Refine
Document Type
- Article (9)
- Conference Proceeding (3)
- Part of a Book (1)
Language
- English (13)
Is part of the Bibliography
- yes (13)
Keywords
- CNC machine tools (1)
- Energy consumption (1)
- G-code (1)
- Machine Learning (1)
- additive manufacturing (1)
- in situ monitoring (1)
- metal printing (1)
- neural network (1)
- semantic segmentation (1)
- thermal distortion (1)
Institute
Computerized Numerical Control (CNC) plays an important role in highly autonomous manufacturing systems with multiple machine tools. The necessary Numerical Control (NC) programs to manufacture the parts are mostly written in standardized G-code. An a priori evaluation of the energy demand of CNC-based machine processes opens up the possibility of scheduling multiple jobs according to balanced energy consumption over a production period. Due to this, we present a combined Machine Learning (ML) and Job-Shop-Scheduling (JSS) approach to evaluate G-code for a CNC-milling process with respect to the energy demand of each G-command. The ML model training data are derived by the Latin hypercube sampling (LHS) method facing the main G-code operations G00, G01, and G02. The resulting energy demand for each job enhances a JSS algorithm to smooth the energy demand for multiple jobs, as peak power consumption needs to be avoided due to its expense.
Computerized Numeric Control (CNC) plays an essential role in highly autonomous manufacturing systems for interlinked process chains for machine tools. NC-programs are mostly written in standardized G-code. Evaluating CNC-controlled manufacturing processes before their real application is advantageous due to resource efficiency. One dimension is the estimation of the energy demand of a part manufactured by an NC-program, e.g. to discover optimization potentials. In this context, this paper presents a Machine Learning (ML) approach to assess G-code for CNC-milling processes from the perspective of the energy demand of basic G-commands. We propose Latin Hypercube Sampling as an efficient method of Design of Experiments to train the ML model with minimum experimental effort to avoid costly setup and implementation time of the model training and deployment.
Abstract
This data descriptor contains information about an extensive production data set for a five-axis CNC milling process. Three geometrically different products were manufactured and relevant features from the numerical control of the machine were recorded. The recorded manufacturing process contains the preparation of the machine for the next product (changeover) as well as the machining process (production). The experimental manufacturing was organized with the aid of a changeover matrix to ensure that all possible changeover combinations for the three products were considered. The production was repeated five times, resulting in 30 manufacturing sessions and five complete changeover matrices. The data set was recorded in a laboratory environment. A rich feature set including i.e. the NC-code of the products, tool information, and a Jupyter notebook is provided with the data set.
Powder Bed Monitoring Using Semantic Image Segmentation to Detect Failures during 3D Metal Printing
(2023)
Monitoring the metal Additive Manufacturing (AM) process is an important task within the scope of quality assurance. This article presents a method to gain insights into process quality by comparing the actual and target layers. Images of the powder bed were captured and segmented using an Xception–style neural network to predict the powder and part areas. The segmentation result of every layer is compared to the reference layer regarding the area, centroids, and normalized area difference of each part. To evaluate the method, a print job with three parts was chosen where one of them broke off and another one had thermal deformations. The calculated metrics are useful for detecting if a part is damaged or for identifying thermal distortions. The method introduced by this work can be used to monitor the metal AM process for quality assurance. Due to the limited camera resolutions and inconsistent lighting conditions, the approach has some limitations, which are discussed at the end.
The described data set contains features from the machine control of a five-axis milling machine. The features were recorded during thirteen series productions. Each series production includes a changeover process in which the machine was set up for the production of a different product. In addition to the timestamps and the twenty recorded features derived from Numerical Control (NC) variables, the data set also contains labels for the different production phases. For this purpose, up to 23 phases were assigned, which are based on a generalized milling process. The data set consists of thirteen .csv files, each representing a series production. The data set was recorded in a production company in the contract manufacturing sector for components with real series orders in ongoing industrial production.