An official website of the United States government
Predicting machined surface roughness is critical for estimating a part’s performance characteristics such as susceptibility to fatigue and corrosion. Prior studies have indicated that power consumed at the tool-chip interface may represent an indicator for the surface integrity of the machining process. However, no quantita-tive association has been reported between the machining power and surface roughness due to a lack of data to develop predictive models. This paper presents a data synthesis method to address this gap. Specifically, a conditional generative adversarial network (CGAN) is developed to synthesize power signals associated with varying process parameter combinations. The quality of the synthesized signals is evaluated against experimentally measured power signals by examining the consistency in: 1) the spatial pattern of the signals induced by the cutting process as shown in the frequency domain, and 2) the temporal pattern as shown in the clustering of the synthesized and measured signals corresponding to the same parameter combination. The synthesized signals are then used to augment the measured signals and develop a convolutional neural network (CNN) for predicting the machined surface roughness. Experiments performed using H13 tool steel have shown that data augmentation by CGAN has effectively reduced the error of the surface roughness prediction from 58 %, when no synthetic data is used for CNN training, to 9.1 % when 250 synthetic samples are used. The results demonstrate the effectiveness of CGAN as a data augmentation method and CNN for mapping machining power to surface roughness.
more »
« less
This content will become publicly available on June 1, 2026
Surface roughness prediction in machining using two-stage domain-incremental learning with input dimensionality expansion
Accurate quantification of machined surface roughness is crucial to the characterization of part performance measures, including aerodynamics and biocompatibility. Given this cruciality, there exists a need for predictive metrology models which can predict the surface roughness before a part leaves a machine to reduce metrologyinduced bottlenecks and improve production planning efficiency under emergent production paradigms, e.g., Industry 4.0. Current predictive metrology approaches in machining generally train machine learning models on all available input features at once. However, this approach yields a high number of free parameters during all states of training, possibly leading to suboptimal prediction results because of the complexity of simultaneously optimizing all parameters at once. In addition, previous machine learning-enabled surface roughness prediction studies have used limited test dataset sizes, which reduces the reliability and robustness of the reported results. To address these limitations, this study proposes a two-stage model training approach based on domainincremental learning, wherein a second stage of training is performed using an expanded input domain. The proposed method is evaluated on a 3,000-element experimentally collected testing dataset of machined H13 tool steel surfaces, where it achieves 16.3 % roughness prediction error compared to the 29.5 % error of the conventional single-stage training approach, indicating the suitability of the two-stage training method for reducing surface roughness prediction error.
more »
« less
- PAR ID:
- 10618651
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Journal of Manufacturing Systems
- Volume:
- 80
- Issue:
- C
- ISSN:
- 0278-6125
- Page Range / eLocation ID:
- 503 to 510
- Subject(s) / Keyword(s):
- Surface roughness domain-incremental learning input expansion predictive metrology machining
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Laser powder bed fusion (PBF‐LB) is an additive manufacturing (AM) technology for producing complex geometry parts. However, the high cost of post‐processing coarse as‐built surfaces drives the need to control surface roughness during fabrication. Prior studies have evaluated the relationship between process parameters and as‐built surface roughness, but they rely on forward models using trial‐and‐error, regression, and data‐driven methods based only on areal surface roughness parameters that neglect spatial surface characteristics. In contrast, this study introduces, for the first time, an inverse data‐centric framework that leverages machine learning algorithms and an experimental dataset of Inconel 718 as‐built surfaces to predict the PBF‐LB process parameters required to achieve a desired as‐built roughness. This inverse model shows a prediction accuracy of ≈80%, compared to 90% for the corresponding forward model. Additionally, it incorporates deterministic surface roughness parameters, which capture both height and spatial information, and significantly improves prediction accuracy compared to only using areal parameters. The inverse model provides a digital tool to process engineers that enables control of surface roughness by tailoring process parameters. Hence, it establishes a foundation for integrating surface roughness control into the digital thread of AM, thereby reducing the need for post‐processing and improving process efficiency.more » « less
-
This paper introduces a new digital integration that combines edge diffractometry with convolutional neural networks (CNN) for via metrology and inspection. The beam propagation method (BMP) was used to simulate the interferogram generated by edge diffractometry to characterize via edge roughness (VER). A comprehensive database was established to link different fringe patterns to VER for CNN training. The well-trained CNN-based methodology provided a fast and accurate assessment of VER, with a root mean squared error (RMSE) of 0.073 and an average mean absolute deviation ratio (MADR) of 2.274%. In addition, the proposed digital approach was compared to the multilayer perceptron machine (MLP) in terms of computational efficiency and predictive accuracy. The proposed digital integration greatly improved the accuracy and speed of VER measurement, characterization, and quantification, potentially enhancing device yield and reliability. The successful application of this digital approach could open up possibilities for various types of via or pattern metrology.more » « less
-
Previous literature shows that deep learning is an effective tool to decode the motor intent from neural signals obtained from different parts of the nervous system. However, deep neural networks are often computationally complex and not feasible to work in real-time. Here we investigate different approaches' advantages and disadvantages to enhance the deep learning-based motor decoding paradigm's efficiency and inform its future implementation in real-time. Our data are recorded from the amputee's residual peripheral nerves. While the primary analysis is offline, the nerve data is cut using a sliding window to create a “pseudo-online” dataset that resembles the conditions in a real-time paradigm. First, a comprehensive collection of feature extraction techniques is applied to reduce the input data dimensionality, which later helps substantially lower the motor decoder's complexity, making it feasible for translation to a real-time paradigm. Next, we investigate two different strategies for deploying deep learning models: a one-step (1S) approach when big input data are available and a two-step (2S) when input data are limited. This research predicts five individual finger movements and four combinations of the fingers. The 1S approach using a recurrent neural network (RNN) to concurrently predict all fingers' trajectories generally gives better prediction results than all the machine learning algorithms that do the same task. This result reaffirms that deep learning is more advantageous than classic machine learning methods for handling a large dataset. However, when training on a smaller input data set in the 2S approach, which includes a classification stage to identify active fingers before predicting their trajectories, machine learning techniques offer a simpler implementation while ensuring comparably good decoding outcomes to the deep learning ones. In the classification step, either machine learning or deep learning models achieve the accuracy and F1 score of 0.99. Thanks to the classification step, in the regression step, both types of models result in a comparable mean squared error (MSE) and variance accounted for (VAF) scores as those of the 1S approach. Our study outlines the trade-offs to inform the future implementation of real-time, low-latency, and high accuracy deep learning-based motor decoder for clinical applications.more » « less
-
During machining, kinetic energy is imparted to a workpiece to remove material. The integrity of the machined surface, which depends on the energy transfer, affects the quality and performance of the product, therefore needs to be quantified. Prior studies have indicated the potential of using machining power, or the power consumption at the tool-chip interface, as a process signature for predicting machined surface integrity. However, direct measurement of machining power is constrained by the availability of special equipment and the associated cost. To address this gap, this paper presents a machine learning-based method for machining power prediction through multi-sensor fusion and sequence-to-sequence translation from acoustic and vibration signals, which represent portions of the in-situ kinetic energy dissipation, to the machining power signal as a process signature. Specifically, a neural network architecture is developed to separately translate the acoustic and vibration signals to corresponding machining power signals. The two predicted power signals are subsequently fused to arrive at a unified power signal prediction. To check for spurious decision logic, the sensor fusion model is interpreted using integrated gradients to reveal temporal regions of the input data which have the most influence on the machining power prediction accuracy of the fusion model. Systematic cutting experiments performed on a lathe using 1018 steel have shown that the developed sensor fusion method for process signature prediction can successfully map machine acoustics to power consumption with 5.6% error, tool vibration to power consumption with 8.2% error, and acoustics and vibration, jointly, to power with 2.5% error. Model parameter interpretation reveals that the vibration signal is more influential on the machining power prediction result than the acoustic signal, but that overall model accuracy is diminished if only the vibration signal is used.more » « less
