CN116821620A - Data analysis method based on electric bicycle charging pile - Google Patents
Data analysis method based on electric bicycle charging pile Download PDFInfo
- Publication number
- CN116821620A CN116821620A CN202310768154.4A CN202310768154A CN116821620A CN 116821620 A CN116821620 A CN 116821620A CN 202310768154 A CN202310768154 A CN 202310768154A CN 116821620 A CN116821620 A CN 116821620A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- charging pile
- electric bicycle
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000006870 function Effects 0.000 claims description 45
- 230000002159 abnormal effect Effects 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 39
- 238000004458 analytical method Methods 0.000 claims description 27
- 238000007418 data mining Methods 0.000 claims description 26
- 230000004927 fusion Effects 0.000 claims description 21
- 238000003032 molecular docking Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 125000004122 cyclic group Chemical group 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 13
- 230000008030 elimination Effects 0.000 claims description 10
- 238000003379 elimination reaction Methods 0.000 claims description 10
- 230000010354 integration Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- RKMGAJGJIURJSJ-UHFFFAOYSA-N 2,2,6,6-Tetramethylpiperidine Substances CC1(C)CCCC(C)(C)N1 RKMGAJGJIURJSJ-UHFFFAOYSA-N 0.000 claims description 6
- RINRSJBJOGCGBE-UHFFFAOYSA-N 3,3,5,6-tetramethyl-2h-pyrazine Chemical compound CC1=NCC(C)(C)N=C1C RINRSJBJOGCGBE-UHFFFAOYSA-N 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 230000003750 conditioning effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 230000010365 information processing Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
Abstract
The invention discloses a data analysis method based on electric bicycle charging piles, which relates to the technical field of data information processing and solves the problems of low intelligent degree and high damage probability of the existing charging piles.
Description
Technical Field
The invention relates to the field of data information processing, in particular to a data analysis method based on an electric bicycle charging pile.
Background
With the rapid development of social economy, urban areas are continuously enlarged, however, the traveling time of residents is greatly prolonged due to the speed of enlarging the urban areas, and traveling by taking the electric bicycle is the first choice of traveling and commuting modes of vast residents for facilitating traveling and reducing the time of taking public transportation means.
The electric bicycle charging pile is equipment for providing a charging facility for an electric bicycle, and mainly aims to provide charging service for the electric bicycle, so that a user can charge the electric bicycle conveniently during riding. Some features and configurations of the electric bicycle charging post include, for example, configuration of charging port and socket, charging power and current, charging mode, etc.: the electric bicycle charging pile should have a suitable charging mode, such as manual charging, automatic charging, remote monitoring, etc. These methods have difficulty in processing data information during operation, for example, when various problems such as charge amount, detection of charging line, fire abnormality, and data information alarm occur. The design and configuration of the electric bicycle charging stake should consider user's needs and service environment to improve charging efficiency and user experience.
In the actual operation process, the problems of messy parking of vehicles, lack of charging facilities and the like are also caused, electric bicycle charging piles are forcefully put in each city for solving the problems, residents scan two-dimensional codes on the charging piles by using mobile phones, charging time is selected, the vehicles are stopped at specified positions, the charging process is convenient, in the charging process, the residents can check the charging condition at any time through mobile phone app, after charging is finished, the two-dimensional code is scanned to click to finish charging, a cross rod automatically falls down, the common electric bicycle charging piles have single function, the intelligent degree is low, the damage probability is high, data intercommunication among different charging piles cannot be carried out, a series of problems such as position prejudgment of the adjacent position optimal charging piles cannot be made, the prior art has lag data information processing and analyzing capability, the data information analysis efficiency is poor, and timely analysis on the data of the electric bicycle charging piles is difficult.
Therefore, aiming at the defects of the charging pile, the intelligent degree of the charging pile is improved by a data analysis method based on the charging pile of the electric bicycle, so that the use sense of the charging pile is improved, and the data analysis capability of the charging pile of the electric bicycle is improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses a data analysis method based on an electric bicycle charging pile, which realizes the remote storage and backup of data by adopting a plurality of wireless scanning monitoring units to perform data fusion on a network level, adopts a characteristic tag analysis model to extract characteristic tags to improve the automation degree and reduce the abnormal probability, adopts a cross-platform streaming media protocol HTMP to accelerate the bidirectional transmission speed of the data, adopts a dynamic factor optimizing model to realize accurate data mining and filter abnormal waveform interference in the data mining process, adopts a clustering fusion template to analyze and fuse feedback data, and greatly improves the data information analysis capability.
The invention adopts the following technical scheme:
a data analysis method based on electric bicycle charging piles comprises the following steps:
step one, acquiring electric bicycle charging pile data, namely acquiring service life of a charging pile by arranging a wireless scanning monitoring module at the front side of the electric bicycle charging pile, wherein the wireless scanning monitoring module comprises an RFID radio frequency identification unit, a two-dimensional code collection unit and a WiFi camera unit;
step two, preprocessing the collected data, filtering, integrating and cleaning the collected electric bicycle charging pile data through a data cleaning module to screen incomplete data, abnormal data, invalid data and redundant data so as to achieve availability and effectiveness of the data, normalizing and normalizing the electric bicycle charging pile data through an integration extraction module, extracting characteristic values of the electric bicycle charging pile data through a characteristic mining model through the integration extraction module, and classifying and blocking the electric bicycle charging pile data according to the characteristic values so as to facilitate data analysis and processing in the next step;
analyzing and processing bicycle charging pile data, performing feature analysis and statistics processing on the preprocessed information through a data analysis and processing module, wherein the data analysis and processing module comprises a source data acquisition unit, a data attribute classification unit, a data feature analysis unit, a data statistics processing unit and a data docking unit, the source data acquisition unit is used for acquiring address information of data to be processed and source data containing features, the data attribute classification unit is used for dividing the data to be processed into attribute data blocks according to attribute vectors, the data feature analysis unit is used for extracting feature vectors of the attribute data blocks and analyzing feature tag codes, the data statistics processing unit is used for statistically sorting dynamic structures of the data blocks, and the data docking unit is used for transmitting the dynamic structures of the data blocks to a backup management cloud server and performing charging pile large data analysis through a charging pile database management platform;
the output end of the source data acquisition unit is connected with the input end of the data attribute classification unit, the output end of the data attribute classification unit is connected with the input end of the data characteristic analysis unit, the output end of the data characteristic analysis unit is connected with the input end of the data statistics processing unit, and the output end of the data statistics processing unit is connected with the input end of the data docking unit;
the data docking unit of the data analysis and processing module is used for transmitting the dynamic structure of the data block to the big data analysis and comparison module, the big data analysis and comparison module comprises a big data importing unit, a big data summarizing unit, a big data mining unit and a big data real-time prediction unit, the big data importing unit is used for storing data acquired by the front end of the big data analysis and comparison module in a distributed mode, the big data summarizing unit is used for carrying out cluster deployment operation on the data in the distributed memory and summarizing operation results, the big data mining unit is used for mining real-time position data and state data of electric bicycle charging piles in a database, the big data real-time prediction unit predicts the positions of fault charging piles and the positions of optimal charging piles according to distance, time and working states, and returns predicted values to an automatic updating feedback port, and automatically updates the feedback data every 30 seconds and transmits the feedback data to a user side on-line management platform;
the output end of the big data importing unit is connected with the input end of the big data summarizing unit, the output end of the big data importing unit is connected with the input end of the big data mining unit, and the output end of the big data mining unit is connected with the input end of the big data real-time prediction unit;
generating a record form log, and generating an electric bicycle charging pile data log by using the data block dynamic structure output by the data analysis and processing module and the feedback data output by the big data analysis and comparison module through the form log generating module, wherein the electric bicycle charging pile data log comprises a charging pile working state, a charging pile fault condition, an idle charging pile distribution condition and an area electric bicycle real-time density.
As a further technical scheme of the invention, the RFID radio frequency identification unit, the two-dimensional code collection unit and the WiFi camera unit realize the fusion of collected data on a network platform through a multi-terminal wireless intercommunication interface, and the fused data set realizes the remote storage and backup on different electric bicycle charging pile devices through a topological network.
As a further technical scheme of the invention, the data feature analysis unit adopts an independent feature tag analysis model to extract feature tags, and a feature tag output formula is as follows:
（1）
in the case of the formula (1),output function for feature tag, +.>Integration parameters for the first feature, < >>For the independent condition of feature density +.>For independent densitometric dimensions, < >>Compensating correction value for error->Is an redundancy prevention parameter;
if abnormal reporting errors occur in the characteristic label extraction process, screening out abnormal values of the characteristic labels through a characteristic label abnormal reporting error model and outputting the abnormal values, wherein the output formula of the abnormal values of the characteristic labels is as follows:
（2）
in the formula (2) of the present invention,output function for characteristic tag outlier, +.>Is maximum abnormality threshold->For outlier diagnostic function, ++>For outlier address width, +.>For outlier node depth, ++>For the number of outlier symbol outlier total +.>For counting total element number, +.>As a statistical element, < > for>Is a noise feedback value->Is the noise amplitude.
As a further technical scheme of the invention, the big data real-time prediction unit collects relevant parameters of the electric bicycle charging pile forming a prediction information set, integrates the parameters and establishes a prediction model based on time propulsion, and a user verifies and evaluates the availability and accuracy of the prediction model through a simulation experiment and outputs a prediction result to an automatic updating feedback port.
As a further technical scheme of the invention, the big data analysis and comparison module divides feedback data into data segment slices by using a cross-platform streaming media protocol HTMP, and the data segment slices realize the transmission operation of the big data analysis and comparison module to the user side on-line management platform by adopting IP address and content data double encapsulation after the user side on-line management platform and the big data analysis and comparison module finish the server link docking operation.
As a further technical scheme of the invention, the big data mining unit adopts a dynamic factor optimizing model to realize accurate data mining and filter abnormal waveform interference in the data mining process, and an output formula of the dynamic factor optimizing model is as follows:（3）
in the formula (3) of the present invention,outputting a function for the dynamic factor optimizing model, +.>For optimizing the threshold control function->Adjusting the model output function for the waveform, +.>Is a transversely extending domain->Is a longitudinally extending domain->Is a lateral extension domain->The longitudinal extension domain is->Waveform adjusting function at time +_>For dynamic factor lateral range, +.>For dynamic factor longitudinal range, +.>For waveform conditioning function>For waveform phase parameter, y is adjacent optimizing domain difference parameter, ++>For abnormal waveform elimination constant, < >>Adjusting auxiliary parameters for the abnormal waveform; in the optimizing process, the dynamic factor optimizing model continuously performs adjacent two groups of optimizing effect comparison to obtain an optimal path, and a path comparison output formula is as follows:
（4）
in the formula (4) of the present invention,for the path contrast output function, +.>For the path variable +.>For the path update function,for the path state comparison function, +.>For the path passing time, +.>For the path traversal range, ++>For the time span parameter>Is a range span parameter; the dynamic factor optimizing model is provided with a delay auxiliary elimination plate to eliminate time delay in the optimizing process, and the delay elimination output formula is as follows:
（5）
in the formula (5) of the present invention,to delay the cancellation output function, +.>For delay factor, ++>For optimizing dimension, < >>For delay class parameter, ++>Is a delay diagnostic function.
As a further technical scheme of the present invention, the table Shan Rizhi generating module analyzes and fuses the feedback data through a cluster fusion template, and the cluster fusion output formula is as follows:
（6）
in the formula (6) of the present invention,for clustering fusion output function, +.>For template period parameter, +.>For the total dimension of the template cycle period,/->For the period time fill constant,/-, for>For the abnormal parameters of the mode>For the pattern similarity parameter, +.>Is an auxiliary feedback constant; after the analyzing and fusing steps are completed, carrying out cyclic updating processing on the output result, wherein a cyclic updating formula is as follows:
（7）
in the formula (7) of the present invention,for cyclic updating functions, ++>For updating the time parameter->A parameter is predicted for the number of elements,for dynamic adjustment of parameters->Supplement parameters for dynamic difference->For the total number of cycles, +.>For the circulation interval +.>Is a ladder-type redundancy preventing parameter->Is a linear auxiliary parameter.
Has the positive beneficial effects that:
the invention discloses a data analysis method based on an electric bicycle charging pile, which adopts a plurality of wireless scanning monitoring units to realize data fusion at a network level to realize data remote storage and backup, adopts a characteristic tag analysis model to extract characteristic tags to improve the automation degree and reduce the abnormal probability, adopts a cross-platform streaming media protocol HTMP to accelerate the data bidirectional transmission speed, adopts a dynamic factor optimizing model to realize accurate data mining and filter abnormal waveform interference in the data mining process, and adopts a clustering fusion template to analyze and fuse feedback data.
Drawings
Fig. 1 is a schematic diagram of an overall architecture of a data analysis method based on an electric bicycle charging pile according to the present invention;
fig. 2 is a schematic diagram of a method for extracting feature labels of a data analysis method based on an electric bicycle charging pile;
FIG. 3 is a flowchart of the prediction operation of the big data real-time prediction unit of the data analysis method based on the electric bicycle charging pile;
FIG. 4 is a schematic flow chart of a dynamic factor optimizing model of a big data mining unit of the data analysis method based on the electric bicycle charging pile;
fig. 5 is a schematic diagram of a cluster fusion template workflow of a data analysis method form log generation module based on an electric bicycle charging pile.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a data analysis method based on an electric bicycle charging pile comprises the following steps:
step one, acquiring electric bicycle charging pile data, namely acquiring service life of a charging pile by arranging a wireless scanning monitoring module at the front side of the electric bicycle charging pile, wherein the wireless scanning monitoring module comprises an RFID radio frequency identification unit, a two-dimensional code collection unit and a WiFi camera unit;
step two, preprocessing the collected data, filtering, integrating and cleaning the collected electric bicycle charging pile data through a data cleaning module to screen incomplete data, abnormal data, invalid data and redundant data so as to achieve availability and effectiveness of the data, normalizing and normalizing the electric bicycle charging pile data through an integration extraction module, extracting characteristic values of the electric bicycle charging pile data through a characteristic mining model through the integration extraction module, and classifying and blocking the electric bicycle charging pile data according to the characteristic values so as to facilitate data analysis and processing in the next step;
analyzing and processing bicycle charging pile data, performing feature analysis and statistics processing on the preprocessed information through a data analysis and processing module, wherein the data analysis and processing module comprises a source data acquisition unit, a data attribute classification unit, a data feature analysis unit, a data statistics processing unit and a data docking unit, the source data acquisition unit is used for acquiring address information of data to be processed and source data containing features, the data attribute classification unit is used for dividing the data to be processed into attribute data blocks according to attribute vectors, the data feature analysis unit is used for extracting feature vectors of the attribute data blocks and analyzing feature tag codes, the data statistics processing unit is used for statistically sorting dynamic structures of the data blocks, and the data docking unit is used for transmitting the dynamic structures of the data blocks to a backup management cloud server and performing charging pile large data analysis through a charging pile database management platform;
the output end of the source data acquisition unit is connected with the input end of the data attribute classification unit, the output end of the data attribute classification unit is connected with the input end of the data characteristic analysis unit, the output end of the data characteristic analysis unit is connected with the input end of the data statistics processing unit, and the output end of the data statistics processing unit is connected with the input end of the data docking unit;
the data docking unit of the data analysis and processing module is used for transmitting the dynamic structure of the data block to the big data analysis and comparison module, the big data analysis and comparison module comprises a big data importing unit, a big data summarizing unit, a big data mining unit and a big data real-time prediction unit, the big data importing unit is used for storing data acquired by the front end of the big data analysis and comparison module in a distributed mode, the big data summarizing unit is used for carrying out cluster deployment operation on the data in the distributed memory and summarizing operation results, the big data mining unit is used for mining real-time position data and state data of electric bicycle charging piles in a database, the big data real-time prediction unit predicts the positions of fault charging piles and the positions of optimal charging piles according to distance, time and working states, and returns predicted values to an automatic updating feedback port, and automatically updates the feedback data every 30 seconds and transmits the feedback data to a user side on-line management platform;
the output end of the big data importing unit is connected with the input end of the big data summarizing unit, the output end of the big data importing unit is connected with the input end of the big data mining unit, and the output end of the big data mining unit is connected with the input end of the big data real-time prediction unit;
generating a record form log, and generating an electric bicycle charging pile data log by using the data block dynamic structure output by the data analysis and processing module and the feedback data output by the big data analysis and comparison module through the form log generating module, wherein the electric bicycle charging pile data log comprises a charging pile working state, a charging pile fault condition, an idle charging pile distribution condition and an area electric bicycle real-time density.
In the above embodiment, the RFID radio frequency identification unit, the two-dimensional code collection unit and the WiFi camera unit realize the fusion of the collected data on the network platform through the multi-terminal wireless intercommunication interface, and the fused data set realizes the remote storage and backup on different electric bicycle charging pile devices through the topology network.
In a specific embodiment, after an electronic tag on an electric bicycle enters a reader through a recognizer, a radio frequency signal sent by the reader is received, electric bicycle product information stored in a chip and a signal with a certain frequency are sent out by the tag through energy obtained by induction current, the reader reads the information and decodes the information and sends the information to a central information system for relevant data processing, the central information system accesses the processed information from a wireless broadband cluster terminal through a multi-terminal wireless intercommunication interface, a control instruction of the cluster terminal directs data to be fused on a network platform, a remote storage and backup tool of the cluster terminal firstly backs up the acquired data to a cloud platform through an Ethernet, and then the acquired data is stored in a data storage module of 5 adjacent electric bicycle charging piles in a multi-link transmission mode, so that subsequent large data analysis operation is facilitated.
As shown in fig. 2, in the above embodiment, the data feature analysis unit extracts a feature tag by using an independent feature tag analysis model, and the feature tag output formula is as follows:
（1）
in the case of the formula (1),output function for feature tag, +.>Integration parameters for the first feature, < >>For the independent condition of feature density +.>For independent densitometric dimensions, < >>Compensating correction value for error->Is an redundancy prevention parameter;
if abnormal reporting errors occur in the characteristic label extraction process, screening out abnormal values of the characteristic labels through a characteristic label abnormal reporting error model and outputting the abnormal values, wherein the output formula of the abnormal values of the characteristic labels is as follows:
（2）
in the formula (2) of the present invention,output function for characteristic tag outlier, +.>Is maximum abnormality threshold->For outlier diagnostic function, ++>For outlier address width, +.>For outlier node depth, ++>For the number of outlier symbol outlier total +.>For counting total element number, +.>As a statistical element, < > for>Is a noise feedback value->Is the noise amplitude.
In a specific embodiment, a candidate feature subset is generated first, a heuristic search method is used, when each iteration search is performed, whether the rest feature subset is accepted is determined according to a heuristic principle, after the feature subset is generated, the feature subset is subjected to quality evaluation through a filtering verification method, feature labels are generated after the feature subset is evaluated, abnormal error reporting occurs in the feature label generating process, when the abnormal error reporting occurs, feature label abnormal error reporting models through machine deep learning are used for screening and outputting feature label abnormal values, and compared with the existing feature extraction method, namely a feature extraction model based on a transmission image, the feature label analysis model has the advantages of being high in automation degree and low in abnormal probability, and feature extraction results of the two models can be clearly seen through a table 1.
Table 1 comparison of the feature extraction results of the two models
As shown in fig. 3, in the above embodiment, the big data real-time prediction unit collects relevant parameters of the electric bicycle charging pile forming the prediction information set, integrates the parameters and establishes a prediction model based on time advance, and the user verifies and evaluates the availability and accuracy of the prediction model through simulation experiments and outputs the prediction result to the automatic update feedback port.
In a specific embodiment, the big data real-time prediction unit performs a prediction operation, including the following steps:
firstly, determining a predicted target, wherein the predicted target data comprise the damage degree of the electric bicycle charging pile, the brand distribution condition of the electric bicycle and the regional use condition data of the electric bicycle;
selecting a prediction method, adopting a path prediction method based on the minimum time of a transmission path and performing prediction preparation work;
thirdly, establishing a prediction model, integrating the predicted target data parameters into a data packet and establishing a prediction model based on time propulsion;
(IV) evaluating the stability of the prediction model and performing prediction operation, randomly dividing the training set into n different subsets through cross validation, wherein each subset is called a fold, then performing m times of training and evaluation on the model, selecting 1 fold for evaluation, and m-1 folds for training, and finally evaluating the model through the average value and the standard deviation of the m times of evaluation errors and using model prediction;
and fifthly, analyzing and outputting the prediction result, generating a prediction form by the prediction result through a form generation instruction, and transmitting the form to an automatic updating feedback port.
In the above embodiment, the big data analysis and comparison module uses the cross-platform streaming media protocol HTMP to split the feedback data into data segment slices, and the data segment slices implement the transmission operation of the big data analysis and comparison module to the client on-line management platform by adopting the IP address and content data dual-encapsulation after the client on-line management platform and the big data analysis and comparison module complete the server link docking operation.
In a specific embodiment, the working principle of the HTMP protocol is divided into the following steps, firstly, the electric bicycle charging pile client establishes a TCP streaming media link connection with the server, in the connection process, both ports confirm the protocol version number and exchange shaft transmission random number information through a handshake process, after the handshake is completed, the electric bicycle charging pile client sends a connection command to the server, the server input end receives the connection command and responds to the connection command, the return module generates a return connection result, after the connection result is returned, the electric bicycle charging pile client establishes a data streaming link with the server to transmit audio and video data, in the transmission process, both sides can send link control commands to realize control of a transmission link and an operation mode, such as backup, start, stop, permanent closing, dormancy, transmission speed visualization display and replacement instructions, and when the connection between the electric bicycle charging pile client and the server is closed, both sides end message transmission and disconnect.
As shown in fig. 4, in the foregoing embodiment, the big data mining unit uses a dynamic factor optimizing model to implement accurate data mining and filter abnormal waveform interference in the data mining process, where an output formula of the dynamic factor optimizing model is as follows:
（3）
in the formula (3) of the present invention,outputting a function for the dynamic factor optimizing model, +.>For optimizing the threshold control function->Adjusting the model output function for the waveform, +.>Is a transversely extending domain->Is a longitudinally extending domain->Is a lateral extension domain->The longitudinal extension domain is->Waveform adjusting function at time +_>For dynamic factor lateral range, +.>For dynamic factor longitudinal range, +.>For waveform conditioning function>For waveform phase parameter, y is adjacent optimizing domain difference parameter, ++>For abnormal waveform elimination constant, < >>Adjusting auxiliary parameters for the abnormal waveform; in the optimizing process, the dynamic factor optimizing model continuously performs adjacent two groups of optimizing effect comparison to obtain an optimal path, and a path comparison output formula is as follows:
（4）
in the formula (4) of the present invention,for the path contrast output function, +.>For the path variable +.>For the path update function,for the path state comparison function, +.>For the path passing time, +.>For the path traversal range, ++>For the time span parameter>Is a range span parameter; the dynamic factor optimizing model is provided with a delay auxiliary elimination plate to eliminate time delay in the optimizing process, and the delay elimination output formula is as follows: />（5）
In the formula (5) of the present invention,to delay the cancellation output function, +.>For delay factor, ++>For optimizing dimension, < >>For delay class parameter, ++>Is a delay diagnostic function.
In a specific embodiment, a dynamic factor optimizing model is optimized based on a graph neural network deep learning method, a traditional optimizing model can only conduct non-real-time limited dynamic optimizing on data information with linear correlation, the limitation of the traditional optimizing model is broken through by adopting the dynamic factor optimizing model, two groups of adjacent optimizing are conducted on the dynamic factor optimizing model in a circulating mode through deep dynamic optimizing and optimal solution prediction, optimizing results are compared in a eliminating match mode to obtain an optimal path, a time calibration unit is included in the dynamic factor optimizing model, delay detection is conducted once after each optimizing, if delay is found, delay is neutralized by using a delay elimination function, and optimizing effect comparison of the dynamic factor optimizing model and the traditional optimizing model can be clearly shown through a table 2.
Table 2 comparison of the optimizing effect of two kinds of optimizing models
As shown in fig. 5, in the foregoing embodiment, the table Shan Rizhi generating module parses and fuses the feedback data through a cluster fusion template, where a cluster fusion output formula is:（6）
in the formula (6) of the present invention,for clustering fusion output function, +.>For template period parameter, +.>For the total dimension of the template cycle period,/->For the period time fill constant,/-, for>For the abnormal parameters of the mode>For the pattern similarity parameter, +.>Is an auxiliary feedback constant; after the analyzing and fusing steps are completed, carrying out cyclic updating processing on the output result, wherein a cyclic updating formula is as follows:
（7）
in the formula (7) of the present invention,for cyclic updating functions, ++>For updating the time parameter->A parameter is predicted for the number of elements,for dynamic adjustment of parameters->Supplement parameters for dynamic difference->For the total number of cycles, +.>For the circulation interval +.>Is a ladder-type redundancy preventing parameter->Is a linear auxiliary parameter.
In a specific embodiment, a member group to be clustered is generated firstly, an initial point of each member group is randomly generated by a random function, randomness is high, complexity is low, an abnormal reference template is set for the clustered member group, each reference template comprises an abnormal time parameter and a mode abnormal warning, when the condition that the fusion time is too long or too short occurs in the clustering fusion process, the mode abnormal warning sends alarm data to an output end of a form log generation module, the fusion time is set by a user, cyclic update processing is carried out on an output result after each fusion step is finished, namely, cluster fusion is continued until the charging process of an electric bicycle is finished completely, in the cyclic update process, in order to prevent data redundancy in the cyclic process, the form generation speed is reduced, a step type redundancy preventing parameter is added in a cyclic update formula, and the step type redundancy preventing parameter enables the width of each cycle not to exceed the width of the last cycle, and redundancy is prevented.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the method and details of the methods described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (7)
1. A data analysis method based on electric bicycle charging piles is characterized in that: the method comprises the following steps:
step one, acquiring electric bicycle charging pile data, namely acquiring service life of a charging pile by arranging a wireless scanning monitoring module at the front side of the electric bicycle charging pile, wherein the wireless scanning monitoring module comprises an RFID radio frequency identification unit, a two-dimensional code collection unit and a WiFi camera unit;
step two, preprocessing the collected data, filtering, integrating and cleaning the collected electric bicycle charging pile data through a data cleaning module to screen incomplete data, abnormal data, invalid data and redundant data so as to achieve availability and effectiveness of the data, normalizing and normalizing the electric bicycle charging pile data through an integration extraction module, extracting characteristic values of the electric bicycle charging pile data through a characteristic mining model through the integration extraction module, and classifying and blocking the electric bicycle charging pile data according to the characteristic values so as to facilitate data analysis and processing in the next step;
analyzing and processing bicycle charging pile data, performing feature analysis and statistics processing on the preprocessed information through a data analysis and processing module, wherein the data analysis and processing module comprises a source data acquisition unit, a data attribute classification unit, a data feature analysis unit, a data statistics processing unit and a data docking unit, the source data acquisition unit is used for acquiring address information of data to be processed and source data containing features, the data attribute classification unit is used for dividing the data to be processed into attribute data blocks according to attribute vectors, the data feature analysis unit is used for extracting feature vectors of the attribute data blocks and analyzing feature tag codes, the data statistics processing unit is used for statistically sorting dynamic structures of the data blocks, and the data docking unit is used for transmitting the dynamic structures of the data blocks to a backup management cloud server and performing charging pile large data analysis through a charging pile database management platform;
the output end of the source data acquisition unit is connected with the input end of the data attribute classification unit, the output end of the data attribute classification unit is connected with the input end of the data characteristic analysis unit, the output end of the data characteristic analysis unit is connected with the input end of the data statistics processing unit, and the output end of the data statistics processing unit is connected with the input end of the data docking unit;
the data docking unit of the data analysis and processing module is used for transmitting the dynamic structure of the data block to the big data analysis and comparison module, the big data analysis and comparison module comprises a big data importing unit, a big data summarizing unit, a big data mining unit and a big data real-time prediction unit, the big data importing unit is used for storing data acquired by the front end of the big data analysis and comparison module in a distributed mode, the big data summarizing unit is used for carrying out cluster deployment operation on the data in the distributed memory and summarizing operation results, the big data mining unit is used for mining real-time position data and state data of electric bicycle charging piles in a database, the big data real-time prediction unit predicts the positions of fault charging piles and the positions of optimal charging piles according to distance, time and working states, and returns predicted values to an automatic updating feedback port, and automatically updates the feedback data every 30 seconds and transmits the feedback data to a user side on-line management platform;
the output end of the big data importing unit is connected with the input end of the big data summarizing unit, the output end of the big data importing unit is connected with the input end of the big data mining unit, and the output end of the big data mining unit is connected with the input end of the big data real-time prediction unit;
generating a record form log, and generating an electric bicycle charging pile data log by using the data block dynamic structure output by the data analysis and processing module and the feedback data output by the big data analysis and comparison module through the form log generating module, wherein the electric bicycle charging pile data log comprises a charging pile working state, a charging pile fault condition, an idle charging pile distribution condition and an area electric bicycle real-time density.
2. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: the RFID radio frequency identification unit, the two-dimensional code collection unit and the WiFi camera unit realize fusion of collected data on a network platform through a multi-terminal wireless intercommunication interface, and the fused data set realizes remote storage and backup on different electric bicycle charging pile devices through a topological network.
3. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: the data characteristic analysis unit adopts an independent characteristic label analysis model to extract characteristic labels, and the characteristic label output formula is as follows:
（1）
in the case of the formula (1),output function for feature tag, +.>Integration parameters for the first feature, < >>In the case of independent density of features,for independent densitometric dimensions, < >>Compensating correction value for error->Is an redundancy prevention parameter;
if abnormal reporting errors occur in the characteristic label extraction process, screening out abnormal values of the characteristic labels through a characteristic label abnormal reporting error model and outputting the abnormal values, wherein the output formula of the abnormal values of the characteristic labels is as follows:
（2）
in the formula (2) of the present invention,output function for characteristic tag outlier, +.>Is maximum abnormality threshold->For outlier diagnostic function, ++>For outlier address width, +.>For outlier node depth, ++>For the number of outlier symbol outlier total +.>For counting total element number, +.>As a statistical element, < > for>Is a noise feedback value->Is the noise amplitude.
4. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: the big data real-time prediction unit collects relevant parameters of the electric bicycle charging pile forming the prediction information set, integrates the parameters and establishes a prediction model based on time propulsion, and a user verifies and evaluates the availability and accuracy of the prediction model through a simulation experiment and outputs a prediction result to an automatic updating feedback port.
5. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: and the big data analysis and comparison module divides the feedback data into data segment slices by using a cross-platform streaming media protocol HTMP, and the data segment slices realize the transmission operation of the big data analysis and comparison module to the user side on-line management platform by adopting an IP address and content data double package after the user side on-line management platform and the big data analysis and comparison module complete the server link docking operation.
6. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: the big data mining unit adopts a dynamic factor optimizing model to realize accurate data mining and filter abnormal waveform interference in the data mining process, and an output formula of the dynamic factor optimizing model is as follows:
（3）
in the formula (3) of the present invention,outputting a function for the dynamic factor optimizing model, +.>For optimizing the threshold control function->Adjusting the model output function for the waveform, +.>Is a transversely extending domain->Is a longitudinally extending domain->Is a lateral extension domain->The longitudinal extension domain isWaveform adjusting function at time +_>For dynamic factor lateral range, +.>For dynamic factor longitudinal range, +.>For waveform conditioning function>For waveform phase parameter, y is adjacent optimizing domain difference parameter, ++>For abnormal waveform elimination constant, < >>Adjusting auxiliary parameters for the abnormal waveform; in the optimizing process, the dynamic factor optimizing model continuously performs adjacent two groups of optimizing effect comparison to obtain an optimal path, and a path comparison output formula is as follows:
（4）
in the formula (4) of the present invention,for the path contrast output function, +.>For the path variable +.>For the path update function->For the path state comparison function, +.>For the path passing time, +.>For the path traversal range, ++>For the time span parameter>Is a range span parameter; the dynamic factor optimizing model is provided with a delay auxiliary elimination plate to eliminate time delay in the optimizing process, and the delay elimination output formula is as follows:
（5）
in the formula (5) of the present invention,to delay the cancellation output function, +.>For delay factor, ++>For optimizing dimension, < >>For delay class parameter, ++>Is a delay diagnostic function.
7. The data analysis method based on the electric bicycle charging pile according to claim 1, wherein the method comprises the following steps: the table Shan Rizhi generation module analyzes and fuses the feedback data through a cluster fusion template, and a cluster fusion output formula is as follows:
（6）
in the formula (6) of the present invention,for clustering fusion output function, +.>For template period parameter, +.>For the overall dimension of the cycle of the template,for the period time fill constant,/-, for>For the abnormal parameters of the mode>For the pattern similarity parameter, +.>Is an auxiliary feedback constant; after the analyzing and fusing steps are completed, carrying out cyclic updating processing on the output result, wherein a cyclic updating formula is as follows:
（7）
in the formula (7) of the present invention,for cyclic updating functions, ++>For updating the time parameter->Predicting parameters for the number of elements, < >>For dynamic adjustment of parameters->Supplement parameters for dynamic difference->For the total number of cycles, +.>For the circulation interval +.>Is a ladder-type redundancy preventing parameter->Is a linear auxiliary parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768154.4A CN116821620A (en) | 2023-06-28 | 2023-06-28 | Data analysis method based on electric bicycle charging pile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768154.4A CN116821620A (en) | 2023-06-28 | 2023-06-28 | Data analysis method based on electric bicycle charging pile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116821620A true CN116821620A (en) | 2023-09-29 |
Family
ID=88116191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310768154.4A Withdrawn CN116821620A (en) | 2023-06-28 | 2023-06-28 | Data analysis method based on electric bicycle charging pile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116821620A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117411615A (en) * | 2023-12-13 | 2024-01-16 | 广州市信亦达电子科技有限公司 | Two-dimensional code anti-counterfeiting encryption method and system based on random number |
-
2023
- 2023-06-28 CN CN202310768154.4A patent/CN116821620A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117411615A (en) * | 2023-12-13 | 2024-01-16 | 广州市信亦达电子科技有限公司 | Two-dimensional code anti-counterfeiting encryption method and system based on random number |
| CN117411615B (en) * | 2023-12-13 | 2024-04-02 | 广州市信亦达电子科技有限公司 | Two-dimensional code anti-counterfeiting encryption method and system based on random number |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106168799B (en) | A method of batteries of electric automobile predictive maintenance is carried out based on big data machine learning | |
| CN115857447B (en) | Digital twinning-based complex industrial system operation monitoring method and system | |
| CN109639481A (en) | A kind of net flow assorted method, system and electronic equipment based on deep learning | |
| CN110445653A (en) | Network state prediction technique, device, equipment and medium | |
| CN116821620A (en) | Data analysis method based on electric bicycle charging pile | |
| CN113608882B (en) | Information processing method and system based on artificial intelligence and big data and cloud platform | |
| CN115527203B (en) | Cereal drying remote control method and system based on Internet of things | |
| CN111191400B (en) | Vehicle part life prediction method and system based on user fault reporting data | |
| CN116882790B (en) | Carbon emission equipment management method and system for mine ecological restoration area | |
| CN113155173A (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| CN109547251B (en) | Service system fault and performance prediction method based on monitoring data | |
| CN114511112A (en) | Intelligent operation and maintenance method and system based on Internet of things and readable storage medium | |
| CN112684301A (en) | Power grid fault detection method and device | |
| CN111666193B (en) | Method and system for monitoring and testing terminal function based on real-time log analysis | |
| CN106304085B (en) | Information processing method and device | |
| CN114331206A (en) | Point location addressing method and device, electronic equipment and readable storage medium | |
| CN110263622A (en) | Train fire monitoring method, apparatus, terminal and storage medium | |
| CN113987001A (en) | Rail transit signal system fault analysis method and device and electronic equipment | |
| CN112291226B (en) | Method and device for detecting abnormity of network flow | |
| CN112164223B (en) | Intelligent traffic information processing method and device based on cloud platform | |
| CN107124327A (en) | The method that the reverse-examination of JT808 car-mounted terminal simulators is surveyed | |
| CN107580329B (en) | Network analysis optimization method and device | |
| CN114169623A (en) | Power equipment fault analysis method and device, electronic equipment and storage medium | |
| CN114244691A (en) | Video service fault positioning method and device and electronic equipment | |
| CN109408697A (en) | Based on internet behavior early warning system and its method under big data information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230929 |
|
| WW01 | Invention patent application withdrawn after publication |