Monitoring system and method for charging piles

Abstract

To provide a monitoring system and method for charging piles that can provide early warning of abnormal conditions in electric vehicle charging piles and take appropriate measures. [Solution] A monitoring system (1) for a charging pile (2) that charges an electric vehicle (3) via a power module (20) of the charging pile (2) includes an image capture module (10) configured to capture at least one environmental image signal related to the electric vehicle (3), and a control module (16) connected to the image capture module (10) and configured to apply artificial intelligence techniques to analyze the at least one environmental image signal, generate an analysis result, and control the power module (20) according to the analysis result.

Description

Technical Field

[0001] The present invention relates to a monitoring system and method for a charging pile, and particularly to a monitoring system and method that can early warn of an abnormal state of a charging pile and take appropriate measures.

Background Art

[0002] With the popularization of electric vehicles, the safety of charging piles has attracted attention. As an important facility for electric vehicles to replenish energy, the safety of charging piles is essential for ensuring the safety of users and vehicles. In modern charging pile technology, a series of safety protection measures including overload protection, leakage protection, lightning protection, etc. have been developed. These functions are constructed based on the vehicle's battery management system (BMS) and the charging pile's power detection system, and even if an accident occurs during the charging process, the power can be immediately cut off to prevent the accident.

[0003] However, during the vehicle charging process, in addition to power abnormalities, there are many environmental factors that may cause safety hazards such as ignition and collision accidents of neighboring vehicles. In particular, public charging stations are generally unmanned, so when a problem occurs, the problem cannot be reported immediately, which may lead to more serious accidents.

[0004] Therefore, early warning of an abnormal state of a charging pile and taking appropriate measures has become one of the goals pursued by the industry.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Therefore, an object of the present invention is to provide a monitoring system and method for a charging pile that can early warn of an abnormal state of a charging pile and take appropriate measures.

Means for Solving the Problems

[0006] One embodiment of the present invention discloses a monitoring system for a charging pile, the charging pile charging electric vehicles via power modules. The monitoring system includes an image capture module configured to capture at least one environmental image signal related to an electric vehicle, and a control module connected to the image capture module and configured to analyze the at least one environmental image signal by applying artificial intelligence techniques, generate analysis results, and control the power modules in accordance with the analysis results.

[0007] Another embodiment of the present invention discloses a monitoring method for a charging pile, the charging pile charging electric vehicles via power modules. The monitoring method includes the steps of capturing at least one environmental image signal related to an electric vehicle, and analyzing the at least one environmental image signal by applying artificial intelligence technology to generate an analysis result, and controlling a power module in accordance with the analysis result.

[0008] These and other objects of the present invention will undoubtedly become clear to those skilled in the art after reading the detailed description of preferred embodiments shown in the following various figures and drawings. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram of a monitoring system according to one embodiment of the present invention. [Figure 2] Figure 1 is a schematic diagram of the operation scenario of the monitoring system shown. [Figure 3A] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 3B] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 3C] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 3D] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 4]This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 5A] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 5B] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 6] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 7] This figure shows different environmental image signals according to an embodiment of the present invention. [Figure 8] This is a schematic diagram of a monitoring method relating to one embodiment of the present invention. [Modes for carrying out the invention]

[0010] Certain terms are used throughout the specification and the claims below to refer to specific components. As those skilled in the art will understand, hardware manufacturers may refer to components by different names. This document is not intended to distinguish between components that have different names but the same function. In the specification and claims below, the terms “include” and “comprise” are used in open-ended form and should be interpreted as “include, but not limited to…”. The term “couple” is intended to mean an indirect or direct electrical connection.

[0011] Refer to Figure 1. Figure 1 is a schematic diagram of a monitoring system 1 according to one embodiment of the present invention. The monitoring system 1 is used in a charging pile 2. The charging pile 2 can charge an electric vehicle 3 via a power module 20, and the monitoring system 1 monitors various information during the charging process to the charging pile 2 to warn of abnormal conditions early and to stop the operation of the power module 20 if necessary. The monitoring system 1 includes an image capture module 10, a temperature sensing module 12, a communication module 14, and a control module 16. The image capture module 10 is used to capture at least one environmental image signal IMG related to the electric vehicle 3. The temperature sensing module 12 is used to sense a temperature signal TMP of the environment near the electric vehicle 3. The communication module 14 is used to exchange messages with a host. The control module 16 is connected to the image capture module 10, the temperature sensing module 12, the communication module 14, and the power module 20 of the charging pile 2. It is used to determine the environmental information of the electric vehicle 3 based on the environmental image signal IMG or the temperature signal TMP, and to receive messages from or output messages to an external host via the communication module 14.

[0012] More specifically, the image capture module 10 may be a camera installed in the housing of the charging pile 2, which captures images of the electric vehicle 3 and its surrounding area within a certain range facing the electric vehicle 3, generates an environmental image signal IMG, and transmits it to the control module 16. In one embodiment, the image capture module 10 may be a camera positioned above the parking space, which transmits the environmental image signal IMG to the control module 16 by wired or wireless means. In another embodiment, the image capture module 10 may consist of multiple cameras positioned at different locations near the parking space, which capture images of the electric vehicle 3 from multiple angles or directions, generate an environmental image signal IMG, and transmit it to the control module 16. In yet another embodiment, the image capture module 10 may include multiple cameras, each capable of capturing images of the electric vehicle 3 at different wavelengths, such as natural light, infrared light, and thermal images, to generate an environmental image signal IMG and transmit it to the control module 16. In short, the image capture module 10 can be implemented using any image capture device or equipment capable of capturing all or part of the electric vehicle 3 and its surrounding area within a certain range, and is not limited to these examples.

[0013] The control module 16 can analyze the environmental image signal IMG captured by the image capture module 10 using artificial intelligence technology, generate analysis results, and control the power module 20 accordingly. As is known in the art, artificial intelligence technology combines computer science, data analysis, machine learning, and algorithm design techniques to create intelligent systems that can mimic human learning, reasoning, and self-correction. These systems can make decisions and perform tasks without direct human intervention by analyzing and learning from large amounts of data. For example, in the field of image recognition applications, artificial intelligence technology can determine whether a particular event occurs in an image by learning and identifying specific patterns in complex datasets using deep learning and / or machine learning methods. The present invention utilizes artificial intelligence technology to analyze the environmental image signal IMG, uses deep learning and / or machine learning methods to recognize specific abnormal situations in the environmental image signal IMG, then determines whether the probability of a dangerous situation occurring is greater than a threshold, and if the probability of a dangerous situation occurring exceeds the threshold, stops charging the electric vehicle 3 to avoid greater damage.

[0014] Specifically, refer to Figure 2. Figure 2 is a schematic diagram of the operation scenario of the monitoring system 1. In Figure 2, the charging pile 2 is charging the electric vehicle 3, and the monitoring system 1 is installed inside the charging pile 2 (and therefore not shown in Figure 2). The image capture module 10 is a camera installed in the housing of the charging pile 2, which captures images of the electric vehicle 3 and its surrounding area within a certain range facing the electric vehicle 3, and generates an environmental image signal IMG as shown in Figure 3A, which is transmitted to the control module 16. As can be seen from Figure 3A, the environmental image signal IMG includes images of the electric vehicle 3 and its surrounding area within a certain range.

[0015] As described above, the control module 16 can analyze the environmental image signal IMG using artificial intelligence technology, generate analysis results, and control the power module 20 accordingly. Taking smoke detection as an example, smoke generation is often accompanied by overheating and is an early sign of fire, but smoke detection is often misjudged due to external environmental factors. In this case, the present invention can more accurately determine whether or not smoke is present using artificial intelligence technology and avoid misjudgments.

[0016] For example, Figures 3B, 3C, and 3D show different environmental image signals (IMG). The environmental image signal (IMG) in Figure 3B shows smoke being generated near the bottom battery of the electric vehicle 3 (i.e., within a predetermined range). Artificial intelligence technology can analyze the characteristics of the smoke situation using machine learning, for example, the smoke becomes denser (lower light transmittance) closer to the battery and thinner (higher light transmittance) further away from the battery, and the smoke is continuously emitted from the area of ​​the bottom battery. AI technology can further evaluate the probability of overheating occurring at the bottom battery of the electric vehicle 3. Furthermore, if the analysis results of the AI ​​technology indicate that the probability of fire occurring is greater than a threshold, the control module 16 may stop charging the electric vehicle 3 to mitigate damage. Furthermore, the control module 16 can notify the administrator via the communication module 14, for example, by connecting to the administrator's messaging software by communicating with a messaging software service host, and send the analysis results to notify the administrator of the abnormal situation. In one embodiment, the control module 16 can simultaneously determine whether the ambient temperature near the electric vehicle 3 is abnormal based on the temperature signal TMP from the temperature sensing module 12, thereby assisting in determining the probability of battery overheating or fire, and enabling timely control of the operation of the power module 20.

[0017] The environmental image signal IMG in FIG. 3C indicates that the electric vehicle 3 is in a foggy area. The AI technology can analyze the characteristics of fog, such as the fog being uniformly distributed in the air and having no obvious flow (the phenomenon spreading from the smoke point), through machine learning. The AI technology may further determine that the fog is just a normal weather condition and not an abnormal surrounding environment. In this case, the control module 16 does not stop charging the electric vehicle 3. In one embodiment, the control module 16 can simultaneously determine whether the ambient temperature near the electric vehicle 3 is abnormal based on the temperature signal TMP from the temperature sensing module 12, and assist in the determination of whether the fog is a weather condition.

[0018] The environmental image signal IMG in FIG. 3D indicates that the vehicle 4 in front of the electric vehicle 3 is continuously emitting thick smoke (e.g., due to incomplete combustion or low temperature). The AI technology can analyze the characteristics of thick smoke, such as being discharged from the rear of vehicle 4 and being injected in a certain direction, through machine learning. The AI technology may further determine that the thick smoke is just due to the exhaust of vehicle 4 and not an abnormal surrounding environment. In this case, the control module 16 does not stop charging the electric vehicle 3. In one embodiment, the control module 16 can simultaneously determine whether the ambient temperature near the electric vehicle 3 is abnormal based on the temperature signal TMP from the temperature sensing module 12, and assist in the determination of whether it is due to the exhaust of vehicle 4.

[0019] It is important to note that FIGS. 3B to 3D are examples of different smoke situations showing various scenarios of smoke generation. In these situations, relying only on a fixed determination method may lead to misidentification. In contrast, the embodiments of the present invention use artificial intelligence technology, utilize deep learning and machine learning algorithms, learn and identify specific patterns from complex datasets in images, recognize various forms of smoke, and provide a rapid response at the early stage of a fire. The AI technology not only improves the detection speed, but also enhances the accuracy and reduces unnecessary interference caused by misidentification alarms.

[0020] It should be noted that the present invention is not limited to detecting smoke conditions. Those skilled in the art can appropriately derive this to detect other abnormal conditions. For example, the environmental image signal IMG in Figure 4 indicates that a fire source has appeared near (i.e., within a predetermined range) the bottom battery of the electric vehicle 3. AI technology can analyze the characteristics of the fire source situation through machine learning. For example, sparks may appear first near the battery, then flames, and smoke may be continuously emitted from the area of ​​the bottom battery. AI technology can further evaluate the probability of a fire in the bottom battery of the electric vehicle 3. Furthermore, if the analysis results of the AI ​​technology indicate that the probability of a fire occurring is greater than a threshold, the control module 16 can stop charging the electric vehicle 3 to mitigate damage. Furthermore, the control module 16 can notify an administrator via the communication module 14, for example, by connecting to the administrator's messaging software by communicating with a messaging software service host, and send the analysis results to notify the administrator of the abnormal situation. Alternatively, the control module 16 can notify the fire department via the communication module 14, for example, by connecting to a fire alarm receiving system and transmitting analysis results to the fire brigade to inform relevant parties of an abnormal situation, or by prompting the fire alarm receiving system to issue a fire alarm, thereby allowing people to evacuate in advance. In one embodiment, the control module 16 can simultaneously determine whether the ambient temperature near the electric vehicle 3 is abnormal based on the temperature signal TMP from the temperature sensing module 12, thereby avoiding misinterpreting a non-fire situation as a fire.

[0021] The environmental image signal IMG in Figure 5A indicates that water is accumulating at the bottom of the electric vehicle 3 (i.e., within a predetermined range). AI technology can analyze the characteristics of the water accumulation using machine learning. For example, if the height or range of the water accumulation does not change significantly over a certain period of time, the AI ​​technology can further determine that the water accumulation is normal and not due to an abnormal surrounding environment. In this case, the control module 16 does not stop charging the electric vehicle 3.

[0022] The environmental image signal IMG in Figure 5B indicates that the bottom of the electric vehicle 3 is submerged in water. AI technology can analyze the characteristics of the submersion situation through machine learning. For example, if the water level continues to rise over time and exceeds half the height of the tires, the AI ​​technology can further assess the probability of submersion occurring at the location of the electric vehicle 3. Furthermore, if the analysis results of the AI ​​technology indicate that the probability of submersion is greater than a threshold, the control module 16 can stop charging the electric vehicle 3 to mitigate potential damage. In addition, the control module 16 can notify the administrator via the communication module 14. For example, it can communicate with a messaging software service host via the communication module 14 to connect to the administrator's messaging software and send the analysis results to notify the administrator of the abnormal situation.

[0023] The environmental image signal IMG in Figure 6 indicates that electric vehicle 3 has collided with another vehicle 5. AI technology can analyze collision characteristics using machine learning, such as whether the position of electric vehicle 3 has shifted due to the collision, and whether there are any visible changes in the appearance of electric vehicle 3 or vehicle 5. Next, AI technology can further evaluate the probability that electric vehicle 3 will experience a severe collision. Furthermore, if the analysis results of the AI ​​technology indicate that the probability of electric vehicle 3 experiencing a severe collision is greater than a threshold, the control module 16 can stop charging electric vehicle 3 to mitigate potential damage. In addition, the control module 16 can notify the administrator via the communication module 14, for example, by communicating with a messaging software service host to connect to the administrator's messaging software and send the analysis results to notify the administrator of the abnormal situation.

[0024] The environmental image signal IMG in Figure 7 indicates that an earthquake is occurring in the area where the electric vehicle 3 is located. The AI ​​technology can use machine learning to analyze the characteristics of the earthquake situation, such as whether the position of the electric vehicle 3 has shifted due to the earthquake and the degree of shaking of the electric vehicle 3. Next, the AI ​​technology can further evaluate the probability of a strong earthquake occurring in the area where the electric vehicle 3 is located. Furthermore, if the analysis results of the AI ​​technology indicate that the probability of a strong earthquake occurring in the area of ​​the electric vehicle 3 is greater than a threshold, the control module 16 can stop charging the electric vehicle 3 to mitigate potential damage. In addition, the control module 16 can notify the administrator via the communication module 14, for example, by communicating with a messaging software service host to connect to the administrator's messaging software and send the analysis results to notify the administrator of the abnormal situation.

[0025] The embodiments described above demonstrate that the monitoring system 1 can use artificial intelligence technology to analyze an environmental image signal IMG to determine whether an abnormal situation such as a fire, flooding, strong earthquake, or vehicle accident has occurred inside or around the charging vehicle 3. However, the present invention is not limited to these scenarios. The artificial intelligence technology is not limited by initial settings, as it can be continuously updated by machine learning to identify various abnormal situations, self-correct, and adjust the basis for judgment. On the other hand, when the control module 16 determines thresholds related to dangerous situations, it is preferable to use artificial intelligence technology to optimize the threshold settings, and the thresholds can be dynamically determined, for example, by using a convolutional neural network (CNN), but this is not limited to this method. In one embodiment, the thresholds may be set manually by an operator, which is also within the scope of the present invention.

[0026] Furthermore, in addition to analyzing the environmental image signal IMG using artificial intelligence technology, the control module 16 can also control the operation of the power module 20 based on sensing signals from other modules. For example, if the temperature sensing module 12 detects that the temperature signal TMP near the electric vehicle 3 exceeds a temperature threshold, the control module 16 can control the power module 20 to stop charging the electric vehicle 3 or reduce the charging current to avoid danger due to high temperature. At the same time, the control module 16 can optimize the setting of the temperature threshold using artificial intelligence technology, or the temperature threshold can be set manually by an operator. Alternatively, in one embodiment, multiple temperature thresholds can be set for different controls. For example, if the temperature signal TMP exceeds a first temperature threshold, the charging current is reduced by 4 amperes; if the temperature signal TMP exceeds a second temperature threshold, the charging current is reduced by a further 4 amperes; and if the temperature signal TMP exceeds a third temperature threshold, charging the electric vehicle 3 is stopped. Such adjustments to charging operations based on different temperature thresholds should be well known to those skilled in the art.

[0027] On the other hand, in addition to being used to communicate with a messaging software service host and connect to the administrator's messaging software, the communication module 14 can also, in one embodiment, be connected to a strong earthquake notification service host to receive early earthquake warnings issued by the host. In other words, in addition to analyzing the environmental image signal IMG using artificial intelligence technology to determine the earthquake situation, the control module 16 can receive early earthquake warnings via the communication module 14 and pre-control the power module 20 to stop charging the electric vehicle 3 to avoid more serious damage if the electric vehicle 3's location is affected by a strong earthquake.

[0028] Similarly, in another embodiment, the communication module 14 may also be connected to a fire alarm control panel to receive fire alarms issued by the panel. In other words, in addition to analyzing the environmental image signal IMG using artificial intelligence technology to determine the fire situation, the control module 16 can receive fire alarms via the communication module 14 and pre-control the power module 20 to stop charging the electric vehicle 3 to avoid more serious damage if the electric vehicle 3's location is affected by the fire.

[0029] Furthermore, the monitoring system 1 may include a warning device connected to the control module 16 and used to issue warning signals. For example, the warning device may be a speaker, indicator light, screen, etc., used to emit sound, light signals, images, or text messages. The control module 16 can control the warning device to issue a warning signal based on the charging status of the power module 20 or when an abnormal condition occurs.

[0030] The aforementioned operation of monitoring system 1 can be summarized as monitoring method 8, as shown in Figure 8. Monitoring method 8 includes the following steps.

[0031] Step 80: Start.

[0032] Step 82: Capture at least one environmental image signal related to the electric vehicle.

[0033] Step 84: Apply artificial intelligence technology to analyze at least one environmental image signal, generate analysis results, and control the power module according to the analysis results.

[0034] Step 86: Finish.

[0035] The detailed operation and variations of monitoring method 8 can be found in the previous explanation and will not be repeated here.

[0036] Conventional safety measures for charging piles are based on the vehicle's battery management system and power detection system. However, these safety measures can only respond to abnormal power input and output and cannot provide early warnings for environmental factors. In particular, at public charging stations where dedicated inspection staff are not permanently stationed, problems may not be reported immediately when they occur, potentially leading to more serious accidents. In contrast, the monitoring system of the present invention utilizes various monitoring technologies, especially artificial intelligence technology, to detect environmental information during the charging process, determine abnormal situations at an early stage, take action, and prevent greater damage. Therefore, the present invention can enhance the safety protection of electric vehicle charging.

[0037] Those skilled in the art will readily see that many modifications and changes can be made to the apparatus and method while maintaining the teachings of the present invention. Accordingly, the above disclosure should be interpreted as being limited only by the boundaries of the appended claims.

Claims

1. A monitoring system for a charging pile, wherein the charging pile charges electric vehicles via power modules, and the monitoring system is An image capture module configured to capture at least one environmental image signal related to the electric vehicle, Includes a control module connected to the image capture module, configured to analyze the at least one environmental image signal by applying artificial intelligence technology, calculate the probability of a dangerous condition occurring, generate analysis results, and control the power module according to the analysis results, The at least one environmental image signal indicates the smoke situation within a predetermined range of the electric vehicle, and the hazardous condition is a fire. The control module is a monitoring system that determines the smoke situation when the environmental image signal has a density gradient exceeding a predetermined value, becoming denser closer to the electric vehicle's battery and fainter further away from the battery.

2. Further comprising a temperature sensing module configured to sense a temperature signal of the environment near the electric vehicle, The monitoring system according to claim 1, wherein the control module determines, based on the temperature signal, whether or not the smoke is due to exhaust from the electric vehicle.

3. The monitoring system according to claim 1 or 2, wherein the artificial intelligence technology uses machine learning to recognize the smoke situation and determines the probability of the dangerous state occurring based on the characteristics of the smoke.

4. The monitoring system according to claim 1 or 2, wherein if the analysis results indicate that the probability of a dangerous condition occurring is greater than a threshold, the control module controls the power module to stop charging the electric vehicle.

5. The monitoring system according to claim 4, wherein the control module is further configured to set the threshold.

6. The control module further includes a communication module connected to the control module, The control module exchanges messages with the host using the communication module. The monitoring system according to claim 1 or 2, wherein the host is a strong earthquake notification service host used to issue strong earthquake notifications, and when the communication module receives a strong earthquake notification and the strong earthquake notification indicates that the electric vehicle's location is affected by a strong earthquake, the control module is further configured to control the power module to stop charging the electric vehicle and to perform a comparative verification of the analysis results.

7. The monitoring system according to claim 6, wherein the host is a fire alarm control panel used to issue fire alarms, and the control module is further configured to control the power module to stop charging the electric vehicle when the communication module receives a fire alarm and the fire alarm indicates that the electric vehicle's location is affected by a fire.

8. The monitoring system according to claim 6, wherein the host is a communication software service host connected to at least one communication software of at least one administrator, and the control module is further configured to transmit the analysis results to the at least one communication software of the at least one administrator via the communication module and the communication software service host.

9. The monitoring system according to claim 1 or 2, further comprising a warning device connected to the control module and configured to issue a warning signal, wherein the control module is further configured to control the warning device to issue the warning signal based on the charge state of the power module.

10. A monitoring method for a charging pile, wherein the charging pile charges electric vehicles via power modules, and the monitoring method is The steps include capturing at least one environmental image signal related to the electric vehicle, The process includes the steps of: applying artificial intelligence technology to analyze the at least one environmental image signal, calculating the probability of a dangerous condition occurring, generating analysis results, and controlling the power module according to the analysis results, The at least one environmental image signal indicates the smoke situation within a predetermined range of the electric vehicle, and the hazardous condition is a fire. A monitoring method in which the smoke situation is determined when the environmental image signal has a density gradient exceeding a predetermined value, becoming denser closer to the electric vehicle's battery and fainter further away from the battery.

11. The monitoring method according to claim 10, wherein the state of the smoke is determined to be due to the exhaust of the electric vehicle based on a temperature signal of the environment near the electric vehicle.

12. The monitoring method according to claim 10 or 11, wherein the artificial intelligence technology uses machine learning to recognize the smoke situation and determines the probability of the occurrence of the dangerous state based on the characteristics of the smoke.

13. The monitoring method according to claim 12, further comprising the step of controlling the power module to stop charging the electric vehicle if the analysis results indicate that the probability of a dangerous condition occurring is greater than a threshold.

14. The monitoring method according to claim 13, further comprising the step of setting the threshold.

15. This further includes the step of exchanging messages with the host, The monitoring method according to claim 10 or 11, wherein the host is a strong earthquake notification service host used to issue strong earthquake notifications, and the monitoring method further includes the steps of receiving the strong earthquake notification and controlling the power module to stop charging the electric vehicle if the strong earthquake notification indicates that the electric vehicle's location is affected by the strong earthquake, and comparing and verifying the analysis results.

16. The monitoring method according to claim 15, wherein the host is a fire alarm control panel used to issue a fire alarm, and the monitoring method further includes the step of receiving the fire alarm and controlling the power module to stop charging the electric vehicle if the fire alarm indicates that the electric vehicle's location is affected by a fire.

17. The monitoring method according to claim 15, wherein the host is a communication software service host connected to at least one communication software of at least one administrator, and the monitoring method further includes the step of transmitting the analysis results to the at least one communication software of the at least one administrator via the communication software service host.

18. The monitoring method according to claim 10 or 11, further comprising the step of controlling a warning device to issue a warning signal based on the charge state of the power module.

Images