Search

Thermal layout optimization problems are common in integrated circuit design, where a large number of electronic components are placed on the layout, and a low temperature (i.e., high efficiency) is achieved by optimizing the positions of the electronic components. The operating temperature value of the layout is obtained by measuring the temperature field from the expensive simulation. Based on this, the thermal layout optimization problem can be viewed as an expensive combinatorial optimization problem. In order to reduce the evaluation cost, surrogate models have been widely used to replace the expensive simulations in the optimization process. However, facing the discrete decision space in thermal layout problems, generic surrogate models have large prediction errors, leading to a wrong guidance of the optimization direction. In this work, the layout scheme and its temperature field are represented by images whose relation can be well approximated by a deep neural network. Therefore, we propose an online deep surrogate-assisted optimization algorithm for thermal layout optimization. First, the iterative local search is developed to explore the discrete decision space to generate new layout schemes. Then, we design a deep neural network to build an image-to-image mapping model between the layout and the temperature field as the approximated evaluation. The operating temperature of the layout can be measured by the temperature field predicted by the mapping model. Finally, a segmented fusion model management strategy is proposed to online updates the parameters of the network. The experimental results on three kinds of layout datasets demonstrate the effectiveness of our proposed algorithm, especially when the required computational budget is limited. [ABSTRACT FROM AUTHOR]

Recovering the global accurate complex physics field from limited sensors is critical to the measurement and control of the engineering system. General reconstruction methods for recovering the field, especially the deep learning with more parameters and better representational ability, usually require large amounts of labeled data which is unaffordable in practice. To solve the problem, this paper proposes uncertainty guided ensemble self-training (UGE-ST), using plentiful unlabeled data to improve reconstruction performance and reduce the required labeled data. A novel self-training framework with the ensemble teacher and pre-training student designed to improve the accuracy of the pseudo-label and remedy the impact of noise is first proposed. On the other hand, uncertainty guided learning is proposed to encourage the model to focus on the highly confident regions of pseudo-labels and mitigate the effects of wrong pseudo-labeling in self-training, improving the performance of the reconstruction model. Experiments including the airfoil velocity and pressure field reconstruction and the electronic components' temperature field reconstruction indicate that our UGE-ST can save up to 90% of the data with the same accuracy as supervised learning. [ABSTRACT FROM AUTHOR]

Deep Neural Networks have been successfully applied in hyperspectral image classification. However, most of prior works adopt general deep architectures while ignore the intrinsic structure of the hyperspectral image, such as the physical noise generation. This would make these deep models unable to generate discriminative features and provide impressive classification performance. To leverage such intrinsic information, this work develops a novel deep learning framework with the noise inclined module and denoise framework for hyperspectral image classification. First, the spectral signature of hyperspectral image is modeled with the physical noise model to describe the high intra‐class variance of each class and great overlapping between different classes in the image. Then, a noise inclined module is developed to capture the physical noise within each object and a denoise framework is then followed to remove such noise from the object. Finally, the CNN with noise inclined module and the denoise framework is developed to obtain discriminative features and provides good classification performance of hyperspectral image. Experiments are conducted over two commonly used real‐world datasets and the experimental results show the effectiveness of the proposed method. The implementation of the proposed method and other compared methods could be accessed at https://github.com/shendu‐sw/noise‐physical‐framework. [ABSTRACT FROM AUTHOR]

Deep learning methods have played a more important role in hyperspectral image classification. However, general deep learning methods mainly take advantage of the samplewise information to formulate the training loss while ignoring the intrinsic data structure of each class. Due to the high spectral dimension and great redundancy between different spectral channels in the hyperspectral image, these former training losses usually cannot work so well for the deep representation of the image. To tackle this problem, this work develops a novel deep manifold embedding method (DMEM) for deep learning in hyperspectral image classification. First, each class in the image is modeled as a specific nonlinear manifold, and the geodesic distance is used to measure the correlation between the samples. Then, based on the hierarchical clustering, the manifold structure of the data can be captured and each nonlinear data manifold can be divided into several subclasses. Finally, considering the distribution of each subclass and the correlation between different subclasses under data manifold, DMEM is constructed as the novel training loss to incorporate the special classwise information in the training process and obtain discriminative representation for the hyperspectral image. Experiments over four real-world hyperspectral image datasets have demonstrated the effectiveness of the proposed method when compared with general sample-based losses and showed superiority when compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

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]

Recently, more attention has been focused on the surrogate model using deep learning methods due to its powerful representational ability. However, it is usually challenging to obtain sufficient labeled samples for effective training because of the time-consuming numerical calculation, especially for the temperature field prediction of heat source layout (HSL-TFP). This work develops a novel and effective training method to overcome this problem for the deep surrogate model in HSL-TFP. First, the prediction of temperature field is modeled as an image-to-image regression problem, and the feature pyramid network (FPN) is chosen as the backbone of the deep network. Then, considering the inter-sample difference and the limited number of training samples, pairwise temperature field difference is utilized as data augmentation to train the surrogate model. Finally, deep transfer learning is introduced to take advantage of the valuable information from similar tasks and accelerate learning among different HSL-TFP problems. Experiments employing physic simulation data are conducted to validate the effectiveness of the proposed method. The results demonstrate that the proposed methods have significantly improved the prediction precision of the deep surrogate model with a small sample. [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]

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]

• 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]