Electric two-wheeled vehicle charging method and device with intelligent fault diagnosis function and storage medium

Abstract

The invention discloses an electric two-wheeled vehicle charging method and device with an intelligent fault diagnosis function and a storage medium, and relates to the technical field of electric vehicle charging fault diagnosis, the method has an intelligent fault diagnosis function, various data in the charging process can be monitored and analyzed in real time, potential faults can be recognized in advance, and charging safety and equipment reliability are improved. According to data collected by a sensor network, such as charging state, short circuit fluctuation, leakage current and cable temperature, the system can automatically identify faults such as poor plug contact, micro short circuit, electric leakage and temperature abnormity, generate corresponding fault instructions and timely take measures such as power failure and alarm to prevent accidents. And the self-discharge monitoring function can also judge whether self-discharge abnormity exists in the battery according to battery discharge data, and timely notify a user to overhaul, so that the battery is prevented from being damaged.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging fault diagnosis, and specifically to a charging method, device and storage medium for electric two-wheel vehicles with intelligent fault diagnosis. Background Art

[0002] With the popularization of electric two-wheel vehicles, especially in residential areas such as urban communities, the demand for outdoor charging piles is increasing day by day. Although many community charging piles are equipped with sunshades to prevent direct sunlight, since they are still in an outdoor environment, the charging piles still face many potential fault risks.

[0003] The charging pile is located outdoors and is easily affected by weather factors. For example, in rainy days, the charging pile interface and cable may be corroded by metal due to the penetration of water vapor and rain, resulting in poor plug contact, which in turn affects the charging efficiency and even poses a risk of electric leakage. In addition, in high-temperature weather, the temperature of the charging pile and cable may rise sharply. If not monitored and processed in time, abnormal thermal expansion and contraction of the cable are likely to occur, affecting the long-term use safety of the cable. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a charging method, device and storage medium for electric two-wheel vehicles with intelligent fault diagnosis to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A charging method for electric two-wheel vehicles with intelligent fault diagnosis includes the following steps: Step 1, abnormal monitoring of the charging port: Using a convolutional neural network, a fault recognition model is constructed to identify the first charging state data during the initial charging time period when the i-th charging pile is connected to the j-th electric vehicle charging port, and a plug contact coefficient and a metal corrosion index are constructed. A preset contact resistance threshold and a corrosion threshold are set, and it is determined whether there are the following faults: When , it is determined that the plug is not fully inserted, and a first fault instruction is generated; When , it is determined that there is a risk of plug corrosion caused by water vapor at the identified port, affecting the conductivity, and a second fault instruction is generated; When and as well as , charging is resumed and step 2 is entered; Step 2, continuous monitoring in the second stage: After resuming charging, using the fault recognition model, enter the second charging time period, and collect the second charging time period Construct a short - circuit fluctuation factor from the internal second comprehensive data , leakage current and the cable temperature gradient coefficient , preset a short - circuit threshold , humidity threshold, leakage current threshold , temperature gradient threshold and charging current threshold , and determine whether there are the following faults: When , it is determined that there is a risk of micro - short - circuit fault, and a third fault instruction is generated; When the ambient humidity > the set humidity threshold and the leakage current , it is determined that there is a risk of micro - leakage on rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > the set temperature gradient threshold and the charging current , it is determined that there is an abnormal expansion and contraction of the cable connected to the charging port, and a fifth fault instruction is generated; Step Three: Self - discharge monitoring after power - off: After the second charging period is completed, that is, after the user's charging behavior ends or after any previous forced power - off process, the electric vehicle BMS is connected through the backup power supply of the charging pile to collect the third discharge data of the electric vehicle battery within the third time period , and construct a self - discharge trend index ; Preset a self - discharge threshold , and determine whether there are the following faults: When , it is determined that the battery has abnormal self - discharge, and a sixth fault instruction is generated.

[0006] Preferably, Step One includes: S11. Install a sensor network inside each charging pile, and the user monitors the status data of each electric vehicle charging process in real - time. The status data of each electric vehicle charging process includes: the first charging status data within the initial charging period , the second comprehensive data within the second charging period , and the third discharge data within the third time period ; The sensor network includes: pressure sensors, resistance sensors, electrochemical sensors, current sensors, fiber optic temperature sensors, leakage current sensors, and temperature - humidity sensors; S12. Monitor the first charging status data of the i - th charging pile and the corresponding j - th electric vehicle charging port in real - time. The first charging status data includes: electric vehicle model, battery type, battery rated voltage, battery capacity, contact resistance , actual insertion force and the metal mass loss value caused by corrosion ; S13. Use a convolutional neural network to construct an initial convolutional neural network model, and use the state data of each electric vehicle charging process to train and test the initial convolutional neural network model. Then, use the trained initial convolutional neural network model as a fault recognition model. At the same time, use the intermediate layer output of the device operation state model as a feature vector to identify feature information, and use the obtained feature information to train and test the fault recognition model. Finally, use the trained fault recognition model for data operation prediction to construct the plug contact coefficient and the metal corrosion index ; S131. Extract the contact resistance and the actual insertion force from the first charging state data. After dimensionless processing, calculate the plug contact coefficient through the following formula : In the formula, represents the standard insertion force; S132. Extract the metal mass loss value caused by corrosion from the first charging state data, and identify the initial metal mass of the port by identifying the electric vehicle model . After dimensionless processing, calculate the metal corrosion index through the following formula : Among them, according to the electric vehicle model, refer to the standard of the charging interface to obtain the initial metal mass of the plug port.

[0007] Preferably, step one further includes: S14. Preset a contact resistance threshold , and compare the plug contact coefficient with the contact resistance threshold to determine whether there is a risk of poor contact caused by the plug not being fully inserted, including: When the plug contact coefficient > the contact resistance threshold , it is determined that the plug is not fully inserted, and a first fault instruction is generated, including: the system sends a charging prompt message "The charging plug is not fully inserted. Please reinsert it to ensure good contact of the plug" to the user, and automatically pauses the charging time for 30 seconds, and then monitors the plug contact coefficient again. When When it is normal until then, it enters the recovery charging process in Step 2; if the problem that the plug is not fully inserted still exists, the system will completely interrupt the charging and prompt the operation and maintenance personnel to check the charging equipment; When the plug contact coefficient ≤ contact resistance threshold , it is determined that the plug is inserted normally, and a continue charging message is generated; the plug contact coefficient reflects the quality of the electrical connection. The lower the coefficient, the better the contact quality, the smaller the resistance to current flow, and the more reliable the electrical connection.

[0008] S15. Preset corrosion threshold , and compare the metal corrosion index with the corrosion threshold to determine whether there is a risk of plug corrosion caused by water vapor in the plug, including: When the metal corrosion index > corrosion threshold , it is determined that it is recognized that there is a risk of plug corrosion caused by water vapor in the plug, which affects the conductivity, and a second fault instruction is generated, including: the system sends a charging prompt content to the user "There is a risk of corrosion in the charging plug. Please check whether there is water vapor or corrosion in the plug. Wipe the plug and the port with a lint-free cloth to avoid continued charging", and automatically pauses the charging time, set to 60 seconds - 120 seconds later, and then monitors the metal corrosion index again , when , it is normal, then it enters the recovery charging process in Step 2; if there is still a risk of plug corrosion caused by water vapor, the system will completely interrupt the charging and prompt the operation and maintenance personnel to check the charging equipment; When the plug contact coefficient ≤ contact resistance threshold , it is determined that the plug has no water vapor and corrosion, is inserted normally, and a continue charging message is generated.

[0009] Preferably, Step 2 includes: S21. After the recovery charging, determine to enter the second charging time period , and collect and obtain the second comprehensive data through the sensor network. The second comprehensive data includes: the charging current of the port , environmental humidity , the length of the charging pile port cable , the temperature at both ends of the cable, the live wire current and the neutral wire current ; S22. After training and testing the convolutional neural network initial model fault recognition model with the second comprehensive data using the fault recognition model, analyze and calculate to obtain the short-circuit fluctuation factor , leakage current and cable temperature gradient coefficient : S221. Short - circuit fluctuation factor It is obtained by calculating through the following formula: In the formula, represents the charging current at the k - th sampling point during the second charging period and represents the average charging current; represents the total number of charging sampling points; S222. Cable temperature gradient coefficient It is obtained by calculating through the following formula: In the formula, represents the length of the cable at the charging pile port, represents the temperature difference between the two ends of the cable; represents the temperature at one end of the cable connected to the electric vehicle charging port, represents the temperature at the other end of the cable connected to the charging pile; S223. Leakage current It is obtained by calculating through the following formula: is the live - wire current, is the neutral - wire current; if there is a difference between the two, the difference is the leakage current.

[0010] Preferably, step two further includes: S23. Preset short - circuit threshold , and compare the short - circuit fluctuation factor with the short - circuit threshold to determine whether there is a risk of micro - short - circuit fault, including: When the short - circuit fluctuation factor > the short - circuit threshold , it is determined that there is a risk of micro - short - circuit fault, and a third fault instruction is generated, including: automatically disconnecting the relevant power supply and starting the circuit isolation measure; When the short - circuit fluctuation factor ≤ the short - circuit threshold , it is determined that there is no risk of micro - short - circuit fault, and continuous monitoring is carried out.

[0011] Preferably, step two further includes: S24. Preset humidity threshold and leakage - current threshold , and compare the ambient humidity and the leakage current with the humidity threshold and the leakage - current threshold respectively Make a comparison to determine whether there is a risk of micro-leakage on rainy days, including: When the environmental humidity >humidity threshold and leakage current , it is determined that there is a risk of micro-leakage on rainy days, and a fourth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30% and turns on the air-drying function during charging to reduce the humidity until the environmental humidity ≤humidity threshold. After that, if it returns to normal within 1 minute, continue charging; after the charging pile reduces the current charging current by 30%, if the leakage current still exceeds the leakage current threshold , then automatically cut off the power + disconnect the power supply; When the environmental humidity ≤set humidity threshold and , it means there is no risk of micro-leakage on rainy days, and continuous monitoring is carried out; when the environmental humidity ≤set humidity threshold and , it means there is a risk of leakage on non-rainy days, and the charging pile power path is automatically switched to the standby grounding path. After switching to the standby grounding path , then resume charging, and prompt the user to maintain the charging pile equipment; if , then trigger the first charging pile anomaly alarm, including: forcibly cut off the power + lock the charging pile, and prompt the electric vehicle user not to charge forcibly, and replace it with another charging pile to continue charging.

[0012] Preferably, step two further includes: S25. Preset the temperature gradient threshold and the charging current threshold , and compare the cable temperature gradient coefficient and the charging current with the temperature gradient threshold and the charging current threshold respectively to determine whether there is abnormal thermal expansion and contraction of the cable connected to the charging port, including: When the cable temperature gradient coefficient >set temperature gradient threshold and the charging current , it is determined that there is abnormal thermal expansion and contraction of the cable connected to the charging port, and a fifth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30% and turns on the temperature control fan or liquid cooling system during charging to reduce the cable temperature gradient until the cable temperature gradient coefficient >set temperature gradient. After that, if it returns to normal within 2 minutes, continue charging; after the charging pile reduces the current charging current by 15%-30%, if the charging current still exceeds the charging current threshold , then automatically cut off the power + disconnect the power supply; When the cable temperature gradient coefficient Set the temperature gradient threshold and charging current , it is determined that there is no abnormal thermal expansion and contraction of the cable connected to the charging port, and continuous monitoring is carried out; when the cable temperature gradient coefficient Set the temperature gradient threshold and charging current , a short-circuit fluctuation factor is constructed and go to step S23 for judgment; When the cable temperature gradient coefficient > Set the temperature gradient threshold and charging current , it indicates that the cable temperature is abnormal and not caused by thermal expansion and contraction. Trigger the second charging pile abnormal alarm, including: the system will automatically switch the charging path to the standby heat dissipation circuit. If the switch is successful, continue charging; if the switch is not successful, force a power-off + lock the charging pile, and remind the user to check the status of the charging pile cable, maintain or replace the cable.

[0013] Preferably, step three includes: S31. After the second charging period is completed, that is, after the user's charging behavior ends or after any previous forced power-off process, collect the third discharge data of the electric vehicle battery within the third time period through the standby power supply of the charging pile connected to the electric vehicle BMS. The third discharge data includes: the charged power that has ended charging and the power lost per unit time ; S32. Use the fault identification model to train and test the convolutional neural network initial model fault identification model with the third discharge data, and then analyze and calculate to obtain the self-discharge trend index : The self-discharge trend index is calculated and obtained through the following formula: In the formula, represents the charged power that has ended charging, represents the power lost per unit time; S33. Preset the self-discharge threshold , and compare the self-discharge trend index with the self-discharge threshold to determine whether there is a risk of abnormal self-discharge of the electric vehicle battery, including: When , it is determined that the battery has abnormal self-discharge, and a sixth fault instruction is generated, including: through the charging pile device screen, APP or text message, prompt the user "Your battery has abnormal self-discharge, it is recommended to stop using and perform battery maintenance"; when , it is determined that the battery has normal self-discharge, and continuous monitoring is carried out.

[0014] An electric two-wheeler charging device with intelligent fault diagnosis, comprising: A configuration unit for installing a sensor network inside each charging pile to enable users to monitor the status data of each electric vehicle during the charging process in real time. The status data of each electric vehicle during the charging process includes: the first charging status data within the initial charging time period the second comprehensive data within the second charging time period and the third discharge data within the third time period ; A fault recognition model building unit for using a convolutional neural network to build an initial convolutional neural network model, training and testing the initial convolutional neural network model with the status data of each electric vehicle during the charging process, and using the trained initial convolutional neural network model as a fault recognition model. At the same time, the intermediate layer output of the device operation status model is used as a feature vector to identify feature information, and the fault recognition model is trained and tested with the obtained feature information, and the trained fault recognition model is used for data operation prediction; An initial charging time period anomaly monitoring unit for identifying that when the i-th charging pile is connected to the j-th electric vehicle charging port, it is the initial charging time period, collecting the first charging status data within the initial charging time period to construct a plug contact coefficient and a metal corrosion index , presetting a contact resistance threshold and a corrosion threshold , and determining whether there are the following faults: When , it is determined that the plug is not fully inserted, and a first fault instruction is generated; When , it is determined that there is a risk of plug corrosion caused by water vapor in the identification port, affecting the electrical conductivity, and a second fault instruction is generated; When and , the charging is resumed; A second-stage continuous monitoring unit for using the fault recognition model to enter the second charging time period, collecting the second comprehensive data within the second charging time period to construct a short-circuit fluctuation factor , a leakage current and a cable temperature gradient coefficient , presetting a short-circuit threshold , a humidity threshold, a leakage current threshold , a temperature gradient threshold and a charging current threshold , and determining whether there are the following faults: When , it is determined that there is a risk of micro short-circuit fault, and a third fault instruction is generated; When the environmental humidity > the set humidity threshold and the leakage current , it is determined that there is a risk of micro-leakage on rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > the set temperature gradient threshold and the charging current , it is determined that there is an abnormal expansion and contraction due to heat and cold of the cable connected to the charging port, and a fifth fault instruction is generated; The self-discharge monitoring unit is used to, after the second charging period is completed, that is, after the user's charging behavior ends or after any previous forced power-off process, collect the third discharge data of the electric vehicle battery in the third time period through the backup power supply of the charging pile connected to the electric vehicle BMS, and construct a self-discharge trend index ; ; Preset a self-discharge threshold , and determine whether there are the following faults: when , it is determined that the battery has an abnormal self-discharge, and a sixth fault instruction is generated.

[0015] A storage medium includes a computer processor for loading and executing the steps of any one of the above electric two-wheeler charging methods with fault intelligent diagnosis and the fault instructions.

[0016] The present invention provides an electric two-wheeler charging method, device and storage medium with fault intelligent diagnosis. It has the following beneficial effects: (1) The invention can timely detect possible fault risks during the charging process through abnormal monitoring and real-time data collection of the charging pile port, such as problems like the plug not being fully inserted, metal corrosion caused by water vapor, and leakage. This fault intelligent diagnosis mechanism can effectively avoid the reduction of charging efficiency or leakage risk caused by poor contact or metal corrosion, thus significantly improving the safety of the charging process. As an outdoor device, the charging pile is greatly affected by weather factors.

[0017] (2) By setting multiple monitoring indicators such as environmental humidity and temperature, the invention can detect the influence of external factors such as rainy-day moisture and temperature changes on the charging pile and the cable in real time. In the case of moisture intrusion or too high cable temperature, it can automatically detect and issue an alarm, and take measures in time to reduce the probability of faults. For example, when determining the risk of micro-leakage on rainy days, the charging pile can adjust the charging state or take other safety measures to maximize the avoidance of faults caused by environmental humidity or high temperature.

[0018] (3) When a fault risk occurs in a certain link of the charging pile, the system can automatically generate a fault instruction and send an alarm message to the user in real time through the charging pile device screen, APP or text message, etc., to inform the user of the possible fault risk in advance. This active warning mechanism enables the user to detect problems in time and take effective measures to reduce the risk of equipment damage or accidents during the charging process.

[0019] (4) After the charging of the present invention is completed, it also has the function of monitoring the self-discharge of the battery. By collecting the discharge data of the electric vehicle battery and analyzing the self-discharge trend index, it can timely detect the abnormal self-discharge of the battery and avoid the performance degradation of the battery caused by long-term self-discharge. Through this function, the user can perform maintenance or replacement in advance when the battery shows abnormalities, thereby extending the service life of the battery. Description of the Drawings

[0020] Figure 1 Schematic diagram of the steps of the charging method for an electric two-wheeler with intelligent fault diagnosis according to the present invention; Figure 2 Schematic diagram of the process of the charging device for an electric two-wheeler with intelligent fault diagnosis according to the present invention. Detailed Embodiments

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment 1 Please refer to Figure 1 , the present invention provides a charging method for an electric two-wheeler with intelligent fault diagnosis, including the following steps: Step 1. Abnormal monitoring of the charging port: Using a convolutional neural network, a fault recognition model is constructed to identify when the i-th charging pile is connected to the j-th electric vehicle charging port. For the initial charging time period, the first charging state data within the initial charging time period is collected, and the plug contact coefficient and the metal corrosion index are constructed. A preset contact resistance threshold and a corrosion threshold are set, and it is judged whether there are the following faults: When , it is determined that the plug is not fully inserted, and a first fault instruction is generated; When , , it is determined that there is a risk of plug corrosion caused by water vapor in the recognition port, which affects the electrical conductivity, and a second fault instruction is generated; When and , charging is resumed and step two is entered; Step Two, Second-stage continuous monitoring: After resuming charging, using the fault recognition model, enter the second charging time period, collect the second comprehensive data within the second charging time period to construct a short-circuit fluctuation factor , leakage current and cable temperature gradient coefficient , preset short-circuit threshold , humidity threshold, leakage current threshold , temperature gradient threshold and charging current threshold , and determine whether there are the following faults: When , it is determined that there is a risk of micro short-circuit fault, and a third fault instruction is generated; When the ambient humidity > the set humidity threshold and the leakage current , it is determined that there is a risk of micro leakage in rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > the set temperature gradient threshold and the charging current , it is determined that the cable connected to the charging port has abnormal thermal expansion and contraction, and a fifth fault instruction is generated; Step Three, Self-discharge monitoring after power-off: After the second charging time period is completed, that is, after the user's charging behavior ends or after any previous forced power-off process, the electric vehicle BMS is connected through the backup power supply of the charging pile to collect the third discharge data of the electric vehicle battery within the third time period to construct a self-discharge trend index ; Preset self-discharge threshold , and determine whether there are the following faults: When , it is determined that the battery has abnormal self-discharge, and a sixth fault instruction is generated.

[0023] In this embodiment, the present invention can detect possible fault risks in a timely manner during the charging process through abnormal monitoring and real-time data collection of the charging pile ports, such as problems like the plug not being fully inserted, metal corrosion caused by water vapor, and electric leakage. This intelligent fault diagnosis mechanism can effectively avoid the reduction of charging efficiency or the risk of electric leakage caused by poor contact or metal corrosion, thus significantly enhancing the safety of the charging process. As an outdoor device, the charging pile is greatly affected by weather factors. By setting multiple monitoring indicators such as environmental humidity and temperature, the present invention can detect in real time the impact of external factors such as rainy-day moisture and temperature changes on the charging pile and the cable. In the case of moisture intrusion or the cable temperature being too high, it can automatically detect and issue an alarm, and take timely measures to reduce the probability of faults. For example, when determining the risk of micro-electric leakage on a rainy day, the charging pile can adjust the charging state or take other safety measures to maximize the avoidance of faults caused by environmental humidity or high temperature.

[0024] When a fault risk occurs in a certain link of the charging pile, the system can automatically generate a fault instruction and send an alarm message to the user in real time through the charging pile device screen, APP, or text message, etc., to inform the user of the possible fault risk in advance. This proactive warning mechanism enables the user to discover problems in a timely manner and take effective measures to reduce the risk of equipment damage or accidents during the charging process.

[0025] After the charging is completed, the present invention also has the function of monitoring the self-discharge of the battery. By collecting the discharge data of the electric vehicle battery and analyzing the self-discharge trend index, it can timely detect the abnormal self-discharge situation of the battery and avoid the performance degradation of the battery caused by long-term self-discharge. Through this function, the user can perform maintenance or replacement in advance when the battery shows abnormalities, thereby extending the service life of the battery.

[0026] Through the fault recognition model constructed by applying a convolutional neural network, it can automatically analyze and diagnose various potential faults during the charging process, reduce the need for manual intervention, and improve the maintenance efficiency and accuracy of the charging pile equipment. This intelligent operation and maintenance system not only enhances the safety of the equipment but also provides data support for the charging pile operator to make quick decisions. The user does not need to pay attention to the complex details during the charging process, and the system can automatically detect and handle abnormalities. Through real-time fault alarms and intelligent adjustments, the user can charge more reassuringly without worrying about the safety hazards caused by the external environment affecting the charging equipment. At the same time, the real-time feedback of fault information and battery health status enables the user to make a quick response, thereby improving the convenience and safety of the charging experience.

[0027] Embodiment 2 This embodiment is an explanatory description based on Embodiment 1. Specifically, Step 1 includes: S11. Install a sensor network inside each charging pile to monitor the status data of each electric vehicle charging process in real time. The status data of each electric vehicle charging process includes: the first charging status data within the initial charging time period the second comprehensive data within the second charging time period, and the third discharge data within the third time period ; The sensor network includes: pressure sensors, resistance sensors, electrochemical sensors, current sensors, fiber optic temperature sensors, leakage current sensors, and temperature and humidity sensors; S12. Monitor the first charging status data of the i-th charging pile and the corresponding j-th electric vehicle charging port in real time. The first charging status data includes: electric vehicle model, battery type, battery rated voltage, battery capacity, contact resistance , actual insertion force , and the metal mass loss value caused by corrosion ; It can provide detailed basis for fault diagnosis, so as to timely identify and handle various abnormal situations during the charging process. ;

[0028] S13. Use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the status data of each electric vehicle charging process. Then use the trained initial convolutional neural network model as a fault recognition model. At the same time, use the intermediate layer output of the device operation status model as a feature vector to identify feature information, and train and test the fault recognition model with the obtained feature information. Use the trained fault recognition model for data operation prediction to construct the plug contact coefficient and the metal corrosion index ; S131. Extract the contact resistance and the actual insertion force in the first charging status data. After dimensionless processing, calculate and obtain the plug contact coefficient through the following formula : Data example: , , ; Calculate the plug contact coefficient ; S132. Extract the metal mass loss value caused by corrosion in the first charging status data, and identify the initial metal mass of the port by identifying the electric vehicle model . After dimensionless processing, calculate and obtain the metal corrosion index through the following formula : Among them, according to the electric vehicle model, the initial metal mass of the plug port is obtained by referring to the standard of the charging interface.

[0029] Data example: , ; Calculate the metal corrosion index ; S14. Preset the contact resistance threshold , and compare the plug contact coefficient with the contact resistance threshold to determine whether there is a risk of poor contact caused by the plug not being fully inserted, including: When the plug contact coefficient > the contact resistance threshold , it is determined that the plug is not fully inserted, and a first fault instruction is generated, including: the system sends a charging prompt message to the user "The charging plug is not fully inserted. Please reinsert it to ensure good contact of the plug", and automatically pauses the charging time, set to 30 seconds later, and then monitors the head contact coefficient again. When until it indicates normal, then enter the resume charging process of step two; if the problem of the plug not being fully inserted still exists, the system will completely interrupt the charging and prompt the maintenance personnel to check the charging equipment; When the plug contact coefficient ≤ the contact resistance threshold , it is determined that the plug is inserted normally, and a continue charging message is generated; the plug contact coefficient reflects the quality of the electrical connection. The lower the coefficient, the better the contact quality, the smaller the resistance to current flow, and the more reliable the electrical connection.

[0030] S15. Preset the corrosion threshold , and compare the metal corrosion index with the corrosion threshold to determine whether there is a risk of plug corrosion caused by water vapor in the plug, including: When the metal corrosion index > the corrosion threshold , it is determined that it is recognized that there is a risk of plug corrosion caused by water vapor in the plug, which affects the conductivity, and a second fault instruction is generated, including: the system sends a charging prompt message to the user "There is a corrosion risk in the charging plug. Please check whether there is water vapor or corrosion on the plug, wipe the plug and the port with a lint-free cloth, and avoid continued charging", and automatically pauses the charging time, set to 60 seconds - 120 seconds later, and then monitors the metal corrosion index again. When , after indicating normal, it enters the recovery charging process in step two; if there is still a risk of plug corrosion caused by water vapor, the system will completely interrupt the charging and prompt the operation and maintenance personnel to check the charging device; When the plug contact coefficient ≤ contact resistance threshold , it is determined that there is no water vapor and corrosion on the plug, it is inserted normally, and a continue charging message is generated.

[0031] In this embodiment, by detecting whether the plug contact coefficient is lower than the contact resistance threshold, the system can intelligently judge whether the plug is fully inserted. When it is found that the plug is not fully inserted, a fault instruction is generated and a prompt message is sent to the user to remind them to reinsert the charging plug. This intelligent processing mechanism can effectively prevent the impact of poor plug contact on charging efficiency and safety, and interrupt the charging in time when the problem is not solved to prevent further equipment damage.

[0032] By comparing the metal corrosion index with the corrosion threshold, the system can identify whether there is a risk of metal corrosion caused by water vapor at the charging port. When a corrosion risk is found, the system will suspend the charging and send a check prompt to the user, suggesting measures to clean the plug to avoid the continuous expansion of corrosion. If the problem remains unresolved, the system will interrupt the charging and prompt the operation and maintenance personnel to check the equipment, thus effectively preventing the decline in conductivity or other electrical faults caused by corrosion.

[0033] Embodiment 3 This embodiment is an explanatory description based on Embodiment 1. Specifically, step two includes: S21. After resuming charging, determine to enter the second charging time period , and collect and obtain the second comprehensive data through the sensor network. The second comprehensive data includes: the charging current of the port , ambient humidity , the length of the charging pile port cable , the temperatures at both ends of the cable, the live wire current and the neutral wire current ; S22. Using the fault identification model, after training and testing the convolutional neural network initial model fault identification model with the second comprehensive data, analyze and calculate to obtain the short - circuit fluctuation factor , leakage current and the cable temperature gradient coefficient : S221. The short - circuit fluctuation factor is calculated and obtained through the following formula: In the formula, represents in the second charging period The charging current at the k-th sampling point inside represents the average charging current; N represents the total number of charging sampling points; Data example: Assume the total number of sampling points = 5, the charging current ; Calculate the charging current at the k-th sampling point during the second charging period inside : ; ; ; ; ; Calculate the short-circuit fluctuation factor , sum and calculate, specifically: S222. Cable temperature gradient coefficient Obtained by calculating through the following formula: In the formula, represents the length of the cable at the charging pile port, represents the temperature difference between the two ends of the cable; represents the temperature at one end of the cable connected to the electric vehicle charging port, represents the temperature at the other end of the cable connected to the charging pile; Data example: Assume the cable length is 30m, ; Calculate the cable temperature gradient coefficient ; S223. Leakage current Obtained by calculating through the following formula: is the live wire current, is the neutral wire current; if there is a difference between the two, the difference is the leakage current.

[0034] In this embodiment, by collecting comprehensive data such as charging current, ambient humidity, cable temperature, and current difference, in the second charging time period, in-depth monitoring of the charging process is achieved. By calculating the short-circuit fluctuation factor, leakage current, and cable temperature gradient coefficient, potential risks during the charging process can be identified in real time, preventing safety hazards such as short circuits, leakage, or overheating of the cable, and improving the safety of the charging process. The calculation method of the short-circuit fluctuation factor enables the system to accurately monitor the fluctuation of the charging current. By analyzing the deviation between the charging current at each sampling point and the average current, the system can timely detect possible short-circuit or current instability problems, give early warnings, and take corresponding measures (such as pausing charging or adjusting the current), thus avoiding damage to the battery or circuit.

[0035] By calculating the cable temperature gradient coefficient, the system can effectively monitor the temperature change of the cable during the charging process, ensuring that the cable temperature does not exceed the safety threshold. Excessive cable temperature may lead to cable damage or fire risk. Real-time monitoring of the temperature difference and cable length provides effective technical protection against this risk.

[0036] In this embodiment, the leakage current is obtained by calculating the difference between the live wire current and the neutral wire current. Detection of the leakage current can effectively identify electrical leakage problems in the charging system and prevent the occurrence of leakage accidents. Timely detection of the leakage current and taking corresponding measures, such as automatic power-off or alarm, can greatly improve the safety of the charging pile and reduce the potential hazards caused by electrical faults.

[0037] Embodiment 4 This embodiment is an explanatory description based on Embodiment 1. Specifically, Step 2 further includes: S23. Preset a short-circuit threshold , and compare the short-circuit fluctuation factor with the short-circuit threshold to determine whether there is a risk of micro short-circuit fault, including: When the short-circuit fluctuation factor > the short-circuit threshold , it is determined that there is a risk of micro short-circuit fault, and a third fault instruction is generated, including: automatically disconnecting the relevant power supply and starting the circuit isolation measure; When the short-circuit fluctuation factor ≤ the short-circuit threshold , it is determined that there is no risk of micro short-circuit fault, and continuous monitoring is carried out.

[0038] S24. Preset a humidity threshold and a leakage current threshold , and compare the ambient humidity and the leakage current with the humidity threshold and the leakage current threshold Compare to determine whether there is a risk of micro-leakage in rainy days, including: When the ambient humidity > humidity threshold and the leakage current , it is determined that there is a risk of micro-leakage in rainy days, and a fourth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30% and turns on the air drying function during charging to reduce the humidity until the ambient humidity ≤ humidity threshold. After that, if it returns to normal within 1 minute, continue charging; after the charging pile reduces the current charging current by 30%, if the leakage current still exceeds the leakage current threshold , then automatically cut off the power + cut off the power supply; When the ambient humidity ≤ set humidity threshold and , it means there is no risk of micro-leakage in rainy days, and continuous monitoring is carried out; when the ambient humidity ≤ set humidity threshold and , it means there is a risk of leakage in non-rainy days, and the charging pile power path is automatically switched to the standby grounding path. After switching to the standby grounding path , then resume charging and prompt the user to maintain the charging pile equipment; if , then trigger the first charging pile abnormal alarm, including: forcibly cut off the power + lock the charging pile, and prompt the electric vehicle user not to charge forcibly, and replace it with another charging pile to continue charging.

[0039] S25. Preset temperature gradient threshold and charging current threshold , and compare the cable temperature gradient coefficient and the charging current with the temperature gradient threshold and the charging current threshold respectively to determine whether there is abnormal thermal expansion and contraction in the cable connected to the charging port, including: When the cable temperature gradient coefficient > set temperature gradient threshold and the charging current , it is determined that there is abnormal thermal expansion and contraction in the cable connected to the charging port, and a fifth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30% and turns on the temperature control fan or liquid cooling system during charging to reduce the cable temperature gradient until the cable temperature gradient coefficient > set temperature gradient. After that, if it returns to normal within 2 minutes, continue charging; after the charging pile reduces the current charging current by 15%-30%, if the charging current still exceeds the charging current threshold , then automatically cut off the power + cut off the power supply; When the cable temperature gradient coefficient set temperature gradient threshold and the charging current , it is determined that there is no abnormal thermal expansion and contraction of the cable connected to the charging port, and continuous monitoring is carried out; when the cable temperature gradient coefficient is less than the set temperature gradient threshold and the charging current , then a short - circuit fluctuation factor is constructed and judged in step S23; When the cable temperature gradient coefficient is greater than the set temperature gradient threshold and the charging current , it means that the cable temperature is abnormal and not caused by thermal expansion and contraction. A second charging pile abnormal alarm is triggered, including: the system will automatically switch the charging path to the standby heat dissipation loop. If the switch is successful, charging will continue; if the switch is not successful, power will be cut off forcibly + the charging pile will be locked, and the user will be reminded to check the cable status of the charging pile, maintain or replace the cable.

[0040] In this embodiment, by presetting the short - circuit threshold and comparing it with the short - circuit fluctuation factor, this embodiment can effectively identify the risk of micro - short - circuit faults. When the short - circuit fluctuation factor exceeds the set threshold, the system will automatically cut off the power supply and start the circuit isolation measure to prevent more serious electrical faults caused by the short - circuit. This active safety protection mechanism greatly improves the safety during the charging process and reduces the risk of damage to electrical equipment.

[0041] By monitoring the ambient humidity and the leakage current and comparing them with the set humidity and leakage current thresholds, the system can effectively identify the risk of micro - leakage in rainy days. If a risk occurs, the system will intelligently reduce the charging current and start the air - drying function to reduce the influence of humidity and ensure the safety of the charging process. If the humidity is too high and the leakage current cannot be effectively controlled, the system will automatically cut off the power supply to avoid potential hazards caused by electrical leakage. This mechanism enhances the adaptability of the charging pile in a humid environment and avoids safety hazards caused by environmental factors.

[0042] By setting the temperature gradient threshold and the charging current threshold, the system can effectively monitor whether there is abnormal thermal expansion and contraction of the cable. When the cable temperature gradient coefficient exceeds the set threshold and the charging current is too high, the system will automatically reduce the charging current and start the temperature - controlled fan or liquid - cooling system to adjust the cable temperature gradient and avoid overheating or damage of the cable. If the charging current cannot be effectively controlled, the system will cut off the power supply, reducing the safety risk of the cable caused by temperature abnormalities.

[0043] Embodiment 5 This embodiment is an explanatory description based on Embodiment 4. Specifically, step three includes: S31. After the second charging time period is completed, that is, after the user's charging behavior ends or after any previous forced power - off process, the electric vehicle BMS is connected through the standby power supply of the charging pile to collect the third time period The third discharge data of the electric vehicle battery, where the third discharge data includes: the charged power that has ended and the power loss per unit time ; S32. After training and testing the initial convolutional neural network fault recognition model with the third discharge data using the fault recognition model, analyze and calculate to obtain the self-discharge trend index : Self-discharge trend index is calculated and obtained through the following formula: In the formula, represents the charged power that has ended, represents the power loss per unit time; Data example: ; ; Calculate the self-discharge trend index : ; S33. Preset the self-discharge threshold , and compare the self-discharge trend index with the self-discharge threshold to determine whether there is a risk of abnormal self-discharge of the electric vehicle battery, including: When , it is determined that the battery has abnormal self-discharge, and a sixth fault instruction is generated, including: through the charging pile device screen, APP or text message, to the user "Your battery has abnormal self-discharge, it is recommended to stop using and perform battery maintenance"; when , it is determined that the battery has normal self-discharge, and continuous monitoring is carried out.

[0044] In this embodiment, through the real-time collection and analysis of the third discharge data, the system can accurately identify whether there is abnormal self-discharge in the electric vehicle battery. The calculation of the self-discharge trend index and the comparison mechanism with the preset self-discharge threshold can issue an alarm in time when abnormal self-discharge of the battery occurs. In this way, users can discover and handle problems at the initial stage, avoiding damage or failure of the battery caused by abnormal self-discharge, thereby improving the service life and charging safety of the battery. Once it is detected that the battery has abnormal self-discharge, the system will notify the user of the abnormal information in a timely manner through the charging pile screen, APP or text message. This proactive notification method can effectively enhance the user's safety awareness and remind the user to take measures to perform battery maintenance as soon as possible. In this way, users can identify and avoid potential safety hazards earlier.

[0045] The following is the specific sample data example Chart 1: The contact resistance threshold is: = 1.10 mΩ; the corrosion threshold = 3.2% short - circuit threshold = 0.0058 A 2 ; the humidity threshold is 85%; the leakage current threshold = 30 mA; the temperature gradient threshold of the cable is 2.3 m / °C; the charging current threshold = 8 A; The self - discharge threshold = 4.5%; The following is the judgment of the fault instruction corresponding to the sample data example chart 1 as follows: Abnormal monitoring of the charging port, the plug is not fully inserted (the first fault instruction): Triggered when the plug contact coefficient > 1.10 mΩ. Triggered battery cart numbers: 002 (1.15 mΩ), 007 (1.14 mΩ), 009 (1.13 mΩ); The risk of plug corrosion (the second fault instruction): Triggered when the metal corrosion index > 3.2%.

[0046] Triggered battery cart numbers: 003 (3.2%), 005 (3.5%), 007 (3.3%), 008 (3.4%) Resume charging when the conditions are met: Resume normal charging when the plug contact coefficient ≤ 1.10 mΩ and the metal corrosion index ≤ 3.2%. Normal vehicles: 001, 004, 006, 009, 010; Continuous monitoring in the second stage: Micro - short - circuit fault (the third fault instruction); Triggered when the short - circuit fluctuation factor > 0.0058 A². Triggered battery cart numbers: 002 (0.0060 A²), 005 (0.0059 A²), 010 (0.0061 A²), automatically disconnect the relevant power supply and start the circuit isolation measures; The risk of micro - leakage in rainy days (the fourth fault instruction): Triggered when the ambient humidity > 85% and the leakage current > 30 mA. Triggered battery cart numbers: 002 (humidity 90%, leakage 35 mA), 003 (humidity 88%, leakage 28 mA), 005 (humidity 92%, leakage 50 mA), 008 (humidity 95%, leakage 30 mA); Abnormal thermal expansion and contraction of the cable (the fifth fault instruction): Triggered when the cable temperature gradient coefficient > 2.3 m / °C and the charging current > 8 A. Triggered battery cart numbers: 005 (2.3 m / °C, charging current 10 A), 010 (2.3 m / °C, charging current 8 A); Self-discharge monitoring after full charge: Abnormal self-discharge (the sixth fault instruction): Triggered when the self-discharge trend index > 4.5%. Triggered battery cart numbers: 002 (4.5%), 008 (4.6%); Example 6 Please refer to Figure 2 , an electric two-wheeler charging device with intelligent fault diagnosis, including: A configuration unit for installing a sensor network inside each charging pile to enable users to monitor the status data of each electric vehicle during the charging process in real time. The status data of each electric vehicle during the charging process includes: the first charging status data within the initial charging time period the second comprehensive data within the second charging time period and the third discharge data within the third time period ; A fault identification model building unit for using a convolutional neural network to build an initial convolutional neural network model, training and testing the initial convolutional neural network model with the status data of each electric vehicle during the charging process, and using the trained initial convolutional neural network model as the fault identification model. At the same time, the intermediate layer output of the device operation status model is used as a feature vector to identify the feature information, and the fault identification model is trained and tested with the obtained feature information, and the trained fault identification model is used for data operation prediction; An initial charging time period abnormal monitoring unit for identifying that when the i-th charging pile is connected to the j-th electric vehicle charging port, it is the initial charging time period, collecting the first charging status data within the initial charging time period and constructing a plug contact coefficient and a metal corrosion index , presetting a contact resistance threshold and a corrosion threshold , and determining whether there are the following faults: When , it is determined that the plug is not fully inserted, and a first fault instruction is generated; When , it is determined that there is a risk of plug corrosion due to water vapor in the identification port, affecting the conductivity, and a second fault instruction is generated; When and , the charging is resumed; A second-stage continuous monitoring unit for using the fault identification model to enter the second charging time period, collecting the second comprehensive data within the second charging time period and constructing a short-circuit fluctuation factor , a leakage current and a cable temperature gradient coefficient , presetting a short-circuit threshold , a humidity threshold, and a leakage current threshold The temperature gradient threshold and the charging current threshold , and determine whether there are the following faults: When , it is determined that there is a risk of micro-short circuit fault, and a third fault instruction is generated; When the ambient humidity > the set humidity threshold and the leakage current , it is determined that there is a risk of micro-leakage in rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > the set temperature gradient threshold and the charging current , it is determined that there is an abnormal thermal expansion and contraction of the cable connected to the charging port, and a fifth fault instruction is generated; The self-discharge monitoring unit is used to, after the second charging period is completed, that is, after the user's charging behavior ends or after any previous forced power-off process, collect the third discharge data of the electric vehicle battery in the third time period through the backup power supply of the charging pile connected to the electric vehicle BMS, and construct a self-discharge trend index ; Preset a self-discharge threshold , and determine whether there are the following faults: When , it is determined that the battery has abnormal self-discharge, and a sixth fault instruction is generated.

[0047] A storage medium includes a computer processor for loading and executing the steps of any one of the above electric two-wheeler charging methods with fault intelligent diagnosis and the fault instructions.

[0048] The setting of the size of the threshold is for the convenience of comparison. Regarding the size of the threshold, it depends on the amount of sample data and the number of base numbers set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantified value is not affected.

[0049] The above formulas are all obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for charging an electric two-wheeled vehicle with intelligent fault diagnosis, characterized in that: The following steps are involved: Step 1: Charging port abnormality monitoring: Use convolutional neural network to build a fault recognition model to identify the initial charging time period when the i-th charging pile is connected to the j-th electric vehicle charging port, and collect the initial charging time period First charge status data, build plug contact coefficient and metal corrosion index , preset contact resistance threshold and corrosion threshold , and determine whether the following faults exist: when , it is determined that the plug is not fully inserted, and a first fault instruction is generated; when , it is determined that there is water vapor in the identification port, which may cause the risk of plug corrosion and affect the conductivity, and a second fault instruction is generated; when as well as , then resume charging and go to step 2; Step 2: The second stage continues: After resuming charging, use the fault identification model to enter the second charging time period and collect the second charging time period Second comprehensive data, construct short-circuit volatility factor , leakage current and cable temperature gradient coefficient , preset short-circuit threshold , humidity threshold, leakage current threshold , temperature gradient threshold and charging current threshold , and determine whether the following faults exist: when , it is determined that there is a risk of micro short circuit fault, and a third fault instruction is generated; When the ambient humidity > Set humidity threshold and leakage current , it is determined that there is a risk of micro-leakage in rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > Set the temperature gradient threshold and charging current , it is determined that the cable connected to the charging port has abnormal thermal expansion and contraction, and a fifth fault instruction is generated; Step 3: Self-discharge monitoring after power failure: Second charging time period After completion, that is, the user's charging behavior ends or after any previous forced power-off process, the charging pile backup power supply is connected to the electric vehicle BMS to collect the third time period The third discharge data of electric vehicle batteries is used to build a self-discharge trend index ; Preset self-discharge threshold , and determine whether there are the following faults: , it is determined that the battery has self-discharge abnormality and a sixth fault instruction is generated.

2. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 1, characterized in that: Step one includes: S11. Install a sensor network inside each charging pile, and the user monitors the status data of each electric vehicle charging process in real time. The status data of each electric vehicle charging process includes: initial charging time period The first charging status data and the second charging time period Second comprehensive data and third time period Internal third discharge data; The sensor network includes: pressure sensor, resistance sensor, electrochemical sensor, current sensor, fiber optic temperature sensor, leakage current sensor and temperature and humidity sensor; S12: Real-time monitoring of the first charging status data of the i-th charging pile and the corresponding j-th electric vehicle charging port, the first charging status data including: electric vehicle model, battery type, battery rated voltage, battery capacity, contact resistance , Actual insertion force and metal mass loss due to corrosion ; S13. Use a convolutional neural network to construct an initial convolutional neural network model, and use the state data of each electric vehicle charging process to train and test the initial convolutional neural network model, and use the trained initial convolutional neural network model as a fault recognition model. At the same time, use the intermediate layer output of the equipment operation state model as a feature vector to identify feature information, and use the acquired feature information to train and test the fault recognition model, and use the trained fault recognition model as a data operation prediction to construct a plug contact coefficient and metal corrosion index ; S131: Extracting contact resistance from first charging state data and actual insertion force , after dimensionless processing, the plug contact coefficient is calculated by the following formula : In the formula, Indicates standard insertion force; S132: Extracting the metal mass loss value caused by corrosion in the first charging state data and identify the initial metal quality of the port by identifying the electric vehicle model After dimensionless processing, the metal corrosion index is calculated by the following formula : Among them, according to the electric vehicle model, the initial metal mass of the plug port is obtained by referring to the standard of the charging interface.

3. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 2, characterized in that: Step 1 also includes: S14, preset contact resistance threshold , and the plug contact coefficient Contact resistance threshold Compare to determine whether there is a risk of poor contact due to the plug not being fully inserted, including: When the plug contact factor >Contact resistance threshold , it is determined that the plug is not fully inserted, and the first fault instruction is generated, including: the system sends a charging reminder to the user "the charging plug is not fully inserted, please reinsert it to ensure good contact of the plug", and automatically pauses the charging time, set to 30 seconds, and monitors the head contact coefficient again ,when If the problem of the plug not being fully inserted persists, the system will completely interrupt charging and prompt the operator to check the charging equipment. When the plug contact factor ≤Contact resistance threshold , determine that the plug is inserted normally, and generate a message to continue charging; S15, preset corrosion threshold , and the metal corrosion index Corrosion Threshold Compare to determine whether there is a risk of plug corrosion due to water vapor, including: When the metal corrosion index >Corrosion threshold , it is determined that there is water vapor in the plug, which may cause corrosion risk and affect the conductivity, and a second fault instruction is generated, including: the system sends a charging reminder to the user, "There is a risk of corrosion in the charging plug. Please check whether the plug has water vapor or corrosion. Use a lint-free cloth to wipe the plug and port to avoid further charging", and automatically pauses the charging time, which is set to 60 seconds to 120 seconds, and monitors the metal corrosion index again. ,when , indicating that it is normal, the system will enter the second step of the recovery charging process; if there is still a risk of plug corrosion caused by water vapor, the system will completely interrupt charging and prompt the operation and maintenance personnel to check the charging equipment; When the plug contact factor ≤Contact resistance threshold , determine that the plug has no water vapor and corrosion, is inserted normally, and generate a message to continue charging.

4. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 1, characterized in that: Step 2 includes: S21. After resuming charging, determine to enter the second charging time period , collect and obtain the second comprehensive data through the sensor network, the second comprehensive data includes: the charging current of the port , Ambient humidity , Charging pile port cable length , cable end temperature, live wire current and neutral current ; S22, using the fault identification model, after training and testing the convolutional neural network initial model fault identification model with the second comprehensive data, analyze and calculate to obtain the short circuit fluctuation factor , leakage current and cable temperature gradient coefficient : S221, the short circuit fluctuation factor Calculated by the following formula: In the formula, Indicates the second charging period The charging current at the kth sampling point, Indicates the average charging current; Indicates the total number of charging sampling points; S222, the cable temperature gradient coefficient Calculated by the following formula: In the formula, Indicates the length of the charging pile port cable. Indicates the temperature difference between the two ends of the cable; Indicates the temperature of the cable end connected to the electric vehicle charging port. Indicates the temperature at the other end of the cable connected to the charging pile; S223, the leakage current Calculated by the following formula: is the live wire current, is the neutral current; if there is a difference between the two, the difference is the leakage current.

5. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 4, characterized in that: Step 2 also includes: S23, preset short circuit threshold , and the short-circuit fluctuation factor With short circuit threshold Compare to determine whether there is a risk of micro short circuit failure, including: When the short-circuit fluctuation factor >Short circuit threshold , it is determined that there is a risk of micro short circuit fault, and a third fault instruction is generated, including: automatically disconnecting the relevant power supply and starting circuit isolation measures; When the short-circuit fluctuation factor ≤ short circuit threshold , it is determined that there is no risk of micro short circuit failure and continuous monitoring is performed.

6. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 5, characterized in that: Step 2 also includes: S24, preset humidity threshold and leakage current threshold , and the ambient humidity and leakage current Respectively with humidity threshold and leakage current threshold Compare to determine whether there is a risk of micro-leakage in rainy days, including: When the ambient humidity >Humidity threshold and leakage current , it is determined that there is a risk of micro-leakage in rainy days, and the fourth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30%, and turns on the air drying function during charging to reduce the humidity until the ambient humidity ≤ humidity threshold, if it returns to normal within 1 minute, continue charging; after the charging pile reduces the current charging current by 30%, the leakage current Still exceeds the leakage current threshold , then the power is automatically cut off + power is cut off; When the ambient humidity ≤ set humidity threshold and , indicating the risk of micro leakage on rainless days, continuous monitoring; when the ambient humidity ≤ set humidity threshold and , indicating that there is a risk of leakage in non-rainy days, the charging pile power path is automatically switched to the backup grounding path. , then resume charging and prompt the user to maintain the charging pile equipment; if , then the abnormal alarm of the first charging pile is triggered, including: forced power off + locking the charging pile, and reminding the electric vehicle user not to force charging, and change other charging piles to continue charging.

7. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 6, characterized in that: Step 2 also includes: S25, preset temperature gradient threshold and charging current threshold , and the cable temperature gradient coefficient With charging current Respectively with the temperature gradient threshold and the charging current threshold Compare to determine whether the cable connected to the charging port has abnormal thermal expansion and contraction, including: When the cable temperature gradient coefficient > Set the temperature gradient threshold and charging current , it is determined that the cable connected to the charging port has abnormal thermal expansion and contraction, and the fifth fault instruction is generated, including: the charging pile reduces the current charging current by 15%-30%, and turns on the temperature control fan or liquid cooling system during charging to reduce the cable temperature gradient until the cable temperature gradient coefficient > Set the temperature gradient. If it returns to normal within 2 minutes, continue charging. After the charging pile reduces the current charging current by 15%-30%, the charging current Still exceeds the charging current threshold , then the power is automatically cut off + power is cut off; When the cable temperature gradient coefficient Set the temperature gradient threshold and charge current , it is determined that there is no abnormal thermal expansion and contraction of the cable connected to the charging port, and continuous monitoring is performed; when the cable temperature gradient coefficient Set the temperature gradient threshold and charge current , then construct the short-circuit fluctuation factor Go to step S23 for judgment; When the cable temperature gradient coefficient > Set the temperature gradient threshold and charging current , it means that the cable temperature is abnormal, not caused by thermal expansion and contraction, triggering the second charging pile abnormal alarm, including: the system will automatically switch the charging path to the backup heat dissipation circuit. If the switch is successful, charging will continue; if the switch is unsuccessful, the power will be forced to be cut off + the charging pile will be locked, and the user will be reminded to check the status of the charging pile cable and maintain or replace the cable.

8. The electric two-wheeled vehicle charging method with intelligent fault diagnosis according to claim 7, characterized in that: Step three includes: S31, in the second charging time period After completion, that is, the user's charging behavior ends or after any previous forced power-off process, the charging pile backup power supply is connected to the electric vehicle BMS to collect the third time period The third discharge data of the electric vehicle battery, the third discharge data includes: the amount of electricity that has been charged and the amount of power lost per unit time ; S32, using the fault recognition model, after training and testing the convolutional neural network initial model fault recognition model with the third discharge data, analyzing and calculating to obtain the self-discharge trend index : The self-discharge trend index Calculated by the following formula: In the formula, Indicates the amount of power that has been charged. Indicates the amount of electricity lost per unit time; S33, preset self-discharge threshold , and the self-discharge trend index and self-discharge threshold Compare and determine whether there is an abnormal risk of electric vehicle battery self-discharge, including: when , it is determined that the battery has self-discharge anomaly, and a sixth fault instruction is generated, including: through the charging pile device screen, APP or SMS, the user is informed that "your battery has self-discharge anomaly, it is recommended to stop using it and perform battery maintenance"; when , it is determined that the battery self-discharge is normal and continues to monitor.

9. An electric two-wheeled vehicle charging device with intelligent fault diagnosis, applied to an electric two-wheeled vehicle charging method with intelligent fault diagnosis as claimed in any one of claims 1 to 8, characterized in that: include: Configuration unit, used to install a sensor network inside each charging pile, so that users can monitor the status data of each electric vehicle charging process in real time. The status data of each electric vehicle charging process includes: initial charging time period The first charging status data and the second charging time period Second comprehensive data and third time period Internal third discharge data; Construct a fault identification model unit, which is used to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the state data of each electric vehicle charging process, and use the trained initial convolutional neural network model as a fault identification model, and use the intermediate layer output of the equipment operation state model as a feature vector to identify feature information, and train and test the fault identification model through the acquired feature information, and use the trained fault identification model as data operation prediction; The initial charging time period abnormality monitoring unit is used to identify that when the i-th charging pile is connected to the j-th electric vehicle charging port, it is the initial charging time period, and collect the initial charging time period First charge status data, build plug contact coefficient and metal corrosion index , preset contact resistance threshold and corrosion threshold , and determine whether there are any of the following faults: when , it is determined that the plug is not fully inserted, and a first fault instruction is generated; when , it is determined that there is water vapor in the identification port, which may cause the risk of plug corrosion and affect the conductivity, and a second fault instruction is generated; when as well as , then resume charging and go to step 2; The second stage continuous monitoring unit is used to use the fault identification model to enter the second charging time period and collect the second charging time period Second comprehensive data, construct short-circuit volatility factor , leakage current and cable temperature gradient coefficient , preset short-circuit threshold , humidity threshold, leakage current threshold , temperature gradient threshold and charging current threshold , and determine whether there are any of the following faults: when , it is determined that there is a risk of micro short circuit fault, and a third fault instruction is generated; When the ambient humidity > Set humidity threshold and leakage current , it is determined that there is a risk of micro-leakage in rainy days, and a fourth fault instruction is generated; When the cable temperature gradient coefficient > Set the temperature gradient threshold and charging current , it is determined that the cable connected to the charging port has abnormal thermal expansion and contraction, and a fifth fault instruction is generated; The self-discharge monitoring unit is used in the second charging time period After completion, that is, the user's charging behavior ends or after any previous forced power-off process, the charging pile backup power supply is connected to the electric vehicle BMS to collect the third time period The third discharge data of electric vehicle batteries is used to build a self-discharge trend index ; Preset self-discharge threshold , and determine whether there are the following faults: , it is determined that the battery has self-discharge abnormality and a sixth fault instruction is generated.

10. A storage medium comprising a computer processor for loading and executing the steps and fault instructions of the electric two-wheeled vehicle charging method with intelligent fault diagnosis according to any one of claims 1 to 8.

Images