Computer Aided Process Planning System Research Articles

BrepMFR: Enhancing machining feature recognition in B-rep models through deep learning and domain adaptation

Feature Recognition (FR) plays a crucial role in modern digital manufacturing, serving as a key technology for integrating Computer-Aided Design (CAD), Computer-Aided Process Planning (CAPP) and Computer-Aided Manufacturing (CAM) systems. The emergence of deep learning methods in recent years offers a new approach to address challenges in recognizing highly intersecting features with complex geometric shapes. However, due to the high cost of labeling real CAD models, neural networks are usually trained on computer-synthesized datasets, resulting in noticeable performance degradation when applied to real-world CAD models. Therefore, we propose a novel deep learning network, BrepMFR, designed for Machining Feature Recognition (MFR) from Boundary Representation (B-rep) models. We transform the original B-rep model into a graph representation as network-friendly input, incorporating local geometric shape and global topological relationships. Leveraging a graph neural network based on Transformer architecture and graph attention mechanism, we extract the feature representation of high-level semantic information to achieve machining feature recognition. Additionally, employing a two-step training strategy under a transfer learning framework, we enhance BrepMFR's generalization ability by adapting synthetic training data to real CAD data. Furthermore, we establish a large-scale synthetic CAD model dataset inclusive of 24 typical machining features, showcasing diversity in geometry that closely mirrors real-world mechanical engineering scenarios. Extensive experiments across various datasets demonstrate that BrepMFR achieves state-of-the-art machining feature recognition accuracy and performs effectively on CAD models of real-world mechanical parts.

Computer Aided Process Planning for Rough Machining Based on Machine Learning with Certainty Evaluation of Inferred Results

Process planning is well known as the key toward achieving highly efficient machining. However, it is difficult to standardize machining skills for process planning, which depend heavily on skilled operators. Hence, in a previous study, a computer aided process planning (CAPP) system using machine learning is developed to determine the operation parameters for finish machining of dies and molds. On the other hand, in rough machining, it is assumed that some machining operations are conducted sequentially using a respective tool according to the workpiece shape, which induces a much higher complexity in process planning. Therefore, in this study, machine learning is adopted to determine operation parameters for rough machining. The developed CAPP system converts the removal volume into a voxel model and infers a machining operation for each voxel. The inferred machining operation is visualized using different colors and identified corresponding to the voxel. Finally, the removal volume is classified using three different machining operations. However, machine learning is said to have a critical problem in that it is difficult to understand the reasons for the inferred results. Hence, it is necessary for the CAPP system to demonstrate the certainty level of the determined operation parameters. Thus, this study proposes a method for calculating the degree of certainty. If an artificial neural network is trained sufficiently, similar inferred results would always be obtained. Consequently, by using the Monte Carlo dropout to delete weights at random, the certainty level is defined as the variance of the inferred results. To verify the usefulness of the CAPP system, a case study is conducted by assuming rough machining of dies and molds. The results confirm that the machining operations are inferred with high accuracy, and the proposed method is effective for evaluating the certainty of the inferred results.

An exhaustive review on intelligent computer-aided process planning in context with various optimisation techniques (OPTE-2021-1994)

Computer-aided process planning (CAPP) is a major technology that aims to integrate computer-aided design (CAD) and computer-aided manufacturing (CAM). Nowadays most of the industries are keen to produce superior quality products with significant reduction in manufacturing time and production cost to meet the customer requirements. CAPP optimisation uses various techniques to serve its purpose and deliver the market ready product. Considerable research has been carried-out on automatic CAPP approaches by various researchers. In this paper an attempt has been made to present the contemporary review on CAPP system in context to the genetic algorithms (GAs), feature-based system (FBS), knowledge-based system (KBS), artificial neural networks (ANN) and STEP-complaint (STEP-C) technologies in the past two decades. The present review focuses on critical analysis and graphically represents the research trends of CAPP system over the years. The structure of the current work contains CAPP introduction, classification, optimisation approaches and conclusions along with recommendations to adopt CAPP system. The paper discusses the types of CAPP systems (generative and variant), computer-aided process planning methods/techniques and past two decades overview on CAPP optimisation techniques.

Machining feature recognition based on a novel multi-task deep learning network

• Propose a novel learning-based machining feature recognition method that can effectively determine the faces that constitute machining features. • Construct a novel multi-task deep learning network based on point cloud data that can realize machining feature segmentation, machining feature identification, and bottom face identification simultaneously. • Propose a novel loss function that can be applied to the tasks of multi-label classification in deep learning. • Promote the application of deep learning in the manufacturing industry. Machining feature recognition is an essential task to realize the integration of computer-aided design (CAD), process planning (CAPP), and manufacturing (CAM) systems. In general, traditional rule-based machining feature recognition approaches are inflexible and computationally expensive. Moreover, it's not easy to design rules for intersecting machining features. To this end, various learning-based approaches were proposed in recent years. However, some of the existing learning-based approaches are complicated, time-consuming, and hard to deal with intersecting machining features, while some only approximately locate the position of the machining features rather than accurately segmenting them from the parts, which is not conducive to subsequent process planning. To address the above issues, a novel multi-task network named Associatively Segmenting and Identifying Network (ASIN) based on point cloud data is proposed for machining feature recognition. The proposed network performs three tasks: clusters the part faces with high similarities into machining features whose type are unidentified, predicts the semantic class (e.g. hole, pocket) for each face to identify the type of each machining feature, and identifies the bottom faces of the machining features. Through the three tasks, ASIN can realize machining feature segmentation, machining feature identification, and bottom face identification simultaneously. The final machining feature recognition results are obtained by combining the results of the above three tasks. After being trained with a large labeled point cloud dataset of 3D CAD models and a novel loss function, ASIN can be used to recognize machining features. Experimental results demonstrate that the proposed approach can effectively segment the machining features by determining the faces that compose them, and performs well in recognizing intersecting machining features.

Management Control and Integration Technology of Intelligent Production Line for Multi-Variety and Complex Aerospace Ring Forgings: A Review

Large and complex ring forgings are key structural parts of the aerospace field, and their quality is closely related to the reliability of aerospace vehicles. However, high-quality production of aerospace ring forgings faces many problems, such as the long process design cycle and impoverished consistency, the difficulties of real-time detection under the severe time-varying state of the deformation process, the complexity of high-quality non-destructive testing under multitudinous defects, and the cumbersome management control of the multi-source and multi-dimensional heterogeneous data. Considering the current situation of multi-variety and multi-batch production for aerospace ring forgings, establishing an intelligent production line is a crucial means to solving the above problems and realizing the standardization and premiumization of key aerospace components. Therefore, management control and integration technology of the intelligent production line play a crucial role. An analysis, including the research progress of the intelligent computer-aided process planning (CAPP) system, the real-time detection and control system, the product quality testing system, and the intelligent management control and integration system, is systematically reviewed in this work. Through intelligently managing and controlling the integrated systems of the production line, the production efficiency of ring forgings can be effectively improved, and the production energy consumption can be remarkably reduced, which is of great significance for enhancing the manufacturing technology level of aerospace products.

Refined Simulation Method for Computer-Aided Process Planning Based on Digital Twin Technology.

Simulation technology is widely used in computer-aided process planning (CAPP). The part machining process is simulated in the virtual world, which can predict manufacturing errors and optimize the process plan. Simulation accuracy is the guarantee of process decision-making and optimization. This article focuses on the use of digital twin technology to build a high-fidelity process model, taking the advantage of the integration of multiple systems, in order to achieve the dynamic association of real-time manufacturing data and process models. Making use of the CAPP/MES systems, the surface inspection data of the part is fed back to the CAPP system and associated with the digital twin process model. The wavelet transform method is used to reduce the noise of the high-frequency signal of the detection data, and the signal-to-noise ratio (SNR) is calculated to verify the noise reduction effect. The surface topography, after noise reduction, was reconstructed in Matlab. On this basis, the Poisson reconstruction algorithm is used to reconstruct the high-fidelity process model for the refined simulation of the subsequent processes. Finally, by comparing the two sets of simulation experiments with the real machining results, we found that the simulation results, based on the digital twin model, are more accurate than the traditional simulation method by 58%.

A Survey and Feasibility Research Study on Computer Aided Process Planning (CAPP)

Abstract: Computer Aided Process Planning (CAPP) is the use of computer system to help and guide process planners in planning and executing different functions. It has emerged as one of the crucial links between integration of Computer Aided Design (CAD) and Computer Aided Manufacturing (CAM). In this paper, an attempt is made to provide a complete survey of CAPP based on different methodology namely, features and solid model, neural networks, optimization, fuzzy logic, knowledge based, web based, hybrid manufacturing, artificial intelligence, virtual, (STEP)-compliant method. The aim of this paper is to provide an update, in and after year 2000, in field of CAPP systems using survey and representing graphically for easy understanding Keywords: CAPP, CAD, CAM, Methodology, Variant, Generative.

Machining sequence learning via inverse reinforcement learning

In recent years, process planning automation has been strongly promoted in conjunction with the development of information technology (IT). In manufacturing industries, machining sequencing is one of the elements of computer-aided process planning (CAPP) systems where it has a significant impact on the quality and cost of machined components. Therefore, effective and robust planning rules are essential for practical CAPP systems, and various metrics and constraints have been proposed to facilitate the creation of those rules. However, since it is challenging to address explicit factors such as interference between rules, processing difficulties, and manageability, discrepancies that require manual corrections often arise between the generated sequences and the planner's intentions. To resolve this problem, we propose a method of acquiring rules that reproduce the planner's decisions by inverse reinforcement learning (IRL). To apply the IRL process, we focus on identifying a machining sequence that characterizes the planner's decision based on past production processes and interviews with experts. This machining sequence can then be represented using a Markov decision process (MDP) when changing the workpiece shape, which enables the application of IRL. Additionally, to reflect the drawing information in the sequence decision, the workpiece shape is represented as a graph with attached tolerance and roughness values. The graphed machining sequence is then inputted to the graph, where convolutional networking and training are performed. We verified the validity of our proposed method using a small dataset.

Classification of research and applications of the computer aided process planning in manufacturing systems

The Computer Aided Process Planning (CAPP) systems are recently developed in manufacturing engineering to provide links between Computer Aided Design (CAD) and Computer Aided Manufacturing (CAM) systems. The CAPP systems are developed by considering the different issues of computer applications in production engineering. Optimization techniques can be applied to the CAPP to increase efficiency in part production processes. The energy consumption of part production process can be analyzed and optimized using the CAPP systems in order to increase added value in the part manufacturing process. Also, artificial neural networks as well as cloud manufacturing systems can be applied to the CAPP systems to share advantages of the different CAPP systems in different industry applications. Flexible process planning systems are developed using dynamic CAPP in order to cope with product varieties in process of part production. To develop potential energy saving strategies during product design and process planning stages, the advanced CAPP systems can be used. In this paper, a review of Computer Process Planning systems (CAPP) is presented and future research works are also suggested. It has been observed that the research filed can be moved forward by reviewing and analyzing recent achievements in the published papers.

Recognition of Multi-Intersecting Features of Boundary Representation CAD Model

This research aims to solve technical problem of automatic feature recognition in a Computer Aided Process Planning system. This feature recognition method was developed to represent a 3D model as classes of manufacturing features based on graph theory. In addition, “accessibility” was proposed to recognize intersecting features with complicated graph structure which cannot be predefined by users. The experimental result shown in case study proofed that this proposed method is effective in multi-intersecting feature recognition.

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.

A customizable process planning approach for rotational parts based on multi-level machining features and ontology

Turning is the one of the most commonly available and least expensive machining operations. Confronted with the increased number of part variants and the requirement for fast system responsiveness in dynamic environments, traditional methods for building a computer-aided process planning (CAPP) system for turning are infeasible due to the fixed feature library and hard-coded heuristic rules. In this paper, a customizable approach for automatic process planning of rotational parts is proposed to boost the productivity of enterprises by realizing multi-level machining feature recognition and knowledge-based machining activity/resource selection. First, from the decomposed cells of the turning area, basic turning features are successively recognized based on a novel cell machinability analysis. The high-level custom features are define based on the directed acyclic graph and recognized from the basic feature precedence graph using the subgraph matching algorithm. To facilitate the knowledge-based process planning, a knowledge base is then established utilizing ontology, in which the taxonomies, properties, and causal relationships among the core concepts, namely, machining feature, machining operation, cutting tool, and machine tool, are formally defined. Finally, a five-step procedure is proposed to automatically infer manufacturing activity/resource for multi-level features through rule-based reasoning. The effectiveness and extensibility of the proposed approach are validated through two case studies on complex rotational parts.

A features subtraction system for rotational parts based on manufacturing and metal removing concepts

Automatic feature recognition (AFR) techniques represent an essential tool that links computer-aided design (CAD) and computer-aided process planning (CAPP) systems. This is by converting low-level geometric entities of part design models created in CAD systems to manufacturing features which are used in CAPP. Whilst different AFR systems have been developed for the purpose of recognising final manufacturing features of a part, most of them do not solve features intersecting issues. The features intersecting is an unavoidable matter that occurs during the rough cutting cycle and forms intermediate manufacturing features. This paper presents a “features subtraction” methodology for solving manufacturing features intersection issues of rotational parts. The system takes the recognised external and internal manufacturing features from a smart interactive AFR (SI-AFR) system as an input. After seven steps of processing, it provides geometrical and topological information of intermediate and final features that can be used to automatically generate CAPP outputs, such as selecting machining process, sequence of operations, cutting tools and cutting conditions, and generating the G-code for machining the part. This has been written using C# coding, and several examples have been processed for this paper to validate the system.

Embedding firefly algorithm in optimization of CAPP turning machining parameters for cutting tool selections

The intervention of human expert to best select proper machining parameters can be reduced by automatic process planning. This includes such tedious work and sufficient knowledge one has to distinguish in choosing various options of cutting tools from the manufacturer’s catalogue. In this work, cutting tool selections of turning machining workpiece by optimizing machining parameters were done. Turning machining features were automatically recognized by volume decomposition method and sub-delta volumes (SDV) were generated. Geometrical data extracted from SDV were then utilized in getting optimum machining parameters by using the firefly algorithm (FA). Machining parameters including cutting speed (CS), feed rate (f) and depth of cut (d) were optimized within an objective function of minimizing unit production cost (UPC). A relevant algorithm embedded with FA is proposed to execute the computer-aided process planning (CAPP) system. The feasibility of the approach and the developed algorithm was verified through an illustrative case study of an industrial part model.

Design of Computer Aided Process Planning System for Holster Mold at PT. Carnegie Universal Industries

PT. Carnegie Universal Industries manufactures holster products and magazine carrier. Holsters have the most variants and the highest demand. To produce a holster, a mold is needed for each type of handgun. A mold uses wooden mold and blue gun. Mold making takes the longest time compared to other stages in the holster production process. The mold making process does not yet have standards, therefore it takes a long time and high cost. The purpose of this study is to develop a process planning to facilitate the making of molds with automated systems using the Computer Aided Process Planning (CAPP) method, speed up production time, and reduce production costs. The CAPP generative approach is generated through decision logic, formulation, search, algorithm and geometric based data. Database programs are created to store detailed information on each print that has been created. This approach design proved that the mold making procedures are simplified and speeded up and have standards, so that the time and costs are used more effectively and efficiently.

Intelligent process planning for smart manufacturing systems: a state-of-the-art review

Process planning is a decision-making procedure to determine the required manufacturing processes and machine tools, and the sequence of the activities that the processes should follow, to produce a designed part or a product component. The quality of the process plan has a major impact on the efficiency and productivity of the whole production process in addition to the quality of the final product. Computer-aided process planning (CAPP) systems have been constantly developing and attracted considerable research efforts during the last four decades. Several approaches such as search logic structure, variant or case-based, generative approach, hybrid, and knowledge-based or expert systems have been employed to develop the CAPP systems with the aim of reducing and finally removing the role of experienced process planners in providing a reliable and optimized process plan to achieve the automated and intelligent CAPP system. However, despite these huge efforts, the process planning task is not completely automated yet and still depends on human experiences and knowledge. Artificial Intelligence, Machine Learning, and Data Analytics seem to be promising tools to achieve the total independence of CAPP systems on the experience of the process planners in the era of Industry 4.0 and smart manufacturing systems. The ideal intelligent CAPP systems will be able to collect the experience and knowledge of the technology experts in addition to being adaptive and self-learning according to the machining process real-time data and work history. In this article, a literature review is carried out with the aim of gaining a comprehensive insight into the state-of-the-art intelligent process planning approaches. Several articles and books based on the types and the applications of the systems are reviewed with a focus on the publishing date within the last decade. The advantages and disadvantages of different approaches are presented and finally, the future research and investigation pathways are demonstrated.

A novel classification of freeform volumetric features and generative CAPP approach for milling machine selection

Feature recognition is an important function of computer-aided process planning (CAPP) system. The freeform feature recognition works performed so far have resulted in successful classification and recognition of freeform surface-based features, but the works do not classify and recognize freeform volumetric features. The research works like automatic generation of delta volume (DV) for volumetric features, finishing, and roughing process were successful when applied to regular form parts, but generated a complex DV for roughing process when applied to freeform parts. Also, the DV generation works do not generate DV for freeform features. So an effort is made (i) to newly classify freeform volumetric features and develop an algorithm to automatically generate DV for freeform volumetric features; (ii) to automatically recognize freeform volumetric features by a set of conditions and colour coding concept; and (iii) to determine the level of complexity and milling machine selection. The problem of complex DV is overcome by generation of sub-delta volume for transition (SDVT). The algorithm is able to recognize freeform volumetric features and the DV’s quantitative data, exploded view, and labelling will aid the downstream activities of CAPP system. The algorithm validation result shows a percentage error of 0.005% for complex part like impeller.

ROBOTIC ASSEMBLY SEQUENCE PLANNING AND OPTIMIZATION BY CUCKOO SEARCH ALGORITHM

The assembly sequence optimization problem is challenging as number of sequences rises staggeringly with part count making it combinatorically explosive, tedious and time consuming to solve. A Computer-Aided Process Planning (CAPP) system for robotic assembly by a discrete cuckoo search algorithm has been proposed by us to generate feasible and optimal sequences considering minimization of orientation changes, tool/gripper changes, assembly stability and base component location. A case study and comparison results with an established soft computing approach are presented to show its effectiveness. It is further integrated with an upstream assembly product database to extract information on assembly directions, contact details, assembly precedence constraints and tool/grippers. Further the assembly sequence output from CAPP system is integrated with a robot task planner developed using Knowledge Based System capable of automatically generating executable robot level program for performing the assembly.

Hole Feature on Conical Face Recognition for Turning Part Model

Computer Aided Process Planning (CAPP) is the bridge between CAD and CAM and pre-processing of the CAD data in the CAPP system is essential. For CNC turning part, conical faces of part model is inevitable to be recognised beside cylindrical and planar faces. As the sinus cosines of the cone radius structure differ according to different models, face identification in automatic feature recognition of the part model need special intention. This paper intends to focus hole on feature on conical faces that can be detected by CAD solid modeller ACIS via. SAT file. Detection algorithm of face topology were generated and compared. The study shows different faces setup for similar conical part models with different hole type features. Three types of holes were compared and different between merge faces and unmerge faces were studied.

Development of a modular computer-aided process planning (CAPP) system for additive-subtractive hybrid manufacturing of pockets, holes, and flat surfaces

Additive manufacturing (AM) can significantly reduce the development time for small batch parts or parts with complicated geometries. However, the accuracy of most metal AM processes requires parts to be subjected to secondary processing (typically machining) in order to obtain requisite tolerances. Process plan development for hybrid manufacturing, which is defined for the following as additive manufacturing followed by subtractive multi-axis computer numerical control (CNC) machining, typically takes weeks rather than hours or days. This paper outlines a feature-based advanced hybrid manufacturing process planning system (FAH-PS) that uses feature-specific geometric, tolerance, and material data inputs to generate four-automated process plans based on user-specified feature precedence for hybrid manufacturing. FAH-PS currently has the capability to identify manufacturing processes for critical pockets, flat surfaces, and hole features. Additional plans generated by FAH-PS minimize tool changes, orientation changes, etc., to improve process times. FAH-PS is modular and extensible to allow for additional feature types, materials, tool sizes, and/or optimization strategies to be included in future versions. A case study, using a custom patient-specific bone plate, demonstrated system capabilities and processing time reductions as compared to the current manual process planning for hybrid manufacturing methodologies. Using the generated FAH-PS process plan resulted in a 35% reduction in machining time from the current hybrid manufacturing strategy. Imploring a strategy of minimizing tool and orientation changes generated a process plan that demonstrated that even further improvements were possible.