18099442. APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR simplified abstract (HYUNDAI MOTOR COMPANY)
Contents
- 1 APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR
Organization Name
Inventor(s)
Tae Woong Park of Hwaseong-si (KR)
Jae Hun Kim of Hwaseong-si (KR)
APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR - A simplified explanation of the abstract
This abstract first appeared for US patent application 18099442 titled 'APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR DIAGNOSING FAULT OF VEHICLE COMPONENT USING ACCELERATION SENSOR
Simplified Explanation
The patent application describes an apparatus for diagnosing a fault of a vehicle component using an acceleration sensor, feature extraction unit, and machine learning model.
- The apparatus includes a processor, memory, and programs for executing the diagnostic process.
- An acceleration sensor is used to detect an acceleration signal from the vehicle.
- A feature extraction unit extracts features related to the fault of the vehicle component from the acceleration signal.
- A machine learning model diagnoses the fault based on the extracted features, selected according to a preset evaluation index among a variety of trained models.
Potential Applications
This technology could be applied in the automotive industry for real-time fault diagnosis of vehicle components, leading to improved maintenance and safety measures.
Problems Solved
This technology helps in quickly identifying faults in vehicle components, reducing downtime and potential safety hazards for drivers and passengers.
Benefits
The benefits of this technology include increased efficiency in diagnosing vehicle faults, leading to cost savings for vehicle owners and improved overall performance and safety of vehicles.
Potential Commercial Applications
One potential commercial application of this technology could be in the development of diagnostic tools for automotive service centers, allowing them to offer more accurate and efficient vehicle maintenance services.
Possible Prior Art
One possible prior art for this technology could be existing diagnostic tools used in the automotive industry that rely on sensor data and machine learning algorithms for fault detection.
Unanswered Questions
How does the apparatus handle different types of vehicle components and faults?
The patent application does not specify how the apparatus can adapt to various types of vehicle components and faults during the diagnostic process.
What is the accuracy rate of the machine learning model in diagnosing faults?
The patent application does not provide information on the accuracy rate of the machine learning model in diagnosing faults of vehicle components.
Original Abstract Submitted
An apparatus for diagnosing a fault of a vehicle component, may include: a processor; a memory storing one or more programs configured to be executed by the processor; and the one or more programs include instructions for: an acceleration sensor for detecting an acceleration signal; feature extraction unit for extracting features related to a fault of a vehicle component from the detected acceleration signal; and a machine learning model for diagnosing a fault of the vehicle component based on the extracted features, wherein the machine learning model may be a model selected according to a preset evaluation index among a plurality of machine learning models trained based on training data sets.
