Gaussian Process Regression Technique Research Articles

Performance, emissions and combustion analysis of hydrogen-enriched compressed natural gas spark ignition engine by optimized Gaussian process regression and neural network at low speed on different loads

The transportation industry is increasingly focused on hydrogen based fuel as a promising alternative due to its potential for reduced emissions and enhanced performance. The purpose of this study is to improve efficiency and reduce emissions on low speed on different loads for heavy duty vehicles. This study can be impactful to train the electronic control unit (ECU) for heavy duty vehicles working on aforementioned conditions. This study investigates the effect of hydrogen ratios (0%–40 %) in HCNG, (0%–15 %) exhaust gas recirculation (EGR) ratios, and spark timing (8°-34o CA bTDC) at low and high loads (15 % & 75 %) under stoichiometric conditions at low speed (700 rpm). Performance, emissions and combustion parameters were thoroughly analysed across these conditions. Brake thermal efficiency increases by 20.7 % & 19.4 % by the addition of (0 %–40 %) hydrogen at low and high load at 14o CA bTDC running on 5 % and 0 % EGR respectively. NOx emissions reduces by 11.9 % & 17.9 % by the addition of (0 %–15 %) EGR and increases by 46.1 % & 46.4 % by increasing the amount of hydrogen in HCNG at low and high load at 14o CA bTDC at 0 % EGR respectively. Coefficient of variation reduces 13.8 % by (0 %–40 %) hydrogen addition at 11 % EGR at 16o CA bTDC. Optimized Gaussian process regression (GPR) and neural network (NN) machine learning techniques were applied to the dataset, and found GPR matern 5/2 is best one. The findings can be utilized in the development of HCNG engine.

The unconfined compressive strength estimation of rocks using a novel hybridization technique based on the regulated Gaussian processor

The unconfined compressive strength (UCS) of rocks is a crucial factor in geotechnical engineering, assuming a central role in various civil engineering undertakings, including tunnel construction, mining operations, and the design of foundations. The precision in forecasting UCS holds paramount importance in upholding the security and steadfastness of these endeavors. This article introduces a fresh methodology for UCS prognostication by amalgamating Gaussian process regression (GPR) with two pioneering optimization techniques: sand cat swarm optimization (SCSO) and the equilibrium slime mould algorithm (ESMA). Conventional techniques for UCS prediction frequently encounter obstacles like gradual convergence and the potential for becoming ensnared in local minima. In this investigation, GPR is the foundational predictive model due to its adeptness in managing nonlinear associations within the dataset. The fusion of GPR with cutting-edge optimizers is envisioned to elevate the precision and expeditiousness of UCS prognostications.An extensive collection of rock samples, each accompanied by UCS measurements, is harnessed to assess the suggested methodology. The efficacy of the GPSC and GPES models is juxtaposed with the conventional GPR technique. The findings reveal that incorporating SCSO and ESMA optimizers into GPR brings about a noteworthy enhancement in UCS prediction accuracy and expedites convergence. Notably, the GPSC models exhibit exceptional performance, evidenced by an exceptional R2 value of 0.995 and an impressively minimal RMSE value of 1.913. These findings emphasize the GPSC model’s potential as an exceedingly auspicious tool for experts in the realms of engineering and geology. It presents a sturdy and dependable method for UCS prediction, a resource of immense value in augmenting the security and efficiency of civil engineering endeavors.

Modeling forecast errors for microgrid operation using Gaussian process regression

Microgrids, denoting small-scale and self-sustaining grids, constitute a pivotal component in future power systems with a high penetration of renewable generators. The inherent uncertainty tied to renewable power generation, typified by photovoltaic and wind turbine systems, necessitates counterbalancing mechanisms. These mechanisms encompass Energy storage systems or conventional thermal fossil-fuel generators imbued with heightened flexibility. Addressing the uncertainty stemming from renewable generators mandates a cost-effective assessment and operational strategy for said compensatory devices. To this end, myriad uncertainty factors warrant scrutiny, conceivably concretized into a unified probability distribution function (PDF) that takes into account their temporal inter-dependencies. Diverse uncertainty factors, characterized by varying marginal distributions and scales, can be assimilated into a multivariate probability distribution through a conversion to normal distributions via rank correlation. However, with the escalation in the number of uncertainty factors embraced within a microgrid context, the endeavour becomes notably intricate when aiming to define conditional probability distributions originating from joint PDFs. This paper presents a method proposing the modelling of net-load forecast error distribution, considering the interplay among uncertainty factors. The approach introduces a data-driven Gaussian process regression technique for training and validating conditional PDFs among these uncertainty factors. Notably, this approach facilitates the transformation of said factors into normal distributions while preserving their inherent marginal characteristics. The resultant conditional density function, as per the proposed methodology, exhibits enhanced suitability for estimating net-load error distribution. Consequently, the conditional density function stemming from this proposed approach demonstrates superior aptitude in approximating the distribution of net load error.

Parameters Measurement and Secrecy Diversity Analysis for Physical Layer Security in WSNs using Projection Pursuit Gaussian Process Regression

Wireless sensor networks are specialized networks, geographically dispersed monitors that keep track of environmental external factors and conduct the collected information to a centralized opinion. The rapid growth of wireless sensor networks and its connected have pushed the saturation level of the communication. Moreover, the information passed is prone to the attacks and hence researchers have considered these as crucial factors in wireless sensor networks. Physical layer security is the one of the main approaches to ensure the secrecy of wireless sensor networks and has been attained with several encryption and signal processing approach. In our approach we propose a novel Projection Pursuit Gaussian Process regression (PPGPR) technique to analyze the diverse secrecy of physical layer in wireless sensor networks. The proposed approach is utilized to safeguard the sensitive data with secured physical layer. Simulations are performed and made an analogous study with state-of-art works to ensure the secrecy of the proposed work. The proposed work can use for the secured wireless communication with higher secrecy capacity than the existing approaches. The performance is analyzed with the parameters such as secrecy capacity, secrecy outage probability, packet delivery ratio, secrecy throughput, and energy consumption.

Differential Game-Based Control for Nonlinear Human-Robot Interaction System With Unknown Desired Trajectory.

Differential game is an effective technique to describe the negotiation between the humans and robots, which is widely used to realize the trajectory tracking tasks in the human-robot interaction (HRI). However, most existing works consider the control-affine HRI systems and assume the desired trajectory is available to both the human and the robot, which limit the scope of applications. To overcome these difficulties, this work focuses on the nonaffine HRI system and supposes that the desired trajectory is not available to the robot. A novel differential game framework encoding the desired trajectory estimator is proposed, where the desired trajectory is estimated via the Gaussian process regression (GPR) technique. To address the challenge arising from the nonlinearity of the HRI system, we equivalently transform the original problem into the one in a differentially flat space, and seek the equilibrium strategies for the transformed problem substitutionally. We further prove that the trajectory tracking error satisfies a probabilistic bound, whose confidence interval tightens as the decrease of noise variance during the interaction. Comparative simulation results show that our method outperforms the learning-based method in terms of robustness, parameters setting, and time consumption. Experiment results further show that the tracking error under the proposed human-robot cooperative algorithm is reduced by 55% compared to the human direct control.

Contact Force Estimation of Robot Manipulators With Imperfect Dynamic Model: On Gaussian Process Adaptive Disturbance Kalman Filter

This paper is concerned with the contact force estimation problem of robot manipulators based on imperfect dynamic models of the manipulator and the contact force. To handle the imperfect dynamic information of the manipulator, a hybrid model, consisting of the nominal model and the residual dynamics, is established for the manipulator, and the Gaussian process regression (GPR) technique is employed to learn the mean and covariance of the residual dynamics. On this basis, a virtual measurement equation is established for contact force estimation and a Gaussian process adaptive disturbance Kalman filter (GPADKF) is developed where the variational Bayes technique is employed to achieve online identification of the noise statistics in the force dynamics. The GPADKF is capable of decoupling the contact force from residual dynamics and system noises, thereby reducing the dependence on accurate dynamic models of the manipulator and the contact force. Simulation and experimental results demonstrate that the proposed scheme outperforms the state-of-art methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Contact force estimation for robot manipulators can be achieved by fusing the dynamic models of the manipulator and the contact force. When both models are imprecise, the traditional inverse dynamics-based and disturbance Kalman filter-based approaches can no longer provide accurate force estimates. To handle this challenge, a computationally efficient hybrid dynamic model is established for the manipulator, which consists of the nominal model and a residual dynamics compensation term learned from offline data via the GPR. On this basis, an adaptive disturbance Kalman filter is constructed by using the variational Bayes technique to deal with the inaccurate noise covariance matrix in the force dynamic model. Compared with the existing approaches, the force estimate obtained via the proposed scheme is more accurate and reliable, as refined noise covariance matrices (provided by both the GPR and the variational Bayes procedure) have been adopted in the Kalman gain calculation. The proposed GPADKF method is the extension of the composite disturbance filtering (CDF) framework. With the proposed scheme, the dependency on the perfect dynamic models in contact force estimation can be significantly reduced, and this makes our approach especially suitable for contact force estimation problems under unfamiliar and complicated environments.

Modelling the Interdependence of Multiple Electricity Markets in the Distribution System Aggregator Bidding

The volatility of market prices and the interdependence of multiple markets make it challenging for Distribution System Aggregators (DSAs) to model these prices. In this paper, a novel statistical model based on Gaussian process regression and mutual information screening technique is developed. This model is able to predict different market prices and quantify their uncertainty whilst incorporating the interdependence of different markets. The proposed model is employed to assist DSAs with market price modelling. Price scenarios for various markets generated by this model make it viable to formulate the optimal involvement of DSAs in multiple markets as a stochastic multi-step two-stage problem. Other than providing a set of scenarios that efficaciously model multiple electricity market prices, after the clearing of each market, the proposed model leverages market clearing results to improve the accuracy of price prediction of subsequent markets. Extensive simulation results on large price datasets demonstrate that the proposed methodology will result in a considerable increase in the profit of the DSA compared to state-of-the-art price prediction approaches.

Transmission line impulse response modelling using machine learning techniques

&lt;p&gt;Conventional methods of circuit simulation such as full-wave electromagnetic fieldsolvers can be very slow. Machine learning is an emerging technology in modelling, simulation, optimization, and design that present attractive alternatives to the conventional methodologies because they can be trained with a small amount of data, and then used to perform fast circuit predictions within the same design space. In this paper, we present applications of machine learning techniques for the modelling of transmission lines from their impulse reponses. The standard multilayer perceptron (MLP) neural network and the gaussian process (GP) regression techniques are demonstrated, and&lt;br /&gt;both models are successfully implemented to model the impulse responses of transmission lines with great accuracies. We show that the GP outperforms the MLP in terms of prediction accuracies and that the GP is more data efficient than the MLP. This is beneficial considering that each training sample is expensive, making the GP a good candidate for the task, compared to the more popular MLP.&lt;/p&gt;

Prediction of concrete strength using MCMC and GPR methods

Concrete strength prediction is a complex nonlinear regression task that involves multiple ingredients and age as key factors. In order to achieve accurate predictions, the Markov Chain Monte Carlo (MCMC) and Gaussian Process Regression (GPR) techniques are employed. The dataset, sourced from Kaggle repositories, comprises a comprehensive collection of 1030 data points. Alongside the existing features (content of ingredients, age and strength), we introduce new ones, including water-cement ratio, sand ratio, and water-binder ratio, to enhance the model's credibility. To determine the optimal kernel function, the dataset is partitioned into training and testing subsets. Notably, the MCMC method yields an R2 of 0.41, while GPR demonstrates a significantly improved R2 of 0.89. Further investigation is warranted to refine the model's fit and optimize its predictive capacity.

Estimation of plasma parameter profiles and their derivatives from linear observations by using Gaussian processes

Gaussian process regression (GPR) has been utilized to provide fast and robust estimates of plasma parameter profiles and their derivatives. We present an alternative GPR technique that performs profile regression analyses based on arbitrary linear observations. This method takes into account finite spatial resolution of diagnostics by introducing a sensitivity matrix. In addition, the profiles of interest and their derivatives can be estimated in the form of a multivariate normal distribution even when only integrated quantities are observable. We show that this GPR provides meaningful measurements of the electron density profile and its derivative in a toroidal plasma by utilizing only ten line-integrated data points given that the locations of magnetic flux surfaces are known.

The GAPS programme at TNG

Context. With the growth of comparative exoplanetology, it is increasingly clear that the relationship between inner and outer planets plays a key role in unveiling the mechanisms governing formation and evolution models. For this reason, it is important to probe the inner region of systems hosting long-period giants in search of undetected lower mass planetary companions. Aims. We aim to present the results of a high-cadence and high-precision radial velocity (RV) monitoring of three late-type dwarf stars hosting long-period giants with well-measured orbits in order to search for short-period sub-Neptunes (SN, M sin i &lt; 30 M⊕). Methods. Building on the results and expertise of our previous studies, we carried out combined fits of our HARPS-N data with literature RVs. We used Markov chain Monte Carlo (MCMC) analyses to refine the literature orbital solutions and search for additional inner planets, applying Gaussian process regression techniques to deal with the stellar activity signals where required. We then used the results of our survey to estimate the frequency of sub-Neptunes in systems hosting cold Jupiters, f(SN|CJ), and compared it with the frequency around field M dwarfs, f(SN). Results. We identify a new short-period, low-mass planet orbiting GJ 328, GJ 328 c, with Pc = 241.8-1.7+1.3 days and Mc sin i = 21.4-3.2+3.4M⊕. We moreover identify and model the chromospheric activity signals and rotation periods of GJ 649 and GJ 849, around which no additional planet is found. Then, taking into account also planetary system around the previously analysed low-mass star BD-11 4672, we derive an estimate of the frequencies of inner planets in such systems. In particular, f(SN|CJ) = 0.25-0.07+0.58 for mini-Neptunes (10 M⊕ &lt; M sin i &lt; 30 M⊕, P &lt; 150 d), marginally larger than f(SN). For lower mass planets (M sin i &lt; 10 M⊕) instead f(SN|CJ) &lt; 0.69, which is compatible with f(SN). Conclusions. In light of the newly detected mini-Neptune, we find tentative evidence of a positive correlation between the presence of long-period giant planets and that of inner low-mass planets, f(SN|CJ) &gt; f(SN). This might indicate that cold Jupiters have an opposite influence in the formation of inner sub-Neptunes around late-type dwarfs as opposed to their solar-type counterparts, boosting the formation of mini-Neptunes instead of impeding it.

Precise Transit Photometry Using TESS: Updated Physical Properties for 28 Exoplanets around Bright Stars

The Transiting Exoplanet Survey Satellite (TESS) follow-up of a large number of known transiting exoplanets provides a unique opportunity to study their physical properties more precisely. Being a space-based telescope, the TESS observations are devoid of any noise component resulting from the interference of Earth’s atmosphere. TESS also provides a greater probability to observe subsequent transit events owing to its longer uninterrupted time-series observations compared to ground-based telescopes. For the exoplanets around bright host stars in particular, TESS time-series observations provide high signal-to-noise ratio (S/N) lightcurves, which can be used for higher-precision studies for these exoplanets. In this work, I have studied the TESS transit photometric follow-up observations of 28 exoplanets around bright stars with V mag ≤ 10. The already high-S/N lightcurves from TESS have been further processed with a critical noise-treatment algorithm, using the wavelet-denoising and the Gaussian-process regression techniques, to effectively reduce the noise components, both correlated and uncorrelated in time, which were then used to estimate the physical properties of these exoplanets. The study has resulted in very precise values for the physical properties of the target exoplanets, with the improvements in precision being significant for most of the cases compared to the previous studies. Also, since a comparatively large number of transit lightcurves from TESS observations were used to estimate these physical properties for each of the target exoplanets, which removes any bias due to the lack of sufficient data sets, these updated physical properties can be considered extremely accurate and reliable for future studies.

Prediction of various parameters of desalination system using BOA- GPR machine learning technique for sustainable development: A case study

The present study examines the performance of desalination based atmospheric water extraction system under various climate situations. The Bayesian optimisation for model training hyperparameters was used to make the process autoregressive, and the Gaussian Process Regression (GPR) technique was used to develop the prediction model. Because of its capacity to incorporate data-specific uncertainties and non-linearities, the GPR model was highly efficient in calculating the efficiency of system in different environmental circumstances. For its prognostic efficiency, the model was examined using multiple statistical methods such as R2, mean squared error (MSE), and mean absolute error (MAE). The findings revealed that the GPR model. The prediction model's statistical parameters showed a high prognostic efficiency, with a training R2 of 0.97, MSE of 7282.3, RMSE of 85.34, and MAE of 63.93, and a test R2 of 0.98, MSE of 7596.3, RMSE of 87.16, and MAE of 72.49. Overall, this paper provides a valuable contribution to developing Desalination technology in different climatic regions. The research also sheds light on the relationship between input variables (climatic conditions) and output variables (energy intensity and water extraction rate) for constructing and optimizing desalination based water extraction system for various geographies and climates.

Forecasting failure load of Sandstone under different Freezing-Thawing cycles using Gaussian process regression method and grey wolf optimization algorithm

The stability analysis of rock is an important basis to ensure the safe exploitation of underground resources and the reliable operation of space engineering. Failure load is one of the most important parameters on which the stability analysis of rocks can be performed. Rocks are constantly subjected to the freezing-thawing (F-T) weathering phenomena. F-T cycles can significantly affect the failure load of rocks and cause geological disasters in cold regions. As a result, the effects of F-T cycles on rock mechanical characteristics should be carefully investigated. Weak, heavily fractured, worn, and thinly bedded rocks, on the other hand, can never provide enough high-quality cores. Aside from being difficult, time-consuming, and costly, this test also entails destructive testing. Therefore, the prediction of failure load under different F-T cycles utilizing simplified indirect test procedures has been emphasized. In this study, a Gaussian process regression (GPR) technique was developed to predict the failure load of rock samples, utilizing 300 datasets obtained from the laboratory tests for Sandstone under different F-T cycles (0,1,4,8,16,32). Seven input parameters effective on the failure load were considered in the datasets. The grey wolf optimization (GWO) algorithm was used to fine-tune the GPR’s hyperparameters. The evaluation indices results showed that the GPR model developed by this study has a high potential ability in the prediction of failure load. The stepwise method was used for feature selection purposes. Confining pressure and porosity parameters were selected as the most effective features on the failure load. Considering only the confining pressure and porosity parameters in the model, the accuracy of the model was increased as the RMSE and R2 were obtained by about 5.57 and 0.9885, respectively. Also, the performance of the GPR model was compared to the other machine learning methods. Finally, the GPR model was recommended to predict the failure load of rock samples. This work’s significance is that it allows geotechnical engineers to accurately estimate the failure load rock samples under F-T cycles. In this way, instead of preparing more samples and waiting a long time to prepare these samples for the same laboratory test, we can use the trained model and minimize the time and costs required for laboratory tests.

Identifying impacts of global climate teleconnection patterns on land water storage using machine learning

Study RegionThe Zambezi River Basin in southern Africa Study focusModelling global freshwater systems is difficult because of the complexities of climate and anthropogenic influence on hydrological systems, especially at local scales. The rapid changes in hydrological systems caused by the influence of global climate trigger complex processes that make traditional machine learning algorithms limited in quantifying impacts of climate variability on freshwater. In this study, we developed a novel machine learning routine based on the Gaussian process regression (GPR) technique to improve understanding of the interaction of non-linear climatic variables with hydrological stores (includes surface water and terrestrial water storage-TWS). The GPR is built on the principle of the Gaussian process, which is a stochastic process that simplifies multivariate Gaussian distribution to infinite-dimensional space, such that the distributions over function values can be defined. The prediction of the GPR is tested using twenty-three independent climate variables against satellite observations of TWS between April 2002 and June 2017. We explored the use of a characteristic length scale for the kernels, which we tagged as ‘first order kernels’, and another set of kernels having a separate length scale for each discrete predictor. The latter was implemented using the automatic relevance determination (ARD), tagged as ‘higher order kernels’. The first and higher order kernels of the GPR technique were further examined using multivariate statistical indices to reveal the close relationship among hydro-climatic similarity and predictability. New hydrological insights for the regionOur results indicate that the large fluctuations of TWS in our tentative test-bed (the Zambezi Basin) for the GPR technique are largely caused by strong changes in sea surface temperature and global teleconnection patterns of the nearby oceans. The GPR introduced in this study provides an improved modelling framework to keep track on the influence of these global climate teleconnection patterns on major hydrological systems, like the Zambezi Basin, which contributes to global hydro-climatology but currently showing large amplitudes of land water storage loss.

Modeling of scour depth and length of a diversion channel flow system with soft computing techniques

Abstract This study employed soft computing techniques, namely, support vector machine (SVM) and Gaussian process regression (GPR) techniques, to predict the properties of a scour hole [depth (ds) and length (Ls)] in a diversion channel flow system. The study considered different geometries of diversion channels (angles and bed widths) and different hydraulic conditions. Four kernel function models for each technique (polynomial kernel function, normalized polynomial kernel function, radial basis kernel, and the Pearson VII function kernel) were evaluated in this investigation. Root mean square error (RMSE) values are 8.3949 for training datasets and 11.6922 for testing datasets, confirming that the normalized polynomial kernel function-based GP outperformed other models in predicting Ls. Regarding predicting ds, the polynomial kernel function-based SVM outperforms other models, recording RMSE of 0.5175 for training datasets and 0.6019 for testing datasets. The sensitivity investigation of input parameters shows that the diversion angle had a major influence in predicting Ls and ds.

An Integrated Framework Based on an Improved Gaussian Process Regression and Decomposition Technique for Hourly Solar Radiation Forecasting

The precise forecast of solar radiation is exceptionally imperative for the steady operation and logical administration of a photovoltaic control plant. This study proposes a hybrid framework (CBP) based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), an enhanced Gaussian process regression with a newly designed physical-based combined kernel function (PGPR), and the backtracking search optimization algorithm (BSA) for solar radiation forecasting. In the CEEMDAN-BSA-PGPR (CBP) model, (1) the CEEMDAN is executed to divide the raw solar radiation into a few sub-modes; (2) PACF (partial autocorrelation coefficient function) is carried out to pick the appropriate input variables; (3) PGPR is constructed to predict each subcomponent, respectively, with hyperparameters optimized by BSA; (4) the final forecasting result is produced by combining the forecasted sub-modes. Four hourly solar radiation datasets of Australia are introduced for comprehensive analysis and several models available in the literature are established for multi-step ahead prediction to demonstrate the superiority of the CBP model. Comprehensive comparisons with the other nine models reveal the efficacy of the CBP model and the superb impact of CEEMDAN blended with the BSA, respectively. The CBP model can produce more precise results compared with the involved models for all cases using different datasets and prediction horizons. Moreover, the CBP model is less complicated to set up and affords extra decision-making information regarding forecasting uncertainty.

Machine learning modeling of power delivery networks with varying decoupling capacitors

&lt;p&gt;This paper presents modeling of power delivery network (PDN) impedance with varying decoupling capacitor placements using machine learning techniques. The use of multilayer perceptron artificial neural networks (ANN) and gaussian process regression (GPR) techniques are explored, and the effects of the hyperparameters such as the number of hidden neurons in the ANN, and the choice of kernel functions in the GPR are investigated. The best performing networks in each case are selected and compared in terms of accuracy using test data consisting of PDN impedance responses that were never encountered during training. Results show that the GPR models were significantly more accurate than the ANN models, with an average mean absolute error of 5.23 mΩ compared to 11.33 mΩ for the ANN.&lt;/p&gt;

A Novel Machine Learning Prediction Model for Aerosol Transport in Upper 17-Generations of the Human Respiratory Tract

The main challenge of the health risk assessment of the aerosol transport and deposition to the lower airways is the high computational cost. A standard large-scale airway model needs a week to a month of computational time in a high-performance computing system. Therefore, developing an innovative tool that accurately predicts transport behaviour and reduces computational time is essential. This study aims to develop a novel and innovative machine learning (ML) model to predict particle deposition to the lower airways. The first-ever study uses ML techniques to explore the pulmonary aerosol TD in a digital 17-generation airway model. The ML model uses the computational data for a 17-generation airway model and four standard ML regression models are used to save the computational cost. Random forest (RF), k-nearest neighbour (k-NN), multi-layer perceptron (MLP) and Gaussian process regression (GPR) techniques are used to develop the ML models. The MLP regression model displays more accurate estimates than other ML models. Finally, a prediction model is developed, and the results are significantly closer to the measured values. The prediction model predicts the deposition efficiency (DE) for different particle sizes and flow rates. A comprehensive lobe-specific DE is also predicted for various flow rates. This first-ever aerosol transport prediction model can accurately predict the DE in different regions of the airways in a couple of minutes. This innovative approach and accurate prediction will improve the literature and knowledge of the field.

Modeling-optimization of performance and emission characteristics of dual-fuel engine powered with pilot diesel and agricultural-food waste-derived biogas

Gaseous-liquid fuel combinations of biogas as primary fuel and diesel as pilot fuel were employed to power a compression ignition (CI) engine in this study. The effects of variable input factors such as engine load, compression ratio, and pilot fuel injection advance on the dual-fuel engine's combustion, thermal, and emission performance were investigated. The data acquired during this lab-based testing was used to develop a prognostic model using a Bayesian optimization strategy for hyperparameter optimization and a contemporary ensemble Gaussian process regression (GPR) technique. During model testing, the error analysis revealed that the developed model could predict the experimental data rather correctly, with R2 values ranging from 0.9995 to 0.9999 and MSE values ranging from 0.00018 to 0.1334. The mean absolute error was discovered to be between 0.0091 and 0.3065. Consequently, the developed GPR model can effectively simulate the on-board performance, emission, and combustion characteristics of a diesel-biogas dual-fuel setting. As a consequence, the current work established the GPR model in the existing CI engine meta-modeling framework as a consistent, trustworthy, and robust system analytical approach for diesel-biogas dual fuel mode of operation.