Anil Kumar Khambampati

Toxic and corrosive byproducts generated during semiconductor manufacturing can accumulate inside exhaust pipes, forming solid residues that pose risks such as pipe clogging, reduced pumping efficiency, and operational accidents. To mitigate these risks, regular preventive maintenance (PM) is required, highlighting the need for non-destructive, real-time monitoring technologies to ensure process efficiency and worker safety. This study proposes a data-driven approach to estimate the free volume index (FVI) and internal deposit conditions using electrical capacitance measurements. Two convolutional neural network (CNN) architectures 1D-CNN and 2D-CNN were developed and trained on simulated capacitance data under various deposition scenarios. The methodology was first evaluated through numerical simulations to test robustness and the performance was benchmarked against a fully connected neural network (FCNN). Subsequently, the approach was validated using real capacitance data collected from an operating semiconductor facility, thereby confirming its practical applicability. The proposed CNN-based method demonstrated high accuracy, robustness to noise, and strong generalization, offering a practical solution for early detection of clogging and process anomalies. This work contributes toward safer and efficient semiconductor manufacturing through intelligent pipe condition monitoring.

In semiconductor manufacturing, the accumulation of byproducts in exhaust pipelines under inadequate temperature control poses significant safety and operational risks. This study introduces an innovative approach employing an electrical capacitance measurement sensor system combined with an artificial neural network (ANN) to monitor residue buildup. The proposed method estimates the free volume index within industrial process exhaust pipes, enabling precise evaluation of residue deposition and gas phase fractions. Numerical simulations and field studies in semiconductor environments validate the model’s effectiveness, demonstrating accurate residue quantification and enhancing safety and operational efficiency. In numerical simulations, the error between true values and estimated values was within 1%, while the values estimated from experimental data showed an error within 5%. These findings underscore the robustness of the model in both controlled and real-world settings. This advancement offers a practical and reliable solution to mitigate hazards and optimize maintenance processes in semiconductor manufacturing.

During pregnancy, it is important to monitor the health of the fetus and fetal movement count is one of the key parameters that can be used to check the health of the fetus. Consequently, there is growing interest in developing non-invasive passive methods for fetal monitoring techniques that can be used outside of clinical settings. This study introduces a home-use system based on electrical resistance tomography that pregnant mothers can utilize for fetus monitoring. The setup utilizes a conductive fabric, functioning as electronic skin (e-skin), positioned on the mother’s abdomen to detect alterations in the fabric’s electrical characteristics caused by fetal movements. This method is validated through both numerical simulations and experimental investigations, which assess conductivity changes on the fabric’s surface in reaction to localized pressure fluctuations, mimicking fetal motions.

Monitoring fetal health is crucial in prenatal care, and existing techniques for assessing fetal movements are often expensive and limited to clinical environments. This research investigates the potential of utilizing electrical resistance tomography (ERT) with a conductive fabric to create a cost-effective and non-invasive imaging solution for fetal monitoring. The fusion of ERT with wearable e-textile devices facilitates continuous and portable monitoring. To improve the quality of ERT-generated images, we propose the application of CycleGAN and pix2pixGAN, both machine learning models based on generative adversarial networks. These models learn to map reconstructed images to target images, thereby enhancing reconstruction precision and image quality. The outcomes of this research highlight the effectiveness of the suggested method in managing noisy data and achieving superior image generation. This work presents a promising approach to fetal monitoring using ERT and deep learning techniques, opening possibilities for more affordable and accessible prenatal care.

Electrical Impedance Tomography (EIT) is a powerful tool for imaging two-phase flow systems in various applications. However, the reconstruction quality of EIT is often limited by the non-linear and ill-posed nature of the inverse problem. In order to improve the quality of EIT reconstruction, a new method using a Generative Adversarial Network (GAN) model is proposed for two-phase flow systems. The GAN model generator and discriminator are adversarially trained on boundary voltages and images of the target location. This training process allows the GAN model to learn the underlying patterns and features present in the EIT data, leading to improved reconstruction outcomes. Numerical and experimental studies are done for two-phase flow setup verification. Results show that the proposed GAN-based model manages to reconstruct target locations with a homogeneous background, indicating the potential for improving EIT-based two-phase flow imaging in industrial applications. Metrics are also compared with other deep learning methods such as neural network and deep neural network, from which the proposed model overcomes image quality metrics such as SSIM and RIE.

Recently, graphene has gained a lot of attention in the electronic industry due to its unique properties and to overcome the limits of miniaturization making way for novel devices in the field of electronics. Among the synthesizing methods for growing large graphene films, chemical vapour deposition is one of the promising and common techniques but defects such as cracks, holes, or wrinkles are hard to avoid. The presence of defects influence the electrical properties of graphene thus the local conductivity distribution across the surface of the graphene can characterize its electrical behavior. The difference in conductivity values of the defect and the background can be estimated with electrical impedance tomography. Due to the very high conductivity of graphene, the reconstructed electrical impedance tomography conductivity images suffer from poor spatial resolution. Considering the graphene defect conductivity and the number of defects are known a priori then the unknowns are defect geometry and background conductivity of graphene that are estimated using hybrid particle swarm optimization - gravitational search algorithm. The defect geometries are described by truncated Fourier series coefficient which can represent the complex shapes. Numerical studies are done for graphene characterization with single and multiple defects. Monte Carlo simulations with 20 runs having different noise seed are carried out to evaluate the robustness of the proposed algorithm. Statistical analysis is done and the results of the proposed algorithm are compared against the conventional modified Newton Raphson method and gravitational search algorithm. Experimental studies with graphene sheet 2.5 cm $\times2.5$ cm with defects are performed for shape estimation. The results showed that the proposed algorithm has a good estimation of background conductivity and defect geometry.

The paper describes a novel method of detecting defects in the fabrication of graphene films which have many important applications due to their unique mechanical and electronic properties. The illustrative method is based upon electrical impedance tomography and is demonstrated using a testbed to obtain the conductivity profile across the entire graphene surface. Sensed data are processed using a described reconstruction procedure that estimates electrode contact impedances and spatial conductivity. The results are presented of numerical simulations and experiments with graphene wafers of size 2.5 cm. The results show that the proposed method can jointly estimate contact impedance at each electrode and conductivity distribution.

Single-layer graphene synthesized using the chemical vapor deposition (CVD) technique contains defects on the graphene surface that are formed during the growth and transfer process. These defects influence the graphene electrical characteristics, especially the conductivity distribution. Nondestructive characterization of graphene samples is therefore essential for developing single-layer graphene devices. Electrical impedance tomography (EIT), a low-cost nondestructive method with high temporal resolution characteristics, can be applied to obtain the local conductivity distribution. Due to the very high conductivity of the background and inaccurate knowledge of contact impedances, the conventional absolute imaging methods do not give desired conductivity reconstruction for graphene. This study uses a nonlinear difference imaging (NDI) approach to estimate the local conductivity changes across the graphene surface quantitatively. In NDI, the conductivity after the change is parameterized as a linear combination of initial and the conductivity change. The conductivity change restricted to the region of interest (ROI) is determined using the Otsu method. The NDI with Otsu method (NDIWO) estimates the initial distribution and conductivity changes simultaneously from the two datasets measured at different time intervals. NDIWO tolerates modeling errors to some extent and quantitively provides more accurate local conductivity changes. The feasibility of NDIWO is tested with numerical simulations and experiments with graphene wafer of size 2.5 cm $\times2.5$ cm, and results show that the proposed method is successful in estimating the conductivity changes with better accuracy than conventional absolute and linear difference imaging.

Recently, graphene has gained a lot of attention in the electronic industry due to its unique properties and has paved the way for realizing novel devices in the field of electronics. For the development of new device applications, it is necessary to grow large wafer-sized monolayer graphene samples. Among the methods to synthesize large graphene films, chemical vapor deposition (CVD) is one of the promising and common techniques. However, during the growth and transfer of the CVD graphene monolayer, defects such as wrinkles, cracks, and holes appear on the graphene surface. These defects can influence the electrical properties and it is of interest to know the quality of graphene samples non-destructively. Electrical impedance tomography (EIT) can be applied as an alternate method to determine conductivity distribution non-destructively. The EIT inverse problem of reconstructing conductivity is highly non-linear and is heavily dependent on measurement accuracy and modeling errors related to an accurate knowledge of electrode location, contact resistances, the exact outer boundary of the graphene wafer, etc. In practical situations, it is difficult to eliminate these modeling errors as complete knowledge of the electrode contact impedance and outer domain boundary is not fully available, and this leads to an undesirable solution. In this paper, a difference imaging approach is proposed to estimate the conductivity change of graphene with respect to the reference distribution from the data sets collected before and after the change. The estimated conductivity change can be used to locate the defects on the graphene surface caused due to the CVD transfer process or environment interaction. Numerical and experimental results with graphene sample of size 2.5 × 2.5 cm are performed to determine the change in conductivity distribution and the results show that the proposed difference imaging approach handles the modeling errors and estimates the conductivity distribution with good accuracy.

Shape-driven approaches have been proposed as an effective strategy for the electrical impedance tomography (EIT) reconstruction problem in recent years. In order to augment the shape-driven approaches, we propose a new method that transforms the shape to be reconstructed as basic primitives directly modeled by using Fourier representations. To allow automatic topological changes between the basic primitives and surrounding objects simultaneously, Boolean operations are employed. The Boolean operations with direct representation of primitives can be utilized for dimensionality and ill-posedness reduction, enabling feasible shape and topology optimization with shape-driven approaches. As a proof of principle, we leverage the proposed method for two dimensional shape reconstruction in EIT with various conductivity distributions. We demonstrate that our method is able to improve EIT reconstructions by enabling accurate shape and topology optimization.