Adjustable Parameters Research Articles

Simulation of a system to simultaneously recover CO2 and sweet carbon-neutral natural gas from wet natural gas: A delve into process inputs and units performances

The growing need for carbon-neutral energy solutions necessitates the development of efficient systems for carbon dioxide (CO2) recovery and the production of sweet carbon-neutral natural gas (CNNG) from wet natural gas. Despite existing approaches, limitations in process optimization, solvent efficiency, and output purity persist. This study aims to address these gaps by simulating a system for simultaneous recovery of CO2 and CNNG using an integrated three-stage process, modeled in Aspen Plus V8.8. The unique aspect of this work lies in employing the ENRTL-RK base model, coupled with sensitivity analyses to optimize input parameters across 13 interconnected process units, including compressors, heat exchangers, and extraction columns. Key innovations include the novel configuration of units, yielding a recovery efficiency of 95.94% for CNNG and a CO2 purity of 93.185% at optimal conditions, surpassing conventional methods. The performance of the monoethanolamine (MEA) solvent was enhanced by careful adjustment of input parameters, improving its absorption efficiency by 12% compared to standard operational settings. Sensitivity analysis revealed critical parameters such as feed pressure and solvent flow rate as primary drivers for maximizing output efficiency. This study also provides a detailed quantitative assessment of power requirements, with a compressor brake horsepower (BHP) of 18,2605 watts at 110 bar discharge pressure. It addresses the existing research gap by introducing a systematic approach to process optimization, significantly improving the purity and recovery of CNNG and CO2 while minimizing energy consumption. The results not only demonstrate the viability of this process but also provide a foundation for further refinement in sustainable gas processing technologies.

Genetic Variability in Oxidative Stress, Inflammatory, and Neurodevelopmental Pathways: Impact on the Susceptibility and Course of Spinal Muscular Atrophy

The spinal muscular atrophy (SMA) phenotype strongly correlates with the SMN2 gene copy number. However, the severity and progression of the disease vary widely even among affected individuals with identical copy numbers. This study aimed to investigate the impact of genetic variability in oxidative stress, inflammatory, and neurodevelopmental pathways on SMA susceptibility and clinical progression. Genotyping for 31 genetic variants across 20 genes was conducted in 54 SMA patients and 163 healthy controls. Our results revealed associations between specific polymorphisms and SMA susceptibility, disease type, age at symptom onset, and motor and respiratory function. Notably, the TNF rs1800629 and BDNF rs6265 polymorphisms demonstrated a protective effect against SMA susceptibility, whereas the IL6 rs1800795 was associated with an increased risk. The polymorphisms CARD8 rs2043211 and BDNF rs6265 were associated with SMA type, while SOD2 rs4880, CAT rs1001179, and MIR146A rs2910164 were associated with age at onset of symptoms after adjustment for clinical parameters. In addition, GPX1 rs1050450 and HMOX1 rs2071747 were associated with motor function scores and lung function scores, while MIR146A rs2910164, NOTCH rs367398 SNPs, and GSTM1 deletion were associated with motor and upper limb function scores, and BDNF rs6265 was associated with lung function scores after adjustment. These findings emphasize the potential of genetic variability in oxidative stress, inflammatory processes, and neurodevelopmental pathways to elucidate the complex course of SMA. Further exploration of these pathways offers a promising avenue for developing personalized therapeutic strategies for SMA patients.

Adjustment of Mechanical Properties of 3D Printed Continuous Carbon Fiber-Reinforced Thermoset Composites by Print Parameter Adjustments.

Reinforcing thermoset polymers with continuous carbon fiber (CF) tow has emerged as a promising avenue to overcome the thermal and mechanical performance limitations of 3D printed polymeric structures for load-bearing applications. Unlike traditional methods, manufacturing continuous fiber-reinforced composites by 3D printing has the unique capability of locally varying the mechanical properties of the composites. In this study, continuous CF thermoset composite specimens were printed with varying line spacing, resin flow rate, and nozzle sizes. The resin flow rates for different line spacings and nozzle sizes were optimized by topographic analysis. Printed composite mechanical properties were evaluated, and their trends were correlated with the trend of print parameter changes. Results showed that tensile strength and modulus could be altered and improved by ~50% by adjusting the printing process parameters. Higher composite strength and modulus were obtained by shortening the line spacing and nozzle diameter.

A Survey of Dynamical and Gravitational Lensing Tests in Scale Invariance: The Fall of Dark Matter?

We first briefly review the adventure of scale invariance in physics, from Galileo Galilei, Weyl, Einstein, and Feynman to the revival by Dirac (1973) and Canuto et al. (1977). In the way that the geometry of space–time can be described by the coefficients gμν, a gauging condition given by a scale factor λ(xμ) is needed to express the scaling. In general relativity (GR), λ=1. The “Large Number Hypothesis” was taken by Dirac and by Canuto et al. to fix λ. The condition that the macroscopic empty space is scale-invariant was further preferred (Maeder 2017a), the resulting gauge is also supported by an action principle. Cosmological equations and a modified Newton equation were then derived. In short, except in extremely low density regions, the scale-invariant effects are largely dominated by Newtonian effects. However, their cumulative effects may still play a significant role in cosmic evolution. The theory contains no “adjustment parameter”. In this work, we gather concrete observational evidence that scale-invariant effects are present and measurable in astronomical objects spanning a vast range of masses (0.5 M⊙< M <1014M⊙) and an equally impressive range of spatial scales (0.01 pc < r < 1 Gpc). Scale invariance accounts for the observed excess in velocity in galaxy clusters with respect to the visible mass, the relatively flat/small slope of rotation curves in local galaxies, the observed steep rotation curves of high-redshift galaxies, and the excess of velocity in wide binary stars with separations above 3000 kau found in Gaia DR3. Last but not least, we investigate the effect of scale invariance on gravitational lensing. We show that scale invariance does not affect the geodesics of light rays as they pass in the vicinity of a massive galaxy. However, scale-invariant effects do change the inferred mass-to-light ratio of lens galaxies as compared to GR. As a result, the discrepancies seen in GR between the total lensing mass of galaxies and their stellar mass from photometry may be accounted for. This holds true both for lenses at high redshift like JWST-ER1 and at low redshift like in the SLACS sample. Of note is that none of the above observational tests require dark matter or any adjustable parameter to tweak the theory at any given mass or spatial scale.

On adaptive resilient secondary control for DC microgrids under false data injection attacks

AbstractDistributed cooperative control strategies for DC microgrids have been rapidly evolving in recent years. However, introducing a cyber layer to enhance robustness, scalability, and reliability also exposes the system to potential cyber‐attacks. The damage inflicted by such attacks on the system performance can be catastrophic, reaching a point where it may devastate the system normal operation. By using model reference adaptive control (MRAC), this article proposes a resilient approach that does not require an accurate model of the system and despite the uncertainties for detecting false data injections into the reference DC voltage and simultaneously mitigating their adverse effects on the system stability and performance. The proposed technique employs an observer to detect possible false data injections in an online manner. By emulating the behavior of an ideal reference model, the MRAC ensures adaptive adjustments of the control parameters over time to mitigate the negative effects of potential attacks effectively and despite non‐idealities such as measurement noise, parameter variations, and environmental changes in DC microgrids, the MRAC effectively manages false data injection attacks. Simulation studies are conducted using diverse scenarios involving a three‐node DC microgrid to show the effectiveness of the proposed method.

Effect of Grain Size and Porosity/Binder Index on the Unconfined Compressive Strength, Stiffness and Microstructure of Cemented Colombian Sands.

Artificial cementation of granular soils results in improved stabilization, increased stiffness, and greater mechanical strength. The porosity index and volumetric cement content η/Civa is presented as a key measure to study the evolution of different soil stabilization types. However, this index had not been previously studied or adjusted for sands in Colombia. Therefore, this study evaluates the applicability of the η/Civa index on unconfined compressive strength (qu) and stiffness (Go), complemented by microstructural analysis, in four sandy soils from Luruaco (Atlántico), Lorica (Córdoba), Medellín (Antioquia), and Bogotá D.C. The soils were stabilized with Type III Portland cement in dosages of 3%, 5%, 7%, and 9%, and subjected to UCS, ultrasound, and SEM-EDS tests after a curing period of 7 days. It was found that increasing cement content results in higher qu values for the samples, and higher molding density also leads to higher qu values. Additionally, the grain size distribution influenced the adjustment of parameter "a". In the sands from Bogotá and Lorica, with high uniformity, the value of "a" was 1.00. In contrast, mineralogy and particle shape played a predominant role in the sands from Medellín and Luruaco, where the coefficient of uniformity is higher, suggesting a possible inverse relationship between particle angularity and the value of "a".

Response of growth and chlorophyll fluorescence parameters of mulberry seedlings to waterlogging stress

This study aimed to investigate the adaptive mechanisms of mulberry (Morus alba) to waterlogged conditions, with a specific focus on the development of adventitious roots (ARs), alteration of growth strategies, and adjustment of chlorophyll fluorescence parameters. To achieve this goal, 4-year-old potted mulberry plants were selected for research, and a waterlogging simulation method was implemented. Four treatments were established to investigate the effects of varying water conditions on leaf waterlogging damage, the number of ARs, plant height, chlorophyll fluorescence parameters, and proton motive force (pmf) parameters in mulberry plants. These treatments included the control group (CK), shallow submerged group (SS), half-submerged group (HS) and deep submerged group (DS). Our results showed that (1) The number of ARs in each group increased with increasing waterlogging time. (2) Waterlogging stress inhibited the height growth of mulberry, and the changes in plant height in the HS and DS groups were significantly lower than those in the CK and SS groups. (3) The maximum photochemical quantum yield (Fv/Fm) in the HS and DS groups decreased significantly under waterlogging stress. The nonphotochemical quenching (NPQt) of mulberry leaves in the submergence group increased significantly in the early stage of waterlogging stress, and the NPQt in the submergence group increased continuously with increasing waterlogging time. (4) Thylakoid conductivity to protons (gH+) in the leaves of mulberry decreased significantly under waterlogging stress, whereas the steady-state rate of proton flux (vH+) and total electrochromic shift (ECSt) increased significantly. The morphological, physiological, and ecological responses of mulberry plants to waterlogging stress include the timely generation of ARs at the stem base, the adjustment of plant growth strategies, and the repair of photosynthetic response centers in leaves through heat dissipation and thylakoid acidification mechanisms.

Analysis of crystallographic phase retrieval using iterative projection algorithms.

For protein crystals in which more than two thirds of the volume is occupied by solvent, the featureless nature of the solvent region often generates a constraint that is powerful enough to allow direct phasing of X-ray diffraction data. Practical implementation relies on the use of iterative projection algorithms with good global convergence properties to solve the difficult nonconvex phase-retrieval problem. In this paper, some aspects of phase retrieval using iterative projection algorithms are systematically explored, where the diffraction data and density-value distributions in the protein and solvent regions provide thesole constraints. The analysis is based on the addition of random error to thephases of previously determined protein crystal structures, followed by evaluation of the ability to recover the correct phase set as the distance from the solution increases. The properties of the difference-map (DM), relaxed-reflect-reflect (RRR) and relaxed averaged alternating reflectors (RAAR) algorithms are compared. All of these algorithms prove to be effective for crystallographic phase retrieval, and the useful ranges of the adjustable parameter which controls their behavior are established. When these algorithms converge to the solution, the algorithm trajectory becomes stationary; however, the density function continues to fluctuate significantly around its mean position. It is shown that averaging over the algorithm trajectory in the stationary region, following convergence, improves the density estimate, with this procedure outperforming previous approaches for phase or density refinement.

Comparative study of bisphenols in e-cigarette liquids: Evaluating fabric phase sorptive extraction, ultrasound-assisted membrane extraction, and solid phase extraction techniques

To address the under-researched risk of bisphenols (BPs) in e-cigarette liquids, comprehensive studies have been conducted to propose optimum sample preparation and analysis methods. To determine twelve BPs in refill liquids for e-cigarettes, three sample preparation methods based on distinct operational and working principles were employed. These included fabric phase sorptive extraction (FPSE), ultrasound-assisted solvent extraction of porous membrane-packed samples (UASE-PMS) and solid phase extraction (SPE) utilizing molecularly imprinted polymers (MIPs) technology. Each extraction method was combined with ultra-performance liquid chromatography coupled with tandem mass spectrometry (UPLC-MS/MS). Key parameters of FPSE and UASE-PMS procedures were optimized. This optimization included selection of the FPSE membrane types, durations of extraction and the choice solvents. Comprehensive validation was conducted, demonstrating linearity across a range from 2 to 60 ng/mL for all BPs (BPS, BPA, BPF, BPE, BPB, BPC, BPZ, BPFL, BPBP, BPP, BPG and BPM). Determination coefficients were above 0.9913, signifying linear relationship. The limits of detection (LODs) were established below 0.90 ng/mL, while the limits of quantification (LOQs) were lower than 2.5 ng/mL. Notably, the method based on UASE-PMS was successfully applied to the analysis of refill liquids for e-cigarettes samples. A comparative analysis of the methods highlighted variances in precision, accuracy, and applicable aspects, such as adjustment of parameters, sample preparation time, cost, handling, availability and possible limitations. Three methods have been identified as suitable for analysing BPs in e-cigarette refill liquids, highlighting the necessity to examine their presence in these products.

Optimal Geometry for Focused Ion Beam-Milled Samples for Direct-Pull Micro-Tensile Testing Performed In Situ in a Scanning Electron Microscope.

A thorough procedure was developed to efficiently manufacture dogbone samples using focused ion beam (FIB) milling for micro-tensile testing. A Bruker PI 89 PicoIndenter, Billerica, MA, USA, was used as a case study, although the analysis and results are applicable to other micro-mechanical testing systems capable of mounting a standard, Ø12.7 mm × Ø3.2 mm pin, scanning electron microscopy (SEM) pin stub (Ted Pella, Redding, CA, USA). Nine dogbones were made from an Fe-45Cu alloy additively manufactured using powder-fed laser-directed energy deposition (DED-LB). Testing showed that fracture was confined to the gauge section for all dogbones and that the fracture mode, ductile vs. brittle, was entirely dependent on the grain orientation relative to the loading direction. The analysis showed that the measured plastic strain to failure can vary from >11% (optimal geometry) to <1% (non-optimal geometry) in micro-tensile testing of high-tensile-strength (>1 GPa) metallic materials. Subsequently, a finite element analysis (FEA) was conducted to identify the improved dogbone geometries. A total of ten thousand dogbone geometries were tested, and their dimensions were defined by a set of four adjustable parameters (corner radius, load surface angle, load surface length, and dogbone head length). The gauge width and gauge length were fixed to 4 µm and 10 µm, respectively. Three-dimensional surface plots of the stress concentration as a function of two parameters were used to identify the optimal ranges of parameter values. The addition of maximum width and length constraints, measuring 25 µm and 30 µm, respectively, allowed us to identify an optimal geometry at load surface angles of 30° and 45°. Their respective dimensions (corner radius, load surface length, and dogbone head length) are, in µm, 12, 6, and 7 and 10, 7, and 7. Testing these two optimal geometries with a range of gauge lengths from 4 to 20 µm showed that smaller gauge lengths only slightly reduced the detrimental stress concentration outside the gauge section. However, smaller gauge lengths will notably improve the FIB surface polishing step as tapering is reduced with smaller dogbone lengths.

Variational quantum algorithm for designing quantum information maskers

Abstract Since the concept of quantum information masking was proposed by Modi et al. [Phys. Rev. Lett. 120, 230501 (2018)], many interesting and significant results have been reported, both theoretically and experimentally. However, designing a quantum information masker is not an easy task, especially for larger systems. In this paper, we propose a variational quantum algorithm to resolve this problem. Specifically, our algorithm is a hybrid quantum-classical model, where the quantum device with adjustable parameters tries to mask quantum information and the classical device evaluates the performance of the quantum device and optimizes its parameters. After optimization, the quantum device behaves as an optimal masker. The loss value during optimization can be used to characterize the performance of the masker. In particular, if the loss value converges to zero, we obtain a perfect masker that masks completely the quantum information generated by the quantum information source, otherwise, the perfect masker does not exist and the subsystems always contain the original information. Nevertheless, these resulting maskers are still optimal. Quantum parallelism is utilized to reduce quantum state preparations and measurements. Our work paves the way for the wide applications of quantum information masking, and some of the techniques used in this work may have potential applications in quantum information processing.

Automated denoising software for calcium imaging signals using deep learning

Dynamic Ca2+ signaling is crucial for cell survival and death, and Ca2+ imaging approaches are commonly used to study and measure cellular Ca2+ patterns within cells. However, the presence of image noise from instrumentation and experimentation protocols can impede the accurate extraction of Ca2+ signals. Removing noise from Ca2+ Spatio-Temporal Maps (STMaps) is essential for precisely analyzing Ca2+ datasets. Current methods for denoising STMaps can be time-consuming and subjective and rely mainly on image processing protocols. To address this, we developed CalDenoise, an automated software that employs robust image processing and deep learning models to remove noise and enhance Ca2+ signals in STMaps effectively. CalDenoise integrates four pipelines capable of efficiently removing salt-and-pepper, impulsive, and periodic noise and detecting and removing background noise. Comprising both an image-processing-based pipeline and three generative-adversarial-network-based (GAN) deep learning models, CalDenoise proficiently removes complex noise patterns. The software features adjustable parameters to enhance accuracy and is integrated into a user-friendly graphical interface for easy access and streamlined usage.CalDenoise can serve as a robust platform for denoising complex dynamic fluorescence signal images across diverse cell types, including Ca2+, voltage, ions, and pH signals.

Hybrid PLM and ADRC Control for Sensorless Induction Motor Drive with Nine-Level Converter Employing SVPWM

This paper outlines the design of a predictive controller combined with an active disturbance rejection control (ADRC)-type controller to enhance the dynamic performance of the induction motor powered by a nine-level converter. The predictive control law proposed is derived from the Poisson Laguerre model, based on predictive control. The motor is controlled using indirect field-oriented control, both with and without a speed sensor. For speed estimation, the Luenberger observer of order 4 is used. The predictive method utilized allows for the dynamic adjustment of control parameters based on those of the induction motor. The paper aims to eliminate internal and external disturbances and reduce total harmonic distortion (THD) through the use of a Nine-level cascaded H-bridge inverter. Space vector pulse width modulation (SVPWM) signals are generated using the logic of hexagon decomposition. The SVPWM method operates by decomposing higher-level hexagons into multiple two-level hexagons. The Poisson-Laguerre model (PLM) is also compared with the ADRC and the proportional-integral (PI) control. Simulations with MATLAB/SIMULINK software for an induction motor are performed to test the performance of each controller and the validity of the observer.

State of Charge Estimation for Lithium-Ion Battery Based on Fractional-Order Kreisselmeier-Type Adaptive Observer

For the safe and efficient use of lithium-ion batteries, the state of charge (SOC) is a particularly important state variable. In this paper, we propose a method for the online estimation of SOC and model parameters based on a fractional-order equivalent circuit model. Firstly, we constructed a fractional-order battery model that includes pseudo-capacitance and determined the values of the circuit elements offline using the least squares method from actual input–output data based on the driving profile of an automobile. Compared to the integer-order battery model, we confirmed that the proposed fractional-order battery model has higher accuracy. Secondly, we constructed a fractional-order Kreisselmeier-type adaptive observer as an observer that performs state estimation and parameter adjustment simultaneously. Applying the general adaptive law to the battery model results in a redundant design with many adjustable parameters, so we proposed an adaptive law that reduces the number of adjustable parameters without compromising the stability of the observer. The effectiveness of the proposed method was verified through numerical simulations. As a result, the high estimation accuracy and convergence of the proposed adaptive law were confirmed.

A Review on Friction Stir Welding of High-Strength Al-Zn-Mg Alloy: Insights on Second-Phase Particles

The friction stir welding (FSW) process is a unique combination of deformation and high temperature, which provides opportunities to modify microstructures through the adjustment of the processing parameters and is an ideal way to join non-weldable aluminum alloys by avoiding the formation of a molten pool. The 7xxx series heat-treatable aluminum alloys are widely used in the aerospace field as high-performance structural materials. The microstructure evolution and mechanical performance of these alloys are affected by the effects of thermomechanical processing, which provides opportunities to optimize the material properties by controlling microstructural features such as intermetallic constituent particles, dispersoids and nanoscale precipitates. This paper focuses on the basic principles of the thermal and mechanical effects generated during FSW on the evolution of second-phase particles in different zones of the weld.

Dynamic model of arriving passengers based on dual value drive

In order to optimize the service process of integrated transportation hubs, the dynamic characteristics of the gathering behavior of arriving passengers were analyzed, and the transformation mechanism of the gathering behavior of arriving passengers in the time dimension of inverse gamma distribution, gamma distribution and chi-square distribution was studied. It was revealed that the gathering behavior was jointly affected by the flight operation time and the utility of the transfer mode, and was converted into the time value and utility value of the arriving passengers respectively. On this basis, a dual-value-driven dynamic model of arriving passengers was established based on the three distributions, and the output was the parameter-adjustable distribution of arriving passengers. The results show that the simulation output with adjustable parameters is consistent with the real distribution, which provides a method and basis for the accurate prediction of the distribution of arriving passengers at hub airports.

Fast stability enhancement of inverter‐based microgrids using NGO‐LSTM algorithm

AbstractTo improve the stability of the inverter‐based microgrid (MG), this paper employs a novel data‐driven based method to coordinately adjust control parameters of inverters in a fast local manner. During the design process, an offline eigenvalue based optimization problem that is used to calculate the optimal control parameters under various operating conditions is first constructed. In order to reduce reliance on full system information, a feature selection algorithm is utilized to extract the most relevant local measurements that influence the adjustment of each control parameter. Then, regarding local measurements as input variables and optimal control parameters as output variables, based on northern goshawk optimization (NGO) and long short‐term memory (LSTM) network, a novel deep learning algorithm is proposed to train the local parameter adjustment model (LPAM) by learning the mapping relationship between them. During the application, to guarantee the stability of MG all the time, a security region based shielding mechanism is developed, where the improper control parameter adjustment will be replaced by a safe one. The case study indicates that the proposed algorithm has better mapping accuracy than traditional LSTM neural networks and also faster calculation speed than the traditional offline optimization‐based method. The effectiveness and advantages of the proposed method are demonstrated in a modified 9‐bus MG.

An Online Data-Driven Method for Accurate Detection of Thermal Updrafts Using SINDy

Utilizing thermal updrafts shows potential for enabling long-endurance cruising of fixed-wing unmanned aerial vehicles without energy consumption. This article presents a novel online method based on sparse identification of nonlinear dynamics (SINDy) approach to achievement identification of thermal sources in the atmosphere. Initially, the algorithm is incorporated into the upper-level planning system, interacting with the lower-level controller. Then, experiments are conducted through software-in-the-loop simulations (SITL) to validate the implementation of the proposed algorithm. It is found that direct observation of thermal sources through measurements using SINDy is unfeasible during straight and circular flight modes. Nevertheless, simulation analysis of the proposed approach indicates that under unobservable conditions, a portion of the parameters can still be identified. By comparing results obtained using the particle filter algorithm, this method is shown to accurately estimate the parameters with negligible errors under observability conditions. The novelty of this approach lies in its significant improvement of the localization accuracy of the thermal source, without the need for parameter adjustments in the algorithm. Finally, the proposed methods are integrated into commonly used hardware platforms, and their online feasibility is verified through hardware-in-the-loop simulations.

Vibration control of a longitudinally vibrating rod connected through an elastic coupler by installing a nonlinear vibration reduction coupler

To study the potential application of the longitudinal vibration control of a rod coupling system by employing NESs, this study proposes a nonlinear vibration reduction coupler (NVRC), where the NVRC can be regarded as the NES which is installed between the two elastic structures. The introduction of NVRC is aimed at controlling the longitudinal vibration of the rod system. Based on the Lagrange method (LM), the longitudinal vibration analysis model of a rod system connected through a linear elastic coupler and an NVRC is established, in which the longitudinal vibration responses of the rod system with an NVRC are predicted. In the numerical analysis, the correctness and stability of LM in calculating longitudinal vibration responses of the rod system with an NVRC are verified, where the chosen reasons for observation points are explained. It can be concluded that the introduction of NVRC can reduce the vibration of each resonance area of the rod system at the same time. Under certain parameters, the vibration characteristics of the rod system are changed by employing NVRC. Furthermore, nonlinear stiffness and viscous damping of NVRC can be chosen as the adjustable parameters that strengthen the vibration reduction ratio of the rod system. Overall, the longitudinal vibration of the rod system can be effectively controlled by choosing reasonable parameters of NVRC. The introduction of NVRC provides an effective way to control the longitudinal vibration of the rod system.

Development of Robot Feature for Stunting Analysis Using Long-Short Term Memory (LSTM) Algorithm

Stunting prevalence in Indonesia persists as a significant challenge necessitating concerted efforts from all stakeholders. We developed robot for stunting analysis using deep learning algorithm. It aligns with the Sustainable Development Goal (SDG) agenda, specifically targeting SDG 3, which focuses on ensuring good health and well-being for all. Long Short-Term Memory (LSTM) is a type of Recurrent Neural Network (RNN) designed to overcome the vanishing gradient problem in traditional RNNs. In general, either LSTM can be used in analysis. This study aims to classify stunting based on age and height using LSTM. The LSTM model was trained with 50 epochs using datasets collected from the health office and robots. The evaluation results show training accuracy of 96.65% and training validation of 96.61%, with precision, recall and f1-score varying with relevance to the f1-score and support value. This research illustrates the potential for using data classification methods in stunting diagnosis. However, it is necessary to adjust parameters and increase the amount of training data to improve model performance. With good convergence at epoch 50, these results show the model's ability to classify stunting based on age and height. However, further validation and testing on larger datasets is needed to thoroughly test the reliability and generalization of the model. This research can contribute to the development of deep learning regarding robots as a means of testing stunting. This research provides initial evidence of the potential of stunting classification methods using robots. However, parameter adjustments and increasing the amount of training data need to be done to improve the overall model performance.