comparability in terms of dynamic accuracy.

Invariant analysis, exact solutions, and conservation laws of time fractional thin liquid film equations

This present paper investigates Lie symmetry analysis, one-dimensional optimal system, exact solutions and conservation laws of the (2 + 1)-dimensional time fractional thin liquid film equations (TFTLFE) with Riemann–Liouville fractional derivative. Explicitly, we obtain six vector fields and the one-dimensional optimal system admitted by TFTLFE. Then, we perform the symmetry reductions with the help of Erdélyi–Kober fractional differential operator and (2 + 1)-dimensional TFTLFE is reduced into (1 + 1)-dimensional fractional partial differential equations (FPDEs). Additionally, by means of compound variable transformation and the power series expansion method, the solution of reduced FPDEs is obtained and its convergence is verified. Moreover, we derive other solutions for the reduced equations taking advantage of the invariant subspace method. Furthermore, the conservation laws are also established utilizing generalized Noether's theorem. Finally, we construct the exact solution using the method of conservation laws.

Design and Application of a Miniature Pneumatic Bellows Loading Device for In-Situ Tensile Testing inside the Scanning Electron Microscope

A miniature pneumatic bellows device was designed for in-situ testing inside the scanning electron microscope. The device uses a pneumatic actuator to load the specimen and displacement is directly monitored with a linear variable differential transformer sensor. Its application allowed the direct monitoring of microstructural and defect evolution in materials at the micro scale. The data produced by this testing device, in combination with measurements from micro digital image correlation, were successfully used to model the crystal plasticity of a martensitic/bainitic steel at the microstructural length scale.

A Quick and Comprehensive Method for Determining Static ATC with NRS and VFT

Electricity market players prioritize available transfer capability (ATC) as an attractive solution. Market participants can gain a financial advantage through accurate and fast ATC solutions. In order to provide a suitable and valuable solution, we use differential load flow equations. A dynamic system's entire time-domain trajectory can be solved by this method, along with a fictional time-domain differential equation. This article uses Newton-Raphson-Seydel instead of Newton-Raphson, which can also be used to determine voltage stability. A variable frequency transformer (VFT) was used in this study to increase and control transmission power. A 50% time saving on small systems was achieved with the proposed method, which was applied to seven different systems. In addition, it performed better on large systems by more than 90%. This proposal for static ATC presents promising results and can be applied to online applications.

DeepWind: a heterogeneous spatio-temporal model for wind forecasting

Deep learning (DL) has shown great potential in enhancing the performance of traditional numerical weather prediction (NWP) methods in weather forecasting. Certain applications such as wind power generation desire more accurate wind predictions which is challenging due to limited observations and complex dynamics. To this end, this paper introduces a DL-based heterogeneous network named DeepWind for NWP correction, which can simultaneously correct the NWP of diverse wind variables across multiple weather stations. In particular, it first exerts the meteorological domain knowledge to achieve an effective transformation of target variables and then develops a heterogeneous neural network to learn spatio-temporal representations. A novel difference loss function is further designed for stable temporal learning. Moreover, this study might be the first to expose an underlying evaluation problem in deep forecasting, which we call evaluation inconsistency, thereby necessitating the assessment of model performance across diverse evaluation metrics. Experimental results demonstrate the superiority of the proposed approach over strong DL baselines, which makes it positioned for deployment in the real-world production environment. Source code is released at https://github.com/Rittersss/DeepWind.

Type‐2 fuzzy‐based adaptively predictive controlled variable frequency transformer coordinated to SMES for improved load frequency control

AbstractTraditionally, phase shifters powered by power electronics are used in conjunction with energy storage devices to improve the load frequency control. Conventional phase shifters provide minimal inertia and offer a significant threat to power quality due to harmonics. This study suggests the type‐2 fuzzy based adaptively predictive controlled variable frequency transformer (F2‐APC‐VFT) as a phase shifter to work in coordination with superconducting magnetic energy storage (SMES) for improved load frequency control. To assess the effectiveness of coordinated control, a two‐area, four‐machine linked power system with F2‐APC‐VFT installed in succession with the connecting line near to area one and SMES in the other area is employed. A type‐2 fuzzy controller is used to tune the cost function weights of the adaptive predictive controller (APC). A simulation study is conducted in MATLAB to show the effectiveness of the suggested strategy. Tuning the cost function weights with a type‐2 fuzzy controller considerably impacts in minimising the frequency and tie‐power deviations. The effectiveness of the F2‐APC is verified by comparing its performance with that of an adaptive neuro fuzzy inference system (ANFIS) controller and constant weight‐based adaptive predictive controller (C‐APC).

Estimation of Poverty Measures for Small Areas Under a Two-fold Nested Error Linear Regression Model: Comparison of Two Methods

Demand for reliable statistics at a local area (small area) level has greatly increased in recent years. Traditional area-specific estimators based on probability samples are not adequate because of small sample size or even zero sample size in a local area. As a result, methods based on models linking the areas are widely used. World Bank focused on estimating poverty measures, in particular poverty incidence and poverty gap called FGT measures, using a simulated census method, called ELL, based on a one-fold nested error model for a suitable transformation of the welfare variable. Modified ELL methods leading to significant gain in efficiency over ELL also have been proposed under the one-fold model. An advantage of ELL and modified ELL methods is that distributional assumptions on the random effects in the model are not needed. In this article, we extend ELL and modified ELL to two-fold nested error models to estimate poverty indicators for areas (say a state) and subareas (say counties within a state). Our simulation results indicate that the modified ELL estimators lead to large efficiency gains over ELL at the area level and subarea level. Further, modified ELL method retaining both area and subarea estimated effects in the model (called MELL2) performs significantly better in terms of mean squared error (MSE) for sampled subareas than the modified ELL retaining only estimated area effect in the model (called MELLI). AMS Subject Classification: 62D05, 62G09

Soliton resolution for the complex short-pulse positive flow with weighted Sobolev initial data in the space-time soliton regions

The Riemann Hilbert approach and ∂‾ steepest descent method are used to study the Cauchy problem of a new complex short-pulse positive flow, from which the long-time asymptotics and soliton resolution conjecture for the complex short-pulse positive flow with initial conditions is obtained in weighted Sobolev spaces. Resorting to the spectral analysis of Lax pair, the introduced transformations of field variables and transformations of independent variables, we establish the basic Riemann-Hilbert problem, and convert the solution of the Cauchy problem of the complex short-pulse positive flow into the corresponding solution of the Riemann Hilbert problem. The jump matrix then expands and deforms continuously over the initial contour. We finally obtain the long-time asymptotics and soliton resolution for the complex short-pulse positive flow in the soliton region by using the ∂‾ steepest descent method. The results also show that N-soliton solutions of the complex short-pulse positive flow are asymptotically stable.

Variable linear transformation improved physics-informed neural networks to solve thin-layer flow problems

Physics-informed neural networks (PINNs) have attracted wide attention due to their ability to seamlessly embed the learning process with physical laws and their considerable success in solving forward and inverse differential equation (DE) problems. While most studies are improving the learning process and network architecture of PINNs, less attention has been paid to the modification of the DE system, which may play an important role in addressing some limitations of PINNs. One of the simplest modifications that can be implemented to all DE systems is the variable linear transformation (VLT). Therefore, in this work, we propose the VLT-PINNs that solve the DE systems of the linear-transformed variables instead of the original ones. To clearly illustrate the importance of prior knowledge in determining the VLT parameters, we choose the thin-layer flow problems as our focus. Ten related cases were tested, including the jet flows, wake flows, mixing layers, boundary layers and Kovasznay flows. Based on the principle of normalization and for a better match of the DE system to the preference of NNs, we identify three principles for determining the VLT parameters: magnitude normalization for dependent variables (principle 1), local normalization for independent variables (principle 2), and appropriate scaling for physics-related parameters in inverse problems (principle 3). The VLT-PINNs with the VLT parameters suggested by the proposed principles show excellent performance over all the test cases, while the results are quite poor with the VLT parameters suggested by traditional linear transformations, such as nondimensionalization and global normalization. Comparison studies also show that only under the constraints of the VLT principles can we obtain satisfactory results. Besides, we find tanh is more appropriate as the activation function than sin for thin-layer flow problems, from both posteriori results and priori analyses with physical intuition. We highlight that our VLT method is an attempt to combine the three advantages of accuracy, universality and simplicity, and hope that it can provide new insights into the better integration of prior knowledge, physical intuition and the nature of NNs. The code for this paper is available on https://github.com/CAME-THU/VLT-PINN.

Borrower‐based macroprudential measures and credit growth: How biased is the existing literature?

AbstractThis paper analyzes over 700 estimates from 34 studies on the impact of borrower‐based measures (such as loan‐to‐value, debt‐to‐income, and debt‐service‐to‐income ratios) on bank loan provision. Our dataset reveals notable fragmentation in the literature concerning variable transformations, methods, and estimated coefficients. We run a meta‐analysis on a subsample of 422 semi‐elasticities from 23 studies employing a consistent estimation framework to draw an economic interpretation. We confirm strong publication bias, particularly against positive and statistically insignificant estimates. After correcting for this bias, the effect indicates a credit growth reduction of −0.6 to −1.1 percentage points following the occurrence of borrower‐based measures, significantly lower than the unadjusted simple mean effect of the collected estimates. Additionally, our study examines the contexts of these estimates, finding that beyond publication bias, model specification and estimation method are vital in explaining the variation in reported coefficients.

A deep learning modeling framework with uncertainty quantification for inflow-outflow predictions for cascade reservoirs

Accurate prediction of reservoir inflows and outflows and their uncertainties is essential for managing water resources and establishing early-warning systems. However, this can be a formidable challenge due to numerous uncertainties, particularly in cascade reservoir systems. To seamlessly quantify aleatoric (data-caused) and epistemic (model network–caused) uncertainties simultaneously in a single framework, we estimated the posterior distribution of parameters in a Bayesian neural network while measuring prediction variance to reflect the noise in data. By randomly discarding certain units within the network, the estimated posterior distribution can be combined with a new loss function. This sophisticated deep learning framework for a long short-term memory network has also included advanced supporting approaches, such as input variable selection, data transformation, and hyperparameter optimization. The model trained in this study was applied to two cascade reservoir systems with four reservoirs in Vietnam, providing uncertainty estimates from two distinct sources. Comparing three global reservoir operation schemes, we found that the proposed model achieved superior performance in all cases, and uncertainty in the forecasts was due primarily to data noise, rather than uncertainty in the model itself. Preprocessing data using a wavelet transform can reduce noise that the model cannot classify on its own, resulting in improved performance, particular with longer lead times. The satisfactory performance of the prediction results confirms that the framework can effectively assess the uncertainty of hydrologic predictions using deep learning.

A novel 6-dimensional force measurement based on the electric 6-DOF loading device

The 6-degrees-of-freedom (6-DOF) platform has gained popularity in industry owing to its advantages, especially in indoor simulation experiment requiring six-dimensional force environments. However, up to date, the measurement of such six-dimensional forces is challenging due to complex structures, difficult decoupling, and high costs. In this study, an electric 6-DOF loading device designed by ourselves is presented, with an ability to load high precision displacement and force. To measure the six-dimensional force of the device’s moving platform, this paper proposes a scheme involving embedding tension-compression sensors in each leg of the device and describes the mechanical model of the device. Then a novel method with a variable transformation matrix is proposed, complemented by a decoupling study that optimizes the variable transformation matrix. Finally, we validate the proposed method through an external force loading experiment. The results indicate that the error in Fy experiment is less than 2.7%, and the error in Fz experiment is less than 1.6%. The novel method exhibits high accuracy, easy installation, fast response, and low cost.

Development and evaluation of regression tree models for predicting in-hospital mortality of a national registry of COVID-19 patients over six pandemic surges.

Objective prognostic information is essential for good clinical decision making. In case of unknown diseases, scarcity of evidence and limited tacit knowledge prevent obtaining this information. Prediction models can be useful, but need to be not only evaluated on how well they predict, but also how stable these models are under fast changing circumstances with respect to development of the disease and the corresponding clinical response. This study aims to provide interpretable and actionable insights, particularly for clinicians. We developed and evaluated two regression tree predictive models for in-hospital mortality of COVID-19 patient at admission and 24 hours (24 h) after admission, using a national registry. We performed a retrospective analysis of observational routinely collected data. Two regression tree models were developed for admission and 24 h after admission. The complexity of the trees was managed via cross validation to prevent overfitting. The predictive ability of the model was assessed via bootstrapping using the Area under the Receiver-Operating-Characteristic curve, Brier score and calibration curves. The tree models were assessed on the stability of their probabilities and predictive ability, on the selected variables, and compared to a full-fledged logistic regression model that uses variable selection and variable transformations using splines. Participants included COVID-19 patients from all ICUs participating in the Dutch National Intensive Care Evaluation (NICE) registry, who were admitted at the ICU between February 27, 2020, and November 23, 2021. From the NICE registry, we included concerned demographic data, minimum and maximum values of physiological data in the first 24 h of ICU admission and diagnoses (reason for admission as well as comorbidities) for model development. The main outcome measure was in-hospital mortality. We additionally analysed the Length-of-Stay (LoS) per patient subgroup per survival status. A total of 13,369 confirmed COVID-19 patients from 70 ICUs were included (with mortality rate of 28%). The optimism-corrected AUROC of the admission tree (with seven paths) was 0.72 (95% CI: 0.71-0.74) and of the 24 h tree (with 11 paths) was 0.74 (0.74-0.77). Both regression trees yielded good calibration and variable selection for both trees was stable. Patient subgroups comprising the tree paths had comparable survival probabilities as the full-fledged logistic regression model, survival probabilities were stable over six COVID-19 surges, and subgroups were shown to have added predictive value over the individual patient variables. We developed and evaluated regression trees, which operate at par with a carefully crafted logistic regression model. The trees consist of homogenous subgroups of patients that are described by simple interpretable constraints on patient characteristics thereby facilitating shared decision-making.

Finite‐time stabilization for a class of more general p‐normal nonlinear systems with input and output nonlinearities

AbstractThis study investigates the global finite‐time state feedback stabilization for a class of more general p‐normal nonlinear systems subjects to input time‐delay and uncertain output function under rational powers. A novel control input compensation signal comprising a finite integral of previous control values is presented, and an equivalent system with control input dependent‐free time delay is obtained by introducing a variable transformation technique that includes the compensation signal. A suitable controller is designed in line with the homogeneous domination method to ensure the globally finite‐time stability of the closed‐loop system. Finally, the effectiveness of the proposed control scheme is verified through a numerical simulation and an induction heater circuit system.

Clinical comparison of marginal fit of ceramic inlays between digital and conventional impressions.

The aim of this stuldy was to compare the clinical marginal fit of CAD-CAM inlays obtained from intraoral digital impression or addition silicone impression techniques. The study included 31 inlays for prosthodontics purposes of 31 patients: 15 based on intraoral digital impressions (DI group); and 16 based on a conventional impression technique (CI group). Inlays included occlusal and a non-occlusal surface. Inlays were milled in ceramic. The inlay-teeth interface was replicated by placing each inlay in its corresponding uncemented clinical preparation and taking interface impressions with silicone material from occlusal and free surfaces. Interface analysis was made using white light confocal microscopy (WLCM) (scanning area: 694 × 510 µm2) from the impression samples. The gap size and the inlay overextension were measured from the microscopy topographies. For analytical purposes (i.e., 95-%-confidence intervals calculations and P-value calculations), the procedure REGRESS in SUDAAN was used to account for clustering (i.e., multiple measurements). For p-value calculation, the log transformation of the dependent variables was used to normalize the distributions. Marginal fit values for occlusal and free surfaces were affected by the type of impression. There were no differences between surfaces (occlusal vs. free). Gap obtained for DI group was 164 ± 84 µm and that for CI group was 209 ± 104 µm, and there were statistical differences between them (p = .041). Mean overextension values were 60 ± 59 µm for DI group and 67 ± 73 µm for CI group, and there were no differences between then (p = .553). Digital impression achieved inlays with higher clinical marginal fit and performed better than the conventional silicone materials.

Development of a Creep Mechanical Frame Setting Based on Arcan Test

Abstract Structural adhesive bonding has several advantages compared to other assembly techniques such as welding and riveting. Yet, creep is an important long-term phenomenon that needs to be considered for the design of such joints. To investigate this aspect, experimental investigations are needed at the scale of the adhesive layer. At such a scale, Arcan setting presents several advantages compared to other existing tests (analysis of different loads, limited edge effects) and was thus chosen for the development of an experimental approach aiming at providing creep characterization of adhesive layers. A mechanically operated testing machine was thus developed and is presented herein. To measure local strains of the adhesive layer, two linear variable differential transformer sensors are fixed on a support placed on the beaks of the Arcan sample according to two directions: normal and tangential to the bonded surface. The developed system (mechanical system and strain measurement) proved to be successful in investigating the creep behavior of adhesive layers while varying several parameters (load levels, type of load, temperature, adhesive thickness).