National Cheng-Kung University

Taiwan Semiconductor Manufacturing Comp. Ltd.

National Taiwan University

Inventec Corp.

Inventec (pudong) Technology Corporation

Empass Technology Inc.

Chin-Yi Lin

Fan-Tien Cheng

Yu-Ming Hsieh

Yang-Chih Huang

Tzong-Lin Wu

Hsien-Cheng Huang

Fu-Lung Hsueh

Ming Hsien Tsai

Sa-Lly Liu

Chia-Chen Chen

Chi-Zen Peng

Ying-Cheng Tseng

Li-Hsuan Peng

Ching-Kang Ing

Yueh-Feng Tsai

Chien-Chang Chen

Po-Hsiang Peng

Tan-Ju Wang

A virtual metrology method based on convolutional autoencoder and transfer learning includes performing a data alignment operation, a modeling operation and a calculating operation. The data alignment operation includes performing a data-length adjusting operation onto a plurality of sets of process data. The modeling operation includes classifying paired data and unpaired process data; creating a pre-trained model by using the unpaired process data, and then inputting the paired data to the pre-trained model to create a virtual metrology model based on convolutional autoencoder. The virtual metrology model based on convolutional autoencoder includes at least one convolutional neural network model. In addition, the calculating operation includes executing one of a predicting step and a transfer learning step according to whether the actual metrology data is obtained, thereby calculating one of a phase-one virtual metrology value and a phase-two virtual metrology value.

Virtual metrology method based on convolutional autoencoder and transfer learning and system thereof

A golden path search method for manufacturing process provides a two-phase process to search for a golden path. A first phase step of the two-phase process includes preparing a search model based on a search algorithm, and selecting a plurality of key process stages of a plurality of process stages by feeding sets of final inspection values and the production paths of the workpieces into the searching model, and then generating a plurality of key paths according to the key process stages. A second phase step of the two-phase process includes building a plurality of prediction models of the key paths according to the production paths and the sets of final inspection values, and predicting a plurality of yield rates corresponding to the key paths according to the prediction models, and then searching for the golden path of the key paths according to the yield rates.

Golden path search method for manufacturing process and system thereof

Embodiments of the present invention provide a multiple-variable predictive maintenance method for a component of a production tool and a computer program product thereof, in which a multiple-variable time series prediction (TSP) and an information criterion algorithm are adapted to build a best vector autoregression model (VAR), thereby forecasting the complicated future trend of accidental shutdown of the component of the production tool. Therefore, the multiple-variable prediction of the present invention can improve the accuracy of prediction compared with the single-variable prediction.

Multiple-variable predictive maintenance method for component of production tool and non-transitory tangible computer readable recording medium thereof

A display device includes a display module and a camera module. The camera module includes a first housing, a second housing and a camera unit. The first housing is movably disposed on the display module. The second housing is separably connected to the first housing. The camera unit is disposed on the second housing. The second housing is able to move with the first housing in relative to the display module, such that the camera unit is exposed from the display module or hidden in the display module. When the second housing is separated from the first housing, the second housing is able to rotate in relative to the first housing, so as to adjust an orientation of the camera unit.

Display device with retractable and rotatable camera module

A virtual metrology method using a convolutional neural network (CNN) is provided. In this method, a dynamic time warping (DTW) algorithm is used to delete unsimilar sets of process data, and adjust the sets of process data to be of the same length, thereby enabling the CNN to be used for virtual metrology. A virtual metrology model of the embodiments of the present invention includes several CNN models and a conjecture model, in which plural inputs of the CNN model are sets of time sequence data of respective parameters, and plural outputs of the CNN models are inputs to the conjecture model.

Virtual metrology method using convolutional neural network and computer program product thereof

A common-mode noise filter is provided, and comprises a first transmission structure and a second transmission structure. At least one first transmission unit is connected between a first signal input end and a first signal output end of the first transmission structure in series. At least one second transmission unit is connected between a second signal input end and a second signal output end of the second transmission structure in series. Two first capacitors are connected between the first signal input end and the second signal input end in series, and connected at a first node together. A first common-mode noise suppression unit is connected between the first node and a reference potential, and comprises a second capacitor and a first lossy element connected to the second capacitor in series or parallel. The first common-mode noise suppression unit can absorb a common-mode noise via the first lossy element.

Common-mode noise filter

Embodiments of the present invention provide a predictive maintenance method for a component of a production tool, in which a time series prediction (TSP) algorithm and an information criterion algorithm are adapted to build a TSP model, thereby forecasting the complicated future trend of accidental shutdown of the component of the production tool. In addition, an alarm scheme is provided for performing maintenance immediately when the component is very likely to enter a dead state, and a death related indicator (DCI) is provided for quantitatively showing the possibility of the component entering the dead state.

Predictive maintenance method for component of production tool and computer program product thererof

A noise suppressor includes a first differential-mode transmission module, a second differential-mode transmission module and a common-mode absorption module. The first and second differential-mode transmission modules are configured to receive a differential signal at one of the first and second differential-mode transmission modules, and output the differential signal at the other of the same. The common-mode absorption module is electrically connected to a reference node, and is configured to absorb common-mode noise of the differential signal from at least one of the first differential-mode transmission module or the second differential-mode transmission module.

Noise suppressor

Embodiments of the present disclosure provide a two-phase process for searching root causes of a yield loss in a production line. In a first phase, an interaction between two process tools, that between two parameters, or that between one process tool and one parameter that is likely to cause the yield loss is identified. In a second phase, a threshold of the parameter that is likely to cause the yield loss and is obtained from the first phase is identified. In each phase, two different algorithms can be used to generate a reliance index (RI) for gauging the reliance levels of their search results.

System and method that consider tool interaction effects for identifying root causes of yield loss

A filter includes shunt circuits coupled between a reference node and each of an input port, an output port, a first node, and a second node. Resonant networks are coupled between the input port and the second node, and between the first node and the output port. Storage element circuits are coupled between the input port and the first node, and between the second node and the output port. The shunt circuits have an equivalent shunt circuit frequency response that partly defines a high passband frequency of the filter, the resonant networks have an equivalent resonant network frequency response that partly defines a low passband frequency of the filter, and the storage element circuits have an equivalent storage element circuit frequency response that defines a stopband frequency of the filter between the low passband frequency and the high passband frequency.

Growing community of inventors

Taipei, Taiwan

Chin-Yi Lin