Intelligent monitoring system and method for automobile charging pile

Abstract

The present application discloses an intelligent monitoring system and method for automobile charging piles, which relate to the technical field of charging pile monitoring, and solve the technical problem that the existing charging pile monitoring system is difficult to carry out targeted monitoring of different vehicles according to the different charging powers of different vehicles, resulting in inaccurate monitoring results; the application comprises: a data acquisition module: real-time acquisition of the charging power and charging temperature of the charging pile, as well as environmental data; a central processing module: generating an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generating a charging safety temperature according to several historical charging data and the aging adjustment factor; and generating a temperature prediction curve according to the environmental data; generating a risk coefficient according to the temperature prediction curve and the charging safety temperature; and generating an alarm signal; an early warning module: obtaining the alarm signal, and giving an alarm according to the alarm signal; monitoring the charging process of the charging pile under different charging powers, thereby increasing the accuracy of the monitoring results.

Description

Technical Field

[0001] The present application belongs to the field of charging pile monitoring technology, and relates to charging pile monitoring technology, and specifically to an intelligent monitoring system and method for automobile charging piles. Background Art

[0002] Charging piles, as key infrastructure for electric vehicle energy replenishment, play an important role in providing a source of electricity for electric vehicles. They are usually installed in public parking lots, residential areas, highway service areas and other places so that car owners can charge anytime and anywhere. Charging piles are mainly divided into two categories: AC charging piles and DC charging piles, each meeting different charging needs. With the rapid development of the electric vehicle industry, the technology of charging piles is also constantly improving. Not only is the charging speed getting faster and faster, but it also incorporates advanced technologies such as intelligence and networking. Modern charging piles generally support a variety of payment methods. Users can easily pay for charging fees through mobile phone APP, card swiping or code scanning. At the same time, charging piles also have functions such as remote monitoring and fault diagnosis, which can monitor the charging status in real time to ensure the safety and reliability of the charging process.

[0003] The prior art (the announcement number is CN109466362B invention patent) discloses a charging pile safety monitoring system, including: a camera module, a data monitoring module, a temperature measurement module, a control module, a communication module and a charging interface module, wherein the camera module, the data monitoring module and the temperature measurement module are respectively connected to the control module, the control module is connected to the communication module, and the control module is connected to the charging interface module; the vehicle image, vehicle information and temperature information of the new energy vehicle during charging are respectively obtained through the camera module, the data monitoring module and the temperature measurement module, so that the control module can timely detect whether the vehicle charging is abnormal, and then output an alarm signal or output abnormal information through the communication module, and timely control the charging interface module to stop working, which can effectively and timely avoid accidents and improve the safety and reliability of the charging pile.

[0004] The above-mentioned charging pile monitoring system obtains the vehicle temperature during charging and compares the vehicle temperature with a pre-set threshold temperature. If the temperature is greater than the threshold temperature, it means that there is an abnormality in the charging process and charging is stopped. However, in the actual working process of the charging pile, due to the different charging power of different vehicles, using the same threshold temperature to judge charging abnormalities is prone to misjudgment, resulting in inaccurate warnings and failure to detect abnormalities in the charging pile in time. Therefore, an intelligent monitoring system for automobile charging piles is needed. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an intelligent monitoring system and method for a car charging pile, which is used to solve the technical problem that the existing charging pile monitoring system is difficult to carry out targeted monitoring of different vehicles according to the different charging power of different vehicles, resulting in inaccurate monitoring results. The present application solves the above problem by generating a charging safety temperature under different charging power according to the historical data of each charging pile, and issuing an early warning to the charging pile according to the charging safety temperature.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides an intelligent monitoring system for a vehicle charging pile, comprising: a data acquisition module, a central processing module, an early warning module and a database;

[0007] The data acquisition module: acquires the charging power and charging temperature of the charging pile in real time through the data acquisition device connected thereto, and acquires the predicted environmental data through the environmental prediction platform;

[0008] The central processing module: obtains historical data of several charging piles in the test area through a database connected thereto; generates an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generates a charging safety temperature according to the several historical charging data and the aging adjustment factor; and,

[0009] Acquire predicted environmental data, real-time charging power and real-time charging temperature; search for corresponding charging safety temperature according to environmental data and charging power, input environmental data into coefficient generation model to obtain environmental impact coefficient; generate temperature prediction curve according to environmental impact coefficient; generate risk coefficient according to temperature prediction curve and charging safety temperature; generate alarm signal according to charging safety temperature, charging temperature and risk coefficient; wherein, the coefficient generation model is obtained by training of artificial intelligence model;

[0010] The early warning module is used to obtain an alarm signal and to generate an alarm according to the alarm signal.

[0011] In the present application, historical data of several charging piles in the area to be tested are obtained; an aging adjustment factor of each charging pile is generated according to several historical charging data in the historical data; a charging safety temperature is generated according to several historical charging data and the aging adjustment factor; predicted environmental data and real-time charging power are obtained; the corresponding charging safety temperature is searched according to the environmental data and the charging power, and the environmental data is input into the coefficient generation model to obtain the environmental impact coefficient; a temperature prediction curve is generated according to the environmental impact coefficient; a risk coefficient is generated according to the temperature prediction curve and the charging safety temperature; an alarm signal is generated according to the charging safety temperature, the charging temperature and the risk coefficient; and an alarm is sounded according to the alarm signal; a corresponding charging safety temperature is generated according to different charging powers and different charging environments; the current charging temperature is obtained, and an abnormal alarm signal is generated according to the charging temperature and the charging safety temperature, and the charging process of the charging pile under different charging powers is monitored, thereby increasing the accuracy of the monitoring results; and it is convenient to promptly remind relevant personnel of abnormal situations occurring during the charging process.

[0012] Preferably, the generating of the aging adjustment factor of each charging pile according to the historical charging data includes:

[0013] Extract the recording time from several historical charging data, as well as the corresponding historical charging time, historical charging power and historical charging temperature; sort the historical charging data according to the recording time from the earliest to the latest, and mark the historical charging time as LTgi, the historical charging power as LGgi, and the historical charging temperature as LWgi; i is the number of the historical charging data; g is the number of the charging pile;

[0014] According to the historical charging time LTgi, the historical charging power LGgi and the historical charging temperature LWgi, the aging adjustment factor LHg corresponding to the charging pile numbered g is calculated by the following formula: LHg=∑[LTgi / DT×a×exp(α1×|LGgi-ZGg| / ZGg+α2×|LWgi-ZWg| / ZWg)]; wherein, i=1, 2,…,Ng; Ng is the total number of historical charging data corresponding to the charging pile numbered g; ZGg is the optimal charging power of the charging pile numbered g; ZWg is the optimal charging temperature of the charging pile numbered g; DT is the unit charging time; α1 and α2 are weight coefficients; a is the adjustment coefficient.

[0015] Preferably, generating the charging safety temperature according to a number of historical charging data and an aging adjustment factor includes:

[0016] Extract historical environmental data, historical charging power and historical charging temperature from several historical charging data in the historical data; divide the historical charging data with the same historical charging power into the same power data group; divide the historical charging data in the same power data group into several environmental data groups according to the historical environmental data; obtain the historical charging temperature with the largest value in each environmental data group as the upper limit of the safe temperature of the corresponding charging pile in the corresponding environmental data group;

[0017] Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile;

[0018] The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and β1+∑(βg)=1, β1>∑(βg); b is the proportional coefficient; it is set according to experience; and the charging safety temperature of each charging pile in each environmental data group in each power data group is calculated in turn.

[0019] Preferably, the environmental data set is obtained by the following method, including:

[0020] Obtain historical data corresponding to all charging piles; extract historical environmental data from several historical charging data in each historical data; extract several environmental items from the historical environmental data; integrate each environmental item into an environmental feature vector; perform cluster analysis on the environmental feature vector to obtain several cluster clusters;

[0021] Extract the minimum and maximum values ​​of each environmental item within the cluster, take the minimum value of each environmental item as the lower boundary of the environmental item; take the maximum value of each environmental item as the upper boundary of the environmental item; integrate the lower boundaries of each environmental item into the lower boundary range of the environmental data group corresponding to the cluster; integrate the upper boundaries of each environmental item into the upper boundary range of the environmental data group corresponding to the cluster; calculate the boundary range of the environmental data group corresponding to each cluster in turn; the boundary range includes the upper boundary range and the lower boundary range.

[0022] The present application divides the historical charging data of each charging pile into several power data groups according to the charging power, and then divides the environmental data in each power data group into different environmental data groups through cluster analysis, so that the division of environmental data groups is more reasonable and the environmental data in each environmental data group is more similar.

[0023] Preferably, the coefficient generation model is obtained by training an artificial intelligence model, including:

[0024] Acquire a number of environmental data and their corresponding environmental impact coefficients through a database; integrate the environmental data and their corresponding environmental impact coefficients into a number of sets of training data and test data;

[0025] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; finally, a coefficient generation model is obtained whose input is environmental data and whose output is an environmental impact coefficient; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0026] Preferably, generating a temperature prediction curve according to the environmental impact coefficient includes:

[0027] Obtain the charging power and environmental impact coefficient, and search for the corresponding power data group according to the charging power; obtain the charging temperature change curve GT(t) corresponding to the power data group; the charging temperature change under different powers is different, and the environmental impact coefficient HXt is obtained; t is the time point; calculate the temperature prediction curve through the formula YT(t)=γ1×HXt×GT(t); where γ1 is the proportionality coefficient.

[0028] Preferably, generating a risk coefficient according to the temperature prediction curve and the charging safety temperature includes:

[0029] Obtain the temperature prediction curve GT(t); and the corresponding charging safety temperature AWjkm;

[0030] The risk coefficient FXT corresponding to each time point is calculated by the formula FXt=γ2×arctan[GT(t)-AWjkm]; where γ2 is the proportionality coefficient.

[0031] Preferably, generating an alarm signal according to the charging safety temperature, the charging temperature and the risk factor includes:

[0032] Get the charging temperature; determine whether the charging temperature is greater than the corresponding charging safety temperature;

[0033] If yes, an abnormal alarm signal and a charging stop signal are generated; the charging pile is stopped in time;

[0034] If not, mark the time point where the risk coefficient is greater than zero as an abnormal time point; obtain the risk coefficient corresponding to each abnormal time point; when the sum of the risk coefficients of each abnormal time point is greater than the risk coefficient threshold; generate an abnormal warning signal; notify relevant personnel that there may be risks in this charging and take preventive measures in advance; the alarm signal includes an abnormal alarm signal and an abnormal warning signal.

[0035] Another aspect of the present application provides an intelligent monitoring method for a vehicle charging pile, comprising the following steps:

[0036] Step 1: Obtain historical data of several charging piles in the area to be tested; generate an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generate a charging safety temperature according to the several historical charging data and the aging adjustment factor; the generating of the charging safety temperature according to the several historical charging data and the aging adjustment factor includes:

[0037] Extract historical environmental data, historical charging power and historical charging temperature from several historical charging data in the historical data; divide the historical charging data with the same historical charging power into the same power data group; divide the historical charging data in the same power data group into several environmental data groups according to the historical environmental data; obtain the historical charging temperature with the largest value in each environmental data group as the upper limit of the safe temperature of the corresponding charging pile in the corresponding environmental data group;

[0038] Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile;

[0039] The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and β1+∑(βg)=1, β1>∑(βg); b is a proportional coefficient; set according to experience; calculate the charging safety temperature of each charging pile in each environmental data group in each power data group in turn;

[0040] Step 2: Obtain predicted environmental data and real-time charging power; find the corresponding charging safety temperature according to the environmental data and charging power, and input the environmental data into a coefficient generation model to obtain an environmental impact coefficient; the coefficient generation model is obtained by training an artificial intelligence model;

[0041] Step 3: Generate a temperature prediction curve based on the environmental impact coefficient; generate a risk coefficient based on the temperature prediction curve and the charging safety temperature;

[0042] Step 4: Generate an alarm signal based on the charging safety temperature, the charging temperature and the risk factor; and sound an alarm based on the alarm signal.

[0043] Compared with the prior art, the beneficial effects of this application are:

[0044] 1. In the present application, historical data of several charging piles in the area to be tested are obtained; an aging adjustment factor of each charging pile is generated according to several historical charging data in the historical data; a charging safety temperature is generated according to several historical charging data and the aging adjustment factor; predicted environmental data and real-time charging power are obtained; the corresponding charging safety temperature is searched according to the environmental data and the charging power, and the environmental data is input into the coefficient generation model to obtain the environmental impact coefficient; a temperature prediction curve is generated according to the environmental impact coefficient; a risk coefficient is generated according to the temperature prediction curve and the charging safety temperature; an alarm signal is generated according to the charging safety temperature, the charging temperature and the risk coefficient; and an alarm is sounded according to the alarm signal; a corresponding charging safety temperature is generated according to different charging powers and different charging environments; the current charging temperature is obtained, and an abnormal alarm signal is generated according to the charging temperature and the charging safety temperature, and the charging process of the charging pile under different charging powers is monitored, thereby increasing the accuracy of the monitoring results; and it is convenient to promptly remind relevant personnel of abnormal situations occurring during the charging process.

[0045] 2. This application divides the historical charging data of each charging pile into several power data groups according to the charging power, and then divides the environmental data in each power data group into different environmental data groups through cluster analysis, so that the division of environmental data groups is more reasonable and the environmental data in each environmental data group is more similar. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 This is a schematic diagram of the principle of the intelligent monitoring system of the vehicle charging pile of this application;

[0048] Figure 2 This is a schematic diagram of the steps of the intelligent monitoring method for the automobile charging pile in this application. DETAILED DESCRIPTION

[0049] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0050] See also Figure 1, the first aspect of the present application provides an intelligent monitoring system and method for a vehicle charging pile, including: a data acquisition module, a central processing module, an early warning module and a database;

[0051] The data acquisition module: acquires the charging power and charging temperature of the charging pile in real time through the data acquisition device connected thereto, the charging temperature being the temperature of the charging head during charging, and acquires predicted environmental data through the environmental prediction platform; the environmental data is the environmental data of the area near the charging pile, including the environmental temperature, environmental humidity and environmental pressure, etc.; the data acquisition device includes a power collector, a temperature collector, a humidity collector and an air pressure collector, etc.;

[0052] The central processing module: obtains historical data of several charging piles in the test area through a database connected to it; each charging pile has a corresponding historical data, and the historical data includes several historical charging data; the historical charging data is various parameters of each charging pile when it is used; an aging adjustment factor of each charging pile is generated according to several historical charging data in the historical data; the aging adjustment factor is the aging effect caused by each use of the corresponding charging pile; a charging safety temperature is generated according to several historical charging data and the aging adjustment factor; the charging safety temperature refers to the safety value of the charging temperature of the corresponding charging pile under the corresponding charging power and the corresponding environment; and,

[0053] Obtain predicted environmental data, real-time charging power and actual charging temperature; find the corresponding charging safety temperature according to the environmental data and charging power, input the environmental data into the coefficient generation model to obtain the environmental impact coefficient; generate a temperature prediction curve according to the environmental impact coefficient; the temperature prediction curve is a curve obtained by predicting the current charging temperature; generate a risk coefficient according to the temperature prediction curve and the charging safety temperature; the risk coefficient is the probability of danger in this charging; generate an alarm signal according to the charging safety temperature, the charging temperature and the risk coefficient; the alarm signal is used to remind relevant personnel to take corresponding measures in time; wherein, the coefficient generation model is obtained by training the artificial intelligence model;

[0054] The early warning module is used to obtain an alarm signal and to generate an alarm according to the alarm signal.

[0055] In this embodiment, historical data of several charging piles in the area to be tested are obtained; aging adjustment factors of each charging pile are generated according to several historical charging data in the historical data; charging safety temperature is generated according to several historical charging data and the aging adjustment factors; predicted environmental data and real-time charging power are obtained; corresponding charging safety temperature is searched according to environmental data and charging power, and environmental data is input into a coefficient generation model to obtain an environmental impact coefficient; a temperature prediction curve is generated according to the environmental impact coefficient; a risk coefficient is generated according to the temperature prediction curve and the charging safety temperature; an alarm signal is generated according to the charging safety temperature, the charging temperature and the risk coefficient; and an alarm is issued according to the alarm signal; corresponding charging safety temperature is generated according to different charging powers and different charging environments; the current charging temperature is obtained, and an abnormal alarm signal is generated according to the charging temperature and the charging safety temperature, and the charging process of the charging pile under different charging powers is monitored, thereby increasing the accuracy of the monitoring results; and it is convenient to promptly remind relevant personnel of abnormal situations occurring during the charging process.

[0056] Generate an aging adjustment factor for each charging pile according to several historical charging data in the historical data, including: extracting the recording time in several historical charging data, and the corresponding historical charging time, historical charging power and historical charging temperature; the historical charging data is the charging data of the charging pile for normal charging, including the historical charging time, historical charging power, historical charging temperature, historical environmental data and the corresponding recording time for each charging; the historical charging time is the charging time of charging, and the historical charging power is the power during charging; the historical charging temperature is the temperature of the charging head during charging; the historical environmental data is the corresponding environmental data during charging; the recording time is the time when the charging pile starts charging, or the time when it ends, which is used to distinguish different charging records; sort the historical charging data according to the order of recording time from first to last, and mark the historical charging time as LTgi, the historical charging power as LGgi, and the historical charging temperature as LWgi; i is the number of the historical charging data; g is the number of the charging pile;

[0057] According to the historical charging time LTgi, the historical charging power LGgi and the historical charging temperature LWgi, the aging adjustment factor LHg corresponding to the charging pile numbered g is calculated by the following formula: LHg=∑[LTgi / DT×a×exp(α1×|LGgi-ZGg| / ZGg+α2×|LWgi-ZWg| / ZWg)]; wherein, i=1, 2,…,Ng; Ng is the total number of historical charging data corresponding to the charging pile numbered g; ZGg is the optimum charging power of the charging pile numbered g; the optimum charging power is the charging power with the least impact on the charging pile set according to experience, which can be the rated charging power of the corresponding charging pile; ZWg is the optimum charging temperature of the charging pile numbered g; the optimum charging power is the charging temperature with the least impact on the charging pile set according to experience; DT is the unit charging time; the unit charging time is set according to experience, which can be 1 hour, etc.; α1 and α2 are weight coefficients; a is the adjustment coefficient.

[0058] This embodiment calculates the aging adjustment factor corresponding to the aging effect of each charging pile caused by each use from the beginning of use to the present through the above formula; when the difference between the charging power of each charging and the optimal charging power is greater, or the difference between the charging temperature and the optimal charging temperature is too large, the impact on the charging pile is greater, and the aging effect is greater; the larger the value of the aging adjustment factor and the longer the duration of each charging are, the larger the corresponding value of the aging adjustment factor is; thus, the aging effect of the charging pile caused by each use from the time the charging pile is put into use to the current use is summed up to finally obtain the aging adjustment factor of the corresponding charging pile; this is convenient for the subsequent adjustment of the rated parameters of the charging pile according to the specific usage of the charging pile.

[0059] Generate a charging safety temperature according to a number of historical charging data and an aging adjustment factor, including: extracting historical environmental data, historical charging power and historical charging temperature from a number of historical charging data in the historical data; dividing historical charging data with the same historical charging power into the same power data group; dividing historical charging data in the same power data group into a number of environmental data groups according to historical environmental data; obtaining the historical charging temperature with the largest value in each environmental data group as the upper limit of the safety temperature of the corresponding charging pile in the corresponding environmental data group;

[0060] Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile;

[0061] The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and the specific weight values ​​are set according to experience; and β1+∑(βg)=1, β1>∑(βg); b is the proportional coefficient; set according to experience; the charging safety temperature of each charging pile in each environmental data group in each power data group is calculated in turn.

[0062] The environmental data group is obtained by the following methods, including: obtaining historical data corresponding to all charging piles; extracting historical environmental data from several historical charging data in each historical data; extracting several environmental items from the historical environmental data; integrating each environmental item into an environmental feature vector; performing cluster analysis on the environmental feature vector to obtain several cluster clusters;

[0063] Extract the minimum and maximum values ​​of each environmental item within the cluster, take the minimum value of each environmental item as the lower boundary of the environmental item; take the maximum value of each environmental item as the upper boundary of the environmental item; integrate the lower boundaries of each environmental item into the lower boundary range of the environmental data group corresponding to the cluster; integrate the upper boundaries of each environmental item into the upper boundary range of the environmental data group corresponding to the cluster; calculate the boundary range of the environmental data group corresponding to each cluster in turn; the boundary range includes the upper boundary range and the lower boundary range.

[0064] In this embodiment, the environmental items include ambient temperature, ambient humidity and ambient pressure; the boundary ranges of the three environmental data groups obtained by cluster analysis are ambient temperature [25, 29], ambient humidity [55, 61], ambient pressure [997, 1005]; and ambient temperature [30, 35], ambient humidity [61, 70], ambient pressure [1002, 1007]; and ambient temperature [20, 25], ambient humidity [55, 61], ambient pressure [997, 1002]; the ambient humidity ranges are similar, and may be divided into different environmental data groups due to large differences in ambient temperature or ambient pressure; such as the first group of boundary ranges and the third group of boundary ranges; in this embodiment, the historical environmental data are clustered by cluster analysis to obtain several environmental data groups; the similarity of multiple environmental items corresponding to each historical environmental data in the same environmental data group is high; so that the degree of environmental influence on the historical charging data corresponding to each environmental data group is roughly the same, which is convenient for improving the accuracy of subsequent analysis.

[0065] This embodiment divides the historical charging data of each charging pile into several power data groups according to the charging power, and then divides the environmental data in each power data group into non-pass environmental data groups through cluster analysis; the charging safety temperature of the charging pile to be monitored under a certain power and a certain environment is generated through the upper limit of the safety temperature corresponding to each charging pile in the environmental data group, and the corresponding aging adjustment factor; the larger the upper limit of the safety temperature in the historical data of the charging pile to be monitored, the larger the corresponding charging safety temperature; the larger the upper limit of the safety temperature of other charging piles under the same power and environment, the larger the charging safety temperature of the charging pile to be monitored; the larger the aging adjustment factor of the charging pile to be monitored, the smaller the corresponding charging safety temperature; the charging safety temperature of the charging pile to be monitored under a certain power and environment is comprehensively generated according to the aging condition of the charging pile to be monitored, as well as its own historical data and the historical data of other charging piles under the same power and environment; so that the charging safety temperature is suitable for the usage of the corresponding charging pile.

[0066] The coefficient generation model is obtained through artificial intelligence model training, including: obtaining a number of environmental data and their corresponding environmental impact coefficients through a database; the environmental impact coefficient is set according to the difference between the actual charging temperature and the theoretical charging temperature under the corresponding environmental data, and the theoretical charging temperature is the charging temperature obtained by relevant experts without considering the environmental impact; the more the actual charging temperature is higher than the theoretical charging temperature, the greater the impact coefficient; otherwise, the smaller it is; integrating the environmental data and their corresponding environmental impact coefficients into several groups of training data and test data;

[0067] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; finally, a coefficient generation model is obtained whose input is environmental data and whose output is an environmental impact coefficient; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0068] Generate temperature prediction curve based on environmental impact coefficient, including:

[0069] Obtain the charging power and environmental impact coefficient, and search for the corresponding power data group according to the charging power; obtain the charging temperature change curve GT(t) corresponding to the power data group; the charging temperature change under different powers is different, and the corresponding charging temperature change curves are also different; the charging temperature change curve refers to the change curve of the theoretical charging temperature under the corresponding power; obtain the environmental impact coefficient HXt; t is the time point; calculate the temperature prediction curve through the formula YT(t)=γ1×HXt×GT(t); where γ1 is the proportionality coefficient; all proportionality coefficients in this application are set based on experience.

[0070] This embodiment obtains the predicted value of environmental data corresponding to each time point, and generates the environmental impact coefficient of the corresponding time point according to the environmental data, and adjusts the predicted charging temperature of the corresponding time point in the charging temperature change curve according to the environmental impact coefficient; then, curve fitting is performed through the predicted charging temperature at each time point to obtain a temperature prediction curve; the curve fitting method can use interpolation or other methods; or directly use the predicted charging temperature at each time point to form a discrete predicted charging data group; similar effects can also be achieved.

[0071] Generate risk factors based on temperature prediction curve and charging safety temperature, including:

[0072] Obtain the temperature prediction curve GT(t); and the corresponding charging safety temperature AWjkm;

[0073] The risk coefficient FXT corresponding to each time point is calculated by the formula FXt=γ2×arctan[GT(t)-AWjkm]; where γ2 is the proportionality coefficient, which is set according to experience and is used to limit the risk coefficient between [-1, 1] to facilitate subsequent calculations.

[0074] In this embodiment, the risk coefficient at each time point is generated by the difference between the predicted charging temperature at each time point and the charging safety temperature. The more the predicted charging temperature exceeds the charging safety temperature, the greater the corresponding risk coefficient; the more the predicted charging temperature is lower than the charging safety temperature, the smaller the corresponding risk coefficient;

[0075] Generates alarm signals based on charging safety temperature, charging temperature and risk factor, including:

[0076] Get the charging temperature; determine whether the charging temperature is greater than the corresponding charging safety temperature;

[0077] If yes, an abnormal alarm signal and a stop charging signal are generated; the abnormal alarm signal is an alarm signal that the charging pile has sent an abnormality; the stop charging signal is a signal to stop the charging pile from charging in time;

[0078] If not, mark the time point when the risk coefficient is greater than zero as an abnormal time point; obtain the risk coefficient corresponding to each abnormal time point; when the sum of the risk coefficients of each abnormal time point is greater than the risk coefficient threshold; generate an abnormal warning signal; the abnormal warning signal is a signal that an abnormality may occur in the charging pile; notify relevant personnel that there may be risks in this charging and take preventive measures in advance; the alarm signal includes an abnormal alarm signal and an abnormal warning signal.

[0079] See also Figure 2 Another aspect of the present application provides an intelligent monitoring method for a vehicle charging pile, comprising the following steps:

[0080] Step 1: Obtain historical data of several charging piles in the area to be tested; generate an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generate a charging safety temperature according to the several historical charging data and the aging adjustment factor; the generating of the charging safety temperature according to the several historical charging data and the aging adjustment factor includes:

[0081] Extract historical environmental data, historical charging power and historical charging temperature from several historical charging data in the historical data; divide the historical charging data with the same historical charging power into the same power data group; divide the historical charging data in the same power data group into several environmental data groups according to the historical environmental data; obtain the historical charging temperature with the largest value in each environmental data group as the upper limit of the safe temperature of the corresponding charging pile in the corresponding environmental data group;

[0082] Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile;

[0083] The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and β1+∑(βg)=1, β1>∑(βg); b is a proportional coefficient; set according to experience; calculate the charging safety temperature of each charging pile in each environmental data group in each power data group in turn;

[0084] Step 2: Obtain predicted environmental data and real-time charging power; find the corresponding charging safety temperature according to the environmental data and charging power, and input the environmental data into a coefficient generation model to obtain an environmental impact coefficient; the coefficient generation model is obtained by training an artificial intelligence model;

[0085] Step 3: Generate a temperature prediction curve based on the environmental impact coefficient; generate a risk coefficient based on the temperature prediction curve and the charging safety temperature;

[0086] Step 4: Generate an alarm signal based on the charging safety temperature, the charging temperature and the risk factor; and sound an alarm based on the alarm signal.

[0087] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0088] How this application works:

[0089] In the present application, historical data of several charging piles in the area to be tested are obtained; an aging adjustment factor of each charging pile is generated according to several historical charging data in the historical data; a charging safety temperature is generated according to several historical charging data and the aging adjustment factor; predicted environmental data and real-time charging power are obtained; the corresponding charging safety temperature is searched according to the environmental data and the charging power, and the environmental data is input into the coefficient generation model to obtain the environmental impact coefficient; a temperature prediction curve is generated according to the environmental impact coefficient; a risk coefficient is generated according to the temperature prediction curve and the charging safety temperature; an alarm signal is generated according to the charging safety temperature, the charging temperature and the risk coefficient; and an alarm is sounded according to the alarm signal; a corresponding charging safety temperature is generated according to different charging powers and different charging environments; the current charging temperature is obtained, and an abnormal alarm signal is generated according to the charging temperature and the charging safety temperature, and the charging process of the charging pile under different charging powers is monitored, thereby increasing the accuracy of the monitoring results; and it is convenient to promptly remind relevant personnel of abnormal situations occurring during the charging process.

[0090] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An intelligent monitoring system for car charging piles, include: Data acquisition module, central processing module, early warning module and database; characterized in that, The data acquisition module: acquires the charging power and charging temperature of the charging pile in real time through the data acquisition device connected thereto, and acquires the predicted environmental data through the environmental prediction platform; The central processing module: obtains historical data of several charging piles in the test area through a database connected thereto; generates an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generates a charging safety temperature according to the several historical charging data and the aging adjustment factor; and, Acquire predicted environmental data, real-time charging power and charging temperature; search for corresponding charging safety temperature according to environmental data and charging power, input environmental data into coefficient generation model to obtain environmental impact coefficient; generate temperature prediction curve according to environmental impact coefficient; generate risk coefficient according to temperature prediction curve and charging safety temperature; generate alarm signal according to charging safety temperature, charging temperature and risk coefficient; wherein, the coefficient generation model is obtained by training of artificial intelligence model; The generating of the charging safety temperature according to a number of historical charging data and an aging adjustment factor includes: Extract historical environmental data, historical charging power and historical charging temperature from several historical charging data in the historical data; divide the historical charging data with the same historical charging power into the same power data group; divide the historical charging data in the same power data group into several environmental data groups according to the historical environmental data; obtain the historical charging temperature with the largest value in each environmental data group as the upper limit of the safe temperature of the corresponding charging pile in the corresponding environmental data group; Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile; The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and β1+∑(βg)=1, β1>∑(βg); b is a proportional coefficient; set according to experience; calculate the charging safety temperature of each charging pile in each environmental data group in each power data group in turn; The early warning module is used to obtain an alarm signal and to generate an alarm according to the alarm signal.

2. According to claim 1, an intelligent monitoring system for a vehicle charging pile, It is characterized in that The step of generating the aging adjustment factor of each charging pile according to the historical charging data includes: Extract the recording time from several historical charging data, as well as the corresponding historical charging time, historical charging power and historical charging temperature; sort the historical charging data according to the recording time from the earliest to the latest, and mark the historical charging time as LTgi, the historical charging power as LGgi, and the historical charging temperature as LWgi; i is the number of the historical charging data; g is the number of the charging pile; According to the historical charging time LTgi, the historical charging power LGgi and the historical charging temperature LWgi, the aging adjustment factor LHg corresponding to the charging pile numbered g is calculated by the following formula: LHg=∑[LTgi / DT×a×exp(α1×|LGgi-ZGg| / ZGg+α2×|LWgi-ZWg| / ZWg)]; wherein, i=1, 2,…,Ng; Ng is the total number of historical charging data corresponding to the charging pile numbered g; ZGg is the optimal charging power of the charging pile numbered g; ZWg is the optimal charging temperature of the charging pile numbered g; DT is the unit charging time; α1 and α2 are weight coefficients; a is the adjustment coefficient.

3. According to claim 1, an intelligent monitoring system for a vehicle charging pile, It is characterized in that The environmental data set is obtained by: Obtain historical data corresponding to all charging piles; extract historical environmental data from several historical charging data in each historical data; extract several environmental items from the historical environmental data; integrate each environmental item into an environmental feature vector; perform cluster analysis on the environmental feature vector to obtain several cluster clusters; Extract the minimum and maximum values ​​of each environmental item within the cluster, take the minimum value of each environmental item as the lower boundary of the environmental item; take the maximum value of each environmental item as the upper boundary of the environmental item; integrate the lower boundaries of each environmental item into the lower boundary range of the environmental data group corresponding to the cluster; integrate the upper boundaries of each environmental item into the upper boundary range of the environmental data group corresponding to the cluster; calculate the boundary range of the environmental data group corresponding to each cluster in turn; the boundary range includes the upper boundary range and the lower boundary range.

4. According to claim 1, an intelligent monitoring system for a vehicle charging pile, It is characterized in that The coefficient generation model is obtained through artificial intelligence model training, including: Acquire a number of environmental data and their corresponding environmental impact coefficients through a database; integrate the environmental data and their corresponding environmental impact coefficients into a number of sets of training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; finally, a coefficient generation model is obtained whose input is environmental data and whose output is an environmental impact coefficient; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

5. The intelligent monitoring system for a vehicle charging pile according to claim 1, It is characterized in that The step of generating a temperature prediction curve according to the environmental impact coefficient includes: Obtain the charging power and environmental impact coefficient; search for the corresponding power data group according to the charging power; obtain the charging temperature change curve GT(t) corresponding to the power data group; obtain the environmental impact coefficient HXt; t is the time point; calculate the temperature prediction curve through the formula YT(t)=γ1×HXt×GT(t); where γ1 is the proportionality coefficient.

6. The intelligent monitoring system for a vehicle charging pile according to claim 5, It is characterized in that The generating of the risk coefficient according to the temperature prediction curve and the charging safety temperature includes: Obtain the temperature prediction curve GT(t); and the corresponding charging safety temperature AWjkm; The risk coefficient FXT corresponding to each time point is calculated by the formula FXt=γ2×arctan[GT(t)-AWjkm]; where γ2 is the proportionality coefficient.

7. The intelligent monitoring system for a vehicle charging pile according to claim 6, It is characterized in that The generating of an alarm signal according to the charging safety temperature, the charging temperature and the risk factor comprises: Get the charging temperature; determine whether the charging temperature is greater than the corresponding charging safety temperature; If yes, an abnormal alarm signal and a charging stop signal are generated; If not, mark the time point where the risk coefficient is greater than zero as an abnormal time point; obtain the risk coefficient corresponding to each abnormal time point; when the sum of the risk coefficients of each abnormal time point is greater than the risk coefficient threshold; generate an abnormal warning signal; the alarm signal includes an abnormal alarm signal and an abnormal warning signal.

8. An intelligent monitoring method for a vehicle charging pile, applied to the operation of an intelligent monitoring system for a vehicle charging pile according to any one of claims 1 to 7, It is characterized in that The following steps are involved: Step 1: Obtain historical data of several charging piles in the area to be tested; generate an aging adjustment factor for each charging pile according to several historical charging data in the historical data; generate a charging safety temperature according to the several historical charging data and the aging adjustment factor; the generating of the charging safety temperature according to the several historical charging data and the aging adjustment factor includes: Extract historical environmental data, historical charging power and historical charging temperature from several historical charging data in the historical data; divide the historical charging data with the same historical charging power into the same power data group; divide the historical charging data in the same power data group into several environmental data groups according to the historical environmental data; obtain the historical charging temperature with the largest value in each environmental data group as the upper limit of the safe temperature of the corresponding charging pile in the corresponding environmental data group; Get the aging adjustment factor LHg; mark the upper limit of the safe temperature as AWSjkg; j is the number of the power data group, k is the number of the environmental data group; g is the number of the charging pile; The charging safety temperature AWjkm of the charging pile numbered m in the environmental data group numbered k in the power data group numbered j is calculated by AWjkm=b×exp(-LHm)×[β1×AWSjkm+∑(βg×AWSjkg)]; wherein g is a positive integer; g∈[1,M]; and g≠m; M is the total number of charging piles in the area to be tested; β1 and βg are weight coefficients, and β1+∑(βg)=1, β1>∑(βg); b is a proportional coefficient; set according to experience; calculate the charging safety temperature of each charging pile in each environmental data group in each power data group in turn; Step 2: Obtain predicted environmental data and real-time charging power; find the corresponding charging safety temperature according to the environmental data and charging power, and input the environmental data into a coefficient generation model to obtain an environmental impact coefficient; the coefficient generation model is obtained by training an artificial intelligence model; Step 3: Generate a temperature prediction curve based on the environmental impact coefficient; generate a risk coefficient based on the temperature prediction curve and the charging safety temperature; Step 4: Generate an alarm signal based on the charging safety temperature, the charging temperature and the risk factor; and sound an alarm based on the alarm signal.

Images