A charging pile intelligent management method and system

Abstract

The present application belongs to the technical field of charging pile management, and discloses a kind of charging pile intelligent management method and system;Including: the data acquisition of target area and the charging pile needed to be managed in target area, obtain corresponding electric pile data and area load data;And upload it to the dispatch block chain constructed in advance;Based on the electric pile data collected, the electric pile diagnosis is carried out on the corresponding charging pile, and the corresponding fault diagnosis result is obtained, whether the charging pile exists fault is judged based on the fault diagnosis result, if there is no fault, the corresponding charging pile is marked as healthy electric pile;If there is a fault, generate fault information and carry out fault early warning;The power distribution load management is carried out on the corresponding healthy electric pile in combination with the collected area load data;The present application realizes the intelligent management of charging pile, improves the operation efficiency and safety of charging pile, and realizes more efficient power distribution load management in combination with user charging demand.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of charging pile management, and more particularly to a charging pile intelligent management method and system. BACKGROUND

[0002] With the shortage of energy and the need for environmental protection, electric vehicles are widely promoted and applied to reduce the energy consumption of fuel vehicles and reduce the impact of exhaust emissions on the environment. With the accelerated development of new energy electric vehicles, the number of electric vehicles has increased sharply, and the construction of charging stations has solved part of the electric vehicle charging problem; but the management of charging stations is becoming more difficult;

[0003] Compared with the prior art, the traditional charging pile intelligent management method usually relies on manual operation, and the number of existing charging pile clusters is increasing, and the management efficiency of the corresponding charging piles is becoming lower and lower, which not only reduces the charging efficiency, but also due to the lack of effective scheduling and management mechanism, the use of charging piles often cannot be monitored and adjusted in real time, resulting in that the fault problems and load resource waste of charging piles cannot be discovered in time.

[0004] In view of this, the present application provides a charging pile intelligent management method and system to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0006] A charging pile intelligent management method, comprising:

[0007] Step 1: data collection is performed on the target area and the charging piles required to be managed in the target area to obtain corresponding pile data and area load data; and the data is uploaded to a pre-constructed scheduling block chain;

[0008] Step 2: based on the collected pile data, pile diagnosis is performed on the corresponding charging pile to obtain a corresponding fault diagnosis result, and based on the fault diagnosis result, it is judged whether the charging pile has a fault; if not, the corresponding charging pile is marked as a healthy pile; if so, fault information is generated and a fault warning is performed;

[0009] Step 3: combining the collected area load data, power distribution load management is performed on the corresponding healthy pile.

[0010] Further, the process of data collection on the target area and the charging piles required to be managed in the target area to obtain corresponding pile data and area load data; and uploading the data to the pre-constructed scheduling block chain includes:

[0011] obtain a distribution topology corresponding to the charging piles required to be managed in the target region, and divide the target region based on the distribution topology to obtain a plurality of charging pile regions;

[0012] set a supervision period, and collect data of the charging piles in the corresponding charging pile region in the corresponding supervision period to obtain corresponding charging pile data, the charging pile data including working status, charging data and electricity price of the charging piles; wherein the charging data includes charging pile temperature, charging voltage and charging current;

[0013] At the same time, the corresponding regional load data in the corresponding charging pile region in the corresponding supervision period is obtained, the regional load data including total load supply amount in the corresponding supervision period and individual load consumption amount corresponding to each charging pile;

[0014] Further, the collected regional load data and charging pile data are preprocessed, and the preprocessed charging pile data and regional load data are uploaded to a pre-constructed scheduling blockchain.

[0015] Further, the blockchain includes a master node, a normal node and a working node, the master node being used for managing transaction information between working nodes; the working node being used for adding, deleting or modifying information stored in the corresponding normal node, and also being used for storing corresponding regional load data; and the normal node being used for storing uploaded charging pile data.

[0016] Further, the process of dividing the target region based on the distribution topology to obtain a plurality of charging pile regions includes:

[0017] read the obtained distribution topology, mark the corresponding charging piles in the corresponding distribution topology as management nodes, and mark the power distribution center to which the corresponding target region belongs as a power distribution node;

[0018] the management node n generates a random value zn, zn∈(0,1); and compares it with the node threshold Tn;

[0019] if zn≤Tn, no other operation is performed; if zn>Tn, the corresponding management node n is marked as a regional node; wherein n=1,2,……,N1,N1>0 and N1 is an integer, and N1 represents the total number of management nodes;

[0020] based on the acquisition process of the regional node, all management nodes are traversed, and the management nodes not marked as regional nodes are marked as distribution nodes;

[0021] the position information of the distribution nodes, regional nodes and power distribution nodes is obtained respectively, the position information indicating the coordinate position of the corresponding distribution nodes, regional nodes and power distribution nodes in the world coordinate system;

[0022] Further, the trust factor XR between the corresponding regional node i and the distribution node j is obtained (i,j) ; wherein, i = 1, 2, …, N2, N2 is a natural number, N2 represents the total number of regional nodes, j = 1, 2, …, N3, N3 represents the total number of distribution nodes, N3 is a natural number, and N2+N3=N1, N2

[0023] The obtained trust factor is compared with the corresponding adaptive trust threshold value; and the corresponding regional node and distribution node are divided according to the comparison result, and a plurality of charging regions are obtained;

[0024] Further, the charging pile corresponding to the regional node transmits a clustering notification to other charging piles in the corresponding charging region, and obtains the network throughput and transmission delay between the corresponding charging piles in the corresponding transmission process, and compares them with the pre-set throughput threshold and delay threshold. If the network throughput and transmission delay both meet the corresponding throughput threshold and delay threshold, the corresponding charging region is marked as a charging pile region; if at least one of the network throughput and transmission delay does not meet the corresponding throughput threshold and delay threshold, the regional division is re-performed based on the charging region acquisition process to obtain new charging regions, and so on.

[0025] Further, the node threshold value is obtained: In the formula, p represents the probability that the management node n is selected as a regional node, r represents the number of rounds of selecting regional nodes; mod represents the modulo operation;

[0026] Trust factor In the formula, XR (i,j) represents the trust factor between the regional node i and the distribution node j; lt and wt represent the length and width of the corresponding management region respectively; τ and μ both represent trust measurement parameters, which are previously formulated by those skilled in the art according to actual needs; D (j,gl) represents the distance between the distribution node j and the power distribution node gl;

[0027] In the formula, x gl , x i , x j respectively represent the horizontal coordinates in the position information corresponding to the power distribution node gl, the management node i and the management node j; D (i,gl) represents the distance between the regional node i and the power distribution node gl; θ (i,j) represents the acute angle between the regional node i and the distribution node j with the power distribution node gl as the vertex;

[0028] The formula for obtaining the adaptive trust threshold value is:

[0029] In the formula, D max denotes the maximum value of the distance between the management node and the corresponding power distribution center; λ is a weight coefficient, In the formula, λ min and k are specific parameters, b i denotes the total number of other management nodes adjacent to the corresponding regional node i; P i denotes the adaptive trust threshold corresponding to the regional node i.

[0030] Further, the process of performing electric pile diagnosis on the corresponding charging pile based on the collected electric pile data to obtain the corresponding fault diagnosis result includes:

[0031] Reading the charging data corresponding to each charging pile in the corresponding electric pile area;

[0032] Constructing a two-dimensional rectangular coordinate system with time as the horizontal axis and charging data as the vertical axis, and mapping the corresponding charging data into the corresponding two-dimensional rectangular coordinate to obtain the corresponding charging data curve;

[0033] Based on the charging data curve, obtain the charging data corresponding to a plurality of historical monitoring periods, and based on the same, predict the charging prediction data corresponding to a future monitoring period;

[0034] Interval division is performed on the monitoring period to obtain a plurality of time intervals; based on the charging data curve and the charging prediction data, electric pile diagnosis data corresponding to the time interval to which the charging pile belongs at the current time and the future Q time intervals are obtained, the electric pile diagnosis data being composed of real-time charging data of the corresponding charging pile and charging prediction data corresponding to the Q time intervals; Q is a constant;

[0035] The electric pile diagnosis data is input into a pre-constructed fault monitoring model to obtain a corresponding fault monitoring result, the fault monitoring result including the fault probability of the corresponding charging pile under different fault types in the current time interval and the future Q time intervals;

[0036] A probability threshold is set, and the fault probability in the obtained fault monitoring result is compared with the corresponding probability threshold, if the corresponding fault probability is less than the probability threshold, the corresponding charging pile is marked as a healthy electric pile; if the fault probability is not less than the corresponding probability threshold, it indicates that the corresponding charging pile has a corresponding fault type, then the corresponding charging pile is marked as a fault electric pile, and the fault information is fed back to the corresponding staff.

[0037] Further, the process of constructing the fault monitoring model includes:

[0038] Obtaining the known fault types of the charging pile, and obtaining a plurality of sets of historical fault data corresponding to the plurality of sets of fault types based on a big data algorithm; the historical fault data is the charging data corresponding to the charging pile under the corresponding fault type;

[0039] Obtaining the fault data signal corresponding to the corresponding historical fault data, and performing C times decomposition on the obtained fault data signal based on a wavelet threshold function to obtain corresponding high-frequency signals and low-frequency signals; C is a fixed constant;

[0040] Obtaining the wavelet coefficient corresponding to the high-frequency signal in the cth decomposition layer, and taking it as the fault feature vector corresponding to the corresponding fault data signal; wherein c∈C;

[0041] Statistically obtaining all fault feature vectors corresponding to the historical fault data of the corresponding fault type to obtain a corresponding fault feature set;

[0042] Obtaining the fault feature set corresponding to all fault types, and constructing corresponding training data based thereon;

[0043] Defining the backbone network of the fault supervision model as a BP neural network; the BP neural network includes an input layer, a hidden layer and an output layer, inputting the input vector into the input layer in the corresponding BP neural network, and performing forward propagation according to the input layer, the hidden layer and the output layer, and obtaining the output vector of the corresponding output layer;

[0044] Comparing the output vector of the corresponding output layer with the expected output vector, and obtaining the corresponding output error E;

[0045] Comparing the output error with the expected error, if the output error meets the expected error, the training is ended, if the output error does not meet the expected error, performing backward propagation according to the input layer, the hidden layer and the output layer, and adjusting the weights of the neurons in the input layer, the hidden layer and the output layer;

[0046] When adjusting the weights of each layer, the input vector is propagated in the forward direction again, and the processes of "forward propagation" and "backward propagation" are repeatedly alternated, the weights of each layer are continuously adjusted, until the output error between the actual output vector and the expected output vector of the BP neural network meets the expected error requirement set, the iteration is ended, and the connection weights are fixed; and the corresponding model parameters are saved to obtain the corresponding fault supervision model;

[0047] Further, the output vector of the output layer In the formula, S k represents the kth output vector corresponding to the output layer, k=1, 2, …, K, K>0 and K is an integer, K represents the total number of output vectors corresponding to the output layer; w ykrepresents an initial weight value w between the yth output vector of the hidden layer and the kth output vector of the corresponding output layer;

[0048] H y represents the yth output vector corresponding to the hidden layer; y = 1, 2, …, Y, Y > 0 and Y is an integer; Y represents the total number of output vectors corresponding to the hidden layer; wherein, v py represents an initial weight v between the pth input vector and the yth output vector in the hidden layer; H P represents the pth input vector of the input; f represents an activation function;

[0049] output error wherein, d k represents the expected output vector corresponding to the output vector of the kth output layer;

[0050] The formula for adjusting the corresponding weight value is:

[0051]

[0052] wherein, β is a constant, used to represent the learning efficiency of the corresponding BP neural network;

[0053] Δw yk represents the adjustment value of the initial weight value w between the yth output vector of the hidden layer and the kth output vector of the corresponding output layer;

[0054] Δv py represents the adjustment value of the initial weight v between the pth input vector and the yth output vector in the hidden layer;

[0055] wherein, represents a partial derivative calculation; δ_k represents an output error signal corresponding to the kth output vector of the output layer.

[0056] Further, the process of performing power distribution load management on the corresponding healthy electric pile based on the collected regional load data includes:

[0057] Obtaining the electric pile region of the corresponding healthy electric pile, and obtaining the regional load data corresponding to the electric pile region based on the scheduling block chain;

[0058] Based on the regional load data, obtaining the historical single load consumption corresponding to a plurality of historical supervision periods corresponding to the corresponding healthy electric pile;

[0059] At the same time, based on the regional load data, obtaining the real-time single load consumption corresponding to the real-time time interval to which the current time belongs;

[0060] Based on historical single-body load consumption, load prediction is performed to obtain the expected load consumption in the corresponding current real-time time interval, and the deviation is calculated with the real-time single-body load consumption to obtain the corresponding load deviation;

[0061] A load threshold is set, and the obtained load deviation is compared with the corresponding load threshold;

[0062] If the corresponding load deviation is not less than the load threshold, the corresponding load deviation is marked as standby load;

[0063] If the corresponding load deviation is less than the load threshold, the corresponding ordinary node of the healthy electric pile generates corresponding supplementary transaction information; and feeds back to the working node to which it belongs, and the working node adjusts the charging pile strategy based on the received supplementary transaction information.

[0064] Further, it needs to be further explained that in the specific implementation process, the process of adjusting the charging pile strategy based on the received supplementary transaction information includes:

[0065] The working node broadcasts the corresponding supplementary transaction information to other ordinary nodes; after the other ordinary nodes receive the corresponding supplementary transaction information, the remaining amount of standby load corresponding to the ordinary nodes is obtained, and the remaining amount of standby load is fed back to the working node; the working node obtains the total amount of standby load according to the received remaining amount of standby load, and compares it with the amount of load deficit in the corresponding supplementary transaction information;

[0066] If the total amount of standby load is higher than the amount of load deficit, the working node constructs a corresponding load transaction combined with the supplementary transaction information; and based on the load transaction, the working node transfers load from other ordinary nodes with non-zero standby load remaining amount to the ordinary node that feeds back the supplementary transaction information; after the transmission is completed, the load transaction is broadcast to all ordinary nodes for storage;

[0067] If the total amount of standby load is not higher than the amount of load deficit, the working node feeds back an adjustment transaction to the corresponding ordinary node;

[0068] The working node reduces the pile load of the corresponding healthy electric pile in the corresponding time interval based on the adjustment transaction, and adjusts the charging scheme of the vehicle being charged based on the load deviation before and after the pile load, and then controls the corresponding healthy electric pile to supply power to the corresponding charging vehicle with the adjusted charging scheme.

[0069] Further, a charging pile intelligent management system comprises:

[0070] A data collection module is configured to collect data of target areas and charging piles required to be managed in the target areas, to obtain corresponding charging pile data and area load data, and to upload the data to a pre-constructed scheduling blockchain.

[0071] A fault diagnosis module is configured to perform charging pile diagnosis on corresponding charging piles based on the collected charging pile data, to obtain corresponding fault diagnosis results, to determine whether the charging piles have faults based on the fault diagnosis results, to mark the corresponding charging piles as healthy charging piles if there are no faults, and to generate fault information and perform fault warning if there are faults.

[0072] A load management module is configured to perform power distribution load management on corresponding healthy charging piles in combination with the collected area load data.

[0073] The charging pile intelligent management method and system have the following technical effects and advantages:

[0074] 1. The working state, charging data, electricity price, and other related parameters of the charging piles can be obtained in real time, and these data can be uploaded to the scheduling blockchain. This not only enables the management personnel to grasp the operation of the charging piles at any time, but also improves the timeliness and accuracy of data processing, thereby effectively improving the management efficiency of the charging piles.

[0075] 2. The charging piles in the target areas are divided into regions based on a distributed topology structure, to obtain corresponding charging pile regions. This helps to optimize the allocation of power resources according to the load demand and charging pile distribution of each region, to ensure the stable power supply of the charging piles in each region, to improve the fault response speed and maintenance efficiency, to balance the load of each region, to avoid the waste of resources or power shortage caused by excessively high or low load in some regions, and to reduce the data processing amount of the charging piles and improve the response efficiency of the charging piles. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 FIG. 1 is a schematic diagram of a charging pile intelligent management method according to the present application;

[0077] Figure 2 FIG. 2 is a schematic diagram of a charging pile intelligent management system according to the present application. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0079] Embodiment 1

[0080] Referring to Figure 1 The charging pile intelligent management method described in this embodiment includes:

[0081] Step one: Collect data on the target area and the charging piles needed to be managed in the target area to obtain corresponding pile data and area load data; and upload them to the pre-constructed scheduling blockchain;

[0082] Step two: Diagnose the corresponding charging pile based on the collected pile data to obtain the corresponding fault diagnosis result, determine whether the charging pile has a fault based on the fault diagnosis result, if there is no fault, mark the corresponding charging pile as a healthy pile; if there is a fault, generate fault information and perform fault warning;

[0083] Step three: Manage the power distribution load of the corresponding healthy pile in combination with the collected area load data;

[0084] It should be further explained that, in the specific implementation process, the process of collecting data on the target area and the charging piles needed to be managed in the target area to obtain corresponding pile data and area load data; and uploading them to the pre-constructed scheduling blockchain includes:

[0085] Obtain the distribution topology corresponding to the charging piles needed to be managed in the target area, and divide the corresponding target area based on the distribution topology to obtain a plurality of pile areas, each of which contains at least one charging pile needed to be managed; wherein the distribution topology refers to the distribution of the charging piles needed to be managed in the corresponding target area and the connection state between each charging pile; which can be obtained based on the laying plan of the charging piles in the target area;

[0086] Set a supervision period, and collect data on the charging piles in the corresponding pile area in the corresponding supervision period to obtain corresponding pile data, which includes the working state, charging data, electricity price and other related parameters of the charging pile; wherein the charging data includes pile temperature, charging voltage, and charging current;

[0087] At the same time, obtain the area load data corresponding to the corresponding pile area in the corresponding supervision period, which includes the total load supply amount in the corresponding supervision period and the individual load consumption amount corresponding to each charging pile; wherein the total load supply amount is determined by the total power distribution load and the total basic load, the total power distribution load refers to the load amount that can be provided by the power distribution center to which the corresponding pile area belongs according to the previously formulated power distribution plan; the total basic load refers to the load amount required by other electrical equipment in the corresponding pile area except the charging pile;

[0088] Further, the collected regional load data and electric pile data are preprocessed, and the preprocessed electric pile data and regional load data are uploaded to a pre-constructed scheduling blockchain; the scheduling blockchain includes a master node, a common node and a working node, the master node is used for managing transaction information between working nodes; the working node is used for adding, deleting or modifying information stored in the corresponding common node, and is also used for storing corresponding regional load data; the common node is used for storing uploaded electric pile data,

[0089] Wherein, one master node is connected with several working nodes, the number of working nodes is determined by the number of electric pile regions corresponding to the corresponding target region; one working node is connected with several common nodes, and one working node corresponds to one electric pile region, the number of common nodes connected by the working node is determined by the number of charging piles required to be managed in the electric pile region to which the working node belongs;

[0090] It should be further pointed out that in the specific implementation process, the data preprocessing includes data cleaning, data conversion and data normalization; data cleaning mainly corrects and fills the errors, missing and inconsistent data in the original data to ensure the integrity of the data; data conversion is to unify the data of different formats and units into standard format and unit to facilitate subsequent data analysis and processing; data normalization is to normalize the data to eliminate the dimensional and scale differences between the data, so that the data has comparability;

[0091] It should be further pointed out that in the specific implementation process, the process of dividing the target region based on the distribution topology structure to obtain several electric pile regions includes:

[0092] The obtained distribution topology structure is read, and the corresponding charging pile in the corresponding distribution topology structure is marked as a management node, and the power distribution center to which the corresponding target region belongs is marked as a power distribution node;

[0093] The management node n generates a random value zn, zn∈(0,1); and compares it with the node threshold Tn, if zn≤Tn, no other operation is performed; if zn>Tn, the corresponding management node n is marked as a regional node; wherein, n=1,2,……,N1,N1>0 and N1 is an integer, N1 represents the total number of management nodes; wherein, the formula for obtaining node threshold Tn is: In the formula, p represents the probability of the management node n being selected as a regional node, r represents the number of rounds of selecting regional nodes, the value of r is determined by the total number of selected regional nodes, for example, if the total number of selected regional nodes in the current round is not less than a constant K, secondary marking is performed from the marked regional nodes until the total number of selected regional nodes is less than the constant K; mod represents the modulo operation;

[0094] The area node-based acquisition process traverses all management nodes and marks the management nodes not marked as area nodes as allocation nodes;

[0095] The position information of the allocation nodes, the area nodes and the distribution nodes is respectively acquired, which indicates the coordinate positions of the corresponding allocation nodes, area nodes and distribution nodes in the world coordinate system;

[0096] Further, the trust factor XR between the corresponding area node i and the allocation node j is acquired (i,j) ; wherein i = 1, 2, …, N2, N2 is a natural number, N2 represents the total number of area nodes, j = 1, 2, …, N3, N3 represents the total number of allocation nodes, N3 is a natural number, and N2 + N3 = N1, N2 < K;

[0097] The trust factor XR In the formula, XR (i,j) represents the trust factor between the area node i and the allocation node j; lt and wt respectively represent the length and width of the corresponding management area; τ and μ both represent trust measurement parameters, which are formulated by a person skilled in the art according to actual requirements in advance; D (j,gl) represents the distance between the allocation node j and the distribution node gl; θ (i,j) represents the acute angle between the area node i and the allocation node j with the distribution node gl as the vertex, and the corresponding mathematical formula is as follows:

[0098] In the formula, x gl , x i , x j respectively represent the horizontal coordinates in the position information corresponding to the distribution node gl, the management node i and the management node j; D (i,gl) represents the distance between the area node i and the distribution node gl;

[0099] The obtained trust factor is compared with the corresponding adaptive trust threshold; wherein the acquisition formula of the adaptive trust threshold is: P i = 2pλ×exp{(-λ)×[(-k)log(1+k× In the formula, D max represents the maximum value of the distance between the management node and the corresponding distribution center; λ is a weight coefficient, In the formula, λ min and k are specific parameters, which are determined according to actual requirements, b i represents the total number of other management nodes adjacent to the corresponding area node i; P i represents the adaptive trust threshold corresponding to the area node i;

[0100] If the corresponding trust factor is less than or equal to the adaptive trust threshold, it indicates that the regional node i and the allocation node j are not trust nodes of each other, and no other operation is performed;

[0101] If the corresponding trust factor is greater than the adaptive trust threshold, it indicates that the regional node i and the allocation node j are trust nodes of each other, and the corresponding regional node i and the management node j are divided into the same sub-region; repeat until the corresponding target region is divided into several charging regions;

[0102] Further, the charging pile corresponding to the regional node transmits a clustering notification to other charging piles in the corresponding charging region, and obtains the network throughput and transmission delay between the corresponding charging piles in the corresponding transmission process, and compares them with the respective pre-set throughput threshold and delay threshold. If the network throughput and transmission delay both meet the corresponding throughput threshold and delay threshold, the corresponding charging region is marked as a charging pile region; if at least one of the network throughput and transmission delay does not meet the corresponding throughput threshold and delay threshold, the regional division is re-performed based on the charging region acquisition process to obtain new charging regions, and so on. The rule for determining whether the corresponding network throughput and transmission delay meet the corresponding throughput threshold and delay threshold is: if the corresponding network throughput (or transmission delay) is higher than the corresponding throughput threshold (or delay threshold), it is determined that the corresponding network throughput (or transmission delay) meets the corresponding throughput threshold (or delay threshold).

[0103] It needs to be further explained that, in the specific implementation process, the process of performing charging pile diagnosis on the corresponding charging pile based on the collected charging pile data to obtain the corresponding fault diagnosis result includes:

[0104] Taking any one charging pile region as an example, the charging data corresponding to each charging pile in the corresponding charging pile region is read;

[0105] A two-dimensional rectangular coordinate system with time as the horizontal axis and charging data as the vertical axis is constructed, and the corresponding charging data is mapped into the corresponding two-dimensional rectangular coordinate to obtain a corresponding charging data curve; the charging data curve includes a temperature curve, a voltage curve and a current curve;

[0106] Based on the charging data curve, the charging data corresponding to a plurality of historical monitoring periods is obtained, and based on the same, the charging prediction data corresponding to a future monitoring period is predicted;

[0107] The monitoring period is divided into intervals to obtain a plurality of time intervals; based on the charging data curve and the charging prediction data, charging pile diagnosis data corresponding to the time interval to which the current time of the charging pile belongs and the future Q time intervals is obtained. The charging pile diagnosis data is composed of real-time charging data of the corresponding charging pile and charging prediction data corresponding to Q time intervals; Q is a constant;

[0108] inputting the electric pile diagnosis data into a pre-constructed fault supervision model to obtain corresponding fault supervision results, the fault supervision results including fault probabilities of the corresponding charging pile under different fault types in the current time interval and the next Q time intervals;

[0109] setting a probability threshold, comparing the fault probabilities in the obtained fault supervision results with the corresponding probability threshold respectively, if the corresponding fault probability is less than the probability threshold, it indicates that the corresponding charging pile does not exist the corresponding fault type, then the corresponding charging pile is marked as a healthy electric pile, and the ordinary node corresponding to the corresponding charging pile is set as a public node; if the fault probability is not less than the corresponding probability threshold, it indicates that the corresponding charging pile exists the corresponding fault type, then the corresponding charging pile is marked as a fault electric pile, and the fault information including fault warning, fault type and location information of the corresponding charging pile is fed back to the corresponding staff; at the same time, the ordinary node corresponding to the corresponding fault electric pile is set as a private node, i.e. not participating in the scheduling of the charging pile, until the maintenance completion notification is fed back by the staff, the fault electric pile is unmarked, and the corresponding private node is changed to a public node;

[0110] It should be further pointed out that, in the specific implementation process, the construction process of the fault supervision model includes:

[0111] obtaining the known fault types of the charging pile, and obtaining a plurality of sets of historical fault data corresponding to the corresponding fault types based on big data algorithm; the historical fault data is the charging data corresponding to the charging pile under the corresponding fault type;

[0112] Taking any one fault type as an example, the fault data signal corresponding to the corresponding historical fault data is obtained; and the obtained fault data signal is decomposed C times based on the wavelet threshold function to obtain the corresponding high frequency signal and low frequency signal; wherein C represents the decomposition layer corresponding to the decomposition process of the corresponding wavelet threshold function; C is a fixed constant;

[0113] obtaining the wavelet coefficient corresponding to the high frequency signal corresponding to the cth decomposition layer, and taking it as the fault feature vector corresponding to the corresponding fault data signal; wherein c∈C; (i.e. one fault data signal can correspond to multiple fault feature vectors, and the number of specific fault feature vectors is determined by the decomposition layer number;)

[0114] statistically obtaining all fault feature vectors corresponding to the historical fault data of the corresponding fault type to obtain the corresponding fault feature set; wherein, in the corresponding statistical process, the statistical fault feature vectors are repeatedly checked, if a fault feature vector appears multiple times, the repeated fault feature vectors are removed;

[0115] Obtaining a fault feature set corresponding to all fault types, and constructing corresponding training data based on the fault feature set;

[0116] The backbone network of the fault supervision model is a BP neural network, which is used to learn a nonlinear mapping relationship between an input vector and a corresponding fault type; wherein, the input vector of the BP neural network is a fault feature vector in the training data;

[0117] The BP neural network includes an input layer, a hidden layer and an output layer, the input vector is input into the input layer in the corresponding BP neural network, and the input layer, the hidden layer and the output layer are propagated in the positive direction, and an output vector of the output layer is obtained In the formula, S k represents the kth output vector corresponding to the output layer, k = 1, 2, …, K, K > 0 and K is an integer, K represents the total number of output vectors corresponding to the output layer; w yk represents the initial weight w between the yth output vector of the hidden layer and the kth output vector of the corresponding output layer;

[0118] H y represents the yth output vector corresponding to the hidden layer; y = 1, 2, …, Y, Y > 0 and Y is an integer; Y represents the total number of output vectors corresponding to the hidden layer; In the formula, v py represents the initial weight v between the pth input vector and the yth output vector in the hidden layer; H P represents the pth input vector of the input;

[0119] f represents an activation function, which is selected by a person skilled in the art according to actual needs; wherein, the initial weight w and the initial weight v are network parameters of the corresponding BP neural network, which are parameters set by the staff when constructing the corresponding BP neural network according to actual needs;

[0120] Further, the output vector of the corresponding output layer is compared with the expected output vector, and the corresponding output error E is obtained; the formula for obtaining the corresponding output error E is:

[0121] In the formula, d k represents the expected output vector corresponding to the output vector of the kth output layer;

[0122] The output error is compared with the expected error, if the output error meets the expected error, the training is ended, if the output error does not meet the expected error, the input layer, the hidden layer and the output layer are propagated in the reverse direction, and the weights of the neurons in the input layer, the hidden layer and the output layer are adjusted; the formula for corresponding weight adjustment is:

[0123]

[0124] wherein, β is a constant, used to represent the learning efficiency of the corresponding BP neural network;

[0125] Δw yk represents the adjustment value of the initial weight w between the yth output vector of the hidden layer and the kth output vector of the corresponding output layer;

[0126] Δv py represents the adjustment value of the initial weight v between the pth input vector and the yth output vector in the hidden layer;

[0127] δ_k represents the output error signal corresponding to the kth output vector of the output layer; and the corresponding acquisition formula is as follows: wherein, represents the partial differential calculation;

[0128] When the weights of each layer are adjusted, the input vector is again propagated in the positive direction, and the processes of "input forward propagation" and "output backward propagation" are repeatedly alternated, and the weights of each layer are continuously adjusted, until the output error between the actual output vector and the expected output vector of the BP neural network meets the set expected error requirement, the iteration is ended, and the connection weights are fixed; and the corresponding model parameters are saved, and the corresponding fault monitoring model is obtained; wherein, the expected error and the expected output vector are determined according to actual needs.

[0129] It needs to be further explained that, in the specific implementation process, the process of managing the power distribution load of the corresponding healthy power pile in combination with the collected regional load data includes:

[0130] obtaining the power pile region of the corresponding healthy power pile, and obtaining the regional load data corresponding to the power pile region based on the scheduling block chain;

[0131] obtaining the historical single-body load consumption corresponding to a plurality of historical monitoring periods of the corresponding healthy power pile based on the regional load data;

[0132] At the same time, the real-time single-body load consumption corresponding to the real-time time interval to which the current time belongs is obtained based on the regional load data;

[0133] Based on the historical single-body load consumption, the expected load consumption corresponding to the corresponding current real-time time interval is obtained through load prediction, and the expected load consumption is compared with the real-time single-body load consumption to obtain the load deviation;

[0134] A load threshold is set, and the obtained load deviation is compared with the corresponding load threshold;

[0135] If the corresponding load deviation is not less than the load threshold, it indicates that the expected load consumption of the corresponding healthy electric pile is higher than the real-time single load consumption, that is, there is a load surplus in the corresponding healthy electric pile, and the corresponding load deviation is marked as standby load;

[0136] If the corresponding load deviation is less than the load threshold, it indicates that the expected load consumption of the corresponding healthy electric pile is lower than the real-time single load consumption, that is, there is a load deficit in the corresponding healthy electric pile; the corresponding ordinary node of the corresponding healthy electric pile generates corresponding supplementary transaction information; and feeds back to the working node to which it belongs, and the working node adjusts the charging pile strategy based on the received supplementary transaction information;

[0137] It needs to be further explained that, in the specific implementation process, the process of adjusting the charging pile strategy based on the received supplementary transaction information includes:

[0138] Further, the working node broadcasts the corresponding supplementary transaction information to other ordinary nodes; when other ordinary nodes receive the corresponding supplementary transaction information, the remaining amount of standby load corresponding to itself is obtained, and is fed back to the working node; wherein, if the ordinary node itself has a load deficit, the remaining amount of standby load corresponding to it is zero;

[0139] The working node obtains the total amount of corresponding standby load according to the received remaining amount of standby load, and compares it with the amount of load deficit in the corresponding supplementary transaction information;

[0140] If the total amount of standby load is higher than the amount of load deficit, the working node constructs a corresponding load transaction in combination with the supplementary transaction information; and based on the load transaction, the working node transfers load from other ordinary nodes with non-zero standby load remaining amount to the ordinary node that feeds back the supplementary transaction information; after the transmission is completed, the load transaction is broadcast to all ordinary nodes for storage;

[0141] If the total amount of standby load is not higher than the amount of load deficit, the working node feeds back an adjustment transaction to the corresponding ordinary node;

[0142] Further, the working node reduces the pile load of the corresponding healthy electric pile in the corresponding time interval based on the adjustment transaction, and adjusts the charging scheme of the vehicle being charged based on the load deviation before and after the pile load, and then controls the corresponding healthy electric pile to supply power to the corresponding charging vehicle with the adjusted charging scheme, and feeds back the adjusted charging scheme to the corresponding vehicle owner; wherein, the specific adjustment process is determined according to the actual amount of load deficit, and at the same time, the adjusted expected charging time cannot exceed the original expected charging time as a constraint condition.

[0143] The application divides the charging piles in the target area based on the distribution topology structure, obtains the corresponding pile area, and uploads the data collected by each pile area to the scheduling block chain, which helps to grasp the operation of the charging pile at any time, improves the timeliness and accuracy of data processing, and effectively improves the management efficiency of the charging pile; by constructing a fault supervision model, not only can reduce the charging interruption phenomenon caused by charging pile failure, but also can prolong the service life of the charging pile and reduce the maintenance cost; the power distribution load management of the healthy charging pile can ensure the load balance of the charging pile, improve the utilization efficiency of power resources, and reduce energy waste.

[0144] Embodiment 2

[0145] Please refer to Figure 2 The embodiment does not describe part in detail, see the description of embodiment 1, and provides a charging pile intelligent management system, including:

[0146] A data acquisition module is used for collecting data of a target area and charging piles needed to be managed in the target area, obtaining corresponding pile data and area load data, and uploading them to a pre-constructed scheduling block chain;

[0147] A fault diagnosis module is used for diagnosing the charging pile based on the collected pile data, obtaining the corresponding fault diagnosis result, judging whether the charging pile has a fault based on the fault diagnosis result, marking the corresponding charging pile as a healthy charging pile if there is no fault, and generating fault information and performing fault warning if there is a fault;

[0148] A load management module is used for power distribution load management of the corresponding healthy charging pile in combination with the collected area load data.

[0149] Each module is connected through wired and / or wireless mode to realize data transmission between modules.

[0150] Embodiment 3

[0151] The embodiment discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to realize the operation mode of the charging pile intelligent management method and system provided above.

[0152] Since the electronic device introduced in the embodiment is the electronic device used in the implementation of the method and system for intelligent management of charging piles in the embodiment, the specific implementation of the electronic device and various changes thereof can be understood by those skilled in the art based on the method for intelligent management of charging piles in the embodiment, and therefore, how the electronic device implements the method in the embodiment will not be described in detail. As long as the electronic device used in the implementation of the method and system for intelligent management of charging piles in the embodiment is implemented by those skilled in the art, it belongs to the scope of protection of the present application.

[0153] The above formulas are dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and the preset parameters and threshold values in the formula are set by those skilled in the art according to the actual situation.

[0154] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solution falling within the concept of the present application shall be considered as falling within the protection scope of the present application. It should be noted that, for ordinary technical users in the technical field, some improvements and refinements without departing from the principles of the present application are also considered as falling within the protection scope of the present application.

Claims

1. A charging pile intelligent management method, characterized in that, Comprise: Step one: data collection on target area and charging piles needed to be managed in target area, obtain corresponding electric pile data and area load data; And upload it to the pre-constructed scheduling blockchain; Step two: electric pile diagnosis on corresponding charging pile based on collected electric pile data, obtain corresponding fault diagnosis result, judge whether charging pile has fault based on fault diagnosis result, if there is no fault, mark corresponding charging pile as healthy electric pile; If there is a fault, generate fault information and perform fault warning; Step three: power distribution load management on corresponding healthy electric pile combined with collected area load data; Data collection on target area and charging piles needed to be managed in target area, obtain corresponding electric pile data and area load data; And upload it to the pre-constructed scheduling blockchain, the process includes: Obtain the distribution topology structure corresponding to the charging piles needed to be managed in the target area, and divide the target area based on the distribution topology structure to obtain a plurality of electric pile areas; Set the supervision period, and collect data of charging piles in the corresponding electric pile area in the corresponding supervision period to obtain corresponding electric pile data, the electric pile data includes the working state of the charging pile, charging data, electricity price; wherein, the charging data includes electric pile temperature, charging voltage, charging current; At the same time, obtain the area load data corresponding to the corresponding electric pile area in the corresponding supervision period, the area load data includes the total amount of load supply in the corresponding supervision period and the single load consumption corresponding to each charging pile; Further, data preprocessing is performed on the collected area load data and electric pile data, and the preprocessed electric pile data and area load data are uploaded to the pre-constructed scheduling blockchain; The scheduling blockchain includes master node, ordinary node and working node, the master node is used for managing working node; the working node is used for adding, deleting or modifying the information stored in the corresponding ordinary node, and is also used for storing the corresponding area load data; the ordinary node is used for storing the uploaded electric pile data; The process of dividing the target area based on the distribution topology structure to obtain a plurality of electric pile areas includes: Read the obtained distribution topology structure, and mark the corresponding charging piles in the corresponding distribution topology structure as management nodes, and mark the power distribution center to which the corresponding target area belongs as power distribution nodes; The management node Generating a random value , ; and comparing it to a node threshold ; If then no further action is taken; if then the respective management node n is marked as a regional node; wherein and is an integer, denotes the total number of management nodes; Based on the acquisition process of area nodes, all management nodes are traversed, and the management nodes not marked as area nodes are marked as distribution nodes; Respectively obtain the position information of distribution nodes, area nodes and power distribution nodes, the position information refers to the coordinate position of the corresponding distribution nodes, area nodes and power distribution nodes in the world coordinate system; Further, a trust factor between the corresponding regional node and the distribution node is acquired Further, a trust factor between the corresponding regional node and the distribution node is acquired Further, a trust factor between the corresponding regional node and the distribution node is acquired wherein, n is a natural number, n is a natural number, n represents the total number of regional nodes, n represents the total number of distribution nodes, n is a natural number; the acquired trust factor is compared with a corresponding adaptive trust threshold; and the corresponding regional node and the distribution node are classified according to the comparison result, to obtain a plurality of charging regions; The regional node corresponding to the charging pile transmits a clustering notification to other charging piles in the corresponding charging area, and obtains network throughput and transmission delay between the corresponding charging piles in the corresponding transmission process, and compares them with the respective pre-set throughput threshold and delay threshold. If the network throughput and transmission delay both meet the corresponding throughput threshold and delay threshold, the corresponding charging area is marked as a charging pile area. If at least one of the network throughput and transmission delay does not meet the corresponding throughput threshold and delay threshold, the charging area is re-divided based on the obtained charging area to obtain new charging areas, and so on. 2.The method of claim 1, wherein, the node threshold ; wherein, denotes a management node denotes a probability of being selected as a regional node, denotes a round of selecting a regional node; denotes a modulo operation; trust factor ; wherein represents the trust factor between a zone node and a distribution node ; and represent the length and width of the respective management zone, respectively; and both represent trust metric parameters; represents the distance between a distribution node and a power distribution node ; ; wherein , , denote the horizontal coordinate within the position information corresponding to the respective distribution node , the management node and the management node ; denote the distance between the area node and the distribution node ; denote the acute angle subtended by the area node and the distribution node with the apex at the distribution node ; The adaptive trust threshold formula is: ; where, denotes the maximum value of the distance between the management node and the respective distribution center; is a weight coefficient; is a specific parameter, denotes the adaptive trust threshold corresponding to the area node . 3.The method of claim 1, wherein, The process of performing charging pile diagnosis on the corresponding charging pile based on the collected charging pile data to obtain the corresponding fault diagnosis result includes: Reading the charging data corresponding to each charging pile in the corresponding charging pile area; A two-dimensional rectangular coordinate system with time as the horizontal axis and charging data as the vertical axis is constructed, and the corresponding charging data is mapped into the corresponding two-dimensional rectangular coordinate to obtain the corresponding charging data curve; Based on the charging data curve, the charging data corresponding to a plurality of historical monitoring periods is obtained, and the charging prediction data corresponding to a future monitoring period is predicted based thereon; The supervision period is divided into intervals to obtain a plurality of time intervals; based on the charging data curve and the charging prediction data, the electric pile diagnosis data corresponding to the time interval to which the current time of the charging pile belongs and the future time interval are obtained, the electric pile diagnosis data is composed of real-time charging data of the corresponding charging pile and charging prediction data corresponding to the time interval; The constant is a constant; The constant is a constant;​ The electric pile diagnosis data is input into a pre-constructed fault supervision model to obtain corresponding fault supervision results, the fault supervision results including fault probabilities of the corresponding charging pile under different fault types in a current time interval and a future time interval. ​ A probability threshold is set, and the fault probability in the obtained fault monitoring result is compared with the corresponding probability threshold. If the corresponding fault probability is less than the probability threshold, the corresponding charging pile is marked as a healthy charging pile. If the fault probability is not less than the corresponding probability threshold, the corresponding charging pile is marked as a fault charging pile, and the fault information is fed back to the corresponding staff.

4. The intelligent management method of the charging pile according to claim 3, characterized in that, The construction process of the fault monitoring model includes: Obtaining the known fault types of the charging pile, and obtaining a plurality of sets of historical fault data corresponding to a plurality of sets of corresponding fault types based on a big data algorithm; the historical fault data is the charging data corresponding to the charging pile under the corresponding fault type; obtaining a fault data signal corresponding to the corresponding historical fault data; and based on a wavelet threshold function, processing the obtained fault data signal to obtain a corresponding high-frequency signal and a low-frequency signal; is a fixed constant; Get the The wavelet coefficients corresponding to the high-frequency signals within each decomposition layer are used as the fault feature vectors corresponding to the fault data signals; where... ; All fault feature vectors corresponding to the historical fault data of the corresponding fault type are counted to obtain the corresponding fault feature set; Obtaining the fault feature set corresponding to all fault types, and constructing the corresponding training data based thereon; The backbone network defining the fault monitoring model is The neural network; the neural network comprises an input layer, a hidden layer and an output layer The neural network comprises an input layer, a hidden layer and an output layer, and the input vector is input into the corresponding The input layer in the neural network, and the forward propagation is performed according to the input layer, the hidden layer and the output layer, and the output vector of the corresponding output layer is obtained. comparing the output vector of the respective output layer with the desired output vector and obtaining a respective output error ; The output error is compared with the expected error. If the output error meets the expected error, the training is ended. If the output error does not meet the expected error, the back propagation is performed according to the input layer, the hidden layer and the output layer, and the weight of the neurons in the input layer, the hidden layer and the output layer is adjusted. When the weights of each layer are adjusted, the input vector is propagated in the positive direction again, and the positive direction propagation and the negative direction propagation are repeatedly alternated, and the weights of each layer are continuously adjusted until the output error between the actual output vector and the expected output vector of the BP neural network meets the expected error requirement, and the iteration is ended. The connection weights are fixed; and the corresponding model parameters are saved to obtain the corresponding fault monitoring model.

5. The intelligent management method of the charging pile according to claim 4, characterized in that, The output vector of the output layer In the formula, Indicates the first layer corresponding to the output layer Output vectors , and It is an integer. This represents the total number of output vectors corresponding to the output layer; The hidden layer is represented by the first... The output vector and the corresponding output layer's first output vector The initial weights w between the output vectors; represents the i-th output vector corresponding to the hidden layer; and is an integer; represents the total number of output vectors corresponding to the hidden layer; ; where represents the initial weight between the i-th input vector and the j-th output vector in the hidden layer; ; represents the i-th input vector of the input; represents the activation function;​​​ Output error ; where, represents the expected output vector corresponding to the output vector of the th output layer. The formula for adjusting the corresponding weight is: ； In the formula, It is a constant used to represent the corresponding The learning efficiency of neural networks; adjustment values of initial weights between the first output vector of the hidden layer and the first output vector of the corresponding output layer ​ denotes the adjustment value of the initial weight between the th input vector and the th output vector in the hidden layer ; In the formula, This represents partial differential calculation; Represents the first output layer The output error signal corresponding to each output vector.

6. The intelligent management method of the charging pile according to claim 3, characterized in that, The process of performing power distribution load management on the corresponding healthy charging pile in combination with the collected regional load data includes: Obtaining the charging pile area of the corresponding healthy charging pile, and obtaining the regional load data corresponding to the corresponding charging pile area based on the dispatching block chain; Based on the area load data, historical single-body load consumptions corresponding to a plurality of historical supervision periods of a corresponding healthy electric pile are obtained; At the same time, based on the area load data, real-time single-body load consumptions corresponding to a real-time time interval to which the current time belongs are obtained; Based on the historical single-body load consumptions, load prediction is performed to obtain expected load consumptions corresponding to the current real-time time interval, and deviation calculation is performed between the expected load consumptions and the real-time single-body load consumptions to obtain corresponding load deviations; A load threshold is set, and the obtained load deviations are compared with the corresponding load threshold; If the corresponding load deviation is not less than the load threshold, the corresponding load deviation is marked as standby load; If the corresponding load deviation is less than the load threshold, a corresponding supplementary transaction information is generated by a normal node corresponding to the corresponding healthy electric pile; and the normal node feeds back the supplementary transaction information to a working node to which the normal node belongs, and the working node performs charging pile strategy adjustment based on the received supplementary transaction information.

7. The method of claim 6, wherein, The process of performing charging pile strategy adjustment based on the received supplementary transaction information includes: The working node broadcasts the corresponding supplementary transaction information to other normal nodes; after receiving the corresponding supplementary transaction information, other normal nodes obtain the remaining amount of standby load corresponding to the normal nodes, and feed back the remaining amount to the working node; the working node obtains the total amount of standby load according to the received remaining amount of standby load, and compares the total amount of standby load with the amount of load in deficit in the corresponding supplementary transaction information; If the total amount of standby load is higher than the amount of load in deficit, the working node constructs a corresponding load transaction in combination with the supplementary transaction information; and based on the load transaction, the working node performs load transmission from other normal nodes with non-zero standby load remaining amount to the normal node feeding back the supplementary transaction information; after the transmission is completed, the working node broadcasts the load transaction to all normal nodes for storage; If the total amount of standby load is not higher than the amount of load in deficit, the working node feeds back an adjustment transaction to the corresponding normal node; The working node reduces the electric pile load of the corresponding healthy electric pile in the corresponding time interval based on the adjustment transaction, adjusts the charging scheme of the vehicle being charged based on the electric pile load before and after the adjustment, and then controls the corresponding healthy electric pile to supply power to the corresponding vehicle in the adjusted charging scheme.

8. A charging pile intelligent management system, characterized in that, A charging pile intelligent management method for realizing any one of claims 1 to 7, comprising: A data acquisition module is configured to acquire data of a target area and charging piles required to be managed in the target area, obtain corresponding electric pile data and area load data, and upload the data to a pre-constructed scheduling block chain; A fault diagnosis module is configured to perform electric pile diagnosis on the corresponding charging pile based on the acquired electric pile data, obtain a corresponding fault diagnosis result, determine whether the charging pile has a fault based on the fault diagnosis result, mark the corresponding charging pile as a healthy electric pile if the charging pile has no fault, and generate fault information and perform fault warning if the charging pile has a fault; A load management module is configured to perform power distribution load management on the corresponding healthy electric pile in combination with the acquired area load data.

Images