Inline hyperspectral thickness determination of thin films using neural networks

Tremmel, Anton J.; Weiss, Roman; Schardt, Michael; Koch, Alexander W.

doi:10.1117/12.2262070

Cited by 5 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 a, the conventional method of training for an ANN algorithm is shown, matching those in previous works 15 – 19 . A multilayer perceptron (MLP) type ANN algorithm was constructed and trained using Python, similarly to the previous work 15 , 17 , 19 . In the wavelength range of the spectrometer to be used for the CRM measurement, a wavelength range in which the intensity of the measured light is sufficiently greater than noise was selected, and the number of samples for that range was established as the number of input nodes.…”

Section: Methodssupporting

confidence: 78%

“…In Fig. 2 a, the conventional method of training for an ANN algorithm is shown, matching those in previous works 15 – 19 . A multilayer perceptron (MLP) type ANN algorithm was constructed and trained using Python, similarly to the previous work 15 , 17 , 19 .…”

Section: Methodssupporting

confidence: 68%

“…Therefore, reflectance spectra are received from 881 input nodes and thin film thickness analysis values are output from one output node through a hidden layer. A sigmoid function was applied as the activation function like the previous works 15 , 19 , and the loss was calculated according to the average of the mean squared error between the outputs and the ideal value as determined in the simulation. After the error estimation is completed, a basic backpropagation algorithm is utilized to update the weights connecting each layer.…”

Section: Methodsmentioning

confidence: 99%

“…Because the proposed method can basically offer strict validation of the ANN algorithms using certified values of the CRMs, it is not necessary to use validation data separately from ideally created reflectance spectra used for training datasets. The design parameters of the ANN algorithm were number of hidden layers (L = 1, 2, 3) and number of nodes in each layer (N = 50, 100, 150, 200), which were selected as simple cases based on the previous works 15 , 17 , 19 . Therefore, with the combination of these two parameters, 12 ANN algorithms were developed and then trained.…”

Section: Methodsmentioning

confidence: 99%

“…It is practically impossible to extract information of only the thin film thickness from the reflectance spectrum obtained experimentally, which increases measurement uncertainty. In this respect, given the advantages of an ANN, several studies have been reported to measure the thickness of transparent thin films or multiple thin films with a broad spectral light source and X-rays 15 – 19 . However, in all of these earlier works, the performance evaluation was limited to the level of a simple comparison with the results of existing analysis methods or other measurement techniques.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A novel method to design and evaluate artificial neural network for thin film thickness measurement traceable to the length standard

Lee

Jin

2022

Sci Rep

View full text Add to dashboard Cite

The artificial neural networks (ANNs) have been often used for thin-film thickness measurement, whose performance evaluations were only conducted at the level of simple comparisons with the existing analysis methods. However, it is not an easy and simple way to verify the reliability of an ANN based on international length standards. In this article, we propose for the first time a method by which to design and evaluate an ANN for determining the thickness of the thin film with international standards. The original achievements of this work are to choose parameters of the ANN reasonably and to evaluate the training instead of a simple comparison with conventional methods. To do this, ANNs were built in 12 different cases, and then trained using theoretical spectra. The experimental spectra of the certified reference materials (CRMs) used here served as the validation data of each trained ANN, with the output then compared with a certified value. When both values agree with each other within an expanded uncertainty of the CRMs, the ANN is considered to be reliable. We expect that the proposed method can be useful for evaluating the reliability of ANN in the future.

show abstract

Section: Methodssupporting

confidence: 78%

Section: Methodssupporting

confidence: 68%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A novel method to design and evaluate artificial neural network for thin film thickness measurement traceable to the length standard

Lee

Jin

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

Real‐Time Metrology for Roll‐To‐Roll and Advanced Inline Manufacturing: A Review

Maize

Cakmak

et al. 2022

Adv Materials Technologies

View full text Add to dashboard Cite

Roll‐to‐Roll (R2R) manufacturing is changing how state‐of‐the‐art technology is made. Roll‐to‐Roll is part of a family of advanced scalable inline manufacturing techniques that make traditional and state‐of‐the‐art products at high yield and reduced cost. R2R manufacturing has grown rapidly and is fundamental to several advanced technologies such as functional materials and films, sensors for medicine, biology, and environment monitoring, energy harvesting devices, and flexible electronics. Advantages of R2R manufacturing include ease of machine design, adaptability to a wide range of additive processing methods, and very high throughput. To keep up with advances in R2R manufacturing, novel methods have emerged to measure important product metrics (thickness, roughness, conductivity) and monitor quality (uniformity, defects) inline and in real‐time. This review provides an overview of the state‐of‐the‐art for real‐time inline metrology and quality control in modern R2R manufacturing. The survey considers both established inline metrology techniques such as line‐scan imaging and reflectometry, and techniques recently adapted or that show promise for real‐time inline R2R metrology such as ellipsometry, hyper‐spectral imaging, and Raman spectroscopy.

show abstract

Hyperspectral imaging for dynamic thin film interferometry

Suja

Sentmanat

Hofmann

et al. 2020

Sci Rep

View full text Add to dashboard Cite

In this manuscript we report an arrangement utilizing hyperspectral imaging for the unconditional and automated reconstruction of thickness profiles from thin liquid film interferograms. Approaches utilizing hyperspectral imaging (using the pushbroom like techniques) have previously been reported for characterizing static thin films 30,31. However, these approaches are not suited for dynamic films, primarily due to the nature of image acquisition, and to the best of our knowledge have never been modified for use with dynamic films. Here, we describe a compact setup employing a snapshot hyperspectral imager and the related algorithms for automated determination of thickness profiles of thin films. In section "Methods", we detail the theory, the experimental setup and the developed algorithms. In section "Results and discussion", we establish the accuracy of this technique by comparing the absolute pixel-wise differences across the manually reconstructed and the automatically reconstructed thickness profiles. Finally, we conclude the paper by discussing the key advantages and unique characteristics of hyperspectral thin film interferometry.

show abstract

Inline hyperspectral thickness determination of thin films using neural networks

Cited by 5 publications

References 3 publications

A novel method to design and evaluate artificial neural network for thin film thickness measurement traceable to the length standard

A novel method to design and evaluate artificial neural network for thin film thickness measurement traceable to the length standard

Real‐Time Metrology for Roll‐To‐Roll and Advanced Inline Manufacturing: A Review

Hyperspectral imaging for dynamic thin film interferometry

Contact Info

Product

Resources

About