Abstract: Various embodiments of the present invention disclose techniques for determining a graph-based prediction based at least in part on a cross-entity relationship graph data object and using a hybrid graph-based processing machine learning framework. In some embodiments, the hybrid graph-based prediction machine learning framework is configured to generate the graph-based prediction based at least in part on a comprehensive representation of the cross-entity relationship graph data object that is generated based at least in part on output data of a graph convolutional neural machine learning model and an image-based graph convolutional neural network machine learning model.

Abstract: A method includes obtaining a series of more than two Boolean events, each respective Boolean event having either a first value indicating that reimbursement for a respective overpayment of a service was timely received or a second value indicating reimbursement was not timely received. The method includes determining an actual number of switch events in the series of Boolean events and determining an expected number of switch events. The method includes determining a confidence interval for the expected number of switch events, and determining a score based on the actual number of switch events, the expected number of switch events, and the confidence interval. The score is indicative of a fault in a process generating the series of Boolean events. The method includes generating an alert based on the score being greater than or equal to a threshold score.

Abstract: An oxygen storage capacity (OSC) monitoring system for a vehicle having a catalytic converter includes an inlet oxygen sensor that generates an inlet sensor signal (ISS) based on an oxygen content of exhaust flowing into the catalytic converter. A control module receives the ISS, increases a closed loop fuel control gain during a first period and determines a fuel control factor based on the ISS during the first period. The control module determines an OSC when an average value of the fuel control factor is greater than a first value and is less than a second value during the first period.

Abstract: A method for detecting emissions from an internal combustion engine generally including determining a reference air/fuel mixture signal based on an engine speed and an airflow into the engine. The method includes determining an actual air/fuel mixture signal from an air/fuel mixture sensor and comparing the reference air/fuel mixture signal to the actual air/fuel mixture signal. The method also includes determining whether an air/fuel imbalance condition occurs based on the comparison and setting a service indicator based on the determination of whether the air/fuel imbalance condition occurred.

Abstract: A fuel control compensation system for sensor degradation in an exhaust system of a vehicle includes a first module that determines a response time of a signal generated by a sensor of the exhaust system. A second module determines an offset gain based on the response time and a nominal response time. Fuel control of an engine of the vehicle is regulated based on the offset gain.

Abstract: A method of generating a metric data set for determining a performance of a catalytic converter includes sampling data from a post catalytic converter oxygen sensor to provide a raw data set and generating a revised data set based on the raw data set. Data within the revised data set is eliminated based on characteristics of data points of the revised data set and the revised data set is filtered to provide the metric data set.

Abstract: An engine diagnostic system includes a catalytic converter and an outlet O2 sensor. The outlet O2 sensor generates an outlet signal that is based on an oxygen level of exhaust gases exiting the catalytic converter. A controller adjusts a secondary fuel trim based on the outlet signal. The controller indicates a fault status if the secondary fuel trim has achieved a fuel trim limit and the outlet signal is out of a diagnostic range.

Abstract: A method and apparatus for controlling the equivalence ratio in an internal combustion engine to improve catalytic converter performance including varying an equivalence ratio setpoint between a rich and a lean state periodically, and introducing a fuel enrichment pulse to the equivalence ratio that sweeps the equivalence ratio across stoichiometry.