A charging pile detection method, system and charging pile

Abstract

The present invention discloses a detection method, system and charging pile of a charging pile, the method comprising obtaining user data, operation data, charging data, geographic data and environmental data of the charging pile; performing information preprocessing on the geographic data to obtain a regional distribution map of the charging pile; performing discretization processing on the regional distribution map to obtain a discretized distribution map; performing clustering processing on the discretized distribution map to obtain a sub-region; performing characterization calculation according to the environmental data and the sub-region to obtain a characterization parameter; performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter; performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; performing a health prediction operation according to the second characteristic parameter to obtain a prediction result. The method can improve the detection accuracy by considering environmental factors.

Description

Technical Field

[0001] The present invention relates to the technical field of charging piles, and in particular to a detection method and system for a charging pile and a charging pile. Background Art

[0002] At present, charging piles are facilities for power load status analysis. The current or voltage changes during the charging process will cause load mutations, affecting the stability of the power grid and the quality of power. Continuous operation status analysis of charging piles helps optimize charging strategies, protect the power grid, and save resources. However, long-term instability of the power grid will damage the charging piles and shorten their service life.

[0003] In one prior art, the load is predicted mainly by monitoring the operation of the charging pile, such as charging current, voltage and time, combined with a prediction algorithm. The evaluation method for charging piles mainly adopts state monitoring, load analysis and prediction. State monitoring mainly monitors the operation of the charging pile, including charging current, charging voltage and charging time, and then predicts the load according to the prediction algorithm. However, this method requires a comprehensive consideration of various factors, including ambient temperature, to predict the load. There are problems such as complex algorithms, time-consuming and energy-consuming. In addition, this method can only determine the load size within the prediction time period. The prediction accuracy is not high, and it is impossible to determine the load status at a certain moment. At present, when detecting the operating status and load of the charging pile, the impact of environmental factors on the load and operating status of the charging pile is not considered. In the detection, charging mainly depends on the condition of the charging pile itself, and there is a lack of effective monitoring and evaluation methods.

[0004] The existing technology does not consider the impact of environmental factors on the load and operating status of the charging pile, resulting in low detection accuracy. Summary of the invention

[0005] The present invention provides a charging pile detection method, system and charging pile to improve detection accuracy.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a detection method for a charging pile, comprising: Obtain user data, operation data, charging data, geographic data and environmental data of charging piles; The geographic data is preprocessed to obtain a regional distribution map of charging piles; Discretizing the regional distribution map to obtain a discretized distribution map; Performing clustering processing on the discretized distribution map to obtain sub-regions; Performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; Performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter; Performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; According to the second characteristic parameter, a health prediction operation is performed to obtain a prediction result.

[0007] In an optional implementation, the preprocessing of the geographic data to obtain a regional distribution map of charging piles includes: Extracting coordinates according to the geographic data to obtain coordinate information; According to the coordinate information, numbering processing is performed to obtain a regional distribution map.

[0008] In an optional implementation, the discretizing the regional distribution map to obtain a discretized distribution map includes: According to the regional distribution map, coordinate gridding processing is performed to obtain discretization information; An information labeling operation is performed according to the discretized information to obtain a discretized distribution map.

[0009] In an optional implementation, performing characterization calculation according to the environmental data and the sub-area to obtain the characterization parameter includes: Extracting the environmental data in each sub-area to obtain the environmental temperature, environmental humidity and environmental illumination; Performing environmental calculation on the ambient temperature, the ambient humidity and the ambient light illumination in each of the sub-areas to obtain characterization parameters; The characterization parameters are calculated by the following formula, including:

[0010] in, is the characterization parameter, is the number of blocks, For the The ambient light intensity of each block, For the The ambient humidity of each block, For the The ambient temperature of each block.

[0011] In an optional implementation, performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain the first characteristic parameter includes: Performing exponential smoothing calculation according to the user data, the operation data, and the charging data to obtain a smoothed value; Performing feature calculation according to the smoothing value and the characterization parameter to obtain a first feature parameter; The smoothing value is calculated by the following formula:

[0012] The first characteristic parameter is calculated by the following formula, including:

[0013] in, For time The smoothing value of the node, is the first smoothing parameter, For time Charging voltage of charging pile, For time Charging pile operating voltage, For time The smoothing value of the node, For time The first characteristic parameter, is the second smoothing parameter, For time The horizontal component, is the characterization parameter.

[0014] In an optional implementation, performing adaptive dynamic prediction processing on the first characteristic parameter to obtain the second characteristic parameter includes: The second characteristic parameter is calculated by the following formula, including:

[0015] in, For time The second characteristic parameter, is the first characteristic parameter versus time The partial guide, is the environmental factor, is the impact factor, for White noise at all times, For time The first characteristic parameter.

[0016] In an optional implementation, performing a health prediction operation according to the second characteristic parameter to obtain a prediction result includes: Calculating the health index according to the second characteristic parameter to obtain the health index; According to the health index, determine whether the health index is greater than a preset health threshold, and if so, output a charging pile operation abnormality result; if not, output a charging pile detection normal result; The health index is calculated by the following formula:

[0017] in, is the health index, is the charging pile compensation coefficient, is the weight coefficient, is the environmental data weight, For time The second characteristic parameter.

[0018] In a second aspect, the present invention provides a detection system for a charging pile, comprising: A data acquisition module is used to acquire user data, operation data, charging data, geographic data and environmental data of the charging pile; An information processing module performs information preprocessing on the geographic data to obtain a regional distribution map of charging piles; A regional discretization module discretizes the regional distribution map to obtain a discretized distribution map; A clustering processing module performs clustering processing on the discretized distribution map to obtain sub-regions; A characterization calculation module, performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; a feature calculation module, performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first feature parameter; A dynamic prediction module performs adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; The result output module performs a health prediction operation according to the second characteristic parameter to obtain a prediction result.

[0019] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned charging pile detection methods when executing the computer program.

[0020] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned charging pile detection methods.

[0021] Compared with the prior art, the present invention has the following beneficial effects: the present invention discloses a detection method for a charging pile, comprising obtaining user data, operation data, charging data, geographic data and environmental data of the charging pile; performing information preprocessing on the geographic data to obtain a regional distribution map of the charging pile; performing discretization processing on the regional distribution map to obtain a discretized distribution map; performing clustering processing on the discretized distribution map to obtain sub-regions; performing characterization calculation based on the environmental data and the sub-regions to obtain characterization parameters; performing time series analysis based on the user data, the operation data, the charging data and the characterization parameters to obtain a first characteristic parameter; performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; performing a health prediction operation based on the second characteristic parameter to obtain a prediction result.

[0022] The present invention takes into account the impact of environmental factors on the load and operating status of the charging pile by preprocessing and discretizing geographic data, and combining environmental data for characterization calculation, which is beneficial to improving the accuracy of load prediction and can better adapt to charging needs under different environmental conditions. At the same time, by adaptive dynamic prediction processing to obtain the second characteristic parameter, the present invention can adjust the prediction model according to real-time data, thereby improving the flexibility and accuracy of the prediction. In summary, the present invention improves the accuracy of charging pile detection, optimizes the charging strategy, and enhances the adaptability and service life of the charging pile by comprehensively considering multi-source data and environmental factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flow chart of a detection method for a charging pile provided in the first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of the detection system of the charging pile provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in 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.

[0025] Reference Figure 1 The first embodiment of the present invention provides a detection method for a charging pile, comprising the following steps: S11, obtaining user data, operation data, charging data, geographic data and environmental data of the charging pile; S12, performing information preprocessing on the geographic data to obtain a regional distribution map of charging piles; S13, discretizing the regional distribution map to obtain a discretized distribution map; S14, clustering the discretized distribution map to obtain sub-regions; S15, performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; S16, performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter; S17, performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; S18: Perform a health prediction operation based on the second characteristic parameter to obtain a prediction result.

[0026] In step S11, user data, operation data, charging data, geographic data and environmental data of the charging pile are obtained, including: In this embodiment, the data collection process is started when the charging pile is powered on. This step involves the initialization of the charging pile, ensuring that all systems and sensors of the charging pile are in working condition and ready to start data collection. After the charging pile is powered on, it is necessary to send registration data to the server, which includes the model, serial number, location information, etc. of the charging pile, so that the server can identify and record the identity and attribute information of the charging pile. Secondly, through the user interface or mobile application of the charging pile, the user identifies by swiping a card, scanning a code, or logging into an account. The charging behavior of the identified user is associated with the account information, and the user's charging habits and preferences are recorded. The system automatically records the user's charging time, frequency, power, and other information. The built-in sensors and monitoring systems of the charging pile monitor its operating status in real time, including current, voltage, power, etc., and record any abnormal or fault events, such as overload, short circuit, disconnection, etc. The historical data of maintenance and repair is also recorded to facilitate the analysis of the maintenance cycle and durability of the charging pile. During the charging process, record the start and end time of charging, charge amount, charging rate, etc., obtain accurate power consumption data during the charging process through the interface with the meter, and collect user feedback on the charging experience, including through mobile applications or on-site feedback mechanisms. Use the built-in GPS module of the charging pile to obtain its precise geographic location, and convert the geographic coordinates into readable address or area information through the interface with the map service. Install environmental sensors such as thermometers, hygrometers, and light meters near the charging pile. Regularly synchronize data from sensors to the control system of the charging pile, and use the weather API to obtain more extensive environmental data, such as weather forecasts and historical weather data.

[0027] It should be noted that user data refers to user information related to the use of charging piles, such as user charging habits, charging frequency, etc. Operation data refers to parameters related to the daily operation of charging piles, such as operating time, fault records, operating voltage, operating current, etc. Charging data refers to the specific parameters of the charging pile during the charging process, such as charging voltage and charging current. Geographic data refers to the geographical location information of the charging pile, which is the longitude and latitude coordinates in this case. Environmental data refers to the relevant parameters of the environment where the charging pile is located, such as temperature, humidity, and light intensity.

[0028] In step S12, the geographic data is preprocessed to obtain a regional distribution map of charging piles, including: Extracting coordinates according to the geographic data to obtain coordinate information; According to the coordinate information, numbering processing is performed to obtain a regional distribution map.

[0029] In a specific embodiment, first, it is necessary to collect geographic data of the charging pile, which includes the location information of the charging pile, which refers to the longitude and latitude coordinates. The longitude and latitude of the charging pile location, road information, surrounding facilities, etc. are provided through Google Maps. The detailed address of the charging pile equipment deployment and the physical properties of the charging pile are recorded through the operating data of the charging business. GIS is used to obtain information including terrain, climate conditions and urban planning. Secondly, the acquired geographic data is cleaned to remove noise and errors in the geographic data. Fill in or delete missing location points in the geographic data. Specifically, the unknown coordinate points are estimated using the adjacent point interpolation method. Duplicate charging pile location information is deduplicated to avoid data interference. The outlier detection technology (DBSCAN) is used to eliminate erroneous data points that deviate from the true location. After completing the cleaning and integration of the geographic data, visualization and spatial computing technologies need to be used to generate a regional distribution map. The location information of charging piles is projected onto a two-dimensional map to intuitively present the distribution of charging piles. The location of each charging pile is represented by a dot map, which is suitable for small-scale areas. A color gradient distribution map is generated based on the density of charging piles through a heat map to show the comparison between high-density and low-density areas. Finally, the potential distribution of areas without charging piles is estimated through spatial interpolation (such as Kriging interpolation), and combined with road data, a regional distribution map with traffic convenience as the weight is generated.

[0030] It should be noted that different data sources use different coordinate systems, such as WGS84, GCJ-02 or WebMercator. In this step, all geographic data need to be uniformly converted to a consistent coordinate system (such as WGS84) to ensure the accuracy of location information. Since the resolution of geographic data varies from source to source, the data needs to be processed uniformly: low-resolution data is refined using interpolation; high-resolution data is downsampled to reduce redundant calculations. Through overlay analysis, multi-source data (charging pile location, road network and surrounding environment) are integrated into a single geographic data set. Spatial data fusion technology (weighted overlay method or spatial clustering) is used to ensure data consistency and availability. When generating regional distribution maps, in order to ensure clear information, layered visualization technology is used to display different types of information separately: the first layer shows the actual location of the charging pile; the second layer overlays surrounding facilities (parking lots, shopping malls); and the third layer shows the road network or regional boundaries.

[0031] In step S13, the regional distribution map is discretized to obtain a discretized distribution map, including: According to the regional distribution map, coordinate gridding processing is performed to obtain discretization information; An information labeling operation is performed according to the discretized information to obtain a discretized distribution map.

[0032] In a specific embodiment, coordinate gridding is to divide the continuous geographic space into several regular grids, and each grid unit represents a certain geographic range. The result of gridding is a discretized information set, in which each grid unit corresponds to a fixed area in a two-dimensional space. In this case, square or rectangular grids are used for division, and hexagonal grids can also be selected according to needs. Before division, it is necessary to ensure that all geographic coordinates use a unified coordinate system (WGS84). The original data comes from multiple different coordinate systems and needs to be converted and projected. For the grid cells at the border of the map, a clipping algorithm is required to ensure that the grid is completely located in the target area to avoid blank data. According to the range of each grid cell, the geographic data covered by it is counted: count the number of charging piles belonging to a certain grid cell (count the number of charging piles); divide the number of charging piles by the grid area (calculate the density value); take the average value of continuous attributes such as ambient temperature in the grid (calculate the average value). For each geographic data point, determine the grid cell it is in, and assign relevant information to the corresponding unit. In this case, the point-in-polygon judgment algorithm (ray method) is used to quickly determine the grid to which the point belongs. Each grid cell can be represented as a data structure, and the final annotation result is a complete discretized distribution map that supports visualization and further analysis.

[0033] It should be noted that the setting of the grid size needs to balance accuracy and computational efficiency: smaller grids are suitable for fine-grained analysis, but the computational complexity is higher; larger grids are suitable for macro trend analysis, but local information is lost. The output of the discretized distribution map is a standardized map data structure or database, which can be expressed in the following forms: Visualization table: each grid cell is marked with a different color or symbol to intuitively present the distribution of charging piles; Data table: a detailed data table that records each grid cell and its attributes; GIS file: supports further analysis and processing through GIS software (Shapefile and GeoJSON format).

[0034] In step S14, the discretized distribution map is clustered to obtain sub-regions, including: In this embodiment, density clustering (DBSCAN) is used for clustering. Specifically, the coordinates and related features of the grid cells are extracted from the discretized distribution map as input data points: coordinate features: latitude and longitude or index coordinates (x, y) of each grid cell; density features: charging pile density value of each grid cell. According to the data distribution, set the parameters ε and MinPts. Use the k-distance graph method to calculate the distance from each point to its k nearest neighbors. In this case, take k=MinPts and draw a distance increase graph. Select the position where the distance increases sharply in the graph as ε. Set MinPts to twice the feature dimension, that is, MinPts=4. Then, execute the DBSCAN algorithm to cluster the data points. Mark all points as unvisited; for each point P, check the number of neighborhood points within the radius ε: if the number of neighborhood points ≥MinPts, it is marked as a core point; otherwise, it is marked as a boundary point or a noise point. Starting from the central core point, recursively expand the points in its neighborhood until no new core points can be found, and the expansion of a cluster is completed. Repeat the above process for all points until all points are processed, each data point is assigned to a cluster, and unassigned points are marked as noise points. Map the clustering results back to the discretized distribution map: assign a unique identification ID to each cluster (Cluster 1, Cluster 2), mark each grid unit as the cluster it belongs to, and mark the unassigned points as noise (Noise), and you can get the processed sub-area.

[0035] It should be noted that the output of clustering processing is a set of sub-regions, which contains the following information: Sub-region ID: the unique identifier of each sub-region; Region range: the set of grid cells or boundary coordinates contained in the sub-region; Regional features: the feature mean of each sub-region (charging station density, traffic flow). Density clustering (DBSCAN) divides densely populated areas into a cluster based on the density connection of data points, and classifies sparse areas as noise or independent points. It is suitable for scenarios with sparse and high-density areas, can identify sub-regions of any shape, and can handle noise points without specifying the number of clusters.

[0036] In step S15, characterization calculation is performed according to the environmental data and the sub-area to obtain characterization parameters, including: Extracting the environmental data in each sub-area to obtain the environmental temperature, environmental humidity and environmental illumination; Performing environmental calculation on the ambient temperature, the ambient humidity and the ambient light illumination in each of the sub-areas to obtain characterization parameters; The characterization parameters are calculated by the following formula, including:

[0037] in, is the characterization parameter, is the number of blocks, For the The ambient light intensity of each block, For the The ambient humidity of each block, For the The ambient temperature of each block.

[0038] It should be noted that in order to quantify the environmental characteristics of each sub-area, the extracted data is subjected to feature calculation to obtain comprehensive characterization parameters. These characterization parameters are defined by formulas, combining the environmental data of all grid cells in the sub-area to reflect the overall environmental conditions of the area. Characterization parameters are a single value that combines ambient light, humidity, and temperature to describe the environmental characteristics of the sub-area. This formula is calculated by dividing the number of blocks by , gives an average value, which helps to reduce the impact of extreme values ​​in a single block when comparing different regions or performing time series analysis.

[0039] In a specific example, assume that the city is divided into 5 blocks ( =5), the environmental data of each block is as follows: Block 1: Ambient Light Illumination =300lux; ambient humidity =45%; ambient temperature =22℃; Block 2: Ambient Light Illumination =350lux; ambient humidity =50%; ambient temperature =24℃; Block 3: Ambient Light Illumination =280lux; ambient humidity =40%; ambient temperature =20℃; Block 4: Ambient Light Illumination =320lux; ambient humidity =48%; ambient temperature =23℃; Block 5: Ambient Light Illumination =330lux; ambient humidity =47%; ambient temperature =21℃; Calculate the sum of each block: + + =300+45+22=367; + + =350+50+24=424; + + =280+40+20=340; + + =320+48+23=391; + + =330+47+21=398. Sum the sum of all blocks: 367 + 424 + 340 + 391 + 398 = 1920 Calculate the characterization parameters: =1920 / 5=384.

[0040] In this case, the characterization parameter c is 384, which means that after considering the average effects of ambient light, humidity, and temperature, the comprehensive environmental conditions of the five blocks can be represented by this single value. This value can be used for further analysis, such as comparing environmental conditions in different time periods or different areas, or for predicting the performance of charging piles under these conditions.

[0041] In step S16, a time series analysis is performed based on the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter, including: Performing exponential smoothing calculation according to the user data, the operation data, and the charging data to obtain a smoothed value; Performing feature calculation according to the smoothing value and the characterization parameter to obtain a first feature parameter; The smoothing value is calculated by the following formula:

[0042] The first characteristic parameter is calculated by the following formula, including:

[0043] in, For time The smoothing value of the node, is the first smoothing parameter, For time Charging voltage of charging pile, For time Charging pile operating voltage, For time The smoothing value of the node, For time The first characteristic parameter, is the second smoothing parameter, For time The horizontal component, is the characterization parameter.

[0044] It should be noted that the formula Combined with the current charging voltage and operating voltage , and the smoothed value of the previous moment , able to respond quickly to new voltage changes while maintaining a certain reliance on historical data to smooth short-term fluctuations. Allows to adjust the sensitivity to new data, when the parameter When the parameter is larger, the impact of new data on the smoothing value is more significant; when When it is smaller, the smoothed value is more dependent on historical data.

[0045] In a specific embodiment, =0.3, =0.4, =220V, =210V, =200, =205, c=190. Calculate the current smoothing value

[0046] Calculate the first characteristic parameter

[0047] In this case, the smoothed value is 134.5, which means that the voltage level of the charging pile has increased after considering the current charging voltage and operating voltage. The first characteristic parameter is 85.8, which shows that the performance index of the charging pile has improved after considering voltage changes and environmental factors.

[0048] In step S17, the first characteristic parameter is subjected to adaptive dynamic prediction processing to obtain a second characteristic parameter, including: The second characteristic parameter is calculated by the following formula, including:

[0049] in, For time The second characteristic parameter, is the first characteristic parameter versus time The partial guide, is the environmental factor, is the impact factor, for White noise at all times, For time The first characteristic parameter.

[0050] It should be noted that adaptive dynamic prediction means that the model will continuously adjust its parameters based on new data to improve the accuracy of the prediction. In the context of charging piles, this involves adjusting the value of the parameters based on real-time data (charging pile operating status, environmental conditions, etc.). Environmental coefficient Allows the model to take into account the impact of environmental factors on the performance of the charger. For example, extreme temperature or humidity can affect charging efficiency or the durability of the charger. Including a variety of factors, such as the frequency of use of the charging pile, maintenance records, user feedback, etc., these factors can help the model more accurately predict the performance changes of the charging pile. Represents the unpredictable random fluctuations in the model. In practical applications, this is caused by measurement errors, unconsidered external factors, etc. The second characteristic parameter Can be used to: By analyzing the second characteristic parameter The changing trend of can predict when the charging pile needs maintenance; according to the second characteristic parameter The prediction results can be used to adjust the charging strategy of the charging pile to improve efficiency or extend service life; by detecting the second characteristic parameter Abnormal fluctuations can be used to assess the risks in the operation of charging piles.

[0051] In step S18, a health prediction operation is performed according to the second characteristic parameter to obtain a prediction result, including: Calculating the health index according to the second characteristic parameter to obtain the health index; According to the health index, determine whether the health index is greater than a preset health threshold, and if so, output a charging pile operation abnormality result; if not, output a charging pile detection normal result; The health index is calculated by the following formula:

[0052] in, is the health index, is the charging pile compensation coefficient, is the weight coefficient, is the environmental data weight, For time The second characteristic parameter.

[0053] In a specific embodiment, assuming =1.2, =0.8, =0.7, =85.8. Calculate health index =60.02. Assuming the preset health threshold is 50, according to the calculated health index : if >50, then the abnormal operation result of the charging pile is output; if ≤50, the output charging pile detection is normal. In this case, =60.02>50, it can be judged that there is an abnormality in the charging pile, and the abnormal result of the charging pile detection is output.

[0054] It should be noted that the charging pile compensation coefficient This allows the health index to be adjusted based on the specific situation of the charger. For example, if a charger is known to have a slight performance degradation, the charger compensation factor can be increased. The value of reflects this. Used to give different weights to different performance indicators when calculating the health index, which helps the system more accurately reflect the overall health of the charging pile. Environmental data weights The impact of environmental factors on the health of charging piles is taken into account. For example, in extreme weather conditions, charging piles are more likely to fail. The value should be adjusted accordingly.

[0055] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1Schematic diagram of the working scenario of the method.

[0056] In smart cities, the popularity of electric vehicles has led to a continuous increase in the number of charging piles. However, due to the wide geographical distribution of charging piles, their operating states vary due to environmental factors and usage intensity. In order to improve the operating efficiency of charging piles and reduce downtime caused by equipment failures, it is necessary to introduce an intelligent detection method to predict and optimize the health status of charging piles. Through the method of the present invention, data collection, regional analysis, environmental feature extraction and health prediction are performed on a group of charging piles in a certain area of ​​the city to achieve comprehensive monitoring and intelligent management of the status of charging piles and improve the detection accuracy of charging piles.

[0057] First, collect user charging habits through mobile applications, such as charging time, frequency and preferred charging piles; obtain information such as operating time and fault records from the charging pile logs; monitor the current, voltage and other parameters of each charging pile in real time; use the built-in GPS module to obtain the precise geographic location of each charging pile; sensors installed near the charging piles collect information such as ambient temperature, humidity, and light intensity.

[0058] Extract the coordinate information of each charging pile from the geographic data, assign a unique number to each charging pile, and generate a regional distribution map. Grid the regional distribution map to obtain a discretized distribution map. Apply the density clustering algorithm (DBSCAN) clustering to the discretized distribution map, and use the density and usage frequency of charging piles in the grid as input features to divide it into high-density sub-areas and low-density sub-areas, while marking areas with low or abnormal usage. The system generates several sub-areas and numbers each sub-area. Identify the sub-areas of charging piles, such as commercial areas, residential areas, industrial areas, etc. Extract environmental data on each sub-area and calculate the characterization parameters.

[0059] Integrate user data, operation data, charging data, and characterization parameters to form a time series data set. Use a time series model (such as ARIMA or LSTM) to predict usage trends and operation status within a certain period of time in the future. According to the first characteristic parameter, adjust the weight and parameters of the prediction model to optimize the prediction results. Output the second characteristic parameter to generate key indicators including operation status and health assessment. Calculate the health index based on the second characteristic parameter. Compare the health index with the preset threshold to determine the health status of the charging pile. If the health index is lower than the set threshold, trigger an early warning.

[0060] In summary, the present invention discloses a detection method for a charging pile, including obtaining user data, operation data, charging data, geographic data and environmental data of the charging pile; performing information preprocessing on the geographic data to obtain a regional distribution map of the charging pile; performing discretization processing on the regional distribution map to obtain a discretized distribution map; performing clustering processing on the discretized distribution map to obtain a sub-region; performing characterization calculation based on the environmental data and the sub-region to obtain a characterization parameter; performing time series analysis based on the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter; performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; performing a health prediction operation based on the second characteristic parameter to obtain a prediction result. The present invention can improve detection accuracy by considering environmental factors.

[0061] Reference Figure 2 The second embodiment of the present invention provides a detection system for a charging pile, comprising: A data acquisition module is used to acquire user data, operation data, charging data, geographic data and environmental data of the charging pile; An information processing module performs information preprocessing on the geographic data to obtain a regional distribution map of charging piles; A regional discretization module discretizes the regional distribution map to obtain a discretized distribution map; A clustering processing module performs clustering processing on the discretized distribution map to obtain sub-regions; A characterization calculation module, performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; a feature calculation module, performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first feature parameter; A dynamic prediction module performs adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; The result output module performs a health prediction operation according to the second characteristic parameter to obtain a prediction result.

[0062] Preferably, the information processing module is specifically used to perform information preprocessing on the geographic data to obtain a regional distribution map of charging piles, including: Extracting coordinates according to the geographic data to obtain coordinate information; According to the coordinate information, numbering processing is performed to obtain a regional distribution map.

[0063] Preferably, the region discretization module is specifically used to discretize the region distribution map to obtain a discretized distribution map, including: According to the regional distribution map, coordinate gridding processing is performed to obtain discretization information; An information labeling operation is performed according to the discretized information to obtain a discretized distribution map.

[0064] Preferably, the characterization calculation module is specifically used to perform characterization calculation according to the environmental data and the sub-area to obtain characterization parameters, including: Extracting the environmental data in each sub-area to obtain the environmental temperature, environmental humidity and environmental illumination; Performing environmental calculation on the ambient temperature, the ambient humidity and the ambient light illumination in each of the sub-areas to obtain characterization parameters; The characterization parameters are calculated by the following formula, including:

[0065] in, is the characterization parameter, is the number of blocks, For the The ambient light intensity of each block, For the The ambient humidity of each block, For the The ambient temperature of each block.

[0066] Preferably, the feature calculation module is specifically used to perform time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain the first feature parameter, including: Performing exponential smoothing calculation according to the user data, the operation data, and the charging data to obtain a smoothed value; Performing feature calculation according to the smoothing value and the characterization parameter to obtain a first feature parameter; The smoothing value is calculated by the following formula:

[0067] The first characteristic parameter is calculated by the following formula, including:

[0068] in, For time The smoothing value of the node, is the first smoothing parameter, For time Charging voltage of charging pile, For time Charging pile operating voltage, For time The smoothing value of the node, For time The first characteristic parameter, is the second smoothing parameter, For time The horizontal component, is the characterization parameter.

[0069] Preferably, the dynamic prediction module is specifically used to perform adaptive dynamic prediction processing on the first characteristic parameter to obtain the second characteristic parameter, including: The second characteristic parameter is calculated by the following formula, including:

[0070] in, For time The second characteristic parameter, is the first characteristic parameter versus time The partial guide, is the environmental factor, is the impact factor, for White noise at all times, For time The first characteristic parameter.

[0071] Preferably, the result output module is specifically used to perform a health prediction operation according to the second characteristic parameter to obtain a prediction result, including: Calculating the health index according to the second characteristic parameter to obtain the health index; According to the health index, determine whether the health index is greater than a preset health threshold, and if so, output a charging pile operation abnormality result; if not, output a charging pile detection normal result; The health index is calculated by the following formula:

[0072] in, is the health index, is the charging pile compensation coefficient, is the weight coefficient, is the environmental data weight, For time The second characteristic parameter.

[0073] It should be noted that a charging pile detection system provided in an embodiment of the present invention is used to execute all process steps of a charging pile detection method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0074] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above-mentioned detection method of each charging pile are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0075] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0076] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0077] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0078] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0079] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0080] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0081] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting a charging pile, characterized in that: include: Obtain user data, operation data, charging data, geographic data and environmental data of charging piles; The geographic data is preprocessed to obtain a regional distribution map of charging piles; Discretizing the regional distribution map to obtain a discretized distribution map; Performing clustering processing on the discretized distribution map to obtain sub-regions; Performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; Performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first characteristic parameter; Performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; According to the second characteristic parameter, a health prediction operation is performed to obtain a prediction result.

2. The detection method of the charging pile according to claim 1, characterized in that: The step of preprocessing the geographic data to obtain a regional distribution map of charging piles includes: Extracting coordinates according to the geographic data to obtain coordinate information; According to the coordinate information, numbering processing is performed to obtain a regional distribution map.

3. The detection method of the charging pile according to claim 1, characterized in that: The discretization process of the regional distribution map to obtain a discretized distribution map includes: According to the regional distribution map, coordinate gridding processing is performed to obtain discretization information; According to the discretized information, an information labeling operation is performed to obtain a discretized distribution map.

4. The detection method of the charging pile according to claim 1, characterized in that: The performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters includes: Extracting the environmental data in each sub-area to obtain the environmental temperature, environmental humidity and environmental illumination; Performing environmental calculation on the ambient temperature, the ambient humidity and the ambient light illumination in each of the sub-areas to obtain characterization parameters; The characterization parameters are calculated by the following formula, including: in, is the characterization parameter, is the number of blocks, For the The ambient light intensity of each block, For the The ambient humidity of each block, For the The ambient temperature of each block.

5. The detection method of the charging pile according to claim 1, characterized in that: The performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain the first characteristic parameter includes: Performing exponential smoothing calculation according to the user data, the operation data, and the charging data to obtain a smoothed value; Performing feature calculation according to the smoothing value and the characterization parameter to obtain a first feature parameter; The smoothing value is calculated by the following formula: The first characteristic parameter is calculated by the following formula, including: in, For time The smoothing value of the node, is the first smoothing parameter, For time Charging voltage of charging pile, For time Charging pile operating voltage, For time The smoothing value of the node, For time The first characteristic parameter, is the second smoothing parameter, For time The horizontal component, is the characterization parameter.

6. The detection method of the charging pile according to claim 2, characterized in that: The step of performing adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter includes: The second characteristic parameter is calculated by the following formula, including: in, For time The second characteristic parameter, is the first characteristic parameter versus time The partial guide, is the environmental factor, is the impact factor, for White noise at all times, For time The first characteristic parameter.

7. The detection method of the charging pile according to claim 1, characterized in that: The step of performing a health prediction operation according to the second characteristic parameter to obtain a prediction result includes: Calculating the health index according to the second characteristic parameter to obtain the health index; According to the health index, determine whether the health index is greater than a preset health threshold, and if so, output a charging pile operation abnormality result; if not, output a charging pile detection normal result; The health index is calculated by the following formula: in, is the health index, is the charging pile compensation coefficient, is the weight coefficient, is the environmental data weight, For time The second characteristic parameter.

8. A charging pile detection system, characterized in that: include: A data acquisition module is used to acquire user data, operation data, charging data, geographic data and environmental data of the charging pile; An information processing module performs information preprocessing on the geographic data to obtain a regional distribution map of charging piles; A regional discretization module discretizes the regional distribution map to obtain a discretized distribution map; A clustering processing module performs clustering processing on the discretized distribution map to obtain sub-regions; A characterization calculation module, performing characterization calculation according to the environmental data and the sub-area to obtain characterization parameters; a feature calculation module, performing time series analysis according to the user data, the operation data, the charging data and the characterization parameter to obtain a first feature parameter; A dynamic prediction module performs adaptive dynamic prediction processing on the first characteristic parameter to obtain a second characteristic parameter; The result output module performs a health prediction operation according to the second characteristic parameter to obtain a prediction result.

9. A charging pile, characterized in that: Used to communicate with the detection system of the charging pile as claimed in claim 8, and send the user data, operation data, charging data, geographic data and environmental data of the charging pile to the detection system of the charging pile.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the charging pile detection method according to any one of claims 1 to 7.

Images