A state monitoring method, a state monitoring apparatus and a state monitoring system for a developing device are provided. After image information is obtained through the acquired video information of the developing device, it is determined by an analysis unit whether the image information includes nozzle anomaly information, and alarm information is issued after the nozzle anomaly information is determined. Moreover, similarity between the image information that does not include the nozzle anomaly information and second preset nozzle anomaly information is compared, and the nozzle information is stored in the analysis unit in a case that the similarity between the image information and the second preset nozzle anomaly information is greater than a first threshold.

A substrate processing apparatus includes: a process chamber performing film-forming processing to a substrate; a substrate support that is provided in the process chamber and includes a plurality of mounting surfaces on which the substrate is mounted; and a detector that is disposed outside or inside the process chamber and detects a state of a film-forming material adhering to at least one of the plurality of mounting surfaces in a non-contact manner.

Embodiments herein generally relate to inspection systems for substrates or wafers for solar cell applications. The inspection system is configured to analyze substrates or wafers for chips, cracks, and other defects. The system includes conveyor apparatuses, and the conveyor apparatuses include one or more conveyor elements. The conveyor elements are configured to transport rectangular wafers having a width between about 175 mm to about 250 mm. The conveyor elements include a first conveyor belt and second conveyor belt to transport the substrates. The spacing of the belts reduces vibrations of the substrate edge.

A method of inspection and an inspection system for the film deposition process for substrates that includes glass and wafer are disclosed. The inspection system includes multiple camera modules positioned in a load lock unit of a process chamber, such as the camera modules that can capture images of the substrate in the load lock. The images are analyzed by a controller of the inspection system to determine the accuracy of robots in handling the substrate, calibration of the robots based on the analysis, and defects in the substrate caused during the handling and deposition process.

A wafer defect detection apparatus and a method of fabricating an IC using the same. Images of a plurality of semiconductor wafers forming a wafer lot are captured at a targeted process step of a fabrication flow and preprocessed, wherein a medoid image is identified as a reference wafer image. In one arrangement, preprocessed wafer images of a semiconductor wafer lot may be analyzed for defects based on an ensemble of image analysis techniques using at least one of the reference wafer image from the wafer lot and a template patch to enhance the predictive power of defect detection.

In one embodiment, a semiconductor manufacturing apparatus includes a processor configured to process a film provided on an end portion of a substrate. The apparatus further includes a detector configured to detect information relating to a shape of the end portion of the substrate. The apparatus further includes a controller configured to control the processing of the film by the processor, based on the information relating to the shape of the end portion of the substrate.

A diagnostic system of a substrate transfer hand including a base part coupled to a hand tip portion of a robot arm and a substrate holding part coupled to the base part to hold a substrate, includes a camera which is secured to the base part and takes an image of the substrate holding part; and a diagnostic device which obtains image information of the image taken by the camera and diagnoses normality of the substrate holding part based on the image information.

A front surface of a semiconductor wafer is rapidly heated by irradiation of a flash of light. Temperature of the front surface of the semiconductor wafer is measured at predetermined intervals after the irradiation of the flash of light, and is sequentially accumulated to acquire a temperature profile. From the temperature profile, an average value and a standard deviation are each calculated as a characteristic value. It is determined that the semiconductor wafer is cracked when an average value of the temperature profile deviates from the range of ±5σ from a total average of temperature profiles of a plurality of semiconductor wafers or when a standard deviation of the temperature profile deviates from the range of 5σ from the total average thereof of the plurality of semiconductor wafers.

There is provided a method for manufacturing a semiconductor structure, including: preparing a plate-like semiconductor structure; and inspecting the semiconductor structure, the inspection of the semiconductor further including: performing a measurement of irradiating a surface of the semiconductor structure with a light from a light source in an oblique direction to the surface, and detecting a reflected light reflected or scattered by the surface by a two-dimensional detector, at a plurality of locations within at least a predetermined range of the surface of the semiconductor structure, to acquire a reflected light distribution that is a distribution of an integrated value obtained by integrating intensity of the reflected light measured at the plurality of locations, with respect to a position at the detector; and fitting the reflected light distribution by a multiple Gaussian function obtained by adding at least a first Gaussian function and a second Gaussian function distributed more widely than the first Gaussian function, to acquire a parameter of the second Gaussian function as an index corresponding to a surface roughness of the semiconductor structure.

Two machine learning modules or models are used to generate a recipe. A first machine learning module determines a set of recipes based on measured signals. The second machine learning module analyzes the set of recipes based on a cost function to determine a final recipe. The second machine learning module also can determine settings if the set of recipes fail evaluation using the cost function.