Abstract: This disclosure is directed to solutions of detecting and classifying wafer defects using machine learning techniques. The solutions take only one coarse resolution digital microscope image of a target wafer, and use machine learning techniques to process the coarse SEM image to review and classify a defect on the target wafer. Because only one coarse SEM image of the wafer is needed, the defect review and classification throughput and efficiency are improved. Further, the techniques are not distractive and may be integrated with other defect detecting and classification techniques.

Abstract: A semiconductor wafer defect detection system captures test images of a semiconductor wafer. The system analyzes the test images with an analysis model trained with a machine learning process. The analysis model generates simulated integrated circuit layouts based on the test images. The system detects defects in the semiconductor wafer by comparing the simulated integrated circuit layouts to reference integrated circuit layouts.

Abstract: A process tube device can detect the presence of any external materials that may reside within a fluid flowing in the tube. The process tube device detects the external materials in-situ which obviates the need for a separate inspection device to inspect the surface of a wafer after applying fluid on the surface of the wafer. The process tube device utilizes at least two methods of detecting the presence of external materials. The first is the direct measurement method in which a light detecting sensor is used. The second is the indirect measurement method in which a sensor utilizing the principles of Doppler shift is used. Here, contrary to the first method that at least partially used reflected or refracted light, the second method uses a Doppler shift sensor to detect the presence of the external material by measuring the velocity of the fluid flowing in the tube.

Abstract: Some implementations described herein provide techniques and apparatuses for a semiconductor processing tool including an electrostatic chuck having a voltage-regulation system to regulate an electrical potential throughout regions of a semiconductor substrate positioned above the electrostatic chuck. The voltage-regulation system may determine that an electrical potential within a region of the semiconductor substrate does not satisfy a threshold. The voltage-regulation system may, based on determining that the electrical potential throughout the region does not satisfy the threshold, position one or more electrically-conductive pins within the region. While positioned within the region, the one or more electrically-conductive pins may change the electrical potential of the region.

Abstract: A semiconductor wafer defect detection system captures test images of a semiconductor wafer. The system analyzes the test images with an analysis model trained with a machine learning process. The analysis model generates simulated integrated circuit layouts based on the test images. The system detects defects in the semiconductor wafer by comparing the simulated integrated circuit layouts to reference integrated circuit layouts.

Abstract: In a method of inspection of a semiconductor substrate a first beam of light is split into two or more second beams of light. The two or more second beams of light are respectively transmitted onto a first set of two or more first locations on top of the semiconductor substrate. In response to the transmitted two or more second beams of light, two or more reflected beams of light from the first set of two or more first locations are received. The received two or more reflected beams of light are detected to generate two or more detected signals. The two or more detected signals are analyzed to determine whether a defect exists at the set of the two or more first locations.

Abstract: Some implementations described herein provide techniques and apparatuses for a semiconductor processing tool including an electrostatic chuck having a voltage-regulation system to regulate an electrical potential throughout regions of a semiconductor substrate positioned above the electrostatic chuck. The voltage-regulation system may determine that an electrical potential within a region of the semiconductor substrate does not satisfy a threshold. The voltage-regulation system may, based on determining that the electrical potential throughout the region does not satisfy the threshold, position one or more electrically-conductive pins within the region. While positioned within the region, the one or more electrically-conductive pins may change the electrical potential of the region.

Abstract: In a method of inspection of a semiconductor substrate a first beam of light is split into two or more second beams of light. The two or more second beams of light are respectively transmitted onto a first set of two or more first locations on top of the semiconductor substrate. In response to the transmitted two or more second beams of light, two or more reflected beams of light from the first set of two or more first locations are received. The received two or more reflected beams of light are detected to generate two or more detected signals. The two or more detected signals are analyzed to determine whether a defect exists at the set of the two or more first locations.

Abstract: Some implementations described herein provide techniques and apparatuses for a semiconductor processing tool including an electrostatic chuck having a voltage-regulation system to regulate an electrical potential throughout regions of a semiconductor substrate positioned above the electrostatic chuck. The voltage-regulation system may determine that an electrical potential within a region of the semiconductor substrate does not satisfy a threshold. The voltage-regulation system may, based on determining that the electrical potential throughout the region does not satisfy the threshold, position one or more electrically-conductive pins within the region. While positioned within the region, the one or more electrically-conductive pins may change the electrical potential of the region.

Abstract: A process tube device can detect the presence of any external materials that may reside within a fluid flowing in the tube. The process tube device detects the external materials in-situ which obviates the need for a separate inspection device to inspect the surface of a wafer after applying fluid on the surface of the wafer. The process tube device utilizes at least two methods of detecting the presence of external materials. The first is the direct measurement method in which a light detecting sensor is used. The second is the indirect measurement method in which a sensor utilizing the principles of Doppler shift is used. Here, contrary to the first method that at least partially used reflected or refracted light, the second method uses a Doppler shift sensor to detect the presence of the external material by measuring the velocity of the fluid flowing in the tube.

Abstract: In a method of inspection of a semiconductor substrate a first beam of light is split into two or more second beams of light. The two or more second beams of light are respectively transmitted onto a first set of two or more first locations on top of the semiconductor substrate. In response to the transmitted two or more second beams of light, two or more reflected beams of light from the first set of two or more first locations are received. The received two or more reflected beams of light are detected to generate two or more detected signals. The two or more detected signals are analyzed to determine whether a defect exists at the set of the two or more first locations.

Abstract: An apparatus for inspecting a semiconductor substrate includes a rotatable base configured to support a substrate, and a nozzle arm includes a nozzle and a light monitoring device. The light monitoring device includes a laser transmitter and an array of light sensors arranged in the nozzle arm and facing the substrate. The light monitoring device is configured to transmit a laser pulse towards the substrate, wherein the laser pulse impinges on the substrate, receive a reflected laser pulse from the substrate, calculate whether one or more light sensors received the laser pulse, and calculate a distance between the light monitoring device and the substrate using the turnaround time for determining a process quality on the substrate.

Abstract: This disclosure is directed to solutions of detecting and classifying wafer defects using machine learning techniques. The solutions take only one coarse resolution digital microscope image of a target wafer, and use machine learning techniques to process the coarse SEM image to review and classify a defect on the target wafer. Because only one coarse SEM image of the wafer is needed, the defect review and classification throughput and efficiency are improved. Further, the techniques are not distractive and may be integrated with other defect detecting and classification techniques.

Abstract: This disclosure is directed to solutions of detecting and classifying wafer defects using machine learning techniques. The solutions take only one coarse resolution digital microscope image of a target wafer, and use machine learning techniques to process the coarse SEM image to review and classify a defect on the target wafer. Because only one coarse SEM image of the wafer is needed, the defect review and classification throughput and efficiency are improved. Further, the techniques are not distractive and may be integrated with other defect detecting and classification techniques.

Abstract: Wafer inspection apparatuses and methods are described. The wafer inspection apparatus includes an optical module, at least one wafer holder for carrying a plurality of wafers, and a plurality of optical sensors. The optical module is configured to emit a plurality of light beams for simultaneously scanning the plurality of wafers carried by the at least one wafer holder. The plurality of optical sensors is configured to receive the light beams reflected by the plurality of wafers.

Abstract: Wafer inspection apparatuses and methods are described. The wafer inspection apparatus includes an optical module, at least one wafer holder for carrying a plurality of wafers, and a plurality of optical sensors. The optical module is configured to emit a plurality of light beams for simultaneously scanning the plurality of wafers carried by the at least one wafer holder. The plurality of optical sensors is configured to receive the light beams reflected by the plurality of wafers.

Abstract: A semiconductor wafer defect detection system captures test images of a semiconductor wafer. The system analyzes the test images with an analysis model trained with a machine learning process. The analysis model generates simulated integrated circuit layouts based on the test images. The system detects defects in the semiconductor wafer by comparing the simulated integrated circuit layouts to reference integrated circuit layouts.

Abstract: A system includes an inspection device and an image processing unit. The inspection device is configured to scan a wafer to generate an inspected image. The image processing unit is configured to receive the inspected image, and is configured to analyze the inspected image by using at least one deep learning algorithm in order to determine whether there is any defect image shown in a region of interest in the inspected image. When there is at least one defect image shown in the region of interest in the inspected image, the inspection device is further configured to magnify the region of interest in the inspected image to generate a magnified inspected image for identification of defects.

Abstract: Wafer inspection apparatuses and methods are described. The wafer inspection apparatus includes an optical module, at least one wafer holder for carrying a plurality of wafers, and a plurality of optical sensors. The optical module is configured to emit a plurality of light beams for simultaneously scanning the plurality of wafers carried by the at least one wafer holder. The plurality of optical sensors is configured to receive the light beams reflected by the plurality of wafers.

Abstract: This disclosure is directed to solutions of detecting and classifying wafer defects using machine learning techniques. The solutions take only one coarse resolution digital microscope image of a target wafer, and use machine learning techniques to process the coarse SEM image to review and classify a defect on the target wafer. Because only one coarse SEM image of the wafer is needed, the defect review and classification throughput and efficiency are improved. Further, the techniques are not distractive and may be integrated with other defect detecting and classification techniques.