摘要:
Provided is an anomaly detection method and system capable of constructing determination condition rules of anomaly detection from case-based anomaly detection by way of multivariate analysis of a multi-dimensional sensor signal, applying the rules to design-based anomaly detection of individual sensor signals, and also appropriately executing setting and control of threshold values for highly sensitive, early, and clearly visible detection of anomalies. Anomaly detection on the basis of a case base by way of multivariate analysis controls design-based anomaly detection. That is to say, (1) anomaly detection on the basis of a case base performs selection of sensor signals and anomaly detection according to various types of anomalies. Specifically, anomaly detection (characteristic conversion), evaluation of level of effect of each signal, construction of determination conditions (rules), and display and selection of sensor signals corresponding to the anomaly are performed. (2) Design-based anomaly detection for individual sensor signals performs anomaly detection after the above have been performed. Specifically, setting and control of thresholds, display of thresholds, and anomaly detection and display are performed.
摘要:
In case-based anomaly indication detection in a facility, there are problems such as error generation due to insufficient learning data or execution difficulty due to increased memory capacity and calculation time when the learning data period has been increased to obtain the learning data sufficiently. Provided is a method for monitoring facility state on the basis of a time series signal outputted from the facility, wherein an operation pattern label for each fixed interval is assigned on the basis of the time series signal, learning data is selected on the basis of the operation pattern label for each fixed interval, a normal model is created on the basis of the selected learning data, an anomaly measure is calculated on the basis of the time series signal and the normal model, and the facility state is determined to be anomaly or normal on the basis of the calculated anomaly measure.
摘要:
Provided are an anomaly detection/diagnostic method and an anomaly detection/diagnostic system whereby it is possible, in equipment such as a plant, to detect anomalies promptly and with high sensitivity, wherein anomaly detection is carried out using operating information such as the operating time of the equipment and output signals from a plurality of sensors appended to the equipment, and wherein maintenance logs such as written procedure reports comprising procedure logs and instances of past countermeasures such as replacement part information are targeted to make associations between detected anomalies and countermeasures, and create links between anomaly detection and past maintenance logs, making reference to equipment records as well, while classifying and presenting anomalies that require action, thereby improving diagnostic accuracy.
摘要:
When size of a defect on an increasingly miniaturized pattern is obtained by defect inspection apparatus in the related art, a value is inconveniently given, which is different from a measured value of the same defect by SEM. Thus, a dimension value of a defect detected by defect inspection apparatus needs to be accurately calculated to be approximated to a value measured by SEM. To this end, size of the defect detected by the defect inspection apparatus is corrected depending on feature quantity or type of the defect, thereby defect size can be accurately calculated.
摘要:
A method of detecting a defect, including the steps of: illuminating step for illuminating a sample with a light; detecting step for detecting light from the specimen which is illuminated by the light and forming an image by processing the detected light; processing step for extracting a defect candidate by processing the image of the sample formed in the detecting step and determining an inspection condition by using images including the image of the sample acquired in the detecting step, a partial image including the extracted defect candidate and a reference image which corresponds to the partial image including the defect candidate.
摘要:
A fault inspection method and apparatus in which the scattergram is separated or objects of comparison are combined in such a manner as to reduce the difference between an inspection object image and a reference image. As a result, the difference between images caused by the thickness difference in the wafer can be tolerated and the false information generation prevented without adversely affecting the sensitivity.
摘要:
A defect classification method to classify defects by using a classifier having a binary tree structure based on features of defects extracted from detected signals acquired from a defect inspection apparatus includes a classifier construction process for constructing the classifier by setting a branch condition including defect classes respectively belonging to groups located on both sides of the branch point, a feature to be used for branching, and a discriminant reference, for each branch point in the structure based on instruction of defect classes and feature data respectively associated therewith beforehand. The process includes a priority order specification process for previously specifying target classification performance of purity and accuracy for each defect class, whole and in worst case, with priority order, and an evaluation process for evaluating whether the specified target classification performance under the branching condition is satisfied and displaying a result of evaluation, every item.
摘要:
This invention provides method for detecting advance signs of anomalies, event signals outputted from the facility are used to create a separate mode for each operating state, a normal model is created for each mode, the sufficiency of learning data for each mode is checked, a threshold is set according to the results of said check, and anomaly identification is performed using said threshold. Also, for diagnosis, a frequency matrix is created in advance, with result events on the horizontal axis and cause events on the vertical axis, and the frequency matrix is used to predict malfunctions. Malfunction events are inputted as result events, and quantized sensor signals having anomaly measures over the threshold are inputted as cause events.
摘要:
A pattern inspection method and apparatus in which a deep ultraviolet light or an ultraviolet light is irradiated onto a specimen on which a pattern is formed, an image of the specimen which is irradiated with the deep ultraviolet light or the ultraviolet light is formed and the formed image is detected with a rear-surface irradiation type image sensor, which is sensitive to wavelengths of no greater than 400 nmm. A signal outputted from the image sensor is processed so as to detect a defect of the specimen by converting an analog image signal outputted from the image sensor to a digital image signal with an A/D converter, and a display displays information of the defect detected.
摘要:
A method and apparatus for detecting defects are provided for detecting defects or foreign matter on an object to be inspected. The apparatus includes a movable stage for mounting a specimen, an illumination system for irradiating a circuit pattern with light from an inclined direction, and an image-forming optical system for forming an image of an irradiated detection area on a detector from the upward and oblique directions. With this arrangement, diffracted light and scattered light caused on the circuit pattern through the illumination by the illumination system is collected. A spatial filter is provided on a Fourier transform surface for blocking the diffracted light from a linear part of the circuit pattern. The scattered and reflected light received by the detector is converted into an electrical signal. The converted electrical signal of one chip is compared with that of the other adjacent chip.