Partial Hybrid Research Articles

Optimal Control Allocation for Distributed Electric Propulsion in a Series/Parallel Partial Hybrid Powertrain

Abstract The SUbsonic Single Aft eNgine (SUSAN) Electrofan is a NASA concept transport aircraft representative of technology anticipated for a 2040 entry-into-service date. The powertrain consists of a single thrust-producing geared turbofan engine with generators driving a series/parallel partial hybrid power/propulsion system. The architecture includes 16 underwing contrarotating fans, eight on each side. The distributed fans can be used by the flight control system to augment or replace the rudder function. This paper sets up the optimal control problem of setpoint determination for individual wingfans in the distributed propulsion system, accounting for electrical string efficiencies, saturations, and failures. The solution minimizes power consumption while maintaining thrust and torque on the airframe for maneuvering. Additionally, thrust that would have been lost due to temporary fan speed or power saturation is optimally redistributed to maintain overall desired thrust and torque on the aircraft. A simulation of a coordinated turn utilizing the distributed electric propulsion for yaw rate control in a multiple wingfan failure scenario demonstrates the robustness of the powertrain design to failures and helps define its limitations.

Comparative analysis of modified partial least squares regression and hybrid deep learning models for predicting protein content in Perilla (Perilla frutescens L.) seed meal using NIR spectroscopy

Perilla seed meal (PSM), a byproduct of oil extraction from Perilla frutescens L. seeds, is rich in protein (24.26–42.85%) and holds potential as an economical and sustainable animal feed. Traditional methods for assessing protein content are labor-intensive and costly. This study explores Near-Infrared Reflectance Spectroscopy (NIRS) for the rapid, precise, and non-destructive determination of PSM protein content in 126 samples. We developed and evaluated Modified Partial Least Squares (MPLS) regression and deep learning (DL) models, including 1D-CNN (Convolutional Neural Network), LSTM Long Short-Term Memory), and hybrid architectures incorporating skip connections, inception modules, and spectral derivatives. Model performance was validated externally using parameters such as RSQexternal (R-squared), bias, SEP(C) (Standard Error of Prediction), RPD (Residual Prediction Deviation), slope, SD (Standard Deviation), p-value (≥0.05), and the correlation between reference and predicted values. The 1D CNN-LSTM-Inception derivative 1 model achieved the best performance (RPD: 8.0, RSQexternal: 0.98), followed by the MPLS-based model (RPD: 4.88, RSQexternal: 0.96) and the 1D CNN derivative 1 model (RPD: 3.07, RSQexternal: 0.96). These models provide a reliable and advanced technology for the non-destructive screening of PSM protein content, thus aiding in the rapid identification and selection of superior perilla chemotypes from varied backgrounds.

Hi-gMISnet: generalized medical image segmentation using DWT based multilayer fusion and dual mode attention into high resolution pGAN

Objective. Automatic medical image segmentation is crucial for accurately isolating target tissue areas in the image from background tissues, facilitating precise diagnoses and procedures. While the proliferation of publicly available clinical datasets led to the development of deep learning-based medical image segmentation methods, a generalized, accurate, robust, and reliable approach across diverse imaging modalities remains elusive. Approach. This paper proposes a novel high-resolution parallel generative adversarial network (pGAN)-based generalized deep learning method for automatic segmentation of medical images from diverse imaging modalities. The proposed method showcases better performance and generalizability by incorporating novel components such as partial hybrid transfer learning, discrete wavelet transform (DWT)-based multilayer and multiresolution feature fusion in the encoder, and a dual mode attention gate in the decoder of the multi-resolution U-Net-based GAN. With multi-objective adversarial training loss functions including a unique reciprocal loss for enforcing cooperative learning in pGANs, it further enhances the robustness and accuracy of the segmentation map. Main results. Experimental evaluations conducted on nine diverse publicly available medical image segmentation datasets, including PhysioNet ICH, BUSI, CVC-ClinicDB, MoNuSeg, GLAS, ISIC-2018, DRIVE, Montgomery, and PROMISE12, demonstrate the proposed method’s superior performance. The proposed method achieves mean F1 scores of 79.53%, 88.68%, 82.50%, 93.25%, 90.40%, 94.19%, 81.65%, 98.48%, and 90.79%, respectively, on the above datasets, surpass state-of-the-art segmentation methods. Furthermore, our proposed method demonstrates robust multi-domain segmentation capabilities, exhibiting consistent and reliable performance. The assessment of the model’s proficiency in accurately identifying small details indicates that the high-resolution generalized medical image segmentation network (Hi-gMISnet) is more precise in segmenting even when the target area is very small. Significance. The proposed method provides robust and reliable segmentation performance on medical images, and thus it has the potential to be used in a clinical setting for the diagnosis of patients.

Deep learning-based method for defect detection in electroluminescent images of polycrystalline silicon solar cells

To achieve defect detection in bare polycrystalline silicon solar cells under electroluminescence (EL) conditions, we have proposed ASDD-Net, a deep learning algorithm evaluated offline on EL images. The model integrates strategies such as downsampling adjustment, feature fusion optimization, and detection head improvement. The ASDD-Net utilizes the Space to Depth (SPD) module to effectively extract edge and fine-grained information. The proposed Enhanced Cross-Stage Partial Network Fusion (EC2f) and Hybrid Attention CSP Net (HAC3) modules are placed at different positions to enhance feature extraction capability and improve feature fusion effects, thereby enhancing the model's ability to perceive defects of different sizes and shapes. Furthermore, placing the MobileViT_CA module before the second detection head balances global and local information perception, further enhancing the performance of the detection heads. The experimental results show that the ASDD-Net model achieves a mAP value of 88.81% on the publicly available PVEL-AD dataset, and the detection performance is better than the current SOTA model. The experimental results on the ELPV and NEU-DET datasets verify that the model has some generalization ability. Moreover, the proposed model achieves a processing frame rate of 69 frames per second, meeting the real-time defect detection requirements for solar cell surface defects.

Abstract LB208: An intricate connection between canonical Wnt and MAPK/ERK signaling drives the partial hybrid EMT state involving FOXC2/p63 activation leading to cancer stemness and metastasis

Abstract The epithelial to mesenchymal transition (EMT) is a dynamic process underlying metastasis. Here we show that TCF1, a TCF7 gene product, promotes a hybrid epithelial/mesenchymal (E/M) phenotype in basal breast cancer cells that was enriched in stemness and metastasis as compared to cells residing in the M-like state. E/M cells (CD104highCD44high) were enriched in canonical Wnt signaling, thereby upregulating FOXC2 which was turn able of converting M into E/M cells. Consistent with the E/M state, FOXC2 upregulated TA and ΔNp63 isoforms which control epithelial differentiation and Wnt signaling via β4 integrin/CD104 and Frizzled 7 upregulation respectively. Importantly, Wnt3a was able of stimulating ERK phosphorylation in E/M cells leading to FOXC2 and p63 upregulation thereby preventing E/M to M differentiation. These findings were further corroborated by ATAC-sequencing pointing predominantly to FOXC2 as a master regulator of the E/M state that was suppressed by ERK inhibition. Together, these results demonstrate that TCF7 stimulates Wnt3a/ERK activation which in turn activates the FOXC2/p63 axis, thereby promoting the hybrid EMT state underlying stemness and metastasis. Citation Format: Huizhi Liang, Outhiriaradjou Benard, Zuen Ren, Kimita Suyama, Jingli Wang, Anthony Griffen, Hao Wang, Lindsay LeFave, Larry Norton, Rachel B. Hazan. An intricate connection between canonical Wnt and MAPK/ERK signaling drives the partial hybrid EMT state involving FOXC2/p63 activation leading to cancer stemness and metastasis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB208.

An Eight-Node Non-Conforming Generalized Partial Hybrid Element and Its Application in Stress Analysis of Repaired Composite Laminate Structures

To ensure the overall continuity of displacement and out-of-plane stress in composite laminate structures and to quantitatively analyze the mechanical properties of composite materials after damage or repair, a finite element solution method is applied based on the modified generalized H–R variational principle. This method utilizes an eight-node non-conforming generalized partial hybrid element (NCGPME8). The partial hybrid model established with this hybrid element can accurately satisfy the out-of-plane stress boundary conditions of the structure, ensuring the continuity of out-of-plane stress. Numerical examples are used to validate that this hybrid model can effectively compute thick and thin laminate structures with high accuracy and rapid convergence of out-of-plane stress. Finally, considering the insensitivity to irregular meshes and the accuracy in calculating in-plane stress, this method is propagated by element coefficient deduction or element material replacement, then employed to analyze the in-plane and out-of-plane stress distributions of laminates with damage from stepwise grinding perforations, and laminates repaired in a stepwise fashion. Stress and displacement at different locations on the laminates are compared and analyzed, leading to a quantitative assessment of the impact of damage and repair on the stress distribution of the laminates.

Enhancing age-related postural sway classification using partial least squares-discriminant analysis and hybrid feature set

Feature sets in a machine learning algorithm can have an impact on the robustness, interpretability, and characterization of the data. To detect age-related changes, traditional linear methods for analyzing center of pressure (COP) signals offer limited insight into the complex nonlinear dynamics of postural control. To overcome this limitation, a novel approach that combines a partial least squares-discriminant analysis (PLS-DA) classifier with the nonlinear dynamics of COP time series was proposed. Three small feature sets were compared: time-domain features alone, entropy-based features alone, and a hybrid approach incorporating both types of features. The performance of the PLS-DA model was assessed in four different eyes and surface conditions by using the accuracy, sensitivity, selectivity, precision metrics, and ROC curves. The results indicated that the PLS-DA model utilizing the hybrid feature set achieved significantly higher accuracy than the time-domain and entropy-based feature sets. The best classification performance was observed when the eyes were open on a compliant surface, with an overall accuracy of 89% for training and 88% for cross-validation. For the old group, while the results indicated 93% sensitivity, 94% specificity, and 93% precision in the training, the results revealed 88% sensitivity, 93% specificity, and 91% precision in cross-validation. Notably, the hybrid feature set yielded an AUC value of 0.96, indicating a superior performance. This study emphasizes the robust classification capabilities of PLS-DA for age-related postural changes and highlights the effectiveness of utilizing a small hybrid feature set to improve classification accuracy and reliability.

A novel concept of solar photovoltaic partial shading and thermal hybrid system for performance improvement

Large values from external causes, such as partial shade, can greatly influence output power of PV. The applications of partial shading are frequently utilized in simulation software. However, in this research work, partial shading and the integration of the photovoltaic Thermal (PV/T) Hybrid Solar Panel is implemented, and analysis is done to see how it affects the output power of solar panels under genuine climatic circumstances. Many research investigations have been conducted and researchers continue to look at PV/T systems to enhance their performance. The application is designed to provide information on solar panel output power under normal and partial shading situations. The maximum amount of power that solar panels can generate is 298.50 W. Under typical circumstances, partial shading in a solar panel can result in a maximum power value of 141.13 W, and this partial shading leads the power to increase.

Style Drift and Performance Evaluation of Green Funds in China

Based on data of China's open equity and partial equity hybrid green funds from 2018 to 2022, this paper conducts the sharp style analysis model to construct green fund style drift indicator, and apply the TM model to construct stock selection and timing indicators. Moreover, this paper constructs a panel fixed-effect model to empirically analyze the impact of green fund style drift, stock selection and timing on green fund performance. This research finds that there is a drift of investment style in green funds. Such style drift and timing have a negative impact on the performance of green funds. Stock selection has a significant positive impact on green funds. Furthermore, this research introduces style drift, stock selection and timing indicators into green fund performance evaluation, and use principal component analysis method to build a green fund performance-evaluation system. Then, this paper applies the rating system to the existing green fund market and effectively supplements the existing rating system.

Hybrid Working, Well-being and Gender: A Study on a Public Sector Organization During the COVID-19 Pandemic

During the COVID-19 global pandemic, likewise private sector, public sector organisations also shifted to partial homeworking or hybrid working to comply with the government-imposed social distancing policies. This study examines the effect of enforced hybrid working on employee well-being via markers of stress, workload, loneliness, and detachment. This study also investigates the impact of involuntary hybrid working on the gender division of labour. This study applies qualitative research within a cross-sectional design to identify the well-being outcomes and experiences of male and female employees. The findings of this study reveal that factors such as disruptions in internet connectivity, increased workload, longer working hours with no fixed schedule, and lack of interaction with colleagues and social support negatively affect well-being leading to increased stress while working from home. Family responsibilities including child caring while working from home influence female employees’ well-being. In addition, hybrid working provides advantages of both onsite and homeworking and thus, provides an opportunity to balance work and family life.

OC-099 ROBOTICALLY-ASSISTED ENHANCED-VIEW TOTALLY EXTRAPERITONEAL (R-ETEP) TECHNIQUE FOR ENDOSCOPIC RETROMUSCULAR HERNIA REPAIR. A RETROSPECTIVE ANALYSIS OF OUR FIRST 99 CASES

Abstract Introduction The availability of robotics has marked the beginning of a new era in hernia surgery. Due to its tiltable instruments the robot grants a dexterity which is not comparable to any conventional minimally invasive approach. In 2019 we have established r-eTEP-repair in our hospital. The objective of this analysis is to share our experience of the first ninety-nine cases. Materials and Methods A retrospective analysis was carried out of all patients who underwent a r-eTEP repair in our hospital from September 2019 to January 2023 using gathered data out of our hospital information system (ORBIS Dedalus). Results Within the study period, we operated on a total of 99 patients. In 27 patients an extraperitoneal transversus abdominis release (eTAR) was performed. Complete closure of the hernia defect was possible in all cases and an uncoated synthetic mesh was placed in the retromuscular plane. In 3 cases a partial open hybrid procedure with robotic transversus abdominis release was performed. The median defect size was 25cm2 (2,25–375 cm2). The median mesh size was 540 cm2 (260–1350 cm2). The postoperative complication rate was 6.06%. There was one intraoperative complication and no abdominal reoperations. Median length of hospital stay was 3 days (2–10). Conclusion eTEP is a safe and minimally invasive procedure for a retromuscular mesh placement. In combination with a transversus abdominis release, even complex findings can comfortably be treated endoscopically.

Hybrid-nanofluid Flow through Partially Porous Wavy Channels: Thermo-hydraulic Performance and Entropy Analysis

Comprehensive numerical simulations are made to examine the combined effect of three distinct passive techniques: partial porous insert, corrugated walls, and hybrid nanofluid on thermo-hydraulic properties and entropy generation of three different wavy channels (triangular, sinusoidal, and trapezoidal) for the first time. The finite element method is used, and the simulations are performed considering Ag-TiO2-Water hybrid nanofluid (0 to 4%) as a coolant for Reynolds number range from 5 to 500 and Darcy number, 10−6. The present study will be helpful in designing and establishing a viable heat exchanging device from both the first law and second law of thermodynamics perspectives with maximum performance. It is demonstrated that the insertion of porous media between the corrugated walls enhances the thermal performance with simultaneous increment in pressure losses. It is observed that the trapezoidal channel is founded to be viable with a performance factor higher than 1 for a given range of Reynolds number, unlike the other two channels, which are viable only for higher Reynolds number. Therefore, the trapezoidal channel performs best with maximum enhancement in thermal performance by 90%. Also, from entropy generation analysis, it is shown that all three channels are thermodynamically advantageous from a second law perspective but only for low values of Reynolds number.

SHEAR STRENGTH OF THE STRENGTH–DUCTILITY TYPE SEISMIC RETROFITTING TECHNIQUE FOR EXISTING RC COLUMNS USING PRESTRESSING BAR AND STEEL PLATES

This study explores a seismic retrofit method for existing RC columns using a cast-in-site partial thick hybrid wing-wall (THW) technique. The THW technique plays two important roles: (1) to enable easy and cost-effective construction and (2) to considerably increase lateral strength and ductility. The aim of this study is to experimentally determine the shear resistance (truss and arch mechanism) and shear strength of the columns retrofitted using the THW technique. Based on the analytical assessment of the THW technique, design equations of ultimate shear strength and steel plate thickness are proposed.

Climate policy and financial system stability: evidence from Chinese fund markets

ABSTRACT The impacts of climate policies on the global financial system have aroused wide attention all over the world. Fund markets are an important part of the financial system and play a crucial role in the stability of the financial system. In this paper, the impacts of climate policies on fund markets are evaluated from direct and indirect risk contagion channels using the data of Chinese ordinary stock funds and partial stock hybrid funds during 2007–2020. Risk contagion indicates that a fund's selling of stocks causes the stock price to fall, causing asset losses to other funds holding the same stocks. We construct a risk contagion model based on common asset holdings of funds. The analysis of direct risk exposure of funds to climate policy in China shows that five climate-policy-relevant sectors account for more than half of the total value of shareholdings. The climate risk stress-test indicates that ignoring the indirect risk contagion channel significantly underestimates the adverse effects of and climate policies on fund markets. More stringent, short-term climate targets and earlier implementation of climate policies helps to mitigate otherwise drastic changes required in energy markets in China to achieve a 2°C long-term target, and reduces the adverse effects of climate policies on the fund market. Furthermore, the impact of climate policies on different investment funds shows significant differences, leading to winners and losers. The losers are funds that adopt a high-carbon investment strategy, while winners are funds adopting a green investment strategy.

Forecasting groundwater level of karst aquifer in a large mining area using partial mutual information and NARX hybrid model

Predicting the groundwater level of karst aquifers in North China Coalfield is essential for early warning of mine water hazards and regional water resources management. However, the dynamic changes of strata structure and hydrogeological parameters driven by coal mining activity cause challenges to the process-oriented groundwater model. In order to achieve accurate prediction of groundwater level in large mining areas, this study was the first to use the data-driven Nonlinear Autoregressive with External Input (NARX) model to predict the groundwater level of six karst aquifer observation wells in Pingshuo Mining Area. Three variable input scenarios were set up, solely considering meteorological factors, anthropogenic disturbance factors, and considering both meteorological and anthropogenic disturbance factors. The novel partial mutual information (PMI) screening algorithm was adopted to determine optimized input variables in each scenario. The input and feedback delay coefficients of NARX model were determined by using Seasonal-trend Decomposition Procedure Based on Loess (STL) algorithm and auto- and cross-correlation functions. The results showed that PMI algorithm can effectively screen out the optimal input variables for predicting groundwater level, the NSE coefficients of the PMI-NARX models under the three scenarios were 38.81%, 4.26% and 41.46% higher than those of the corresponding control experiments, respectively. In addition, the prediction performance of the PMI-NARX built on the basis of meteorological factors is poor (NSE <0.63). However, in scenarios which solely use anthropogenic disturbance factors and both use meteorological and anthropogenic disturbance factors, the PMI-NARX coupling models exhibit good prediction performance (NSE and R2 are all greater than 0.8). Especially under solely considering anthropogenic disturbance factors scenario, the model still exhibited good prediction accuracy with a negligible number of input variables. The results can provide technical and theoretical support for the prediction of groundwater level in other mining areas.

On a Partial Fractional Hybrid Version of Generalized Sturm–Liouville–Langevin Equation

As we know one of the most important equations which have many applications in various areas of physics, mathematics, and financial markets, is the Sturm–Liouville equation. In this paper, by using the α-ψ-contraction technique in fixed point theory and employing some functional inequalities, we study the existence of solutions of the partial fractional hybrid case of generalized Sturm–Liouville-Langevin equations under partial boundary value conditions. Towards the end, we present two examples with numerical and graphical simulation to illustrate our main results.

Development of the hybrid MCDM model for evaluating and selecting bucket wheel excavators for the modernization process

This paper presents a methodology for evaluating and ranking different bucket wheel excavators (BWE) for determining which machine should enter in the process of revitalization and modernization. Various multicriteria methods are used. Combining them achieves the best effect when choosing BVE for the modernization process. AHP, TOPSIS, VIKOR, and PROMETHEE methods are used. The hybrid models are developed from the multi-criteria decision making (MCDM) methods and they are used to evaluate the basic indicators that characterize the operation of a BWE. The methods will be applied to each group of the parameters, their sub-parameters and alternatives in the selection. The models are defined in two parts. In the first part, the priority vectors of parameters are defined by applying the AHP method. Other methods are applied in the second part where the evaluation of alternatives is made according to the defined parameters. That forms three partial hybrid models AHP-TOPSIS, AHP-VIKOR, AHP-PROMETHEE. The analysis parameters are qualified in four groups Technical, Working, Maintenance, and Economics parameters. Validation and selection of the optimal method will be performed in relation to the expert analysis with prepared questionnaires. The selected method should help in defining which machine will enter in the process of revitalization and modernization. According to this method, there is a 100% match with AHP-PROMETHEE, and the ranking given with AHP-TOPSIS corresponds to 75%, while AHP-VIKOR corresponds to 50%. Model AHP-PROMETHEE for the selecting of the BWE is a reliable and suitable tool for this purpose. In comparison to the classical statistical methods, this approach can achieve great saving. The BWE are very expensive machines and their value is 20–30 million euros. The investment in revitalization and modernization is 25–35% of the purchase price. This explains the importance of forming such an evaluation model. The presented analysis showed the possibility of the application of hybrid combined methods. The results in the paper presented the benefit from two aspects. The first aspect is the formation of a model that can be applied to other similar problems. Another aspect is the choice of the machine itself based on a complex analysis of a large number of parameters. Generally, the model becomes universal and can be used for later similar analyzes.

A narrative loom of hybrid nanofluid-filled wavy walled tilted porous enclosure imposing a partially active magnetic field

Improved controllability along with enhanced thermal performance in modern thermal devices could be achieved using the combination of partial magnetic fields and hybrid nanofluid flow. The present attempt demonstrates the impact of partially active magnetic fields on the enhanced thermal performance of hybrid nanofluid (Cu–Al2O3–H2O) flow in an oblique wavy porous enclosure. The enclosure is partially heated from the bottom and cooled through its wavy sides and suffers from a partially active magnetic field normal to the sidewalls. The transport equations involving complex wavy walls, localized thermal gradient, porous substance, hybrid nanofluid, partial magnetic fields are solved by the finite volume approach numerically using a written FORTRAN code. The effectiveness of the novel implementation of a partial magnetic field is examined rigorously for wide ranges of variations of active heating length (Lh), active width of the partial magnetic field (Wb) and its positions, magnetic field strength (Ha), the inclination of the cavity (γ), Darcy-Rayleigh number (Ram), Darcy number (Da), and hybrid nanoparticles concentration (ζ) additionally applying no and whole-domain magnetic field. The correlation for the average Nusselt number is derived. Finally, the results conclude that the presence of complex wavy walls enhances the heat transfer of ∼22.16% compared to a plain vertical wall; however, the strength of circulation drops. A partially active magnetic field can be utilized as an effective means to control field variables with a lesser reduction in heat transfer (∼13.97%) compared to the whole domain magnetic field. The middle-centered partial magnetic field offers a significant impact on the overall thermal behavior depending on the active width and intensity of the magnetic field, active heating length, and all other involved parameters. Tilting of the cavity reduces the heat transfer rate.

Inner Properties Estimation of Gala Apple Using Spectral Data and Two Statistical and Artificial Intelligence Based Methods.

Fruits provide various vitamins to the human body. The chemical properties of fruits provide useful information to researchers, including determining the ripening time of fruits and the lack of nutrients in them. Conventional methods for determining the chemical properties of fruits are destructive and time-consuming methods that have no application for online operations. For that, various researchers have conducted various studies on non-destructive methods, which are currently in the research and development stage. Thus, the present paper focusses on a non-destructive method based on spectral data in the 200–1100-nm region for estimation of total soluble solids and BrimA in Gala apples. The work steps included: (1) collecting different samples of Gala apples at different stages of maturity; (2) extracting spectral data of samples and pre-preprocessing them; (3) measuring the chemical properties of TSS and BrimA; (4) selecting optimal (effective) wavelengths using artificial neural network-simulated annealing algorithm (ANN-SA); and (5) estimating chemical properties based on partial least squares regression (PLSR) and hybrid artificial neural network known as the imperialist competitive algorithm (ANN-ICA). It should be noted that, in order to investigate the validity of the methods, the estimation algorithm was repeated 500 times. In the end, the results displayed that, in the best training, the ANN-ICA predicted the TSS and BrimA with correlation coefficients of 0.963 and 0.965 and root mean squared error of 0.167% and 0.596%, respectively.

Determination of the uranium elemental concentration in molten salt fuel using laser-induced breakdown spectroscopy with partial least squares-artificial neural network hybrid models

Accurate uranium (U) composition analysis of the molten salt nuclear fuel mixture is a necessary step in nuclear fuel quality control. Laser-induced breakdown spectroscopy (LIBS) is an optical emission spectrometry technique for elemental composition. The non-linear phenomena in LIBS signal are the drawback of this technique, especially for high atomic number (Z) element in a complex matrix. To overcome this limitation, a hybrid chemometrics model of the partial least squares-artificial neural network (PLS-ANN) was used to quantify the U composition in the salt fuel mixture of Molten salt breeder reactor. This work shows the optimisation of several parameters, viz., spectra pre-treatment procedure, factor number of PLS for ANN input, number of hidden neurons and layers in ANN, activation function, and number of ANN iterations. The collective advantages of data dimension reduction from PLS and the nonlinear processing ability from ANN, improved the accuracy of LIBS quantitative analysis for U from ≈7% using simple PLS to ≈4% precision using a hybrid model.