Search

The abnormal rise in contact temperature in switchgear may lead to overheating or even explosion. It is necessary to monitor the rise in real contact temperature to ensure the safety and stability of switchgear. The accurate measurement of real contact temperature is still a problem, and the continuous state of switchgear cannot be assessed accurately by the temperature monitor. In this paper, a particular installation scheme of temperature sensor is put forward and a calculation algorithm for temperature rise of tulip contacts by the measured temperature of bus bar in real time based on artificial neural network (ANN) is established. An electromagnetic-thermal-fluid coupled simulation model for 10-kV/4000-A switchgears was built, and the thermal characteristic was studied taking the influential factors such as load current, ambient temperature, and contact resistance into consideration. The effectiveness of simulation model is discussed by the comparison to temperature rise experiment. Then, an ANN with three layers of structure is established to calculate the temperature of tulip contacts. The sensitivity and accuracy of network are calculated and verified. The results of this paper may provide a novel method for the monitor of switchgear temperature and assess continuous condition of high-current switchgear. [ABSTRACT FROM AUTHOR]

Numerical studies on plate fins with longitudinal rectangular perforations placed perpendicular to an aluminum base plate are carried out under laminar natural convection conditions. In this paper, a detailed parametric study by varying the dimensions of fin and perforation is carried out to obtain a physical insight into the enhanced heat transfer characteristics of a perforated fin. The perforated fins are found to have an augmented heat transfer rate compared to the solid fins having same contact area. This paper uses a computationally efficient algorithm using soft computing to determine the optimized geometry with a limited set of numerical solutions. This is achieved with the help of artificial neural network (ANN). To reduce the effort in determining suitable parameters for ANN, genetic algorithm (GA) is used. The ANN is trained based on a minimal set of numerical/computational fluid dynamics (CFD) results. The trained ANN can then predict the base plate temperature for any other untrained set of parameters in the same range. A multiobjective optimization of the perforated fin is carried out with two objectives: minimum base plate temperature and maximum weight reduction. This is carried out by applying the GA on the ANN as the fitness function to obtain the multiobjective optimal. The obtained optimized fin geometry can thus be used effectively in many heat transfer applications that necessitate heat transfer enhancement with reduced weight compared to the conventional fins. [ABSTRACT FROM AUTHOR]

It is agreed that air-cooled heat sink (ACHS) would become incapable of 3-D integrated circuits (ICs). A switch from ACHS to a microfluidic heat sink (MFHS) is believed to be a promising solution. Tier-specific MFHS, where the flow rate of each tier can be controlled independently, has been further proposed in consideration of the power consumptions of pumps. However, these works are generally based on a steady power map, which in reality is mostly time-dependent. In this paper, a machine learning (ML)-based control method, combining the Bayesian optimization (BO) and the artificial neural network (ANN), is applied to 3-D ICs with the tier-specific MFHS, considering a time-dependent power map. BO is first applied because it has been demonstrated to outperform other state-of-the-art black-box optimization techniques due to its quick converge. However, as more and more data are acquired when the system keeps working, its computational time increases sharply due to the increasing calculation complexity, which cannot be accepted as we aim for dynamic thermal management. Therefore, ANN is then applied. With the online learning method, its calculation complexity remains constant as more data are acquired. Because of this, its time consumption remains small as the system keeps working. Results of the flow rates and the temperatures are finally presented, which prove that with the ML-based control method, power consumptions of the pumps are intelligently saved while, at the same time, the temperature constraints are met. [ABSTRACT FROM AUTHOR]

As a critical electrical connector component in the modern industrial environment, spring-wire sockets and their manufacture quality are closely relevant to equipment safety. These types of defects in a component are difficult to properly distinguish due to the defect similarity and diversity. In such cases, defect types can only be determined using cumbersome human visual inspection. To satisfy the requirements of quality control, a machine vision apparatus for component inspection is presented in this paper. With a brief description of the apparatus system design, our emphasis is put on the defect recognition algorithm. A multitask convolutional neural network (CNN) is proposed for detecting those ambiguous defects. Compared with the image processing method in machine vision, the defect inspection problem is converted into object detection and classification problems. Instead of breaking it down into two separate tasks, we jointly handle both aspects in a single CNN. In addition, data augmentation methods are discussed to analyze their effects on defects recognition. Successful inspection results using the presented model are obtained using challenging real-world defect image data gathered from a spring-wire socket module inspection line in an industrial plant. [ABSTRACT FROM AUTHOR]

Due to the excellent self-learning ability of deep learning, we propose a novel deep-learning-based method to inspect surface-mount technology (SMT) solder joints in this paper. In contrast to the state-of-the-art learning-based methods in which low-level features are extracted before learning, our method directly implements the inspection task without low-level feature extraction, which is based on a novel cascaded convolutional neural network (CNN). Three kinds of CNNs with different network parameters compose the proposed cascaded CNN. First, one kind of CNN is employed to adaptively learn the regions of interest (ROIs) of SMT solder joint images. Then, both the learned ROIs and the entire solder joint images are fed into the other two kinds of CNNs, respectively. Finally, inspection results are achieved by the learned cascaded CNN. Comparison experiments indicate that our proposed method can achieve more excellent inspection performance for SMT solder joints than that of the state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

Through-silicon via (TSV) is a vertical channel that passes through a chip to connect stacked dies in 3-D packaging. Void may be produced during the high aspect ratio TSV filling process with copper electroplating method. Therefore, void detection becomes an important aspect for high-quality TSV devices. In this paper, a rapid void detection method using a single 2-D X-ray imaging was developed. An image processing method was used to divide the X-ray image into some small blocks for multithreshold image cutting and feature extraction. An artificial neural network was then used to find and locate the blocks that contain voids. The effects of segmentation threshold, various block widths, and heights were studied; a block size of \(30 \times 40\) pixels (width \(\times \) height) is recommended. The void detection is more sensitive to block width than height. Experiments show that the method proposed in this paper can automatically and rapidly detect voids in TSVs using one 2-D X-ray image. [ABSTRACT FROM AUTHOR]

Design and analysis of high-speed SerDes channels primarily deal with ensuring signal integrity (SI) for desired electrical performance. SI is predominantly judged by time domain (TD) metrics: bit error rate (BER), eye-height (EH), and eye-width (EW). With increasing bit rates and stringent BER criteria, TD simulations are becoming compute-time-intensive. A full-factorial, cost-effective design space exploration for SI is made possible by learning-based mapping of frequency-domain S-parameter data to EH/EW. A major challenge in this mapping procedure is the identification of relevant S-parameter data, such as return loss, insertion loss, crosstalks, and the frequency points at which they are sampled. This paper outlines a methodology to identify the critical S-parameters at specific frequency points using information theory-based definition of data relevance using a fast correlation-based filter solution for feature selection. This technique is applied for identifying relevant features for generating artificial neural network-based prediction models of EH/EW within 2.5% accuracy for channels with high data rates and complex topologies. [ABSTRACT FROM PUBLISHER]

This paper presents a multi-resolution modeling approach using wavelet neural networks. A lithium battery model, which has three resolutions, is developed to depict the modeling approach. By combining the advantages of dyadic activation functions and the orthonormal property of wavelet functions, the developed battery model possesses two salient features. First, the model is built from a coarser approximation to a finer representation by adding more details incrementally. Second, the model at a low resolution is compatible with the model at a high resolution, which means that the parameters used in a low resolution can be directly incorporated into a high resolution without any modification. This paper's results show that this battery modeling provides great flexibility for users to choose a suitable resolution to meet their requirements for model accuracy and model execution speed. [ABSTRACT FROM PUBLISHER]

Design space exploration and sensitivity analysis for electrical performance of high-speed serial links is a critical and challenging task for a robust, cost-efficient, and signal-integrity-compliant channel design. The generation of time-domain (TD) metrics like eye height and eye width at higher bit error rates requires longer bit sequences in TD circuit simulation, which is compute time intensive. Intelligent techniques to identify smaller design sets that cover the design space optimally may provide incorrect sensitivity analysis. This paper explores learning-based modeling techniques that rapidly map relevant frequency-domain metrics like differential insertion loss and total cross talk, in the presence of equalization, to TD metrics like eye height and eye width, thus facilitating a full-factorial design space sweep. Numerical results performed with multilayer-perceptron-based artificial neural network as well as least-squares support vector machine (LS-SVM) on Serial ATA 3.0 and Peripheral Component Interconnect Express Gen3 channels generate an average error of less than 2%. [ABSTRACT FROM PUBLISHER]

In this paper, a novel methodology for high-level modeling of bus communication in embedded systems is introduced. It allows the dynamic evaluation of their signal integrity (SI) characteristics at the virtual prototyping step (i.e., before physical realization). The method is based on the association of functional and nonfunctional modules. Functional modules represent the ideal behavior of the system, while nonfunctional modules use neural networks to model SI effects. This approach was implemented in SystemC-AMS, using the timed data flow model of computation. The method is illustrated by a Universal Serial Bus (USB) 3.0 application, where modular and parameterizable models are introduced. The method achieved good accuracy (<5%) while allowing significant simulation speedup (up to 2000 times), compared with SPICE-based reference models. This methodology can be used to perform an early SI analysis in the virtual prototyping of bus communication in the embedded systems. [ABSTRACT FROM PUBLISHER]

This paper presents a new multiport power-aware behavioral model formulation and extraction for high-speed input/output (I/O) buffers that enable the transient prediction of power and ground bouncing effects under simultaneously switching output (SSO) buffers for signal and power integrity evaluation. The derivation of the proposed model is based on the analysis and extension of the I/O buffer information specification (IBIS) buffer issue resolution documents (BIRDs) (i.e., BIRD-95.6 and BIRD-98.3) and the macromodeling via parametric identification of logic gates (Mpilog) (i.e., artificial neural network). The analysis of the previous IBIS and Mpilog modeling approaches is followed by a new model formulation that integrates both the previous BIRDs with a well-designed characterization and parametric extraction procedure. The accuracy and computational performances of the proposed model is evaluated under a realistic SSO scenario. [ABSTRACT FROM AUTHOR]

This paper presents the detailed design, fabrication, and measurement of right-angled microcoaxial bends for silicon (Si)-based radio frequency and microwave integrated circuits. The design of the right-angled microcoaxial bends is performed using the high-frequency structural simulator and the trained artificial neural networks (ANNs) models. The ANN models enable fast and accurate design of microcoaxial bends to achieve desired impedance. The right-angled straight and curved microcoaxial bends are fabricated by a multilayer copper (Cu) Damescene process, which has a low thermal budget and is fully compatible with a complementary metal–oxide–semiconductor back-end-of-line process. Insertion loss less than 0.04 dB at frequency from 0.1 to 40 GHz is realized for both straight and curved bends. The measured return loss is less than −20 dB at frequency from 0.1 to 40 GHz for both microcoaxial bends. The impedance for both microcoaxial bends is well matched to 50 $\Omega $ . Besides the low loss and the high impedance matching, the microcoaxial bends also show other advanced characteristics, including high-quality factors ( $Q$ -factors) as well as supporting pure transverse electromagnetic mode. The use of high-performance bends allows us to fold microcoaxial passive components to meander structures for miniaturization while maintain low loss and perfectly matched impedance. [ABSTRACT FROM PUBLISHER]

In this paper, an adjoint state-space dynamic neural network method for modeling nonlinear circuits and components is presented. This method is used for modeling the transient behavior of the nonlinear electronic and photonic components. The proposed technique is an extension of the existing state-space dynamic neural network (SSDNN) technique. The new method simultaneously adds the derivative information to the training patterns of nonlinear components, allowing the training to be done with less data without sacrificing model accuracy, and, consequently, makes training faster and more efficient. In addition, this method has been formulated such that it can be suitable for the parallel computation. The use of derivative information and parallelization makes training using the proposed technique much faster than the SSDNN. In addition, the models created using the proposed method are much faster to evaluate compared with the conventional models present in traditional circuit simulation tools. The validity of the proposed technique is demonstrated through the transient modeling of the physics-based CMOS driver, commercial NXP’s 74LVC04A inverting buffer, and nonlinear photonic components. [ABSTRACT FROM PUBLISHER]

Light-emitting diodes (LEDs) have been adopted in a wide variety of lighting situations. As lighting technology evolves, illumination devices are moving toward miniaturization and high-power applications. Packaging of illumination devices is essential to providing a path for heat dispersion. A full understanding of the viscosity change of the encapsulation material is critical to ensure manufacturability and improved process yield. The typical viscosity model is the initial viscosity plus the change in viscosity over time at a given temperature. The change in viscosity is a function of the reaction rate and the pro-exponential factor. This paper includes the pro-exponential factor in the regression model to improve the prediction accuracy. Through experimental data, the material's viscosity is determined as a function of process temperature, the ratio of the curing agent, and the curing time. A computer-aided parametric design is used to assess the effect of the variation of individual factors on the quality function and proposes a robust LED encapsulation process. An artificial neural network that considers interactions between parameters and establishes fitness functions is used to further enhance the accuracy of predictions and determine the optimal process solution through an iterative training algorithm. The optimal process scenario suggested by this research is a 10% curing agent preheated at 333^\circK for 40 min. This robust process can improve the signal-to-noise ratios by approximately 43%. [ABSTRACT FROM PUBLISHER]

Product delivery time is as vital as the yield rate for semiconductor manufacturing companies since the industry has become highly competitive and more dynamic nowadays. In the manufacturing process, appropriate parameter settings can shorten the machine cycle time and in turn the product delivery time. This paper presents the application of 'IF-THEN' rules extracted from a multilayer perceptron (MLP) artificial neural network to tune moulding machine parameters to improve the machine cycle time. We can extract the 'IF-THEN' rules by scrutinising the connecting weights inside the MLP network. Historical genuine operating data of a moulding machine input parameters and cycle time were collected from an integrated circuit packaging company in Taiwan. The data were fitted in with an MLP network, and the 'IF-THEN' rules were extracted afterwards. The 'IF-THEN' rules not only indicate which input parameters dominate the machine cycle time but also explain how to tune them. We have applied the extracted rules to tune the moulding machine parameters. Practical results show that the moulding machine cycle time agrees very well with the extracted rules, and also justify the feasibility of the proposed method. [ABSTRACT FROM PUBLISHER]