“…These practices make it difficult to formalize context-specific information and establish semantics in CAD models. Despite some recent efforts to automate the creation of annotations, the process depends heavily on user input as the knowledge is not linked to the geometry of the 3D product representation (Soria & van der Hoek, 2019) and the results are not comparable to those provided directly by engineers (Cheng, He, Lv, & Cai, 2019). If the user does not actively maintain the annotations or neglects to retrieve the information to annotate, some important information may be lost.…”
In this paper, we describe a voice-based interaction mechanism to annotate 3D models directly from a computer-aided design (CAD) modeling environment. The audio signal is captured and automatically transcribed to a textual 3D note, which is attached to the geometry and made available to other product information and business processes across the enterprise via a product data management system. Our approach provides a more natural and intuitive method to capture design and engineering knowledge that is particularly effective when large amounts of information need to be communicated. We discuss the rationale of the software architecture and the value of this modality for capturing knowledge in a collaborative engineering context. Finally, we examine the results of an experiment to validate our proposal. Our results show that 3D annotations are an effective mechanism to communicate design knowledge, which suggests the need for further developments in the areas of multimodal interaction methods and interfaces for CAD and collaborative tools.
“…These practices make it difficult to formalize context-specific information and establish semantics in CAD models. Despite some recent efforts to automate the creation of annotations, the process depends heavily on user input as the knowledge is not linked to the geometry of the 3D product representation (Soria & van der Hoek, 2019) and the results are not comparable to those provided directly by engineers (Cheng, He, Lv, & Cai, 2019). If the user does not actively maintain the annotations or neglects to retrieve the information to annotate, some important information may be lost.…”
In this paper, we describe a voice-based interaction mechanism to annotate 3D models directly from a computer-aided design (CAD) modeling environment. The audio signal is captured and automatically transcribed to a textual 3D note, which is attached to the geometry and made available to other product information and business processes across the enterprise via a product data management system. Our approach provides a more natural and intuitive method to capture design and engineering knowledge that is particularly effective when large amounts of information need to be communicated. We discuss the rationale of the software architecture and the value of this modality for capturing knowledge in a collaborative engineering context. Finally, we examine the results of an experiment to validate our proposal. Our results show that 3D annotations are an effective mechanism to communicate design knowledge, which suggests the need for further developments in the areas of multimodal interaction methods and interfaces for CAD and collaborative tools.
“…applying data mining techniques to the annotated text) [20], but knowledge in an unstructured textual form can be cumbersome for humans, particularly when compared to verbal communication. Some efforts have been made to automate the creation of these annotations [21], but the results and the knowledge conveyed are not comparable to those provided by actual designers and engineers.…”
This paper describes a novel voice interaction mechanism for capturing and managing design knowledge within a collaborative Computer-Aided Design (CAD) environment. We present a software module for speech recognition that integrates with a CAD application to allow the automatic creation of textual annotations in a 3D model directly from voice data. Audio is transcribed automatically, resulting in a textual note that is searchable and available to other users via a Product Data Management (PDM) system, providing an intuitive mechanism to document modeling processes and design knowledge. The system consists of three functional blocks: (1) audio recording, (2) speech recognition, and (3) query management against a cloud-based service. In this paper, we justify the need for our system from a human-computer interaction standpoint and discuss the rationale of its design and implementation in the context of collaborative design communication. Finally, we discuss some application spaces that demonstrate the capability of voice annotations for capturing knowledge.
“…Operators of CNC machines have the flexibility to design and customize machine parameters such as feed rate, cutting depth, spindle speed, and more. Modern CNC machines offer advanced capabilities such as controlling multiple axes, error correction, and performing diverse tasks [2].…”
The STEP file is the “standard for the exchange of product model data,” which is usually used to exchange geometric data in boundary representation (B-rep) between different computer-aided design (CAD) platforms. These data can be fully utilized and integrated into a larger manufacturing organization, such as a computer-aided manufacturing (CAM) environment for computer numerical control (CNC) machining applications based on ISO 6983. The 3D models of 2D machining profiles were created in CAD software and saved as STEP files. The data structure was analyzed by comparing the geometric entities of the CAD model and the STEP file. The algorithm was created using the hypertext preprocessor (PHP) programming language and produced a computer interface system to convert STEP files into G-code format. The machining blocks with profile machining features were simulated using a CNC simulator and PC-based open architecture control (OAC) software. The G-code was validated on a three-axis CNC milling machine, and the result was compared to the CAD model to confirm the machining profile. The integrated interface system I2S demonstrates its ability to interpret all 2D profiles and generate machining tool paths and G-code, allowing data flow between CAD and CAM environments and shortening product development cycles.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.