Search

KR-20260067488-A - METHOD FOR DETECTING ABNORMAL SIGN OF ELECTIC VEHICLE IN MECHANICAL PARKING STATION

KR20260067488AKR 20260067488 AKR20260067488 AKR 20260067488AKR-20260067488-A

Abstract

Embodiments of the present invention relate to a method for detecting abnormal signs of an electric vehicle in a mechanical parking lot, and more specifically, to a method for detecting abnormal signs of an electric vehicle in a mechanical parking lot that can prevent fire by detecting abnormal signs early before a fire occurs in the mechanical parking lot. According to one embodiment of the present invention, a method for detecting abnormal signs of an electric vehicle in a mechanical parking lot is provided, comprising: a step of sensing a plurality of detection targets regarding the electric vehicle in the mechanical parking lot; a step of collecting measurement information from the plurality of detection targets sensed; a step of preprocessing abnormal sign-related data from the measurement information; and a step of determining whether there is an abnormal sign of the electric vehicle by training the preprocessed data with an AI.

Inventors

  • 김종욱
  • 송우승

Assignees

  • 사단법인 도시생명네트워크

Dates

Publication Date
20260513
Application Date
20241105

Claims (5)

  1. In a method for detecting abnormal signs of an electric vehicle in a mechanical parking garage, A step of sensing a plurality of detection targets for the electric vehicle in the above mechanical parking lot; A step of collecting measurement information from a plurality of sensed targets; A step of preprocessing abnormal sign-related data from the above measurement information; and A method for detecting abnormal signs in an electric vehicle in a mechanical parking lot, comprising the step of determining whether there are abnormal signs in the electric vehicle by training an AI on the above-mentioned preprocessed data.
  2. In claim 1, A method for detecting abnormal signs in an electric vehicle within a mechanical parking garage, wherein the above abnormal sign is the possibility of fire in the battery of the electric vehicle.
  3. In claim 1, The above plurality of detection targets are, A method for detecting abnormal signs of an electric vehicle in a mechanical parking lot, comprising at least some of the following: BMS information of the battery of the electric vehicle, the temperature of the battery, off-gas from the battery, sound generated from the battery, a thermal image of the electric vehicle, and an image of the electric vehicle.
  4. In claim 1, The above data preprocessing is, A step of refining the above data; A step of extracting features for identifying abnormal signs of the above electric vehicle; A step of labeling the above data; and A method for detecting abnormal signs of an electric vehicle in a mechanical parking lot, comprising the step of normalizing and standardizing the above data.
  5. In claim 1, A method for detecting abnormal signs in an electric vehicle within a mechanical parking lot, further comprising the step of transmitting to the outside whether there are abnormal signs in the electric vehicle.

Description

Method for detecting abnormal signs of electric vehicles in mechanical parking stations Embodiments of the present invention relate to a method for detecting abnormal signs in an electric vehicle within a mechanical parking garage, and more specifically, to a method for detecting abnormal signs in an electric vehicle within a mechanical parking garage that can prevent a fire by detecting abnormal signs early before a fire occurs in the mechanical parking garage. Recently, the adoption of electric vehicles has been steadily expanding. Due to the characteristics of electric vehicles, the spread of a fire in a vehicle is very rapid, taking only 5 to 10 minutes, which makes it difficult for fire trucks to respond immediately to the scene. The main cause of electric vehicle fires is the battery located in the vehicle's undercarriage. When a fire occurs, it spreads to the surrounding area within a short period of time, and the flames, reaching temperatures of nearly 1400 degrees, cause significant damage to underground parking structures such as floors, beams, and pillars, raising concerns about building collapse. If an electric vehicle catches fire, a rapid response is required for initial fire suppression; however, since there are limitations to extinguishing the fire once it has already progressed, it is necessary to quickly identify abnormal signs before it develops into a fire. In particular, mechanical parking lots are being continuously installed, primarily in areas with high parking demand, as they feature independent parking spaces in building and tower configurations, typically utilizing elevator-type parking systems that allow multiple vehicles to be parked in a limited space for entry and exit. In this case, the parking tower facilitates the entry and exit of vehicles by using a method where, once a vehicle stops at a single entrance, it is transported to a parking space via a separate device. However, when a fire breaks out in a vehicle inside a parking tower, it cannot be extinguished and easily spreads to surrounding vehicles, causing significant damage. In particular, electric vehicles, which have been increasing recently, have a problem in that they cannot extinguish fires in electric vehicles with fire extinguishing equipment installed in narrow parking towers, as fires cannot be suppressed by simply spraying fire extinguishing liquid when the fire spreads to the battery and they must be moved to an open area for separate firefighting operations. FIG. 1 is a drawing illustrating a system for detecting abnormal signs in an above-ground mechanical parking system, and FIG. 2 is a drawing illustrating a system for detecting abnormal signs in an underground mechanical parking system. Figure 3 is a graph showing the situation in which a fire develops in an electric vehicle battery. FIG. 4 is a drawing showing a detection target, which is an element indicating abnormal signs in an electric vehicle battery. FIG. 5 is a flowchart illustrating a method for detecting abnormal signs of an electric vehicle in a mechanical parking lot according to an embodiment of the present invention. FIG. 6 is a flowchart showing the detailed steps of the step (S30) of preprocessing abnormal sign-related data. FIG. 7 is a drawing showing the screen displayed on a terminal when transmitting whether there are signs of an electric vehicle abnormality to the outside. Specific embodiments will be described below with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatuses, and/or systems described herein. However, this is merely illustrative and the disclosed embodiments are not limited thereto. In describing the embodiments, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions could unnecessarily obscure the essence of the disclosed embodiments. Furthermore, terms described below are defined in consideration of their functions in the disclosed embodiments, and these may vary depending on the intent or practice of the user or operator. Therefore, such definitions should be based on the content throughout this specification. Terms used in the detailed description are intended merely to describe the embodiments and should not be limiting. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form. In this description, expressions such as "include" or "comprise" are intended to refer to certain characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof other than those described. Figure 1 is a drawing illustrating a system for detecting abnormal signs in an above-ground mechanical parking garage, and Figure 2 is a drawing illustra