An intelligent detection method and system for electric charging pile

Abstract

The present invention discloses an intelligent detection method for an electric charging pile, the method comprising: collecting monitoring parameters of a battery storage area of ​​the electric charging pile; using an entropy-weighted fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate a fire risk index; applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executing the generated maintenance task plan and continuously monitoring the task execution effect, so as to optimize the entropy-weighted fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic and iterative manner. By using the embodiments of the present invention, the accuracy of fire risk assessment can be improved, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric charging piles, and in particular to an intelligent detection method and system for electric charging piles. Background Art

[0002] With the popularity of electric vehicles, the use frequency and application scope of power charging piles, as an important infrastructure connecting power sources and electric vehicles, are expanding day by day. Charging piles not only provide charging services for electric vehicles, but also undertake corresponding energy management and storage functions. However, the high-voltage electrical equipment of charging piles, battery storage during the charging process, and the complexity of their surrounding environment make charging piles face a variety of potential safety risks, especially fire risks.

[0003] At present, the safety management of charging piles mainly relies on regular inspections and manual inspections. This traditional management method has many shortcomings. First, the time interval of regular inspections may not be enough to detect potential safety hazards in a timely manner; second, manual inspections are inefficient and may lead to inaccurate inspection results due to human factors; finally, the lack of a systematic evaluation and optimization mechanism makes it difficult to continuously improve safety management strategies. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent detection method and system for electric charging piles to solve the deficiencies in the prior art, improve the accuracy of fire risk assessment, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

[0005] An embodiment of the present application provides an intelligent detection method for a power charging pile, the method comprising:

[0006] Collect monitoring parameters of the battery storage area of ​​the power charging pile;

[0007] Analyzing the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculating a fire risk index;

[0008] Applying an adaptive fire inspection and maintenance strategy algorithm to generate an inspection and maintenance task plan according to the fire risk index;

[0009] The generated maintenance task plan is executed, and the task execution effect is continuously monitored to cyclically iterate and optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm.

[0010] Optionally, the entropy weight-fuzzy logic fire risk assessment network is used to analyze the monitoring parameters and calculate the fire risk index, including:

[0011] Performing standardization on the monitoring parameters;

[0012] Calculate the entropy value of each standardized monitoring parameter and determine the weight of each monitoring parameter;

[0013] Using a pre-built fuzzy logic rule base, inputting standardized monitoring parameters into the rule base to fuzzify the monitoring parameters, and generating fuzzy output values ​​through fuzzy reasoning;

[0014] Defuzzifying the fuzzy output value and converting it into a risk level output;

[0015] The fire risk index is calculated based on the weight of each monitoring parameter and the defuzzified risk level.

[0016] Optionally, the fire risk index is calculated as follows: FRI(t) = sum_{i=1}^{n} w_i cdotR_i(t), wherein FRI(t) is the fire risk index at time t, n is the number of monitoring parameters, w_i is the weight of the i-th monitoring parameter, and R_i(t) is the risk level corresponding to the i-th monitoring parameter after defuzzification.

[0017] Optionally, the maintenance task plan is determined as follows: M_{plan}(t) = Optimize(FRI(t), P(t), C(t)), wherein M_{plan}(t) is the maintenance plan at time t, P(t) is the predicted risk trend in a future period of time, C(t) is the maintenance cost, and Optimize is the mathematical optimization function in the adaptive fire maintenance strategy algorithm.

[0018] Another embodiment of the present application provides a detection system for a power charging pile, the system comprising:

[0019] A collection module, used to collect monitoring parameters of the battery storage area of ​​the power charging pile;

[0020] A calculation module, used to analyze the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculate a fire risk index;

[0021] A generation module, for applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index;

[0022] The execution module is used to execute the generated maintenance task plan and continuously monitor the task execution effect, so as to cyclically iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm.

[0023] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0024] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0025] Compared with the prior art, the present invention provides a detection method for an electric charging pile, which collects monitoring parameters of the battery storage area of ​​the electric charging pile; uses an entropy weight-fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate the fire risk index; applies an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executes the generated maintenance task plan, and continuously monitors the task execution effect, so as to cyclically iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, thereby improving the accuracy of fire risk assessment, thereby improving the maintenance efficiency of the charging pile and effectively reducing the fire risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A hardware structure block diagram of a computer terminal for a method for detecting a power charging pile provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of a flow chart of a method for detecting a power charging pile provided by an embodiment of the present invention;

[0028] Figure 3 A schematic structural diagram of a detection system for an electric charging pile provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0030] The embodiment of the present invention firstly provides an intelligent detection method for a power charging pile, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0031] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of a distributed energy storage management method provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the computer terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the distributed energy storage management method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] See also Figure 2 , an embodiment of the present invention provides a method for detecting a power charging pile, which may include the following steps:

[0035] S201, collecting monitoring parameters of a battery storage area of ​​a power charging pile;

[0036] Specifically, collecting monitoring parameters of the battery storage area of ​​the power charging pile is the first step of the fire inspection method, and the detailed process can be as follows:

[0037] Step 1: First, deploy an intelligent monitoring system in the battery storage area of ​​the power charging station, which includes a millimeter-wave radar sensor, a spectrometer, a battery electrochemical characteristic analyzer, and an enhanced environmental monitoring sensor.

[0038] Step 2: Implement non-contact high-precision temperature monitoring through millimeter-wave radar sensors, which can directly measure the temperature of the battery's internal cells through the battery shell. Compared with traditional thermocouples or infrared temperature measurement, millimeter-wave radar has higher penetration and accuracy, and can capture the heat distribution inside the battery in real time.

[0039] Step 3: Use a spectrometer to collect gas samples in the battery storage area and monitor in real time the concentration of volatile organic compounds (VOCs), hydrogen and other flammable gases that may be caused by battery thermal runaway. The spectrometer can analyze the chemical composition of the air at the molecular level, and its measurement results will serve as an important indicator for fire warning.

[0040] Step 4: Obtain the instantaneous charge and discharge status, internal resistance and other key electrochemical parameters of the battery pack through the battery electrochemical characteristic analyzer. The analyzer can accurately grasp the health status of a single battery cell or even the entire battery pack through seamless connection with the battery management system (BMS).

[0041] Step 5: Use enhanced environmental monitoring sensors to monitor environmental parameters such as humidity, oxygen concentration, temperature fluctuations, etc. in the battery storage area in real time to promptly understand changes in external conditions that may affect battery safety.

[0042] Step 6: Based on the above monitoring parameters, a multi-dimensional data collection platform is integrated to transmit the data of all sensors to the central processing unit in real time. This platform also has preliminary data processing capabilities, which can screen, normalize and perform preliminary analysis on abnormal values, reducing the computational burden of the central processing unit.

[0043] Step 7: Establish a data security protocol to ensure that all monitoring data is transmitted securely, completely, and without interference. This protocol can encrypt the data and prevent unauthorized access through a comprehensive authentication mechanism.

[0044] Step 8: The central processing unit collects and organizes the data as the input of the entropy weight-fuzzy logic fire risk assessment network, and then calculates the fire risk index, and generates the corresponding fire maintenance task plan based on this index.

[0045] Through the above steps, the monitoring parameters in the battery storage area of ​​the power charging pile can be collected comprehensively and efficiently, providing a scientific and accurate basis for the subsequent risk assessment and implementation of maintenance strategies.

[0046] S202, analyzing the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculating a fire risk index;

[0047] Specifically, the monitoring parameters can be standardized; the entropy value of each standardized monitoring parameter is calculated to determine the weight of each monitoring parameter; the standardized monitoring parameters are input into the pre-constructed fuzzy logic rule base to fuzzify the monitoring parameters, and a fuzzy output value is generated through fuzzy reasoning; the fuzzy output value is defuzzified and converted into a risk level output; the fire risk index is calculated according to the weight of each monitoring parameter and the risk level after defuzzification. Among them, a method for calculating the fire risk index is: FRI(t) = sum_{i=1}^{n} w_i cdot R_i(t), wherein the FRI(t) is the fire risk index at time t, n is the number of monitoring parameters, w_i is the weight of the i-th monitoring parameter, and R_i(t) is the risk level corresponding to the i-th monitoring parameter after defuzzification.

[0048] Exemplarily, a specific implementation method includes:

[0049] Step 2.1: Standardization of monitoring parameters

[0050] - Implementation: Wavelet transform can be used to standardize the collected monitoring parameters. Wavelet transform is a mathematical tool that can analyze signals at multiple scales. It can decompose monitoring parameters into waveforms of different frequencies and then standardize these decomposed waveforms. For example, if the monitoring parameters include battery temperature and voltage, through wavelet transform, the high-frequency component of battery temperature (indicating rapid changes or noise) and the low-frequency component of voltage (indicating long-term trends) can be extracted and unified between 0 and 1 to ensure that they have the same scale in subsequent steps, providing standardized clean data for weighted and fuzzy logic reasoning.

[0051] Step 2.2: Calculate the entropy value of the standardized monitoring parameters and determine the weights

[0052] - Implementation: Monte Carlo simulation can be used to calculate the entropy of the normalized monitoring parameters. Monte Carlo simulation is a statistical technique that uses random samples to understand the behavior of complex systems. By generating a large number of possible parameter states and measuring the frequency of their occurrence, the probability distribution of each parameter state can be determined. From the probability distribution, the information entropy of the monitoring parameters can be evaluated, and based on these entropy values, the weight of each parameter's impact on the fire risk assessment can be inferred. Taking temperature as an example, if there are multiple possible temperature change paths, Monte Carlo simulation can be used to estimate the probability of each path and calculate the entropy of the temperature parameter based on these probabilities.

[0053] Step 2.3: Use fuzzy logic rule base to perform parameter fuzzification and fuzzy reasoning

[0054] - Implementation: Parameters can be fuzzified by defining customized fuzzy membership functions. These functions can be triangular, trapezoidal or Gaussian in shape, depending on the understanding of the impact of each parameter on the risk of fire. For example, for the battery temperature parameter, a trapezoidal fuzzy membership function can be defined, with a membership of 1 when the temperature is within the safe range and a linear decrease after exceeding the safe temperature range. Using these membership functions, the standardized parameters are converted into metrics in fuzzy sets, and then fuzzy reasoning is performed through defined fuzzy logic rules (for example: "If the temperature is high and the voltage is unstable, then the risk is high") to generate fuzzy output values.

[0055] Step 2.4: Defuzzify the fuzzy output value

[0056] - Implementation: Defuzzification can be performed using the Center of Gravity method. This method calculates the weighted average of the values ​​in the fuzzy sets, where the weights are the values ​​of their membership functions. This method considers all possible risk levels and gives them corresponding weights. After defuzzification, a specific risk assessment value can be obtained. For example, if the fuzzy output is represented as a membership function of "low risk", "medium risk" and "high risk", the Center of Gravity method will calculate the weighted center of these three fuzzy sets and output a single risk level value, which will be used to calculate the fire risk index.

[0057] Step 2.5: Calculate the fire risk index

[0058] - Implementation: The fire risk index can be calculated using the fuzzy comprehensive evaluation method. This method takes into account the weight of each monitoring parameter (determined by the entropy value) and the risk level after defuzzification, and calculates the total risk index by weighted summation. For example, assuming there are two monitoring parameters - temperature (w_1 weight) and gas concentration (w_2 weight), and their risk levels after defuzzification are R_1 and R_2, respectively, then the fire risk index FRI can be calculated by the expression FRI(t) = w_1* R_1 + w_2 * R_2, thereby providing a quantified fire risk value for the power charging pile.

[0059] S203, applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index;

[0060] Specifically, a method for determining a maintenance task plan is: M_{plan}(t) = Optimize(FRI(t), P(t), C(t)), where M_{plan}(t) is the maintenance plan at time t, P(t) is the predicted risk trend in the future, C(t) is the maintenance cost, and Optimize is the mathematical optimization function in the adaptive fire maintenance strategy algorithm. A specific implementation method can be as follows:

[0061] Step 1: First, establish an adaptive fire inspection strategy algorithm based on reinforcement learning. In this algorithm, the generation process of fire inspection tasks is regarded as a sequential decision problem, and the power charging pile as an agent learns how to generate the best inspection plan by interacting with the environment.

[0062] Step 2: Define the state space as the input of the adaptive algorithm. The state space includes information such as the real-time monitored fire risk index, historical maintenance records, current power charging pile operation status, and predicted future environmental changes.

[0063] Step 3: Define the behavior space, which is all possible maintenance behaviors that the algorithm can take. Behaviors can be specifying the inspection of a certain device, scheduling maintenance orders, assigning specific personnel to perform maintenance, etc.

[0064] Step 4: Design a reward function to evaluate the effectiveness of the maintenance plan. The reward function is based on multiple factors, such as the efficiency of the maintenance task plan, cost control, and the degree of reduction in the fire risk index after the maintenance task is performed.

[0065] Step 5: Use Deep Reinforcement Learning (DRL) algorithms, especially Deep Q-Network (DQN), to train the model so that it can select the best behavior based on the current state. DQN can handle a large number of state inputs and output the best inspection behavior.

[0066] Step 6: Train in a simulation environment and continuously iterate the algorithm. The simulation environment simulates various possible risk scenarios based on the data of real power charging piles. The agent learns to generate maintenance plans through trial and error in this environment and evaluates the pros and cons of the maintenance plans through reward functions.

[0067] Step 7: After training is completed, the trained agent is deployed to actual operation. In the actual operation of the electric charging pile, the agent will calculate the fire risk index in real time and generate a maintenance task plan in real time based on the current status.

[0068] Step 8: Set up a feedback loop to continuously monitor the effect of performing maintenance tasks and feed the results back to the reinforcement learning model. If the maintenance task leads to risk reduction or maintenance cost optimization, the agent is rewarded, otherwise it is punished. Such a negative feedback mechanism can enable the agent to predict and plan maintenance tasks more accurately during the continuous learning process.

[0069] Step 9: Combined with the mathematical optimization function Optimize, Optimize means using advanced mathematical optimization techniques, such as random forest regression analysis, to balance the relationship between risk reduction and cost control. By setting specific constraints (such as budget constraints, personnel scheduling, spare parts inventory, etc.), minimize costs and maximize safety when generating maintenance plans. This optimization is based on the optimal strategy provided by DQN and is achieved through linear programming, integer programming or other suitable mathematical programming methods.

[0070] Step 10: Through the above process, the generated maintenance task plan is output in a clear and actionable form and connected to the management system of the power charging pile to ensure that maintenance personnel can receive timely and accurate task assignments.

[0071] The above-mentioned specific implementation method utilizes the latest deep reinforcement learning technology to provide an adaptive, dynamic and optimized maintenance task planning method, which can not only improve the fire safety of power charging piles, but also optimize operating costs, making the entire maintenance process more efficient and intelligent.

[0072] S204, executing the generated maintenance task plan and continuously monitoring the task execution effect, so as to optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic iterative manner.

[0073] Specifically, one implementation may include:

[0074] Step 1: Execute the maintenance task plan First, based on the output of the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, the generated maintenance task plans are executed. These plans detail the timetable of the maintenance tasks, the required personnel and equipment, the expected goals, and the safety precautions. For example: The system generates a maintenance plan that orders a technical team to inspect the high-risk battery pack and perform a software update on the control system on Wednesday morning.

[0075] Step 2: Monitor the performance of the task Through the built-in monitoring system and feedback mechanism, data on the execution of maintenance tasks is collected in real time. This data includes the number of tasks completed, changes in risk index, equipment performance after maintenance, and any unexpected event reports. For example: The technical team completed the maintenance task, the system recorded this activity, and monitored that the temperature of the battery pack was more stable and the fire risk index decreased.

[0076] Step 3: Data Analysis and Evaluation Use data analysis tools to evaluate whether the tasks performed have achieved the expected goals and to assess the effectiveness of the tasks performed. If the risk is reduced, this indicates that the tasks were performed successfully; if the risk index has not changed significantly, further optimization may be required. For example: The analysis shows that although the temperature of some battery packs has stabilized, the overall fire risk index has not decreased as expected, which suggests that there may be other undetected risk factors.

[0077] Step 4: Iterative optimization loop Feed the results of task execution and data analysis back to the risk assessment network and maintenance strategy algorithm. Use this real-world data to retrain and optimize the model to iteratively improve the performance and accuracy of both systems. For example: Retraining the risk assessment network with the latest data may find a new risk pattern related to temperature and charging rate, and the adaptive maintenance strategy algorithm may adjust its priority and shift maintenance attention to battery packs characterized by this pattern.

[0078] Step 5: Update the maintenance task plan Based on the iteratively optimized model output, update the maintenance task plan to reflect the latest risk assessment and improved strategies. Ensure that the maintenance task plan is continuously synchronized with the real-time risk assessment and prevention strategy. For example: Based on the optimized data, the system may recommend focusing on battery packs with faster charging rates in the next maintenance cycle, and may postpone routine maintenance tasks in low-risk areas.

[0079] Step 6: Continuous Monitoring and Adaptation Finally, ensure that monitoring and updating of the entire system is ongoing, not a one-time activity. As the environment, technology, and operating conditions change, the system should be able to adapt to new challenges and update the maintenance task plan in real time. For example: If the electric charging station adds new battery technology or expands the scale of operation, the system should be able to identify these changes and automatically adjust the maintenance strategy to keep the maintenance tasks relevant and effective.

[0080] Through the above detailed steps, a dynamic system with self-learning and adaptive capabilities can be created, which continuously integrates new data and continuously optimizes risk assessment and maintenance strategies to ensure the continued safe operation and efficiency of power charging piles.

[0081] It can be seen that by collecting the monitoring parameters of the battery storage area of ​​the power charging pile; using the entropy weight-fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate the fire risk index; applying the adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executing the generated maintenance task plan, and continuously monitoring the task execution effect, so as to iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, the accuracy of fire risk assessment can be improved, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

[0082] Another embodiment of the present invention provides a detection system for a power charging pile, see Figure 3 , the system may include:

[0083] A collection module 301 is used to collect monitoring parameters of a battery storage area of ​​a power charging pile;

[0084] A calculation module 302 is used to analyze the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculate a fire risk index;

[0085] A generation module 303, for applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index;

[0086] The execution module 304 is used to execute the generated maintenance task plan and continuously monitor the task execution effect to cyclically iterate and optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm.

[0087] It can be seen that by collecting the monitoring parameters of the battery storage area of ​​the power charging pile; using the entropy weight-fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate the fire risk index; applying the adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executing the generated maintenance task plan, and continuously monitoring the task execution effect, so as to iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, the accuracy of fire risk assessment can be improved, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

[0088] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0089] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0090] S201, collecting monitoring parameters of a battery storage area of ​​a power charging pile;

[0091] S202, analyzing the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculating a fire risk index;

[0092] S203, applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index;

[0093] S204, executing the generated maintenance task plan and continuously monitoring the task execution effect, so as to optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic iterative manner.

[0094] It can be seen that by collecting the monitoring parameters of the battery storage area of ​​the power charging pile; using the entropy weight-fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate the fire risk index; applying the adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executing the generated maintenance task plan, and continuously monitoring the task execution effect, so as to iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, thereby improving the accuracy of fire risk assessment, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

[0095] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0096] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0097] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0098] S201, collecting monitoring parameters of a battery storage area of ​​a power charging pile;

[0099] S202, analyzing the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculating a fire risk index;

[0100] S203, applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index;

[0101] S204, executing the generated maintenance task plan and continuously monitoring the task execution effect, so as to optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic iterative manner.

[0102] Specifically, the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0103] It can be seen that by collecting the monitoring parameters of the battery storage area of ​​the power charging pile; using the entropy weight-fuzzy logic fire risk assessment network to analyze the monitoring parameters and calculate the fire risk index; applying the adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; executing the generated maintenance task plan, and continuously monitoring the task execution effect, so as to iteratively optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm, the accuracy of fire risk assessment can be improved, thereby improving the maintenance efficiency of charging piles and effectively reducing fire risks.

[0104] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. An intelligent detection method for a power charging pile, characterized in that: The method comprises: Collect monitoring parameters of the battery storage area of ​​the power charging pile; Analyzing the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculating a fire risk index; Applying an adaptive fire inspection and maintenance strategy algorithm to generate an inspection and maintenance task plan according to the fire risk index; Execute the generated maintenance task plan, and continuously monitor the task execution effect, so as to optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic and iterative manner; The entropy weight-fuzzy logic fire risk assessment network is used to analyze the monitoring parameters and calculate the fire risk index, including: The monitoring parameters are standardized; the entropy value of each standardized monitoring parameter is calculated to determine the weight of each monitoring parameter; Using a pre-built fuzzy logic rule base, inputting standardized monitoring parameters into the rule base to fuzzify the monitoring parameters, and generating fuzzy output values ​​through fuzzy reasoning; Defuzzifying the fuzzy output value and converting it into a risk level output; Calculate the fire risk index based on the weight of each monitoring parameter and the risk level after defuzzification; The fire risk index is calculated as follows: FRI(t) = sum_{i=1}^{n} w_i * R_i(t); Wherein, the FRI(t) is the fire risk index at time t, n is the number of monitoring parameters, w_i is the weight of the i-th monitoring parameter, and R_i(t) is the risk level corresponding to the i-th monitoring parameter after defuzzification.

2. The method according to claim 1, characterized in that The maintenance task plan is determined as follows: M_{plan}(t) = Optimize(FRI(t), P(t), C(t)); Wherein, M_{plan}(t) is the maintenance plan at time t, P(t) is the predicted risk trend in a certain period of time in the future, C(t) is the maintenance cost, and Optimize is the mathematical optimization function in the adaptive fire maintenance strategy algorithm.

3. A detection system for a power charging pile, characterized in that: The system comprises: A collection module, used to collect monitoring parameters of the battery storage area of ​​the power charging pile; A calculation module, used to analyze the monitoring parameters using an entropy weight-fuzzy logic fire risk assessment network and calculate a fire risk index; A generation module, for applying an adaptive fire maintenance strategy algorithm to generate a maintenance task plan according to the fire risk index; An execution module is used to execute the generated maintenance task plan and continuously monitor the task execution effect, so as to optimize the entropy weight-fuzzy logic fire risk assessment network and the adaptive fire maintenance strategy algorithm in a cyclic and iterative manner; The calculation module is specifically used to: perform standardization processing on the monitoring parameters; Calculate the entropy value of each standardized monitoring parameter and determine the weight of each monitoring parameter; Using a pre-built fuzzy logic rule base, inputting standardized monitoring parameters into the rule base to fuzzify the monitoring parameters, and generating fuzzy output values ​​through fuzzy reasoning; Defuzzifying the fuzzy output value and converting it into a risk level output; Calculate the fire risk index based on the weight of each monitoring parameter and the risk level after defuzzification; The fire risk index is calculated as follows: FRI(t) = sum_{i=1}^{n} w_i *R_i(t); Wherein, the FRI(t) is the fire risk index at time t, n is the number of monitoring parameters, w_i is the weight of the i-th monitoring parameter, and R_i(t) is the risk level corresponding to the i-th monitoring parameter after defuzzification.

4. The detection system for the electric charging pile according to claim 3, characterized in that: The maintenance task plan is determined as follows: M_{plan}(t) = Optimize(FRI(t), P(t), C(t)); Wherein, M_{plan}(t) is the maintenance plan at time t, P(t) is the predicted risk trend in a certain period of time in the future, C(t) is the maintenance cost, and Optimize is the mathematical optimization function in the adaptive fire maintenance strategy algorithm.

5. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 2 when executed.

6. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 2.

Images