Distributed charging monitoring method and system based on Internet of Things

Abstract

The invention provides a distributed charging monitoring method and system based on the Internet of Things, and relates to the technical field of charging monitoring, and the method comprises the steps: obtaining a layout position parameter and a sample fault operation and maintenance record; fitting the layout position parameters to obtain an operation and maintenance traffic map, and synchronizing the operation and maintenance traffic map to a cloud scheduling node; performing monitoring index analysis according to the sample fault operation and maintenance record to obtain a sensor array; constructing a charging fault identification model and synchronizing the charging fault identification model to a peripheral monitoring node; connecting the peripheral monitoring node with the cloud scheduling node to generate a distributed monitoring architecture; performing fault identification based on the charging fault identification model to obtain a real-time monitoring result; and the cloud scheduling node receives a real-time monitoring result of the peripheral monitoring node, and obtains a distributed charging operation and maintenance strategy according to the operation and maintenance traffic map. According to the invention, the technical problem of low operation and maintenance efficiency and quality of the charging pile in the prior art can be solved, and the technical effect of improving the performance and reliability of the distributed charging monitoring system based on the Internet of Things is achieved.

Description

Technical Field

[0001] The present application relates to the field of charging monitoring technology, and in particular to a distributed charging monitoring method and system based on the Internet of Things. Background Art

[0002] Charging monitoring of charging pile equipment refers to the real-time monitoring and management of the charging process at a charging station or battery swap station.

[0003] At present, most of the existing charging pile monitoring is not transmitted to the edge node in real time through the Internet of Things, and the real-time status of the charging pile cannot be monitored and analyzed through the edge node, resulting in delayed fault discovery and reduced real-time and accuracy of fault detection. At the same time, if there is no real-time and accurate charging pile operation data, it is impossible to make quick decisions through cloud nodes, which may lead to waste of operation and maintenance resources and unreasonable layout, affecting the operation and maintenance efficiency of the charging pile.

[0004] To sum up, there are technical problems in the prior art that most of the historical usage frequency, failure frequency and other data of charging piles are not monitored in real time through the Internet of Things, which leads to reduced data processing accuracy and efficiency of edge nodes deployed at the charging piles, resulting in waste of operation and maintenance resources of cloud nodes and unreasonable layout, further affecting the operation and maintenance efficiency and quality of the charging piles. Summary of the invention

[0005] The purpose of this application is to provide a distributed charging monitoring method and system based on the Internet of Things, so as to solve the technical problem in the prior art that most of the historical usage frequency, failure frequency and other data of the charging piles are not monitored in real time through the Internet of Things, resulting in reduced data processing accuracy and efficiency of edge nodes deployed at the charging piles, causing waste of operation and maintenance resources of cloud nodes and unreasonable layout, further affecting the operation and maintenance efficiency and quality of the charging piles.

[0006] In view of the above problems, the present application provides a distributed charging monitoring method and system based on the Internet of Things.

[0007] In a first aspect, the present application provides a distributed charging monitoring method based on the Internet of Things, which is implemented by a distributed charging monitoring system based on the Internet of Things, wherein the method includes: interactively obtaining K layout location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in a monitoring area; interactively obtaining a regional traffic map of the monitoring area, fitting the K layout location parameters to the regional traffic map to obtain an operation and maintenance traffic map, and then synchronizing the operation and maintenance traffic map to a pre-built cloud scheduling node; performing monitoring indicator analysis based on the K sample fault operation and maintenance records, and performing sensor layout on the K charging piles to be monitored based on the monitoring indicator analysis results to obtain K sensor arrays; constructing K charging fault recognition models based on the K sample fault operation and maintenance records. The K charging fault identification models are synchronized to the pre-built K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are arranged at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things; the K peripheral monitoring nodes are communicatively connected to the cloud scheduling nodes to construct a distributed monitoring architecture; the K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; the cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

[0008] In the second aspect, the present application also provides a distributed charging monitoring system based on the Internet of Things, which is used to execute the distributed charging monitoring method based on the Internet of Things as described in the first aspect, wherein the system includes: a layout position parameter acquisition module, the layout position parameter acquisition module is used to interactively obtain K layout position parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area; an operation and maintenance traffic map acquisition module, the operation and maintenance traffic map acquisition module is used to interactively obtain a regional traffic map of the monitoring area, fit the K layout position parameters to the regional traffic map to obtain the operation and maintenance traffic map, and then synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node; a sensor array acquisition module, the sensor array acquisition module is used to perform monitoring index analysis based on the K sample fault operation and maintenance records, and based on the monitoring index analysis results, perform sensor layout on the K charging piles to be monitored to obtain K sensor arrays; a peripheral monitoring node construction module, the peripheral monitoring node construction module is used to construct a peripheral monitoring node based on the K sample fault operation and maintenance records K charging fault identification models are constructed, and the K charging fault identification models are synchronized to the pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are arranged at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things; a distributed monitoring architecture generation module, the distributed monitoring architecture generation module is used to connect the K peripheral monitoring nodes to the cloud scheduling node for communication, and construct a distributed monitoring architecture; a real-time monitoring result acquisition module, the real-time monitoring result acquisition module is used for the K peripheral monitoring nodes to receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and to perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; a distributed charging operation and maintenance strategy acquisition module, the distributed charging operation and maintenance strategy acquisition module is used for the cloud scheduling node to receive the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and to perform operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Obtain K layout location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area through interaction; obtain a regional traffic map of the monitoring area through interaction, fit the K layout location parameters to the regional traffic map to obtain the operation and maintenance traffic map, and then synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node; perform monitoring index analysis according to the K sample fault operation and maintenance records, and deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays; construct K charging fault identification models according to the K sample fault operation and maintenance records, and synchronize the K charging fault identification models to the pre-built K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are deployed on the K charging piles to be monitored, and the K peripheral monitoring nodes and the K sensor arrays are connected based on the Internet of Things. ; The K peripheral monitoring nodes are communicatively connected with the cloud scheduling node to construct a distributed monitoring architecture; the K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; the cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy. In other words, the cloud node and multiple edge nodes of multiple charging piles are regarded as a distributed architecture, and the processing tasks of the charging pile monitoring data are distributed to different edge nodes, which ultimately achieves the technical goal of distributed and collaborative data processing and achieves the technical effect of improving the performance and reliability of a distributed charging monitoring system based on the Internet of Things.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of a distributed charging monitoring method based on the Internet of Things in this application;

[0014] Figure 2 This is a structural diagram of the distributed charging monitoring system based on the Internet of Things in this application.

[0015] Description of reference numerals:

[0016] A deployment location parameter acquisition module 11, an operation and maintenance traffic map acquisition module 12, a sensor array acquisition module 13, a peripheral monitoring node construction module 14, a distributed monitoring architecture generation module 15, a real-time monitoring result acquisition module 16, and a distributed charging operation and maintenance strategy acquisition module 17. DETAILED DESCRIPTION

[0017] This application provides a distributed charging monitoring method and system based on the Internet of Things, which solves the technical problem that most of the existing technologies do not monitor the historical usage frequency, fault frequency and other data of charging piles in real time through the Internet of Things, which leads to reduced data processing accuracy and efficiency of edge nodes deployed on charging piles, resulting in waste of operation and maintenance resources of cloud nodes and unreasonable layout, further affecting the operation and maintenance efficiency and quality of charging piles. The technical goal of distributed and collaborative data processing is achieved, and the technical effect of improving the performance and reliability of distributed charging monitoring systems based on the Internet of Things is achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please see attached Figure 1 The present application provides a distributed charging monitoring method based on the Internet of Things, wherein the method is applied to a distributed charging monitoring system based on the Internet of Things, and the method specifically comprises the following steps:

[0021] Step 1: interactively obtain K layout location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area;

[0022] Specifically, the monitoring area is the area to be monitored for charging. Data is exchanged with the monitoring area to obtain K layout location parameters and K sample fault operation and maintenance records of the K charging piles to be monitored in the monitoring area. The layout location parameters are the parameters of the layout location of the charging piles to be monitored in the monitoring area. The sample fault operation and maintenance records are records of charging monitoring and fault operation and maintenance of the charging piles to be monitored in the historical time. For example, the layout location parameters are determined by obtaining the longitude and latitude coordinates of the charging piles to be monitored through the geographic location information system. The sample fault operation and maintenance records are determined by obtaining the historical fault records of the charging piles to be monitored. Furthermore, since there is at least one charging pile in the charging monitoring area, K is an integer greater than or equal to 1.

[0023] Step 2: interactively obtain a regional traffic map of the monitoring area, fit the K deployment location parameters to the regional traffic map to obtain an operation and maintenance traffic map, and synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node;

[0024] Specifically, data is exchanged with the monitoring area to obtain a regional traffic map of the monitoring area. For example, a city map is obtained through a geographic information system to obtain a regional traffic map of the monitoring area. K layout location parameters are fitted to the regional traffic map, and then the specific locations of K charging piles to be monitored are determined in the regional traffic map to generate an operation and maintenance traffic map. Furthermore, a cloud scheduling node is pre-built based on the Internet of Things to perform operation and maintenance arrangements on the charging piles to be monitored. The operation and maintenance traffic map is synchronized to the pre-built cloud scheduling node for subsequent operation and maintenance arrangements.

[0025] Step 3: Perform monitoring index analysis according to the K sample fault operation and maintenance records, and deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays;

[0026] Specifically, obtain K device model parameters of K charging piles to be monitored, use K device model parameters as constraints, call to obtain K sample fault operation and maintenance records, perform monitoring indicator analysis based on K sample fault operation and maintenance records, and obtain K sensor arrays. Among them, multiple sensors are deployed at specific locations of charging piles to achieve effective collection of characteristic data of charging pile faults / abnormalities.

[0027] Step 4: construct K charging fault identification models according to the K sample fault operation and maintenance records, and synchronize the K charging fault identification models to the pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are deployed at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things;

[0028] Specifically, K charging fault identification models are constructed based on K sample fault operation and maintenance records, and the K charging fault identification models are synchronized to the K peripheral monitoring nodes. The K peripheral monitoring nodes are deployed at the K charging piles to be monitored. The K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things, and the K sensor arrays are controlled by the K peripheral monitoring nodes to monitor the K charging piles to be monitored.

[0029] Step 5: Communicate and connect the K peripheral monitoring nodes with the cloud scheduling node to build a distributed monitoring architecture;

[0030] Specifically, K peripheral monitoring nodes are connected to the cloud scheduling node for communication, and the K peripheral monitoring nodes are monitored by the cloud scheduling node. A distributed monitoring architecture is formed based on the cloud scheduling node and the K peripheral monitoring nodes.

[0031] Step 6: The K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results;

[0032] Specifically, based on the Internet of Things, charging pile data is uploaded to K peripheral monitoring nodes through K sensor arrays. With the associated monitoring indicators as constraints, the charging pile data is divided and synchronized to K charging fault identification models to obtain K real-time monitoring results.

[0033] Step 7: The cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

[0034] Specifically, the cloud scheduling node calls K real-time monitoring results from K peripheral monitoring nodes to obtain the layout location parameters of multiple fault monitoring nodes in the K real-time monitoring results. The shortest operation and maintenance route is fitted for the layout location parameters of multiple fault monitoring nodes in the operation and maintenance traffic map to obtain a route that can cover all fault monitoring nodes, from which the shortest distance route is obtained as the shortest operation and maintenance route and added to the distributed charging operation and maintenance strategy.

[0035] The distributed charging monitoring method based on the Internet of Things is applied to a distributed charging monitoring system based on the Internet of Things, which can achieve the technical goals of distributed and collaborative data processing and achieve the technical effect of improving the performance and reliability of the distributed charging monitoring system based on the Internet of Things.

[0036] Furthermore, the present application also includes the following steps:

[0037] Interactively obtain a first device model parameter of a first charging pile to be monitored, and use the first device model parameter as a constraint to call and obtain a first sample fault operation and maintenance record, wherein the first sample fault operation and maintenance record includes multiple sample fault types and multiple sample charging pile operation data sequences;

[0038] Aggregating the first sample fault operation and maintenance records by fault type to obtain M sample fault types and dividing the plurality of sample charging pile operation data sequences based on the M sample fault types to obtain M groups of sample charging pile operation data sequences;

[0039] Interactively obtain M fault latent periods of the M sample fault types, and optimize the data of the M groups of sample charging pile operation data sequences with the M fault latent periods as constraints to obtain M groups of sample optimized data sequences;

[0040] Perform monitoring indicator change analysis on the M groups of sample optimization data sequences to obtain M groups of associated monitoring indicators, and aggregate the M groups of associated monitoring indicators to obtain a first monitoring indicator set;

[0041] Pre-constructing an indicator sensor association table, and using the first monitoring indicator set to traverse the indicator sensor association table to obtain a first sensor array;

[0042] By analogy, K device model parameters of the K charging piles to be monitored are obtained interactively, and the K device model parameters are used as constraints to obtain the K sample fault operation and maintenance records, and monitoring indicator analysis is performed based on the K sample fault operation and maintenance records to obtain the K sensor arrays.

[0043] Specifically, data is exchanged with the monitoring area to obtain K charging piles to be monitored. The first charging pile to be monitored is randomly selected from the K charging piles to be monitored. The first device model parameter of the first charging pile to be monitored is obtained. For example, the first device model parameter may include information such as the model, rated power, and rated voltage of the first charging pile to be monitored. Using the first device model parameter as a constraint, call the first sample fault operation and maintenance record corresponding to the first charging pile to be monitored in the sample fault operation and maintenance record. Among them, the first sample fault operation and maintenance record includes multiple sample fault types and multiple sample charging pile operation data sequences. For example, multiple sample fault types include charging interruptions, communication failures and other faults. Multiple sample charging pile operation data sequences include real-time monitoring data such as voltage, current, and temperature.

[0044] Then, the first sample fault operation and maintenance record is aggregated by fault type, similar fault types are grouped into one category, and M different sample fault types are obtained. According to the aggregated M fault types, the corresponding sample charging pile operation data sequences are divided to form M groups of sample charging pile operation data sequences associated with the M fault types.

[0045] Next, data interaction is performed with the sample fault operation and maintenance records to obtain M fault latency periods of M sample fault types. Each sample fault type has a corresponding fault latency period. The fault latency period refers to the characteristic performance in a period of time before the fault occurs. The fault latency period is set by the actual situation of the fault occurrence corresponding to the fault type. The M groups of sample charging pile operation data sequences are operation data sequences with a longer time span including M fault latency periods. With the M fault latency periods as constraints, the M groups of sample charging pile operation data sequences are traced back to obtain an operation data sequence with a time span including only M fault latency periods, and the M groups of optimized data sequences are obtained as the M groups of sample optimized data sequences, thereby enhancing the characteristic of the fault data.

[0046] Next, the monitoring indicator changes of the M groups of sample optimization data sequences are analyzed to identify the monitoring indicators with a high degree of correlation with the occurrence of the fault, and obtain M groups of associated monitoring indicators. The M groups of associated monitoring indicators are aggregated to form a first monitoring indicator set, which includes key indicators that can reflect the fault status of the first charging pile to be monitored.

[0047] Then, a pre-constructed indicator sensor association table is constructed, including the mapping relationship between different monitoring indicators and corresponding sensors. The indicator sensor association table is traversed using the first monitoring indicator set to obtain sensors that can monitor the indicators of the first monitoring indicator set, forming a first sensor array. Among them, multiple sensors are arranged at specific locations of the charging pile to achieve effective collection of characteristic data of charging pile failures / abnormalities.

[0048] Then, repeat the above steps for the remaining K-1 charging piles to be monitored, and obtain the device model parameters, sample fault operation and maintenance records, monitoring indicator sets and sensor arrays of the K-1 charging piles to be monitored. Finally, obtain K device model parameters, K sample fault operation and maintenance records, K groups of associated monitoring indicators and K sensor arrays corresponding to K charging piles.

[0049] By selecting key monitoring indicators and corresponding sensor arrays for each charging pile to be monitored, accurate monitoring and fault prevention of the charging pile to be monitored can be achieved.

[0050] Furthermore, the present application also includes the following steps:

[0051] Based on the M groups of sample optimization data sequences, a first group of sample optimization data sequences is obtained, wherein each sample optimization data sequence includes multiple indicator change sequences of multiple sample monitoring indicators, and the multiple indicator change sequence data are aligned;

[0052] Based on the first group of sample optimization data sequences, a plurality of monitoring indicator curve graphs of a plurality of sample optimization data sequences are obtained by drawing, wherein each monitoring indicator curve graph includes a plurality of indicator change curves of the plurality of sample monitoring indicators;

[0053] Performing curve aggregation of the plurality of monitoring indicator curve graphs according to the plurality of sample monitoring indicators to obtain a plurality of monitoring indicator curve graphs;

[0054] Performing curvature change analysis on the plurality of curve graphs of the same monitoring indicator to obtain synchronization coefficients of the plurality of indicator changes;

[0055] A fault correlation threshold is preset, and the plurality of indicator change synchronization coefficients are screened based on the fault correlation threshold to obtain the first monitoring indicator set.

[0056] Specifically, a group of sample optimization data sequences is randomly selected from the M groups of sample optimization data sequences as the first group of sample optimization data sequences. Each sample optimization data sequence contains multiple indicator change sequences of multiple sample monitoring indicators. Among them, multiple indicator change sequences are aligned, that is, the timestamps or sampling points are consistent.

[0057] Then, based on the first set of sample optimization data sequences, a monitoring indicator curve chart is drawn for each sample optimization data sequence. Each monitoring indicator curve chart contains multiple indicator change curves of multiple sample monitoring indicators, so as to determine the change of different indicators on the same time scale.

[0058] Next, according to the same sample monitoring indicators in multiple sample monitoring indicators, multiple monitoring indicator curve graphs are aggregated, and the same monitoring indicator curves are placed in the same graph, thereby obtaining multiple same monitoring indicator curve graphs, so as to more clearly observe the changing trends and correlations between multiple curves.

[0059] Next, curve feature extraction and similarity calculation are performed on multiple curve graphs with the same monitoring indicators to obtain the change synchronization coefficient between different monitoring indicators, which reflects the degree of synchronization of changes in different monitoring indicators before and after the fault occurs, that is, whether abnormalities or trend changes occur at the same time.

[0060] In addition, a fault correlation threshold is preset, and the fault correlation threshold is determined based on historical data or expert experience. According to the fault correlation threshold, monitoring indicators whose indicator change synchronization coefficient meets the fault correlation threshold are screened, that is, monitoring indicators with a higher indicator change synchronization coefficient, to form a first monitoring indicator set. The first monitoring indicator set shows a strong correlation when a fault occurs, so it is a key indicator for monitoring and predicting faults, and further determines the key monitoring indicators.

[0061] By optimizing the data sequence through samples, monitoring indicators that are highly correlated with faults are extracted, providing support for the subsequent construction of fault prediction models and the realization of precise monitoring.

[0062] Furthermore, the present application also includes the following steps:

[0063] Based on the plurality of monitoring indicator curve graphs, a first monitoring indicator curve graph is obtained by calling, wherein the first monitoring indicator curve graph includes N monitoring indicator change curves;

[0064] A predetermined curve feature set, wherein the predetermined curve feature set includes a curve peak, a curve valley, a curve inflection point, a peak-to-valley drop, a peak curvature, a valley curvature, and an inflection point curvature;

[0065] Extracting features of the N monitoring indicator change curves based on the curve feature set to obtain N groups of curve features;

[0066] The similarity between the first group of curve features and the N-1 group of curve features is obtained based on the Euclidean distance calculation, and the similarity of N curves is obtained;

[0067] The mean of the N curve similarities is calculated to obtain a first indicator change synchronization coefficient.

[0068] Specifically, a same monitoring indicator curve graph is randomly selected from multiple same monitoring indicator curve graphs as the first same monitoring indicator curve graph. The first same monitoring indicator curve graph includes N monitoring indicator change curves, which are used to reflect the change of the same monitoring indicator in different samples or different time periods.

[0069] Then, according to the characteristics of the monitoring index change curve, a curve feature set is predetermined. The curve feature set includes multiple features that can reflect the shape and change trend of the curve, such as curve peak, curve valley, curve inflection point, peak-valley drop, peak curvature, valley curvature, inflection point curvature, etc.

[0070] Next, according to the curve feature set, feature extraction is performed on the N monitoring indicator change curves in the first monitoring indicator curve graph, and a corresponding feature curve is extracted from each monitoring indicator change curve to form N groups of curve features.

[0071] Next, the Euclidean distance is used to calculate the similarity between the first set of curve features and the remaining N-1 sets of curve features, and then the similarities of N curves are obtained. The smaller the Euclidean distance, the more similar the first set of curve features are to the remaining curve features, that is, the closer the change trends and shapes between the curves are, and vice versa, the greater the difference.

[0072] In addition, the mean of the similarities of the N curves is calculated to obtain the first indicator change synchronization coefficient, which is used to reflect the average similarity of the indicator change curves of different samples or different time periods under the same sample monitoring indicator. Among them, the higher the similarity value, the more similar the change trends of the N monitoring indicator change curves, that is, the stronger the synchronization of the indicator change, and vice versa.

[0073] Through curve feature extraction and similarity calculation, the change synchronization coefficient between different monitoring indicators is obtained, which is used to further screen and determine the key monitoring indicators to form the first monitoring indicator set, providing an important basis for subsequent fault prediction and monitoring.

[0074] Furthermore, the present application also includes the following steps:

[0075] Taking the first monitoring indicator set as a screening constraint, optimizing the indicator composition of the M groups of sample optimization data sequences to obtain M groups of sample fault data sequences;

[0076] Pre-constructing a standard fault identification branch, and using the M groups of sample fault data sequences to train the standard fault identification branch, to obtain M fault identification branches corresponding to the M types of sample faults;

[0077] The M fault identification branches are connected in parallel to obtain a first charging fault identification model of the first charging pile to be monitored, and the first charging fault identification model is synchronized to a first peripheral monitoring node among the K peripheral monitoring nodes;

[0078] By analogy, the K charging fault identification models are constructed according to the K sample fault operation and maintenance records, and the K charging fault identification models are synchronized to the K peripheral monitoring nodes.

[0079] Specifically, the first monitoring indicator set is used as the screening constraint to optimize the indicator composition of the M groups of sample optimization data sequences, that is, the monitoring indicator data matching the first monitoring indicator set is retained, and other irrelevant monitoring indicator data are eliminated. After optimization, the M groups of sample fault data sequences are obtained.

[0080] Then, based on the machine learning model, a standard fault identification branch is pre-built and trained using M groups of sample fault data sequences. For each sample fault type, a corresponding fault identification branch is obtained, and then M fault identification branches are obtained, each of which can identify a sample fault type.

[0081] Next, the M fault identification branches are connected in parallel to form a first charging fault identification model for the first charging pile to be monitored. The first charging fault identification model can simultaneously monitor M different sample fault types, thereby improving the comprehensiveness and accuracy of fault identification. Furthermore, the K peripheral monitoring nodes correspond to the K charging piles to be monitored. The constructed first charging fault identification model is synchronized to the first peripheral monitoring node among the K peripheral monitoring nodes corresponding to the first charging pile to be monitored.

[0082] Next, for the remaining K-1 charging piles to be monitored, repeat the above steps, and build a corresponding charging fault identification model based on the sample fault operation and maintenance records of each charging pile to be monitored. The K-1 charging fault identification models are synchronized to the corresponding K-1 peripheral monitoring nodes respectively.

[0083] By determining a charging fault identification model for each charging pile to be monitored and deploying the charging fault identification model to the corresponding peripheral monitoring node, the operating data of the charging pile can be monitored in real time. If any abnormality or signs of failure are found, an alarm can be issued in time or corresponding preventive measures can be taken.

[0084] Furthermore, the present application also includes the following steps:

[0085] The M fault latency periods are serialized and the shortest period is called to obtain a fault latency limit, and the fault latency limit is used as a period for the first sensor array to transmit data to the first peripheral monitoring node;

[0086] The first peripheral monitoring node receives a first associated monitoring sequence uploaded by the first sensor array at intervals of the fault latency limit;

[0087] The first associated monitoring sequence is divided based on the M groups of associated monitoring indicators as constraints, and the divided results are mapped and synchronized to the M fault identification branches of the first charging fault identification model to obtain a first real-time monitoring result, wherein the first real-time monitoring result includes N types of faults, 0≤N≤M.

[0088] Specifically, the M fault latency periods are serialized according to the length of the period to obtain a sequential arrangement of the M fault latency periods. The shortest fault latency period is called from the sequentially arranged M fault latency periods as the fault latency limit. The period of data transmission from the first sensor array to the first peripheral monitoring node is set as the fault latency limit.

[0089] Then, the first associated monitoring sequence is periodically uploaded to the first peripheral monitoring node through the first sensor array according to the fault latency limit period.

[0090] Next, with M groups of associated monitoring indicators as constraints, the first associated monitoring sequence is divided into multiple parts according to different associated monitoring indicators, and each part corresponds to an associated monitoring indicator. Among them, the division is to divide the data according to the associated monitoring indicators of each fault, and identify whether multiple faults exist in the first associated monitoring sequence. The divided results are mapped and synchronized to the M fault identification branches of the first charging fault identification model, and each fault identification branch corresponds to a part of the associated monitoring indicator division. After synchronization, the first real-time monitoring result is obtained. Since there may be faults corresponding to each group of associated monitoring indicators in the division results, or there may be no faults corresponding to each group of associated monitoring indicators, the first real-time monitoring result includes N types of fault types existing in the first associated monitoring sequence, where N is an integer greater than or equal to 0 and less than or equal to M.

[0091] By optimizing the efficiency of data transmission through the fault latent period, it is ensured that the first peripheral monitoring node can receive the monitoring data related to fault identification in real time and accurately, thereby improving the timeliness and accuracy of fault identification, helping to take preventive measures in a timely manner and reducing the impact of faults on charging pile operations.

[0092] Furthermore, the present application also includes the following steps:

[0093] The cloud scheduling node calls the number of fault types from the K real-time monitoring results, and removes fault-free peripheral monitoring nodes based on the result of the fault type number call to obtain multiple fault monitoring nodes;

[0094] According to the mapping relationship between the K peripheral monitoring nodes and the K charging piles to be monitored, obtaining multiple layout position parameters of the multiple fault monitoring nodes;

[0095] The shortest operation and maintenance route is fitted for the multiple layout location parameters in the operation and maintenance traffic map to obtain the distributed charging operation and maintenance strategy.

[0096] Specifically, the number of fault types in each real-time monitoring result is called from the K real-time monitoring results through the cloud scheduling node. According to the result of calling the number of fault types, the number of fault types that do not match the K peripheral monitoring nodes is eliminated, and the number of fault types that match the K peripheral monitoring nodes is retained, that is, the fault data is retained and the normal data is eliminated, thereby forming multiple fault monitoring nodes.

[0097] Then, according to the mapping relationship between the K peripheral monitoring nodes and the K charging piles to be monitored, the layout position parameters of the charging pile to be monitored corresponding to each fault monitoring node are obtained.

[0098] Next, a path planning algorithm is used in the operation and maintenance traffic map to fit the layout parameters of multiple fault monitoring nodes to the shortest operation and maintenance route, and a route that can cover all fault monitoring nodes is obtained. The shortest distance route is obtained as the shortest operation and maintenance route and added to the distributed charging operation and maintenance strategy so that operation and maintenance personnel can efficiently go to multiple fault monitoring nodes for fault handling.

[0099] Through the cloud-based scheduling node, the fault monitoring node can be quickly determined based on the real-time monitoring results, and the distributed charging operation and maintenance strategy can be obtained based on the location information of the fault monitoring node, which helps to improve the operation and maintenance effect of the charging facilities and ensure the normal operation of the charging piles.

[0100] In summary, the distributed charging monitoring method based on the Internet of Things provided by this application has the following technical effects:

[0101] Obtain K layout location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area through interaction; obtain a regional traffic map of the monitoring area through interaction, fit the K layout location parameters to the regional traffic map to obtain the operation and maintenance traffic map, and then synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node; perform monitoring index analysis according to the K sample fault operation and maintenance records, and deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays; construct K charging fault identification models according to the K sample fault operation and maintenance records, and synchronize the K charging fault identification models to the pre-built K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are deployed on the K charging piles to be monitored, and the K peripheral monitoring nodes and the K sensor arrays are connected based on the Internet of Things. ; The K peripheral monitoring nodes are communicatively connected with the cloud scheduling node to construct a distributed monitoring architecture; the K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; the cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy. In other words, the cloud node and multiple edge nodes of multiple charging piles are regarded as a distributed architecture, and the processing tasks of the charging pile monitoring data are distributed to different edge nodes, which ultimately achieves the technical goal of distributed and collaborative data processing and achieves the technical effect of improving the performance and reliability of a distributed charging monitoring system based on the Internet of Things.

[0102] Embodiment 2

[0103] Based on the distributed charging monitoring method based on the Internet of Things in the aforementioned embodiment, the present application also provides a distributed charging monitoring system based on the Internet of Things, please refer to the attached Figure 2 , the system comprising:

[0104] A deployment location parameter acquisition module 11, wherein the deployment location parameter acquisition module 11 is used to interactively obtain K deployment location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area;

[0105] An operation and maintenance traffic map acquisition module 12, the operation and maintenance traffic map acquisition module 12 is used to interactively obtain a regional traffic map of the monitoring area, fit the K deployment location parameters to the regional traffic map to obtain an operation and maintenance traffic map, and then synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node;

[0106] A sensor array acquisition module 13, the sensor array acquisition module 13 is used to perform monitoring index analysis according to the K sample fault operation and maintenance records, and to deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays;

[0107] A peripheral monitoring node construction module 14, the peripheral monitoring node construction module 14 is used to construct K charging fault identification models according to the K sample fault operation and maintenance records, and synchronize the K charging fault identification models to the pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are arranged at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things;

[0108] A distributed monitoring architecture generation module 15, wherein the distributed monitoring architecture generation module 15 is used to connect the K peripheral monitoring nodes and the cloud scheduling node to build a distributed monitoring architecture;

[0109] A real-time monitoring result acquisition module 16, wherein the real-time monitoring result acquisition module 16 is used for the K peripheral monitoring nodes to receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and to perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results;

[0110] The distributed charging operation and maintenance strategy acquisition module 17 is used for the cloud scheduling node to receive the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and to perform operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

[0111] Furthermore, the sensor array acquisition module 13 in the system is also used for:

[0112] Interactively obtain a first device model parameter of a first charging pile to be monitored, and use the first device model parameter as a constraint to call and obtain a first sample fault operation and maintenance record, wherein the first sample fault operation and maintenance record includes multiple sample fault types and multiple sample charging pile operation data sequences;

[0113] Aggregating the first sample fault operation and maintenance records by fault type to obtain M sample fault types and dividing the plurality of sample charging pile operation data sequences based on the M sample fault types to obtain M groups of sample charging pile operation data sequences;

[0114] Interactively obtain M fault latent periods of the M sample fault types, and optimize the data of the M groups of sample charging pile operation data sequences with the M fault latent periods as constraints to obtain M groups of sample optimized data sequences;

[0115] Perform monitoring indicator change analysis on the M groups of sample optimization data sequences to obtain M groups of associated monitoring indicators, and aggregate the M groups of associated monitoring indicators to obtain a first monitoring indicator set;

[0116] Pre-constructing an indicator sensor association table, and using the first monitoring indicator set to traverse the indicator sensor association table to obtain a first sensor array;

[0117] By analogy, K device model parameters of the K charging piles to be monitored are obtained interactively, and the K device model parameters are used as constraints to obtain the K sample fault operation and maintenance records, and monitoring indicator analysis is performed based on the K sample fault operation and maintenance records to obtain the K sensor arrays.

[0118] Furthermore, the sensor array acquisition module 13 in the system is also used for:

[0119] Based on the M groups of sample optimization data sequences, a first group of sample optimization data sequences is obtained, wherein each sample optimization data sequence includes multiple indicator change sequences of multiple sample monitoring indicators, and the multiple indicator change sequence data are aligned;

[0120] Based on the first group of sample optimization data sequences, a plurality of monitoring indicator curve graphs of a plurality of sample optimization data sequences are obtained by drawing, wherein each monitoring indicator curve graph includes a plurality of indicator change curves of the plurality of sample monitoring indicators;

[0121] Performing curve aggregation of the plurality of monitoring indicator curve graphs according to the plurality of sample monitoring indicators to obtain a plurality of monitoring indicator curve graphs;

[0122] Performing curvature change analysis on the plurality of curve graphs of the same monitoring indicator to obtain synchronization coefficients of the plurality of indicator changes;

[0123] A fault correlation threshold is preset, and the plurality of indicator change synchronization coefficients are screened based on the fault correlation threshold to obtain the first monitoring indicator set.

[0124] Furthermore, the sensor array acquisition module 13 in the system is also used for:

[0125] Based on the plurality of monitoring indicator curve graphs, a first monitoring indicator curve graph is obtained by calling, wherein the first monitoring indicator curve graph includes N monitoring indicator change curves;

[0126] A predetermined curve feature set, wherein the predetermined curve feature set includes a curve peak, a curve valley, a curve inflection point, a peak-to-valley drop, a peak curvature, a valley curvature, and an inflection point curvature;

[0127] Extracting features of the N monitoring indicator change curves based on the curve feature set to obtain N groups of curve features;

[0128] The similarity between the first group of curve features and the N-1 group of curve features is obtained based on the Euclidean distance calculation, and the similarity of N curves is obtained;

[0129] The mean of the N curve similarities is calculated to obtain a first indicator change synchronization coefficient.

[0130] Furthermore, the peripheral monitoring node construction module 14 in the system is also used for:

[0131] Taking the first monitoring indicator set as a screening constraint, optimizing the indicator composition of the M groups of sample optimization data sequences to obtain M groups of sample fault data sequences;

[0132] Pre-constructing a standard fault identification branch, and using the M groups of sample fault data sequences to train the standard fault identification branch, to obtain M fault identification branches corresponding to the M types of sample faults;

[0133] The M fault identification branches are connected in parallel to obtain a first charging fault identification model of the first charging pile to be monitored, and the first charging fault identification model is synchronized to a first peripheral monitoring node among the K peripheral monitoring nodes;

[0134] By analogy, the K charging fault identification models are constructed according to the K sample fault operation and maintenance records, and the K charging fault identification models are synchronized to the K peripheral monitoring nodes.

[0135] Furthermore, the real-time monitoring result obtaining module 16 in the system is also used for:

[0136] The M fault latency periods are serialized and the shortest period is called to obtain a fault latency limit, and the fault latency limit is used as a period for the first sensor array to transmit data to the first peripheral monitoring node;

[0137] The first peripheral monitoring node receives a first associated monitoring sequence uploaded by the first sensor array at intervals of the fault latency limit;

[0138] The first associated monitoring sequence is divided based on the M groups of associated monitoring indicators as constraints, and the divided results are mapped and synchronized to the M fault identification branches of the first charging fault identification model to obtain a first real-time monitoring result, wherein the first real-time monitoring result includes N types of faults, 0≤N≤M.

[0139] Furthermore, the distributed charging operation and maintenance strategy acquisition module 17 in the system is also used for:

[0140] The cloud scheduling node calls the number of fault types from the K real-time monitoring results, and removes fault-free peripheral monitoring nodes based on the result of the fault type number call to obtain multiple fault monitoring nodes;

[0141] According to the mapping relationship between the K peripheral monitoring nodes and the K charging piles to be monitored, obtaining multiple layout position parameters of the multiple fault monitoring nodes;

[0142] The shortest operation and maintenance route is fitted for the multiple layout location parameters in the operation and maintenance traffic map to obtain the distributed charging operation and maintenance strategy.

[0143] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The distributed charging monitoring method based on the Internet of Things and the specific examples in the aforementioned embodiment 1 are also applicable to the distributed charging monitoring system based on the Internet of Things in this embodiment. Through the aforementioned detailed description of the distributed charging monitoring method based on the Internet of Things, those skilled in the art can clearly understand the distributed charging monitoring system based on the Internet of Things in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0144] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0145] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A distributed charging monitoring method based on the Internet of Things, characterized in that: The method comprises: Interactively obtain K layout location parameters and K sample fault operation and maintenance records of K charging piles to be monitored in the monitoring area; Interactively obtain a regional traffic map of the monitoring area, fit the K deployment location parameters to the regional traffic map to obtain an operation and maintenance traffic map, and synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node; Perform monitoring index analysis according to the K sample fault operation and maintenance records, and deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays; Constructing K charging fault identification models according to the K sample fault operation and maintenance records, and synchronizing the K charging fault identification models to pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are deployed at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things; The K peripheral monitoring nodes are connected to the cloud scheduling node for communication to construct a distributed monitoring architecture; The K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; The cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

2. The method according to claim 1, characterized in that Performing monitoring index analysis according to the K sample fault operation and maintenance records, and deploying sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays, the method further comprising: Interactively obtain a first device model parameter of a first charging pile to be monitored, and use the first device model parameter as a constraint to call and obtain a first sample fault operation and maintenance record, wherein the first sample fault operation and maintenance record includes multiple sample fault types and multiple sample charging pile operation data sequences; Aggregating the first sample fault operation and maintenance records by fault type to obtain M sample fault types and dividing the plurality of sample charging pile operation data sequences based on the M sample fault types to obtain M groups of sample charging pile operation data sequences; Interactively obtain M fault latent periods of the M sample fault types, and optimize the data of the M groups of sample charging pile operation data sequences with the M fault latent periods as constraints to obtain M groups of sample optimized data sequences; Perform monitoring indicator change analysis on the M groups of sample optimization data sequences to obtain M groups of associated monitoring indicators, and aggregate the M groups of associated monitoring indicators to obtain a first monitoring indicator set; Pre-constructing an indicator sensor association table, and using the first monitoring indicator set to traverse the indicator sensor association table to obtain a first sensor array; By analogy, K device model parameters of the K charging piles to be monitored are obtained interactively, and the K device model parameters are used as constraints to obtain the K sample fault operation and maintenance records, and monitoring indicator analysis is performed based on the K sample fault operation and maintenance records to obtain the K sensor arrays.

3. The method according to claim 2, characterized in that Performing monitoring indicator change analysis on the M groups of sample optimization data sequences to obtain M groups of associated monitoring indicators, aggregating the M groups of associated monitoring indicators to obtain a first monitoring indicator set, the method further comprising: Based on the M groups of sample optimization data sequences, a first group of sample optimization data sequences is obtained, wherein each sample optimization data sequence includes multiple indicator change sequences of multiple sample monitoring indicators, and the multiple indicator change sequence data are aligned; Based on the first group of sample optimization data sequences, a plurality of monitoring indicator curve graphs of a plurality of sample optimization data sequences are obtained by drawing, wherein each monitoring indicator curve graph includes a plurality of indicator change curves of the plurality of sample monitoring indicators; Performing curve aggregation of the plurality of monitoring indicator curve graphs according to the plurality of sample monitoring indicators to obtain a plurality of monitoring indicator curve graphs; Performing curvature change analysis on the plurality of curve graphs of the same monitoring indicator to obtain synchronization coefficients of the plurality of indicator changes; A fault correlation threshold is preset, and the plurality of indicator change synchronization coefficients are screened based on the fault correlation threshold to obtain the first monitoring indicator set.

4. The method according to claim 3, characterized in that Performing curvature change analysis on the plurality of curve graphs of the same monitoring indicator to obtain synchronization coefficients of the plurality of indicator changes, the method further comprising: Based on the plurality of monitoring indicator curve graphs, a first monitoring indicator curve graph is obtained by calling, wherein the first monitoring indicator curve graph includes N monitoring indicator change curves; A predetermined curve feature set, wherein the predetermined curve feature set includes a curve peak, a curve valley, a curve inflection point, a peak-to-valley drop, a peak curvature, a valley curvature, and an inflection point curvature; Extracting features of the N monitoring indicator change curves based on the curve feature set to obtain N groups of curve features; The similarity between the first group of curve features and the N-1 group of curve features is obtained based on the Euclidean distance calculation, and the similarity of N curves is obtained; The mean of the N curve similarities is calculated to obtain a first indicator change synchronization coefficient.

5. The method according to claim 2, characterized in that K charging fault identification models are constructed according to the K sample fault operation and maintenance records, and the K charging fault identification models are synchronized to pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are arranged at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things, and the method further includes: Taking the first monitoring indicator set as a screening constraint, optimizing the indicator composition of the M groups of sample optimization data sequences to obtain M groups of sample fault data sequences; Pre-constructing a standard fault identification branch, and using the M groups of sample fault data sequences to train the standard fault identification branch, to obtain M fault identification branches corresponding to the M types of sample faults; The M fault identification branches are connected in parallel to obtain a first charging fault identification model of the first charging pile to be monitored, and the first charging fault identification model is synchronized to a first peripheral monitoring node among the K peripheral monitoring nodes; By analogy, the K charging fault identification models are constructed according to the K sample fault operation and maintenance records, and the K charging fault identification models are synchronized to the K peripheral monitoring nodes.

6. The method according to claim 5, characterized in that The K peripheral monitoring nodes receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results. The method also includes: The M fault latency periods are serialized and the shortest period is called to obtain a fault latency limit, and the fault latency limit is used as a period for the first sensor array to transmit data to the first peripheral monitoring node; The first peripheral monitoring node receives a first associated monitoring sequence uploaded by the first sensor array at intervals of the fault latency limit; The first associated monitoring sequence is divided based on the M groups of associated monitoring indicators as constraints, and the divided results are mapped and synchronized to the M fault identification branches of the first charging fault identification model to obtain a first real-time monitoring result, wherein the first real-time monitoring result includes N types of faults, 0≤N≤M.

7. The method according to claim 6, characterized in that The cloud scheduling node receives the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and performs operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy. The method further includes: The cloud scheduling node calls the number of fault types from the K real-time monitoring results, and removes fault-free peripheral monitoring nodes based on the result of the fault type number call to obtain multiple fault monitoring nodes; According to the mapping relationship between the K peripheral monitoring nodes and the K charging piles to be monitored, obtaining multiple layout position parameters of the multiple fault monitoring nodes; The shortest operation and maintenance route is fitted for the multiple layout location parameters in the operation and maintenance traffic map to obtain the distributed charging operation and maintenance strategy.

8. The distributed charging monitoring system based on the Internet of Things is characterized by: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A deployment location parameter acquisition module, the deployment location parameter acquisition module is used to interactively obtain K deployment location parameters and K sample fault operation and maintenance records of K to-be-monitored charging piles in the monitoring area; An operation and maintenance traffic map acquisition module, the operation and maintenance traffic map acquisition module is used to interactively obtain a regional traffic map of the monitoring area, fit the K deployment location parameters to the regional traffic map to obtain the operation and maintenance traffic map, and then synchronize the operation and maintenance traffic map to a pre-built cloud scheduling node; A sensor array acquisition module, the sensor array acquisition module is used to perform monitoring index analysis according to the K sample fault operation and maintenance records, and to deploy sensors on the K charging piles to be monitored based on the monitoring index analysis results to obtain K sensor arrays; A peripheral monitoring node construction module, the peripheral monitoring node construction module is used to construct K charging fault identification models according to the K sample fault operation and maintenance records, and synchronize the K charging fault identification models to the pre-constructed K peripheral monitoring nodes, wherein the K peripheral monitoring nodes are arranged at the K charging piles to be monitored, and the K peripheral monitoring nodes are connected to the K sensor arrays based on the Internet of Things; A distributed monitoring architecture generation module, the distributed monitoring architecture generation module is used to connect the K peripheral monitoring nodes and the cloud scheduling node to build a distributed monitoring architecture; A real-time monitoring result acquisition module, wherein the real-time monitoring result acquisition module is used for the K peripheral monitoring nodes to receive the charging pile data uploaded by the K sensor arrays based on the Internet of Things, and to perform fault identification based on the K charging fault identification models to obtain K real-time monitoring results; A distributed charging operation and maintenance strategy acquisition module is used for the cloud scheduling node to receive the K real-time monitoring results uploaded by the K peripheral monitoring nodes, and to perform operation and maintenance route fitting according to the operation and maintenance traffic map to obtain a distributed charging operation and maintenance strategy.

Images