Search

Temperature reconstruction is vital for ensuring system reliability in electronic component design. However, current approaches struggle to effectively explore system information and physical relationships, thereby limiting their performance. This paper presents deep learning surrogate models for precise temperature field reconstruction, showcasing their effective discernment of system distribution laws. However, the scarcity of high-quality training data poses a significant challenge, often leading to issues like overfitting and compromised precision. To address this problem, the paper proposes an adaptive multi-source information fusion method (MFIF) for integrating physical information from various data sources in the frequency domain. By leveraging frequency domain analysis, a deeper understanding of underlying physical phenomena is achieved, facilitating effective integration of information. Furthermore, by utilizing deep surrogate models and high-quality training samples, the developed multi-source frequency fusion method enables the creation of a multi-source fusion driven deep learning method for temperature field reconstruction. The proposed method enhances the robustness, accuracy, and effectiveness of aircraft temperature field reconstruction in orbit. Experimental results demonstrate a substantial decrease in both noise and errors, while the Signal-to-Noise Ratio can be improved by up to more than 86%. [ABSTRACT FROM AUTHOR]

Oil productions can result in pore pressure drop in the reservoir, generating an increase in effective stress and leading to reservoir compaction. The compaction in the subsurface reservoir translates to the earth's surface, which is manifested as a loss of elevation (land subsidence), causing damages to oil production facilities and surface infrastructures. The Liaohe oilfield, located in Liaohe River Delta (LRD), northeast of China, is one of the most significant subsidence areas in China as a direct consequence of oil extraction from the reservoir. Previous studies carried out in this area assumed the oil production-induced displacement retrieved from Interferometric Synthetic Aperture Radar (InSAR) corresponds only to vertical deformation. In this work, for the first time, we proposed a method to retrieve the full three-dimensional (3D) displacement field over the oilfield. We retrieved the vertical and east-west displacement components by combining the multiple-geometry InSAR line-of-sight (LOS) observations and retrieved the north-south component based on the assumption of a physical relationship between the horizontal and vertical displacement. Two ascending and two descending datasets from Sentinel-1 satellite covering the area were processed by an InSAR time series analysis over the 2017 to 2021 period, providing consistent displacement rate maps and displacement time series in the LOS direction. Spatial local-scale land subsidence was found in several producing fields over the deltaic region, including Shuguang, Huanxiling, and Jinzhou oilfields. The 3D displacement decomposition was then conducted in Shuguang oilfield. The derived 3D displacement field exhibit a circular subsidence bowl with a maximum subsiding rate reaching 212 mm/year, accompanied by a centripetal pattern of horizontal displacements with maximum rates up to 50–60 mm/year moving towards the subsidence center. The retrieved 3D displacements are in good agreement with predictions from the geomechanical modeling by assuming a disk-shaped reservoir subject to a uniform reduction in pore fluid pressure. Finally, we show the importance of knowing both the vertical and horizontal displacement in characterizing the lateral boundary of the subsurface reservoir. [ABSTRACT FROM AUTHOR]

Temperature field prediction is of great importance in the thermal design of systems engineering, and building a surrogate model is an effective method for the task. Ensuring a high prediction performance for the surrogate models, especially deep learning models with high representational power and numerous parameters, typically requires a significant amount of labeled data. However, obtaining labeled data, particularly high-fidelity data can be prohibitively expensive. To solve this problem, this paper proposes a novel deep multi-fidelity modeling method for temperature field prediction, which takes advantage of low-fidelity data to boost performance with less high-fidelity data. First, a pithy pre-train and fine-tune paradigm is proposed for constructing the deep multi-fidelity model, which is straightforward and efficient, allowing for the effective utilization of information from various fidelity levels. Then, a physics-driven self-supervised learning method is proposed to learn the deep multi-fidelity model, which fully utilizes the physics characteristics of the heat transfer system and further reduces the dependence on large amounts of labeled low-fidelity data in the training process. Two diverse temperature field prediction problems are presented to validate the effectiveness of the proposed method. The results show that our approach can significantly improve the model's accuracy, reducing the required high-fidelity data for model construction. [ABSTRACT FROM AUTHOR]

This study examines the ability of the Beijing Climate Center Climate System Model (BCC_CSM) to predict the meridional pattern of summer precipitation over East Asia-Northwest Pacific (EA-NWP) and its East Asia-Pacific (EAP) teleconnection. The differences of summer precipitation modes of the empirical orthogonal function and the bias of atmospheric circulations over EA-NWP are analyzed to determine the reason for the precipitation prediction errors. Results indicate that the BCC_CSM could not reproduce the positive-negative-positive meridional tripole pattern from south to north that differs markedly from that observed over the last 20 years. This failure can be attributed to the bias of the BCC_CSM hindcasts of the summer EAP teleconnection and the low predictability of 500 hPa at the mid-high latitude lobe of the EAP. Meanwhile, the BCC_CSM hindcasts' deficiencies of atmospheric responses to SST anomalies over the Indonesia maritime continent (IMC) resulted in opposite and geographically shifted geopotential anomalies at 500 hPa as well as wind and vorticity anomalies at 850 hPa, rendering the BCC_CSM unable to correctly reproduce the EAP teleconnection pattern. Understanding these two problems will help further improve BCC_CSM's summer precipitation forecasting ability over EA-NWP. [ABSTRACT FROM AUTHOR]

Temperature monitoring over heat source components in engineering systems, such as the energy system, electronic equipments, becomes essential to guarantee the working performance of these components. However, prior methods, which mainly use the interpolate estimation to reconstruct the overall temperature field from limited monitoring points, require large amounts of temperature tensors for an accurate estimation. This may affect the availability and reliability of the system. To solve the problem, this work develops a novel reconstruction method which joints the deep reversible regression model and physics-informed unsupervised learning for temperature field reconstruction of heat-source systems (TFR-HSS). Firstly, we define the TFR-HSS mathematically, numerically model the system with discrete grids, and hence transform the task as an image-to-image regression problem. Then, this work develops the deep reversible regression model which can better learn physical information, especially over the area near the boundaries of the system. Finally, this work proposes the physics-informed reconstruction loss with the physical characteristics of the system and learns the deep model without labelled samples. Experimental studies have conducted over typical two-dimensional heat-source systems to validate the effectiveness of the proposed method. Under the proposed method, the mean average error of the constructed temperature field can achieve about 0.1K, 50% lower than other methods. Besides, the proposed method takes 5.2 ms per sample for inference which can provide real-time predictions. • This work defines temperature field reconstruction of heat-source systems (TFR-HSS) task. • This work provides the mathematical formulation as well as numerically modelling of TFRHSS task. • This work further proposes the reversible regression model which can better fit for TFR-HSS task. • This work develops physics-informed reconstruction loss, which can train the deep model without labelled samples. [ABSTRACT FROM AUTHOR]

Recently, surrogate models based on deep learning have attracted much attention for engineering analysis and optimization. Since constructing data pairs in most engineering problems is time-consuming, data acquisition is becoming the predictive capability bottleneck of most deep surrogate models, which also exist in surrogate for thermal analysis and design. In contrast with data-driven learning, enforcing the physical laws in building surrogates has emerged as a promising alternative to reduce the dependence on annotated data. This paper develops a physics-informed convolutional neural network (CNN) for the thermal simulation surrogate without labeled data. Firstly, we leverage the finite difference method to integrate heat conduction equation and loss function construction, guiding surrogate model training to minimize the violation of physical laws. Since the solution is sensitive to boundary conditions, we properly impose hard constraints by padding in the Dirichlet and Neumann boundaries. The proposed network can learn a mapping from heat source layout to the steady-state temperature field without labeled data, which equals solving an entire family of partial difference equations (PDEs). Moreover, the neural network architecture is well-designed to improve the prediction accuracy of the problem at hand, and pixel-level online hard example mining is proposed to overcome the imbalance of optimization difficulty in the computation domain, which is beneficial to the network training of physics-informed learning. The experiments demonstrate that the proposed method can provide comparable predictions with numerical methods and data-driven deep learning models. We also conduct various ablation studies to investigate the effectiveness of the proposed network components and training methods in this paper. Furthermore, the developed methods can be applied to other design and optimization applications which need to solve parameterized PDEs. [ABSTRACT FROM AUTHOR]

Estimating the full state of physical systems, including thermal and flow status, from sparse measurements of limited sensors is a critical technology for perception and control. Neural networks have been used in recent studies to reconstruct the global field in a supervised learning paradigm. However, these studies encounter two major challenges: the lack of interpretability of black-box models and performance bottleneck caused by network structure and parameter optimization. This paper proposes a hybrid method based on proper orthogonal decomposition (POD) and deep neural networks (DNNs) to further enhance the interpretability and accuracy of flow and heat field reconstruction. The key idea is to leverage the inherent data modes extracted by POD that capture essential features in physical fields, and formulate the reconstruction problem as finding an optimal linear combination of dominant POD modes. To reduce the error introduced by underfitting and model structure, this paper estimates the coefficients of POD modes by establishing and solving a linear optimization problem that minimizes the gap between the recovered field and the exact measurements, rather than employing regression models. However, the underdetermined issue cased by the sparse measurements restricts the optimization problem to obtain a proper solution. To alleviate this problem, this paper presents to utilize the powerful non-linear approximation ability of DNNs to produce a reference field as auxiliary observations, which combines exact measurements to jointly constrain the optimization problem solving. Finally, the global physical field is reconstructed by superposing dominant POD modes weighted with the solved coefficients. By combining with POD technology, the proposed method can also improve the performance of neural networks on reconstruction problems with large-scale and irregular domains. The experiments conducted on the fluid and thermal benchmarks demonstrate that the proposed method can significantly boost neural network reconstruction performance and outperform existing POD-based methods. • A hybrid method based on POD and deep neural networks is developed for flow and heat field reconstruction from sparse measurements. • The data modes extracted by POD are explicitly used to alleviate black-box problems of neural networks. • The field reconstruction problem is converted to a linear optimization jointly constrained by exact measurements and DNN predictions. • The underdetermined issues with sparse measurements can be addressed. [ABSTRACT FROM AUTHOR]

Perception of the full state is an essential technology to support the monitoring, analysis, and design of physical systems, one of whose challenges is to recover global field from sparse observations. Well-known for brilliant approximation ability, deep neural networks have been attractive to data-driven heat and flow field reconstruction studies for practical systems. However, limited by network structure, existing researches mostly learn the reconstruction mapping in finite-dimensional space that usually has poor transferability to the variable resolution of outputs. This paper extends the new paradigm of neural operators and proposes an end-to-end physical field reconstruction method with both excellent performance and mesh transferability named RecFNO. The proposed method aims to learn the mapping from sparse observations to flow and heat fields in infinite-dimensional space, contributing to a more powerful nonlinear fitting capacity and resolution-invariant characteristic. According to different usage scenarios, three types of embeddings are first developed to model the sparse observation inputs: MLP, mask, and Voronoi embedding. The MLP embedding is propitious to more sparse input, while the others benefit from spatial information preservation and perform better with the increase of observation data. Then, stacked Fourier layers are adopted to reconstruct physical field in Fourier space that regularizes the overall recovered field by Fourier modes superposition. Benefiting from the operator in infinite-dimensional space, the proposed method obtains remarkable accuracy and better resolution transferability among meshes. The experiments conducted on fluid mechanics and thermology problems show that the proposed method outperforms existing POD-based and CNN-based methods in most cases and has the capacity to achieve zero-shot super-resolution. • A resolution-invariant temperature and flow field reconstruction method named RecFNO is proposed. • Three types of embeddings for sparse observation are developed. • RecFNO can reconstruct the physical field in function space with excellent performance and resolution transferability. • The validity of the method is confirmed in numerical experiments and practical cases. [ABSTRACT FROM AUTHOR]

• Proposing physics-informed DCNN for HFI-SCB temperature field reconstruction. • Proposing Deep MC-QR method to quantify data uncertainty caused by noise. • Proposing HFI-SCB reliability analysis method based on interval multilevel BN. Temperature field reconstruction is essential for analyzing the reliability of a high-density functionally integrated satellite circuit board (HFI-SCB). As a representative deep learning model, the deep convolutional neural network (DCNN) is a powerful tool for reconstructing the HFI-SCB temperature field. However, DCNN needs a lot of labeled data to learn its parameters, which is contrary to the fact that actual satellite engineering can only acquire noisy unlabeled data. Thus, this paper proposes an unsupervised method, i.e., the physics-informed deep Monte Carlo quantile regression method, for reconstructing the HFI-SCB temperature field and quantifying the data uncertainty caused by sensor noise. The proposed method combines a DCNN with known physics knowledge to reconstruct an accurate HFI-SCB temperature field using only monitoring point temperatures. Besides, the proposed method can quantify the data uncertainty by the Monte Carlo quantile regression. Based on the reconstructed temperature field and the quantified data uncertainty, this paper builds an interval multilevel Bayesian Network to analyze the HFI-SCB reliability. Two case studies are used to validate the proposed method. [ABSTRACT FROM AUTHOR]

Physical field reconstruction is highly desirable for the measurement and control of engineering systems. The reconstruction of the temperature field from limited observation plays a crucial role in thermal management for electronic equipment. Deep learning has been employed in physical field reconstruction, whereas the accurate estimation for the regions with large gradients is still difficult. To solve the problem, we propose a novel deep learning method based on partition modeling to accurately reconstruct the temperature field of electronic equipment from limited observation. Firstly, the temperature field reconstruction (TFR) task of electronic equipment is modeled mathematically and transformed as an image-to-image regression problem. Then a partition modeling framework consisting of an adaptive UNet and a shallow multilayer perceptron (MLP) is developed to establish the mapping from the observation to the temperature field. The adaptive UNet is utilized to reconstruct the whole temperature field, while the MLP is designed to predict the patches with large temperature gradients. Numerical case studies employing finite element simulation data are conducted to demonstrate the accuracy of the proposed method. Furthermore, the generalization is evaluated by investigating cases under different heat source layouts, power intensities, and observation point locations. The maximum absolute errors of the reconstructed temperature field are less than 1 K under the partition modeling approach. • Deep learning is used to reconstruct temperature fields accurately and efficiently. • A partition modeling framework consisting of an UNet and an MLP is developed. • Significantly improve the accuracy of regions with large gradients by nearly 50%. • The mean and maximum absolute errors are less than 0.2 K and 1 K, respectively. [ABSTRACT FROM AUTHOR]

Temperature field inversion of heat-source systems (TFI-HSS) with limited observations is essential to monitor the system health. Although some methods such as interpolation have been proposed to solve TFI-HSS, those existing methods ignore correlations between data constraints and physics constraints, causing the low precision. In this work, we develop a physics-informed neural network-based temperature field inversion (PINN-TFI) method to solve the TFI-HSS task and a coefficient matrix condition number based position selection of observations (CMCN-PSO) method to select optimal positions of noisy observations. For the TFI-HSS task, the PINN-TFI method encodes constrain terms into the loss function and thus the task is transformed into an optimization problem of minimizing the loss function. In addition, we have found that noise significantly affect reconstruction performances of the PINN-TFI method. To alleviate the effect of noises in observations, we propose the CMCN-PSO method to find optimal positions, where the condition number of observations is used to evaluate positions. The results demonstrate that the PINN-TFI method can significantly improve prediction precisions and the CMCN-PSO method can find good positions to improve the robustness of the PINN-TFI method. [ABSTRACT FROM AUTHOR]

[Display omitted] • It is a brand new and practically accessible idea of treating waste (NO x) with waste (red mud). • The sesbania powder successfully avoided the hydraulicity and pulverization of the red mud. • Shaped red mud catalysts exhibited T 90 active window of 275–475 °C. • Sufficient Brönsted acids and oxygen vacancies were obtained with excellent ammonia adsorption ability and reducibility. Recently, we proposed an efficient pretreatment method for waste red mud (RM) to be utilized as an SCR catalyst. However, in terms of the shaping process, RM's hydraulicity and easily pulverization always cause the loss of surface areas and active species, which limits its application. In this study, we prepared shaped RM catalysts using the sesbania powder (sp), guar gum (gg), and carboxymethylcellulose sodium (cs) to investigate the impact of binders on the RM catalysts. The results exhibited that the RM-15sp-550 showed the highest activity with T 90 (the reaction temperature with NO x conversions higher than 90%) active window of 325–450 °C. The gg and cs strongly inhibited the surface reducibility and NH 3 adsorption, which was caused by the decrease of the Fe(III), absorbed oxygen, and acid sites (especially the Brönsted acid sites). The reactions between adsorbed ammonia species on the Brönsted acid sites and gaseous NO were restricted on the RM-15gg-500 and RM-15cs-500. Compared with the RM-15gg-500 and RM-15cs-500, the RM-15sp-500 exhibited more accumulated pores. Raman experiments proposed that more oxygen vacancies formed on the RM-15sp-500 and NH 3 were selectively chemisorbed on the FeTiO 3 during the NH 3 presorbing process, which benefited SCR reaction. The strong viscosity at low temperatures and low decompose temperature of the sp minimized its impact on the RM catalyst. This made it an excellent binder for industrial RM catalyst. The cost analysis showed that the price of the RM catalyst was 67% lower than that of commercial V-W-Ti catalyst, and the use of RM catalyst can also alleviate the RM accumulation issue. [ABSTRACT FROM AUTHOR]

The ever-increasing functional density and complexity of the heat source system, the harsh chip cooling environment, as well as the cost reduction measures that require less sensor involvement are increasingly driving the need to develop new approaches for temperature monitoring and predicting. Most current researches investigate the temperature field reconstruction of the whole system. However, the reconstruction is not necessary or practical in some cases for computing consumption and unprocurable structure. The temperature prediction of the points of interest (PoIs) like the heat-sensitive area in the electronics is essentially important for function maintenance. Thus, a complete solution is proposed based on the graph convolutional networks (GCN) in this paper including the dimensional alignment, graph modeling and corresponding GCN construction. Moreover, various methods have been explored for edge modeling and node embedding obtained by Node2Vec has been integrated for better graph representation. After model training, the real-time temperature prediction of PoIs can be realized according to the corresponding temperature of monitoring points (MoPs) by the GCN. The results of experiments show that this method approach well prediction that the mean absolute error is less than 0.01K under the condition possessing diverse MoPs and PoIs. Moreover, the comparison experiments with the baseline methods further verify the validity of this GCN-based solution. [ABSTRACT FROM AUTHOR]

Critical heat flux (CHF) experiments were conducted in a uniformly heated horizontal helically-coiled tube to investigate the CHF characteristics at near the critical pressures with R134a as the working fluid. The experiments were performed over a wide range of parameters: pressure from 2.85 to 4.03 MPa, i.e., reduced pressures ( P r) ranging from 0.70 to 0.99, mass flux from 250 to 2100 kg m −2 s −1 , inlet subcooling from 45 to 160 kJ kg −1 and heat flux from 20 to 450 kW m −2 . Two types of CHF phenomenon which are dry-out (DO) and departure from nucleate boiling (DNB) have occurred under the experimental conditions. The DO happens at the lower pressures while the DNB happens at the higher pressures. The wall temperature shows a very different characteristic for the two types of CHF. Under the DO conditions, wall temperature gets a sudden rise firstly at the inner-side of the outlet cross-section and temperature at the other side remains on a lower level, while under the DNB conditions, wall temperature around the outlet cross-section jumps almost simultaneously. When the pressure is very close to the critical point, there is a constant pressure region where the wall temperature rises gently and the CHF no longer exists. The effects of the mass flux and inlet subcooling on CHF have also been discussed. Based on the experiment, a correlation applied for the pressure region close to the critical pressure was proposed to estimate the CHF in the horizontal helically-coiled tube. [ABSTRACT FROM AUTHOR]

Red mud, as industrial solid waste, causes severe environmental problems such as soil alkalization and groundwater pollution. In this work, we researched and developed the red mud as a selective catalytic reduction catalyst for NO x removal with NH 3 (NH 3 -SCR). After selective dissolution and specific heat treatment, different Ce precursors were used to modifying its physical and chemical properties. The results showed that Ce(NO 3) 3 and Ce(NH 4) 2 (NO 3) 6 modified red mud (RM cn and RM can) had excellent SCR performance below 300 °C. Ce(SO 4) 2 modified red mud (RM cs) showed relatively low NO x conversions at 200–300 °C. The redox property was improved with the Ce(NO 3) 3 and Ce(NH 4) 2 (NO 3) 6 , while depressed with the Ce(SO 4) 2. Agglomerates generated on the RM cs and blocked the accumulated pores due to the formation of Ce 2 (SO 4) 3. The surface acidity of RM cs enhanced with increased adsorption for ammonia. However, these new adsorbed ammonia species, highly related to the sulfate from the Ce 2 (SO 4) 3 , were inert and did not react with the adsorbed or gaseous NO species at 200–300 °C. The abundant surface lattice oxygen from CeO 2 microcrystals improved the catalytic oxidation capacity of the RM cn and RM can. • Red mud, as industrial waste, was efficiently recovered and used as SCR catalysts. • Cerium modified red mud catalysts exhibited NO x conversion above 90% at 200–300 °C. • The surface lattice oxygen and Fe–O–Ce bridges enhanced the reducibility. [ABSTRACT FROM AUTHOR]