Fused deposition modeling (FDM) is one of the most popular additive manufacturing technologies for fabricating prototypes with complex geometry and different materials. However, current commercial FDM machines have the limitations in process reliability and product quality. In order to overcome these limitations and increase the levels of machine intelligence and automation, machine conditions need to be monitored more closely as in closedloop control systems. In this study, a new method for in situ monitoring of FDM machine conditions is proposed, where acoustic emission (AE) technique is applied. The proposed method allows for the identification of both normal and abnormal states of the machine conditions. The time-domain features of AE hits are used as the indicators. Support vector machines with the radial basis function kernel are applied for state identification. Experimental results show that this new method can potentially serve as a nonintrusive diagnostic and prognostic tool for FDM machine maintenance and process control.

No abstract

No abstract

No abstract

Training machine learning tools such as neural networks require the availability of sizable data, which can be difficult for engineering and scientific applications where experiments or simulations are expensive. In this work, a novel multi-fidelity physics-constrained neural network is proposed to reduce the required amount of training data, where physical knowledge is applied to constrain neural networks, and multi-fidelity networks are constructed to improve training efficiency. A low-cost low-fidelity physics-constrained neural network is used as the baseline model, whereas a limited amount of data from a high-fidelity physics-constrained neural network is used to train a second neural network to predict the difference between the two models. The proposed framework is demonstrated with two-dimensional heat transfer, phase transition, and dendritic growth problems, which are fundamental in materials modeling. Physics is described by partial differential equations. With the same set of training data, the prediction error of physics-constrained neural network can be one order of magnitude lower than that of the classical artificial neural network without physical constraints. The accuracy of the prediction is comparable to those from direct numerical solutions of equations.

The diagnosis of complicated fault severity problems in rotating machinery systems is an important issue that affects the productivity and quality of manufacturing processes and industrial applications. However, it usually suffers from several deficiencies. (1) A considerable degree of prior knowledge and expertise is required to not only extract and select specific features from raw sensor signals, and but also choose a suitable fusion for sensor information. (2) Traditional artificial neural networks with shallow architectures are usually adopted and they have a limited ability to learn the complex and variable operating conditions. In multi-sensor-based diagnosis applications in particular, massive high-dimensional and high-volume raw sensor signals need to be processed. In this paper, an integrated multi-sensor fusion-based deep feature learning (IMSFDFL) approach is developed to identify the fault severity in rotating machinery processes. First, traditional statistics and energy spectrum features are extracted from multiple sensors with multiple channels and combined. Then, a fused feature vector is constructed from all of the acquisition channels. Further, deep feature learning with stacked auto-encoders is used to obtain the deep features. Finally, the traditional softmax model is applied to identify the fault severity. The effectiveness of the proposed IMSFDFL approach is primarily verified by a one-stage gearbox experimental platform that uses several accelerometers under different operating conditions. This approach can identify fault severity more effectively than the traditional approaches.

No abstract

The southern Tibetan Plateau (STP) is the region in which water vapor passes from South Asia into the Tibetan Plateau (TP). The accuracy of precipitable water vapor (PWV) modeling for this region depends strongly on the quality of the available estimates of water vapor advection and the parameterization of land evaporation models. While climate simulation is frequently improved by assimilating relevant satellite and reanalysis products, this requires an understanding of the accuracy of these products. In this study, PWV data from MODIS infrared and near-infrared measurements, AIRS Level-2 and Level-3, MERRA, ERA-Interim, JRA-55, and NCEP final reanalysis (NCEP-Final) are evaluated against ground-based GPS measurements at nine stations over the STP, which covers the summer monsoon season from 2007 to 2013. The MODIS infrared product is shown to underestimate water vapor levels by more than 20% (1.84 mm), while the MODIS near-infrared product overestimates them by over 40% (3.52 mm). The AIRS PWV product appears to be most useful for constructing high-resolution and high-quality PWV datasets over the TP; particularly the AIRS Level-2 product has a relatively low bias (0.48 mm) and RMSE (1.83 mm) and correlates strongly with the GPS measurements ( R = 0.90). The four reanalysis datasets exhibit similar performance in terms of their correlation coefficients ( R = 0.87–0.90), bias (0.72–1.49 mm), and RMSE (2.19–2.35 mm). The key finding is that all the reanalyses have positive biases along the PWV seasonal cycle, which is linked to the well-known wet bias over the TP of current climate models.