Arrhenius Model Research Articles

Evaluation of Machine Learning Models for Predicting the Hot Deformation Flow Stress of Sintered Al-Zn-Mg Alloy

Abstract In predicting flow stress, machine learning (ML) offers significant advantages by leveraging data-driven approaches, enhancing material design, and accurately forecasting material performance. Thus, the present study employs various supervised ML models, including Linear Regression (Lasso and Ridge), Support Vector Regression (SVR), Ensemble Methods (RF, GB, XGB), and Neural Networks (ANN, MLP), to predict flow stress in the hot deformation of an Al-Zn-Mg alloy. The ML methodology involves sequential steps from data extraction to cross-validation and hyperparameter tuning, which is conducted using the hyperopt library. Model performance is assessed using average absolute relative error (AARE), root mean squared error (RMSE), and mean squared error (MSE). The results show that ensemble methods (RF, GB, XGB) and neural networks outperform traditional regression methods, demonstrating superior predictive accuracy. Visualization using half violin plots reveals the models' error ranges, with XGB consistently exhibiting the best performance. SVR, RF, GB, XGB, ANN, and MLP showed better performance than the Arrhenius model in the context of AARE and MSE metrics. Interestingly, SVR had a somewhat higher AARE of 1.89% and an MSE of 0.251 MPa2, while XGB had the lowest AARE of 0.2% and the lowest MSE of 0.011 MPa2. When ML models were evaluated using the skill score in relation to the Arrhenius model, XGB scored higher than SVM at 0.714, with a score of 0.986. In contrast Lasso and Ridge exhibited negative scores of −0.847 and −0.456, respectively.

Research on predicting the thermocompression deformation behavior of Mg-Li matrix composite using machine learning and traditional techniques

Artificial intelligence and machine learning (ML) technologies have emerged as powerful tools for analyzing the thermal compression deformation behavior of metal matrix composites, offering significant potential to optimize their plastic deformation processing techniques. In this study, the Al3La/LAZ532 composite based on in-situ self-reaction technology was successfully prepared by adding La2O3 particles. Then, the thermal compression flow behavior of the as-cast composite was comparatively researched using a traditional Arrhenius model and advanced machine learning methods (Linear Regression, AdaBoost, Random Forest, and XGBoost). The flow stresses were predicted under various thermal operating conditions, and the performance of all models was assessed using root mean square error (RMSE), coefficient of determination (R2) and mean absolute error (MAE). Analysis shows that the Random Forest model outperforms traditional models and other ML methods in predictive accuracy, achieving an R2 of 0.97, an MAE of 5.8, and an RMSE of 7.07. Additionally, the stable hot working zone for the composite at 300 °C and a strain rate of 0.001∼0.01 s⁻1 can be identified by combining the microscopic structure with the macroscopic hot working map. This zone is characterized by a uniformly distributed, fine-grained structure with high levels of dynamic recrystallization (DRX). The texture with the <0001> axis of the grains aligned parallel to the compression direction (CD) is formed in the thermally deformed microstructure, and the DRX mechanism is discontinuous dynamic recrystallization (DDRX).

Preparation and characterization of dressing-type emulsions formulated with hydrocolloids from the mango (Mangifera indica) peel

Mango is a popular tropical fruit known worldwide and mango peel is a waste product worthy of valorization. This study explores the stabilizing effect of hydrocolloids extracted from mango peel in dressing-type emulsions (DE). Emulsions stabilized with different ratios of mango (Mangifera indica) peel-derived hydrocolloids (PE) and guar gum (1% wt. total concentration) were prepared and characterized: DE1 (0.25/075), DE2 (0.5/0.5), DE3 (0.75/0.25) and DE4 (1/0). Particle size distribution, ζ-potential, proximal composition, color, microstructure, and rheological properties were evaluated. All the samples showed similar proximal compositions. However, PE/guar gum ratio influences color parameters. For the microstructural analysis, Sauter's mean droplet size ranged from 6.41 to 11.11 µm. The ζ- potential values ranged from -18.03±0.21 to -16.97 mV. Emulsions exhibited shear thinning responses that can be well described by the Williamson model, and gel-like viscoelastic character with G’ higher than G”. The activation energy values (Eα) deduced from the application of an Arrhenius model to the viscous flow behaviour of the emulsions ranged from 108.46 to 143.44 Kj/mol. From the microstructural analysis and the rheological characterization, it can be inferred that PE favors the flocculation of the emulsion droplet in high concentrations. Overall, this research contributes to the sustainable exploitation of a mango waste material, such as the peel, in food emulsions.

Thermal Decomposition and Kinetic Analysis of Amazonian Woods: A Comparative Study of Goupia glabra and Manilkara huberi

This study presents a detailed analysis of the thermal degradation and kinetic behavior of two Amazonian wood species, Goupia glabra (cupiúba) and Manilkara huberi (maçaranduba), using thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), Fourier-transform infrared spectroscopy (FTIR-ATR), and direct infusion mass spectrometry (DIMS). Wood samples were subjected to controlled heating rates of 20, 40, and 60 °C/min from 25 to 800 °C under an argon atmosphere. TGA revealed moisture evaporation below 120 °C, with hemicellulose degradation occurring between 220 and 315 °C, cellulose decomposition between 315 and 400 °C, and lignin breakdown over a broader range from 180 to 900 °C. The highest rate of mass loss occurred at 363.99 °C for G. glabra and 360.27 °C for M. huberi at a heating rate of 20 °C/min, with shifts to higher temperatures at faster heating rates. Activation energies were calculated using Arrhenius and Kissinger models, yielding values between 53.46–61.45 kJ/mol for G. glabra and 58.18–62.77 kJ/mol for M. huberi, confirming their stable thermal profiles. DSC analysis identified a significant endothermic peak related to moisture evaporation below 100 °C, followed by two exothermic peaks. For G. glabra, the first exothermic peak appeared at 331.45 °C and the second at 466.08 °C, while for M. huberi, these occurred at 366.41 °C and 466.08 °C, indicating the decomposition of hemicellulose, cellulose, and lignin. Enthalpy values for G. glabra were 12,633.37 mJ and 18,652.66 mJ for the first and second peaks, respectively, while M. huberi showed lower enthalpies of 9648.04 mJ and 14,417.68 mJ, suggesting a higher energy release in G. glabra. FTIR-ATR analysis highlighted the presence of key functional groups in both species, with strong absorption bands in the 3330–3500 cm−1 region corresponding to O-H stretching vibrations, indicative of hydroxyl groups in cellulose and hemicellulose. The 1500–1600 cm−1 region, representing aromatic C=C vibrations, confirmed the presence of lignin. Quantitatively, these results suggest a high content of cellulose and lignin in both species. DIMS analysis further identified polyphenolic compounds and triterpenoids in M. huberi, with major ions at m/z 289 and 409, while G. glabra showed steroidal and polyphenolic compounds with a base peak at m/z 395. These findings indicate the significant presence of bioactive compounds, contributing to the wood’s resistance to microbial degradation. This comprehensive thermal and chemical characterization suggests that both species have potential industrial applications in environments requiring high thermal stability.

Insight into performance and lifetime of ecofriendly pollution barriers in landfill for emergency: A thermogravimetric analysis for novel polymer materials

The novel polymer barrier wall is an in-situ remediation technology designed to effectively control the migration of pollution and prevent the diffusion of pollutants by blocking, sealing, or altering the direction of groundwater flow. With its advantages of rapid chemical reaction (achieving 95 % strength within 15 min) and portable equipment suitable for narrow and rugged emergency sites, this innovative polymer barrier demonstrates promising prospects for practical application. Hence, ensuring the long-term durability of new materials under corrosive and high-temperature leachate conditions is crucial. In this study, a comprehensive investigation was conducted on the corrosion and thermal aging performance of novel polymer materials. Firstly, the mechanical tensile properties of the polymer materials were examined after immersion in leachates, aiming to elucidate the degradation mechanism underlying these properties. Subsequently, thermogravimetric (TG) analysis was performed on the polymer materials immersed in various leachates. And the thermal stability and oxidation stability of novel materials were investigated using a thermogravimetric analyzer coupled with a Fourier transform infrared spectrometer (TG-FTIR). Based on the results obtained from thermal analysis, the service life of polymer materials under different pollutants was ultimately predicted utilizing the Arrhenius model. The findings indicate that the novel polymer materials exhibit commendable durability and pose little risk of causing secondary pollution.

Physicochemical Characterization and Thermodynamic Analysis of Avocado Oil Enhanced with Haematococcus pluvialis Extract

The consumption of fatty acids offers significant health benefits; however, they are prone to degradation by environmental factors. One method to preserve these fatty acids is the addition of synthetic antioxidants. This study focuses on the determination of peroxide and MDA formation rates at temperatures of 25 °C, 45 °C, and 65 °C. The oxidative stability of cold-pressed avocado oil was evaluated using pure astaxanthin, TBHQ, and H. pluvialis extract at concentrations of 100, 500, and 1000 ppm. Kinetic models and thermodynamic analysis were applied to determine the oxidation rate and compare the antioxidant effects of H. pluvialis extract with astaxanthin and TBHQ. The Arrhenius model was used to estimate activation energy (Ea), enthalpy, entropy, and free energy. Avocado oil with 500 ppm of H. pluvialis extract showed antioxidant effects comparable to TBHQ and pure astaxanthin. The activation energy of plain avocado oil was 40.47 kJ mol−1, while with H. pluvialis extract, it was 54.35 kJ mol−1. These findings suggest that H. pluvialis extract offers effective antioxidant properties and could serve as a natural alternative to synthetic antioxidants in food applications, despite the limitations of unprotected astaxanthin.

Outcomes of CEM43 in Predicting Thermal Damage Induced by Focal Laser Ablation in Controlled Ex Vivo Experiments: A Comparison to Histology and MRI.

Focal laser ablation (FLA) serves as a targeted therapy for prostate cancer (PCa). Clinical studies have demonstrated significant variations in ablation volumes with consistent fiber configurations. Consequently, a prediction model is needed for the safe application of FLA in treating PCa. This study aimed to evaluate the reproducibility of FLA-induced temperature profiles in controlled ex vivo experiments using clinical laser treatment protocols. Additionally, it sought to examine the effectiveness of the CEM43 model in predicting the zone of irreversible damage (ZID) and to compare these findings with outcomes derived from the Arrhenius model. Freshly excised postmortem human prostate and porcine liver specimens were used for controlled ex vivo ablation. Tissues were secured in a Perspex sample holder for precise placement of the laser fiber and thermocouples. FLA was conducted with a 1064-nm Nd:YAG laser at 3 W in continuous-wave mode for 10 min. Pre- and post-FLA 3D T1-weighted 7 T MRI scans were obtained to assess the treatment area. Whole-mount hematoxylin and eosin histological slides were prepared and digitized. On histology, the ZID was defined as the total of vaporized, carbonized, and coagulated tissue. A 2D thermal development map was created from temperature data, using bi-cubic interpolation. The cumulative equivalent thermal isoeffect dose at 43°C in minutes (CEM43) model was applied to predict the ZID, with 240 equivalent minutes (240-CEM43) used as the damage threshold. Additionally, the Arrhenius thermal model was used for comparison of CEM43 results. Predicted ZIDs were compared to MRI and histology. FLA treatment was performed on ex vivo human prostate samples (n = 2) and porcine liver specimens (n = 5). For human prostate tissue, FLA did not result in an identifiable ZID upon histological macroscopic examination or a lesion on MRI. Ex vivo porcine liver samples showed a clearly demarcated oval-shaped hyperintense lesion surrounding the laser fiber tip on post-FLA MRI. The MRI lesion (range 1.6-2.1 cm2) corresponded with the shape and location of the ZID on histology, but was smaller (median 1.7 vs. 3.2, p = 0.02). Histological examination of porcine liver samples revealed ZIDs ranging from 2.1 to 4.1 cm2, whereas 240-CEM43-predicted ZIDs ranged from 3.3 to 3.8 cm2. Although the median 240-CEM43-predicted ZID was not significantly larger than the histology ZID (3.8 vs. 3.2 cm2, p = 0.22), it tended to overpredict the histological results in most experiments. The median Arrhenius-predicted ZID was similar to the histologicalZID (3.2 vs. 3.2 cm2, p = 0.56), but varied in size when comparing individual experiments (range 2.5-3.2 cm2). FLA on ex vivo human prostate showed no thermal damage on histopathology or MRI. Ex vivo porcine liver FLA resulted in identifiable ZID on histology and lesions on MRI. 240-CEM43 generally overestimated the ZID and had less variability compared to histology. Results from the Arrhenius model were in better agreement with the histology findings, but still did not predict the individual FLA-induced histological thermal damage. Inter-experiment ZID variability underlines the need for developing a more comprehensive predictive dosimetry model for FLA in PCa treatment.

A comparative study of hot tensile deformation behavior of 6016 aluminum alloy under LSTM neural network and Arrhenius model

Abstract The isothermal tensile test of 6016-T6 aluminum alloy was carried out on Gleeble-3500 at the temperature range of 400 °C–550 °C and the strain rate range of 0.01–10 s−1. The results show that the thermal deformation mechanism of 6016-T6 is dynamic recovery and dynamic recrystallization. In this paper, the phenomenological Arrhenius constitutive model and the data-driven WOA-LSTM constitutive model for predicting the hot tensile deformation behavior of 6016-T6 aluminum alloy were studied in contrast. The whale optimization algorithm was used to optimize the hyperparameters of LSTM neural network to improve the prediction accuracy of flow stress. The optimization results show that the optimal hidden layer node, maximum training period, initial learning rate and mini batch size of WOA-LSTM are 46, 260, 0.0248 and 16, respectively. In addition, the influence of the number of hidden layers on the results of the network was discussed. The appropriate hidden layer of the network was determined to be 2. The result show that the prediction accuracy of WOA-LSTM constitutive model is better than the Arrhenius constitutive model. The mean absolute error and correlation coefficient are 0.9348% and 0.99952, respectively. Among them, in this study, the Arrhenius constitutive model has low precision and only has high precision within a single temperature range.

Temperature Simulation of an Ablation Needle for the Prediction of Tissue Necrosis during Liver Ablation

Background/Objectives: Microwave ablation (MWA) is the leading therapy method for treating patients with liver cancer. MWA simulation is used to further improve the therapy and to help develop new devices. Methods: A water-cooled ablation needle was reconstructed. MWA simulations of a polyacrylamide phantom were carried out and compared with a representative clinical example (tumor diameter: 8.75 mm). The Arrhenius damage model and a critical temperature approach of 60 °C were applied to assess the necrosis zones. Finally, the simulation results were compared to the corresponding MR measurements. Results: Most of the heating in the simulation took place at a distance of 5 mm along the transverse axis and 20 mm along the longitudinal axis above the needle tip. The calculated Dice scores for the Arrhenius model were 0.77/0.53 for the phantom/clinical case. For the critical temperature approach, Dice scores of 0.60/0.66 for the phantom/clinical case were achieved. Conclusions: The comparison between simulated and measured temperature increases showed an excellent agreement. However, differences in the predicted necrosis volume might be caused by omitting consideration of the heat sink effect, especially in the clinical case. Nevertheless, this workflow enables short MWA simulation times (approximately 3 min) and demonstrates a step towards possible integration into daily clinical use.

Billet Size Optimization for Hot Forging of AISI 1045 Medium Carbon Steel Using Zener-Hollomon and Cingara-McQueen Model

This study investigates the effects of initial billet size variations on material flow behavior in hot forging processes, aiming to optimize the forging process using validated predictive models. Material and high-temperature compressive tests inform mathematical models, while simulations are conducted via the finite element method (FEM). Results align with the Zener-Hollomon and Cingara-McQueen approaches. The Arrhenius model predicts AISI 1045 steel flow stress with an R2 of 0.968 and an average absolute relative error (AARE) of 7.079%. The Cingara-McQueen equation achieves an R2 of 0.997 and an AARE of 2.960%. Reducing billets size from 260 mm to 230 mm decreases the material usage by up to 11.5%, while maintaining workpiece integrity. Experimental and simulated loads exhibit an AARE of about 2.69%, thereby indicating potential cost and efficiency improvements in hot forging processes.

Modelling the time-dependent mechanical properties of thermoplastic and thermosetting polymers with Gumbel distribution functions

In this paper, we propose a simple modelling method that accurately describes the time-dependent viscoelastic behaviour of thermoplastic and thermosetting solid polymers. We performed short-term creep and stress relaxation tests on representative samples of three major classes of polymers: an amorphous, a semi-crystalline thermoplastic and a thermosetting polymer. Then, to investigate the relationship between the model parameters and the material composition, we also tested thermoplastic matrix composites with different plasticiser contents. From the short-term tests, master curves were constructed with the use of the time–temperature superposition principle. Then, the temperature dependence of the obtained shift factors was described using the Arrhenius model. The resulting creep compliance and relaxation modulus master curves were normalised and modelled with a two-parameter cumulative Gumbel distribution function (CDF) and its complementary distribution function (CCDF). For the creep and stress relaxation master curves, the median error of modelling was less than 16 % and 16.5 % in all cases, respectively. Furthermore, it was less than 2 % for the thermosetting polymer, making this model an excellent tool for describing the creep and stress relaxation behaviour of thermosetting systems. In the case of the plasticised composites, we found a strong relationship between the material composition and the location parameter of the Gumbel model. Based on this, we developed a method that can be used to estimate the evolution of the creep compliance curve for any arbitrary OLA content (between 0 wt% and 16 wt%) at any desired temperature (between 22 °C and 70 °C).

Influence of core–shell intermetallic on dynamic recrystallization and processing maps of novel Al-Cu-Ni composite through Arrhenius and artificial neural network (ANN) models

Influence of core–shell intermetallic on dynamic recrystallization and processing maps of novel Al-Cu-Ni composite through Arrhenius and artificial neural network (ANN) models

The hot deformation behavior and processing map analysis of a high-nitrogen austenitic stainless steel

Understanding the hot deformation behavior of steel and establishing corresponding hot processing maps are crucial methods for determining appropriate hot processing parameters. In this article, the hot deformation behavior of a high-nitrogen austenitic stainless steel was investigated in the temperature range of 900–1150 °C and the strain rate range of 0.01–10 s−1 on a Gleeble-3500 thermo-mechanical simulator. The results show that the flow stress of experimental steel increases with decreasing deformation temperature and increasing strain rate. Based on the Arrhenius model, a constitutive equation was developed for the experimental steel, with a hot deformation activation energy of 603.347 kJ/mol. The hot processing maps were created employing the dynamic material model to determine the optimum hot processing conditions for the experimental steel at different strain levels.

Antioxidant depletion from a 2 mm high-density polyethylene geomembrane used in brine containment

The depletion of antioxidants from a 2 mm high-density polyethylene geomembrane immersed in brine at seven temperatures (95, 85, 75, 65, 55, 40, and 25°C) for 28 months is reported. An Arrhenius model is used to predict the performance of the geomembrane at low site-specific temperatures. The antioxidant depletion times are reported for temperatures between 20 and 95°C. The solubility of the antioxidant and stabilizer packages, the oxidation by-products, and their susceptibility to hydrolysis are discussed. After 28 months of incubation, no oxidative degradation was observed for samples in the full brine solution even at 95°C. Morphological changes reduced the stress-crack resistance to a stable representative value without a reduction in the tensile elongation at break. The effect of the brine solution concentration on the depletion of antioxidants and stabilizers was investigated at 85°C. It was found that the depletion rate decreases with the increasing brine concentration.

Negative and persistent photoconductivity in Bi-doped Pb0.5Sn0.5Te epitaxial films

This work presents the investigation of the photoconductivity effect in undoped and doped Pb0.5Sn0.5Te epitaxial films, with bismuth (Bi) atoms, at temperatures of 80 and 300 K. The results indicate that the samples show negative photoconductivity effect (NPC) and persistent photoconductivity (PPC). A detailed study was performed on Pb0.5Sn0.5Te sample doped with 0.15 % Bi, which presented higher photoconductivity amplitude than the other samples, by performing Hall effect and photoconductivity measurements in the temperature range of 80–300 K under dark and illuminated conditions. Using Arrhenius model, trap activation energy was extracted and compared with energies found in literature. From the Hall measurement we found that the NPC effect observed is due to a decrease in the mobility when the sample is illuminated while the carrier concentrations are nearly unaltered. It was also found that Pb0.5Sn0.5Te:Bi presented photoconductivity response for a wide range of wavelengths, indicating that it is potentially interesting for application in optic sensor devices.

Prediction flow behavior of Mg-12Gd-3Y-0.6Zr alloy during hot deformation based on Arrhenius and BP-ANN models: a comparative study

Prediction flow behavior of Mg-12Gd-3Y-0.6Zr alloy during hot deformation based on Arrhenius and BP-ANN models: a comparative study

The flow stress prediction of TiB2/2024 aluminum matrix composites based on modified Arrhenius model and gene expression programming model

The high temperature flow data of TiB2/2024 aluminum matrix composites (referred to as TiB2/2024 alloy) was investigated using a Gleeble-3500 thermal simulation testing machine. The experiments were conducted at various deformation temperatures (573 K, 623 K, 673 K, and 723 K), strain rates (0.01s−1, 0.1s−1, 1s−1, and 10s−1), and a maximum deformation of 60%. By comprehensively accounting for the deformation conditions, the relationships between the material parameters α, n, S, f of TiB2/2024 alloy and the deformation temperature, strain, and strain rate were determined, leading to the modification of the Arrhenius model. A constitutive model for TiB2/2024 alloy was constructed using the Gene expression programming (GEP) approach. The flow stress of TiB2/2024 alloy during the compression process was predicted using both the modified Arrhenius model and the GEP model. The statistical analysis was performed to evaluate the prediction accuracy of the two models, and the extended stress-strain data was implemented in finite element simulations of the hot compression process. The results indicate that the flow stress of TiB2/2024 alloy is significantly affected by the strain rate and temperature during the deformation process. The flow stress decreases with increasing temperature and increases with increasing strain rate. Both the modified Arrhenius model and the GEP model can effectively predict the alloy's flow stress. However, the modified Arrhenius model exhibits greater prediction accuracy than the GEP model.

A-priori framework of viscosity and ionic conductivity estimation of ionogel

A-priori framework has been developed to estimate the viscosity and ionic conductivity of ionogel. Six imidazolium-class of ionic liquids (ILs) form ionogels with tetraethyl orthosilicate (TEOS) matrix. Group contribution parameters of TEOS are estimated with the fitting of the density dataset in the predictive Soave−Redlich−Kwong equation of state with the NSM1 alpha function model. Later the parameters are used to estimate the critical property of ILs and TEOS. These facilitate the formulation of the predictive framework of viscosity estimation through the geometric similitude concept with the Valderrama-Patel-Teja cubic equation of state. Later the viscosity of ionogels is estimated through a mixture form of geometric similitude framework as well as the Arrhenius model. Additionally, the estimated viscosities from both frameworks are used to estimate the ionic conductivities of ionogels. The compositional and temperature variance of ionic conductivity reveals the superior ionic conductivity of tetrafluoroborate-based ionogels than the bis(trifluoromethanesulfonyl) imide-based counterparts. Both models estimate the decrease in viscosity as well as incremental trends in ionic conductivity with temperature. However, the concentration of IL rather plays a different trend in the estimation model as well as the class of IL. Such a priori framework shall lead to the design of the ionogels focusing on the physicochemical properties.

Thin layer drying and effect of temperature on the drying characteristics of bushbuck (Gongronema latifolium) leaves

Determination of the drying properties of agricultural products holds several benefits, such as nutrient preservation, processing and storage. The effect of air temperature on the drying properties and kinetics of bushbuck leaves at 30, 40, 50, 60 and 70 °C temperature was investigated. The drying time declined as the temperature rose, indicating a falling rate drying phenomenon. Drying models such as Henderson and Pabis, Newton, Modified Page, Page, Midilli and others, Logarithmic, and Two-term were applied and fitted to the experimental data's moisture ratio. The non-linear regression fitting method results showed that the Midilli and other models gave the best-fit description for the drying process. The values obtained for the coefficient of determination (R2) were observed to have varied from 0.9948 to 0.9995 for the various drying models evaluated. In contrast, the sum of square error (SSE) and root mean square (RMSE) estimate was observed to vary from 0.0056 to 0.0007 and 0.0310 to 0.0163, respectively. On the estimate for the effective moisture diffusivity (Deff), it was observed that it depends on temperature and extends from 1.33×10−9 to 4.83×10−9 m2/s. The value of the activation energy was 26.05 kJ/mol. From this study, it can be deduced that the Arrhenius model could predict the temperature effect on the drying process of bushbuck leaves.

Hot deformation behavior of 30MnB5V steel: Phenomenological constitutive model, ensemble learning algorithm, hot processing map and microstructure evolution

The hot deformation behavior of 30MnB5V steel was experimentally investigated and theoretically analyzed using phenomenological constitutive models and an ensemble learning algorithm. Hot compression experiments were conducted with an MMS-200 thermo-mechanical simulation machine on the 30MnB5V steel at strain rates of 0.01–10 s−1 and temperatures of 950–1150 °C. The characteristics of the true stress-strain curves under different conditions and the corresponding microstructural evolutions were examined in detail. The results indicate that raising the temperature or lowering the strain rate promotes dynamic recrystallization. As temperature decreases or strain rate increases, the degree of recrystallization softening declines, and stress-strain curves transition from recrystallization to sustained work hardening or dynamic recovery types. Subsequently, the strain-compensated Arrhenius model, modified Johnson-Cook (J-C) model, and Bayesian-optimized LightGBM (BO-LightGBM) model were constructed sequentially to predict the flow stress of the tested steel. The accuracy of the three models was evaluated using the coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). The results reveal that the accuracy of the BO-LightGBM model is significantly higher than that of the Arrhenius model and the modified J-C model. Finally, three-dimensional power dissipation maps and hot processing maps were established under various strain conditions. The results suggest that the tested steel demonstrates good workability at deformation temperatures of 1075–1125 °C and strain rates of 0.03–0.22 s−1.