The goal of this work to mitigate flaws in metal parts produced from laser powder bed fusion (LPBF) additive manufacturing (AM) process. As a step towards this goal, the objective of this work is to predict the build quality of a part as it is being printed via deep learning of in-situ layer-wise images obtained from an optical camera instrumented in the LPBF machine. To realize this objective, we designed a set of thin-wall features (fins) from Titanium alloy (Ti-6Al-4V) material with varying length-to-thickness ratio. These thin-wall test parts were printed under three different build orientations and in-situ images of their top surface were acquired during the process. The parts were examined offline using X-ray computed tomography (XCT), and their build quality was quantified in terms of statistical features, such as the thickness and consistency of its edges. Subsequently, a deep learning convolutional neural network (CNN) was trained to predict the XCT-derived statistical quality features using the layer-wise optical images of the thin-wall part as inputs. The statistical correlation between CNN-based predictions and XCT-observed quality measurements exceeds 85%. This work has two outcomes consequential to the sustainability of additive manufacturing: (1) It provides practitioners with a guideline for building thin-wall features with minimal defects, and (2) the high correlation between the offline XCT measurements and in-situ sensor-based quality metrics substantiates the potential for applying deep learning approaches for the real-time prediction of build flaws in LPBF.
more »
« less
A Gaussian Process Model-Guided Surface Polishing Process in Additive Manufacturing
Abstract Polishing of additively manufactured products is a multi-stage process, and a different combination of polishing pad and process parameters is employed at each stage. Pad change decisions and endpoint determination currently rely on practitioners’ experience and subjective visual inspection of surface quality. An automated and objective decision process is more desired for delivering consistency and reducing variability. Toward that objective, a model-guided decision-making scheme is developed in this article for the polishing process of a titanium alloy workpiece. The model used is a series of Gaussian process models, each established for a polishing stage at which surface data are gathered. The series of Gaussian process models appear capable of capturing surface changes and variation over the polishing process, resulting in a decision protocol informed by the correlation characteristics over the sample surface. It is found that low correlations reveal the existence of extreme roughness that may be deemed surface defects. Making judicious use of the change pattern in surface correlation provides insights enabling timely actions. Physical polishing of titanium alloy samples and a simulation of this process are used together to demonstrate the merit of the proposed method.
more »
« less
- Award ID(s):
- 1849085
- NSF-PAR ID:
- 10131960
- Date Published:
- Journal Name:
- Journal of Manufacturing Science and Engineering
- Volume:
- 142
- Issue:
- 1
- ISSN:
- 1087-1357
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Research on robotic lower-limb assistive devices over the past decade has generated autonomous, multiple degree-of-freedom devices to augment human performance during a variety of scenarios. However, the increase in capabilities of these devices is met with an increase in the complexity of the overall control problem and requirement for an accurate and robust sensing modality for intent recognition. Due to its ability to precede changes in motion, surface electromyography (EMG) is widely studied as a peripheral sensing modality for capturing features of muscle activity as an input for control of powered assistive devices. In order to capture features that contribute to muscle contraction and joint motion beyond muscle activity of superficial muscles, researchers have introduced sonomyography, or real-time dynamic ultrasound imaging of skeletal muscle. However, the ability of these sonomyography features to continuously predict multiple lower-limb joint kinematics during widely varying ambulation tasks, and their potential as an input for powered multiple degree-of-freedom lower-limb assistive devices is unknown. The objective of this research is to evaluate surface EMG and sonomyography, as well as the fusion of features from both sensing modalities, as inputs to Gaussian process regression models for the continuous estimation of hip, knee and ankle angle and velocity during level walking, stair ascent/descent and ramp ascent/descent ambulation. Gaussian process regression is a Bayesian nonlinear regression model that has been introduced as an alternative to musculoskeletal model-based techniques. In this study, time-intensity features of sonomyography on both the anterior and posterior thigh along with time-domain features of surface EMG from eight muscles on the lower-limb were used to train and test subject-dependent and task-invariant Gaussian process regression models for the continuous estimation of hip, knee and ankle motion. Overall, anterior sonomyography sensor fusion with surface EMG significantly improved estimation of hip, knee and ankle motion for all ambulation tasks (level ground, stair and ramp ambulation) in comparison to surface EMG alone. Additionally, anterior sonomyography alone significantly improved errors at the hip and knee for most tasks compared to surface EMG. These findings help inform the implementation and integration of volitional control strategies for robotic assistive technologies.
-
null (Ed.)INTRODUCTION: Orthopedic implants are important therapeutic devices for the management of a wide range of orthopedic conditions. However, bacterial infections of orthopedic implants remain a major problem, and not an uncommon one, leading to an increased rate of osteomyelitis, sepsis, implant failure and dysfunction, etc. Treating these infections is more challenging as the causative organism protects itself by the production of a biofilm over the implant’s surface (1). Infections start by the adhesion and colonization of pathogenic bacteria such as Staphylococcus aureus (SA), Staphylococcus epidermidis (SE), Escherichia coli (E. coli), Methicillin-Resistant Staphylococcus aureus (MRSA), and Multi-Drug Resistant Escherichia coli (MDR E. coli) on the implant’s surfaces. Specifically, Staphylococcus comprises up to two-thirds of all pathogens involved in orthopedic implant infections (2). However, bacterial surface adhesion is a complex process influenced by several factors such as chemical composition, hydrophobicity, magnetization, surface charge, and surface roughness of the implant (3). Considering the intimate association between bacteria and the implant surface, we measured the effect of stainless-steel surface properties on bacterial surface attachment and subsequent formation of biofilms controlling above mentioned factors. METHODS: The prominent bacteria responsible for orthopedic implant infections (SA, SE, E. coli, MRSA, and MDR E. coli) were used in this study. We were able to control the grain size of medical grade 304 and 316L stainless steel without altering their chemical composition (grain size range= 20μm-200nm) (4). Grain size control affected the nano-topography of the material surfaces which was measured by an Atomic Force Microscope (AFM). Grain sizes, such as 0.2, 0.5, 1, 2, 3, 9, and 10 μm, were used both polished and non-polished. All the stainless-steel samples were cleaned by treating with acetone and ethanol under sonication. Triplicates of all polished and non-polished samples with different grain sizes were subjected to magnetization of DM, 0.1T, 0.5T, and 1T, before seeding them with the bacteria. Controls were used in the form of untreated samples. Bacterial were grown in Tryptic Soy Broth (TSB). An actively growing bacterial suspension was seeded onto the stainless-steel discs into 24-well micro-titer plates and kept for incubation. After 24 hours of incubation, the stainless-steel discs were washed with Phosphate Buffer Saline (PBS) to remove the plankton bacteria and allow the sessile bacteria in the biofilm to remain. The degree of development of the bacterial biofilms on the stainless-steel discs were measured using spectrophotometric analysis. For this, the bacterial biofilm was removed from the stainless steel by sonication. The formation of biofilms was also determined by performing a biofilm staining method using Safranin. RESULTS SECTION: AFM results revealed a slight decrease in roughness by decreasing the grain size of the material. Moreover, the samples were segregated into two categories of polished and non-polished samples, in which polishing decreased roughness significantly. After careful analysis we found out that polished surfaces showed a higher degree for biofilm formation in comparison to the non-polished ones. We also observed that bacteria showed a higher rate for biofilm formation for the demagnetized samples, whereas 0.5T magnetization showed the least amount of biofilm formation. After 0.5T, there was no significant change in the rate of biofilm formation on the stainless-steel samples. Altogether, stainless steel samples containing 0.5 μm and less grainsize, and magnetized with 0.5 tesla and stronger magnets demonstrated the least degree of biofilm formation. DISCUSSION: In summary, the results demonstrate that controlling the grain size of medical grade stainless steel can control and mitigate bacterial responses on, and thus possibly infections of, orthopedic implants or other implantable devices. The research was funded by Komatsuseiki Kosakusho Co., Ltd (KSJ: Japan) SIGNIFICANCE/CLINICAL RELEVANCE: Orthopedic implants that more than 70% of them are made of metals (i.e., stainless steel, titanium, and cobalt-chromium alloys) are failing through loosening and breakage due to their limited mechanical properties. On the other hand, the risk of infection for these implants and its financial burden on our society is undeniable. We have seen that our uniformly nanograined stainless steel shows improved mechanical properties (i.e., higher stiffness, hardness, fatigue) as compared to conventional stainless steel along with the reduction of biofilm formation on its surface. These promising results made us to peruse the development of nanograined titanium and cobalt-chromium alloys for resolving the complications of orthopedic implants.more » « less
-
null (Ed.)Cyber-physical-social systems (CPSS) are physical devices with highly integrated functions of sensing, computing, communication and control, and are seamlessly embedded in human society. The levels of intelligence and functions that CPSS can perform rely on their extensive collaboration and information sharing through networks. In this paper, information diffusion within CPSS networks is studied. Information dynamics models are proposed to characterize the evolution of information processing and decision making capabilities of individual CPSS nodes. The data-driven statistical models are based on a mesoscale probabilistic graph model, where the individual nodes' sensing and computing functions are represented as the probabilities of correct predictions, whereas the communication functions are represented as the probabilities of mutual influences between nodes. A copula dynamics model is proposed to explicitly capture the information dependency among individuals with joint prediction probabilities and estimated from extremal probabilities. A topology-informed vector autoregression model is proposed to represent the mutual influence of prediction capabilities. A spatial-temporal hybrid Gaussian process regression model is also proposed to simultaneously capture correlations between nodes and temporal correlation in the time series.more » « less
-
null (Ed.)Survival data is often collected in medical applications from a heterogeneous population of patients. While in the past, popular survival models focused on modeling the average effect of the covariates on survival outcomes, rapidly advancing sensing and information technologies have provided opportunities to further model the heterogeneity of the population as well as the non-linearity of the survival risk. With this motivation, we propose a new semi-parametric Bayesian Survival Rule List model in this paper. Our model derives a rule-based decision-making approach, while within the regime defined by each rule, survival risk is modelled via a Gaussian process latent variable model. Markov Chain Monte Carlo with a nested Laplace approximation on the Gaussian process posterior is used to search over the posterior of the rule lists efficiently. The use of ordered rule lists enables us to model heterogeneity while keeping the model complexity in check. Performance evaluations on a synthetic heterogeneous survival dataset and a real world sepsis survival dataset demonstrate the effectiveness of our model.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1115/1.4045334
