Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging.
TL;DR: In this article, an in- situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning is described, where multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera.
Abstract: Process monitoring in additive manufacturing (AM) is a crucial component in the mission of broadening AM industrialization. However, conventional part evaluation and qualification techniques, such as computed tomography (CT), can only be utilized after the build is complete, and thus eliminate any potential to correct defects during the build process. In contrast to post-build CT, in situ defect detection based on in situ sensing, such as layerwise visual inspection, enables the potential for in-process re-melting and correction of detected defects and thus facilitates in-process part qualification. This paper describes the development and implementation of such an in situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning. During the build process, multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera. For each neighborhood in the resulting layerwise image stack, multi-dimensional visual features were extracted and evaluated using binary classification techniques, i.e. a linear support vector machine (SVM). Through binary classification, neighborhoods are then categorized as either a flaw, i.e. an undesirable interruption in the typical structure of the material, or a nominal build condition. Ground truth labels, i.e. the true location of flaws and nominal build areas, which are needed to train the binary classifiers, were obtained from post-build high-resolution 3D CT scan data. In CT scans, discontinuities, e.g. incomplete fusion, porosity, cracks, or inclusions, were identified using automated analysis tools or manual inspection. The xyz locations of the CT data were transferred into the layerwise image domain using an affine transformation, which was estimated using reference points embedded in the part. After the classifier had been properly trained, in situ defect detection accuracies greater than 80% were demonstrated during cross-validation experiments.
Citations
More filters
TL;DR: In this paper, the authors reviewed the research progress of in situ monitoring during selective laser melting (SLM) process based on images and proposed the main development direction of image-based computer vision.
Abstract: Selective laser melting (SLM) has been widely used in the fields of aviation, aerospace and die manufacturing due to its ability to produce metal components with arbitrarily complex shapes. However, the instability of SLM process often leads to quality fluctuation of the formed component, which hinders the further development and application of SLM. In situ quality control during SLM process is an effective solution to the quality fluctuation of formed components. However, the basic premise of feedback control during SLM process is the rapid and accurate diagnosis of the quality. Therefore, an in situ monitoring method of SLM process, which provides quality diagnosis information for feedback control, became one of the research hotspots in this field in recent years. In this paper, the research progress of in situ monitoring during SLM process based on images is reviewed. Firstly, the significance of in situ monitoring during SLM process is analyzed. Then, the image information source of SLM process, the image acquisition systems for different detection objects (the molten pool region, the scanned layer and the powder spread layer) and the methods of the image information analysis, detection and recognition are reviewed and analyzed. Through review and analysis, it is found that the existing image analysis and detection methods during SLM process are mainly based on traditional image processing methods combined with traditional machine learning models. Finally, the main development direction of in situ monitoring during SLM process is proposed by combining with the frontier technology of image-based computer vision.
9 citations
TL;DR: In this article, an approach for monitoring the laser powder bed fusion (LPBF) process using an area-scan hyperspectral camera to predict the surface roughness Rz with the help of a convolutional neural network was presented.
Abstract: This article discusses the relevance of in situ quality assurance in metal additive manufacturing for cost-efficient product qualification. It presents an approach for monitoring the laser powder bed fusion (LPBF) process using an area-scan hyperspectral camera to predict the surface roughness Rz with the help of a convolutional neural network. These investigations were carried out during LPBF processing of the magnesium alloy WE43 that, due to its bioresorbability and compatibility, holds significant potential for biomedical implants. A data acquisition and processing methodology has been set up to enable efficient management of the hyperspectral data. The hyperspectral images obtained from the process were labeled with the surface roughness Rz as determined by a confocal microscope. The data was used to train a convolutional neural network whose hyperparameters were optimized in a hyperparameter tuning process. The resulting network was able to predict the surface roughness within a mean absolute error (MAE) of 4.1 μm over samples from three different parameter sets. Since this is significantly smaller than the spread of the actual roughness measured (MAE = 14.3 μm), it indicates that the network identified features in the hyperspectral data linking to the roughness. These results provide the basis for future research aiming to link hyperspectral process images to further part properties relevant for quality assurance.
9 citations
TL;DR: In this article , a DenseNet-39 model was developed to detect and classify the melt pool states in laser-based direct energy deposition (L-DED) metal parts.
9 citations
TL;DR: In this paper, the authors compared XCT scans and automated flaw recognition analysis of corresponding data to results obtained from an automated mechanical polishing-based serial sectioning system, and the results point to the need to recognize the limitations of XCT and for supplementary XCT scan quality metrics in addition to the voxel size.
Abstract: In additive manufacturing (AM), internal flaws that form during processing can have a detrimental impact on the resulting fatigue behavior of the component. Nondestructive x-ray computed tomography (XCT) has been routinely used to inspect AM components. This technique, however, is limited by what is resolvable as well as the automated procedures available to analyze the data. In this study, we compared XCT scans and automated flaw recognition analysis of the corresponding data to results obtained from an automated mechanical polishing-based serial sectioning system. Although internal porosity and surface roughness were easily observed by serial sectioning with bright-field optical microscopy, the same level of information could not be obtained from the XCT data. For the acquisition parameters used, XCT had only a 15.7% detection rate compared to that of serial sectioning. The results point to the need to recognize the limitations of XCT and for supplementary XCT scan quality metrics in addition to the voxel size.
8 citations
TL;DR: In this paper, a method that combined acoustic signals with a deep learning algorithm to monitor the spatter behaviors was proposed, where acoustic signals were recorded by a microphone and spatter information was collected by a coaxial high-speed camera simultaneously.
Abstract: As one of the most promising metal additive manufacturing (AM) technologies, the selective laser melting (SLM) process has high expectations ofr its use in aerospace, medical, and other fields. However, various defects such as spatter, crack, and porosity seriously hinder the applications of the SLM process. In situ monitoring is a vital technique to detect the defects in advance, which is expected to reduce the defects. This work proposed a method that combined acoustic signals with a deep learning algorithm to monitor the spatter behaviors. The acoustic signals were recorded by a microphone and the spatter information was collected by a coaxial high-speed camera simultaneously. The signals were divided into two types according to the number and intensity of spatter during the SLM process with different combinations of processing parameters. Deep learning models, one-dimensional Convolutional Neural Network (1D-CNN), two-dimensional Convolutional Neural Network (2D-CNN), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) were trained to establish the relationships between the acoustic signals and characteristics of spatter. After K-fold verification, the highest classification confidence of models is 85.08%. This work demonstrates that it is feasible to use acoustic signals in monitoring the spatter defect during the SLM process. It is possible to use cheap and simple microphones instead of expensive and complicated high-speed cameras for monitoring spatter behaviors.
8 citations
References
More filters
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Abstract: The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
37,861 citations
01 Jun 2010
TL;DR: A brief overview of clustering is provided, well known clustering methods are summarized, the major challenges and key issues in designing clustering algorithms are discussed, and some of the emerging and useful research directions are pointed out.
Abstract: Organizing data into sensible groupings is one of the most fundamental modes of understanding and learning. As an example, a common scheme of scientific classification puts organisms into a system of ranked taxa: domain, kingdom, phylum, class, etc. Cluster analysis is the formal study of methods and algorithms for grouping, or clustering, objects according to measured or perceived intrinsic characteristics or similarity. Cluster analysis does not use category labels that tag objects with prior identifiers, i.e., class labels. The absence of category information distinguishes data clustering (unsupervised learning) from classification or discriminant analysis (supervised learning). The aim of clustering is to find structure in data and is therefore exploratory in nature. Clustering has a long and rich history in a variety of scientific fields. One of the most popular and simple clustering algorithms, K-means, was first published in 1955. In spite of the fact that K-means was proposed over 50 years ago and thousands of clustering algorithms have been published since then, K-means is still widely used. This speaks to the difficulty in designing a general purpose clustering algorithm and the ill-posed problem of clustering. We provide a brief overview of clustering, summarize well known clustering methods, discuss the major challenges and key issues in designing clustering algorithms, and point out some of the emerging and useful research directions, including semi-supervised clustering, ensemble clustering, simultaneous feature selection during data clustering, and large scale data clustering.
6,601 citations
TL;DR: The state-of-the-art of additive manufacturing (AM) can be classified into three categories: direct digital manufacturing, free-form fabrication, or 3D printing as discussed by the authors.
Abstract: This paper reviews the state-of-the-art of an important, rapidly emerging, manufacturing technology that is alternatively called additive manufacturing (AM), direct digital manufacturing, free form fabrication, or 3D printing, etc. A broad contextual overview of metallic AM is provided. AM has the potential to revolutionize the global parts manufacturing and logistics landscape. It enables distributed manufacturing and the productions of parts-on-demand while offering the potential to reduce cost, energy consumption, and carbon footprint. This paper explores the material science, processes, and business consideration associated with achieving these performance gains. It is concluded that a paradigm shift is required in order to fully exploit AM potential.
4,055 citations
TL;DR: Future directions such as the "print-it-all" paradigm, that have the potential to re-imagine current research and spawn completely new avenues for exploration are pointed out.
Abstract: Additive manufacturing (AM) is poised to bring about a revolution in the way products are designed, manufactured, and distributed to end users. This technology has gained significant academic as well as industry interest due to its ability to create complex geometries with customizable material properties. AM has also inspired the development of the maker movement by democratizing design and manufacturing. Due to the rapid proliferation of a wide variety of technologies associated with AM, there is a lack of a comprehensive set of design principles, manufacturing guidelines, and standardization of best practices. These challenges are compounded by the fact that advancements in multiple technologies (for example materials processing, topology optimization) generate a "positive feedback loop" effect in advancing AM. In order to advance research interest and investment in AM technologies, some fundamental questions and trends about the dependencies existing in these avenues need highlighting. The goal of our review paper is to organize this body of knowledge surrounding AM, and present current barriers, findings, and future trends significantly to the researchers. We also discuss fundamental attributes of AM processes, evolution of the AM industry, and the affordances enabled by the emergence of AM in a variety of areas such as geometry processing, material design, and education. We conclude our paper by pointing out future directions such as the "print-it-all" paradigm, that have the potential to re-imagine current research and spawn completely new avenues for exploration. The fundamental attributes and challenges/barriers of Additive Manufacturing (AM).The evolution of research on AM with a focus on engineering capabilities.The affordances enabled by AM such as geometry, material and tools design.The developments in industry, intellectual property, and education-related aspects.The important future trends of AM technologies.
1,792 citations
TL;DR: In this article, a review of additive manufacturing (AM) techniques for producing metal parts are explored, with a focus on the science of metal AM: processing defects, heat transfer, solidification, solid-state precipitation, mechanical properties and post-processing metallurgy.
Abstract: Additive manufacturing (AM), widely known as 3D printing, is a method of manufacturing that forms parts from powder, wire or sheets in a process that proceeds layer by layer. Many techniques (using many different names) have been developed to accomplish this via melting or solid-state joining. In this review, these techniques for producing metal parts are explored, with a focus on the science of metal AM: processing defects, heat transfer, solidification, solid-state precipitation, mechanical properties and post-processing metallurgy. The various metal AM techniques are compared, with analysis of the strengths and limitations of each. Only a few alloys have been developed for commercial production, but recent efforts are presented as a path for the ongoing development of new materials for AM processes.
1,713 citations