Charging pile vehicle network interaction control system based on artificial intelligence

Abstract

The invention relates to the field of charging piles, in particular to a charging pile vehicle network interaction control system based on artificial intelligence, and is used for solving the problems of low charging efficiency, resource waste and poor user experience caused by lack of intelligence and individuation in charging parameter adjustment of a traditional charging pile. The system intelligently adjusts the charging parameters of the charging pile by analyzing the historical charging process of the electric vehicle and the charging historical data of the same type of electric vehicle, improves the charging efficiency, reduces unnecessary energy consumption, and avoids energy waste, so that efficient and accurate charging service is realized, meanwhile, the safety of the charging process can be ensured, and the charging efficiency is improved. The service life of the battery of the electric vehicle is prolonged, more convenient and economical charging experience is provided for a user, the satisfaction degree and loyalty of the user are enhanced, reasonable configuration of electric power resources is achieved, and sustainable development of green electric travel is promoted.

Description

Technical Field

[0001] The present invention relates to the field of charging piles, and in particular to an artificial intelligence-based charging pile vehicle-network interactive control system. Background Art

[0002] With the advancement of urbanization and the improvement of environmental protection awareness, electric vehicles have become an important way to solve urban traffic environment and energy consumption problems due to their zero emissions and quiet and vibration-free characteristics. However, the popularization of electric vehicles faces challenges in charging efficiency, charging facility layout and charging services. Improving the utilization rate and charging efficiency of charging piles is crucial to promoting the development of the electric vehicle industry.

[0003] Existing charging piles mainly use fixed parameter control solutions and lack intelligent and personalized services. This means that the charging piles cannot dynamically adjust parameters according to the actual needs of users and the condition of electric vehicles, resulting in long charging time, low charging efficiency, and even excessive battery loss.

[0004] How to improve the lack of intelligence and personalization in the adjustment of charging parameters of traditional charging piles, resulting in low charging efficiency, waste of resources and poor user experience is the key to the present invention. Therefore, there is an urgent need for an artificial intelligence-based charging pile vehicle-network interactive control system to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned technical problems, the purpose of the present invention is to provide a charging pile vehicle-grid interactive control system based on artificial intelligence, which solves the problem that traditional charging piles lack intelligence and personalization in adjusting charging parameters, resulting in low charging efficiency, waste of resources and poor user experience.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An artificial intelligence-based charging pile vehicle network interactive control system, comprising:

[0008] The self-collection module is used to obtain the control deviation information of the interactive control target and send the control deviation information to the information analysis module; wherein the control deviation information includes the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo;

[0009] A similar acquisition module, used to obtain reference deviation information of similar reference targets and send the reference deviation information to the information analysis module; wherein the reference deviation information includes a reference pressure difference value YCi, a reference flow difference value LCi and a reference flow difference value GCi;

[0010] An information analysis module, used to obtain a control analysis coefficient KFo according to the control deviation information, obtain a reference analysis coefficient CFi according to the reference deviation information, and send the control analysis coefficient KFo and the reference analysis coefficient CFi to the information identification module; and also used to obtain charging adjustment information according to the control charging information and the reference charging information, and send the charging adjustment information to the interactive control module; wherein the charging adjustment information includes a voltage adjustment value YT, a current adjustment value LT, and a power adjustment value WT;

[0011] An information discrimination module, used for classifying the control analysis process o into a control abnormal process and a control normal process according to the control analysis coefficient KFo, and obtaining the control charging information of the control normal process, classifying the reference analysis process i into a reference abnormal process and a reference normal process according to the reference analysis coefficient CFi, and obtaining the reference charging information of the reference normal process, and sending the control charging information and the reference charging information to the information analysis module; wherein the control charging information includes a control voltage value KU, a control current value KI and a control power value KW; and the reference charging information includes a reference voltage value CU, a reference current value CI and a reference power value CW;

[0012] The interactive control module is used to adjust the charging pile according to the charging adjustment information and then charge the electric vehicle.

[0013] As a further solution of the present invention: the specific process of the self-collection module acquiring the control deviation information is as follows:

[0014] Obtain the electric vehicle connected to the charging pile and mark it as an interactive control target;

[0015] Obtain all charging processes within the preset time of the interactive control target, and mark them as control analysis process o in sequence, where o=1, ..., n, n is a positive integer, o is the number of any control analysis process, and n is the total number of control analysis processes. Obtain the average charging voltage of the control analysis process o, and mark it as the control charging pressure value CYo. Obtain the difference between the control charging pressure value CYo and the preset standard voltage, and mark it as the control pressure difference value YCo.

[0016] Obtain the average charging current of the control analysis process o, and mark it as the control charging current value CLo, obtain the difference between the control charging current value CLo and the preset standard current, and mark it as the control current difference LCo;

[0017] Obtain the average charging power of the control analysis process o, and mark it as the control charging power value CGo, obtain the difference between the control charging power value CGo and the preset standard power, and mark it as the control flow difference GCo;

[0018] The control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo are sent to the information analysis module.

[0019] As a further solution of the present invention: the specific process of the same type acquisition module obtaining the reference deviation information is as follows:

[0020] Obtain all electric vehicles of the same model as the interactive control target that have completed charging within a preset time, and mark them as reference targets of the same type;

[0021] Obtain all charging processes of the same reference target within a preset time, and mark them as reference analysis process i in sequence, where i=1, ..., v, v is a positive integer, i is the number of any reference analysis process, and v is the total number of reference analysis processes; obtain the average charging voltage of the reference analysis process i, and mark it as a reference charging voltage value CYi; obtain the difference between the reference charging voltage value CYi and the preset standard voltage, and mark it as a reference voltage difference value YCi;

[0022] Obtain an average charging current of the reference analysis process i and mark it as a reference charging current value CLi, obtain a difference between the reference charging current value CLi and a preset standard current and mark it as a reference current difference LCi;

[0023] Obtain the average charging power of the reference analysis process i, and mark it as the reference charging power value CG i, obtain the difference between the reference charging power value CG i and the preset standard power, and mark it as the reference flow difference GCi;

[0024] The reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi are sent to the information analysis module.

[0025] As a further solution of the present invention: the specific process of the information analysis module obtaining the control analysis coefficient KFo is as follows:

[0026] The control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo are quantified, the values ​​of the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo are extracted, and they are substituted into the formula for calculation. According to the formula The control analysis coefficient KFo is obtained; wherein, e is a mathematical constant, k1, k2 and k3 are respectively the preset proportional coefficients corresponding to the set control pressure difference value YCo, control flow difference value LCo and control flow difference value GCo, k1, k2 and k3 satisfy k1+k2+k3=1, 0<k2<k1<k3<1, and k1=0.35, k2=0.24, k3=0.41.

[0027] As a further solution of the present invention: the specific process of the information analysis module obtaining the reference analysis coefficient CFi is as follows:

[0028] The reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi are quantified, the values ​​of the reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi are extracted, and they are substituted into the formula for calculation. According to the formula The reference analysis coefficient CFi is obtained; wherein, e is a mathematical constant, c1, c2 and c3 are preset proportional coefficients corresponding to the set reference pressure difference value YCi, reference flow difference value LCi and reference flow difference value GCi respectively, c1, c2 and c3 satisfy c1+c2+c3=1, 0<c2<c1<c3<1, and c1=0.33, c2=0.28, c3=0.39.

[0029] As a further solution of the present invention: the specific process of the information identification module obtaining the control charging information is as follows:

[0030] The control analysis coefficient KFo is compared with the preset control analysis threshold KFy. The comparison results are as follows:

[0031] If the control analysis coefficient KFo ≥ the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a control abnormality process;

[0032] If the control analysis coefficient KFo is less than the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a normal control process, and the average value of the control charging voltage values ​​CYo of all normal control processes is obtained and marked as the control voltage value KU, the average value of the control charging current values ​​CLo of all normal control processes is obtained and marked as the control current value KI, the average value of the control charging work values ​​CGo of all normal control processes is obtained and marked as the control power value KW, and the control voltage value KU, the control current value KI and the control power value KW are sent to the information analysis module.

[0033] As a further solution of the present invention: the specific process of the information identification module obtaining the reference charging information is as follows:

[0034] The reference analysis coefficient CFi is compared with the preset reference analysis threshold CFy, and the comparison results are as follows:

[0035] If the reference analysis coefficient CF i ≥ the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference abnormal process;

[0036] If the reference analysis coefficient CF i is less than the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference normal process, and the average value of the reference charging voltage values ​​CYi of all reference normal processes is obtained and marked as the reference voltage value CU, the average value of the reference charging current values ​​CLi of all reference normal processes is obtained and marked as the reference current value CI, the average value of the reference charging power values ​​CGi of all reference normal processes is obtained and marked as the reference power value CW, and the reference voltage value CU, the reference current value CI and the reference power value CW are sent to the information analysis module.

[0037] As a further solution of the present invention: the specific process of the information analysis module obtaining the charging adjustment information is as follows:

[0038] The control voltage value KU and the reference voltage value CU are quantized, the values ​​of the control voltage value KU and the reference voltage value CU are extracted, and the values ​​are substituted into the formula to calculate, and the voltage adjustment value YT is obtained according to the formula YT=s1×KU+s2×CU; wherein s1 and s2 are the preset proportional coefficients corresponding to the set control voltage value KU and the reference voltage value CU, respectively, and s1 and s2 satisfy s1+s2=1, 1>s1>s2>0, and s1=0.69 and s2=0.31;

[0039] The control current value KI and the reference current value CI are quantized, the values ​​of the control current value KI and the reference current value CI are extracted, and the values ​​are substituted into the formula to calculate, and the current adjustment value LT is obtained according to the formula LT = d1 × KI + d2 × CI; wherein d1 and d2 are the preset proportional coefficients corresponding to the set control current value KI and the reference current value CI, respectively, and d1 and d2 satisfy d1 + d2 = 1, 1 > d1 > d2 > 0, and d1 = 0.55 and d2 = 0.45;

[0040] The control power value KW and the reference power value CW are quantified, the values ​​of the control power value KW and the reference power value CW are extracted, and the values ​​are substituted into the formula to calculate, and the power adjustment value WT is obtained according to the formula WT=z1×KW+z2×CW; wherein w1 and w2 are the preset proportional coefficients corresponding to the set control power value KW and the reference power value CW, respectively, and w1 and w2 satisfy w1+w2=1, 1>w1>w2>0, and w1=0.73 and w2=0.27;

[0041] The voltage adjustment value YT, the current adjustment value LT and the power adjustment value WT are sent to the interactive control module.

[0042] As a further solution of the present invention: the specific process of the interactive control module adjusting the charging pile is as follows:

[0043] The voltage value when the charging pile charges the electric vehicle is adjusted according to the voltage adjustment value YT, the current value when the charging pile charges the electric vehicle is adjusted according to the current adjustment value LT, and the power value when the charging pile charges the electric vehicle is adjusted according to the power adjustment value WT.

[0044] Beneficial effects of the present invention:

[0045] The present invention discloses an artificial intelligence-based charging pile vehicle-grid interactive control system, which first collects data on an electric vehicle that performs vehicle-grid interactive control on a charging pile to obtain control deviation information, then collects data on electric vehicles of the same model as the electric vehicle that performs vehicle-grid interactive control to obtain reference deviation information, and then uses artificial intelligence to perform data analysis to obtain a control analysis coefficient and a reference analysis coefficient, wherein the control analysis coefficient can comprehensively measure the degree of abnormality of the control analysis process, and a larger control analysis coefficient indicates a higher degree of abnormality, and the reference analysis coefficient can comprehensively measure the degree of abnormality of the reference analysis process, and a larger reference analysis coefficient indicates a higher degree of abnormality, and finally selects a normal charging process as an analysis element, then obtains control charging information and reference charging information, and finally obtains charging adjustment information according to the control charging information and the reference charging information, and then adjusts the charging pile;

[0046] The present invention provides an artificial intelligence-based charging pile vehicle-grid interactive control system, which analyzes the historical charging process of electric vehicles and the charging history data of electric vehicles of the same type, intelligently adjusts the charging parameters of the charging pile, improves charging efficiency, reduces unnecessary energy consumption, and avoids energy waste, thereby achieving efficient and accurate charging services. At the same time, it can also ensure the safety of the charging process, extend the service life of electric vehicle batteries, and thus provide users with a more convenient and economical charging experience, enhance user satisfaction and loyalty, achieve reasonable allocation of power resources, and promote the sustainable development of green electric travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] Figure 1 It is a principle block diagram of a charging pile vehicle network interactive control system based on artificial intelligence in the present invention;

[0049] Figure 2 It is a flow chart of a working method of a charging pile vehicle network interactive control system based on artificial intelligence in the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0051] Embodiment 1:

[0052] See also Figure 1 As shown, this embodiment is an artificial intelligence-based charging pile vehicle network interactive control system, including the following modules: self-collection module, similar collection module, information analysis module, information identification module and interactive control module;

[0053] The self-collection module is used to obtain the control deviation information of the interactive control target and send the control deviation information to the information analysis module; wherein the control deviation information includes the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo;

[0054] The same type acquisition module is used to obtain reference deviation information of the same type of reference target and send the reference deviation information to the information analysis module; wherein the reference deviation information includes a reference pressure difference value YCi, a reference flow difference value LCi and a reference flow difference value GCi;

[0055] The information analysis module is used to obtain the control analysis coefficient KFo according to the control deviation information, obtain the reference analysis coefficient CFi according to the reference deviation information, and send the control analysis coefficient KFo and the reference analysis coefficient CFi to the information identification module; it is also used to obtain the charging adjustment information according to the control charging information and the reference charging information, and send the charging adjustment information to the interactive control module; wherein the charging adjustment information includes the voltage adjustment value YT, the current adjustment value LT and the power adjustment value WT;

[0056] The information discrimination module is used to classify the control analysis process o into a control abnormal process and a control normal process according to the control analysis coefficient KFo, and obtain the control charging information of the control normal process, classify the reference analysis process i into a reference abnormal process and a reference normal process according to the reference analysis coefficient CFi, and obtain the reference charging information of the reference normal process, and send the control charging information and the reference charging information to the information analysis module; wherein the control charging information includes a control voltage value KU, a control current value KI and a control power value KW; the reference charging information includes a reference voltage value CU, a reference current value CI and a reference power value CW;

[0057] The interactive control module is used to adjust the charging pile according to the charging adjustment information and then charge the electric vehicle.

[0058] Example 2

[0059] See also Figure 2 As shown, this embodiment is a working method of a charging pile vehicle network interactive control system based on artificial intelligence, comprising the following steps:

[0060] Step S1: The self-collection module obtains the control deviation information of the interactive control target, wherein the control deviation information includes the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo, and sends the control deviation information to the information analysis module;

[0061] Step S2: The same type acquisition module obtains reference deviation information of the same type reference target, wherein the reference deviation information includes a reference pressure difference value YCi, a reference flow difference value LCi and a reference flow difference value GCi, and sends the reference deviation information to the information analysis module;

[0062] Step S3: the information analysis module obtains the control analysis coefficient KFo according to the control deviation information, obtains the reference analysis coefficient CFi according to the reference deviation information, and sends the control analysis coefficient KFo and the reference analysis coefficient CFi to the information discrimination module;

[0063] Step S4: the information discrimination module classifies the control analysis process o into a control abnormal process and a control normal process according to the control analysis coefficient KFo, and obtains the control charging information of the control normal process, wherein the control charging information includes the control voltage value KU, the control current value KI and the control power value KW, and sends the control charging information to the information analysis module;

[0064] Step S5: the information discrimination module classifies the reference analysis process i into a reference abnormal process and a reference normal process according to the reference analysis coefficient CF i, and obtains reference charging information of the reference normal process, wherein the reference charging information includes a reference voltage value CU, a reference current value CI, and a reference power value CW, and sends the reference charging information to the information analysis module;

[0065] Step S6: the information analysis module obtains charging adjustment information according to the control charging information and the reference charging information, wherein the charging adjustment information includes a voltage adjustment value YT, a current adjustment value LT and a power adjustment value WT, and sends the charging adjustment information to the interactive control module;

[0066] Step S7: the interactive control module adjusts the charging pile according to the charging adjustment information and then charges the electric vehicle.

[0067] Embodiment 3:

[0068] Based on any of the above embodiments, embodiment 3 of the present invention is a self-acquisition module, and the function of the self-acquisition module is to obtain control deviation information, wherein the control deviation information includes a control pressure difference value YCo, a control flow difference value LCo, and a control flow difference value GCo. The specific process is as follows:

[0069] The self-collection module obtains the electric vehicles connected to the charging pile and marks them as interactive control targets;

[0070] The self-collection module obtains all charging processes within the preset time of the interactive control target, and marks them as control analysis process o in sequence, where o=1, ..., n, n is a positive integer, o is the number of any control analysis process, and n is the total number of control analysis processes. The average charging voltage of the control analysis process o is obtained and marked as the control charging pressure value CYo. The difference between the control charging pressure value CYo and the preset standard voltage is obtained and marked as the control pressure difference value YCo.

[0071] The self-collection module obtains the average charging current of the control analysis process o, and marks it as the control charging current value CLo, obtains the difference between the control charging current value CLo and the preset standard current, and marks it as the control current difference LCo;

[0072] The self-collection module obtains the average charging power of the control analysis process o, and marks it as the control charging power value CGo, obtains the difference between the control charging power value CGo and the preset standard power, and marks it as the control flow difference GCo;

[0073] The self-collection module sends the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo to the information analysis module.

[0074] Embodiment 4:

[0075] Based on any of the above embodiments, embodiment 4 of the present invention is a similar acquisition module, and the function of the similar acquisition module is to obtain reference deviation information, wherein the reference deviation information includes a reference pressure difference value YCi, a reference flow difference value LCi, and a reference flow difference value GC i. The specific process is as follows:

[0076] The same type acquisition module obtains all electric vehicles of the same model as the interactive control target that have completed charging within a preset time, and marks them as similar reference targets;

[0077] The same type acquisition module obtains all charging processes of the same type of reference target within the preset time, and marks them as reference analysis process i in sequence, i=1, ..., v, v is a positive integer, i is the number of any reference analysis process, v is the total number of reference analysis processes, obtains the average charging voltage of the reference analysis process i, and marks it as the reference charging voltage value CYi, obtains the difference between the reference charging voltage value CYi and the preset standard voltage, and marks it as the reference voltage difference value YCi;

[0078] The same type of acquisition module obtains the average charging current of the reference analysis process i, and marks it as the reference charging current value CLi, obtains the difference between the reference charging current value CLi and the preset standard current, and marks it as the reference current difference LCi;

[0079] The same type acquisition module obtains the average charging power of the reference analysis process i, and marks it as the reference charging power value CGi, obtains the difference between the reference charging power value CGi and the preset standard power, and marks it as the reference flow difference GCi;

[0080] The same type of acquisition module sends the reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi to the information analysis module.

[0081] Embodiment 5:

[0082] Based on any of the above embodiments, Embodiment 5 of the present invention is an information analysis module, which has two functions:

[0083] One of them is to obtain the control analysis coefficient KFo and the reference analysis coefficient CFi. The specific process is as follows:

[0084] The information analysis module quantifies the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo, extracts the values ​​of the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo, and substitutes them into the formula for calculation. The control analysis coefficient KFo is obtained; wherein e is a mathematical constant, k1, k2 and k3 are preset proportional coefficients corresponding to the set control pressure difference value YCo, control flow difference value LCo and control flow difference value GCo respectively, k1, k2 and k3 satisfy k1+k2+k3=1, 0<k2<k1<k3<1, k1=0.35, k2=0.24, k3=0.41;

[0085] The information analysis module quantifies the reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi, extracts the values ​​of the reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi, and substitutes them into the formula for calculation. Obtain reference analysis coefficient CF i; wherein e is a mathematical constant, c1, c2 and c3 are preset proportional coefficients corresponding to the set reference pressure difference value YCi, reference flow difference value LC i and reference flow difference value GCi, respectively, c1, c2 and c3 satisfy c1+c2+c3=1, 0<c2<c1<c3<1, and c1=0.33, c2=0.28, c3=0.39;

[0086] The information analysis module sends the control analysis coefficient KFo and the reference analysis coefficient CFi to the information discrimination module;

[0087] The second function is to obtain charging regulation information, where the charging regulation information includes a voltage regulation value YT, a current regulation value LT, and a power regulation value WT. The specific process is as follows:

[0088] The information analysis module quantizes the control voltage value KU and the reference voltage value CU, extracts the values ​​of the control voltage value KU and the reference voltage value CU, and substitutes them into the formula to calculate, and obtains the voltage adjustment value YT according to the formula YT=s1×KU+s2×CU; wherein s1 and s2 are the preset proportional coefficients corresponding to the set control voltage value KU and the reference voltage value CU, respectively, and s1 and s2 satisfy s1+s2=1, 1>s1>s2>0, and s1=0.69 and s2=0.31;

[0089] The information analysis module quantifies the control current value KI and the reference current value CI, extracts the numerical values ​​of the control current value KI and the reference current value CI, and substitutes them into the formula for calculation, and obtains the current adjustment value LT according to the formula LT=d1×KI+d2×CI; wherein d1 and d2 are respectively the preset proportional coefficients corresponding to the set control current value KI and the reference current value CI, d1 and d2 satisfy d1+d2=1, 1>d1>d2>0, and d1=0.55 and d2=0.45;

[0090] The information analysis module quantifies the control power value KW and the reference power value CW, extracts the values ​​of the control power value KW and the reference power value CW, and substitutes them into the formula for calculation, and obtains the power adjustment value WT according to the formula WT=z1×KW+z2×CW; wherein w1 and w2 are respectively the preset proportional coefficients corresponding to the set control power value KW and the reference power value CW, and w1 and w2 satisfy w1+w2=1, 1>w1>w2>0, and w1=0.73 and w2=0.27;

[0091] The information analysis module sends the voltage adjustment value YT, the current adjustment value LT and the power adjustment value WT to the interactive control module.

[0092] Embodiment 6:

[0093] Based on any of the above embodiments, Embodiment 6 of the present invention is an information identification module. The function of the information identification module is to obtain control charging information and reference charging information, wherein the control charging information includes a control voltage value KU, a control current value KI and a control power value KW, and the reference charging information includes a reference voltage value CU, a reference current value CI and a reference power value CW. The specific process is as follows:

[0094] The information discrimination module compares the control analysis coefficient KFo with the preset control analysis threshold KFy. The comparison results are as follows:

[0095] If the control analysis coefficient KFo ≥ the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a control abnormality process;

[0096] If the control analysis coefficient KFo is less than the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a normal control process, and the average value of the control charging pressure values ​​CYo of all normal control processes is obtained and marked as a control voltage value KU, the average value of the control charging current values ​​CLo of all normal control processes is obtained and marked as a control current value KI, the average value of the control charging work values ​​CGo of all normal control processes is obtained and marked as a control power value KW, and the control voltage value KU, the control current value KI and the control power value KW are sent to the information analysis module;

[0097] The information discrimination module compares the reference analysis coefficient CFi with the preset reference analysis threshold CFy, and the comparison results are as follows:

[0098] If the reference analysis coefficient CF i ≥ the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference abnormal process;

[0099] If the reference analysis coefficient CFi is less than the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference normal process, and the average value of the reference charging voltage values ​​CYi of all reference normal processes is obtained and marked as the reference voltage value CU, the average value of the reference charging current values ​​CLi of all reference normal processes is obtained and marked as the reference current value CI, the average value of the reference charging power values ​​CGi of all reference normal processes is obtained and marked as the reference power value CW, and the reference voltage value CU, the reference current value CI and the reference power value CW are sent to the information analysis module.

[0100] Embodiment 7:

[0101] Based on any of the above embodiments, Embodiment 7 of the present invention is an interactive control module. The function of the interactive control module is to adjust the charging pile according to the charging adjustment information. The specific process is as follows:

[0102] The interactive control module adjusts the voltage value of the charging pile when charging the electric vehicle according to the voltage adjustment value YT, adjusts the current value of the charging pile when charging the electric vehicle according to the current adjustment value LT, and adjusts the power value of the charging pile when charging the electric vehicle according to the power adjustment value WT.

[0103] Based on the above embodiments 1-7, the working principle of the present invention is as follows:

[0104] The present invention provides an artificial intelligence-based charging pile vehicle network interactive control system, which obtains control deviation information of an interactive control target through its own acquisition module, wherein the control deviation information includes a control pressure difference value, a control flow difference value, and a control flow difference value, obtains reference deviation information of a similar reference target through a similar acquisition module, wherein the reference deviation information includes a reference pressure difference value, a reference flow difference value, and a reference flow difference value, obtains a control analysis coefficient according to the control deviation information through an information analysis module, obtains a reference analysis coefficient according to the reference deviation information, classifies a control analysis process into an abnormal control process and a normal control process according to the control analysis coefficient through an information discrimination module, and obtains a control The control charging information of the normal process, wherein the control charging information includes a control voltage value, a control current value, and a control power value, the reference analysis process is classified into a reference abnormal process and a reference normal process according to a reference analysis coefficient by an information discrimination module, and reference charging information of the reference normal process is obtained, wherein the reference charging information includes a reference voltage value, a reference current value, and a reference power value, the charging adjustment information is obtained according to the control charging information and the reference charging information by an information analysis module, wherein the charging adjustment information includes a voltage adjustment value, a current adjustment value, and a power adjustment value, and the charging pile is adjusted according to the charging adjustment information by an interactive control module to control the electric vehicle Charging; the system first collects data from electric vehicles that are interactively controlled by the charging piles to obtain control deviation information, and then collects data from electric vehicles of the same model as the electric vehicles that are interactively controlled by the charging piles to obtain reference deviation information, and then uses artificial intelligence to perform data analysis to obtain control analysis coefficients and reference analysis coefficients. The control analysis coefficient can comprehensively measure the degree of abnormality in the control analysis process, and the larger the control analysis coefficient, the higher the degree of abnormality. The reference analysis coefficient can comprehensively measure the degree of abnormality in the reference analysis process, and the larger the reference analysis coefficient, the higher the degree of abnormality. Finally, the normal charging process is selected as the analysis element, and then the control charging information and reference charging information are obtained. Finally, the charging adjustment information is obtained according to the control charging information and the reference charging information, and then the charging pile is adjusted; the system analyzes the historical charging process of electric vehicles and the charging history data of electric vehicles of the same model, intelligently adjusts the charging parameters of the charging pile, improves charging efficiency, reduces unnecessary energy consumption, and avoids energy waste, thereby achieving efficient and accurate charging services, while ensuring the safety of the charging process and extending the service life of electric vehicle batteries, thereby providing users with a more convenient and economical charging experience, enhancing user satisfaction and loyalty, achieving reasonable allocation of power resources, and promoting the sustainable development of green electric travel.

[0105] It should be further explained that the above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by technical personnel in this field according to actual conditions.

[0106] 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.

[0107] The above contents are merely examples and explanations of the present invention. Those skilled in the art 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 invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. A charging pile vehicle network interactive control system based on artificial intelligence, characterized in that: include: The self-collection module is used to obtain the control deviation information of the interactive control target and send the control deviation information to the information analysis module; wherein the control deviation information includes the control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo; A similar acquisition module, used to obtain reference deviation information of similar reference targets and send the reference deviation information to the information analysis module; wherein the reference deviation information includes a reference pressure difference value YCi, a reference flow difference value LCi and a reference flow difference value GCi; An information analysis module, used to obtain a control analysis coefficient KFo according to the control deviation information, obtain a reference analysis coefficient CFi according to the reference deviation information, and send the control analysis coefficient KFo and the reference analysis coefficient CFi to the information identification module; and also used to obtain charging adjustment information according to the control charging information and the reference charging information, and send the charging adjustment information to the interactive control module; wherein the charging adjustment information includes a voltage adjustment value YT, a current adjustment value LT, and a power adjustment value WT; An information discrimination module, used for classifying the control analysis process o into a control abnormal process and a control normal process according to the control analysis coefficient KFo, and obtaining the control charging information of the control normal process, classifying the reference analysis process i into a reference abnormal process and a reference normal process according to the reference analysis coefficient CFi, and obtaining the reference charging information of the reference normal process, and sending the control charging information and the reference charging information to the information analysis module; wherein the control charging information includes a control voltage value KU, a control current value KI and a control power value KW; and the reference charging information includes a reference voltage value CU, a reference current value CI and a reference power value CW; The interactive control module is used to adjust the charging pile according to the charging adjustment information and then charge the electric vehicle.

2. According to the artificial intelligence-based charging pile vehicle network interactive control system of claim 1, it is characterized in that: The specific process of the self-collection module obtaining the control deviation information is as follows: Obtain the electric vehicle connected to the charging pile and mark it as an interactive control target; Obtain all charging processes within the preset time of the interactive control target, and mark them as control analysis process o in sequence, where o=1, ..., n, n is a positive integer, o is the number of any control analysis process, and n is the total number of control analysis processes. Obtain the average charging voltage of the control analysis process o, and mark it as the control charging pressure value CYo. Obtain the difference between the control charging pressure value CYo and the preset standard voltage, and mark it as the control pressure difference value YCo. Obtain the average charging current of the control analysis process o, and mark it as the control charging current value CLo, obtain the difference between the control charging current value CLo and the preset standard current, and mark it as the control current difference LCo; Obtain the average charging power of the control analysis process o, and mark it as the control charging power value CGo, obtain the difference between the control charging power value CGo and the preset standard power, and mark it as the control flow difference GCo; The control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo are sent to the information analysis module.

3. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the same type of acquisition module obtaining reference deviation information is as follows: Obtain all electric vehicles of the same model as the interactive control target that have completed charging within a preset time, and mark them as reference targets of the same type; Obtain all charging processes of the same reference target within a preset time, and mark them as reference analysis process i in sequence, where i=1, ..., v, v is a positive integer, i is the number of any reference analysis process, and v is the total number of reference analysis processes; obtain the average charging voltage of the reference analysis process i, and mark it as a reference charging voltage value CYi; obtain the difference between the reference charging voltage value CYi and the preset standard voltage, and mark it as a reference voltage difference value YCi; Obtain an average charging current of the reference analysis process i and mark it as a reference charging current value CLi, obtain a difference between the reference charging current value CLi and a preset standard current and mark it as a reference current difference LCi; Obtain the average charging power of the reference analysis process i, and mark it as the reference charging power value CGi, obtain the difference between the reference charging power value CGi and the preset standard power, and mark it as the reference flow difference GCi; The reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi are sent to the information analysis module.

4. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the information analysis module obtaining the control analysis coefficient KFo is as follows: The control pressure difference value YCo, the control flow difference value LCo and the control flow difference value GCo are quantified according to the formula The control analysis coefficient KFo is obtained; wherein e is a mathematical constant, and k1, k2 and k3 are preset proportional coefficients corresponding to the set control pressure difference value YCo, control flow difference value LCo and control flow difference value GCo respectively.

5. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the information analysis module obtaining the reference analysis coefficient CFi is as follows: The reference pressure difference value YCi, the reference flow difference value LCi and the reference flow difference value GCi are quantified according to the formula The reference analysis coefficient CFi is obtained; wherein, e is a mathematical constant, and c1, c2 and c3 are preset proportional coefficients corresponding to the set reference pressure difference value YCi, reference flow difference value LCi and reference flow difference value GCi respectively.

6. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the information identification module obtaining the control charging information is as follows: The control analysis coefficient KFo is compared with the preset control analysis threshold KFy. The comparison results are as follows: If the control analysis coefficient KFo ≥ the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a control abnormality process; If the control analysis coefficient KFo is less than the control analysis threshold KFy, the control analysis process o corresponding to the control analysis coefficient KFo is marked as a normal control process, and the average value of the control charging voltage values ​​CYo of all normal control processes is obtained and marked as the control voltage value KU, the average value of the control charging current values ​​CLo of all normal control processes is obtained and marked as the control current value KI, the average value of the control charging work values ​​CGo of all normal control processes is obtained and marked as the control power value KW, and the control voltage value KU, the control current value KI and the control power value KW are sent to the information analysis module.

7. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the information identification module obtaining the reference charging information is as follows: The reference analysis coefficient CFi is compared with the preset reference analysis threshold CFy, and the comparison results are as follows: If the reference analysis coefficient CFi ≥ the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference abnormal process; If the reference analysis coefficient CFi is less than the reference analysis threshold CFy, the reference analysis process i corresponding to the reference analysis coefficient CFi is marked as a reference normal process, and the average value of the reference charging voltage values ​​CYi of all reference normal processes is obtained and marked as the reference voltage value CU, the average value of the reference charging current values ​​CLi of all reference normal processes is obtained and marked as the reference current value CI, the average value of the reference charging power values ​​CGi of all reference normal processes is obtained and marked as the reference power value CW, and the reference voltage value CU, the reference current value CI and the reference power value CW are sent to the information analysis module.

8. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the information analysis module obtaining the charging adjustment information is as follows: The control voltage value KU and the reference voltage value CU are quantized, and the voltage adjustment value YT is obtained according to the formula YT=s1×KU+s2×CU; wherein s1 and s2 are the preset proportional coefficients corresponding to the set control voltage value KU and the reference voltage value CU respectively; The control current value KI and the reference current value CI are quantized, and the current adjustment value LT is obtained according to the formula LT=d1×KI+d2×CI; wherein d1 and d2 are the preset proportional coefficients corresponding to the set control current value KI and the reference current value CI respectively; The control power value KW and the reference power value CW are quantized, and the power adjustment value WT is obtained according to the formula WT=z1×KW+z2×CW; wherein w1 and w2 are the preset proportional coefficients corresponding to the set control power value KW and the reference power value CW respectively; The voltage adjustment value YT, the current adjustment value LT and the power adjustment value WT are sent to the interactive control module.

9. The charging pile vehicle network interactive control system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the interactive control module adjusting the charging pile is as follows: The voltage value when the charging pile charges the electric vehicle is adjusted according to the voltage adjustment value YT, the current value when the charging pile charges the electric vehicle is adjusted according to the current adjustment value LT, and the power value when the charging pile charges the electric vehicle is adjusted according to the power adjustment value WT.

Images