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 article , a review of the state of the art in optical metrology is presented, highlighting the advantages and impacts of the integration of optical coordinate and surface texture measurement technologies in digital manufacturing processes.
Abstract: Abstract With the increasing adoption of Industry 4.0, optical metrology has experienced a significant boom in its implementation, as an ever-increasing number of manufacturing processes are overhauled for in-process measurement and control. As such, optical metrology for digital manufacturing is currently a hot topic in manufacturing research. Whilst contact coordinate measurement solutions have been adopted for many years, the current trend is to increasingly exploit the advantages given by optical measurement technologies. Smart automated non-contact inspection devices allow for faster cycle times, reducing the inspection time and having a continuous monitoring of process quality. In this paper, a review for the state of the art in optical metrology is presented, highlighting the advantages and impacts of the integration of optical coordinate and surface texture measurement technologies in digital manufacturing processes. Also, the range of current software and hardware technologies for digital manufacturing metrology is discussed, as well as strategies for zero-defect manufacturing for greater sustainability, including examples and in-depth discussions of additive manufacturing applications. Finally, key current challenges are identified relating to measurement speed and data-processing bottlenecks; geometric complexity, part size and surface texture; user-dependent constraints, harsh environments and uncertainty evaluation.
13 citations
TL;DR: Wang et al. as mentioned in this paper used a deep transfer learning (DTL) model combining deep convolutional neural network and transfer learning to identify the part quality based on the layer-wise visual images.
Abstract: Selective laser melting is the most commonly used additive manufacturing technique for fabricating metal components. However, the SLMed part quality still largely suffered from the porosity defects that can significantly affect the mechanical properties. Recently, in situ monitoring based on machine learning has been recognized as an effective method to overcome this challenge. In this work, a deep learning method is developed for in situ part quality inspection. The layer-wise visual images are used as the inputs without manual feature extraction and a deep transfer learning (DTL) model combining deep convolutional neural network and transfer learning is creatively applied. First, an off-axial in situ monitoring system by a high-resolution digital camera is developed to capture the images of each deposited layer. Then, samples with different part quality levels are produced by varying process parameters. Thereafter, based on the porosity measurement results obtained by optical microscopy, each captured visual image is labeled. An image dataset associated with a label of three categories of poor, medium, and high quality is created. Finally, the proposed DTL is employed to perform the classification tasks, aiming to identify the part quality based on the layer-wise visual images. Results show that a 99.89% classification accuracy of the developed DTL was obtained, revealing the feasibility and effectiveness of using layer-wise visual images without manual feature extraction to realize quality inspection. Overall, the proposed DTL method provides a promising solution to monitor part quality and reduce porosity defects during the printing process.
13 citations
TL;DR: In this article, the role of manufacturing process parameters and their impact on part variability was investigated using a generalized linear model (GLM) to model the variability and to predict defects.
Abstract: Scalable production using additive manufacturing (AM) requires quality systems that monitor and control manufacturing variability across many machines in a factory environment. AM process variability can result in geometric inaccuracies in parts that can affect their mechanical behavior; however, most research focuses on a single machine and hardware set, while part inaccuracy and AM variability across multiple printers remains poorly understood. This study establishes a framework to study the accuracy of polymer parts made on three identical printers and evaluates the role of manufacturing process parameters and their impact on part variability. We fabricate 90 polymer hexagonal lattice parts over nine builds on three identical Carbon M2 machines with interchangeable hardware tools. Each part is measured using automated metrology that extracts the size and shape of the part features and automatically measures defects. Each hexagonal part consists of 237 individual walls that were measured for 90 parts, resulting in 21,330 individual geometric measurements. Using statistical methods to analyze geometric defects as a function of machine, hardware set, and location in the build, we find that the observed variability can be correlated with process parameters. Geometric defects in the wall thickness depend upon machine and location within the build but do not depend on the hardware tool, while geometric defects in the wall length and height of the part depend upon machine and tool but not location. The uniformity within the parts, measured by standard deviations of the individual features within a part, mostly depends upon unmeasured parameters. We use a generalized linear model (GLM) to model the variability and to predict defects. The framework introduced here can be extended to analyze additional machines and process parameters and provides a practical tool to account for manufacturing variability in an AM production environment.
13 citations
16 Dec 2019
13 citations
TL;DR: Li et al. as discussed by the authors proposed a framework to process the melt pool images by a configuration of Convolutional Auto-Encoder (CAE) neural networks, which learns a deep yet low-dimensional representation from melt pools while preserving the spatial correlation and complex features intrinsic in the images.
Abstract: Laser Powder Bed Fusion (LPBF) is an additive manufacturing process where laser power is applied to fuse the spread powder and fabricate industrial parts in a layer by layer fashion. Despite its great promise in fabrication flexibility, print quality has long been a major barrier for its widespread implementation. Traditional offline post-manufacturing inspections to detect the defects in finished products are expensive and time-consuming and thus cannot be applied in real-time monitoring and control. In-situ monitoring methods by relying on the in-process sensor data, on the other hand, can provide viable alternatives to aid with the online detection of anomalies during the process. Given the crucial importance of melt pool characteristics to the quality of final products, this paper provides a framework to process the melt pool images by a configuration of Convolutional Auto-Encoder (CAE) neural networks. The network’s corresponding bottleneck layer learns a deep yet low-dimensional representation from melt pools while preserving the spatial correlation and complex features intrinsic in the images. As opposed to the manual annotation of data by X-ray imaging or destructive tests, an agglomerative clustering algorithm is applied to these representations to automatically extract the anomalies and annotate the data accordingly. A control charting scheme based on Hotelling’s T2 and S2 statistics is then developed to monitor the process’s stability by keeping track of the learned representations and residuals obtained from the reconstruction of original images. Testing the proposed methodology on the collected data from an experimental build demonstrates that the method can extract a set of complex features that are inextricable otherwise by using hand-crafted feature engineering methods. Moreover, through extensive numerical studies, it is shown that the proposed feature extraction and statistical process monitoring scheme is capable of detecting the anomalies in real-time with accuracy and F1 score of about 95% and 82%, respectively.
12 citations
Cites background from "Application of supervised machine l..."
...conduct another study with the aim of binary classification of voxels from layerwise optical images collected during build-time [12]....
[...]
...In general, two post-build approaches correlate a melt pool image to either a normal or defective location/spot on the part: (1) nondestructive inspection by CT-scan X-ray imaging, and (2) destructive inspection [12,13]....
[...]
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