New energy automobile charging station fire early warning system based on AI algorithm

Abstract

The invention relates to the technical field of charging station fire early warning, and particularly discloses a new energy automobile charging station fire early warning system based on an AI algorithm, and the system comprises the steps: collecting the dynamic parameters of each charging pile in use in a charging process in real time through a multi-mode sensor array disposed in a charging station and a built-in battery management system of each charging pile in use; constructing a three-dimensional dynamic thermodynamic model of each charging pile in use based on the dynamic parameters; further identifying a voltage overload possible risk coefficient of each charging pile in use; and finally, a graded early warning signal is generated based on the possible risk coefficient of voltage overload of each charging pile in use, so that the intelligent early warning system based on real-time monitoring and analysis not only improves the safety and reliability of the charging piles, but also provides more convenient and safer charging experience for users; and the urgent requirements of the current electric vehicle charging field on safety and intelligence are met.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire warning for charging stations, and relates to a fire warning system for new energy vehicle charging stations based on AI algorithms. Background Art

[0002] The importance and necessity of the battery management system (BMS) in addressing the hysteresis of output current / voltage feedback in charging piles is self-evident. As a key component in electric vehicle charging piles, the BMS undertakes the crucial task of monitoring and managing the battery status. However, because current / voltage feedback lag can lead to safety issues such as overload or voltage breakdown, the importance of monitoring it has become increasingly prominent. First, timely and accurate current / voltage feedback information helps the BMS monitor the battery charging status in real time and avoid overload. Overload can lead to degraded battery performance, shortened battery life, and even pose safety hazards, making current / voltage monitoring and feedback essential. Second, voltage breakdown is a serious safety issue that can cause severe damage to the battery and charging pile, and even cause dangerous situations such as fire. Therefore, real-time voltage monitoring and feedback are key to ensuring the safe and stable operation of charging piles.

[0003] However, current battery management systems (BMSs) have several drawbacks and drawbacks in their monitoring of charging pile output current / voltage feedback lag. First, the monitoring technologies and algorithms used by some traditional BMS systems may exhibit lags, preventing real-time monitoring and feedback of current / voltage. This results in the inability to promptly identify and address the risk of overload or voltage breakdown. Second, the limited monitoring accuracy and response speed of some BMS systems prevents them from accurately capturing sudden changes in current / voltage, significantly reducing the effectiveness of early warnings for overload or voltage breakdown. Summary of the Invention

[0004] In view of the above problems existing in the prior art, the present invention provides a new energy vehicle charging station fire warning system based on AI algorithm to solve the above technical problems.

[0005] In order to achieve the above-mentioned and other purposes, the technical solutions adopted by the present invention are as follows:

[0006] The present invention provides a fire warning system for new energy vehicle charging stations based on an AI algorithm. The system includes a dynamic parameter acquisition module, a dynamic parameter analysis module, and a multi-level linkage warning module. The above modules are connected via wired and / or wireless connections to achieve data transmission between the modules.

[0007] Dynamic parameter acquisition module: This module uses a multimodal sensor array deployed in the charging station and the battery management system built into each charging pile to collect the dynamic parameters of each charging pile in use during the charging process in real time. Based on these dynamic parameters, a three-dimensional dynamic thermodynamic model of each charging pile in use is constructed.

[0008] Dynamic parameter analysis module: Based on the three-dimensional dynamic thermodynamic model of each charging pile in use, it identifies the possible risk factor of voltage overload of each charging pile in use;

[0009] Multi-level linkage warning module: Generates graded warning signals based on the possible risk factor of voltage overload of each charging pile in use.

[0010] Exemplarily, the dynamic parameters of each charging pile in use during the charging process include the charging current, voltage, battery temperature, ambient temperature, ambient humidity, and insulation status of the cables inside the charging pile.

[0011] Exemplarily, a three-dimensional dynamic thermodynamic model of a charging station is constructed based on the dynamic parameters, and the specific construction logic is as follows:

[0012] Step S11: synchronously collect the charging current, voltage and corresponding battery temperature data of each charging pile in use, and establish a mapping relationship between the charging equipment and the spatial coordinates;

[0013] Step S12: Calculate the real-time heat generation power of each charging pile in use based on the charging current data, and generate a three-dimensional heat source distribution map of the charging equipment;

[0014] Step S13: quantifying the thermal resistance coefficient of the air medium by combining the shell temperature and ambient temperature data of each charging pile in use, and superimposing the thermal resistance coefficient of the air medium on the three-dimensional heat source distribution map;

[0015] Step S14: Calculating the additional heat generation rate caused by the impedance change of each charging pile cable in use based on the internal cable insulation state parameters, and superimposing the additional heat generation rate on the three-dimensional heat source distribution map;

[0016] Step S15: Correcting the air medium thermal conductivity coefficient according to the ambient humidity data, and constructing a three-dimensional temperature field model through an iterative calculation method;

[0017] Step S16: vector superposition is performed on the three-dimensional heat source distribution map and the three-dimensional space temperature field model to construct a three-dimensional dynamic thermodynamic model of each charging pile in use.

[0018] Exemplarily, the specific implementation of step S13 includes:

[0019] Step S131: Scan the surface temperature field of each charging pile shell in use with an infrared thermal imager, extract the temperature gradient distribution characteristics and mark the local hot spot area;

[0020] Step S132: Calculating the thermal resistance coefficients of natural convection and forced heat dissipation based on the ambient temperature and humidity sensor data;

[0021] Step S133: Analyze the heat conduction path based on the principle of heat flow continuity and quantify the heat accumulation rate of key components;

[0022] Step S134: Generate the thermal resistance coefficient of the air medium according to the product of the thermal resistance coefficient and the heat accumulation rate.

[0023] For example, the logic for identifying the possible risk factor of voltage overload of each charging pile in use is as follows:

[0024] Step S21: extracting key thermal characteristic values of each charging pile in use in the three-dimensional dynamic thermodynamic model in real time, including the battery compartment core temperature, the charging module heat dissipation surface temperature gradient, and the cable channel peak temperature;

[0025] Step S22: Calculate the conductor resistance increment based on the cable channel peak temperature distribution, and convert the resistance increment into an equivalent voltage drop compensation coefficient;

[0026] Step S23: Analyze the battery compartment core temperature change curve and establish a mapping relationship table between electrolyte activity decay and terminal voltage change;

[0027] Step S24: Based on the temperature gradient data of the heat dissipation surface of the charging pile, the junction temperature of the power device is calculated and associated with the voltage ripple increment caused by the switching loss;

[0028] Step S25: The voltage drop compensation coefficient, the terminal voltage change mapping value and the voltage ripple increment are integrated to generate the voltage overload possible risk coefficient of each charging pile in use through a dynamic weight allocation algorithm combined with a weighted summation algorithm.

[0029] Exemplarily, the operation logic of step S22 is:

[0030] Step S221: Delineate the 3D coordinate range of the cable channel corresponding to each charging pile in use in the 3D model of the charging station, and automatically identify the highest temperature point within the channel using a regional extreme value search algorithm. A detection cube is formed with the peak point as the center, expanding along the 3D coordinate axis. The arithmetic mean of all temperature measurement points within the cube is calculated as the representative temperature value.

[0031] Step S222: Obtaining original design parameters of the cable, where the original design parameters include the standard temperature resistivity corresponding to the conductor material type and the resistance per unit length of the cable at a standard ambient temperature; based on the actual total length of the cable, the product of the resistance per unit length and the total length is used as the reference resistance value;

[0032] Step S223: Subtract the standard ambient temperature from the average temperature of the current detection cube to obtain the actual temperature difference value; multiply the reference resistance value by the temperature difference, and then multiply it by the material temperature resistivity to obtain the resistance increment per unit length; add the actual total length of the cable; the total resistance increment is equal to the product of the resistance increment per unit length and the actual total length of the cable;

[0033] Step S224: Obtain the current charging current value passing through the cable in real time; multiply the total resistance increment by the charging current value to obtain the theoretical increase in voltage drop; divide the voltage drop increase by the rated output voltage of the charging pile, and then multiply by 100% to convert it into a percentage, thereby obtaining the equivalent voltage drop compensation coefficient.

[0034] Exemplarily, the operation logic of step S24 is:

[0035] Based on thermocouple sensors placed on the heat dissipation surface of the charging pile, an X-axis coordinate system is established along the direction of the heat sink fins, and a Y-axis coordinate system is established in the vertical direction. After identifying the coordinates of the highest temperature point, a junction temperature inversion model is established using the thermal resistance parameters of the package structure. The highest measurement point temperature is multiplied by the material thermal conductivity correction factor, and the product of the thermal resistance parameter and the real-time power is superimposed to obtain the estimated data value of the power device junction temperature;

[0036] On this basis, a dynamic quantitative model for switching loss was constructed. Using the 25°C ambient test value as a benchmark, a temperature compensation rule was established whereby every 100°C increase in junction temperature corresponds to a 35% increase in loss. Cumulative loss calculations were then performed for multiple devices in parallel.

[0037] The ripple feature reconstruction is then performed. The total switching loss is divided by the switching period to obtain the power fluctuation component. This component is divided by the DC bus voltage value to convert it into an equivalent current ripple, and then multiplied by the total impedance of the charging circuit to obtain the voltage ripple increment.

[0038] Exemplarily, generating a graded warning signal based on the voltage overload risk factor of each charging pile in use includes:

[0039] Compare the voltage overload risk factor of each charging pile in use with the preset safety assessment threshold range [S1, S2];

[0040] If the voltage overload risk factor of a charging pile in use is less than S1, the warning level of the charging pile in use will be marked as level 1, and no warning prompt will be issued for the charging pile in use;

[0041] If the voltage overload risk factor of a charging pile in use is greater than S2, the warning level of the charging pile in use will be marked as level 3, the power supply of the charging pile in use will be automatically cut off, and the dry powder fire extinguishing device will be activated;

[0042] If the voltage overload risk factor of a charging pile in use is within the safety assessment threshold range, the warning level of the charging pile in use will be marked as level two, the sound and light alarm device will be triggered, and the warning information will be pushed through the mobile APP.

[0043] As described above, the fire warning system for new energy vehicle charging stations based on AI algorithms provided by the present invention has at least the following beneficial effects:

[0044] The AI-based fire warning system for new energy vehicle charging stations provided by the present invention utilizes a multimodal sensor array and a battery management system built into the charging pile to collect dynamic parameters of the charging pile in real time during the charging process, construct a three-dimensional dynamic thermodynamic model, identify the potential risk factor for voltage overload, and generate graded warning signals. This system provides a comprehensive understanding of state changes during the charging process, helping to promptly detect abnormalities and take appropriate measures to ensure the safe operation of the charging pile. Furthermore, the construction of a three-dimensional dynamic thermodynamic model more accurately simulates the operating environment and thermal characteristics of the charging pile, helping to analyze the heat distribution and transfer during battery charging, providing a scientific basis for preventing battery overheating. Furthermore, identifying the potential risk factor for voltage overload effectively assesses the voltage safety of the charging pile, promptly identifying potential voltage overload risks and preventing damage to the battery and charging equipment. Finally, based on the generation of graded warning signals based on the potential risk factor for voltage overload, appropriate preventive measures, such as reducing charging power, stopping charging, or performing maintenance, can be taken according to the degree of risk, thereby ensuring the safe operation of the charging pile and electric vehicles. This intelligent early warning system based on real-time monitoring and analysis not only improves the safety and reliability of charging piles, but also provides users with a more convenient and safe charging experience, meeting the current urgent demand for safety and intelligence in the electric vehicle charging field. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 Schematic diagram of the connection of various modules of the system of the present invention. DETAILED DESCRIPTION

[0047] The above contents described below in conjunction with the implementation of the present invention are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall fall within the scope of protection of the present invention.

[0048] Example 1

[0049] See also Figure 1 As shown, a fire warning system for new energy vehicle charging stations based on AI algorithms includes a dynamic parameter acquisition module, a dynamic parameter analysis module, and a multi-level linkage warning module; the above modules are connected through wired and / or wireless connections to achieve data transmission between the modules;

[0050] Dynamic parameter acquisition module: This module uses a multimodal sensor array deployed in the charging station and the battery management system built into each charging pile to collect the dynamic parameters of each charging pile in use during the charging process in real time. Based on these dynamic parameters, a three-dimensional dynamic thermodynamic model of each charging pile in use is constructed.

[0051] The dynamic parameters of each charging pile in use during the charging process include the charging current, voltage, battery temperature, ambient temperature, ambient humidity and the insulation status of the cables inside the charging pile.

[0052] A three-dimensional dynamic thermodynamic model of the charging station is constructed based on the dynamic parameters. The specific construction logic is as follows:

[0053] Step S11: synchronously collect the charging current, voltage and corresponding battery temperature data of each charging pile in use, and establish a mapping relationship between the charging equipment and the spatial coordinates;

[0054] In specific implementation, a multimodal sensor array is installed in a three-dimensional grid layout within the charging station. Specifically, temperature sensing units are installed on the top, side, and base of each charging pile in use, and a current and voltage dual-mode sensor is configured at the charging gun connection port. Charging current data includes but is not limited to instantaneous current value and the effective root mean square value of a 15-second sliding window; battery temperature data is the temperature gradient data of the battery core, which can be obtained using multi-point distributed temperature measurement; and then, through the correlation and matching of the GPS positioning module with the physical coding of the charging pile, combined with the device coordinates in the charging station building BIM model, a three-dimensional coordinate label with an elevation value is established for each working charging pile. The spatial coordinate system is set with the center of the charging station ground as the origin, and establishes the orthogonal coordinate axes of X (east-west), Y (north-south), and Z (vertical).

[0055] Step S12: Calculate the real-time heat generation power of each charging pile in use based on the charging current data, and generate a three-dimensional heat source distribution map of the charging equipment;

[0056] In specific implementation, the DC resistance parameters of the cables of different charging piles in use are obtained by measurement or calibration, and the heat generation power per unit time is obtained by multiplying the square of the real-time current value by the resistance value. The switching loss of the power electronic devices inside the charging pile is further considered, and the correction coefficient is superimposed to finally generate the real-time heat generation power value of each charging pile in use. In the construction of the three-dimensional heat source distribution map, the real-time heat generation power value of the spatial coordinates of each charging pile in use is imported into the three-dimensional modeling software, and a continuous three-dimensional heat source density field is generated by the interpolation algorithm. For example, two adjacent charging piles in a certain area generate 10W and 15W of heat respectively. The software will generate the transition heat source value of the area between the two according to the spatial distance weight, and visualize it in the form of a heat map.

[0057] Step S13: quantifying the thermal resistance coefficient of the air medium by combining the shell temperature and ambient temperature data of each charging pile in use, and superimposing the thermal resistance coefficient of the air medium on the three-dimensional heat source distribution map;

[0058] The specific implementation of step S13 includes:

[0059] Step S131: Scan the surface temperature field of each charging pile shell in use with an infrared thermal imager, extract the temperature gradient distribution characteristics and mark the local hot spot area;

[0060] Step S132: Calculating the thermal resistance coefficients of natural convection and forced heat dissipation based on the ambient temperature and humidity sensor data;

[0061] Step S133: Analyze the heat conduction path based on the principle of heat flow continuity and quantify the heat accumulation rate of key components;

[0062] Step S134: Generate the thermal resistance coefficient of the air medium according to the product of the thermal resistance coefficient and the heat accumulation rate.

[0063] In the specific implementation, an infrared thermal imager is used to perform a panoramic scan of the charging pile shell at a sampling rate of 30 frames per second, generating a two-dimensional temperature distribution thermogram with a resolution of 640×480 pixels. The thermal image is divided into 5mm×5mm grid units through the image processing algorithm built into the edge computing unit, and the temperature difference between adjacent grids is calculated as the gradient value. Based on the set gradient threshold, potential hot spots are automatically marked (for example, three high-gradient grids appear continuously in an area near the charging gun plug end, which is determined to be a heat dissipation abnormality point).

[0064] During the implementation process, environmental data is collected through temperature and humidity sensors. The classic thermal resistance model is used to calculate the natural convection thermal resistance and forced heat dissipation thermal resistance respectively:

[0065] Based on the correlation between the Prandtl number and the Grashof number, the temperature difference (casing temperature - ambient temperature) and characteristic length are substituted into the empirical formula to obtain the natural convection thermal resistance. The fan outlet wind speed is measured by an anemometer, the flow state is determined based on the Reynolds number, and the forced convection thermal resistance is calculated based on the Nusselt number correlation formula.

[0066] The two are connected in parallel to calculate the comprehensive thermal resistance and associated with the grid nodes of the three-dimensional model.

[0067] In heat flow path analysis, the internal structure of the charging pile is divided into a heat-generating core area, a heat transfer path area, and a heat dissipation terminal area. Heat flux sensors measure the heat flux density at the interfaces of each area. Combined with the physical properties of the heat transfer medium, the heat flow difference at each node per unit time is calculated. Using the heat capacity formula, the heat difference is divided by the material's heat capacity and mass to determine the heat accumulation rate.

[0068] Step S14: Calculating the additional heat generation rate caused by the impedance change of each charging pile cable in use based on the internal cable insulation state parameters, and superimposing the additional heat generation rate on the three-dimensional heat source distribution map;

[0069] Aging of cable insulation can lead to increased impedance, thereby increasing Joule heat loss. In this step, the equivalent impedance value of the internal cables of each charging pile in use is first monitored online using an impedance spectrum analyzer, and compared with the initial calibration value to calculate the impedance change ratio. The additional heat generation rate is obtained by multiplying the square of the current by the impedance increment. The additional heat generation rate is incrementally added to the corresponding nodes of each charging pile in use in the original three-dimensional heat source distribution map. At the same time, the distribution of adjacent heat source nodes is interpolated and smoothed to avoid model distortion caused by local numerical mutations.

[0070] Step S15: Correcting the air medium thermal conductivity coefficient according to the ambient humidity data, and constructing a three-dimensional temperature field model through an iterative calculation method;

[0071] During the implementation process, the air humidity is first monitored in real time through capacitive humidity sensors deployed in the charging station, and the thermal conductivity coefficient of the air is dynamically corrected based on the nonlinear relationship between humidity and air thermal conductivity. Specifically, an empirical formula is used to map the humidity value to a correction factor for the thermal conductivity. When constructing a three-dimensional temperature field model, the physical space of the area where each charging pile is in use is discretized into three-dimensional grid cells, and the amount of heat exchange between each grid cell and the environment is calculated based on the corrected air thermal conductivity coefficient. The iterative process uses the Gauss-Seidel algorithm to gradually approximate the steady-state temperature distribution: assuming that the temperature of all grids is the ambient temperature at the initial moment, the temperature value of each grid is updated one by one based on the temperature difference between adjacent grids and the corrected thermal conductivity coefficient, until convergence is determined when the maximum temperature change of the entire grid is less than the set threshold in two consecutive iterations.

[0072] Step S16: vector superposition is performed on the three-dimensional heat source distribution map and the three-dimensional space temperature field model to construct a three-dimensional dynamic thermodynamic model of each charging pile in use.

[0073] In the simulation platform, a three-dimensional heat source distribution map and a three-dimensional temperature field model are spatially vectored. For each grid cell, the combined effect of the heat source vector direction and the temperature gradient vector is calculated. The dynamic heat conduction process is simulated using a time-stepping algorithm. Ultimately, a three-dimensional dynamic thermodynamic model of each charging station in use is generated.

[0074] Dynamic parameter analysis module: Based on the three-dimensional dynamic thermodynamic model of each charging pile in use, it identifies the possible risk factor of voltage overload of each charging pile in use;

[0075] The logic for identifying the possible risk factor of voltage overload for each charging pile in use is as follows:

[0076] Step S21: extracting key thermal characteristic values of each charging pile in use in the three-dimensional dynamic thermodynamic model in real time, including the battery compartment core temperature, the charging module heat dissipation surface temperature gradient, and the cable channel peak temperature;

[0077] Step S22: Calculate the conductor resistance increment based on the cable channel peak temperature distribution, and convert the resistance increment into an equivalent voltage drop compensation coefficient;

[0078] Step S23: Analyze the battery compartment core temperature change curve and establish a mapping relationship table between electrolyte activity decay and terminal voltage change;

[0079] The operation logic of step S23 is:

[0080] First, a three-dimensional temperature monitoring system was established within the battery compartment. The battery pack was divided into upper, middle, and lower layers, and three embedded thermocouple sensors were placed in each layer. Through continuous monitoring, a middle layer was identified as a thermal core when its temperature exceeded the average temperature of other layers by two degrees Celsius for ten consecutive minutes.

[0081] On this basis, an electrolyte activity decay model was constructed, setting 25-30 degrees Celsius as the baseline temperature range corresponding to 100% ion migration activity. When the monitored temperature exceeds this range, a basic decay calculation is performed according to the rule that the activity decreases linearly by 0.6% for every 1 degree Celsius increase in temperature. For high-temperature operating conditions exceeding 45 degrees Celsius, an additional exponential amplification factor is introduced, and an irreversible activity loss of 0.2% per hour is accumulated. When converting the activity decay to terminal voltage drop, a direct mapping relationship between the activity decrease percentage and the voltage value is established, where every 1% activity decay corresponds to a base voltage drop of 0.08 volts. For high-temperature areas above 40 degrees Celsius, a compensation of 0.005 volts is added for every 1 degree Celsius increase in temperature. When the battery has been cycled for more than 500 times, a 1.2x aging compensation factor is activated. Based on the above rules, a three-dimensional parameter mapping table is generated, which contains five dimensions: core temperature, duration, activity decay, theoretical voltage drop, and aging compensation factor. The nearest neighbor interpolation calculation is performed in the table by real-time matching the current temperature-time combination.

[0082] Step S24: Based on the temperature gradient data of the heat dissipation surface of the charging pile, the junction temperature of the power device is calculated and associated with the voltage ripple increment caused by the switching loss;

[0083] Step S25: The voltage drop compensation coefficient, the terminal voltage change mapping value and the voltage ripple increment are integrated to generate the voltage overload possible risk coefficient of each charging pile in use through a dynamic weight allocation algorithm combined with a weighted summation algorithm.

[0084] The operation logic of step S22 is:

[0085] Step S221: Delineate the 3D coordinate range of the cable channel corresponding to each charging pile in use in the 3D model of the charging station, and automatically identify the highest temperature point within the channel using a regional extreme value search algorithm. A detection cube is formed with the peak point as the center, expanding along the 3D coordinate axis. The arithmetic mean of all temperature measurement points within the cube is calculated as the representative temperature value.

[0086] Step S222: Obtaining original design parameters of the cable, where the original design parameters include the standard temperature resistivity corresponding to the conductor material type and the resistance per unit length of the cable at a standard ambient temperature; based on the actual total length of the cable, the product of the resistance per unit length and the total length is used as the reference resistance value;

[0087] Step S223: Subtract the standard ambient temperature from the average temperature of the current detection cube to obtain the actual temperature difference value; multiply the reference resistance value by the temperature difference, and then multiply it by the material temperature resistivity to obtain the resistance increment per unit length; add the actual total length of the cable; the total resistance increment is equal to the product of the resistance increment per unit length and the actual total length of the cable;

[0088] Step S224: Obtain the current charging current value passing through the cable in real time; multiply the total resistance increment by the charging current value to obtain the theoretical increase in voltage drop; divide the voltage drop increase by the rated output voltage of the charging pile, and then multiply by 100% to convert it into a percentage, thereby obtaining the equivalent voltage drop compensation coefficient.

[0089] In its implementation, the present invention first defines the three-dimensional coordinate range of each active charging pile cable channel within a three-dimensional model of the charging station. A detection cube with a set side length is extended along the X / Y / Z axes to form a temperature monitoring area. An extreme value search algorithm based on octree spatial segmentation is used to locate the highest temperature point. A cubic detection volume with a side length equal to the set threshold is established with this point as the center. All temperature measurement nodes within this cube are arithmetic averaged to obtain the representative temperature value of the current cable channel. In the conductor material parameter acquisition stage, the original design parameters of the cable are extracted from the factory parameter database: the cable's unit length benchmark resistance value at 20 degrees Celsius is retrieved and multiplied by the actual total length of the cable installation path to obtain the theoretical base resistance value of the complete cable. When calculating dynamic resistance compensation, the actual temperature rise value is first obtained by subtracting the standard ambient temperature of 20 degrees Celsius from the average temperature within the current detection cube. For example, a temperature rise of 45 degrees Celsius is obtained at a detection temperature of 65 degrees Celsius. This temperature rise value is multiplied by the benchmark resistance value and the material temperature coefficient to obtain the resistance increment per unit length of the cable. The total resistance change is then calculated based on the actual cable length. During the voltage drop dynamic deduction stage, the charging pile working current data is collected in real time, including instantaneous current, effective root mean square value and high-frequency ripple component. The effective value of the current in the current 0.1 second sliding window is taken, and the product of the current value and the total resistance increment is used as the theoretical voltage drop. Finally, the voltage drop value is divided by the rated output voltage of the charging pile and converted into an equivalent voltage drop compensation coefficient.

[0090] The operation logic of step S24 is:

[0091] Based on thermocouple sensors placed on the heat dissipation surface of the charging pile, an X-axis coordinate system is established along the direction of the heat sink fins, and a Y-axis coordinate system is established in the vertical direction. After identifying the coordinates of the highest temperature point, a junction temperature inversion model is established using the thermal resistance parameters of the package structure. The highest measurement point temperature is multiplied by the material thermal conductivity correction factor, and the product of the thermal resistance parameter and the real-time power is superimposed to obtain the estimated data value of the power device junction temperature;

[0092] On this basis, a dynamic quantitative model for switching loss was constructed. Using the 25°C ambient test value as a benchmark, a temperature compensation rule was established whereby every 100°C increase in junction temperature corresponds to a 35% increase in loss. Cumulative loss calculations were then performed for multiple devices in parallel.

[0093] The ripple feature reconstruction is then performed. The total switching loss is divided by the switching period to obtain the power fluctuation component. This component is divided by the DC bus voltage value to convert it into an equivalent current ripple, and then multiplied by the total impedance of the charging circuit to obtain the voltage ripple increment.

[0094] Multi-level linkage warning module: Generates graded warning signals based on the possible risk factor of voltage overload of each charging pile in use.

[0095] Generates graded warning signals based on the potential risk factor of voltage overload for each charging station in use, including:

[0096] Compare the voltage overload risk factor of each charging pile in use with the preset safety assessment threshold range [S1, S2];

[0097] If the voltage overload risk factor of a charging pile in use is less than S1, the warning level of the charging pile in use will be marked as level 1, and no warning prompt will be issued for the charging pile in use;

[0098] If the voltage overload risk factor of a charging pile in use is greater than S2, the warning level of the charging pile in use will be marked as level 3, the power supply of the charging pile in use will be automatically cut off, and the dry powder fire extinguishing device will be activated;

[0099] If the voltage overload risk factor of a charging pile in use is within the safety assessment threshold range, the warning level of the charging pile in use will be marked as level two, the sound and light alarm device will be triggered, and the warning information will be pushed through the mobile APP.

[0100] It should be noted that the intervals and thresholds are set for ease of comparison. The threshold size depends on the amount of sample data and the cardinality set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless numerical calculations. These formulas are derived from software simulations of the most recent real-world conditions using large amounts of data. The preset parameters in these formulas are set by those skilled in the art based on actual conditions.

[0101] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.

[0103] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0104] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The fire warning system for new energy vehicle charging stations based on AI algorithm is characterized by: include: Dynamic parameter acquisition module: This module uses a multimodal sensor array deployed in the charging station and the battery management system built into each charging pile to collect the dynamic parameters of each charging pile in use during the charging process in real time. Based on these dynamic parameters, a three-dimensional dynamic thermodynamic model of each charging pile in use is constructed. Dynamic parameter analysis module: Based on the three-dimensional dynamic thermodynamic model of each charging pile in use, it identifies the possible risk factor of voltage overload of each charging pile in use; Multi-level linkage warning module: Generates graded warning signals based on the possible risk factor of voltage overload of each charging pile in use.

2. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 1 is characterized in that: The dynamic parameters of each charging pile in use during the charging process include the charging current, voltage, battery temperature, ambient temperature, ambient humidity and the insulation status of the cables inside the charging pile.

3. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 2 is characterized in that: A three-dimensional dynamic thermodynamic model of the charging station is constructed based on the dynamic parameters. The specific construction logic is as follows: Step S11: synchronously collect the charging current, voltage and corresponding battery temperature data of each charging pile in use, and establish a mapping relationship between the charging equipment and the spatial coordinates; Step S12: Calculate the real-time heat generation power of each charging pile in use based on the charging current data, and generate a three-dimensional heat source distribution map of the charging equipment; Step S13: quantifying the thermal resistance coefficient of the air medium by combining the shell temperature and ambient temperature data of each charging pile in use, and superimposing the thermal resistance coefficient of the air medium on the three-dimensional heat source distribution map; Step S14: Calculating the additional heat generation rate caused by the impedance change of each charging pile cable in use based on the internal cable insulation state parameters, and superimposing the additional heat generation rate on the three-dimensional heat source distribution map; Step S15: Correcting the air medium thermal conductivity coefficient according to the ambient humidity data, and constructing a three-dimensional temperature field model through an iterative calculation method; Step S16: vector superposition is performed on the three-dimensional heat source distribution map and the three-dimensional space temperature field model to construct a three-dimensional dynamic thermodynamic model of each charging pile in use.

4. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 1 is characterized in that: The specific implementation of step S13 includes: Step S131: Scan the surface temperature field of each charging pile shell in use with an infrared thermal imager, extract the temperature gradient distribution characteristics and mark the local hot spot area; Step S132: Calculating the thermal resistance coefficients of natural convection and forced heat dissipation based on the ambient temperature and humidity sensor data; Step S133: Analyze the heat conduction path based on the principle of heat flow continuity and quantify the heat accumulation rate of key components; Step S134: Generate the thermal resistance coefficient of the air medium according to the product of the thermal resistance coefficient and the heat accumulation rate.

5. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 1 is characterized in that: The logic for identifying the possible risk factor of voltage overload for each charging pile in use is as follows: Step S21: extracting key thermal characteristic values of each charging pile in use in the three-dimensional dynamic thermodynamic model in real time, including the battery compartment core temperature, the charging module heat dissipation surface temperature gradient, and the cable channel peak temperature; Step S22: Calculate the conductor resistance increment based on the cable channel peak temperature distribution, and convert the resistance increment into an equivalent voltage drop compensation coefficient; Step S23: Analyze the battery compartment core temperature change curve and establish a mapping relationship table between electrolyte activity decay and terminal voltage change; Step S24: Based on the temperature gradient data of the heat dissipation surface of the charging pile, the junction temperature of the power device is calculated and associated with the voltage ripple increment caused by the switching loss; Step S25: The voltage drop compensation coefficient, the terminal voltage change mapping value and the voltage ripple increment are integrated to generate the voltage overload possible risk coefficient of each charging pile in use through a dynamic weight allocation algorithm combined with a weighted summation algorithm.

6. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 5 is characterized in that: The operation logic of step S22 is: Step S221: Delineate the 3D coordinate range of the cable channel corresponding to each charging pile in use in the 3D model of the charging station, and automatically identify the highest temperature point within the channel using a regional extreme value search algorithm. A detection cube is formed with the peak point as the center, expanding along the 3D coordinate axis. The arithmetic mean of all temperature measurement points within the cube is calculated as the representative temperature value. Step S222: obtaining original design parameters of the cable, wherein the original design parameters include the standard temperature resistivity corresponding to the conductor material type and the resistance per unit length of the cable at a standard ambient temperature; According to the actual total length of the cable, the product of the resistance per unit length and the total length is used as the reference resistance value; Step S223: Subtract the standard ambient temperature from the average temperature of the current detection cube to obtain the actual temperature difference value; multiply the reference resistance value by the temperature difference, and then multiply by the material temperature resistance coefficient to obtain the resistance increment per unit length; Adding the actual total length of the cable, the total resistance increment is equal to the product of the resistance increment per unit length and the actual total length of the cable; Step S224: Obtain the current charging current value passing through the cable in real time; multiply the total resistance increment by the charging current value to obtain the theoretical increase in voltage drop; divide the voltage drop increase by the rated output voltage of the charging pile, and then multiply by 100% to convert it into a percentage, thereby obtaining the equivalent voltage drop compensation coefficient.

7. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 5 is characterized in that: The operation logic of step S24 is: Based on thermocouple sensors placed on the heat dissipation surface of the charging pile, an X-axis coordinate system is established along the direction of the heat sink fins, and a Y-axis coordinate system is established in the vertical direction. After identifying the coordinates of the highest temperature point, a junction temperature inversion model is established using the thermal resistance parameters of the package structure. The highest measurement point temperature is multiplied by the material thermal conductivity correction factor, and the product of the thermal resistance parameter and the real-time power is superimposed to obtain the estimated data value of the power device junction temperature; On this basis, a dynamic quantitative model for switching loss was constructed. Using the 25°C ambient test value as a benchmark, a temperature compensation rule was established whereby every 100°C increase in junction temperature corresponds to a 35% increase in loss. Cumulative loss calculations were then performed for multiple devices in parallel. The ripple feature reconstruction is then performed. The total switching loss is divided by the switching period to obtain the power fluctuation component. This component is divided by the DC bus voltage value to convert it into an equivalent current ripple, and then multiplied by the total impedance of the charging circuit to obtain the voltage ripple increment.

8. The fire warning system for new energy vehicle charging stations based on AI algorithm according to claim 1 is characterized in that: Generates graded warning signals based on the potential risk factor of voltage overload for each charging station in use, including: Compare the voltage overload risk factor of each charging pile in use with the preset safety assessment threshold range [S1, S2]; If the voltage overload risk factor of a charging pile in use is less than S1, the warning level of the charging pile in use will be marked as level 1, and no warning prompt will be issued for the charging pile in use; If the voltage overload risk factor of a charging pile in use is greater than S2, the warning level of the charging pile in use will be marked as level 3, the power supply of the charging pile in use will be automatically cut off, and the dry powder fire extinguishing device will be activated; If the voltage overload risk factor of a charging pile in use is within the safety assessment threshold range, the warning level of the charging pile in use will be marked as level two, the sound and light alarm device will be triggered, and the warning information will be pushed through the mobile APP.

Images