Search for: All records

Fused deposition modeling (FDM) is one of the widely used additive manufacturing (AM) processes but shares major shortcomings typical due to its layer-by-layer fabrication. These challenges (poor surface finishes, presence of pores, inconsistent mechanical properties, etc.) have been attributed to FDM input process parameters, machine parameters, and material properties. Deep learning, a type of machine learning algorithm has proven to help reveal complex and nonlinear input-output relationships without the need for the underlying physics. This research explores the power of multilayer perceptron deep learning algorithm to create a prediction model for critical input process parameters (layer thickness, extrusion temperature, build temperature, build orientation, and print speed) to predict three functional output parameters (dimension accuracy, porosity, and tensile strength) of FDM printed part. A fractional factorial design of experiment was performed and replicated three times per run (n=3). The number of neurons for the hidden layers, learning rate, and epoch were varied. The computational run time, loss function, and root mean square error (RMSE) were used to select the best prediction model for each FDM output parameter. The findings of this work are being extended to online monitoring and real-time control of the AM process enabling an AM digital twin. 

Fused deposition modeling (FDM) is one of the widely used additive manufacturing (AM) processes but shares major shortcomings typical due to its layer-by-layer fabrication. These challenges (poor surface finishes, presence of pores, inconsistent mechanical properties, etc.) have been attributed to FDM input process parameters, machine parameters, and material properties. Deep learning, a type of machine learning algorithm has proven to help reveal complex and nonlinear input-output relationships without the need for the underlying physics. This research explores the power of multilayer perceptron deep learning algorithm to create a prediction model for critical input process parameters (layer thickness, extrusion temperature, build temperature, build orientation, and print speed) to predict three functional output parameters (dimension accuracy, porosity, and tensile strength) of FDM printed part. A fractional factorial design of experiment was performed and replicated three times per run (n=3). The number of neurons for the hidden layers, learning rate, and epoch were varied. The computational run time, loss function, and root mean square error (RMSE) were used to select the best prediction model for each FDM output parameter. The findings of this work are being extended to online monitoring and real-time control of the AM process enabling an AM digital twin. 

Work-related musculoskeletal disorders contribute to significant loss in productivity and higher costs for employers. This research utilizes body-worn motion and hand-worn force sensors to provide non-intrusive and continuous recognition of tasks, estimate force exertion, and evaluate if operators are working in safe ergonomic ranges. Work-related motions such as lifting, carrying, pulling, and pushing are measured with varied loads up to 10 kg, and then recognized performed using the IBM Watson cloud service platform. The experiments use sequential and quasi-static postures and mimic those commonly found in an automotive assembly environment. Classification performance included generating 70 input features based on 6 motion and 4 force inputs and three of the resulting classifier had a greater than 90% accuracy in simultaneously classifying both the weight being carried and the task being completed. Future work includes measuring non-quasi-static motions and integrating additional sensors, such as those from smart tooling, which tracks tool position and orientation, to provide a continuous and unobtrusive evaluation of worker exertion and risk of musculoskeletal disorder.