WO2023249277A1 - Système de diagnostic et de prédiction de véhicule électrique - Google Patents
Système de diagnostic et de prédiction de véhicule électrique Download PDFInfo
- Publication number
- WO2023249277A1 WO2023249277A1 PCT/KR2023/007260 KR2023007260W WO2023249277A1 WO 2023249277 A1 WO2023249277 A1 WO 2023249277A1 KR 2023007260 W KR2023007260 W KR 2023007260W WO 2023249277 A1 WO2023249277 A1 WO 2023249277A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- electric vehicle
- component
- graph
- vehicle monitoring
- sensing
- Prior art date
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 31
- 238000012806 monitoring device Methods 0.000 claims abstract description 97
- 238000012544 monitoring process Methods 0.000 claims abstract description 75
- 238000012790 confirmation Methods 0.000 claims abstract description 16
- 238000004393 prognosis Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 25
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 description 8
- 230000002265 prevention Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Definitions
- the present invention relates to an electric vehicle diagnosis and prognosis system, and more specifically, to an electric vehicle diagnosis and prognosis system that can predict failure of an electric vehicle by learning time series data of electric vehicle parts.
- a typical electric vehicle charger flows current from the charger to the battery in order to charge the battery in the electric vehicle.
- current may accidentally flow in the reverse direction from the battery to the charger.
- a reverse current prevention diode is generally provided in the charger.
- An electric vehicle charger uses a power conversion device that receives alternating current power and converts it into direct current to charge the battery inside the electric vehicle.
- Power conversion devices may be manufactured and used as a single large capacity device, but may also be used by connecting multiple small capacity power conversion devices in parallel.
- the small capacity power conversion device described above is called a power conversion module or charging module.
- a reverse current prevention diode In the case of a general charging module, a reverse current prevention diode is built into the charging module. If an electric vehicle charger is used for a long time, the reverse current prevention diode may fail. Diodes are semiconductors, so when they fail, they usually become short-circuited. If the reverse current prevention diode fails and becomes short-circuited, reverse current may flow from the vehicle battery to the charger in the early stages of charging.
- the reverse current charges the large capacitance installed on the output side of the charger (right in front of the reverse current prevention diode), it instantaneously becomes a very large surge-type current.
- a separate current sensor is attached to the output side of the charger, and when a large surge current flows, the control circuit detects this and blocks the circuit.
- Korean Patent Publication No. 10-2019-0065906 relates to a method and device for detecting failure of an electric vehicle charger. More specifically, when a reverse current in the form of a surge current flows from the battery to the charger during the electric vehicle charging process, the battery and surrounding circuits may fail. Therefore, it is disclosed that it is possible to detect the presence or absence of a reverse current prevention diode failure in order to prevent reverse current occurring during the charging process of an electric vehicle.
- Korean Patent No. 10-2471911 relates to an intelligent electrical fire prediction monitoring and control system and an electrical fire prediction monitoring and control method using the same. More specifically, it is a sensor that detects electrical signals generated from a power system unit including a plurality of power facilities. Detects various types of current signals through an electrical sensor, monitors them in real time in the signal processing unit, generates and stores various types of converted pattern data, analyzes change trends, and detects leakage current, which is the resistance component of electrical equipment technical standards. It is disclosed that through real-time monitoring, abnormal signs such as leakage current and overcurrent, which are the causes of accidents, can be detected and the cause of the defect can be diagnosed.
- Korean Patent No. 10-2456499 relates to an integrated information system for electric vehicle maintenance, and more specifically, to store and manage knowledge information related to electric vehicles, knowledge information for electric vehicle maintenance, and data for configuration management of electric vehicles.
- information for maintenance of electric vehicles can be managed by integrating all information according to users, electric vehicle handling companies, and mechanics.
- Korean Patent No. 10-2043050 relates to an electric vehicle charger failure determination system. More specifically, if a reverse current in the form of a surge current flows from the battery to the charger during the electric vehicle charging process, the battery and surrounding circuits may fail, so the electric vehicle charging Provides a failure detection method and device for an electric vehicle charger that detects the presence or absence of a failure of the reverse current prevention diode to prevent reverse current occurring in the process.
- Korean Patent Publication No. 10-2021-0041724 relates to a failure determination system for an electric vehicle charger. More specifically, it relates to a device and method for predicting failure of an electric vehicle charger by using artificial intelligence technology to input the surrounding environment of the electric vehicle charger.
- the method of operating an electronic device for predicting a failure of an electric vehicle charger includes acquiring sensor data measured by a sensor provided in a first electric vehicle charger, and obtaining regional information indicating the area where the first electric vehicle charger is located. An operation of acquiring weather information at the time when the sensor data of the area was measured, an artificial neural network using the sensor data, the area information, and the weather information as input variables, and the operating state of the electric vehicle charger as an output variable.
- the purpose of the present invention is to provide an electric vehicle diagnosis and prognosis system that can predict failure of an electric vehicle by learning time series data of electric vehicle parts.
- the purpose of the present invention is to provide an electric vehicle diagnosis and prognosis system that analyzes sensing data for each electric vehicle component to diagnose the condition of each component and prevents the occurrence of failure.
- An electric vehicle diagnosis and prognosis system receives sensing information for each part from a plurality of sensors formed on each part of the electric vehicle, an electric vehicle monitoring device that receives and provides sensing values for each component, and an electric vehicle monitoring device that receives and provides sensing values for each component from the electric vehicle monitoring device.
- An electric vehicle monitoring server that uses the received sensing value for each part to check the status of the part and provides the verification result, and upon receiving the verification result from the electric vehicle monitoring server, a user terminal that performs inspection of the electric vehicle according to the verification result.
- the electric vehicle monitoring device may receive sensing values for each component measured by a sensor, display them as a first graph, divide the first graph into specific units, compress it, and provide it.
- the electric vehicle monitoring server expresses the sensing value for each component as a third graph, analyzes the third graph, determines that the state of the component is normal if the sensing value falls within the normal range, and displays the third graph. If the sensing value is outside the normal range through analysis, the condition of the component can be determined to be abnormal.
- the electric vehicle monitoring server expresses the sensing value for each component as a third graph, determines the performance of the component by analyzing the third graph, and then determines the state of the component according to the matching scenario.
- an electric vehicle diagnosis and prognosis method for achieving this purpose includes the steps of an electric vehicle monitoring device receiving sensing information for each component from a plurality of sensors formed on each component of the electric vehicle and providing the component-specific sensing information to an electric vehicle monitoring server, wherein the electric vehicle monitoring server Checking the status of the part using the sensing value for each part received from the electric vehicle monitoring device and providing it to the user terminal; and when the user terminal receives the confirmation result from the electric vehicle monitoring server, inspecting the electric vehicle according to the confirmation result. May include execution steps.
- the step of the electric vehicle monitoring device receiving component-specific sensing information from a plurality of sensors formed on each component of the electric vehicle and providing the component-specific sensing information to the electric vehicle monitoring server includes the electric vehicle monitoring device receiving component-specific sensing information measured by the sensor. It may include receiving a value, displaying it as a first graph, dividing the first graph into specific units, compressing it, and providing it to an electric vehicle monitoring server.
- the step of the electric vehicle monitoring server checking the status of the component using the sensing value for each component received from the electric vehicle monitoring device and providing the component to the user terminal is the step of the electric vehicle monitoring server sending the sensing value for each component to a third Express it in a graph and analyze the third graph to determine that the part is in a normal state if the sensing value is within the normal range. If the sensing value is outside the normal range by analyzing the third graph, the part is judged to be in an abnormal state. It may include steps.
- the step of the electric vehicle monitoring server checking the status of the component using the sensing value for each component received from the electric vehicle monitoring device and providing the status to the user terminal represents the sensing value for each component in a third graph, After determining the performance of the part by analyzing the third graph, the state of the part can be determined according to the matching scenario.
- the electric vehicle diagnosis and prognosis system to achieve this purpose includes an electric vehicle monitoring device that receives sensing information for each component from a plurality of sensors formed on each component of the electric vehicle, and receives and provides sensing values for each component, the electric vehicle monitoring device The user checks the status of the part using the sensing value for each part received from the user, and upon receiving the confirmation result from the metaverse server and the electric vehicle monitoring server that provides the confirmation result, performs inspection of the electric vehicle according to the confirmation result. Includes terminal.
- the electric vehicle monitoring device may receive sensing values for each component measured by a sensor, display them as a first graph, divide the first graph into specific units, compress it, and provide it.
- the metaverse server expresses the sensing value for each component as a third graph, analyzes the third graph, determines that the state of the component is normal if the sensing value falls within the normal range, and displays the third graph. If the sensing value is outside the normal range through analysis, the condition of the component can be determined to be abnormal.
- the metaverse server expresses the sensing value for each component as a third graph, determines the performance of the component by analyzing the third graph, and then determines the state of the component according to the matching scenario.
- FIG. 1 is a network configuration diagram for explaining an electric vehicle diagnosis and prognosis system according to an embodiment of the present invention.
- Figure 2 is a network configuration diagram for explaining an electric vehicle diagnosis and prognosis system according to another embodiment of the present invention.
- Figure 3 is a flowchart illustrating an embodiment of the electric vehicle diagnosis and prognosis method according to the present invention.
- Figure 4 is a flowchart illustrating an embodiment of the electric vehicle diagnosis and prognosis method according to the present invention.
- Figure 5 is a diagram for explaining the internal structure of an electric vehicle monitoring device according to an embodiment of the present invention.
- parts may include a battery, motor, OBC (On Board Charger), LDC (Low Voltage DC-DC Converter), AAF (Acrive Air Flap), and GPS.
- OBC On Board Charger
- LDC Low Voltage DC-DC Converter
- AAF Automatic Air Flap
- FIG. 1 is a network configuration diagram for explaining an electric vehicle diagnosis and prognosis system according to an embodiment of the present invention.
- the electric vehicle diagnosis and prognosis system includes an electric vehicle monitoring device 100, an electric vehicle monitoring server 200, a user terminal 300, and a plurality of sensors 400_1 to 400_N.
- the electric vehicle monitoring device 100 includes a plurality of sensors (400_1 to 400_N), and the plurality of sensors (400_1 to 400_N) are formed on each part of the electric vehicle 500 to generate sensing information and then transmit the sensing information to the electric vehicle monitoring server.
- the plurality of sensors (400_1 to 400_N) may be implemented as a current sensor, pressure sensor, temperature sensor, vibration sensor, noise sensor, current sensor, etc.
- the electric vehicle monitoring device 100 receives sensing information for each component from a plurality of sensors 400_1 to 400_N formed on each component of the electric vehicle 500, and provides the sensing information for each component to the electric vehicle monitoring server 200. At this time, the electric vehicle monitoring device 100 measures the sensing value for each component received from each component of the electric vehicle 500 and displays it in a first graph.
- the electric vehicle monitoring device 100 receives the sensing value for each component measured by the sensor and displays it in a first graph. At this time, the shape displayed in the first graph is different depending on the state of the component.
- the electric vehicle monitoring device 100 provides the sensing value for each part to the electric vehicle monitoring device 100 each time it receives the sensing value for each part, traffic increases and costs increase. Therefore, the sensing value for each part received from the sensor continuously The compressed sensing value for each component is provided to the electric vehicle monitoring server 200.
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups.
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups.
- the electric vehicle monitoring device 100 analyzes the first graph and, if a waveform exists, divides and groups the graph into a period unit to create a plurality of groups.
- the electric vehicle monitoring device 100 compresses the sensing value of each group of a plurality of groups.
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups, and calculates an average value by averaging the sensing values of the group for each of the plurality of groups. At this time, the electric vehicle monitoring device 100 may divide the sensing values in the first graph into specific number units to create a plurality of groups.
- the electric vehicle monitoring device 100 compresses the sensing values of each of the plurality of groups and displays them as a second graph, then extracts a specific sensing value from the second graph corresponding to each group and sends it to the electric vehicle monitoring server 200. to provide.
- the electric vehicle monitoring device 100 averages the sensing values of each of a plurality of groups and displays the calculated average value in a second graph at a location corresponding to the group. At this time, the second graph averages the specific number of sensing values in the group for each group and then displays the sensing value corresponding to the average value.
- the electric vehicle monitoring device 100 averages the sensing values of each of the plurality of groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and displays the average of the sensing values of the corresponding group for each of the plurality of groups. ) is provided.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each group, merges the groups according to the slope difference value, and extracts only one slope value to provide the electric vehicle monitoring server 200 ) is provided.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is less than a certain value, the first group and the second group After merging the groups, the larger slope value of the largest slope value extracted from the first group and the largest slope value extracted from the second group is provided to the electric vehicle monitoring server 200.
- the electric vehicle monitoring device 100 checks the number of currently merged groups before merging the first group and the second group, and if the number of merged groups is more than a certain number, the electric vehicle monitoring device 100 does not perform merging, but does not perform merging. If the number of groups is less than a certain number, merge is performed.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is greater than a certain value, the first group and the second group Without merging the groups, the largest slope value of each of the first group and the second group is provided to the electric vehicle monitoring server 200.
- the electric vehicle monitoring server 200 can check the status of the corresponding component only by the slope value. It is possible.
- the electric vehicle monitoring server 200 uses the sensing value for each component received from the electric vehicle monitoring device 100 to check the status of the component.
- the electric vehicle monitoring server 200 analyzes the third graph to determine whether the sensing value falls within the normal range and determines the state of the corresponding component according to the determination result.
- the electric vehicle monitoring server 200 may analyze the third graph and determine that the state of the component is normal if the sensing value falls within the normal range.
- the electric vehicle monitoring server 200 may analyze the third graph and determine that the state of the component is abnormal if the sensing value is outside the normal range.
- the electric vehicle monitoring server 200 analyzes the third graph and, when the sensing value is outside the normal range, compares the sensing value immediately before deviating from the normal range and the sensing value immediately after deviating from the normal range to sense the difference. If the value is greater than a certain value, it is determined that the state of the corresponding part has suddenly changed to an abnormal state, and a notification message is provided to the administrator terminal.
- the electric vehicle monitoring server 200 determines that the state of the component is abnormal when the section from when the sensing value deviates from the normal range until the sensing value returns to the normal range occurs repeatedly.
- Figure 2 is a network configuration diagram for explaining an electric vehicle diagnosis and prognosis system according to another embodiment of the present invention.
- the electric vehicle monitoring device 100 is formed on each part of an actual electric vehicle, generates a sensing value, and then provides the sensing value to the metaverse server 500.
- the plurality of sensors (400_1 to 400_N) may be implemented as a temperature sensor, vibration sensor, noise sensor, current sensor, etc.
- the electric vehicle monitoring device 100 receives sensing information for each component from a plurality of sensors (400_1 to 400_N) formed on each component of the electric vehicle, and provides sensing information for each component to the metaverse server 500. At this time, the electric vehicle monitoring device 100 measures the sensing value for each component received from each component of the electric vehicle and displays it in the first graph.
- the electric vehicle monitoring device 100 receives the sensing value for each component measured by the sensor and displays it in a first graph. At this time, the shape displayed in the first graph is different depending on the state of the component.
- the electric vehicle monitoring device 100 provides the sensing value for each part to the metaverse server 500 each time it receives the sensing value for each part, the traffic increases and the cost increases. Therefore, the sensing value for each part received from the sensor continuously It is compressed and the compressed sensing value for each component is provided to the metaverse server 500.
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups.
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups.
- the electric vehicle monitoring device 100 analyzes the first graph and, if a waveform exists, divides and groups the graph into a period unit to create a plurality of groups.
- the electric vehicle monitoring device 100 compresses the sensing value of each group of a plurality of groups.
- the electric vehicle monitoring device 100 compresses the sensing values of each of the plurality of groups and displays them as a second graph, then extracts a specific sensing value from the second graph corresponding to each group and sends it to the electric vehicle monitoring server 200. to provide.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each group, merges the groups according to the slope difference value, extracts only one slope value, and sends the metaverse server 500 ) is provided.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is less than a certain value, the first group and the second group After merging the groups, the larger slope value of the largest slope value extracted from the first group and the largest slope value extracted from the second group is provided to the metaverse server 500.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is greater than a certain value, the first group and the second group Without merging the groups, the largest slope value of each of the first group and the second group is provided to the metaverse server 500.
- the metaverse server 500 can check the status of the corresponding part only by the slope value. It is possible.
- the metaverse server 500 is a server that creates a metaverse space to provide to the user, then creates a car model based on the car owned by the user, places it in the metaverse space, and manages it.
- the metaverse server 500 allows facility icons and component icons to be placed on the virtual electric vehicle in the metaverse space. Accordingly, the metaverse server 500 can simulate the virtual electric vehicle after placing part icons on the virtual electric car.
- the metaverse server 500 uses the sensing values for each component received from the electric vehicle monitoring device 100 to check the status of the component.
- the metaverse server 500 when the metaverse server 500 receives the sensing value for each part from the electric vehicle monitoring server 200, it expresses the sensing value for each part in a third graph and analyzes the third graph to determine the state of the part. At this time, the third graph displays the sensing value with the largest slope among the sensing values for each component received from the corresponding component monitoring device ( ).
- the metaverse server 500 analyzes the third graph to determine whether the sensing value is within the normal range, determines the state of the corresponding part according to the judgment result, and then returns the state of the corresponding part of the electric vehicle to the determined state. Change to to simulate a virtual electric car.
- the metaverse server 500 analyzes the third graph, determines that the state of the part is normal if the sensing value falls within the normal range, and sets the performance of the part to its original performance to simulate a virtual electric vehicle. do.
- the metaverse server 500 analyzes the third graph, determines that the state of the part is abnormal if the sensing value is outside the normal range, and sets the performance of the part to the sensed value to create a virtual electric vehicle. Simulate.
- the metaverse server 500 analyzes the third graph and, when the sensing value is outside the normal range, compares the sensing value immediately before deviating from the normal range and the sensing value immediately after deviating from the normal range to sense the difference. If the value is greater than a certain value, it is determined that the state of the corresponding part has suddenly changed to an abnormal state, and a notification message is provided to the administrator terminal.
- the metaverse server 500 simulates a virtual electric vehicle based on a scenario according to the performance of each part of the electric vehicle.
- the metaverse server 500 when the metaverse server 500 receives the sensing value for each part from the electric vehicle monitoring server 200, it expresses the sensing value for each part in a third graph and determines the performance of the part by analyzing the third graph. Then, the virtual electric vehicle is simulated according to the matched scenario.
- the metaverse server 500 analyzes the third graph to determine the performance of the part, and if there is a scenario set to the same performance as that of the corresponding part among the scenarios, it simulates the electric vehicle according to the scenario.
- the metaverse server 500 displays the temperature value, vibration value, noise value, and current value of the parts of the electric vehicle on the metaverse space 210 through graphs, including a temperature value graph, a vibration value graph, and a noise value graph.
- graphs including a temperature value graph, a vibration value graph, and a noise value graph.
- the metaverse server 500 extracts information when the threshold line is exceeded using the parts monitoring data stored in the parts monitoring database to generate a monitoring pattern, and uses the monitoring pattern to predict the pattern after a certain point in time. Diagnose whether the equipment is malfunctioning.
- the metaverse server 200 extracts a part when it exceeds the threshold line, and if the number of parts is two or more, checks whether the two parts are related, and if so, the part is at the critical point at the same time. Depending on the number of times the line has been exceeded, the presence or absence of a malfunction of the relevant equipment is diagnosed.
- item associations are stored in advance as temperature, current, vibration, and noise.
- FIG. 3 is a flowchart illustrating an embodiment of the electric vehicle diagnosis and prognosis method according to the present invention.
- An embodiment of FIG. 3 relates to an embodiment that can provide sensing values for each component sensed by an electric vehicle monitoring device to an electric vehicle monitoring server.
- the electric vehicle monitoring device 100 receives sensing information for each component from a plurality of sensors 400_1 to 400_N formed on each component of the electric vehicle 500 (step S310).
- the electric vehicle monitoring device 100 divides the first graph into specific units and groups the sensing information for each component to create a plurality of groups (step S320).
- the electric vehicle monitoring device 100 analyzes the first graph and creates a plurality of groups (step S330).
- the electric vehicle monitoring device 100 compresses the sensing value of each of the plurality of groups (step S340).
- step S340 the electric vehicle monitoring device 100 divides the first graph into specific units and groups them to create a plurality of groups, and averages the sensing values of the group for each of the plurality of groups to obtain an average value. Calculate At this time, the electric vehicle monitoring device 100 may divide the sensing values in the first graph into specific number units to create a plurality of groups.
- the electric vehicle monitoring device 100 compresses the sensing values of each of the plurality of groups and displays them as a second graph, then extracts a specific sensing value from the second graph corresponding to each group and sends it to the electric vehicle monitoring server 200. Provided (step S350).
- step S350 the electric vehicle monitoring device 100 averages the sensing values of each of the plurality of groups and displays the calculated average value in a second graph at a position corresponding to the group.
- the second graph averages the specific number of sensing values in the group for each group and then displays the sensing value corresponding to the average value.
- the electric vehicle monitoring device 100 averages the sensing values of each of the plurality of groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and displays the average of the sensing values of the corresponding group for each of the plurality of groups. ) is provided.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each group, merges the groups according to the slope difference value, and extracts only one slope value to provide the electric vehicle monitoring server 200 ) is provided.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is less than a certain value, the first group and the second group After merging the groups, the larger slope value of the largest slope value extracted from the first group and the largest slope value extracted from the second group is provided to the electric vehicle monitoring server 200.
- the electric vehicle monitoring device 100 checks the number of currently merged groups before merging the first group and the second group, and if the number of merged groups is more than a certain number, the electric vehicle monitoring device 100 does not perform merging, but does not perform merging. If the number of groups is less than a certain number, merge is performed.
- the electric vehicle monitoring device 100 calculates a slope difference value by comparing the slope values extracted from each of the first group and the second group, and if the slope difference value is greater than a certain value, the first group and the second group are not merged. Instead, the largest slope value of each of the first group and the second group is provided to the electric vehicle monitoring server 200.
- the electric vehicle monitoring server 200 can check the status of the corresponding component only by the slope value. It is possible.
- Figure 4 is a flowchart illustrating an embodiment of the electric vehicle diagnosis and prognosis method according to the present invention. 4 relates to an embodiment in which an electric vehicle monitoring server can determine the status of a component by receiving sensing values for each component from an electric vehicle monitoring device.
- the electric vehicle monitoring server 200 when the electric vehicle monitoring server 200 receives the sensing value for each part from the electric vehicle monitoring server 200 (step S410), it expresses the sensing value for each part in a third graph and analyzes the third graph. Determine the condition of the part (step S420). At this time, the third graph displays the sensing value with the largest slope among the sensing values for each component received from the electric vehicle monitoring device 100.
- the electric vehicle monitoring server 200 analyzes the third graph to determine whether the sensing value is within the normal range (step S430) and determines the status of the corresponding component according to the determination result (step S440).
- Figure 5 is a diagram for explaining the internal structure of an electric vehicle monitoring device according to an embodiment of the present invention.
- the electric vehicle monitoring device 100 is formed on each component of an actual electric vehicle and generates sensing values.
- the plurality of sensors (400_1 to 400_N) may be implemented as a temperature sensor, vibration sensor, noise sensor, current sensor, etc.
- a plurality of sensors (400_1 to 400_N) are formed in the parts of the electric vehicle, and the parts include battery, motor, OBC (On Board Charger), LDC (Low Voltage DC-DC Converter), AAF (Acrive Air Flap), and GPS. may include.
- the electric vehicle monitoring device 100 receives sensing information for each component from a plurality of sensors 400_1 to 400_N formed on each component of the electric vehicle 500, and provides the sensing information for each component to the electric vehicle monitoring server 200. At this time, the electric vehicle monitoring device 100 measures the sensing value for each component received from each component of the electric vehicle 500 and displays it in a first graph.
- the electric vehicle monitoring device 100 receives the sensing value for each component measured by the sensor and displays it in a first graph. At this time, the shape displayed in the first graph is different depending on the state of the component.
- the electric vehicle monitoring device 100 provides the sensing value for each part to the electric vehicle monitoring device 100 each time it receives the sensing value for each part, traffic increases and costs increase. Therefore, the sensing value for each part received from the sensor continuously The compressed sensing value for each component is provided to the electric vehicle monitoring server 200.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Power Engineering (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Health & Medical Sciences (AREA)
- Sustainable Energy (AREA)
- Sustainable Development (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
Abstract
Selon un mode de réalisation de la présente invention, un système de diagnostic et de prédiction de véhicule électrique comprend : un dispositif de surveillance de véhicule électrique pour recevoir des informations de détection spécifiques à un composant provenant d'une pluralité de capteurs formés dans chaque composant d'un véhicule électrique, et pour recevoir et pour fournir une valeur de détection spécifique à un composant ; un serveur de surveillance de véhicule électrique qui confirme l'état des composants en utilisant la valeur de détection spécifique à un composant reçue provenant du dispositif de surveillance de véhicule électrique et qui fournit le résultat de confirmation ; et un terminal utilisateur pour inspecter le véhicule électrique en fonction du résultat de confirmation lorsque le résultat de confirmation est reçu en provenance du serveur de surveillance de véhicule électrique.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202380009358.8A CN117616438A (zh) | 2022-06-20 | 2023-05-26 | 电动汽车诊断及预知系统 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2022-0075144 | 2022-06-20 | ||
KR20220075144 | 2022-06-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023249277A1 true WO2023249277A1 (fr) | 2023-12-28 |
Family
ID=88543119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2023/007260 WO2023249277A1 (fr) | 2022-06-20 | 2023-05-26 | Système de diagnostic et de prédiction de véhicule électrique |
Country Status (3)
Country | Link |
---|---|
KR (1) | KR102595694B1 (fr) |
CN (1) | CN117616438A (fr) |
WO (1) | WO2023249277A1 (fr) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101864860B1 (ko) * | 2016-09-13 | 2018-06-05 | 오토시맨틱스 주식회사 | 딥러닝을 통한 자동차 상태 진단 방법 |
KR20200002665A (ko) * | 2018-06-29 | 2020-01-08 | 성균관대학교산학협력단 | 운송 수단의 부품에 대한 고장예지 및 건전성 관리 시스템 및 방법 |
KR20200044225A (ko) * | 2018-10-12 | 2020-04-29 | 가톨릭관동대학교산학협력단 | 딥러닝을 기반으로 한 자율차량을 위한 통합진단 시스템 |
KR102204199B1 (ko) * | 2019-08-28 | 2021-01-18 | 주식회사 엔제로 | 자율주행 대중버스에 대한 차량 고장 진단 및 예측 방법 |
KR20210058713A (ko) * | 2019-11-14 | 2021-05-24 | 주식회사 만도 | 차량정보와 모바일 플랫폼을 이용한 차량 예측 유지보수 시스템 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102320382A (zh) * | 2011-07-07 | 2012-01-18 | 中国国际航空股份有限公司 | 飞机性能检测方法 |
KR101560968B1 (ko) * | 2014-02-26 | 2015-10-15 | (주)우광에스디에스 | 설비 직결형 실시간 모니터링 고장 진단 및 고장 시기 예측 진단장치와 그에 따른 고장 진단 및 예측 진단방법 |
KR102043050B1 (ko) | 2017-12-04 | 2019-11-11 | 중앙제어 주식회사 | 전기차 충전기의 고장 검출 방법 및 장치 |
KR20210041724A (ko) | 2019-10-08 | 2021-04-16 | 엘지전자 주식회사 | 전기차 충전기의 고장 예측 장치 및 방법 |
KR102304095B1 (ko) * | 2019-11-11 | 2021-09-27 | 주식회사 에스제이 테크 | 스마트폰 연계 전기자동차 진단 시스템 |
KR102471911B1 (ko) | 2022-08-17 | 2022-11-29 | 사회복지법인 홍애원 | 지능형 전기화재 예측 감시제어시스템 및 이를 이용한 전기화재 예측 감시제어방법 |
-
2023
- 2023-05-26 KR KR1020230068086A patent/KR102595694B1/ko active IP Right Grant
- 2023-05-26 WO PCT/KR2023/007260 patent/WO2023249277A1/fr active Application Filing
- 2023-05-26 CN CN202380009358.8A patent/CN117616438A/zh active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101864860B1 (ko) * | 2016-09-13 | 2018-06-05 | 오토시맨틱스 주식회사 | 딥러닝을 통한 자동차 상태 진단 방법 |
KR20200002665A (ko) * | 2018-06-29 | 2020-01-08 | 성균관대학교산학협력단 | 운송 수단의 부품에 대한 고장예지 및 건전성 관리 시스템 및 방법 |
KR20200044225A (ko) * | 2018-10-12 | 2020-04-29 | 가톨릭관동대학교산학협력단 | 딥러닝을 기반으로 한 자율차량을 위한 통합진단 시스템 |
KR102204199B1 (ko) * | 2019-08-28 | 2021-01-18 | 주식회사 엔제로 | 자율주행 대중버스에 대한 차량 고장 진단 및 예측 방법 |
KR20210058713A (ko) * | 2019-11-14 | 2021-05-24 | 주식회사 만도 | 차량정보와 모바일 플랫폼을 이용한 차량 예측 유지보수 시스템 |
Also Published As
Publication number | Publication date |
---|---|
KR102595694B1 (ko) | 2023-10-31 |
CN117616438A (zh) | 2024-02-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017191872A1 (fr) | Procédé et système de détection d'anomalies de plante | |
WO2017204490A1 (fr) | Dispositif de surveillance de véhicule ferroviaire et procédé de surveillance le mettant en œuvre | |
WO2021054719A1 (fr) | Procédé et système pour la gestion de batterie dans des dispositifs | |
WO2020004994A1 (fr) | Système de prédiction et de diagnostic de dysfonctionnement d'une centrale électrique et procédé associé | |
WO2022071760A1 (fr) | Procédé de protection incendie et système de protection incendie | |
WO2020138623A1 (fr) | Système de surveillance de tableau de contrôle et son procédé de fonctionnement | |
WO2019083300A1 (fr) | Appareil et procédés pour identifier une ou des anomalies dans une batterie rechargeable d'équipement et composant(s) connecté(s) | |
WO2015126029A1 (fr) | Appareil de mesure de l'énergie d'un point d'entrée d'alimentation et système d'étiquetage d'informations de mesure d'énergie l'utilisant | |
WO2020004996A1 (fr) | Dispositif et procédé de génération de données d'apprentissage pour un modèle d'apprentissage d'un système permettant de prédire et diagnostiquer un dysfonctionnement de centrale électrique | |
WO2013042928A1 (fr) | Procédé et dispositif pour déterminer le type de défaut d'une décharge partielle | |
WO2022149890A1 (fr) | Dispositif de diagnostic de batterie, système de batterie et procédé de diagnostic de batterie | |
WO2022071756A1 (fr) | Procédé de protection incendie et système de protection incendie | |
WO2022030971A1 (fr) | Dispositif de diagnostic de batterie, bloc-batterie, système de batterie et procédé de diagnostic de batterie | |
WO2020004774A1 (fr) | Appareil et procédé d'essai d'une carte de circuit imprimé d'un système de gestion de batterie | |
WO2018199659A1 (fr) | Procédé de gestion d'actifs de sous-station | |
WO2021230642A1 (fr) | Dispositif et procédé de diagnostic de batterie | |
WO2022191374A1 (fr) | Tableau répartiteur à surveillance intégrée basée sur l'iot pour diagnostic et prédiction anticipée de défaillances | |
WO2022114654A1 (fr) | Système et procédé de surveillance de processus | |
WO2023090876A1 (fr) | Système de génération d'énergie éolienne à maintenance préventive | |
CN116707144B (zh) | 一种低压配电箱故障预警方法 | |
WO2019177241A1 (fr) | Procédé de maintenance prédictive précise d'une unité d'entraînement | |
WO2019177233A1 (fr) | Procédé de maintenance prédictive précise pour unité de fonctionnement | |
WO2023128669A1 (fr) | Système de surveillance de décharge partielle et procédé de surveillance de décharge partielle | |
WO2018199656A1 (fr) | Procédé de gestion d'actifs de poste électrique | |
WO2023249277A1 (fr) | Système de diagnostic et de prédiction de véhicule électrique |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 202380009358.8 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23827397 Country of ref document: EP Kind code of ref document: A1 |