Variability in product quality continues to pose a major barrier to the widespread application of additive manufacturing (AM) processes in production environment. Towards addressing this barrier, monitoring AM processes and measuring AM materials and parts has become increasingly commonplace, and increasingly precise, making a new wave of AM-related data available. This newfound data provides a valuable resource for gaining new insight to AM processes and decision making. Machine Learning (ML) provides an avenue to gain this insight by 1) learning fundamental knowledge about AM processes and 2) identifying predictive and actionable recommendations to optimize part quality and process design. This report presents a literature review of ML applications in AM. The review identifies areas in the AM lifecycle, including design, process plan, build, post process, and test and validation, that have been researched using ML. Furthermore, this report discusses the benefits of ML for AM, as well as existing hurdles currently limiting applications.

This paper describes Gaussian process regression (GPR) models presented in predictive model markup language (PMML). PMML is an extensible-markup-language (XML) -based standard language used to represent data-mining and predictive analytic models, as well as pre- and post-processed data. The previous PMML version, PMML 4.2, did not provide capabilities for representing probabilistic (stochastic) machine-learning algorithms that are widely used for constructing predictive models taking the associated uncertainties into consideration. The newly released PMML version 4.3, which includes the GPR model, provides new features: confidence bounds and distribution for the predictive estimations. Both features are needed to establish the foundation for uncertainty quantification analysis. Among various probabilistic machine-learning algorithms, GPR has been widely used for approximating a target function because of its capability of representing complex input and output relationships without predefining a set of basis functions, and predicting a target output with uncertainty quantification. GPR is being employed to various manufacturing data-analytics applications, which necessitates representing this model in a standardized form for easy and rapid employment. In this paper, we present a GPR model and its representation in PMML. Furthermore, we demonstrate a prototype using a real data set in the manufacturing domain.

Current ambulance designs are ergonomically inefficient and often times unsafe for practical treatment response to medical emergencies. Thus, the patient compartment of a moving ambulance is a hazardous working environment. As a consequence, emergency medical services (EMS) workers suffer fatalities and injuries that far exceed those of the average work place in the United States. To reduce injury and mortality rates in ambulances, the Department of Homeland Security Science and Technology Directorate has teamed with the National Institute of Standards and Technology, the National Institute for Occupational Safety and Health, and BMT Designers & Planners in a joint project to produce science-based ambulance patient compartment design standards. This project will develop new crash-safety design standards and improved user-design interface guidance for patient compartments that are safer for EMS personnel and patients, and facilitate improved patient care. The project team has been working with practitioners, EMS workers’ organizations, and manufacturers to solicit needs and requirements to address related issues. This paper presents an analysis of practitioners’ concerns, needs, and requirements for improved designs elicited through the web-based survey of ambulance design, held by the National Institute of Standards and Technology. This paper also introduces the survey, analyzes the survey results, and discusses recommendations for future ambulance patient compartments design.

This paper describes how modeling and simulation can play a major role in developing standards recommendations for patient compartment layout of automotive ambulances in the United States to improve performance and safety. Acquiring necessary information from relevant stakeholders is shown as a method that can be used to determine user design requirements. The requirements will in turn be used to develop design concepts taking into consideration human interface with the ambulance work environment. The modeling and simulation of clinical care activities in the ambulance can be used to evaluate the design concepts and determine those that would better meet safety and performance requirements.

The Symposium on Data Analytics for Advanced Manufacturing was held in conjunction with the