Modeling Of Processes Research Articles

Digital Twin Types and Applications in Healthcare.

Digital Twins, represents an innovative approach consisting of real-time digital replicas of physical entities. This innovative concept has already many applications in Industry, automotive, business environment and is also transforming the healthcare industry. Digital Twins have the potential to provide comprehensive models of individual patients, hospital facilities, and medical processes, integrating data from various sources such as electronic health records, wearable devices, and imaging systems. This paper discusses Digital Twin models and their application in healthcare, focusing on care coordination, treatment planning and hospital management development.

MODELS OF CORRELATION FUNCTIONS OF NONSTATIONARY PROCESSES AND SEQUENCES FOR TECHNOLOGICAL SYSTEMS

Precision technological processes for the production of modern microelectronic products require compliance with the quality of source materials, working environments, and precise adherence to regimes. Due to natural fluctuations in the properties of materials and the environment, and variable states of all technological processes, the parameters of the product and technological processes cannot be described by deterministic laws. Due to the inevitable natural properties of fluctuations in the parameters of technological equipment and its operating modes, the state variables of all technological processes are random functions of space-time coordinates. In most cases, these accidents cannot be neglected, since they all affect the output parameters of the products. The most complex mathematical models of technological systems and processes in modern theory are random spatiotemporal fields, representing both input and output characteristics, as well as parameters of the systems under consideration. The purpose of this work is to model real-valued values of correlation functions of non-stationary random processes and sequences. When constructing a correlation theory of random processes and sequences, a complex representation is widely used, i.e. random functions of the form are considered: continuous or discrete time. This approach made it possible to construct a correlation theory of nonstationary random functions using the spectral theory of non-self-adjoint or unitary operators and to introduce the concept of complex spectrum. For applications of the correlation theory of nonstationary random functions and their modeling, it is convenient to deal with real-valued correlation functions. The construction of real-valued correlation functions can be carried out using the well-known fact that the real part of complex-valued correlation functions is also a correlation function (for the imaginary part this statement is unfair, since the imaginary part is a cross-correlation function of the real and imaginary parts of the corresponding random process or sequence) . The resulting models of correlation functions of non-stationary random processes and sequences can be used to construct algorithms for forecasting and filtering non-stationary random functions

Modeling and Prediction of Relaxation-Deformation Processes of Polymer Textile Materials

Modeling and Prediction of Relaxation-Deformation Processes of Polymer Textile Materials

Optimal Tax Trajectory of a Commercial Organisation: Economic and Mathematical Approach

The aim of this study is to form a new concept of tax burden calculation—optimal tax trajectory, which meets the needs of economic entities in view of the optimisation of tax payments and state authorities in terms of budget replenishment and subsequent efficient spending of state resources. The presented concept is developed on the basis of mathematical modelling of related economic processes. The model is based on the differential equation. An attempt is made to analyse the impact of building an optimal tax trajectory on the efficiency of the organisation’s activity. It shows that it is possible to increase the tax burden on economic entities in order to replenish the revenue part of the budget, which does not affect their financial situation. The proposed approach expands the instrumental apparatus for calculating tax payments from the position of taxpayers and fiscal authorities. The construction of the optimal tax trajectory facilitates the adoption of point decisions concerning the increase or decrease of the tax burden of an economic entity in mutual account with the factors of the macroeconomic conjuncture. This approach allows for managing the revenue part of the budget and redistributing it later to solve social problems or overcome business downturns.

Coupling the Glacio-hydrological Degree-day Model (GDM) with PCRaster for spatial dynamic modeling of Himalayan river basins

Abstract. We have seen a surge in glacio-hydrological modeling efforts in the past few decades. This form of modeling is also being carried out in the Himalayan river basins, but a comprehensive high-resolution simulation software that can be effective with a limited number of hydrometeorological data is recommended. In this regard, an open-source, scalable, flexible, and distributed modeling system called PyGDM has been developed by fully coupling the Glacio-hydrological Degree-day Model with PCRaster Python software. To evaluate the potential of using this model in the Himalayan river basins, we calibrated and then validated the model for Trishuli River basin using geographical data and the existing hydrometeorological data. The tests showed a promising result with respect to the effective application of the model in the entire Himalayan region. The PyGDM source code was optimized and adapted to the process models of glacier melting and hydrological processes in Himalayan basins. It increased the speed of the simulation, made the model highly scalable to accommodate new submodels, and enhanced the flexibility of the model to ingest various types of input data and parameters. Hence, the PyGDM model strives to simulate the glacio-hydrological processes of the entire Himalayan region.

Forward and backward modeling of cultural evolutionary processes

Modern cultural evolution theory adopts a variety of concepts and methods developed in mathematical biology, in particular population genetics theory. In addition to forward-looking approaches such as two-locus models, backward-looking approaches such as coalescent theory, which describe ancestral states of the current population, have played an important role in population genetics. Here, we show how forward and backward approaches can be applied to two examples in cultural evolution. The first example deals with the number of cultural traits, which can be analyzed by a backward approach. Cultural coalescent theory illustrates many unique aspects of cultural processes such as information transfer (i.e., social learning) from many donors ("cultural parents"), including or excluding the biological parents. Theory predicts that many cultural traits of intermediate (or higher) frequency (popularity) can exist that are surprisingly old. Many unsolved issues remain, however, such as how to incorporate social structure as well as natural and/or cultural selection, which we believe to be an urgent agenda. The second example is the punishment of sibling incest, a problem to which cultural coalescent theory cannot currently be usefully applied. By analyzing forward recursions, we show that punishment is ineffective in suppressing incest, unless the incestuous inclination is diminished by the presence of punishers. Based on these examples, we discuss the merits and demerits of forward and backward approaches.

Development and verification of material models in modeling of wave strain hardening and additive synthesis processes

BACKGROUND: The creation of competitive machine parts capable of withstanding standard and increased operational loads is an urgent task in mechanical engineering. Developing additive synthesis technologies together with strengthening technologies make it possible to create such products with high load-bearing capacity. However, to improve the efficiency of these technologies, it is necessary to create theoretical models of the processes taking place. The article presents the results of the first stage of creating complex theoretical models of the combined 3DMP process and wave strain hardening (WSH) required for designing technological processes for manufacturing engine parts and brake systems of automotive equipment. . AIMS: Creation and assessment of the adequacy of material models used in finite element modeling of additive synthesis processes with subsequent hardening. MATERIALS AND METHODS: Theoretical models of the material were created in the ANSYS software package, which allows for multidisciplinary calculations. The experimental data required for preparing the models were obtained by testing tensile samples manufactured using standardized methods. The hardness of materials was studied using a KB 30S automatic hardness tester. The adequacy of additive synthesis modeling was assessed based on the distribution of temperature fields. The adequacy of material models for the VDU process was assessed based on the sizes of individual plastic indentations and the distribution diagrams of the depth and degree of hardening in the surface layer. RESULTS: Theoretical models of the following materials were developed: steel, stainless steel, bronze alloy, titanium alloy, aluminum alloy. The theoretical data obtained from the modeling results have a high level of significance. The studies were conducted for various thermal (in the range from +20ºС to +800ºС) and deformation modes. Graphical results of theoretical and experimental studies allow us to obtain a qualitative assessment of the processes under study with the required accuracy. CONCLUSIONS: As a result of the assessment of the adequacy of the developed models, it was established that the discrepancy between the empirical and theoretical data does not exceed 7.4%. The obtained models of materials are statistically significant and can be correctly applied in further studies.

Інтегральний показник для оцінювання ефективності спеціалізованих моніторингових систем

The purpose of the article is to develop a methodology for calculating the integral index based on existing methods for calculating soil pollution, with the proposal of an algorithm for calculating the system of integral indices. Based on the integral indicator, the effectiveness of the developed complex was evaluated in comparison with other known solutions in the field of soil pollution monitoring, which showed the advantage of the developed complex in comparison with analogues at the level of 42%. In addition, performance measurements serve as the basis for setting performance targets and service level agreements. By establishing quantifiable performance indicators and benchmarks, organizations can set clear expectations for system performance and reliability. These performance targets not only provide a means of evaluating the success of software projects, but also serve as the basis for contractual agreements between service providers and customers. To measure these indicators, it is proposed to use information and measurement systems that are easy to implement from a technical and technological point of view. Therefore, the article proposes mathematical and software for monitoring soil and groundwater contamination by harmful emissions and subsequent modeling of processes using an integral indicator.

Feeding a rich diet supplemented with the translation inhibitor cycloheximide decreases lifespan and ovary size in Drosophila.

Drosophila oogenesis has long been an important model for understanding myriad cellular processes controlling development, RNA biology and patterning. Flies are easily fed drugs to disrupt various molecular pathways. However, this is often done under poor nutrient conditions that adversely affect oogenesis, thus making analysis challenging. Cycloheximide is a widely used compound that binds to and stalls the ribosome, therefore reducing protein synthesis. As egg production is a highly nutrient-dependent process, we developed a method to feed female Drosophila a rich diet of yeast paste supplemented with cycloheximide to better determine the effect of cycloheximide treatment on oogenesis. We found that flies readily consumed cycloheximide-supplemented yeast paste. Males and females had reduced lifespans when maintained on cycloheximide, with males exhibiting a dose-dependent decrease. Although females did not exhibit decreased egg laying, their ovaries were smaller and the number of progeny reduced, indicating substandard egg quality. Finally, females fed cycloheximide had disrupted oogenesis, with smaller ovaries, missing ovariole stages, and an increase in apoptotic follicles. Together, these data support that reduced protein synthesis adversely affects oogenesis with a rich diet that provides optimal nutrient conditions. In addition, this method could be used more broadly to test the effect of other drugs on Drosophila oogenesis without the confounding effects caused by poor nutrition.

A comparative study of Chinese and foreign research relevant to the diffusion drift model in the last decade

Abstract. This study evaluates the differential research approaches of Chinese and international scholars regarding the drift diffusion model in mental processes through a literature review from the last decade. The application of DDM theory in cognitive research varies between Chinese and foreign study methodologies. The differences in decision-making mechanisms among cultural groups result in this outcome. Inconsistency has been identified in international academic research. They cover reward rate optimization, decision thresholds, decision time, and more. On the contrary, advancements in Chinese studies involve the development of innovative models. They are Bayesian and semi-parametric. These are designed for mixtures combining drift-diffusion processes and the inverse Gaussian distribution. In addition, they encompass elucidating the neural processes and implementing DDM techniques. This use of DDM reveals the rewarding perception and decision-making linked to depression. It also reveals the brain patterns of social anxiety. These comparisons aim to summarize the differences between Chinese and foreign studies. They also analyze them. It will find the causes of these differences. Moreover, it will determine how Chinese clinical care can use them. The DDM studies show its importance in decision-making patterns. Scholars have the opportunity to apply these tools in a variety of scientific fields, including neuroscience, psychology, artificial intelligence, and cognitive research.

The Neural Basis and Computational Models of Metacognition

Abstract: The ability to reflect on ones own thinking is what makes human cognition "meta." Metacognition, the capability to assess, reflect on, and control first-order cognitive processes, is essential for flexible and adaptive behaviors across various contexts. This review explores the neural mechanisms and computational models underpinning metacognition. The involvement of brain regions, including the insula, precuneus, medial prefrontal cortex, and dorsolateral prefrontal cortex in metacognitive judgments is examined. How distinct regions support both domain-general and domain-specific metacognitive processes is also explored. Furthermore, the neural correlates of metacognitive executive functions, such as error monitoring and cognitive control, are investigated, with a focus on the prefrontal and anterior cingulate cortex and their roles in regulating working memory and performance monitoring. This review also discusses the Bayesian models of human metacognitive processes proposed by Fleming and Daw. Studies on human metacognition have significant implications for the development of artificial intelligence, evidenced by the H-CogAff architecture, revealing how integrating metacognitive frameworks could enhance AIs transparency, reasoning, adaptability, and perception. The findings suggest that investigating the neural mechanisms and computational models of metacognition is crucial not only for understanding human cognitive processes but also for improving the resilience and flexibility of AI systems. Future studies in this field should expand the scope by integrating broader and more qualitative dimensions, such as affective self-assessment and social cognition, while maintaining the precision of current evaluation approaches.

USING THE METHOD OF WEIGHTED RESIDUALS IN THE FEM FORM FOR THE APPROXIMATION OF TWO-DIMENSIONAL DISTRIBUTIONS

The paper is devoted to the description of the method of two-dimensional approximation of data using algorithms of the method of weighted residuals with piecewise specified basis functions in the implementation of the Finite Elements Method. The mathematical formulation of the problem and the main relations of the method for two-dimensional regions are provided. A triangular finite element is involved in the simulation. Information is given about the program developed according to the algorithms of this method, the result of which is the selection of regions of a two-dimensional figure with the specified values of the analyzed parameters. By use of randomly distributed coordinates, the verification of the results for different data sets was performed and a satisfactory correspondence of the approximated and input data was obtained. Additional software, including programs written in Python and a web application created using the Laravel framework in PHP, has been developed to create a database that is scheduled to be processed by approximation. The PyQt5, OSMnx, requests, aiohttp, BeautifulSoup libraries and the PostgreSQL database management system were used to implement the project tasks. Algorithms of the developed software are described. An example of the reproduction of the locations of cities on the map of Ukraine is provided. The developed program of two-dimensional approximation was applied to the analysis of spatio-temporal dynamics of the emergence of cities on the territory of Ukraine. As an example, data on the founding of cities in the period from 800 to 1200 AD were considered and the main urbanized regions at that time were determined. The results of this Finite Element approximation were obtained for the purpose of preparing data for further modeling of sociodynamic processes in the terrain of Ukraine. The obtained results in the form of coordinates of the borders of regions that had a high level of urbanization can be used in various scientific studies, primarily in historical sciences.

Analysis of the changes in filtration and capacity properties of the oil and gas condensate field reservoirs using X-ray computed tomography methods

Objective. To study the nature of changes in structural, capacity and filtration properties of the Chayanda oil and gas condensate field reservoir resulting from mechanical and hydrodynamic testing and to improve the quality of laboratory assessment of the reservoir properties of rocks by applying the digital approach. Materials and methods. A high-resolution X-ray micro-CT scanner ProCon X-Ray CT-MINI was used for computed tomography. Digital analysis of images was carried out in GeoDict software. Results. The results of digital analysis of changes in the pore space of hydrocarbon reservoir by computer tomography methods after the tests with fluid filtration under baric conditions are presented, including comparison of macroscopic changes in the pore space and determination of the nature of changes in reservoir porosity and pore geometry at the macro level. Porosity values were determined using digital methods and compared with laboratory data. Numerical modeling of filtration processes on the created 3D models of the rock was performed. The fact of nonuniform distribution of filtration flows was established: filtration in the rock occurs mainly through isolated alternating channels. It was determined that the change in the rock pore space occurred mainly due to deformation and expansion of the walls of the main filtration channels. Conclusions. Nonuniformity of changes in filtration-capacitance properties of rock specimens caused by mechanical and hydrodynamic tests can lead to incorrect estimation of porosity and permeability when applying traditional laboratory methods. The results of nondestructive digital studies can be advised as a supplement to laboratory studies of core material properties. Joint application of digital and traditional laboratory methods allows obtaining the most complete range of data on reservoir properties to solve problems arising during development.

Modeling the dynamics of addiction relapse via the double-well potential system.

Substance use relapse is difficult to define, and previous work has used one-size-fits-all ad hoc definitions. Researchers have called for a dynamic and personalized understanding of relapse as a concept and model, necessitating novel statistical tools. We aimed to develop and validate a novel statistical model of latent relapse processes: the double-well potential model (DWPM). This model describes posttreatment substance use in terms of a dynamical system with stable equilibria of abstinence and relapse, person-specific dominant equilibria (tilt), the ease of changing between equilibria (steepness), and an overall relapse risk (RR). Using timeline follow-back data from N = 139 adults with a substance use disorder transitioning back to the community after residential treatment, we examined individual differences and the criterion-related validity of DWPM parameters to determine the clinical utility of the double-well model. While nonuse was the predominant stable state across participants, we found significant between-subjects variability steepness and RR. These individual differences were predictable via demographics, baseline psychopathology, treatment history, and treatment condition. Steepness and RR also predicted long-term outcomes, including life satisfaction and criminal behavior, above and beyond traditional metrics of relapse (proportion of days used and time to first use). Thus, the DWPM is a strong theoretical and statistical representation of the underlying relapse processes. Moreover, the parameters show criterion-related validity and may be useful in precision medicine. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Under the magnifying glass: A combined 3D model applied to cloudy warm Saturn-type exoplanets around M dwarfs

Warm Saturn-type exoplanets orbiting M dwarfs are particularly suitable for an in-depth cloud characterisation through transmission spectroscopy because the contrast of their stellar to planetary radius is favourable. The global temperatures of warm Saturns suggest efficient cloud formation in their atmospheres which in return affects the temperature, velocity, and chemical structure. However, a consistent modelling of the formation processes of cloud particles within the 3D atmosphere remains computationally challenging. We explore the combined atmospheric and micro-physical cloud structure and the kinetic gas-phase chemistry of warm Saturn-like exoplanets in the irradiation field of an M dwarf. The combined modelling approach supports the interpretation of observational data from current (e.g. JWST and CHEOPS) and future missions (PLATO, Ariel, and HWO). A combined 3D cloudy atmosphere model for HATS-6b was constructed by iteratively executing the 3D general circulation model (GCM) expeRT/MITgcm and a detailed kinetic cloud formation model, each in its full complexity. The resulting cloud particle number densities, particle sizes, and material compositions were used to derive the local cloud opacity which was then used in the next GCM iteration. The disequilibrium H/C/O/N gas-phase chemistry was calculated for each iteration to assess the resulting transmission spectrum in post-processing. We present the first model atmosphere that iteratively combines cloud formation and 3D GCM simulation and applied it to the warm Saturn HATS-6b. The cloud opacity feedback causes a temperature inversion at the sub-stellar point and at the evening terminator at gas pressures higher than 10$^ $ bar. Furthermore, clouds cool the atmosphere between $10^ $ bar and 10 bar, and they narrow the equatorial wind jet. The transmission spectrum shows muted gas-phase absorption and a cloud particle silicate feature at $ The combined atmosphere-cloud model retains the full physical complexity of each component and therefore enables a detailed physical interpretation with JWST NIRSpec and MIRI LRS observational accuracy. The model shows that warm Saturn-type exoplanets around M dwarfs are ideal candidates for a search for limb asymmetries in clouds and chemistry, for identifying the cloud particle composition by observing their spectral features, and for identifying in particular the cloud-induced strong thermal inversion that arises on these planets.

New Groups and Post-Traumatic Growth: Experimental Evidence That Gaining Group Memberships Supports Recovery From Natural Disaster

This paper provides the first experimental test of whether two social identity model of traumatic identity change processes—(i) group membership gain, and (ii) group membership continuity—predict post-traumatic growth (PTG) and post-traumatic stress (PTS) via social identity revitalization. Participants ( N = 210, Mage = 49.59 years) were adult flood survivors who were randomly allocated to one of three conditions: group membership gain, group membership continuity, or a weather control. Participants then completed measures of PTG, PTS, and social identity revitalization. Participants in the group membership gain condition reported greater social identity revitalization, compared to the group membership continuity and control conditions. Social identity revitalization, in turn, predicted PTG, and the indirect effect of group membership gain on PTG was significant. We concluded that gaining new group memberships play a role in supporting natural disaster recovery by fostering positive reappraisals of the disaster via social identity revitalization.

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multi-time scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multi-output prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dynamic modeling of complex energy conversion processes.

Recombination efficiency in c-plane (In,Ga)N/GaN quantum wells: saturation of localisation sites versus Auger–Meitner recombination

Abstract Light emitting diodes based on c-plane (In,Ga)N/GaN quantum wells (QWs) can have >90% emission efficiency at modest current densities but this drops significantly at higher excitation, an effect known as efficiency droop that limits device efficacy at high brightness. Several explanations for this have been proposed including the saturation of carrier localisation sites at high excitation densities, resulting in a greater exposure of carriers to defects and hence a significant increase in the associated non-radiative recombination processes. Here, power- and temperature-dependent photoluminescence spectroscopy of c-plane (In,Ga)N/GaN QWs is used to investigate the relationship between the saturation of localised states and emission efficiency. For the samples studied, we find that the saturation of localised sites broadly coincides with the onset of efficiency droop. However, it is also found that as the localised states saturate with increasing excitation, the relative contribution of defect-associated non-radiative processes to overall recombination decreases rather than increases. Based on these observations and on modelling of recombination processes in the QW, it is concluded that the saturation of localised states does not significantly contribute to the reduction in emission efficiency at high excitation. Our studies rather suggest that defect-related non-radiative recombination is out-competed by radiative and Auger–Meitner recombination at the carrier densities required for saturation.

The HVAC system engineering method for a new family of unified cabins of combine harvesters

BACKGROUND: Designing a combine harvester cabin climate system is a complex and multi-stage process that includes solving a set of tasks. To solve them, a design engineer must have knowledge and skills in various fields, starting with thermal engineering calculations and ending with experimental research methods and computer modeling, which requires a large amount of intellectual and time resources. Therefore, the task of creating a unified method of engineering of combine harvester cabin HVAC system is highly relevant. AIM: Development of the HVAC system for a unified cabin of a grain harvester and a forage harvester. The designed HVAC system is purposed to create a comfortable microclimate in the cabin of the combine for 2 people in summer and winter operating conditions. METHODS: The methodology of calculation and selection of the combine harvester cabin HVAC system, which includes the development of engineering calculation methods and mathematical modeling of thermodynamic and ventilation processes in the cabin, is considered. RESULTS: The main parameters were determined: heat intakes and heat losses for the grain harvester and forage harvester cabins, which amounted to 2.8 and 2.2 kW for the grain harvester, 2.9 and 2.35 kW for the forage harvester; the required air flow rate supplied to the cabin to ensure a comfortable temperature — 740 m3/h; the percentage of air recirculation regarding the conditions of absence of fogging and creation of excessive pressure in the cabin — 75%; the cooling and heating capacity of the HVAC system, taking into account the operating conditions of the combine, are 7.8 and 6.3 kW respectively. The selection of the main equipment of the HVAC system for a unified cabin for a new family of unified cabins of combines — the BUHLER 1000 MFWD evaporator-heater and the Valeo TM16 compressor are chosen. CONCLUSION: The HVAC system designed in accordance with the presented methodology is capable of ensuring a comfortable cabin air temperature in the range of 22–24 °C at various operating modes of the combine harvester in different regions. In addition, the HVAC system parameters eliminate fogging of the cabin windows and the penetration of dusty air inside due to the created excessive pressure.

Comparing Feature and Trajectory-Based Remaining Useful Life Modeling of Electrical Resistance Heating Wires

Industrial heating significantly contributes to global greenhouse gas emissions, accounting for a substantial portion of annual emissions. The transition to fossil-free operations in the heating industry is closely linked to advancements in industrial electrical heating systems, especially those using resistance heating wires. In this context, Prognostics and Health Management is crucial for enhancing system reliability and sustainability through predictive maintenance strategies. The integration of machine learning technologies into Prognostics and Health Management has significantly improved the precision and applicability of Remaining Useful Life modeling. This improvement enables more accurate predictions of component lifespans, optimizes maintenance schedules, and enhances operational efficiency in industrial heating applications. These developments are essential for reducing greenhouse gas emissions in the sector. This paper serves as a guide for conducting Remaining Useful Life modeling for industrial batch processes. It evaluates and compares two methodologies: deep learning-based approaches using full time-series data, such as recurrent neural networks and their variants, and feature-engineering-based methods, including random forest regression and support vector machines. Our results show that the feature-oriented approach performs better overall in terms of predictive accuracy and computational efficiency. The study includes a detailed sensitivity analysis and hyperparameter estimation for each method, providing valuable insights into developing robust and transparent Prognostics and Health Management systems. These systems are crucial in supporting the heating industry’s move towards more sustainable and emission-free operations. The findings reveal that feature-oriented methods are both performant and robust, particularly excelling in handling outliers. The random forest regression model, in particular, demonstrated the highest performance on the test dataset according to the chosen evaluation metrics. Conversely, trajectory-oriented methods exhibited less bias across varying levels of degradation, a helpful characteristic for Prognostics and Health Management systems. While feature-oriented methods tend to systematically underestimate Remaining Useful Life at high true values and overestimate it at low actual values, this issue is less pronounced in trajectory-oriented models. Overall, these insights highlight the strengths and limitations of each approach, guiding the development of more effective and reliable predictive maintenance strategies.