Application of FEM and Abductive Network to Determine Forging Force and Billet Dimensions of Near Net-Shape Helical Bevel Gear Forging

In this paper, the use of the finite element method in conjunction with abductive network is presented to predict the maximum forging force and the volume of billet during near net-shape helical bevel gear forging. The maximum forging load and volume of billet are influenced by the process parameters such as modules, number of teeth, and die temperature. A finite element method is used to investigate the forging of helical bevel gear. In order to verify the prediction of FEM simulation for forging load, the experimental data are compared with the results of current simulation. A finite element analysis is also utilized to investigate the process parameters on forging load and volume of billet. Additionally, the abductive network was applied to synthesize the data sets obtained from the numerical simulation. The prediction models are then established for the maximum forging load and volume of billet of near net-shape helical bevel gear forging under a suitable range of process parameters. After the predictions of the maximum forging force and the volume of billet, the optimum of the power of forging machine and the dimensions of billet are determined.

Predicting wastewater temperatures in sewer pipes using abductive network models

A predictive modelling technique was employed to estimate wastewater temperatures in sewer pipes. The simplicity of abductive predictive models attracts large numbers of users due to their minimal computation time and limited number of measurable input parameters. Data measured from five sewer pipes over a period of 12 months provide 33,900 training entries and 39,000 evaluation entries to support the models' development. Two simple predictive models for urban upstream combined sewers and large downstream collector sewers were developed. They delivered good correlation between measured and predicted wastewater temperatures proven by their R2 values of up to 0.98 and root mean square error (RMSE) of the temperature change along the sewer pipe ranging from 0.15 °C to 0.33 °C. Analysis of a number of potential input parameters indicated that upstream wastewater temperature and downstream in-sewer air temperature were the only input parameters that are needed in the developed models to deliver this level of accuracy.

Study of Phase Distribution of a Liquid-Solid Circulating Fluidized Bed Reactor Using Abductive Network Modeling Approach

This communication deals with the Abductive Network modeling approach to investigate the phase holdup distributions of a liquid–solid circulating fluidized bed (LSCFB) system. The Abductive Network model is developed/trained using experimental data collected from a pilot scale LSCFB reactor involving 500-μm size glass beads and water as solid and liquid phases, respectively. The trained Abductive Network model successfully predicted experimental phase holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The statistical performance indicators including the mean absolute error (~4.67%) and the correlation coefficient (0.992) also show favorable indications of the suitability of Abductive Network modeling approach in predicting the solids holdup of the LSCFB system.

Predictions of Maximum Forging Load and Effective Stress for Strain-Hardening Material of near Net-Shape Helical Gear Forging

In this paper, the use of the finite element method in conjunction with abductive network is presented to predict the maximum forging force and effective stress for strain-hardening material during near net-shape helical forging. The maximum forging load and effective stress are influenced by the material properties such as yielding stress, strength coefficient and strain hardening exponent. A finite element method is used to investigate the clamping-type forging of helical gear. In order to verify the prediction of FEM simulation for forging load, the experimental data are compared with the results of current simulation. A finite element analysis is also utilized to investigate the material properties on forging load and maximum effective stress. Additionally, the abductive network was applied to synthesize the data sets obtained from the numerical simulation. The prediction models are then established for the maximum forging load and maximum effective stress of near net-shape helical gear forging under a suitable range of material parameters.

Predictions of Scratch Characters for Engineering Material by Using FEM and Abductive Network

Scratch test is mainly used to study mechanical properties of materials near their surface. This study applies the finite element method (FEM) in conjunction with an abductive network to predict the scratch character such as rear contact angle, shape ratio and hardness for strain hardening bulk material of scratch process. To verify the prediction of FEM simulation of scratch process, the experimental data are compared with the results of current simulation. A finite element analysis is also utilized to investigate the material properties on side view contour, rear contact angle, hardness and shape ratio. Additionally, the abductive network was applied to synthesize the data sets obtained from the numerical simulation. The prediction models are then established for the rear contact angle, hardness and shape ratio of nanoscratch process under a suitable range of material parameters.

Application of FEM Simulation and Abductive Network to Predict the Springback of U-Shaped Bending Process with Counter Force

This study applies the finite element method (FEM) in con-junction with an abductive network to predict springback’s angle during the U-shaped bending process with counter force. To verify the prediction of FEM simulation for springback, the experimental data are compared with the results of current simulation. Bending force, effective stress distribution and springback are investigated for different process parameters, such as profile radius of die, blank holder force and counter force of U-shaped bending process, by finite element analysis. The abductive network is then utilized to synthesize the data sets obtained from numerical simulations. Finally, prediction model is established for predicting springback’s angle under a suitable range of process parameters.