Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems

Recently, studies applying deep learning technology to recognize the machining feature of three-dimensional (3D) computer-aided design (CAD) models are increasing. Since the direct utilization of boundary representation (B-rep) models as input data for neural networks in terms of data structure is difficult, B-rep models are generally converted into a voxel, mesh, or point cloud model and used as inputs for neural networks for the application of 3D models to deep learning. However, the model’s resolution decreases during the format conversion of 3D models, causing the loss of some features or difficulties in identifying areas of the converted model corresponding to a specific face of the B-rep model. To solve these problems, this study proposes a method enabling tight integration of a 3D CAD system with a deep neural network using feature descriptors as inputs to neural networks for recognizing machining features. Feature descriptor denotes an explicit representation of the main property items of a face. We constructed 2236 data to train and evaluate the deep neural network. Of these, 1430 were used for training the deep neural network, and 358 were used for validation. And 448 were used to evaluate the performance of the trained deep neural network. In addition, we conducted an experiment to recognize a total of 17 types (16 types of machining features and a non-feature) from the B-rep model, and the types for all 75 test cases were successfully recognized.

Development of the PC-based Integrated Interface System of STEP file for CNC Machining Application: Circular Features

STEP is a general data format that observes the international standard ISO 10303-21. STEP means Standard for the Exchange of Product model data. It consists of the 3D geometry of a computer-aided design (CAD) model in the configuration of boundary representation (B-rep). By extracting, refining and decoding the geometric data correctly, the data can be utilized for writing G-code for Computer Numerical Control (CNC) machining application. Usually G-codes can either be manually generated by skilled machinists or automatically generated by computer-aided manufacturing (CAM) software. However, manually generated G-code is inefficient and susceptible to error. Meanwhile automated generation G-code requires significant setup cost. This paper describes the design and development of an integrated interface system, an instrument aimed to be used to analyze STEP files and generate machining tool path based on ISO 6983 format. This developed interface reduces the need for high setup cost as well as eliminates human limitations. The interface at present is able of detecting circular machining features on the workpiece. Circular machining features are created by 3D modelling software and retained as STEP file. The STEP file which contains geometrical data is then uploaded to the interface system as an input file which is structurally analyzed and processed. Finally, the ideal machining tool path in the G Code format is proposed and generated. By bypassing the CAM software and its proprietary post processor, the outcome of this research is important to enhance compatibility between different CNC machine systems

CAD Integration of Mechanical Numerical Control Board Parts Based on Machining Features

The development and application of computer-aided design (CAD) technology has led to rapid improvements in product design automation, crafting process automation and numerical control programming automation. Machining feature refers to basic configuration units that constitute part shapes and the collection of non-geometric information with engineering semantics attached to it. The integration of mechanical numerical control parts is the integration of part design features and machining features, and each feature corresponds to a set of processing methods. Based on the summaries and analyses of previous research works, this paper expounded the current status and significance of mechanical numerical control board part integration, elaborated the development background, current status and future challenges of machining features and CAD technology, introduced a data transfer method of CAD integration and machining features-based part integration system, analyzed the design and machining features of CAD integration of board parts, constructed the graphics processing model and information reorganization model for CAD integration of board parts; conducted the feature description and modeling analysis of CAD integration of plate parts; discussed the crafting information similarity of mechanical numerical control plate part integration; explored the feature information and expression of feature library for plate parts integration.

Novel Integration of CAPP in a G-Code Generation Module Using Macro Programming for CNC Application

In the modern manufacturing industry, the role of computer-aided process planning (CAPP) is becoming increasingly crucial. Through the application of new technologies, experience, and intelligence, CAPP is contributing to the automation of manufacturing processes. In this article, the integration of a proposed CAPP system that is named as BKCAPP and G-code generation module provides a completed CAD–CAPP–CNC system that does not involve any manual processing in the CAM modules. The BKCAPP system is capable of automatically performing machining feature and operation recognition processes from design features in three-dimensional (3D) solid models, incorporating technical requirements such as the surface roughness, geometric dimensions, and tolerance in order to provide process planning for machining processes, including information on the machine tools, cutting tools, machining conditions, and operation sequences. G-code programs based on macro programming are automatically generated by the G-code generation module on the basis of the basic information for the machining features, such as the contour shape, basic dimensions, and cutting information obtained from BKCAPP. The G-code generation module can be applied to standard machining features, such as faces, pockets, bosses, slots, holes, and contours. This novel integration approach produces a practical CAPP method enabling end users to generate operation consequences and G-code files and to customize specific cutting tools and machine tool data. In this paper, a machining part consisting of basic machining features was used in order to describe the method and verify its implementation.

Predicting Build Orientation of Additively Manufactured Parts With Mechanical Machining Features Using Deep Learning

Additive Manufacturing (AM) is a revolutionary development that is being viewed as a core technology for fabricating current and future engineered products. While AM has many advantages over subtractive manufacturing processes, one of the primary limitations of AM is to swiftly evaluate precise part build orientations. Current algorithms are either computationally expensive or provide multiple alternative orientations, requiring additional decision tradeoffs. To hasten the process of finding accurate part build orientation, a data-driven predictive model is introduced by mapping standard machining features to build orientation angles. A combinatory learning algorithm of classification and regression is utilized for the prediction of build orientation. The framework uses 54,000 voxelized standard tessellated language (STL) files as input to train the classification algorithm for eighteen standard machining features using a nine-layer 3D Convolutional Neural Network (CNN). Additionally, a multi-machining feature dataset of 1000 voxelized STL files are evaluated in parallel by performing quaternion rotations to obtain build orientation angles based on minimization of support structure volume. A regression model is then developed to establish a relationship between the machining features and orientation angles to predict optimal build orientation for new parts.

Mining and Reuse on Design Knowledge of Non-standard Special Tool Based on Deep Learning

Aiming at the problems of design difficulty, low efficiency and unstable quality of non-standard special tools, facing the strong correlation between part machining features and tools, this article takes the two-dimensional engineering drawings of tools and parts as research objects, proposes the research on mining and reuse on design knowledge of non-standard special tool based on deep learning. Firstly, a dual-channel deep belief network is established to complete the feature modeling of machining features and tool features; secondly, the deep belief network is used to realize the association relationship mining between the machining features and tool features; thirdly, both the key local features of the tool and the overall similar design case of the tool are reused through association rule reasoning; finally, the non-standard special turning tool is used as an example to verify the effectiveness of the proposed method.