Hyundai Motor Company

Kia Motors Corporation

Kia Corporation

Seoul National University

Industry-university Cooperation Foundation Hanyang University

Kookmin University

Jae-Min Jin

In-Soo Jung

Seung-Hyun Lee

Dong-Chul Lee

Joon-Hyuk Chang

Yong-Joo Lee

Kyoung-Doug Min

Seung-Il Lee

Sung-Hwan Shin

An embodiment method of predicting vehicle clutch life based on real-time judder diagnosis includes storing to a cloud server actual road driving data measured by an actual road driving information collection device while a vehicle travels, extracting a judder occurrence entry condition by downloading the actual road driving data from the cloud server and checking judder occurrence information in a clutch life prediction device, calculating a judder index by checking judder index information from the actual road driving data in the clutch life prediction device, predicting a clutch useful life of a double clutch transmission (DCT) using a clutch useful life prediction curve for the judder index, and generating a maintenance notification at a time of clutch maintenance.

Method of predicting vehicle clutch life based on real-time judder diagnosis and system for diagnosing vehicle judder in real time

A vehicle judder diagnostic method using artificial intelligence applied to a mobile-based GDS according to the present disclosure is characterized in that the mobile-based GDS samples a plurality of sensor signals of a sensor mounted in a vehicle in a vehicle during operation in a judder evaluation mode to quickly, separately diagnose whether the judder phenomenon of the vehicle is a geometric judder or a friction judder by mounting a deep neural network (DNN) model, developed by the trial and error process of a DNN by using the plurality of sensor signals of a test vehicle mounted with a double clutch transmission (DCT), as a judder determination artificial intelligence modelin the mobile-based GDS.

Vehicle judder diagnostic method using artificial intelligence and mobile-based GDS

An automation method of an artificial intelligence (AI)-based diagnostic technology for equipment application includes receiving one or more pieces of data among vibration data, noise data, and controller area network (CAN) data, a data input processing operation of trimming the input data, an operation of extracting features from the trimmed data, setting a setting value of a hyper-parameter with respect to the one or more pieces of data thereamong, and generating a total of N models to include both of machine learning (ML) and deep learning (DL) as N individual models and generating ensemble prediction model structures for the N individual models. As a parameter updating is being proceeded due to the hyper-parameter so as to minimize values of cost functions of the N individual models, a reward for model accuracy performance is optimized and the ensemble prediction model structures of the N individual models change.

Automation method of AI-based diagnostic technology for equipment application

A mechanical diagnosis method for combustion abnormality using engine noise includes: calculating an Energy K and a Loudness standard deviation index (N) with Kurtosis analysis by a diagnosis controllerfrom noise data measured together with a signal component by rotation excitation of an engine; calculating a plurality of order frequency peak order component values by a Modulation Frequency Transform; and distinguishing a cylinder where abnormal combustion occurs from a cylinder where normal combustion occurs by applying a predetermined threshold to these calculated values, thereby classifying, by Modulation Frequency analysis, problem samples of the rotation excitation and combustion excitation influence of the engine in which the abnormality state determination of the engine has been difficult only with energy distribution while overcoming the limitation of Kurtosis analysis.

Mechanical combustion abnormality diagnosis determination method and combustion abnormality diagnosis system using engine noise

An engine combustion control method may include: determining, by a controller, whether a fuel injection timing of an engine matches with an engine running condition of the engine; performing, by the controller, when the fuel injection timing matches with the engine running condition of the engine, a fuel injection variable establishment control (or a variable control of a fuel injection timing) that performs a Wavelet process on a frequency band selected by matching a vibration frequency of a vibration sensor signal to an engine frequency transformed under an engine running condition; and when the fuel injection timing matches with the engine running condition, updating a fuel injection parameter by correcting a target value of a combustion factor based on the fuel injection timing.

Sampling vibration frequency rate downsizing type engine combustion control method and engine combustion control system

A method for controlling engine combustion may include receiving a signal of a crank position sensor, determining an angular velocity and an angular acceleration of a crank on the basis of the signal of the crank position sensor, determining a combustion characteristic index for each cylinder using the angular velocity and the angular acceleration of the crank, judging an unstable combustion cylinder using the combustion characteristic index for each cylinder, and changing a combustion factor for controlling the unstable combustion cylinder.

Growing community of inventors

Seoul, South Korea

Jae-Min Jin