Abstract: The present invention discloses a system and method for predicting the dryness of clothing articles in a clothes dryer 10. In one embodiment of this invention, the clothes dryer 10 uses a temperature sensor 52, a phase angle sensor 54, and a humidity sensor 56 to generate signal representations of the temperature of the clothing articles, the motor phase angle, and the humidity of the heated air in the duct, respectively. A controller 58 receives the signal representations and determines a feature vector. A neural network 168 uses the feature vector to predict a percentage of moisture content and a degree of dryness of the clothing articles in the clothes dryer 10. In another embodiment of this invention, the clothes dryer uses a combination of sensors to predicts a percentage of moisture content and a degree of dryness of the clothing articles.

Abstract: An exemplary inspection apparatus for inspecting an article comprises a flexible sensor for sensing a characteristic of the article, which sensor conforms to a surface of the article, a finger cover which fits over a finger of a user, and an attachment device for removably attaching the sensor to the finger cover. The apparatus allows the user to traverse the sensor over a large range of smoothly varying concave or convex inspection surfaces, for example, while providing the user with direct control of the sensor.

Abstract: This invention discloses a system and method for measuring and monitoring three-dimensional shaped objects with projections of computer models of the objects. The computer models of the three-dimensional shaped objects are in the form of grid patterns. An image of the computer model of grid patterns is simultaneously projected from a dual projection system in two directions onto a real world instance of the object. Any variation between the computer model and the real world instance of the object is highlighted directly on the object by interference patterns of the two projections on the real world instance. The variation is quantified by counting the number of interference patterns on the real world instance of the object.

Abstract: The present invention discloses an ultrasonic phased array transducer with an ultralow backfill and a method for making. The ultrasonic phased array includes a low density backfill material having an ultralow acoustic impedance. The backfill material is either an aerogel, a carbon aerogel, an xerogel, or a carbon xerogel. A piezoelectric ceramic material and two matching layers are bonded to the backfill material. In one embodiment, a plurality of interconnect vias are formed in the backfill material with conducting material deposited in the vias. A portion of the bonded matching layers, the piezoelectric ceramic material, and the backfill material have isolation cuts therethrough to form an array of electrically and acoustically isolated individual elements. In a second embodiment, the backfill material is bonded to an electronic layer at a face opposite to the piezoelectric ceramic material and the matching layers.

Abstract: The present invention discloses a system and method for isolating failures in a locomotive. In the present invention, the cause of failures occurring in the locomotive sub-systems are determined quickly and efficiently, while minimizing the need for human interaction. However, the present invention can incorporate information provided by an operator to produce a more refined diagnosis. In the present invention, incidents are recorded in an incident log and mapped to indicators, which are sent to a fault isolator for diagnosis. The fault isolator uses a diagnostic knowledge base having diagnostic information between failures occurring in locomotive and observable symptoms happening therein. A diagnostic engine then processes the mapped indicators with the diagnostic information in the diagnostic knowledge base and produces a list of the most likely causes for any failures. The present invention then provides a course of action to correct the failures.

Abstract: The present invention discloses a system and method for estimating a change point time in a manufacturing process. The change point estimate is estimated by a change point estimator after receiving an alarm from a statistical process control chart. The change point estimate is estimated by estimating the point of a process before and after a particular point in time and declaring the point with the maximum absolute difference to be the change point time. In the present invention there are three versions for estimating the change point estimate. After estimating the change point time any other likely change point times are then determined and used to match the dates of those changes to any possible changes in the product variables that occurred during the manufacturing process. A source causing the change in the process is then identified, allowing an engineer to provide the necessary corrective action to remedy the change.

Abstract: The present invention discloses a method and system for selecting a previously used color match from a plurality of previously used color matches that best matches a color standard. In the present invention, each of the plurality of previously used matches are identified with a spectral reflectance and a color formula. The present invention includes measuring a color spectrum and spectral reflectance of the color standard. The spectral reflectance of each of the plurality of the previously used color matches are then processed. The processed plurality of previously used color matches are searched for a set of previous color matches that have a high probability of being adapted to attain the color spectrum and spectral reflectance of the color standard. Next, a color match that provides the best match with the color of the standard is determined from the set of previous color matches. The formula of the best match is used to reproduce the color of the standard.

Abstract: The present invention discloses a method for building a self-learning evidential reasoning system from examples. In this invention a hierarchical model structure for the self-learning evidential reasoning system is defined. After the model structure has been defined examples are supplied by experts. The examples are entered directly into example spreadsheets and then used to train the model structure. The model structure is then trained to minimize error between model output and the desired output. The error is minimized by using a gradient descent optimization. The model structure is then put into production and then used to make a recommendation. The self-learning evidential reasoning system can be used in various fields, such as analyzing the risk of financial service applications.

Abstract: The present invention discloses a multi-resolution detector for use in an x-ray imaging implementation such as computed tomography and digital radiography. The multi-resolution detector includes a two-dimensional, m.times.n element array of low resolution detector elements and at least one high resolution detector element located about the two-dimensional, m.times.n element array of low resolution detector elements. After an object has been completely scanned with the multi-resolution detector the scan data from both the two-dimensional, m.times.n element array of low resolution detector elements and the high resolution detector element is used to reconstruct a high resolution image. In particular, the scan data generated from the two-dimensional, m.times.n element array of low resolution detector elements is used along with the initial scan data generated from the high resolution detector element to iteratively construct a high resolution image of the object.

Abstract: In this invention there is a method and system for matching new customer records to existing customer records in a database. The new customer records are validated for quality and normalized into a standard form. A hash key is selected to generate a candidate set of records from the existing records in the database that likely matches the new customer records. The new customer records are then matched to each of the records in the candidate set. Once the matching has been performed, a decision is made on whether to create a new customer record, update an existing record, or save the new record in a pending file for resolution at a later time. In another embodiment, there is a methodology for learning matching rules for matching records in a database. The matching rules are then used for matching a new customer record to existing records in a database.

Abstract: A fuzzy logic supervisory control architecture for aircraft engines includes a series of fuzzy proportional integral controllers each designed for a specific operating range and a fuzzy logic hierarchical controller for combining the fuel flow derivative outputs of the individual controllers. The hierarchical controller utilizes fuzzy logic on the input space fuzzified to linguistic values for engine temperature, power turbine speed and spool acceleration to determine a weighting to be given to each of the controller outputs for fuel flow derivative.

Abstract: The present invention discloses a method and system for laser ultrasonic imaging an object. In the present invention, a synthetic aperture focusing technique (SAFT) is used to generate a high resolution subsurface images of the object. In addition, the present invention filters low frequency components from detected laser ultrasound waveform data to further enhance resolution, SNR, and contrast. Geometric knowledge permits the present invention to generate images of objects having a complex and arbitrary-shape.

Abstract: The present invention discloses a system and a method for estimating a measure of confidence in a match generated from a case-based reasoning system. The measure of confidence is determined by using a confidence function that is derived for all existing cases in the case base. The confidence function is then used to estimate the confidence of any matches between a new case and an existing case. In the present invention, a retrieval unit uses a similarity index and retrieves any existing cases from the case base that has a measurement of similarity to the new case that is within a predetermined similarity threshold. The confidence function then maps the similarity measurement for each retrieved case to a corresponding measure of how many different outcomes are likely given the level of similarity. A report of the existing cases that have the best measures of confidence are then provided in a list.

Abstract: The present invention discloses a method and system for inspecting a surface of an object with laser ultrasound. In the present invention, the surface is scanned with a source laser emitting a laser beam at a plurality of scanning positions. The emitted laser beam generates surface or Lamb waves at the plurality of scanning positions and transmits the waves throughout the surface. The surface of the object is scanned with a detector laser emitting a laser beam onto the object surface at the plurality of scanning positions. Surface displacement produced by the waves reflected from the surface is detected with a detector at each scanning position. The detected displacement at each scanning position contains signals representing a laser ultrasound waveform data set corresponding to a two-dimensional surface region along the object. The laser ultrasound waveform data sets at each scanning position are processed with a synthetic aperture focusing technique in order to generate high resolution images.

Abstract: The present invention discloses a method and system for determining the total colorant loading and relative colorant proportions for a color formula that is used for reproducing a color standard. In the present invention, a spectrophotometer measures the spectral reflectance of the color standard. A plurality of color matching attributes are then specified and used for attaining a match with the color standard. A merit function scale for quantifying how well a previously used color match corresponds to the color standard is developed. The merit function scale includes qualitative descriptions for the color matching attributes and a corresponding range of quantitative values. Next, a database of previously used color matches are searched and the merit function scale is used for determining a set of color matches that best approximates the color standard. A color match is determined from the set of previous color matches that optimally reproduces the color standard.

Abstract: The present invention discloses a high density interconnect for an ultrasonic phased array and method for making. The high density interconnect includes a backfill material having grooves formed therein. Each of the grooves are separated a predetermined distance from each other and have a predetermined groove depth. A conducting material is deposited in each of the grooves. The grooved backfill is cut or formed into sections having different lengths. The sections are then reconsolidated into an unitary structure, wherein one end of the structure is electrically conductive in one direction. One surface of the high density interconnect is metallized for bonding with an ultrasonic phased array transducer while the other side is patterned with solder bumps for connection to integrated circuit boards or flexible circuit boards.

Abstract: A method and system create a color match that reproduces a color standard. First, the color spectrum of a color standard is read. After reading the color spectrum, a plurality of formula keys corresponding to the color spectrum of the color standard are obtained. Each of the plurality of formula keys have a different combination of colorants that formulate the color standard. The plurality of formula keys are restricted to combinations that have a greater probability of generating a color match with the color standard. Each of the plurality of formula keys are then evaluated in order of probability of generating a color match with the color standard to determine whether the colorants in each formula key can be combined to reproduce the color standard. The formula keys having a greater probability of generating a color match are evaluated prior to formula keys having a lesser probability of generating a color match. Each evaluation generates a degree of match between each formula key and the color standard.

Abstract: A system and method for determining fiber-depth of at least one layer of reinforcing fibers within an electrically conductive workpiece is provided. The system comprises an eddy current probe having one or more eddy current elements for generating a respective electrical signal indicative of a spacing with respect to a predetermined section of the reinforcing fibers. A signal processor is connected to the eddy current probe to receive and to process each spacing-indication electrical signal so as to generate data indicative of fiber-depth of the predetermined section relative to a workpiece surface. A display device may be connected to the signal processor to provide visual indicia representative of the fiber depth. Further a controller may be connected to receive and store the fiber-depth data which can be used by a machining device for selectively removing material from the workpiece surface, in accordance with the stored fiber-depth data.

Abstract: The present invention discloses a device and method for separating lint particles in a clothes dryer. In the present invention, the device and method use a cyclone to separate the lint particles. The cyclone includes a housing container having an inlet port and an outlet port. A screen is positioned about the inlet port. A tubing extends through the outlet port into the housing container. A drawing means draws moisture and lint laden air from the clothes dryer through the screen. A circulating means circulates the moisture and lint laden air in the housing container about the tubing. A removing means removes the moisture and lint laden air from the housing container and retains any lint particles within the housing container. The cyclone improves upon the efficiency of accumulating lint particles without compromising the passage of air flow in the exhaust duct and improves upon the passage of air flow without decreasing the amount of lint particles being trapped.

Abstract: The present invention discloses a method and system for performing risk and credit analysis of financial service applications with a neural network. The neural network imitates and perfects a credit manager's evaluation and decision process to control loss and guide business expansion. In particular, the neural network screens applications to control loss and to find directions where business volume can increase with a minimum increase in loss. Initially, data variables are pre-processed and applied to the neural network. The neural network in the present invention is optimized by a non-iterative regression process, as opposed to the computationally intensive back propagation algorithm.