Computer Assisted Process Planning for Prismatic Components using Artificial Intelligence and Internet of Things Based Monitoring of CNC Milling Machine

Abstract

Computer-aided process planning (CAPP) systems help human planners in the creation of better process strategies to address the challenges of manual process planning. Manual process planning is incredibly challenging since it requires process planning knowledge for documentation, tool selection, machine selection, cutting parameters selection, and decision making. Human process planners must be able to use manuals, configure tools and fixtures, and plan for raw materials and process selection. Process planners should understand drawings and determine the time and cost of production. Computer-aided process planning (CAPP) bridges the gap between computer aided design and computer aided manufacturing. New artificial intelligence techniques play a significant role in CAPP. newlineFeature-based modeling is the current trend in recognizing part features. SolidWorks software is used for CAD modeling and storing part manufacturing details in STEP 242 file format. This file type stores details such as material, size, stock, dimensional tolerance, and surface finish. The file is interfaced with neural networks to figure out the required machining operations and cutting tools. The application of artificial neural network techniques (ANN) in CAPP is dealt with in this study because of their learning ability and massive potential toward dynamic planning. Artificial neural networks are used for machining operation selection and cutting tool selection. In this work, various prismatic features such as a hole, slot, step, rounded, pocket, boss, chamfer, fillet, and face features are considered. The details like material, size, stock, dimensional tolerance, and surface finish are properly normalised and given as input to neural networks and outputs will be the required machining operations. In cutting tool selection, the inputs of the neural networks include feature type, material type, the shape of the cutter, tool diameter, number of flutes, tool length, tolerance, surface finish, and dimension details. The output of the neural ..