Machine learning based nominal root stress calculation model for gears with a progressive curved path of contact

Urbas, Uroš; Zorko, Damijan; Vukašinović, Nikola

doi:10.1016/j.mechmachtheory.2021.104430

Cited by 25 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By applying the AIS algorithm, they optimized the volume of the planetary gear train. Research [27] proposed a machine learning method in the design of non-involuted gears. With this method, predicted parameter Y Z and nominal gear root stress were proposed.…”

Section: Mass Reduction Impact On Improving Energy Efficiencymentioning

confidence: 99%

Influence of Open Differential Design on the Mass Reduction Function

Karakašić,

Konjatić,

Glavaš

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The transmission of power and motion in road vehicles with internal combustion engines is achieved by different design variants of differential transmissions. The open differential transmission (ODT) is installed to a greater extent in passenger cars with rear-wheel drive due to its simpler design. Due to its robustness, it is possible to reduce its mass. Reducing the mass of the ODT, as well as reducing the mass of the other design elements of the vehicle, contributes to reducing the overall mass of the vehicle and improves the energy efficiency of the vehicle. The paper develops and proposes an algorithm that combines the design of the ODT according to ISO 23509:2006, the numerical calculation of the design elements (ring gear and drive shaft with pinion) using the finite element method (FEM) and the numerical global–local model, the topological optimization method (TOM) and the results of the FEM analysis in determining the design parameters. In addition, the proposed algorithm uses the application of the response surface method (RSM) in the construction of a mathematical model. With the proposed mathematical model, the mathematical objective function of the ODT overall mass reduction describes the influence of the previously selected design parameters on the overall mass reduction of the ODT. The mathematical model is also used to analyze the partial influence of the design parameters on the objective functions of the partial mass reduction of the ring gear and pinion drive shaft. Using the R2 and root mean square error (RMSE), an accuracy check of the proposed mathematical model was performed. According to the proposed algorithm and mathematical model, the two mentioned design elements of the ODT were optimized. After optimization, the overall mass of the ODM was reduced by 16.5%.

show abstract

Section: Mass Reduction Impact On Improving Energy Efficiencymentioning

confidence: 99%

Influence of Open Differential Design on the Mass Reduction Function

Karakašić,

Konjatić,

Glavaš

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Besides, in the gear transmission field, some attempts using artificial intelligence (AI) have been made. For instance, Urbas et al 19 proposed a machine learning (ML) model to calculate the nominal stress in tooth root, which could be used as an alternative to FEM simulation. However, their research was based on simulation data and lacked further validation of experimental data.…”

Section: Introductionmentioning

confidence: 99%

A novel prediction approach of polymer gear contact fatigue based on a WGAN‐XGBoost model

Jia

Wei

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Polymer gears have long been used on power transmissions with the fundamental durability data, including fatigue S‐N curves, yielding important data informing reliable and compact designs. This paper proposed a prediction method for polyformaldehyde (POM) gear fatigue life based on the innovative WGAN‐XGBoost algorithm. The findings generated herein revealed that the proposed method performs well in terms of prediction accuracy. The predicted fatigue lives, analyzed under different loading conditions, were within 1.5 times dispersion band compared with experimental results. Furthermore, based upon the enhanced fatigue dataset, a thermo‐mechanical coupled prediction formula for POM gear contact fatigue life was proposed. These findings offered a new approach for high‐power density design of polymer gears.

show abstract

“…Based on the recognized polymer gear failure modes and available design methods, a comprehensive polymer gears design optimization approach was introduced in [12]. Attempts have been undertaken to integrate machine learning algorithms into the gear design [13,14], demonstrating their effectiveness in assessing unconventional gear designs.…”

Section: Introductionmentioning

confidence: 99%

Effect of Process Parameters on the Crystallinity and Geometric Quality of Injection Molded Polymer Gears and the Resulting Stress State during Gear Operation

Zorko

2023

Polymers

Self Cite

View full text Add to dashboard Cite

The quality of gear manufacturing significantly influences the way load is distributed in meshing gears. Despite this being well-known from practical experience, gear quality effects were never systematically characterized for polymer gears in a manner able to account for them in a standard calculation process. The present study employs a novel combination of numerical and experimental methods, leading to a successful determination of these effects. The findings of the study enhance existing gear design models and contribute to a more optimized polymer gear design. The study first explores the effect of injection-molding parameters on the gear quality and secondly the effect of resulting gear quality on the stress conditions in a polymer gear pair. For the gear sample production, different combinations of process parameters were investigated, and a classic injection-molding and the Variotherm process were utilized. Gear quality and crystallinity measurements were conducted for all produced gears, providing insights into the correlation between them. Based on the evaluated gear quality of produced samples, the effect of gear quality was further studied by numerical means within a meaningful range of quality grades and transmitted loads. Special attention was dedicated to lead and pitch deviations, which were found to exert a noteworthy influence on the stress state (both root and flank) of the gear. The effect of lead deviation was most pronounced when improving the gear quality from grade Q12 to grade Q10 (30% to 80% stress reduction, depending on the load). However, enhancing the quality grade from Q10 to Q8 yielded less improvement (5% to 20% stress reduction, depending on the load). A similar pattern was evident also for pitch deviations.

show abstract

Machine learning based nominal root stress calculation model for gears with a progressive curved path of contact

Cited by 25 publications

References 45 publications

Influence of Open Differential Design on the Mass Reduction Function

Influence of Open Differential Design on the Mass Reduction Function

A novel prediction approach of polymer gear contact fatigue based on a WGAN‐XGBoost model

Effect of Process Parameters on the Crystallinity and Geometric Quality of Injection Molded Polymer Gears and the Resulting Stress State during Gear Operation

Contact Info

Product

Resources

About