Search

The thermal decomposition and sintering kinetics of microfine magnesite were investigated to inaugurate a new One-step process for preparing high-density sintered magnesia. The optimal parameters for the discharging particle size of magnesite through ball milling were determined using an orthogonal experiment and Three-Way Measures ANOVA. The model for the thermal decomposition process of microfine magnesite was established through TGA-DSC and nonlinear regression analysis. Meanwhile, by describing the sintering process of microfine magnesite in detail through microstructure and CTE, the kinetic mechanisms of grain growth at different sintering stages were obtained. The results revealed that increasing the ratio of ball to powder can quickly obtain microfine magnesite which the bulk density reaches 3.45 g·cm−3 after One-step sintering. The thermal decomposition process required an activation energy of only 124.98 kJ·mol−1, which is much lower than existing technology and followed the Two-dimensional phase boundary reaction mechanism R 2. Additionally, the densification process was dominated alternatively by grain boundary diffusion and volume diffusion. This paper provided a detailed theoretical basis and leads a new direction in the One-step preparation of high-density sintered magnesia. [ABSTRACT FROM AUTHOR]

• Machine learning (ML) techniques were pioneered to analyze non-linear relationships. • Algorithm's predictive power validated ML models, preventing spurious relations. • Recursive feature elimination explored predictor importance. • Presence of non-linear relationships is suggested, advising further investigation. • Acknowledgment of skepticism stresses rigorous analysis for long-term correlations. The Earth's climate is a complex system that can be influenced by various internal and external factors. Previous research has explored the relationship between climate and external forcings such as solar activity and GCR. However, the relations are intricate and intertwined into almost chaotic meteorological measurements. This paper delves deeper into understanding their interactions. GCR flux, Sunspot number (SSN), total solar irradiance (TSI), UV irradiance (UVI), and the Oceanic Niño Index (ONI) are the predictor variables, while total cloud amount (TCA) and low cloud amount (LCA) are the response variables. The analysis begins with standard statistical techniques and continues with multiple regression models including random forest, which is a machine learning (ML) method that can be used for non-linear regression. Subsequently, Recursive Feature Elimination (RFE) is employed to scrutinize the correlation among the predictor parameters. In the ML model, the final 25% of the dataset is held out and tested for validation, so, the predictive power of the algorithm is measured. Both geographical and temporal patterns have been investigated. This study suggests that a non-linear relationship might exist between the parameters, and should be investigated further, particularly in specific regions of the world. [ABSTRACT FROM AUTHOR]

This paper focuses on researching the various factors that influence the material melting rate during the hot air melting process. To achieve this purpose, the paper proposes a melting model for Acrylonitrile-Butadiene-Styrene (ABS) plastic under hot air heating based on Computational Fluid Dynamics (CFD). Orthogonal experiments were conducted based on the parameter range of each factor obtained in the pre-experiment. The results showed that the outlet distance, hot air velocity, hot air temperature, and their interaction items are important factors that affect the melting rate of ABS materials. Based on the simulation results, a multiple nonlinear regression model was constructed to predict the melting rate under different parameters. Comparing the simulation values with the predicted values of the multiple nonlinear regression model, the error between the two was no >10%, indicating the effectiveness of the prediction model. The research results can help guide the hot air welding melting process for different materials and characteristics, and provide a certain reference value for the development of hot air welding technology. • Welding of airbag labels was performed using hot air welding technology; • Realizes real-time monitoring of melt quality during the material melting process • Using CFD modeling to study the effects of outlet distance, hot air velocity, and hot air temperature on the melting rate. [ABSTRACT FROM AUTHOR]

• New perturbed relative motion equations are derived. • Periodic orbits of deputy satellite are obtained numerically. • One, two, and three loops periodic orbits are analyzed. • The velocity and position of deputy satellite are also analyzed. • Single variable regression model developed to find the true anomaly initial value. This paper presents a novel dynamical system for the perturbed relative motion of deputy satellite. The governing equations are derived in the LVLH frame under the second zonal harmonic coefficient effect of the Earth on both chief and deputy satellites. An extended numerical analysis on the deputy satellite motion is performed, where the initial state vector of deputy satellite and eccentricity of chief satellite are used as initial conditions for finding its own periodic orbits. The interior loops of periodic orbits are obtained using numerical integrator RKEOM. Such orbits are analysed for different parameters and their stability are also discussed, where these orbits have considerable importance in the resonance analysis of motion The second zonal harmonic coefficient effect on the periodicity, initial position, initial true anomaly is studied, alongside exploring these orbits with one, two and three loops. Furthermore, a single variable nonlinear regression model is developed to predict initial true anomaly using eccentricity of chief satellite's orbit. [ABSTRACT FROM AUTHOR]

Oil price forecasting is one of the most challenging issues since it is noisy, non-stationary, and chaotic. In this paper, we design a Bayesian Nonlinear Quantile method consisting of a Threshold Improved model and an Adaptive MCMC model to improve predicting performance. Specifically, the threshold improve model is introduced to solve the problems caused by the completely asymmetric distribution, and the Adaptive MCMC model is used to get the optimal threshold. Besides, the two-stage framework is applied to improve traditional methods' performance, including the Indirect GARCH model and Asymmetric Slope model. The experimental results show that our approach provides a promising alternative to oil price prediction, and the framework also improve the performance of the traditional methods. The contribution of this paper is to improve the accuracy of the oil price forecasting model, and the framework applies to other energy prices as well. [ABSTRACT FROM AUTHOR]

In this paper we provide the first solution to the challenging problem of designing a globally convergent estimator for the parameters of the standard model of a continuous stirred tank reactor. Because of the presence of non-separable exponential nonlinearities in the system dynamics that appear in Arrhenius law, none of the existing parameter estimators is able to deal with them in an efficient way and, in spite of many attempts, the problem was open for many years. To establish our result we propose a novel procedure to obtain a suitable nonlinearly parameterized regression equation and introduce a radically new estimation algorithm—derived applying the Immersion and Invariance methodology—that is applicable to these regression equations. A further contribution of the paper is that parameter convergence is exponential and is guaranteed with weak excitation requirements. To achieve this remarkable property we rely on the utilization of a recently introduced parameter estimator that seamlessly combines a classical least-squares search with the dynamic regressor extension and mixing estimation procedure. • A globally convergent estimator for the parameters of a CSTR. • A novel procedure to obtain a suitable nonlinearly parameterized regression equation of the CSTR. • Parameter convergence is guaranteed with extremely weak excitation requirements. [ABSTRACT FROM AUTHOR]

The construction of noise maps is of great significance for the management and control of urban noise and the protection of residents' physical and mental health. The European Noise Directive recommends using computational methods to construct strategic noise maps when possible. The current noise maps based on model calculation rely on complex noise emission and propagation models, and their huge number of regional grids needs to consume a lot of calculation time. This seriously restricts the update efficiency of noise maps, making it difficult to realize large-scale application and real-time dynamic update of noise maps. In order to improve the computational efficiency of noise maps, based on big data-driven technology, this paper combines the traditional CNOSSOS-EU noise emission modeling method with the multivariate nonlinear regression modeling method, and proposes an efficient calculation method of large-region dynamic traffic noise maps based on hybrid modeling method. First, this paper constructs the (daily and nightly) noise contribution prediction models of road sources with different classes, considering the daily and nightly periods and different urban road classes. Parameters of the proposed model are evaluated by using the multivariate nonlinear regression method to replace the complex nonlinear acoustic mechanism modeling. On this basis, in order to further improve the computational efficiency, noise contribution attenuations of the constructed models are parameterized and evaluated quantitatively. And then, the database containing the index table of the road noise sources-receivers and the corresponding noise contribution attenuations is constructed. The experimental results show that compared with the traditional calculation methods based on acoustic mechanism model, the noise map calculation method based on hybrid model proposed in this paper greatly reduces the model computations of noise map, improves the efficiency of noise mapping. It will provide technical support for constructing dynamic noise maps of large urban regions. Overall framework diagram of the proposed traffic noise mapping method. The schematic diagram of efficient update of the constructed dynamic noise map. [Display omitted] • A method of large-region traffic noise maps based on hybrid modeling is proposed. • The method is independent of acoustic calculation software and generous monitors. • The sound pressure level contribution prediction models are developed. • The method is applicable to hourly dynamic update of large-region noise maps. • The method is flexible, expandable and with great portability. [ABSTRACT FROM AUTHOR]

Highlights • The paper contributes set-membership regression (SMR), a new approach to nonlinear parameter estimation under measurement uncertainty. • Links between SMR and both guaranteed parameter estimation and classical statistical inference are investigated. • Several approaches to describing tight enclosures of the SMR regions using complete- search methods are developed. • Case studies are presented to illustrate various theoretical and computational aspects of SMR. Abstract This paper introduces set-membership nonlinear regression (SMR), a new approach to nonlinear regression under uncertainty. The problem is to determine the subregion in parameter space enclosing all (global) solutions to a nonlinear regression problem in the presence of bounded uncertainty on the observed variables. Our focus is on nonlinear algebraic models. We investigate the connections of SMR with (i) the classical statistical inference methods, and (ii) the usual set-membership estimation approach where the model predictions are constrained within bounded measurement errors. We also develop a computational framework to describe tight enclosures of the SMR regions using semi-infinite programming and complete-search methods, in the form of likelihood contour and polyhedral enclosures. The case study of a parameter estimation problem in microbial growth is presented to illustrate various theoretical and computational aspects of the SMR approach. [ABSTRACT FROM AUTHOR]

Highlights • Generating Pareto curves to show the optimal trade-off between Robustness and Performance. • Find the optimal PI and PID controller for First-Order and Integrating Plus Delay Processes. • Investigating the difference between ideal and serial PID, and the impact of filtering. • Comprehensive comparison between optimal-, SIMC- and "improved" SIMC-tuning. Abstract The first-order plus delay process model with parameters k (gain), τ (time constant) and θ (delay) is the most used representation of process dynamics. This paper has three objectives. First, we derive optimal PI- and PID-settings for this process. Optimality is here defined as the minimum Integrated Absolute Error (IAE) to disturbances for a given robustness level. The robustness level, which is here defined as the sensitivity peak (M s), may be regarded as a tuning parameter. Second, we compare the optimal IAE-performance with the simple SIMC-rules, where the SIMC tuning parameter τ c is adjusted to get a given robustness. The "original" SIMC-rules give a PI-controller for a first-order with delay process, and we find that this SIMC PI-controller is close to the optimal PI-controller for most values of the process parameters (k , τ , θ). The only exception is for delay-dominant processes where the SIMC-rule gives a pure integrating controller. The third objective of this paper is to propose and study a very simple modification to the original SIMC-rule, which is to add a derivative time τ d = θ /3 (for the serial PID-form). This gives performance close to the IAE-optimal PID also for delay-dominant processes. We call this the "improved" SIMC-rule, but we put "improved" in quotes, because this controller requires more input usage, so in practice the original SIMC-rule, which gives a PI-controller, may be preferred. [ABSTRACT FROM AUTHOR]

[Display omitted] Fibrillar dry adhesives have shown great potential in many applications thanks to their tunable adhesion, notably for pick-and-place handling of fragile objects. However, controlling and monitoring alignment with the target objects is mandatory to enable reliable handling. In this paper, we present an in-line monitoring system that allows optical analysis of an array of individual fibrils (with a contact radius of 350 µm) in contact with a smooth glass substrate, followed by the prediction of their adhesion performance. Images recorded at maximum compressive preload represent characteristic contact signatures that were used to extract visual features. These features, in turn, were used to create a linear model and to train different linear and non-linear regression models for predicting adhesion force depending on the misalignment angle. Support vector regression and boosted tree models exhibited highest accuracies and outperformed an analytical model reported in literature. Overall, this new approach enables predictions in gripping objects by contact observations in near real-time, which likely improves the reliability of handling operations. [ABSTRACT FROM AUTHOR]

Given that blade machining errors can substantially degrade aeroengine performance and reliability, there is a critical imperative to implement stringent control over blade machining errors during the manufacturing process. Nevertheless, the prevailing complexity surrounding the numerous machining error types and their obfuscated interrelationships impedes the comprehensive control of blade profile errors. Consequently, unveiling the nonlinear relationships between the distinct machining errors represents a task of paramount importance. To uncover these nonlinear relationships, this work pioneers the application of factor analysis and Genetic Algorithm-optimized BP neural networks to enable nonlinear regression for diverse blade machining errors. Specifically, this paper first constructs an orthogonal factor analysis model to reduce the dimensionality of complex, high-dimensional blade machining error data and extract underlying correlations. This analysis reveals three distinct error groups, each dominated by a latent common factor. Building on these factor analysis outputs, GA-BP neural networks are then leveraged to perform nonlinear regression for intra-group errors. Guided by the Maximal Information Coefficients (MIC) between different errors, we identify control error types within each group to serve as network inputs, with other errors designated as outputs. To prevent overfitting and accelerate convergence of the neural network, Monte Carlo method is used to augment the limited raw error dataset. The augmented data trains the GA-BP network, establishing multivariate nonlinear models with control errors as independent variables and other errors as dependent variables. The model accuracy is validated by a separate validation set. The comparisons between the predicted and true values in the validation set reveal that the relative errors are around 5 %, indicating that the models achieve an accuracy of approximately 95 %. These results demonstrate the satisfactory performance of the established models. Overall, this work elucidates previously unclear relationships between distinct blade machining errors. These new insights establish the foundation for comprehensive error control and will directly benefit blade design, manufacturing, and performance. [ABSTRACT FROM AUTHOR]

This paper presents a novel method for determining the fundamental frequency and modeling slender masonry structures, which is particularly relevant in the context of structural dynamics. This research evaluates the effectiveness of machine learning techniques, specifically artificial neural networks (ANN), and regression methods, including multiple linear regression (MLR) and multiple nonlinear regression (MNLR), in predicting the fundamental frequency of structures, considering both their geometrical and mechanical properties. The objective is to provide a comprehensive comparison of these methods, emphasizing their benefits, limitations, and potential applications in structural health monitoring. The ANN model demonstrated superior performance to linear and non linear regression methods. The findings could significantly impact both theoretical understanding and practical applications in this field. Moreover, this work paves the way for future research, potentially leading to the creation of more accurate and efficient predictive models for slender masonry structures. This methodology ensures a thorough understanding of the model's behavior and its responsiveness to variations in input parameters. • Comprehensive Database: Robust database of slender masonry structures' characteristics. • Empirical Formulations: New empirical formulas for predicting slender structure frequencies. • ANN Model: ANN model for frequency prediction of slender masonry structures. • Parametric Analysis: Study on geometrical/mechanical parameters' impact on frequency. • Future Research: Groundwork for refining models, ANN identified as the precise model. [ABSTRACT FROM AUTHOR]

Accurate cluster photovoltaic power prediction (CPPP) is crucial for the operation and control of renewable energy grid-connected power systems. The traditional modeling strategies for CPPP such as direct aggregation (DA) and statistical upscaling (SU) have limitations such as error accumulation and upscaling factor uncertainty. To address these issues, this paper proposed a novel hybrid approach for CPPP by combining machine learning models with an improved SU technique. Firstly, a robust broad learning system (BLS) model, in which the Generalized Maximum Correntropy Criterion (GMCC) is used to replace the original mean square error (MSE) loss in BLS, is proposed to solve the problem of multiple outliers affecting the prediction accuracy of regional cluster stations, and it is called GBLS. Then, the Relevance Vector Machine (RVM) as an effective nonlinear regression model is further utilized to compensate for the prediction errors obtained by the GBLS to form the hybrid prediction model, namely GBLS-RVM. Moreover, to mitigate the uncertainty associated with scaling factors in traditional SU strategy, a new SU strategy is developed to refine the relationship between the reference station and the cluster sub-region, enabling direct modeling for regional power prediction. Finally, data from two PV clusters in different regions of China are used to validate the effectiveness of the proposed model, and the results show that under the improved SU strategy, the GBLS-RVM model, reduced RMSE by approximately 33.7% compared to the traditional BLS model, and the RMSE decreased by 12.89% and 30.2% when compared to traditional DA and traditional SU strategies. • A novel hybrid method for CPPP is developed by combining ML and improved SU technique. • A BLS with GMCC (GMCC-BLS) as a prediction model is developed to handle the outliers in measurement data. • An innovative error correction strategy based on RVM is proposed to improve prediction reliability. • A new SU technique is used to establish direct relationships between reference stations and subregions. [ABSTRACT FROM AUTHOR]

• Single-layered 2D nanosheets of α-ZrP were obtained through exfoliation. • Free amine groups were covalently attached to the single-layered α-ZrP nanosheets. • AF-ZrP shows an extraordinarily high adsorption capacity for Pb2+ and Congo red dye. • Non-linear regression methods are more accurate compared to linear methods. This paper reports a facile route for preparing single-layered and crystalline 2D nanosheets of α-zirconium phosphate (α-ZrP), which were further functionalized through covalent attachment of amino organosilane on its exfoliated surfaces (AF-ZrP) to enhance their sorption capacity for Pb2+ and Congo red removal. Two possible surface arrangements of NH 2 groups were observed: one as free amine groups without bonding and the other as protonated or hydrogen-bonded amine groups. AF-ZrP exhibits extraordinary adsorption capacities of 1640 and 1213 mg g−1 for removing Pb2+ ions and CR dye. Further, linear and non-linear regression methods have been studied and compared for fitting four adsorption isotherm models and two kinetics models. Non-linear Freundlich isotherm and non-linear pseudo-second order kinetic models prove the most suitable. The high adsorption capacity, easy regeneration, and reusability rendered AF-ZrP a suitable adsorbent for removing Pb2+ ions and Congo red (CR) dye at industrial scale. [ABSTRACT FROM AUTHOR]

Deep neural operators, such as DeepONet, have changed the paradigm in high-dimensional nonlinear regression, paving the way for significant generalization and speed-up in computational engineering applications. Here, we investigate the use of DeepONet to infer flow fields around unseen airfoils with the aim of shape constrained optimization, an important design problem in aerodynamics that typically taxes computational resources heavily. We present results that display little to no degradation in prediction accuracy while reducing the online optimization cost by orders of magnitude. We consider NACA airfoils as a test case for our proposed approach, as the four-digit parameterization can easily define their shape. We successfully optimize the constrained NACA four-digit problem with respect to maximizing the lift-to-drag ratio and validate all results by comparing them to a high-order CFD solver. We find that DeepONets have a low generalization error, making them ideal for generating solutions of unseen shapes. Specifically, pressure, density, and velocity fields are accurately inferred at a fraction of a second, hence enabling the use of general objective functions beyond the maximization of the lift-to-drag ratio considered in the current work. Finally, we validate the ability of DeepONet to handle a complex 3D waverider geometry at hypersonic flight by inferring shear stress and heat flux distributions on its surface at unseen angles of attack. The main contribution of this paper is a modular integrated design framework that uses an over-parametrized neural operator as a surrogate model with good generalizability coupled seamlessly with multiple optimization solvers in a plug-and-play mode. • Generating an efficient and inexpensive surrogate model based on DeepONets. • The surrogate model is invariant to the low or high-dimensional parameterizations. • Prediction of flow field is used for various cost functions in the optimization loop. • Computing drag to lift ratio using the inferred high-dimensional flow field. • Integration of the Dakota optimization framework with the DeepONet surrogate. [ABSTRACT FROM AUTHOR]

In this paper, a novel adaptive stable backstepping controller(BSC) based on support vector regression (SVR) has been introduced for nonlinear dynamical systems. Stable BSC is designed over Lyapunov stability of the closed-loop system. The nonlinear system dynamics required to constitute the BSC architecture are identified via SVR. The prediction competency of SVR and the stable behavior of BSC are aggregated in this architecture for nonlinear systems. The performance evaluation of the proposed adaptive BSC has been examined on a nonlinear inverted pendulum(IP) and a nonlinear mass–spring–damper(NMSD) system. The acquired results provide a successful and stable BSC control performance for both nonlinear systems. [ABSTRACT FROM AUTHOR]

One of the most versatile and powerful algorithms for the identification of nonlinear dynamical systems is the NARMAX (Nonlinear Auto-regressive Moving Average with eXogenous inputs) approach. The model represents the current output of a system by a nonlinear regression on past inputs and outputs and can also incorporate a nonlinear noise model in the most general case. In recent papers, one of the authors introduced a NARX (no noise model) formulation based on Gaussian Process (GP) regression and derived the corresponding expressions for Higher-order Frequency Response Functions (HFRFs). This paper extends the theory for the GP-NARX framework by providing a means of converting the GP prediction bounds in the time domain into bounds on the HFRFs. The approach is demonstrated on the Duffing oscillator. [ABSTRACT FROM AUTHOR]

The increasing penetration of distributed energy sources demands higher observability of the distribution networks for better scheduling, operation, dispatching and control. However, the huge amounts of nodes in the distribution networks implies that any additional measuring instrument would be of huge costs burden for DSO. In this paper, we proposes a full-scale framework for line parameters, topology, phase label estimation and angle recovery utilizing smart meter measurements only for the non- μ PMU distribution networks. Firstly, we linearize the three-phase power flow model and induce the relationship of nodal voltage magnitudes and power injections. Then, a joint estimation method based on linear regression and topology characteristics is proposed to find line parameters, topology, and phase label. Finally, the nodal angle information is recovered by non-linear regression based on the estimation result. Simulations on both single-phase and three-phase networks are implemented. The results suggest that the proposed framework can provide an accurate estimation result with limited measurements. • Linearized power flow-based method to estimate line parameters without nodal angle. • It enables topology identification, phase labeling and nodal angle recovery. • The required data can be obtained from smart meters under current standards. [ABSTRACT FROM AUTHOR]

Shield jamming due to insufficient thrust force poses a critical hazard in mechanised tunnelling through squeezing ground. The time-dependency of squeezing due to creep can substantially alter the thrust force requirements, and the use of existing design tools that neglect it might therefore be misleading for the feasibility assessment of mechanised tunnelling or the design of the tunnel boring machine (TBM). This paper develops an equation for estimating the required thrust force in creeping rock under squeezing conditions during ongoing TBM advance, as well as during construction standstills. The method uses and extends the applicability of existing design nomograms through design equations established via multiparametric nonlinear regression, considering the results of 12,300 transient numerical simulations that cover a wide range of in-situ stresses and ground, TBM, and creep parameters relevant in tunnelling practice. The proposed method approximates the numerical results with sufficient accuracy to provide a reliable basis for decision-making during design and a valuable tool for fast assessments of the shield jamming risk. Its versatility and suitability in practical situations are demonstrated via two application examples from the Fréjus safety gallery and the Gotthard base tunnel. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of estimating remaining surgery duration (RSD) from surgical video frames. We propose a Bayesian long short-term memory (LSTM) network-based Deep Negative Correlation Learning approach called BD-Net for accurate regression of RSD prediction as well as estimation of prediction uncertainty. Our method aims to extract discriminative visual features from surgical video frames and model the temporal dependencies among frames to improve the RSD prediction accuracy. To this end, we propose to train an ensemble of Bayesian LSTMs on top of a backbone network by the way of deep negative correlation learning (DNCL). More specifically, we deeply learn a pool of decorrelated Bayesian regressors with sound generalization capabilities through managing their intrinsic diversities. BD-Net is simple and efficient. After training, it can produce both RSD prediction and uncertainty estimation in a single inference run. We demonstrate the efficacy of BD-Net on publicly available datasets of two different types of surgeries: one containing 101 cataract microscopic surgeries with short durations and the other containing 80 cholecystectomy laparoscopic surgeries with relatively longer durations. Experimental results on both datasets demonstrate that the proposed BD-Net achieves better results than the state-of-the-art (SOTA) methods. A reference implementation of our method can be found at: https://github.com/jywu511/BD-Net. • A novel Bayesian LSTM-based deep negative correlation learning network called BD-NET; • BD-Net can estimate both remaining surgery duration and prediction uncertainty; • Comprehensive validation on two publicly available datasets. [ABSTRACT FROM AUTHOR]

Circular hollow sections (CHS) are widely used in construction, particularly in space structures. This paper aims at investigating the feasibility of employing a machine leaning approach to predict the axial strength of longitudinal branch plate-to-CHS connections subjected to branch loadings. Using nonlinear finite element analysis, numerical models are developed for the connections subjected to tensile or compressive branch loading. The difference between the load–displacement responses for the connections under compressive and under tensile loading is established. Furthermore, the influence of various geometric and material parameters on the strength is investigated in depth. Using the results, two different strength models for the prediction of both tensile and compressive strength of longitudinal branch plate-to-CHS T-connections are developed. One prediction model is attained using traditional nonlinear regression analysis, and the other model is attained through symbolic regression. Finally, theoretical predictions are compared with numerical results, and strengths predicted with current design methodologies. [ABSTRACT FROM AUTHOR]

• One-dimensional freezing numerical simulation of frozen sand molds. • The relative curvature of ice-water interface decreases first and then increases. • The freezing behavior of wet sand depends on various frozen sand characteristics. • Multiple nonlinear regression shows reliable predictive results for freezing time. The essence of the freezing process in frozen sand molds is the heat transfer issue within the water-containing porous medium. In this paper, the evolutionary mechanism of the water-ice phase interface in frozen sand molds was studied through simulations and experiments at the mesoscale. Firstly, the evolutions of the phase field and temperature field during the unidirectional freezing process of frozen sand molds with different pore structures were investigated through numerical simulations. Then, utilizing the low-temperature freezing in-situ characterization platform, the nucleation mechanism of ice crystal bonding bridges between sand particles of varying materials was explored. The influence of sand mold characteristics on the freezing behavior of frozen sand molds was evaluated by the unique variable principle. Additionally, power function relationships for freezing time of frozen sand molds with different scales and materials were established, enabling the prediction of the time required for complete freezing of frozen sand molds. According to the results of multiple nonlinear regression analysis, the model showed reliable accuracy in predicting the time for fully frozen. This work will provide a valuable reference for further research on the engineering application of frozen sand molds. [ABSTRACT FROM AUTHOR]

• Improved method in a class of ill-conditioned parameter estimation problems. • A subset selection criterion based on MSE for the estimates. • Statistical analysis to compare the proposed and conventional methods. • Performance comparison through two case studies: linear and nonlinear regressions. • The proposed method gives better estimates with smaller variances. In cases of ill-conditioned estimation problems, not all parameters can be estimated accurately and a selection of parameter subset composed of more influential and less correlated parameters may be needed to increase parameter estimability. This paper proposes to choose a subset for estimation from transformed parameters along the directions of the principal components of the parameter covariance matrix while retaining the initial guesses for the unselected transformed parameters. Since estimating a subset of the transformed parameters can adjust all the original parameter values and any constraint on the original parameter values can still be applied to the transformed parameters, the proposed regularization method can overcome the limitation of the existing methods, i.e., parameter subset selection and truncated singular value decomposition (also known as 'principal component regression'). It is demonstrated that the proposed method can provide better parameter estimates with smaller variances than the existing parameter subset selection methods, first through statistical analysis, and then through case studies of linear and nonlinear regressions. In addition, based on the derived statistical properties, a criterion is suggested for selecting an optimal subset, which gives the smallest mean squared error of the estimates. Furthermore, with the advantage of a lower variance of the estimates, the proposed regularization method gives a more consistent choice of the number of parameters to estimate with the smallest mean squared error of the estimates even when significant errors in the initial guesses and high levels of measurement noise exist. [ABSTRACT FROM AUTHOR]

The cloud particle size distribution varies with height and the phase may change from water to mixed phase to ice through the vertical profile of the cloud, giving rise to different radiative characteristics. Researchers suggested an empirical equation for an approximation of the relation between cloud-particle effective radius and reflectance of channel IR3.7 for Advanced Very High Resolution Radiometer (AVHRR) and Multi-Functional Transport Satellite (MTSAT)-1R satellites. However, when we examined this empirical equation for MSG satellites, there was no correlation between the cloud particle effective radius and those from the Terra and Aqua/MODIS (Moderate Resolution Imaging Spectrometers) products. Given the fact that this relationship is empirical and not applicable for Meteosat satellites with 3.9 µm wavelength cloud properties, we need to introduce a new nonlinear equation that is independent from other cloud properties, to retrieve the cloud effective radius from MSG satellite over Middle East. Thus, in this study, a development of the mentioned method, based on a nonlinear regression model, was introduced to estimate the water/ice-cloud particle effective radius from the 3.9 µm wavelength reflectivity of the Meteosat Second Generation Indian Ocean Data Coverage (MSG-1(IODC)) satellite over the Middle East region. For this purpose, the LibRadTran radiative transfer model was used. This approach is almost independent from other cloud properties, which makes this relationship more efficient for retrieving a cloud's effective radius. To evaluate this approach, the results have been compared to the effective-radius product of the MODIS on board the Terra and Aqua satellites, and cloud effective radius parameter from the MSG-1 satellite's optimal cloud analysis (OCA) data. The average of correlation coefficient, standard deviation, and RMSE (root mean square error) of this retrieved algorithm method for 29 randomly selected case studies, in comparison to the corresponding MODIS product, are 0.93, 3.093, and 3.639, and compared with OCA product, 0.88, 4.015, and 4.51, respectively. Therefore, the results of analysis in the Middle East region show that the retrieved effective particle radius from Meteosat satellites corresponds strongly with MODIS data from the Terra and Aqua satellites, and also with the OCA products of the MSG-1. Furthermore, using the algorithm that is presented in this paper, a nonlinear regression relationship can be made for retrieving cloud effective radius in the intended place. [ABSTRACT FROM AUTHOR]

In this paper, the face stability of plane strain tunnel heading in anisotropic and non-homogeneous clays is investigated by the lower bound (LB) finite element limit analysis (FELA) with second-order cone programming (SOCP). New LB solutions of the problem are numerically derived and described by the set of the dimensionless parameters consisting of the stability load factor, the cover-depth ratio, the normalized overburden pressure, normalized strength gradient, and anisotropic strength ratio while failure mechanisms associated with these parameters are also discussed and compared. The computed LB solutions are validated with the existing results of isotropic strengths confirming the accuracy and correctness of the solutions. Based on a nonlinear regression, the new design equations for the stability load factor and factor of safety for plane strain headings in anisotropic and non-homogeneous clays are first time proposed for assessing the undrained stability of relatively long-wall tunnels particularly considering the effects of strength anisotropy and non-homogeneity. [ABSTRACT FROM AUTHOR]

In Internet of Things (IoT) applications, federated learning is commonly used for distributedly training models in a privacy-preserving manner. Recently, federated learning is broadly applied to autonomous driving for training intelligent decision models without disseminating local data remotely. Although federated learning provides a safer training manner for protecting data privacy in autonomous driving, the model training process is still vulnerable to poisoning attacks from vehicle client ends. It is beneficial to study poisoning attacks for enhancing the robustness of the training process to generate reliable decisions for safe driving. Until now, a few researches on poisoning attacks against classification models under federated learning scenarios have been proposed. However, those poisoning attacks against classification tasks cannot be directly applied to regression tasks in a federated learning framework, especially autonomous driving tasks such as steering angle control and brake control. The biggest challenge is that the output of non-linear regression models in federated learning is a dynamic sequential value decided by an online updated non-linear function. Thus, minor attacks can affect the overall non-linear function inference outputs leading to a failed stealthy attack. Based on existing challenges, this paper proposes an ATT ack against F ederated L earning based A utonomous V ehicle framework(ATT_FLAV) to evaluate and enhance the robustness of the federated learning-based autonomous driving models and take the steering angle control task as a representative non-linear regression task to illustrate the methodology. In the proposed framework, a bandit-based A ttack R egion- UCB (AR-UCB) algorithm is designed for dynamic data poisoning attacks against the non-linear regression model. This is a black-box attack strategy that chooses the target attack label region dynamically in each federated learning round based on historical attack experiences. Compared with the attack performance of baseline poisoning attacks and the robustness under defense schemas, the proposed poisoning attack strategy can achieve superior attack performance via continuous data poisoning attacks against the federated learning framework. [ABSTRACT FROM AUTHOR]

• The dynamic direct tensile test of thermally damaged sandstone was carried out. • A predictive model for dynamic tensile properties of thermally damaged sandstones. • The composition and mass fractions of sandstone were analyzed by XRD. The stability of surrounding rock in the combustion void is the key to continuous, safe, and efficient gas production in an underground coal gasification project. The key factors influencing the stability of surrounding rock in the combustion void are high temperature and impact dynamic load. At the same time, rock structure failure mainly depends on the rock materials' tensile strength. Therefore, it is fundamental to study the dynamic tensile mechanical properties of thermally damaged rocks to control the surrounding rock stability of the combustion void in UCG projects. This paper used the coal measures as the research object. The dynamic direct tensile test of thermally damaged sandstone was carried out using a high-temperature load system and split Hopkinson tension bar (SHTB) test system. The test results showed that the dynamic tensile strength of sandstone increased linearly with the increase in strain rate. In contrast, it increased first and then decreased with temperature. In addition, the nonlinear regression method was applied to establish the prediction model of dynamic tensile properties of thermally damaged sandstone. XRD analyzed the composition and mass fractions of sandstone. From the standpoint of composition change, the change mechanism of the mechanical properties of thermally damaged coal measured in sandstone was illustrated. [ABSTRACT FROM AUTHOR]

• The impact and size effect are first used in the presented model. The paper demonstrates that the impact effect and size effect are important in revealing the cutting mechanism of CFRP. • Based on the size effect and contact position of cutting edge and workpiece, cutting region is first divided into four parts which is effected by chipping, pressing, impacting and bouncing respectively. • The model of carbon fibers distribution is introduced into the presented model as another factors of cutting region division. The impact and size effect are generally neglected in force prediction model of cutting Carbon Fiber Reinforced Polymer (CFRP). Since carbon fibers are frequently cut in and out, the main cutting mechanisms of CFRP are mixed by impact, shear and other mechanisms, which are difficult to be clarified. Thus, we establish an impact effect-based cutting force prediction model of CFRP considering size effect. In the model, cutting regions are effected by chipping, pressing, impacting and bouncing, respectively. The cutting force is calculated based on the representative volume element (RVE) and minimum potential energy principle (MPEP). After chip breakage, the free-damped vibration force prediction model is established. The dynamics force prediction model is proofed with high prediction accuracy. Besides, the influences of cutting parameters on impact, cutting and vibration are analyzed by nonlinear regression analysis. It demonstrates that the impact and size effect are of great significance in revealing the cutting mechanisms of CFRP. [ABSTRACT FROM AUTHOR]

• SLE is properly described with refined e-NRTL electrolyte-solvent parameters. • Systems showing multiple precipitate equilibria are more difficult to predicted. The aim of this work is to use the refined binary electrolyte-solvent interaction parameters of the e-NRTL model obtained in a previous paper (J.L. Valverde et al. Fluid Phase Equilibria (2022), 551, 113264) and to analyse the impact of considering the electrolyte-electrolyte interaction parameters different from zero on the prediction of solid-liquid equilibria in salt-water mixtures. For this purpose, experimental data were fitted to the complete e-NRTL model by non-linear regression. Ternary (two salts + water) and quaternary (three salts + water) systems were considered. Almost all the systems analyzed were precisely predicted by using the e-NRTL model with the electrolyte-water pairs regressed previously and electrolyte-electrolyte ones set to zero. Including the electrolyte-electrolyte binary parameters in a proper way can slightly improve the solid-liquid equilibria prediction for some of the selected systems. The Na 2 SO 4 +K 2 SO 4 +Li 2 SO 4 +H 2 O mixture was described poorly than the remainder ones computed due to the complexity of the system which exhibits the formation of multiple salts. [ABSTRACT FROM AUTHOR]

• Modelling energy savings of renovations in the Dutch non-profit housing stock. • Assessment of 1.6 million dwellings, 21 building features and 3 empirical models. • Empirical models outperform the theoretical building energy model. • Shortcomings exist when predicting effects of specific energy-saving interventions. In Europe, the energy performance of dwellings is measured using theoretical building energy models based on the Energy Performance of Buildings Directive (EPBD), which estimates the energy consumption of dwellings. However, literature shows large performance gaps between the theoretically predicted energy consumption and the actual energy consumption of dwellings. The goal of this paper is to investigate the extent to which empirical models provide more accurate estimations of actual energy consumption when compared to a theoretical building energy model, in order to estimate average actual energy savings of renovations. We used the Dutch non-profit housing stock to demonstrate the results. We examined three empirical models to predict the actual energy consumption of dwellings: a linear regression model, a non-linear regression model, and a machine learning model (GBM). This paper shows that these three models alleviate the performance gap by giving a good prediction of actual energy consumption on sectoral cross-sections. However, these models still have shortcomings when predicting the effects of specific renovation interventions, for example newly introduced heat pumps. The non-linear and machine learning model (GBM) outperform the theoretical model in terms of estimating energy savings through renovation interventions. [ABSTRACT FROM AUTHOR]

Regression analysis method has been extensively used to predict tunnel during excavations. This paper applies the method to solve for the tunnel strain for a circular opening in a strain-softening rock mass. Support pressure, in-situ stress and geological strength index (GSI) are three important geological parameters that are simultaneously considered in evaluating tunnel strain. A numerical procedure of the strain-softening rock mass is incorporated to solve for tunnel strain with a series of GSI, in-situ stress and support pressure. A detailed result of the tunnel strain is solved using the repeated numerical procedures. A nonlinear regression model for predicting tunnel strain is obtained through analysing the result with the regression method. Twelve fitting equations are considered in the regression model, correlating the tunnel strain with the support pressure, GSI, initial stress and critical softening parameters. The analysis framework is validated by comparing the calculated tunnel strain to that predicted by existing studies. The influence of the critical softening parameter on tunnel strain and the radius of the plastic zone are investigated. The response surfaces of tunnel strain versus the initial stress and support pressures for different rock mass qualities with various softening behaviours are also analysed. Then a guidance of the support design is derived based on the regression model and is demonstrated in an actual tunnel case with field measurements. [ABSTRACT FROM AUTHOR]

In this paper, a large database of 491 test results of circular concrete-filled steel tube (CFT) columns under axial compression was collected from the available literature. The collected results were employed to investigate the effects of loading conditions, diameter-to-thickness ratio, concrete type and compressive strength on the load-carrying capacity of CFT columns, from which models for the hoop stress of steel tubes are obtained through nonlinear regression analyses. Based on the von Mises yield criterion together with the proposed hoop stress models, a model for predicting the load-carrying capacity of CFT columns was developed. The performances of the proposed model and the existing models were evaluated using the database. Due to the rationality of the model development process, the proposed model offers a more reasonable and accurate prediction of load-carrying capacity for CFT columns under various loading conditions. • A large database of 491 test results of circular CFT columns under axial compression is collected. • The model for predicting the load-carrying capacity of the CFT columns is developed. • The proposed model shows a more reasonable and accurate prediction of load carrying capacity for CFT columns. [ABSTRACT FROM AUTHOR]

Highlights • 1-D freezing behavior assessment of ice-rich sandy soil considering the phase change of water. • Numerical simulation model shows reliable prediction results for 1-D freezing test. • Freezing behavior of ice-rich sandy soil are dependent on various geotechnical properties. • The larger the porosity of the specimen, the greater the increase in the time for fully frozen. • Height of specimen has the greatest impact on the time for fully frozen. Abstract This paper evaluates a methodology that enables one-dimensional freezing to make a homogeneous frozen soil specimen. Numerical analyses that simulate one-dimensional freezing are conducted, considering the phase change of pore water. After evaluating the applicability of the numerical analysis model, the effects of geotechnical characteristics on the freezing behavior of ice-rich sandy soil are evaluated through parametric studies. In addition, a nonlinear regression model is proposed that can predict the time required for complete freezing of saturated soil. According to the results from nonlinear regression analysis, the model demonstrates reliable accuracy (R2 = 0.998) in predicting the amount of time required for complete freezing, even with data from testing datasets not used in the developing stage. [ABSTRACT FROM AUTHOR]

Abstract: In the Czech Hydrometeorological Institute (CHMI) there exists a unique set of meteorological measurements consisting of the values of vertical atmospheric levels of beta and gamma radiation. In this paper a stochastic data-driven model based on nonlinear regression and on nonhomogeneous Poisson process is suggested. In the first part of the paper, growth curves were used to establish an appropriate nonlinear regression model. For comparison we considered a nonhomogeneous Poisson process with its intensity based on growth curves. In the second part both approaches were applied to the real data and compared. Computational aspects are briefly discussed as well. The primary goal of this paper is to present an improved understanding of the distribution of environmental radiation as obtained from the measurements of the vertical radioactivity profiles by the radioactivity sonde system. [Copyright &y& Elsevier]

Abstract: In this paper, a new machine learning solution for function approximation is presented. It combines many simple and relatively inaccurate estimators to achieve high accuracy. It creates – in incremental manner – hierarchical, tree-like structure, adapting it to the specific problem being solved. As most variants use the errors of already constructed parts to direct further construction, it may be viewed as example of boosting – as understood in general sense. The influence of particular constituent estimator on the whole solution’s output is not constant, but depends on the feature vector being evaluated. Provided in this paper are: general form of the metaalgorithm, a few specific, detailed solutions, theoretical basis and experimental results with one week power load prediction for country-wide power distribution grid and on simple test datasets. [Copyright &y& Elsevier]

Abstract In this paper, two correlations for oil formation volume factor (B o) for volatile oil reservoirs are developed using non-linear regression technique and genetic programming using commercial software. More than 1200 measured values obtained from PVT laboratory analyses of five representative volatile oil samples are selected under a wide range of reservoir conditions (temperature and pressure) and compositions. Matching of PVT experimental data with an equation of state (EOS) model using a commercial simulator (Eclipse Simulator), was achieved to generate the oil formation volume factor (B o). The obtained results of the B o as compared with the most common published correlations indicate that the new generated model has improved significantly the average absolute error for volatile oil fluids. The hit-rate (R 2) of the new non-linear regression correlation is 98.99% and the average absolute error (AAE) is 1.534% with standard deviation (SD) of 0.000372. Meanwhile, correlation generated by genetic programming gave R 2 of 99.96% and an AAE of 0.3252% with a SD of 0.00001584. The importance of the new correlation stems from the fact that it depends mainly on experimental field production data, besides having a wide range of applications especially when actual PVT laboratory data are scarce or incomplete. [ABSTRACT FROM AUTHOR]

Recent research has proven that cold-formed steel shear wall with corrugated steel sheathing is a promising lateral force resisting system in high wind and seismic zones. Extensive experimental investigations, including monotonic and cyclic tests on cold-formed steel shear walls with corrugated steel sheathing, were recently completed at University of North Texas. This paper summarizes previous and newly conducted tests and presents finite element analyses in order to establish a set of nominal shear strengths for the corrugated steel sheathed shear walls. In addition, a design method for determining the deflection of the corrugated steel sheathed shear walls under in-plane lateral loading was proposed based on the experimental results and nonlinear regression analyses. The deflections obtained from the proposed design equation were compared with the test deflections and good agreement was obtained. [ABSTRACT FROM AUTHOR]

Based on the measurement signals obtained from oil-gas-water three-phase flow experiments, multi-scale time irreversibility is investigated to characterize the dynamic behavior of different flow patterns. Firstly, the conductance fluctuation signals of oil-gas-water three-phase flow in the vertical upward pipe are collected. Subsequently, three typical flow patterns, i.e., oil in water-type bubble flow, oil in water-type transition flow and oil in water-type slug flow, are defined and analyzed. Using multi-scale time irreversibility index and the surrogate data approach, multi-scale time irreversibility can be detected from the collected signals with different flow patterns. Furthermore, in order to quantitatively characterize the time irreversibility of oil-gas-water three-phase flow, a novel criterion, i.e., Average value of Asymmetric Distance (AAD), is proposed in this paper. The proposed criterion is validated by the experiments. The experiment results show that the conductance signals acquired from different typical flow patterns of oil-gas-water three-phase flow have different time irreversibility. The AAD value obtained for the oil in water-type slug flow is larger than the AAD value obtained for the oil in water-type transition flow, and the AAD value obtained for the oil in water-type transition flow is larger than the AAD value obtained for the oil in water-type bubble flow. In addition, the mechanism leading to the formation of time irreversibility is further explored in terms of adaptive optimal kernel time-frequency representation. It is proved that AAD can be used to reveal the characteristics of asymmetry in the evolution of oil-gas-water three-phase flow pattern. The utilization of AAD will provide an important reference for characterization and analysis of the non-linear dynamic characteristics of oil-gas-water three-phase flow regime evolution in real applications. [ABSTRACT FROM AUTHOR]

In the branch of forensic science known as firearm evidence identification, various similarity scores have been proposed to compare firearm marks. Some similarity score comparisons, for example, congruent matching cells (CMC) method, are based on pass-or-fail tests. The CMC method compares the pairwise topography images of breech face impressions, from which the similarity score is derived for quantifying their topography similarity. For an image pair, the CMC method determines a certain number of correlated cell pairs. Next, each correlated pair is determined to be a congruent match cell (CMC) pair, or not based on several identification parameters. The number of CMC pairs as a threshold is required so that the two images of surface topographies can be either identified as matching or determined to be non-matching. To reliably estimate error rates or evaluate likelihood ratio (LR), the key is to find an appropriate probability distribution for the frequency distribution of the observed CMC results. This paper discusses four statistical models for CMC measurements, which are binomial and three binomial-related probability distributions. In previous studies, for a sequence of binomial distributed or other binomial-related distributed random variables (r.v.), the number of Bernoulli trials N for each r.v. is assumed to be the same. However, in practice, N(the number of cell pairs in an image pair) varies from one r.v. (or one image pair) to another. In that case, the term, frequency function, of the CMC results is not appropriate. In this paper, the generalized frequency function is introduced to depict the behavior of the CMC values and its limiting distribution is provided. Based on that, nonlinear regression models are used to estimate the model parameters. The methodology is applied to a set of actual CMC values of fired cartridge cases. [ABSTRACT FROM AUTHOR]

This paper presents analytical research results to predict the shear behavior of reinforced concrete (RC) beams shear-strengthened with near-surface mounted (NSM) FRP. In this study, a section analysis method based on the modified compressive field theory (MCFT) was proposed to predict the shear behavior of RC beams shear-strengthened with NSM FRP reinforcement. The analytical method was applied to derive the analytical effective strain of the FRP shear reinforcement of 71 specimens collected from the existing literature. Then, the correlation between this analytical FRP effective strain and the major variables for shear strengthening design was analyzed through nonlinear regression analysis. From the results, a model capable of predicting the effective strain of NSM FRP reinforcement was finally proposed. This FRP effective strain model predicted the effective strain of NSM FRP reinforcement more accurately compared to models proposed by other researchers. In addition, the section analysis method using this model predicted the shear behaviour of other researchers beams shear-strengthened with NSM FRP reinforcement very well. [ABSTRACT FROM AUTHOR]

• Compile experimental test results on circular concrete-filled tube members under shear loading. • Shed light on the current Artificial Intelligence approach and its application in structural engineering. • Developing AI-based models/equations to predict the shear strength of circular concrete-filled tube members. The complex shear behavior of circular concrete-filled tube (CCFT) members has been a challenge for an adequate design equation. Collapses due to shear failure are primarily seen in shear links, pile foundations, and coupling beams in composite shear walls. The current design provisions are based on limited experimental data, leading to very conservative expressions of shear strength. The recent advances in Artificial Intelligence (AI) technologies provided an opportunity to establish design models directly from the data with no need to postulate a mathematical expression. This study utilized three AI techniques alongside 141 experimental test results from the literature to overcome the complex behavior of the CCFT members by proposing reliable design equations/models. Namely, Gaussian Processing Regression (GPR), Gene Expression Programming (GEP) and Nonlinear Regression (NR) analysis. The predictor variables include axial loading, materials properties, section slenderness ratio and shear span ratio. This paper sheds light on the current data-based techniques in solving complex structural problems by addressing the noted AI methods and their application in predicting the shear capacity of CCFT members. It is concluded that the data-driven proposed model demonstrates remarkable accuracy in predicting shear capacity compared to the current design equations and can be used for routine design practice. The statistical validation results show that among the proposed methods, GPR showed the highest efficiency in predicting the shear capacity of CCFT with an average error of 0.5%, whereas for GEP and NR, average errors are 1.26% and 1.09%, respectively. [ABSTRACT FROM AUTHOR]

For maximum metal recovery, considering the movement of ore and waste during the blasting process in loading design is meaningful for reducing ore loss and ore dilution in an open-pit mine. The blast-induced rock movement (BIRM) can be directly measured; nevertheless, it is time-consuming and relative expensive. To solve this problem, a novel intelligent prediction model was proposed by using dimensional analysis and optimized artificial neural network technique in this paper based on the BIRM monitoring test in Husab Uranium Mine, Namibia and Phoenix Mine, USA. After using dimensional analysis, five input variables and one output variable were determined with both considering the dimension and physical meaning of each dimensionless variable. Then, artificial neural network technique (ANN) technique was utilized to develop an accurate prediction model, and a metaheuristic algorithm namely the Equilibrium Optimizer (EO) algorithm was applied to search the optimal hyper-parameter combination. For comparison aims, a linear model and a non-linear regression model were also performed, and the comparison results show that the provided hybrid ANN-based model can yield better prediction performance. As a result, it can be concluded that the developed intelligent model in this article has the potential to predict BIRM during bench blasting, and the analysis method and modeling process in this paper can provide a reference for solving other engineering problems. [ABSTRACT FROM AUTHOR]

Soft sensors have been widely used in industrial processes over the past two decades because they use easy-to-measure process variables to predict difficult-to-measure ones. Some success has been achieved by the dominant traditional methods of modeling soft sensors based on statistics, such as principal components analysis (PCA) and partial least square (PLS), but such sensors usually become inaccurate and inefficient when processing strong nonlinear data. In this paper, a new soft sensor modeling approach is proposed based on a deep learning network. First, stacked auto-encoders (SAEs) are employed to extract high-level feature representations of the input data. In the process of training each layer of a SAE, the Limited-memory Broyden-Fletcher-Goldfarb-Shanno algorithm (L-BFGS) is adopted to optimize the weights parameters. Then, a support vector regression (SVR) is added to predict the target value on the basis of the features obtained from the SAE. To improve the model performance, Genetic Algorithm (GA) is used to obtain the optimal parameters of the SVR. To evaluate the proposed method, a soft sensor model for estimating the rotor deformation of air preheaters in a thermal power plant boiler is studied. The experimental results demonstrate that the soft sensor based on the SAE-SVR algorithm is more effective than the existing methods are. [ABSTRACT FROM AUTHOR]

This paper proposes a decision support (DS) framework that incorporates weather-related factors for the purpose of estimating the duration of projects. Inclement weather can have a serious effect on construction projects, particularly with regard to duration and costs. The weather has an impact on human resource productivity, supplier effectiveness and material damage which can, in turn, affect the duration of a construction project. The proposed five-module framework integrates weather variables, project performance variables and duration of project activities. This framework uses expert knowledge about the importance of weather variables, pairwise comparisons of weather variables with respect to different performance criteria, and similarly, pairwise comparisons of performance variables with respect to project activities. A model based on this framework, using multivariate statistical techniques and an analytical network process (ANP), is developed to estimate the duration of project activities, taking into account the impact of weather. The proposed model is illustrated with data from a construction project from Iran. Validation of the model is provided by comparing the actual duration of an activity with the estimated duration, using the proposed framework. [ABSTRACT FROM AUTHOR]

• The pseudo-second and pseudo-first order models are the most common adsorption kinetic models. • The meaning of these models can be contradictory in the literature. • Their validity and insights on adsorption mechanisms are reviewed and discussed. • The shortcomings of linear regression are discussed. • Nonlinear regression and model selection criteria are promoted and illustrated using case studies. The study of adsorption kinetics is ubiquitous when reporting new adsorbent materials in the literature. The information these tests provide are no doubt valuable, but the conclusions drawn from adsorption kinetic models are many times contradictory between papers. In this work, the validity and meaning of common kinetic models are reviewed from literature dealing with their mathematical development, and are discussed. It is found that the most common models, the pseudo second order and pseudo first order models, have the ability to fit to kinetic data originating from systems limited by the surface reaction and by diffusion. Thus, these models are not associated with just one adsorption mechanism and further precautions when analyzing the data should be taken. Other less common models are also discussed, as they can be used to gain clearer insights into the rate limiting step. Another important topic discussed is the type of regression used. Linear regression has a bias toward the pseudo second order model and the estimated parameters can be very bad, which is particularly true for the pseudo-first order model. Thus, the wrong kinetic model is more easily chosen. The benefits of employing nonlinear regression and criteria for model selection are elaborated upon, using case studies reporting the adsorption of different solutes as examples. [ABSTRACT FROM AUTHOR]

This paper is concerned with the fault prediction for the nonlinear stochastic system with incipient faults. Based on the particle filter and the reasonable assumption about the incipient faults, the modified fault estimation algorithm is proposed, and the system state is estimated simultaneously. According to the modified fault estimation, an intuitive fault detection strategy is introduced. Once each of the incipient fault is detected, the parameters of which are identified by a nonlinear regression method. Then, based on the estimated parameters, the future fault signal can be predicted. Finally, the effectiveness of the proposed method is verified by the simulations of the Three-tank system. [ABSTRACT FROM AUTHOR]

Both linear and nonlinear models have been proposed for forecasting the power output of photovoltaic systems. Linear models are simple to implement but less flexible. Due to the stochastic nature of the power output of PV systems, nonlinear models tend to provide better forecast than linear models. Motivated by this, this paper suggests a fairly simple nonlinear regression model known as multivariate adaptive regression splines (MARS), as an alternative to forecasting of solar power output. The MARS model is a data-driven modeling approach without any assumption about the relationship between the power output and predictors. It maintains simplicity of the classical multiple linear regression (MLR) model while possessing the capability of handling nonlinearity. It is simpler in format than other nonlinear models such as ANN, k-nearest neighbors (KNN), classification and regression tree (CART), and support vector machine (SVM). The MARS model was applied on the daily output of a grid-connected 2.1 kW PV system to provide the 1-day-ahead mean daily forecast of the power output. The comparisons with a wide variety of forecast models show that the MARS model is able to provide reliable forecast performance. [ABSTRACT FROM AUTHOR]

The present work advances the PC-transport approach in the context of Large Eddy Simulation (LES) of turbulent combustion. Accurate modeling of combustion systems requires large kinetic mechanisms. However, realistic high-fidelity simulations of turbulent reacting flows still represent a big challenge on the current computational tools. Therefore, a parameterization of the thermo-chemical state-space using a reduced number of variables is needed. To this end, the potential offered by Principal Component Analysis (PCA) in identifying low-dimensional manifolds is very appealing. The present paper extends the PC-transport approach, coupled with Gaussian Process Regression (GPR), to a lifted methane/air flame in LES. Previous investigations by the authors showed the great potential of the PC-GPR model in the context of Sandia flames. This study investigated some key features of the model: the sensitivity to the training data set and the scaling methods. To this end, two different canonical reactors were used: unsteady counter-flow laminar flames (CFLF) and unsteady perfectly stirred reactor (PSR). Moreover, the authors proposes an approach to address the issue of data density inherent to large numerical data sets, by means of a kernel density weighting of the data set before applying PCA. Finally, a subgrid scale (SGS) closure model was coupled to the PC-transport approach to treat complex turbulence/chemistry interactions. [ABSTRACT FROM AUTHOR]