Efficient Method for Product Cost Estimation using Artificial Intelligence Techniques

Automatic prediction of target cost for Computer Aided Design (CAD) models in an efficient approach is a huge challenge faced by many manufacturing corporations. The time, cost and effort can be saved by using automatic cost estimation methods for 3D CAD models. The target cost of each CAD model is the addition of material and production cost. Material cost comprises of material source and material preparation costs. The production cost includes manufacturing, complexity of manufacturing and secondary operations costs. Considering all the above cost parameters, the target cost of a product is estimated automatically using Artificial Intelligence (AI) techniques. This paper proposes a Random Forest Regression (RFR) model to consolidate the target amount of a model by utilizing material data and geometric features. Further, to improve the efficiency of the model, Grid Search (GS) algorithm is also employed. The proposed model is validated and tested using Mean Square Error function in Python for the CAD dataset. The results show that this proposed model achieves greater average accuracy of 95% in predicting the target cost of a CAD models with minimum error.