Direct current charging pile power supply abnormity diagnosis and prediction system based on artificial intelligence

Abstract

The invention belongs to the field of charging pile abnormality diagnosis, relates to a data analysis technology, is used for solving the problem that a DC charging pile power supply abnormality monitoring system in the prior art cannot diagnose an abnormality type during charging abnormality, and particularly relates to an artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system, which comprises a diagnosis and prediction platform, the diagnosis and prediction platform is in communication connection with an operation monitoring module, a fault analysis module, a depth analysis module and a storage module; the operation monitoring module is used for monitoring and analyzing the operation state of the direct current charging pile. A charging gun connected with the direct current charging pile is marked as a monitoring object, and the monitoring coefficient of the monitoring object in the operation period is obtained. Monitoring coefficients of all monitoring objects of the direct current charging pile are sent to a fault analysis module through a diagnosis and prediction platform; according to the invention, the operation state of the DC charging pile can be monitored and analyzed, and the charging state of the monitored object in the operation period is fed back through the monitoring coefficient.

Description

Technical Field

[0001] The present invention belongs to the field of abnormal diagnosis of charging piles and relates to data analysis technology, and specifically to a DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence. Background Art

[0002] With the rapid development of the electric vehicle market, DC charging piles are important facilities for its energy supply. Their stability and reliability are crucial to the operation of electric vehicles. In order to ensure the normal operation of DC charging piles, an abnormal monitoring system is needed to monitor its operating status.

[0003] The DC charging pile power supply abnormality monitoring system in the prior art can only monitor the abnormal state of the DC charging pile, but cannot diagnose the abnormality type when charging is abnormal, and thus cannot troubleshoot the charging pile fault link that causes charging abnormality, resulting in low efficiency in abnormality handling of the charging pile when charging is abnormal.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence, which is used to solve the problem that the DC charging pile power supply abnormality monitoring system in the prior art cannot diagnose the abnormality type when charging is abnormal;

[0006] The technical problem to be solved by the present invention is: how to provide a DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence that can diagnose the abnormality type when charging is abnormal.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence, including a diagnosis and prediction platform, wherein the diagnosis and prediction platform is communicatively connected with an operation monitoring module, a fault analysis module, a depth analysis module and a storage module;

[0009] The operation monitoring module is used to monitor and analyze the operation status of the DC charging pile: mark the connected charging gun of the DC charging pile as a monitoring object, generate an operation cycle and divide the operation cycle into several operation periods, obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operation period, and obtain the monitoring coefficient of the monitoring object in the operation period by numerically calculating the power data GL, current data DL and voltage data DY; send the monitoring coefficients of all monitoring objects of the DC charging pile to the fault analysis module through the diagnosis prediction platform;

[0010] The fault analysis module is used to perform fault analysis on the DC charging pile and obtain the efficiency data of the monitored object during the operation period, obtain the monitoring threshold and the efficiency threshold through the storage module, compare the monitoring coefficient and the efficiency coefficient of the monitored object during the operation period with the monitoring threshold and the efficiency threshold respectively, and judge whether the charging state of the monitored object during the operation period meets the requirements through the comparison results;

[0011] The in-depth analysis module is used to perform in-depth analysis on the fault type of the DC charging pile.

[0012] As a preferred embodiment of the present invention, the process of acquiring power data GL includes: acquiring the power value of the monitored object during operation in real time, calling the normal power range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal power range as the normal power value, marking the absolute value of the difference between the power value and the normal power value as the abnormal power value, and marking the maximum value of the abnormal power value within the operation period as the power data GL; the process of acquiring current data DL includes: acquiring the current value of the monitored object in real time, calling the normal current range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal current range as the normal current value, marking the absolute value of the difference between the current value and the normal current value as the abnormal current value, and marking the maximum value of the abnormal current value within the operation period as the current data DL; the process of acquiring voltage data DY includes: acquiring the voltage value of the monitored object during operation in real time, calling the normal voltage range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal voltage range as the normal voltage value, and marking the absolute value of the difference between the voltage value and the normal voltage value as the voltage data DY.

[0013] As a preferred embodiment of the present invention, the process of acquiring the efficiency data of the monitored object during the operating period includes: acquiring the charging amount and the operating time of the monitored object during the operating period, and marking the ratio of the charging amount to the operating time as the efficiency coefficient of the monitored object during the operating period.

[0014] As a preferred embodiment of the present invention, the specific process of comparing the monitoring coefficient and efficiency coefficient of the monitored object during the operation period with the monitoring threshold and efficiency threshold respectively includes: if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is greater than or equal to the efficiency threshold, it is determined that the charging state of the monitored object during the operation period meets the requirements; if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is less than the efficiency threshold, it is determined that the charging state of the monitored object during the operation period does not meet the requirements, the corresponding monitored object is marked as an abnormal object, a charger abnormality signal is generated and sent to the diagnosis and prediction platform, and the diagnosis and prediction platform sends the charger abnormality signal to the mobile phone terminal of the manager after receiving the charger abnormality signal; if the monitoring coefficient is greater than or equal to the monitoring threshold, it is determined that the charging state of the monitored object during the operation period does not meet the requirements, a deep analysis signal is generated and sent to the diagnosis and prediction platform, and the diagnosis and prediction platform sends the deep analysis signal to the deep analysis module after receiving the deep analysis signal.

[0015] As a preferred embodiment of the present invention, the specific process of the deep analysis module performing deep analysis on the fault type of the DC charging pile includes: marking the number of marking times of abnormal objects in the operating period as abnormal data YC, summing and averaging the monitoring coefficients JC of all monitored objects in the operating period to obtain the monitoring performance value JB, obtaining the depth coefficient SD of the operating period by numerically calculating the abnormal data YC and the monitoring performance value JB, and marking the fault type of the DC charging pile by the depth coefficient SD.

[0016] As a preferred embodiment of the present invention, the specific process of marking the fault type of a DC charging pile includes: obtaining the depth threshold SDmax through the storage module, and comparing the depth coefficient SD with the depth threshold SDmax: if the depth coefficient SD is less than the depth threshold SDmax, then generating a charging gun abnormal signal and sending the charging gun abnormal signal and the abnormal object to the mobile phone terminal of the manager through the diagnosis and prediction platform; if the depth coefficient SD is greater than or equal to the depth threshold SDmax, then generating a charging pile abnormal signal and sending the charging pile abnormal signal to the mobile phone terminal of the manager through the diagnosis and prediction platform.

[0017] As a preferred embodiment of the present invention, the working method of the DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence includes the following steps:

[0018] Step 1: Monitor and analyze the operating status of the DC charging pile: mark the connected charging gun of the DC charging pile as the monitoring object, generate an operating cycle and divide the operating cycle into several operating periods, obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operating period and perform numerical calculation to obtain the monitoring coefficient;

[0019] Step 2: Perform fault analysis on the DC charging pile: obtain the charging capacity and running time of the monitored object during the running period, mark the ratio of the charging capacity to the running time as the efficiency coefficient of the monitored object during the running period, and judge whether the charging state of the monitored object during the running period meets the requirements through the monitoring coefficient and the efficiency coefficient;

[0020] Step 3: Conduct an in-depth analysis of the fault type of the DC charging pile: mark the number of times the abnormal object is marked during the operation period as abnormal data YC, sum and average the monitoring coefficients JC of all monitored objects during the operation period to obtain the monitoring performance value JB, and perform numerical calculations to obtain the depth coefficient SD. The fault type of the DC charging pile is marked by the depth coefficient SD.

[0021] The present invention has the following beneficial effects:

[0022] 1. The operation monitoring module can monitor and analyze the operation status of the DC charging pile, mark each charging gun of the DC charging pile, and then perform statistics and analysis on multiple operation parameters of the monitored object in a periodic monitoring manner to obtain the monitoring coefficient, and use the monitoring coefficient to provide feedback on the charging status of the monitored object during the operation period;

[0023] 2. The fault analysis module can be used to analyze the faults of DC charging piles. By combining the efficiency coefficient and monitoring coefficient of the monitored object during the operation period, it can be determined whether the monitored object has a charging fault, so as to issue a timely warning when charging abnormalities occur;

[0024] 3. The deep analysis module can be used to conduct in-depth analysis on the fault types of DC charging piles, and the monitoring coefficients of all monitoring objects during the operation period can be comprehensively analyzed to obtain the depth coefficient. The fault link of the DC charging pile can be marked according to the depth coefficient, so as to implement targeted processing measures for the fault link and improve the efficiency of handling charging abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0027] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Embodiment 1

[0030] like Figure 1 As shown, the artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system includes a diagnosis and prediction platform, which is communicatively connected to an operation monitoring module, a fault analysis module, a deep analysis module and a storage module.

[0031] The operation monitoring module is used to monitor and analyze the operation status of the DC charging pile: mark the connected charging gun of the DC charging pile as a monitoring object, generate an operation cycle and divide the operation cycle into several operation periods, and obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operation period. The acquisition process of the power data GL includes: real-time acquisition of the power value of the monitoring object during operation, calling the normal power range of the monitoring object through the storage module, marking the average value of the maximum value and the minimum value in the normal power range as the normal power value, marking the absolute value of the difference between the power value and the normal power value as the abnormal power value, and marking the maximum value of the abnormal power value in the operation period as the power data GL; the acquisition process of the current data DL includes: real-time acquisition of the current value of the monitoring object, calling the normal current range of the monitoring object through the storage module, marking the average value of the maximum value and the minimum value in the normal current range as the normal current value, marking the absolute value of the difference between the current value and the normal current value as the abnormal current value, and The maximum value in the operation time period is marked as current data DL; the process of obtaining voltage data DY includes: obtaining the voltage value of the monitored object during operation in real time, calling the normal voltage range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal voltage range as the normal voltage value, and marking the absolute value of the difference between the voltage value and the normal voltage value as voltage data DY; obtaining the monitoring coefficient of the monitored object in the operation period through the formula JC=α1*GL+α2*DL+α3*DY, where JC is the value of the monitoring coefficient, α1, α2 and α3 are all proportional coefficients, and α1>α2>α3>1; sending the monitoring coefficients of all monitored objects of the DC charging pile to the fault analysis module through the diagnosis and prediction platform; monitoring and analyzing the operation status of the DC charging pile, marking each charging gun of the DC charging pile, and then statistically analyzing and analyzing multiple operation parameters of the monitored object in a periodic monitoring manner to obtain the monitoring coefficient, and feedback the charging status of the monitored object in the operation period through the monitoring coefficient.

[0032] The fault analysis module is used to perform fault analysis on the DC charging pile: obtain the charging amount and running time of the monitored object during the running period, mark the ratio of the charging amount to the running time as the efficiency coefficient of the monitored object during the running period, obtain the monitoring threshold and efficiency threshold through the storage module, and compare the monitoring coefficient and efficiency coefficient of the monitored object during the running period with the monitoring threshold and efficiency threshold respectively: if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is greater than or equal to the efficiency threshold, it is determined that the charging state of the monitored object during the running period meets the requirements; if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is less than the efficiency threshold, it is determined that the charging state of the monitored object during the running period does not meet the requirements, and the corresponding monitored object is marked as abnormal. For a normal object, a charger abnormality signal is generated and sent to the diagnosis and prediction platform. After receiving the charger abnormality signal, the diagnosis and prediction platform sends the charger abnormality signal to the mobile phone terminal of the manager; if the monitoring coefficient is greater than or equal to the monitoring threshold, it is determined that the charging state of the monitored object during the operation period does not meet the requirements, and a deep analysis signal is generated and sent to the diagnosis and prediction platform. After receiving the deep analysis signal, the diagnosis and prediction platform sends the deep analysis signal to the deep analysis module; a fault analysis is performed on the DC charging pile, and the efficiency coefficient and the monitoring coefficient of the monitored object during the operation period are combined to determine whether the monitored object has a charging fault, so as to give a timely warning when a charging abnormality occurs.

[0033] The depth analysis module is used to perform in-depth analysis on the fault type of the DC charging pile: the number of times the abnormal object is marked during the operation period is marked as abnormal data YC, the monitoring coefficients JC of all monitored objects during the operation period are summed and averaged to obtain the monitoring performance value JB, and the depth coefficient SD of the operation period is obtained by the formula SD=β1*YC+β2*JB, where β1 and β2 are both proportional coefficients, and β1>β2>1; the depth threshold SDmax is obtained through the storage module, and the depth coefficient SD is compared with the depth threshold SDmax: if the depth coefficient SD is less than the depth threshold SDmax, an abnormal signal of the charging gun is generated, and the abnormal signal of the charging gun and the abnormal object are sent to the mobile terminal of the manager through the diagnosis and prediction platform; if the depth coefficient SD is greater than or equal to the depth threshold SDmax, an abnormal signal of the charging pile is generated, and the abnormal signal of the charging pile is sent to the mobile terminal of the manager through the diagnosis and prediction platform; the fault type of the DC charging pile is deeply analyzed, and the monitoring coefficients of all monitored objects during the operation period are comprehensively analyzed to obtain the depth coefficient, and the fault link of the DC charging pile is marked according to the depth coefficient, so as to implement targeted processing measures for the fault link and improve the processing efficiency of charging abnormalities.

[0034] In addition, it also includes an internal RCD leakage protection module and an over-temperature detection module connected to the diagnosis and prediction platform; the main function of the internal RCD leakage protection module is to detect the residual current in the circuit (i.e., current imbalance). When the detected residual current exceeds the set threshold, the RCD will automatically disconnect the circuit to prevent electric shock and electrical fire, and send relevant information to the diagnosis and prediction platform. The main function of the over-temperature detection module is to detect the temperature inside the DC pile. When the detected temperature value exceeds the set threshold, the protection action instruction is activated, and the relevant information is sent to the diagnosis and prediction platform for power outage protection, thereby reducing the risk of damage to the quality charging pile during use.

[0035] Embodiment 2

[0036] like Figure 2 As shown, the DC charging pile power supply abnormality diagnosis and prediction method based on artificial intelligence includes the following steps:

[0037] Step 1: Monitor and analyze the operating status of the DC charging pile: mark the connected charging gun of the DC charging pile as the monitoring object, generate an operating cycle and divide the operating cycle into several operating periods, obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operating period and perform numerical calculation to obtain the monitoring coefficient;

[0038] Step 2: Perform fault analysis on the DC charging pile: obtain the charging capacity and running time of the monitored object during the running period, mark the ratio of the charging capacity to the running time as the efficiency coefficient of the monitored object during the running period, and judge whether the charging state of the monitored object during the running period meets the requirements through the monitoring coefficient and the efficiency coefficient;

[0039] Step 3: Conduct an in-depth analysis of the fault type of the DC charging pile: mark the number of times the abnormal object is marked during the operation period as abnormal data YC, sum and average the monitoring coefficients JC of all monitored objects during the operation period to obtain the monitoring performance value JB, perform numerical calculations on the abnormal data YC and the monitoring performance value JB to obtain the depth coefficient SD, and mark the fault type of the DC charging pile by the depth coefficient SD.

[0040] The DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence, when working, marks the connected charging gun of the DC charging pile as the monitoring object, generates an operation cycle and divides the operation cycle into several operation periods, obtains the power data GL, current data DL and voltage data DY of the monitoring object in the operation period and performs numerical calculation to obtain the monitoring coefficient; obtains the charging amount and the operation time of the monitoring object in the operation period, marks the ratio of the charging amount to the operation time as the efficiency coefficient of the monitoring object in the operation period, and judges whether the charging state of the monitoring object in the operation period meets the requirements through the monitoring coefficient and the efficiency coefficient; marks the number of markings of abnormal objects in the operation period as abnormal data YC, sums and averages the monitoring coefficients JC of all monitoring objects in the operation period to obtain the monitoring performance value JB, and performs numerical calculation to obtain the depth coefficient SD, and marks the fault type of the DC charging pile through the depth coefficient SD.

[0041] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0042] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula JC = α1*GL+α2*DL+α3*DY; technicians in this field collect multiple groups of sample data and set corresponding monitoring coefficients for each group of sample data; substitute the set monitoring coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of α1, α2 and α3 as 3.35, 2.62 and 2.19 respectively;

[0043] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding monitoring coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the monitoring coefficient is proportional to the value of the power data.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0045] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence is characterized by: It includes a diagnosis and prediction platform, which is communicatively connected to an operation monitoring module, a fault analysis module, a depth analysis module and a storage module; The operation monitoring module is used to monitor and analyze the operation status of the DC charging pile: mark the connected charging gun of the DC charging pile as a monitoring object, generate an operation cycle and divide the operation cycle into several operation periods, obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operation period, and obtain the monitoring coefficient of the monitoring object in the operation period by numerically calculating the power data GL, current data DL and voltage data DY; send the monitoring coefficients of all monitoring objects of the DC charging pile to the fault analysis module through the diagnosis prediction platform; The fault analysis module is used to perform fault analysis on the DC charging pile and obtain the efficiency data of the monitored object during the operation period, obtain the monitoring threshold and the efficiency threshold through the storage module, compare the monitoring coefficient and the efficiency coefficient of the monitored object during the operation period with the monitoring threshold and the efficiency threshold respectively, and judge whether the charging state of the monitored object during the operation period meets the requirements through the comparison results; The in-depth analysis module is used to perform in-depth analysis on the fault type of the DC charging pile.

2. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to claim 1 is characterized in that: The process of acquiring the power data GL includes: acquiring the power value of the monitored object during operation in real time, calling the normal power range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal power range as the normal power value, marking the absolute value of the difference between the power value and the normal power value as the abnormal power value, and marking the maximum value of the abnormal power value within the operation period as the power data GL; the process of acquiring the current data DL includes: acquiring the current value of the monitored object in real time, calling the normal current range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal current range as the normal current value, marking the absolute value of the difference between the current value and the normal current value as the abnormal current value, and marking the maximum value of the abnormal current value within the operation period as the current data DL; the process of acquiring the voltage data DY includes: acquiring the voltage value of the monitored object during operation in real time, calling the normal voltage range of the monitored object through the storage module, marking the average value of the maximum value and the minimum value of the normal voltage range as the normal voltage value, and marking the absolute value of the difference between the voltage value and the normal voltage value as the voltage data DY.

3. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to claim 2 is characterized in that: The process of acquiring the efficiency data of the monitored object during the operation period includes: acquiring the charge amount and the operation time of the monitored object during the operation period, and marking the ratio of the charge amount to the operation time as the efficiency coefficient of the monitored object during the operation period.

4. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to claim 3 is characterized in that: The specific process of comparing the monitoring coefficient and efficiency coefficient of the monitored object during the operation period with the monitoring threshold and efficiency threshold respectively includes: if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is greater than or equal to the efficiency threshold, it is determined that the charging state of the monitored object during the operation period meets the requirements; if the monitoring coefficient is less than the monitoring threshold and the efficiency coefficient is less than the efficiency threshold, it is determined that the charging state of the monitored object during the operation period does not meet the requirements, the corresponding monitored object is marked as an abnormal object, a charger abnormality signal is generated and sent to the diagnosis and prediction platform, and the diagnosis and prediction platform sends the charger abnormality signal to the mobile phone terminal of the manager after receiving the charger abnormality signal; if the monitoring coefficient is greater than or equal to the monitoring threshold, it is determined that the charging state of the monitored object during the operation period does not meet the requirements, a deep analysis signal is generated and sent to the diagnosis and prediction platform, and the diagnosis and prediction platform sends the deep analysis signal to the deep analysis module after receiving the deep analysis signal.

5. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to claim 4 is characterized in that: The specific process of the deep analysis module performing deep analysis on the fault type of the DC charging pile includes: marking the number of times the abnormal object is marked during the operation period as abnormal data YC, summing and averaging the monitoring coefficients JC of all monitored objects during the operation period to obtain the monitoring performance value JB, and obtaining the depth coefficient SD of the operation period by numerically calculating the abnormal data YC and the monitoring performance value JB, and marking the fault type of the DC charging pile by the depth coefficient SD.

6. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to claim 5 is characterized in that: The specific process of marking the fault type of the DC charging pile includes: obtaining the depth threshold SDmax through the storage module, and comparing the depth coefficient SD with the depth threshold SDmax: if the depth coefficient SD is less than the depth threshold SDmax, then generating a charging gun abnormal signal and sending the charging gun abnormal signal and the abnormal object to the manager's mobile terminal through the diagnosis and prediction platform; if the depth coefficient SD is greater than or equal to the depth threshold SDmax, then generating a charging pile abnormal signal and sending the charging pile abnormal signal to the manager's mobile terminal through the diagnosis and prediction platform.

7. The artificial intelligence-based DC charging pile power supply abnormality diagnosis and prediction system according to any one of claims 1 to 6, characterized in that: The working method of the DC charging pile power supply abnormality diagnosis and prediction system based on artificial intelligence includes the following steps: Step 1: Monitor and analyze the operating status of the DC charging pile: mark the connected charging gun of the DC charging pile as the monitoring object, generate an operating cycle and divide the operating cycle into several operating periods, obtain the power data GL, current data DL and voltage data DY of the monitoring object in the operating period and perform numerical calculation to obtain the monitoring coefficient; Step 2: Perform fault analysis on the DC charging pile: obtain the charging capacity and running time of the monitored object during the running period, mark the ratio of the charging capacity to the running time as the efficiency coefficient of the monitored object during the running period, and judge whether the charging state of the monitored object during the running period meets the requirements through the monitoring coefficient and the efficiency coefficient; Step 3: Conduct an in-depth analysis of the fault type of the DC charging pile: mark the number of times the abnormal object is marked during the operation period as abnormal data YC, sum and average the monitoring coefficients JC of all monitored objects during the operation period to obtain the monitoring performance value JB, and perform numerical calculations to obtain the depth coefficient SD. The fault type of the DC charging pile is marked by the depth coefficient SD.

Images