Gm Global Technolgoy Operations, Inc.

Indian Institute of Technology Kharagpur

Pulak Bandyopadhyay

Steven W Holland

Yilu Zhang

Mutasim Abdurrahman Salman

Satnam Singh

Soumen De

Guoxian Xiao

Leandro G Barajas

Brian Daniel Kaminski

Rahul G Chougule

Debprakash Patnaik

John Stilianos Agapiou

Yuen-Kwok Chin

Xidong Tang

Mark N Howell

Xiaodong Zhang

Stephan R Biller

Sugato Chakrabarty

Pattada A Kallappa

Sabyasachi Bhattacharya

Qing Chang

George Paul Montgomery, Jr

Fan Bai

Arun Kumar

Xinyu Du

Bo Yu

Ansaf Ibrahem Alrabady

Balarama Vempaty Murty

Jon T Carter

Yong Han Lee

Jorge F Arinez

Shubha Kadambe

Rami I Debouk

Youngkwan Cho

Xiaofeng Mao

Asim Tewari

Fangming Gu

Robert Bruce Tilove

Daniel J Reaume

Deepika Sachdeva

Jeffrey Morgan Alden

Dwight A Blaser

Eric A Steinhilper

Patrick M Hilber

Calvin E Wolf

Kootaala P Unnikrishnan

Andrea M Simon

Basel Q Shadid

Somnath Sengupta

Kiran Deshpande

Siddhartha Mukhopadhyay

Alok Kanti Deb

Ram Dwibhashyam

Robert K Aas

Aloysius Anagonye

Robert J Casper

Jeremy Krall

Joseph M Martinez

Brian W Quinn

A method of detecting anomalies in the service repairs data of equipment. A failure mode-symptom correlation matrix correlates failure modes to symptoms. Diagnostic trouble codes are collected for an actual repair for the equipment. The diagnostic trouble codes are provided to a diagnostic reasoner for identifying failure modes. Diagnostic assessment is applied by the diagnostic reasoner for determining the recommended repairs to perform on the equipment in response to identifying the failure modes. Each of the recommended repairs is compared with the actual repair used to repair the equipment. A mismatch is identified in response to any recommended repair not matching the actual repair. Reports are generated for displaying all of the identified mismatches. The reports are analyzed for determining repair codes having an increase in a number of anomalies. Service centers are alerted of a correct repair for the identified failure mode.

Detecting anomalies in field failure data

A vehicle repair assist system for repairing a vehicle fault in a vehicle. A symptom input module is provided for entering vehicle symptom information relating to the fault. A diagnostic code module retrieves diagnostic trouble codes from the vehicle. The diagnostic trouble codes are generated in response to a fault occurrence. A knowledge-based fault module identifies potential causes of the vehicle fault based on at least one of the symptom information and diagnostic trouble codes. A repair assistant module identifies recommended repair parts and repair procedures for repairing the cause of the vehicle fault. The repair assistant module communicates with the knowledge-based fault module for obtaining a prioritized listing of the recommended repair parts and repair procedures for repairing the vehicle fault.

Repair assist system for vehicle servicing

A method includes collecting state of health (SOH) data and usage data from a plurality of vehicles. A peer group is identified among the vehicles. A vehicle health prognosis is generated for each vehicle of the peer based on the collected SOH and usage data. The vehicles of the peer group are ranked based on the generated vehicle health prognosis and the rank is reported to an output device that is associated with each vehicle or with a user of each vehicle. If evaluation of the ranking indicates that the health prognosis of a vehicle of the peer group is improvable by modifying vehicle usage, an alert is issued to a user of that vehicle.

Vehicle health prognosis

A method and system for using Equivalent Time Sampling to improve the effective sampling rate of sensor data, and using the improved-resolution data for diagnosis and control. Data samples from existing sensors are provided, where the sampling rate of the existing sensors is not sufficient to accurately characterize the parameters being measured. High-resolution data sets are reconstructed using Equivalent Time Sampling. High-resolution input data sets are used in a system model to simulate the performance of the system being measured. Results from the system model, and high-resolution output data sets from Equivalent Time Sampling, are provided to an estimator, which provides accurate estimation of measured quantities and estimation of quantities not measured. Output from the estimator is used for fault diagnosis and control of the system being measured.

State estimation, diagnosis and control using equivalent time sampling

A vehicle fault diagnosis and prognosis system includes a computing platform configured to receive a classifier from a remote server, the computing platform tangibly embodying computer-executable instructions for evaluating data sequences received from a vehicle control network and applying the classifier to the data sequences, wherein the classifier is configured to determine if the data sequences define a pattern that is associated with a particular fault.

Fault prediction framework using temporal data mining

A method and system for comparing and merging fault models which are derived from different data sources. Two or more fault models are first represented as bipartite weighted graphs, which define correlations between failure modes and symptoms. The nodes of the graphs are compared to find failure modes and symptoms which are the same even though the specific terminology may be different. A graph matching method is then used to compare the graphs and determine which failure mode and symptom correlations are common between them. Finally, smoothing techniques and domain expert knowledge are used to merge and update the fault models, producing an integrated fault model which can be used by onboard vehicle systems, service facilities, and others.

Graph matching system for comparing and merging fault models

A system may be used to detect corrosion between a first metal and a second metal, where the second metal is positioned adjacent to the first metal. The system may include a processor electrically coupled to each of the first and the second metals and configured to monitor a complex impedance between the first metal and the second metal, where the complex impedance may include a real component and an imaginary component. The processor may compare the real component of the complex impedance to a first threshold, compare the imaginary component of the complex impedance to a second threshold, and indicate a likelihood of corrosion if at least one of the real and imaginary components are below their respective threshold.

System and method for detecting a likelihood of corrosion

A method is provided for enhancing service diagnostics utilizing service repair data of previously serviced vehicles. Service repair data of previously serviced vehicles is obtained from a memory storage device. The service data is compiled into a service diagnostic code dataset and a service labor code dataset. The service diagnostic code dataset and service labor code dataset are categorized into an electronic data table. Respective combinations are formed in the electronic data table. An aggregate count is determined for each respective combination in the electronic data table. Either of a respective diagnostic code or a respective service labor code is identified having a correlation with more than one of either service diagnostic codes or service labor codes. At least one of a service repair procedure used to repair the vehicle or a respective service diagnostic code used to identify the fault is modified in response to analyzing the respective combinations.

Process for service diagnostic and service procedures enhancement

Systems and methods for capturing and analyzing significant parameter data from vehicle systems whenever a diagnostic trouble code (DTC) is triggered. A multi-dimensional matrix is constructed, with vehicles, DTCs, and parameter data comprising three dimensions of the matrix. The data matrix is populated with DTC and parameter data from many different vehicles, either when vehicles are taken to a dealer for service, or via wireless data download. Time can be added as a fourth dimension of the matrix, providing an indication of whether a particular system or component is temporally degrading. When sufficient data is accumulated, the data matrix is pre-processed, features are extracted from the data, and the features are classified, using a variety of mathematical techniques. Trained classifiers are then used to diagnose the root cause of any particular fault signal, and also to provide a prognosis of system health and remaining useful life.

Event-driven fault diagnosis framework for automotive systems

An integrated diagnosis and prognosis system that collects vehicle information over the life of a vehicle and its development. The system provides the collected vehicle information to supplier management, product development management, service/dealership management, customer relations departments and production facilities, which use the information to take certain action for existing vehicles, fleets of vehicles or future vehicles to improve vehicle reliability and quality.

Integrated diagnosis and prognosis system as part of the corporate value chain

Manufacturing facility process optimization includes monitoring communication signals within a facility device network, analyzing work station specific patterns in the communication signals, developing operational dependencies for work stations based upon the work station specific patterns, and predictively evaluating impacts to the work stations of the proposed configuration of the manufacturing facility process based upon the operational dependencies.

Method for distributed hybrid emulation of manufacturing systems

A system and method for enhancing vehicle diagnostic and prognostic algorithms and improving vehicle maintenance practices. The method includes collecting data from vehicle components, sub-systems and systems, and storing the collected data in a database. The collected and stored data can be from multiple sources for similar vehicles or similar components and can include various types of trouble codes and labor codes as well as other information, such as operational data and physics of failure data, which are fused together. The method generates classes for different vehicle components, sub-systems and systems, and builds feature extractors for each class using data mining techniques of the data stored in the database. The method also generates classifiers that classify the features for each class. The feature extractors and feature classifiers are used to determine when a fault condition has occurred for a vehicle component, sub-system or system.

Aggregated information fusion for enhanced diagnostics, prognostics and maintenance practices of vehicles

Disclosed herein are a system and method for trend prediction of signals in a time series using a Markov model. The method includes receiving a plurality of data series and input parameters, where the input parameters include a time step parameter, preprocessing the plurality of data series according to the input parameters, to form binned and classified data series, and processing the binned and classified data series. The processing includes initializing a Markov model for trend prediction, and training the Markov model for trend prediction of the binned and classified data series to form a trained Markov model. The method further includes deploying the trained Markov model for trend prediction, including outputting trend predictions. The method develops an architecture for the Markov model from the data series and the input parameters, and disposes the Markov model, having the architecture, for trend prediction.

System and method for signal prediction

Disclosed herein are a system, method and apparatus for reporting, making alerts and predicting fault codes generated by machines in a line. Historical fault code data is received and filtered according to particular criteria to generate filtered fault code data. Classification of the filtered fault code data into physical groups and into logical groups is followed by sorting the groups to produce fault trend data. Processing the fault trend data with a plurality of analyzers generates output including reports, alerts, and predictions of future fault code occurrences.

System and method for production system performance prediction

Methods, systems, and computer program products for controlling production systems. Methods include monitoring actual performance of a production system that includes a plurality of machines. The actual performance of the production system is compared to a planned level of performance of the production system. One or more short-term production constraints in the production system are identified in response to the actual performance being more than a threshold value away from the planned level of performance. A corrective action for the production system is determined to mitigate one or more of the short-term production constraints. The corrective action is applied to the production system.

Applying real-time control to a production system

Growing community of inventors

Rochester Hills, MI, United States of America

Pulak Bandyopadhyay