Ford Motor Company Limited

Nathan R Soderborg

Mahesh Vora

Agus Sudjianto

Timothy Mark Feldkamp

John V James

Kenneth A Marko

Bruce David Bryant

Toni Brockers

John King

Dingjun Li

Carolyn Zelek

Siyuan Jiang

Xiaoping Liu

Steve C Wang

David John Buche

A method and computer-implemented system for optimizing a product. Based on the 'voice of the customer', aspects of the product that are critical to the customer satisfaction, and target values, therefore, are identified. Aspects are characterized in terms of their contributing factors. Each contributing factor is characterized in a transfer function in terms of control and noise factors impacting the contributing factors. Contributing factors are optimized during product design by shifting nominal design values for control factors with respect to the transfer function such that target contributing factors are attained with minimum variability due to existing noises and variability in control. Where target values cannot be obtained through design optimization, conventional methods of manufacturing optimization are implemented. The extent to which the target values are attained and maintained over the life of the product are assessed.

Method and system for product optimization

A systemwhich receives a computer, aided model or designand which probabilistically analyzes the modelby use of a modified Latin Hypercube sampling technique and combined MARS and Kriging simulation methodologies, thereby allowing a simulation to be conducted at a most probable point of operation and allowing products having desired characteristics and attributes to be created.

Method and apparatus for analyzing a design

A system and method for processing test measurements collected from an internal combustion engine that is cold-tested for diagnostic purposes. Test measurements are collected from an engine. The test measurements are 'pre-processed' by filtering and subsampling techniques so that Principle Component Analysis can be applied to condense the quantity of test measurements while still retaining a statistically accurate indication of a majority of the original measurements. The pre-processed test measurements are then passed through one or more classifiers including: a Neural Network classifier, a Fuzzy Logic classifier, a cluster-based classifier (or 'Spherical' classifier) and a Genetic Program classifier. Results from these classifiers can be used to obtain a verdict about an engine (i.e., whether the engine is 'normal' or 'faulty').

System and method for processing test measurements collected from an

System and method for filtering a misfire data stream having numerical values that indicate whether a firing of a cylinder was a misfire or a proper firing, to yield an optimum measurement misfire-rate for accurate and rapid determination of whether an engine is misfiring beyond a threshold level. The method includes measuring firings of the cylinder during operation of the engine to produce measured cylinder firing signals, processing the measured cylinder firing signals received to produce a current misfire detection data stream of first and second logic signals, wherein the first logic signals indicate a current misfire condition and the second logic signals indicate a current normal firing of the engine, combining the current misfire detection data stream with previously detected and stored measured data representing an engine misfire rate, replacing the previously stored measured data by the combined current and previously stored data to produce a misfire rate output measurement, storing threshold values, comparing the combined current and previously stored data and the stored threshold values, generating an actuation signal if the combined current and previously stored data signal exceeds the stored threshold values, and indicating a misfire condition in the engine upon receiving the actuation signal.

System and method for filtering a misfire detecting data stream to yield

Growing community of inventors

Ann Arbor, MI, United States of America

Nathan R Soderborg