In this paper, the design and performance differences between Relational Database Management Systems (RDBMS) and NoSQL Database Systems are examined, with attention to their applicability for real-world Internet of Things for manufacturing (IoTfM) data. While previous work has extensively compared SQL and NoSQL for both generalized and IoT uses, this work specifically examines the tradeoffs and performance differences for manufacturing applications by using a high-fidelity data set collected from a large US manufacturing firm. Growing an IoT system beyond the pilot stage requires scalable data storage; this work seeks to determine the impact of selected database systems on data write performance at scale. Payload size and message frequency were used as the primary characteristics to maintain model fidelity in simulated clients. As the number of simulated asset clients grow, the data write latency was calculated to determine how both database systems’ performance were affected. To isolate the RDBMS and NoSQL differences, a cloud environment was created using Amazon Web Services (AWS) with two identical data ingestion pipelines: writing data to an RDMBS (1) using AWS Aurora MySQL, and (2) using AWS DynamoDB NoSQL. The findings may provide guidance for further experimentation in large-scale manufacturing IoT implementations.

Directed Energy Deposition (DED) is an additive manufacturing technique in which a heat source is used to generate a small pool of molten material while powder feedstock is fed into the melt pool to create tracks of raised material on the surface of a part. Given the appropriate process parameters for the chosen material system and process conditions, fully dense complex geometric features are able to be constructed. In order to generate a high quality clad, two main criteria must be met: sufficient bonding with the substrate with minimized dilution of the clad by the base material and minimal porosity. Track shape is a key indicator in determining the quality of the process. This paper evaluates the influence of several of the key processing parameters — laser power, scanning speed, and powder mass flowrate — on single-clad track morphology. An analysis of variance (ANOVA) is performed to evaluate the significance of the main input parameters and the interactions between multiple parameters. A second-order polynomial model is then fit to the data to allow for predictive modelling of track shape based on a set of inputs. Finally, a multi-criteria cost function is generated, and sequential quadratic programming is performed to solve the objective function. Through these operations, the correct combination of processing parameters can be selected in order to generate a cladded track with desirable geometric traits.

Hybrid manufacturing machine tools have the potential to be a disruptive technology as they can leverage the benefits of both additive and subtractive manufacturing by incorporating both processes on the same machine while limiting the downsides of the individual processes. Since these machines use two very disparate manufacturing processes and hybrid manufacturing is an emerging technology, it will be useful to monitor data coming from the machine and apply it to improve the manufacturing process, the operation of the machine, and to integrate the machine into the larger digital framework of Industrial Internet of Things (IoT). The present work discusses IoT devices that would be beneficial to add to a hybrid machine tool as well as applications for those devices. The proposed methods discussed in this work have not been experimentally implemented on a hybrid machine tool and so there are no performance data available yet. The hybrid machine tool used as a basis to generate these IoT applications is the Mazak VC-500A/5x AM Hot Wire Deposition, which is a 5-axis machine tool incorporated with a wire feedstock 4kW laser deposition system. Methodologies and applications will be outlined for machine health and process monitoring. Other areas covered include process benchmarking, secure networking options for the proposed IoT framework, and hybrid process improvement. Limitations of these methods and future work for new sensor devices and application areas is also discussed.

Monitoring of the health of water-based coolant used for machining requires measurement of various parameters of the coolant, including refractive index, temperature, pH, and turbidity. One of the primary parameters that is used to determine the concentration of the coolant is the refractive index, which is typically measured manually by an operator at regular intervals during machine operation. This paper describes the conceptualization and preliminary design of a coolant health monitoring system that will automatically measure the refractive index of the coolant and will digitize the resulting measurement for communication to a factory supervisory control and data acquisition (SCADA) system. To enable rapid integration into a factory’s network architecture, the coolant concentration measurement will be transmitted by the monitoring system using the MTConnect format. Having an MTConnect-enabled sensor will allow the data to be remotely aggregated and compared to other machine data to help give a better understanding of overall machine health. The economical approach to its design allows the coolant health monitor to be realizable for both small manufacturing enterprises (SMEs) and large manufacturers alike. This widespread implementation will further benefit industry’s movement toward Internet-of-Things (IoT)-equipped manufacturing facilities.

Computer-aided manufacturing (CAM) software allows for the generation of toolpaths for computer numerical control (CNC) machine tools and enables the creation of sophisticated parts that would not otherwise be possible with conventional manual machining methods. Voxel-based CAM is a recent approach to toolpath planning that enables creation of paths for parts that would be difficult to create with traditional CAM software. However, the use of voxel-based CAM necessitates the presence of powerful hardware (specifically, graphics processing units) in order to perform the necessary computations for creating toolpaths. The concepts of virtualization and desktop-as-a-service offer a promising solution to this challenge, as they allow for many users to access computer hardware that is hosted on a single server. This work investigates the performance impact caused by multiple simultaneous users on voxel-based CAM deployed in a virtualized environment. The implementation of a Python application for multi-user simulation on the virtualized platform is described and timing results gathered from a sequence of simulations are presented and analyzed as the number of users is varied. The results from these simulations demonstrate consistent operational times for a low number of simultaneous users before a period of high performance variation due to resource sharing.

In the present study, a voxel based model for the interaction between cutting teeth of an arbitrary end mill geometry and a workpiece is presented. In this framework, the workpiece geometry is modeled using a voxelized representation that is dynamically updated as material is locally removed by each tooth of the cutting tool. A ray casting approach is used to mimic the process of the rake face of a tool moving through the workpiece material and to calculate the undeformed chip thickness and its variation in time. The resulting voxel based model framework was validated by comparison of predictions with experimentally measured milling forces. The results demonstrate the model’s ability to accurately simulate the interaction of cutting teeth with the bulk material of the workpiece. Implications of this new voxel based model framework are briefly discussed in terms of utility for predicting local surface finish and computational scalability of complex cutting configurations.

The amount of data that can be gathered from a machining process is often misunderstood, and even if these data are collected, they are frequently underutilized. Intelligent uses of data collected from a manufacturing operation can lead to increased productivity and lower costs. While some large-scale manufacturers have developed custom solutions for data collection from their machine tools, small- and medium-size enterprises need efficient and easily deployable methods for data collection and analysis. This paper presents three broad solutions to data collection from machine tools, all of which rely on the open-source and royalty-free MTConnect protocol: the first is a machine monitoring dashboard based on Microsoft Excel; the second is an open source solution using Python and MTConnect; and the third is a cloud-based system using Google Sheets. Time studies are performed on these systems to determine their capability to gather near real-time data from a machining process.

Engineering students are often unaware of manufacturing challenges introduced during the design process. Students tend to design parts that are either very difficult or impossible to manufacture because they are unaware of the intricacies and limitations of the manufacturing processes available. Design for manufacturability (DFM) education must be improved to help address this issue. This work discusses a vision for the implementation of a rapid method for facilitating DFM education in terms of subtractive and additive manufacturing processes. The goal is to teach students about how their designs impact the ease and cost of manufacturing, in addition to giving them knowledge and confidence to move fluidly between additive and subtractive manufacturing mindsets. For subtractive manufacturing, this is accomplished through a high-performance-computing accelerated and parallelized trajectory planning software package that enables students to visualize the subtractive manufacturability of the parts they design as rapidly as they get feedback when using additive manufacturing processes. Implementation of the subtractive manufacturability analysis tool in a sophomore-level design class is presented, along with the assessment of the students’ conceptual manufacturing-related understanding.

Laser powder-bed fusion (L-PBF) is an additive manufacturing (AM) process that enables fabrication of functional metal parts with near-net-shape geometries. The drawback to L-PBF is its lack of dimensional precision and accuracy. The efficiency of powder fusion process in powder-bed AM processes is highly affected by process errors, powder irregularities as well as geometric factors. Formation of defects such as lack of fusion and over-fusion due to the aforementioned factors causes dimensional errors that significantly damage the precision. This paper addresses the development of an automated in-situ inspection system for powder-bed additive manufacturing processes based on machine vision. The results of the in-situ automated inspection of dimensional accuracy allows for early identification of faulty parts or alternatively in-situ correction of geometric errors by taking appropriate corrective actions. In this inspection system, 2D optical images captured from each layer of the AM part during the build are analyzed and the geometric errors and defects impairing the dimensional accuracy are detected in each layer. To successfully detect geometric errors, fused geometric objects must be detected in the powder layer. Image processing algorithms are effectively designed to detect the geometric objects from images of low contrast captured during the build inside the chamber. The developed algorithms are implemented to a large number of test images and their performance and precision are evaluated quantitatively. The failure probabilities for the algorithms are also determined statistically.

Over the past few decades, both small- and medium-sized manufacturers as well as large original equipment manufacturers (OEMs) have been faced with an increasing need for low cost and scalable intelligent manufacturing machines. Capabilities are needed for collecting and processing large volumes of real-time data generated from manufacturing machines and processes as well as for diagnosing the root cause of identified defects, predicting their progression, and forecasting maintenance actions proactively to minimize unexpected machine down times. Although cloud computing enables ubiquitous and instant remote access to scalable information and communication technology (ICT) infrastructures and high volume data storage, it has limitations in latency-sensitive applications such as high performance computing and real-time stream analytics. The emergence of fog computing, Internet of Things (IoT), and cyber-physical systems (CPS) represent radical changes in the way sensing systems, along with ICT infrastructures, collect and analyze large volumes of real-time data streams in geographically distributed environments. Ultimately, such technological approaches enable machines to function as an agent that is capable of intelligent behaviors such as automatic fault and failure detection, self-diagnosis, and preventative maintenance scheduling. The objective of this research is to introduce a fog-enabled architecture that consists of smart sensor networks, communication protocols, parallel machine learning software, and private and public clouds. The fog-enabled architecture will have the potential to enable large-scale, geographically distributed online machine and process monitoring, diagnosis, and prognosis that require low latency and high bandwidth in the context of data-driven cyber-manufacturing systems.

Laser powder-bed fusion (L-PBF) is an additive manufacturing (AM) process that enables fabrication of functional metal parts with near-net-shape geometries. The drawback to L-PBF is its lack of precision as well as the formation of defects due to process randomness and irregularities associated with laser powder fusion. Over the past two decades much research has been conducted to control laser powder fusion in order to provide parts of higher quality. This paper addresses online quality monitoring in AM by in-situ automated visual inspection of each layer which is aimed to geometric objects and defects from high-resolution visual images. A scheme for online defect detection system is presented that consists of three levels of processing: low-level, intermediate-level, and high-level processing. Each level is described and appropriately divided to several stages, when insightful. Techniques that are feasible in each level for successful defect detection and classification are identified and described. Requirements and specifications of the measurement data to achieve desired performance of the online defect detection system are stated. Image processing algorithms are developed for first level of processing and implemented for segmentation of geometric objects. Due to the large variation of intensities within the powder region and fused regions, and also the non-multi-modal nature of the image, the basic segmentation algorithms such as thresholding do not produce appropriate results. In this work, morphological operations are effectively designed and implemented following thresholding to achieve the desired object segmentation. Examples of implementations are given. The paper provides the results of object segmentation which is the initial stage of development of an in-situ automated visual inspection for L-PBF process.