A smart lamp pole with new energy vehicle charging safety monitoring
By integrating auxiliary monitoring arms and diversion covers on the smart lamp pole, combining video data and temperature sensors, the risk identification model is used to improve charging safety, and the risk judgment problem of external factors when charging outdoors in the smart lamp pole is solved, and the risk judgment problem is achieved More accurate charging safety monitoring and cooling assistance.
Patent Information
- Application Number
- CN202410579931.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-10
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-10
AI Technical Summary
When charging a smart lamp pole, external environmental factors affect the accuracy of charging safety monitoring, resulting in uncertainty in charging risk judgment, especially when charging outdoors, foreign objects such as flammable objects affect battery heat dissipation, making it difficult to distinguish between battery quality and environmental problems.
Design a smart lamp pole, including a lamp pole, auxiliary monitoring arm, diffuser and risk identification module, collect bottom video data and temperature values through cameras and temperature sensors, input the trained risk identification model, and generate emergency commands to improve Charging safety and assists heat dissipation through a flow shield.
It improves the accuracy of charging risk judgment for new energy vehicles, ensures charging safety, avoids external factors affecting the battery temperature, and improves charging efficiency.
Smart Images

Figure CN118499748B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart lamp poles, and in particular to a smart lamp pole with new energy vehicle charging safety monitoring. Background Art
[0002] With the popularization of new energy vehicles, the construction of charging facilities is also developing rapidly; smart lamp poles, as a new type of urban infrastructure, integrate multiple functions such as lighting, video surveillance, environmental monitoring, wireless communications, and new energy vehicle charging. It can not only improve the utilization efficiency of public spaces, but also support the development of smart cities.
[0003] For example, the patent with publication number CN114312404A discloses a charging pile integrated smart lamp pole, which includes a fixed bottom column and a lighting fixture column, wherein the fixed bottom column and the lighting fixture column are fixed by welding, a horizontally arranged lighting panel is fixed to the top of the lighting fixture column by bolts, and a horizontally arranged fixed base is welded to the bottom of the fixed bottom column;
[0004] The patent with publication number CN1 17207810A discloses an electric vehicle charging pile based on an embedded lamp pole, including a smart street light device, the smart street light device includes a lamp pole, a display screen is fixedly installed on the surface in the middle of the smart street light device, a camera is fixedly installed on the top of the lamp pole, a lighting lamp is fixedly installed on the top of the lamp pole, and a charging pile is fixedly installed on the bottom of the lamp pole.
[0005] At present, since the main function of smart lamp poles is lighting, they are generally installed on outdoor roadsides. When new energy vehicles are charging, the surrounding environment will affect the heat dissipation of new energy vehicles during charging. At present, charging piles obtain the charging current, voltage and temperature of new energy vehicle batteries through charging protocols. When the battery temperature is too high, the charging piles will take measures to reduce the current. This method can avoid the risk of excessive battery temperature, but it also affects the charging efficiency. At present, smart lamp poles only monitor charging safety from the charging protocol. When the vehicle itself is charging outdoors, there will be risks caused by some uncertain factors. Only monitoring through charging protocols will affect the accuracy of charging safety judgments. For example, during the charging process, foreign objects (such as flammable objects such as cigarette butts, plastic bags or waste paper) are blown to the bottom of the vehicle by the wind, affecting the heat dissipation of the battery pack. At this time, if the battery pack temperature is abnormal, it is impossible to determine whether the battery pack is a quality problem or an environmental problem. Summary of the invention
[0006] In view of this, the purpose of the present invention is to propose a smart lamp pole with new energy vehicle charging safety monitoring to achieve under-vehicle monitoring, improve the accuracy of charging risk judgment, assist in under-vehicle heat dissipation, and ensure under-vehicle efficiency.
[0007] In order to achieve the above-mentioned technical objectives, the present invention provides a smart lamp pole with new energy vehicle charging safety monitoring, which includes: a lamp pole, on the outer surface of which a charging pile, a camera and a lighting lamp are fixed in sequence from bottom to top, which are respectively used for charging the car, collecting video data around the lamp pole and lighting the periphery of the lamp pole; an auxiliary monitoring arm, rotatably connected to the charging pile, and a first data acquisition module and a second data acquisition module are fixed at the end of the auxiliary monitoring arm, which are respectively used for obtaining the video data under the vehicle and the temperature value under the vehicle, respectively; a deflector, fixed in the auxiliary monitoring arm, for guiding air to the bottom of the vehicle to assist in charging and heat dissipation; a risk identification module, which inputs the video data under the vehicle and the temperature value under the vehicle into a trained risk identification model and outputs a risk category; an analysis module, which determines whether to generate an emergency instruction based on the risk category.
[0008] Preferably, a charging socket is embedded and fixed on the outer surface of the charging pile, and the charging socket is used to connect a charging cable and obtain a normal connection signal of the charging cable.
[0009] Preferably, an extension arm is slidably connected inside the auxiliary monitoring arm, a cover is fixed on the surface of the extension arm, and the first data acquisition module and the second data acquisition module are both embedded and fixed on the cover.
[0010] Preferably, the extension arm is equipped with a first driving mechanism for driving the extension arm to slide, and the first driving mechanism includes: a rack fixed in the extension arm; a driving gear meshing with the rack; a second stepper motor fixed on the auxiliary monitoring arm and slidably connected to the extension arm, and the output end of the second stepper motor is fixedly connected to the driving gear; a distance acquisition module fixed on the cover and used to collect real-time distance values; a first control module, generating an adjustment instruction according to the real-time distance value, and controlling the second stepper motor to adjust the extension arm closer to the car based on the adjustment instruction.
[0011] Preferably, a fixed shell is embedded and fixed on the surface of the charging pile, a connecting pipe shaft is rotatably connected to the bottom of the fixed shell, and the auxiliary monitoring arm is rotatably connected to the fixed shell through the connecting pipe shaft.
[0012] Preferably, the air guide cover is fixed in the extension arm, an air guide pipe is slidably and sealably connected in the air guide cover, and the air guide pipe is connected to the connecting pipe axis.
[0013] Preferably, a second driving mechanism for driving the connecting tube shaft to rotate is fixed on the fixed shell, and the second driving mechanism includes: a first stepper motor, fixed on the fixed shell; a worm, fixedly connected to the output end of the first stepper motor; a worm wheel, sleeved and fixed on the connecting tube shaft, and the worm and the worm wheel are meshed; a second control module, which generates a flipping instruction according to the normal connection signal of the charging cable, and controls the first stepper motor to drive the auxiliary monitoring arm to flip based on the flipping instruction.
[0014] Preferably, a worm gear fan and a third control module are fixed in the lamp pole, and the air outlet of the worm gear fan is connected with the connecting pipe shaft through a conduit, and the third control module is used to control the opening and closing of the worm gear fan.
[0015] Preferably, the training method of the risk identification model includes:
[0016] Collect k groups of risk characteristic data in advance, where k is an integer greater than 1, and the risk characteristic data includes under-vehicle video data and under-vehicle temperature values;
[0017] Generate corresponding actual labels for each group of risk feature data according to the risk category when collected. When the risk category is abnormal, the actual label is 1, and when the risk category is normal, the actual label is 0; use each group of risk feature data as the input of the machine learning model, and the machine learning model uses the predicted label of each group of risk feature data as the output, the actual label as the prediction target, and minimizing the sum of the prediction accuracies of all risk feature data as the training target; train the machine learning model until the sum of the prediction accuracies converges, stop training, and use the trained machine learning model as a risk identification model, and the machine learning model is either a naive Bayes model or a support vector machine model.
[0018] Preferably, the specific method for determining whether to generate an emergency instruction based on the risk category includes:
[0019] The emergency directive risk levels include level one and level two;
[0020] When the risk identification model output is marked as 1, an emergency instruction is generated, and the risk level is level 1. The third control module controls the turbine fan to start based on the emergency instruction to assist in cooling the underbody;
[0021] At the same time, the analysis module calculates the cooling speed value of the bottom of the vehicle within a preset time based on the bottom temperature value of the vehicle, and compares the cooling speed value with the preset cooling speed value threshold. If the cooling speed value is less than the preset cooling speed value threshold, the risk level of the emergency instruction is increased to level 2, and the charging pile stops working based on the emergency instruction with the risk level of level 2; if the cooling speed value is greater than or equal to the preset cooling speed value threshold, the risk level of the emergency instruction remains unchanged;
[0022] When the risk identification model output is marked as 0, no emergency instructions are generated.
[0023] It can be seen from the above technical solutions that the present application has the following beneficial effects:
[0024] 1: By rotating an auxiliary monitoring arm connected to the charging pile, and installing the first data acquisition module and the second data acquisition module on the auxiliary monitoring arm, when the car is charging, the auxiliary monitoring arm can be flipped and parallel to the road surface, so that the first data acquisition module and the second data acquisition module face the bottom of the car, and the risk category is determined based on the temperature value of the bottom of the car and the video data of the bottom of the car, and the charging risk situation is analyzed based on the risk category, thereby improving the accuracy of charging risk judgment.
[0025] 2: An extension arm is telescopically connected in the auxiliary monitoring arm, and a deflector is installed in the extension arm. By adjusting the telescopic length of the extension arm in the auxiliary monitoring arm, the distance from the car can be controlled. The deflector can guide the airflow to the bottom of the car to assist in heat dissipation from the bottom of the car, or blow foreign objects away from the bottom of the car, thereby solving the problem of battery heat dissipation, thereby solving the problem of needing to reduce current and improving charging efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0027] Figure 1 A schematic diagram of the overall structure of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0028] Figure 2 A schematic diagram of the flipping state structure of the auxiliary monitoring arm of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0029] Figure 3 A schematic diagram of a partial explosion structure of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0030] Figure 4 A partial cross-sectional structural diagram of an auxiliary monitoring arm of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0031] Figure 5 A schematic diagram of the installation and use status of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0032] Figure 6 A schematic diagram of the overall structure of the base of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0033] Figure 7A schematic diagram of a cross-sectional structure of a base of a smart lamp pole with new energy vehicle charging safety monitoring provided by the present invention;
[0034] Figure 8 A flowchart of the risk identification module provided by the present invention;
[0035] Fig. 9 A flow chart of the first control module provided by the present invention;
[0036] Fig.10 This is a flow chart of the fire identification module provided by the present invention.
[0037] Description of the drawings: 1. Lamp pole; 101. Charging pile; 101a. Charging socket; 102. Camera; 103. Lighting; 2. Auxiliary monitoring arm; 21. First data acquisition module; 22. Second data acquisition module; 23. Air deflector; 231. Air duct; 24. Fixed shell; 241. Connecting tube shaft; 25. First stepper motor; 251. Worm; 252. Worm wheel; 201. Extension arm; 201a. Cover; 201b. Rack; 201c. Driving gear; 201d. Second stepper motor; 3. Base; 31. Air duct; 311. Fin. DETAILED DESCRIPTION
[0038] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, and use. It should be understood that in all of these figures, the same or similar reference numerals indicate the same or similar parts and features. The various drawings only schematically represent the concepts and principles of the embodiments of the present disclosure, and do not necessarily show the specific dimensions and proportions of the various embodiments of the present disclosure. Specific parts in specific drawings may be exaggerated to illustrate the relevant details or structures of the embodiments of the present disclosure.
[0039] Embodiment 1
[0040] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 and Figure 8 As shown, the smart lamp pole with new energy vehicle charging safety monitoring described in this embodiment includes a lamp pole 1, and a charging pile 101, a camera 102 and a lighting lamp 103 are fixed on the outer surface of the lamp pole 1 from bottom to top, which are respectively used for charging the car, collecting video data around the lamp pole 1 and lighting the surrounding area of the lamp pole 1; a charging socket 101a is embedded and fixed on the outer surface of the charging pile 101, and the charging socket 101a is used to connect the charging cable and obtain the normal connection signal of the charging cable, such as Figure 5As shown, the lamp pole 1 is installed on the sidewalk, and a parking line is drawn on the side road of the sidewalk. The new energy vehicle that needs to be charged is parked within the parking line. The two ends of the charging cable are electrically connected to the new energy vehicle and the charging socket 101a respectively. After normal connection, the charging pile 101 will obtain the voltage, current and temperature of the new energy vehicle battery based on the charging protocol. The charging pile 101 can read these data normally, which means that the normal connection signal of the charging cable is obtained. This is a known public technology and will not be elaborated on here.
[0041] Furthermore, it also includes: an auxiliary monitoring arm 2, a worm fan, a guide cover 23, a first data acquisition module 21, a second data acquisition module 22, a risk identification module, an analysis module and a third control module, and the first data acquisition module 21, the second data acquisition module 22, the risk identification module, the analysis module and the third control module are connected by wire and / or wirelessly;
[0042] The auxiliary monitoring arm 2 is rotatably connected to the charging pile 101, and the first data acquisition module 21 and the second data acquisition module 22 are fixed at the end of the auxiliary monitoring arm 2. The first data acquisition module 21 and the second data acquisition module 22 are respectively used to obtain the under-vehicle video data and the under-vehicle temperature value. In this embodiment, the first data acquisition module 21 is a high-definition camera, and the second data acquisition module 22 is a temperature sensor. The air deflector 23 is fixed in the auxiliary monitoring arm 2, and the worm fan is fixed in the lamp pole 1 (not shown). The inside of the air deflector 23 is connected to the air outlet of the worm fan. The worm fan blows air and sends the air through the air deflector 23 to the underside of the new energy vehicle, which can assist in charging and heat dissipation. The third control module is used to control the opening and closing of the worm fan; the risk identification module inputs the under-vehicle video data and the under-vehicle temperature value into the trained risk identification model and outputs the risk category; the analysis module determines whether to generate an emergency instruction based on the risk category to achieve safety monitoring when the new energy vehicle is charging.
[0043] The training methods of risk identification models include:
[0044] Collect k groups of risk characteristic data in the experimental environment, where k is an integer greater than 1, and the risk characteristic data includes vehicle bottom video data and vehicle bottom temperature value;
[0045] Generate corresponding actual labels for each set of risk feature data according to the risk category at the time of collection. When the risk category is abnormal, the actual label is 1, and when the risk category is normal, the actual label is 0. Take each set of risk feature data as the input of the machine learning model, and the machine learning model uses the predicted label of each set of risk feature data as the output, the actual label as the prediction target, and the minimization of the sum of the prediction accuracy of all risk feature data as the training target. The calculation formula for prediction accuracy is: zk = (ak-wk) 2, where k is the number of the risk feature data, zk is the prediction accuracy, ak is the predicted labeling value corresponding to the k-th group of risk feature data, and wk is the actual labeling corresponding to the k-th group of risk feature data; the machine learning model is trained until the sum of the prediction accuracies converges, the training is stopped, and the trained machine learning model is used as the risk identification model. The machine learning model is either a naive Bayes model or a support vector machine model.
[0046] The specific methods for determining whether to generate emergency instructions based on risk categories include:
[0047] The risk levels of emergency orders include level one and level two. The severity of emergency orders at level two is higher than that of emergency orders at level one.
[0048] When the output of the risk identification model is marked as 1, an emergency instruction is generated, and the risk level is level one. The third control module controls the start of the worm fan based on the emergency instruction to assist the heat dissipation under the vehicle, or blow foreign objects under the vehicle away from the vehicle. By assisting the heat dissipation under the vehicle, a better heat dissipation environment is provided for the battery pack of the new energy vehicle, and the temperature value of the battery pack is reduced. The charging pile 101 does not need to reduce the charging current to ensure the charging efficiency;
[0049] At the same time, the analysis module calculates the cooling speed value of the bottom of the vehicle within the preset time based on the bottom temperature value of the vehicle, and compares the cooling speed value with the preset cooling speed value threshold. If the cooling speed value is less than the preset cooling speed value threshold, the risk level of the emergency instruction is increased to level 2. At this time, it means that the heat dissipation problem caused by the foreign matter under the vehicle is no longer solved by the auxiliary heat dissipation of the worm fan, or the heat of the battery pack itself has exceeded the safe charging range. The charging pile 101 stops working or reduces the charging current based on the emergency instruction with the risk level of level 2;
[0050] If the cooling speed value is greater than or equal to the preset cooling speed value threshold, the risk level of the emergency instruction remains unchanged. This indicates that there is a heat dissipation problem caused by foreign matter under the vehicle. After the turbine fan is started to assist in heat dissipation, L is significantly improved.
[0051] When the risk identification model output is marked as 0, no emergency instructions are generated.
[0052] The method for calculating the cooling speed value of the bottom of the vehicle within a preset time based on the bottom temperature value of the vehicle specifically includes:
[0053] S1. Obtain the vehicle bottom temperature value before the turbo fan is started as the initial temperature value, marked as Q1, where Q1 is a value greater than 1;
[0054] S2. Get the vehicle bottom temperature value after reaching the preset time as the end temperature value, marked as Q2, Q2 is a value greater than 1;
[0055] S3. The expression of the cooling speed value H is: H = (Q1-Q2) / S, where S is the preset time.
[0056] For example, the temperature value of the bottom of the vehicle before the worm fan is started is 30 degrees, the preset time is 5 minutes, the temperature value of the bottom of the vehicle after the preset time is reached is marked as 25 degrees, and the cooling rate value is (30-25) / 5, that is, 1 degree / minute, wherein the preset time and the preset cooling rate value thresholds are obtained by technical personnel in this field based on a large amount of experimental data.
[0057] Embodiment 2
[0058] See also Figure 2 , Figure 3 and Figure 4 As shown, based on the first embodiment, the difference between the second embodiment is that the auxiliary monitoring arm 2 is slidably connected with the extension arm 201, the extension arm 201 is equipped with a first driving mechanism that drives the extension arm 201 to slide, the extension arm 201 is fixed with a cover 201a on the surface, the first data acquisition module 21 and the second data acquisition module 22 are both embedded and fixed on the cover 201a, and the cover 201a is used to protect the first driving mechanism;
[0059] Specifically, the first driving mechanism includes a rack 201b, a driving gear 201c and a second stepper motor 201d, the rack 201b is fixed in the extension arm 201, the driving gear 201c is meshed with the rack 201b, the second stepper motor 201d is fixed on the auxiliary monitoring arm 2, the bottom of the extension arm 201 is hollowed out for the second stepper motor 201d to pass through, so that the second stepper motor 201d is slidably connected to the extension arm 201, the output end of the second stepper motor 201d is fixedly connected to the driving gear 201c, the second stepper motor 201d drives the driving gear 201c to rotate, and the driving gear 201c drives the extension arm 201 to slide in the auxiliary monitoring arm 2 through the rack 201b. The purpose is that due to different people's driving skills, the distance between the new energy vehicle and the curb after parking is different. Through the design of the extension arm 201, the distance between the first data acquisition module 21 and the second data acquisition module 22 and the chassis of the vehicle can be adjusted to ensure the best data acquisition effect.
[0060] See also Fig. 9 As shown, more specifically, the first driving mechanism further includes a distance acquisition module and a first control module. The distance acquisition module is a sensor with a distance measurement function such as an ultrasonic sensor or an infrared sensor, which is not specifically limited here. The distance acquisition module is fixed at the end of the cover 201a and is used to collect a real-time distance value, that is, the distance from the distance acquisition module to the new energy vehicle; the first control module generates an adjustment instruction according to the real-time distance value, and controls the second stepping motor 201d to adjust the extension arm 201 to approach the vehicle based on the adjustment instruction;
[0061] Specifically, when the charging pile 101 is working normally and charging the new energy vehicle, the first control module compares the real-time distance value with the preset distance value threshold. When the real-time distance value is greater than the preset distance value threshold, the first control module generates an adjustment instruction and controls the second stepper motor 201d to work, so that the extension arm 201 is close to the new energy vehicle, and compares the real-time distance value with the preset distance value threshold in real time until the real-time distance value is equal to the preset distance value threshold, and the second stepper motor 201d stops working; when the real-time distance value is less than or equal to the preset distance value threshold, the first control module does not generate an adjustment instruction;
[0062] Embodiment 3
[0063] See also Figure 2 , Figure 3 and Figure 4 As shown, this embodiment is based on the above embodiment, a fixed shell 24 is embedded and fixed on the surface of the charging pile 101, and a connecting tube shaft 241 is rotatably connected to the bottom of the fixed shell 24, and the auxiliary monitoring arm 2 is rotatably connected to the fixed shell 24 through the connecting tube shaft 241, and the auxiliary monitoring arm 2 and the fixed shell 24 can be completely removed from the charging pile 101, which is convenient for disassembly and maintenance;
[0064] Furthermore, the air guide cover 23 is fixed in the extension arm 201, and an air guide pipe 231 is slidingly and sealedly connected in the air guide cover 23. The connecting pipe shaft 241 is a hollow structure, and a duct is connected to the air outlet of the worm turbine fan. The duct and the connecting pipe shaft 241 are rotatably and sealably connected, and the air guide pipe 231 is connected to the connecting pipe shaft 241, so that wind energy can be transmitted from the worm turbine fan to the duct, from the duct to the connecting pipe shaft 241 and then to the air guide pipe 231, so that after the extension arm 201 is adjusted in position, the wind blown out by the worm turbine fan can still enter the air guide cover 23 through the air guide pipe 231.
[0065] Specifically, a second driving mechanism for driving the connecting pipe shaft 241 to rotate is fixed on the fixed shell 24, and the second driving mechanism includes: a first stepper motor 25, which is fixed on the fixed shell 24; a worm 251, which is fixedly connected to the output end of the first stepper motor 25; a worm wheel 252, which is sleeved and fixed on the connecting pipe shaft 241, and the worm 251 is meshed with the worm wheel 252. The first stepper motor 25 drives the worm wheel 252 to rotate through the worm 251, and the auxiliary monitoring arm 2 can be turned over through the connecting pipe shaft 241. The purpose is that when the charging pile 101 is not charging, the auxiliary monitoring arm 2 can be retracted into the fixed shell 24, which does not affect the passage of pedestrians and also avoids the auxiliary monitoring arm 2 from being exposed to the outside for a long time and accelerating damage;
[0066] More specifically, the second driving mechanism also includes a second control module. The second control module obtains the normal connection signal of the charging cable, that is, generates a flipping instruction. Based on the flipping instruction, the first stepper motor 25 is controlled to drive the worm 251 to drive the worm wheel 252 to rotate ninety degrees, so that the auxiliary monitoring arm 2 can be flipped ninety degrees. Conversely, when the normal connection signal of the charging cable is disconnected, the second control module will generate a reset instruction to retract the auxiliary monitoring arm 2 into the fixed shell 24.
[0067] Embodiment 4
[0068] Based on the above embodiments, see Figure 6 and Figure 7 As shown, a base 3 is fixed at the bottom of the lamp pole 1, and the base 3 can be buried in the ground. An air duct 31 is fixed in the base 3. The air duct 31 is U-shaped or spiral-shaped, etc., and no specific limitation is made here. The U-shaped or spiral-shaped design allows the air duct 31 to have a larger contact area with the external air under the same occupied space. Fins 311 are evenly fixed on the outer surface of the air duct 31, which is conducive to heat conduction to the air duct 31. When the base 3 is buried and installed, the air duct 31 is buried in the ground. The deeper it is buried, the better the heat exchange effect. The wind entering the worm turbine fan passes through the air duct 31, exchanges heat with the air duct 31, reduces the temperature of the wind blown out from the worm turbine fan, and improves the heat dissipation effect.
[0069] Embodiment 5
[0070] See also Fig.10 As shown in the above embodiment, a fire extinguisher and a fourth control module are also installed in the lamp pole 1. The fire extinguisher adopts a dry powder fire extinguisher or a foam fire extinguisher with remote opening and closing, which is not specifically limited here. The deflector 23 is connected to the fire extinguisher. A fire identification module is installed at the end of the auxiliary monitoring arm 2. The fire identification module inputs the undercar video data and the undercar temperature value into the fire identification model to output the fire category. The fourth control module determines whether to generate a fire extinguishing instruction based on the fire category, and controls the opening and closing of the fire extinguisher based on the fire extinguishing instruction.
[0071] The training method of the fire recognition model includes:
[0072] Collect m groups of fire characteristic data in the experimental environment, including under-vehicle video data and under-vehicle temperature values;
[0073] Generate corresponding actual labels for each set of fire characteristic data according to the fire category at the time of collection. When the fire category is dangerous, the actual label is 1, and when the fire category is safe, the actual label is 0. Take each set of fire characteristic data as the input of the machine learning model, and the machine learning model uses the predicted label of each set of fire characteristic data as the output, the actual label as the prediction target, and the minimization of the sum of the prediction accuracy of all fire characteristic data as the training target. The calculation formula of prediction accuracy is: xm = (ym-em) 2, where m is the number of the fire characteristic data, xm is the prediction accuracy, ym is the prediction label value corresponding to the mth group of fire characteristic data, and em is the actual label corresponding to the mth group of fire characteristic data; the machine learning model is trained until the sum of the prediction accuracy reaches convergence, the training is stopped and the trained machine learning model is used as the fire recognition model, and the machine learning model is one of a naive Bayes model or a support vector machine model;
[0074] When the fire identification module output is marked as 1, a fire extinguishing instruction is generated;
[0075] When the fire identification module output is marked as 0, no fire extinguishing instruction is generated.
[0076] The exemplary implementation scheme of the present disclosure is described in detail above with reference to the preferred embodiments. However, it can be understood by those skilled in the art that, without departing from the concept of the present disclosure, various modifications and variations can be made to the above-mentioned specific embodiments, and various technical features and structures proposed in the present disclosure can be combined in various ways without exceeding the protection scope of the present disclosure, which is determined by the attached claims.
Claims
1. A smart lamp pole with new energy vehicle charging safety monitoring, characterized in that: include: A lamp pole (1) has a charging pile (101), a camera (102) and a lighting lamp (103) fixed on its outer surface in order from bottom to top, which are used for charging a car, collecting video data around the lamp pole (1) and illuminating the area around the lamp pole (1), respectively; An auxiliary monitoring arm (2) is rotatably connected to the charging pile (101), and a first data acquisition module (21) and a second data acquisition module (22) are fixed to the end of the auxiliary monitoring arm (2), which are used to obtain under-vehicle video data and under-vehicle temperature values, respectively; A deflector (23) is fixed in the auxiliary monitoring arm (2) and is used to guide air to the bottom of the vehicle to assist in charging and heat dissipation; An extension arm (201) is slidably connected inside the auxiliary monitoring arm (2), a cover (201a) is fixed on the surface of the extension arm (201), and the first data acquisition module (21) and the second data acquisition module (22) are both embedded and fixed on the cover (201a); A fixed shell (24) is embedded and fixed on the surface of the charging pile (101), a connecting tube shaft (241) is rotatably connected to the bottom of the fixed shell (24), and the auxiliary monitoring arm (2) is rotatably connected to the fixed shell (24) via the connecting tube shaft (241); The air guide cover (23) is fixed in the extension arm (201), an air guide pipe (231) is slidably and sealably connected in the air guide cover (23), and the air guide pipe (231) is in communication with the connecting pipe shaft (241); The risk identification module inputs the under-vehicle video data and under-vehicle temperature value into the trained risk identification model and outputs the risk category; The analysis module determines whether to generate emergency instructions based on risk categories.
2. According to claim 1, a smart lamp pole with new energy vehicle charging safety monitoring is characterized in that: A charging socket (101a) is embedded and fixed on the outer surface of the charging pile (101), and the charging socket (101a) is used to connect a charging cable and obtain a normal connection signal of the charging cable.
3. The smart lamp pole with new energy vehicle charging safety monitoring according to claim 1 is characterized in that: A first driving mechanism for driving the extension arm (201) to slide is installed in the extension arm (201), and the first driving mechanism comprises: A rack (201b) fixed in the extension arm (201); A driving gear (201c) meshing with the rack (201b); A second stepper motor (201d) is fixed on the auxiliary monitoring arm (2) and is slidably connected to the extension arm (201); an output end of the second stepper motor (201d) is fixedly connected to the driving gear (201c); A distance acquisition module, fixed on the cover (201a), for acquiring real-time distance values; The first control module generates an adjustment instruction according to the real-time distance value, and controls the second stepping motor (201d) to adjust the extension arm (201) to approach the car based on the adjustment instruction.
4. The smart lamp pole with new energy vehicle charging safety monitoring according to claim 1 is characterized in that: A second driving mechanism for driving the connecting pipe shaft (241) to rotate is fixed on the fixed shell (24), and the second driving mechanism comprises: A first stepper motor (25) is fixed on the fixed housing (24); A worm (251) fixedly connected to an output end of the first stepper motor (25); A worm wheel (252) is sleeved and fixed on the connecting pipe shaft (241), and the worm (251) is meshed with the worm wheel (252); The second control module generates a flipping instruction according to a normal connection signal of the charging cable, and controls the first stepper motor (25) to drive the auxiliary monitoring arm (2) to flip based on the flipping instruction.
5. The smart lamp pole with new energy vehicle charging safety monitoring according to claim 1 is characterized in that: A worm gear fan and a third control module are fixed inside the lamp pole (1); a duct is fixed to the air outlet of the worm gear fan, and the worm gear fan is connected to the connecting pipe shaft (241) via the duct; the third control module is used to control the opening and closing of the worm gear fan.
6. The smart lamp pole with new energy vehicle charging safety monitoring according to claim 5 is characterized in that: The training methods of risk identification models include: Collect k groups of risk characteristic data in advance, where k is an integer greater than 1, and the risk characteristic data includes under-vehicle video data and under-vehicle temperature values; Generate corresponding actual labels for each group of risk feature data according to the risk category when collected. When the risk category is abnormal, the actual label is 1, and when the risk category is normal, the actual label is 0; use each group of risk feature data as the input of the machine learning model, and the machine learning model uses the predicted label of each group of risk feature data as the output, the actual label as the prediction target, and minimizing the sum of the prediction accuracies of all risk feature data as the training target; train the machine learning model until the sum of the prediction accuracies converges, stop training, and use the trained machine learning model as a risk identification model, and the machine learning model is either a naive Bayes model or a support vector machine model.
7. The smart lamp pole with new energy vehicle charging safety monitoring according to claim 6 is characterized in that: Methods for determining whether to generate emergency instructions based on risk categories include: The emergency directive risk levels include level one and level two; When the risk identification model output is marked as 1, an emergency instruction is generated, and the risk level is level 1. The third control module controls the turbine fan to start based on the emergency instruction to assist in cooling the underbody; At the same time, the analysis module calculates the cooling speed value of the bottom of the vehicle within a preset time based on the bottom temperature value of the vehicle, and compares the cooling speed value with a preset cooling speed value threshold value. If the cooling speed value is less than the preset cooling speed value threshold value, the risk level of the emergency instruction is increased to level 2, and the charging pile (101) stops working based on the emergency instruction with the risk level of level 2; if the cooling speed value is greater than or equal to the preset cooling speed value threshold value, the risk level of the emergency instruction remains unchanged; When the risk identification model output is marked as 0, no emergency instructions are generated.
