Abstract: A mechanical fault detection method and system computes a similarity index to quantify the relationship of a measured spectral signature to a theoretical fault signature. A vibration sensor detects vibrations on machinery with rotating components. The vibration sensor generates a representation of the vibration and provides it to a vibration analyzer. The vibration analyzer is configured to identify peak amplitudes in the generated representation, determine a corresponding frequency for each of the peak amplitudes, and match the determined corresponding frequencies to a theoretical set of frequencies. The analyzer determines a number of matching frequencies and identifies a detection condition when the number of matching frequencies meets a predetermined criterion. The system and method combines vibration amplitude threshold detection with similarity index threshold detection to significantly reduce false fault alarms and false pass errors.

Abstract: A mechanical fault detection method and system computes a similarity index to quantify the relationship of a measured spectral signature to a theoretical fault signature. A vibration sensor detects vibrations on machinery with rotating components. The vibration sensor generates a representation of the vibration and provides it to a vibration analyzer. The vibration analyzer is configured to identify peak amplitudes in the generated representation, determine a corresponding frequency for each of the peak amplitudes, and match the determined corresponding frequencies to a theoretical set of frequencies. The analyzer determines a number of matching frequencies and identifies a detection condition when the number of matching frequencies meets a predetermined criterion. The system and method combines vibration amplitude threshold detection with similarity index threshold detection to significantly reduce false fault alarms and false pass errors.

Abstract: An image analysis method designed to identify images in a sequence of images that are statistically different in a pre-selected region of interest. The method is suitable when there is no a priori knowledge of the nature of the interesting images. A reference image is used to identify specific regions of the image that may contain interesting changes (Detect Zone), that will not have interesting changes, but can be used to assess image quality (Veto zone), and an unanalyzed region (Ignore zone). To improve the spatial sensitivity, the Detect and Veto zones can be divided into specific cells. The analysis may also be performed on compressed data and another method automatically classifies a cell as either in the Detect zone or Ignore zone. The sensitivity can be further improved by removing periodic feature variation prior to the statistics calculation.

Abstract: An image analysis method designed to identify images in a sequence of images that are statistically different in a pre-selected region of interest. The method is suitable when there is no a priori knowledge of the nature of the interesting images. A reference image is used to identify specific regions of the image that may contain interesting changes (Detect Zone), that will not have interesting changes, but can be used to assess image quality (Veto zone), and an unanalyzed region (Ignore zone). To improve the spatial sensitivity, the Detect and Veto zones can be divided into specific cells. The analysis may also be performed on compressed data and another method automatically classifies a cell as either in the Detect zone or Ignore zone. The sensitivity can be further improved by removing periodic feature variation prior to the statistics calculation.

Abstract: A gear defect analyzing system records the interaction of each tooth of a gear system until the interaction begins to repeat and then processes the information in such a way as to identify defective gear tooth. Signals from a gear box are detected by an accelerometer and a shaft encoder and fed to an interface circuit and then to an analog signal preprocessing circuit. The preprocessing circuit conditions the signal so that it can be analyzed by a microcomputer. The system has the capability of identifying the class of incoming signals, determining the optimal time domain average, eliminating unwanted spectral components and interference, computing specific measurements relating to gear wear and then performing analysis of time history within a given system operating state to determine which gears and gear teeth are defective. By recording each tooth-to-tooth interaction over a period of time, and then processing the recorded matrix of data, it is possible to locate individual tooth defects.