Multi-Objective Optimization for FDM Process Parameters with Evolutionary Algorithms

AbstractThe qualities of injection-molded parts are affected by process parameters. Warpage and volume shrinkage are two typical defects. Moreover, insufficient or excessively large clamping force also affects the quality of parts and the cost of the process. An experiment based on the orthogonal design was conducted to minimize the above defects. Moldflow software was used to simulate the injection process of each experiment. The entropy weight was used to determine the weight of each index, the comprehensive evaluation value was calculated, and multi-objective optimization was transformed into single-objective optimization. A regression model was established by the random forest (RF) algorithm. To further illustrate the reliability and accuracy of the model, back-propagation neural network and kriging models were taken as comparative algorithms. The results showed that the error of RF was the smallest and its performance was the best. Finally, genetic algorithm was used to search for the minimum of the regression model established by RF. The optimal parameters were found to improve the quality of plastic parts and reduce the energy consumption. The plastic parts manufactured by the optimal process parameters showed good quality and met the requirements of production.

Download Full-text

Reference point based multi-objective optimization using evolutionary algorithms

Proceedings of the 8th annual conference on Genetic and evolutionary computation - GECCO '06 ◽

10.1145/1143997.1144112 ◽

2006 ◽

Cited By ~ 142

Author(s):

Kalyanmoy Deb ◽

J. Sundar

Keyword(s):

Evolutionary Algorithms ◽

Reference Point ◽

Multi Objective Optimization ◽

Multi Objective

Download Full-text

Mechanical properties optimization of the steering column based on multi-objective optimization design

Advances in Mechanical Engineering ◽

10.1177/1687814016682941 ◽

2016 ◽

Vol 8 (12) ◽

pp. 168781401668294 ◽

Cited By ~ 1

Author(s):

Si Chen ◽

Zhaohui Wang ◽

Mi Lv

Keyword(s):

Mechanical Properties ◽

Process Parameters ◽

Optimization Design ◽

Strain Difference ◽

Optimization Method ◽

Equivalent Strain ◽

Multi Objective Optimization ◽

Optimal Process ◽

Multi Objective ◽

Initial Results

The mechanical properties of the steering column have a significant influence on the comfort and stability of a vehicle. In order for the mechanical properties to be improved, the rotary swaging process of the steering column is studied in this article. The process parameters, including axial feed rate, hammerhead speed, and hammerhead radial reduction, are systematically analyzed and optimized based on a multi-objective optimization design. The response surface methodology and the genetic algorithm are employed for optimal process parameters to be obtained. The maximum damage value, the maximum forming load, and the equivalent strain difference obtained with the optimal process parameters are, respectively, decreased by 30.09%, 7.44%, and 57.29% compared to the initial results. The comparative results present that the quality of the steering column is improved. The torque experiments and fatigue experiments are conducted with the optimal steering column. The maximum torque is measured to be 260 NM, and the service life is measured to be 2 weeks (40 NM, 2500 times), which are, respectively, increased by 8.3% and 8.69% compared to the initial results. The above results display that the mechanical properties of the steering column are optimized to verify the feasibility of the multi-objective optimization method.

Download Full-text