Charging service platform data analysis method and system based on Internet of Things

Abstract

The invention discloses a charging service platform data analysis method and system based on the Internet of Things, and relates to the technical field of data analysis, and the charging service platform data analysis method comprises the following steps: extracting key operation feature data of a charging service platform; identifying abnormal operation data in the current charging service platform; key factors influencing the operation fault of the charging pile equipment are identified; and dynamically adjusting the operation parameters of the charging pile equipment, and optimizing the operation of the charging service platform in combination with the real-time monitoring data. According to the method, key operation characteristic data are analyzed through a fault diagnosis algorithm, abnormal data in the platform are quickly identified, the accuracy and response speed of fault detection are remarkably improved, and service interruption caused by faults is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a charging service platform data analysis method and system based on the Internet of Things. Background Art

[0002] At present, charging pile equipment mainly relies on wired networks, wireless networks and other methods for data communication transmission, and realizes intelligent management of charging equipment through cloud-based background management systems, including charging equipment operation status monitoring, user identity identification, charging billing management and equipment maintenance, so as to provide efficient and convenient charging services. However, due to the high dependence of the charging service platform on network communication, once a communication failure occurs, such as network delay, interruption or data loss, the charging pile may not work properly. This not only affects the user's normal charging needs, but may also cause users to distrust the charging service, resulting in a decline in service quality.

[0003] In the prior art, it is not easy to quickly identify abnormal data in the platform, which makes it impossible to significantly improve the accuracy and response speed of fault detection, increases service interruptions caused by faults, and is not easy to predict the operating status of charging pile equipment at future times. It is impossible to identify in advance the key factors affecting the operating failure of charging pile equipment, and it is not easy to take measures in advance, which increases the risk of equipment failure. At the same time, it is not easy to issue early warnings based on key failure factors, and it is not easy to dynamically adjust the operating parameters of the charging pile equipment, so that the equipment cannot operate in the best state, thereby reducing the equipment life.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related technology, the present invention proposes a charging service platform data analysis method and system based on the Internet of Things to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a charging service platform data analysis method based on the Internet of Things is provided, and the charging service platform data analysis method comprises the following steps: S1. Based on the Internet of Things technology, obtain the real-time operation data of the charging service platform, pre-process the real-time operation data, and extract the key operation characteristic data of the charging service platform; S2. Analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; S3. Based on the abnormal operation data, a charging fault prediction model is established, and the charging fault prediction model is used to predict the operation status of the charging pile equipment at future times, and the key factors affecting the operation failure of the charging pile equipment are identified; S4. Issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

[0007] Further, using a fault diagnosis algorithm to analyze the extracted key operating characteristic data and identifying abnormal operating data in the current charging service platform includes the following steps: S21. Obtain the historical status record of the charging service platform from the extracted key operation feature data, count the abnormal frequency of the charging pile equipment in operation, and calculate the distribution ratio of various abnormalities at different times and for different charging pile equipment; S22. Use frequency statistics technology to conduct in-depth analysis of the abnormal distribution ratio in historical key operating characteristic data; based on the analysis results, build an abnormal data identification model for the charging service platform; S23. Deploy the abnormal data recognition model to the area where abnormalities of charging pile equipment are high. If the value in the high-incidence area is greater than the preset threshold, use the fault diagnosis algorithm to diagnose the current key operating characteristic data and mark the abnormal operating data in the current charging service platform.

[0008] Furthermore, the abnormal data recognition model is deployed to the abnormal high-incidence area of ​​the charging pile equipment. If the value of the high-incidence area is greater than the preset threshold, the fault diagnosis algorithm is used to diagnose the current key operation characteristic data, and the abnormal operation data in the current charging service platform is marked, including the following steps: S231, using a fault diagnosis algorithm to analyze the operating characteristic data, and screen out a preliminary characteristic parameter subset that affects the abnormality of the charging pile equipment as the core parameters; S232, initializing fault diagnosis algorithm parameters, performing binary conversion on each characteristic parameter, calculating the correlation and adaptability scores between characteristic parameters, and evaluating their importance to abnormality identification; S233, based on the decreasing method, calculating the step size scaling factor, and dynamically adjusting the change amplitude and feature weight of each abnormal feature parameter; S234, performing random disturbance adjustment on the operation characteristic parameters, and selecting the characteristic parameters with the highest adaptability score as the preferred characteristic parameters to form the core characteristic set of the area with high incidence of abnormal charging pile equipment; S235, performing chaos perturbation optimization on the preferred characteristic parameters, recalculating the adaptability score, and comparing the optimized score with the original preferred characteristic parameter score, and retaining the best abnormal characteristic parameters; S236: Determine whether the fault diagnosis algorithm has reached the maximum number of iterations. If so, output the best abnormal characteristic parameters as the operation abnormality data in the current charging service platform. Otherwise, return to step S232 to continue optimization.

[0009] Furthermore, the operation characteristic parameters are randomly disturbed and adjusted, and the characteristic parameters with the highest adaptability score are selected as the preferred characteristic parameters to form the core characteristic set of the abnormal high-incidence area of ​​charging pile equipment, including the following steps: S2341, perform random disturbance adjustment on the characteristic parameters, and increase diversity by changing the characteristic parameter values; S2342, the adaptive score of the perturbed feature parameters is calculated again to evaluate the importance of each feature parameter in anomaly identification; S2343. According to the recalculated adaptability score, the feature parameters with the best performance are selected to form a set of preferred feature parameters as core candidate features; S2344. Use the optimal feature parameter set to analyze abnormal high-incidence areas, and finally form a core feature set of abnormal high-incidence areas of charging pile equipment.

[0010] Furthermore, based on the abnormal operation data, a charging fault prediction model is established, and the charging fault prediction model is used to predict the operation status of the charging pile equipment at a future moment, and the key factors affecting the operation failure of the charging pile equipment are identified, including the following steps: S31, dividing the identified abnormal operation data set in the current charging service platform into a training set and a test set; S32, randomly initializing the parameters and the maximum number of iterations of the optimization algorithm, and setting the value range of the hyperparameters of the charging fault prediction model; S33, optimizing the hyperparameters of the charging fault prediction model by using an optimization algorithm to obtain optimal hyperparameters, and establishing a final charging fault prediction model based on the optimal hyperparameters; S34. Use the final charging fault prediction model to predict the operating status of the charging pile equipment at a future time, and identify key factors that affect the operating failure of the charging pile equipment.

[0011] Furthermore, the optimization algorithm is used to optimize the hyperparameters of the charging fault prediction model to obtain the optimal hyperparameters, and the final charging fault prediction model is established based on the optimal hyperparameters, including the following steps: S331. Randomly generate an initial candidate configuration set from the hyperparameter space of the charging fault prediction model, and initialize key parameters of the optimization algorithm; S332, calculating the fitness value of each hyperparameter candidate configuration, and dividing the candidate configurations into different optimization groups based on the fitness value; S333. Adjust the distribution of alternative configurations of hyperparameters according to the adaptive optimization rule, concentrate the alternative configurations with high fitness in the key areas that affect the model performance, and gradually eliminate the alternative configurations with low fitness; S334. In each optimization group, a number of hyperparameter candidate configurations with the best fitness are selected through a competition mechanism and enter the next round of iteration as the main configuration; S335. Repeat steps S332 to S334 until the maximum number of iterations is reached, output the hyperparameters with the best fitness, and establish the final charging fault prediction model based on the optimal hyperparameters.

[0012] According to another aspect of the present invention, a charging service platform data analysis system based on the Internet of Things is also provided, and the charging service platform data analysis system includes: The data acquisition module is used to obtain the real-time operation data of the charging service platform based on the Internet of Things technology, and pre-process the real-time operation data to extract the key operation characteristic data of the charging service platform; A fault analysis module is used to analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; A fault prediction module is used to establish a charging fault prediction model based on abnormal operation data, and use the charging fault prediction model to predict the operation status of the charging pile equipment at future moments, and identify key factors that affect the operation failure of the charging pile equipment; The dynamic adjustment module is used to issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

[0013] The beneficial effects of the present invention are: 1. The present invention analyzes key operating characteristic data through a fault diagnosis algorithm, quickly identifies abnormal data in the platform, significantly improves the accuracy and response speed of fault detection, reduces service interruptions caused by faults, and uses operating abnormality data to establish a charging fault prediction model to predict the operating status of the charging pile equipment at future times, identify fault trends in advance, and help the operation and maintenance team take measures in advance to reduce the risk of equipment failure. Early warnings are issued based on key fault factors, and the operating parameters of the charging pile equipment are dynamically adjusted so that the equipment can operate in the best state, thereby extending the equipment life and improving charging efficiency.

[0014] 2. The present invention analyzes the distribution of historical abnormal data, constructs an abnormal data recognition model and deploys it to high-incidence areas to achieve accurate abnormality detection and rapid fault diagnosis, effectively improving the fault recognition efficiency of the charging service platform, reducing service interruptions, and improving the stability and operational reliability of the platform, while optimizing the operation and maintenance management costs.

[0015] 3. The present invention optimizes the hyperparameters of the charging fault prediction model, accurately establishes a prediction model, predicts the future operating status of the equipment, identifies fault trends and key factors in advance, effectively reduces the risk of equipment failure, improves the platform's operating stability and operation and maintenance efficiency, and at the same time ensures the user's charging experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of a charging service platform data analysis method based on the Internet of Things according to an embodiment of the present invention; Figure 2 It is a principle block diagram of a charging service platform data analysis system based on the Internet of Things according to an embodiment of the present invention.

[0018] In the figure: 1. Data acquisition module; 2. Fault analysis module; 3. Fault prediction module; 4. Dynamic adjustment module. DETAILED DESCRIPTION

[0019] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0020] According to an embodiment of the present invention, a charging service platform data analysis method and system based on the Internet of Things are provided.

[0021] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the charging service platform data analysis method based on the Internet of Things according to an embodiment of the present invention, the charging service platform data analysis method includes the following steps: S1. Based on the Internet of Things technology, obtain the real-time operation data of the charging service platform, pre-process the real-time operation data, and extract the key operation characteristic data of the charging service platform; Specifically, the operating status of the charging service platform is monitored in real time through sensors (such as current, voltage, and temperature sensors), and the charging service platform operating data is transmitted and acquired through wired networks (such as Ethernet) or wireless networks (such as Wi-Fi, 4G / 5G, and NB-IoT).

[0022] Specifically, real-time operation data includes equipment operation status data, user charging data, usage behavior data, fault and abnormality data, etc.

[0023] Specifically, key operating characteristic data include electrical performance characteristics, equipment health characteristics, communication and network characteristics, user behavior characteristics, etc.

[0024] S2. Analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; Specifically, the abnormal operation data includes abnormal electrical parameter data, abnormal communication status data, abnormal equipment operation status data, abnormal user behavior data, abnormal statistics and historical data, etc.

[0025] S3. Based on the abnormal operation data, a charging fault prediction model is established, and the charging fault prediction model is used to predict the operation status of the charging pile equipment at future moments, and key factors affecting the operation failure of the charging pile equipment are identified; Specifically, the key factors that affect the operation failure of charging pile equipment include voltage fluctuation, current overload, abnormal temperature, sensor failure, equipment aging, network interruption, overload usage, excessive humidity, etc.

[0026] S4. Issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

[0027] It should be explained that the operating status of the equipment is monitored in real time, and the key factors that may cause the current failure are identified in combination with the charging fault prediction model; when it is detected that the key fault factor exceeds the safety threshold (such as excessive current, network interruption, etc.), an early warning is immediately issued to the operation and maintenance personnel and the platform; in response to the fault warning situation, the voltage, current and other operating parameters of the charging pile are dynamically adjusted (such as limiting power output or reducing current); in the case of minor abnormalities, the equipment is switched to a safe mode (such as low-load operation) to avoid further damage; the charging pile load is reallocated according to the equipment status and user needs to reduce the frequency of use of abnormal equipment; the data in the early warning signal is further analyzed to locate the source of the fault (such as equipment hardware, communication network or environmental reasons); historical data is compared with current data to quickly confirm whether manual intervention or automatic repair is required; fault diagnosis and real-time monitoring data are used to continuously optimize the charging fault prediction model to improve the accuracy of the early warning; combined with the results of real-time data analysis, the equipment utilization rate is optimized to ensure the continuity and reliability of charging services; after the adjustment is completed, the early warning signal, equipment status and operating parameters are feedback recorded to provide data support for future operation and maintenance and model optimization.

[0028] In this optional embodiment, based on the Internet of Things technology, real-time operation data of the charging service platform is obtained, and the real-time operation data is preprocessed to extract key operation feature data of the charging service platform, including the following steps: S11, obtaining corresponding duplicate data in the real-time operation data of the charging service platform, and performing denoising, filtering and smoothing on the duplicate data; S12, connecting the unprocessed data rows in the real-time operation data of the charging service platform to generate a new data table, associating different data tables through external key values, generating a complete data table, and obtaining an accurate data set; S13. Based on the obtained accurate data set, a key characteristic curve is constructed, and the change characteristic index of the operating state of the charging device is extracted by calculating the difference in the change amplitude of the characteristic curve at adjacent moments; S14, preset a threshold value of the amplitude, if the difference of the amplitude of change exceeds the threshold, then add a new key operation moment set; otherwise, retain the existing key moment set; S15. Check the distribution of key operating moments. If the distribution is too dense, merge adjacent moments. Otherwise, retain the current key moment set as the key operating characteristic data of the charging service platform.

[0029] In this optional embodiment, analyzing the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform includes the following steps: S21. Obtain the historical status record of the charging service platform from the extracted key operation feature data, count the abnormal frequency of the charging pile equipment in operation, and calculate the distribution ratio of various abnormalities at different times and for different charging pile equipment; S22. Use frequency statistics technology to conduct in-depth analysis of the abnormal distribution ratio in historical key operating characteristic data; based on the analysis results, build an abnormal data identification model for the charging service platform; S23. Deploy the abnormal data recognition model to the area where abnormalities of charging pile equipment are high. If the value in the high-incidence area is greater than the preset threshold, use the fault diagnosis algorithm to diagnose the current key operating characteristic data and mark the abnormal operating data in the current charging service platform.

[0030] In this optional embodiment, the abnormal data recognition model is deployed to the abnormal high-incidence area of ​​the charging pile equipment. If the value of the high-incidence area is greater than the preset threshold, the fault diagnosis algorithm is used to diagnose the current key operation characteristic data, and the abnormal operation data in the current charging service platform is marked, including the following steps: S231, using a fault diagnosis algorithm to analyze the operating characteristic data, and screen out a preliminary characteristic parameter subset that affects the abnormality of the charging pile equipment as the core parameters; S232, initializing fault diagnosis algorithm parameters, performing binary conversion on each characteristic parameter (i.e., encoding conversion principle), calculating the correlation and adaptability scores between characteristic parameters, and evaluating their importance to abnormality identification; S233, based on the decreasing method (i.e., nonlinear decreasing step length), calculating the step length scaling factor, and dynamically adjusting the variation range and feature weight of each abnormal feature parameter; S234, performing random disturbance adjustment on the operation characteristic parameters, and selecting the characteristic parameters with the highest adaptability score as the preferred characteristic parameters to form the core characteristic set of the area with high incidence of abnormal charging pile equipment; S235, performing chaos perturbation optimization on the preferred characteristic parameters (i.e., elite particles), recalculating the adaptability score, and comparing the optimized score with the original preferred characteristic parameter score, and retaining the best abnormal characteristic parameters; S236: Determine whether the fault diagnosis algorithm has reached the maximum number of iterations. If so, output the best abnormal characteristic parameters as the operation abnormality data in the current charging service platform. Otherwise, return to step S232 to continue optimization.

[0031] Specifically, the fault diagnosis algorithm is an improved krill swarm algorithm. The krill swarm algorithm is a meta-heuristic swarm intelligence algorithm that simulates the process of a krill swarm responding to a specific danger and environment and gradually increasing the population density. In order to enable the krill swarm algorithm to handle feature selection problems, the present invention discretizes it using the coding conversion principle, and in order to further improve the global search capability of the krill swarm algorithm, it is improved by adopting nonlinear step size reduction and elite particle local search.

[0032] In this optional embodiment, the formula for calculating the step size scaling factor is: ; In the formula, η i Indicates i The step size scaling factor for the iteration; η 0 represents the initial step size scaling factor; λ Represents the decay rate (controls the speed at which the step size decreases); k Represents the nonlinear control index (determines the degree of nonlinearity of the decrease, usually (0< k ≤1); e Represents a natural constant.

[0033] In this optional embodiment, the operation characteristic parameters are randomly disturbed and adjusted, and the characteristic parameters with the highest adaptability score are selected as the preferred characteristic parameters. The core characteristic set of the abnormal high-incidence area of ​​charging pile equipment is formed, including the following steps: S2341, perform random disturbance adjustment on the characteristic parameters, and increase diversity by changing the characteristic parameter values; S2342, the adaptive score of the perturbed feature parameters is calculated again to evaluate the importance of each feature parameter in anomaly identification; S2343. According to the recalculated adaptability score, the feature parameters with the best performance are selected to form a set of preferred feature parameters as core candidate features; S2344. Use the optimal feature parameter set to analyze abnormal high-incidence areas, and finally form a core feature set of abnormal high-incidence areas of charging pile equipment.

[0034] In this optional embodiment, a charging fault prediction model is established based on the abnormal operation data, and the charging fault prediction model is used to predict the operation status of the charging pile device at a future moment, and identifying the key factors affecting the operation failure of the charging pile device includes the following steps: S31, dividing the identified abnormal operation data set in the current charging service platform into a training set and a test set; S32, randomly initializing the parameters and the maximum number of iterations of the optimization algorithm, and setting the value range of the hyperparameters of the charging fault prediction model; S33, optimizing the hyperparameters of the charging fault prediction model by using an optimization algorithm to obtain optimal hyperparameters, and establishing a final charging fault prediction model based on the optimal hyperparameters; S34. Use the final charging fault prediction model to predict the operating status of the charging pile equipment at a future time, and identify key factors that affect the operating failure of the charging pile equipment.

[0035] In this optional embodiment, the hyperparameters of the charging fault prediction model are optimized by using an optimization algorithm to obtain the optimal hyperparameters, and the final charging fault prediction model is established based on the optimal hyperparameters, including the following steps: S331. Randomly generate an initial candidate configuration set from the hyperparameter space of the charging fault prediction model, and initialize key parameters of the optimization algorithm; S332, calculating the fitness value of each hyperparameter candidate configuration, and dividing the candidate configurations into different optimization groups based on the fitness value; S333. According to the adaptive optimization rule (i.e., the adaptive mechanism), the distribution of the alternative configurations of the hyperparameters is adjusted, the alternative configurations with high fitness are concentrated in the key areas that affect the model performance, and the alternative configurations with low fitness are gradually eliminated; S334. In each optimization group (i.e., within a niche), a number of hyperparameter candidate configurations with the best fitness are selected through a competition mechanism (i.e., competition exclusion within the niche) and enter the next round of iteration as the main configuration; S335. Repeat steps S332 to S334 until the maximum number of iterations is reached, output the hyperparameters with the best fitness, and establish the final charging fault prediction model based on the optimal hyperparameters.

[0036] Specifically, the optimization algorithm is a microhabitat-based adaptive invasive weed optimization algorithm. The present invention adds microhabitat ideas and adaptive mechanisms to traditional invasive weed optimization algorithms to obtain an adaptive weed invasion algorithm based on microhabitat ideas. The microhabitat idea is used to increase the population diversity of the algorithm.

[0037] In this optional embodiment, the competition mechanism formula is: ; In the formula, P ( n ) indicates the n The number of hyperparameter candidate configurations selected as the main configuration to enter the next iteration in the optimization group; H max Indicates the maximum number of alternative hyperparameter configurations set; K ( n ) indicates the n The number of alternative hyperparameter configurations in an optimization group; sum ( K ) represents the sum of the number of alternative hyperparameter configurations in all optimization groups.

[0038] According to another embodiment of the present invention, Figure 2 As shown, a charging service platform data analysis system based on the Internet of Things is also provided, and the charging service platform data analysis system includes: Data acquisition module 1, used to acquire real-time operation data of the charging service platform based on the Internet of Things technology, pre-process the real-time operation data, and extract key operation characteristic data of the charging service platform; Fault analysis module 2, used to analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; Fault prediction module 3, used to establish a charging fault prediction model based on the abnormal operation data, and use the charging fault prediction model to predict the operation status of the charging pile equipment at a future time, and identify the key factors affecting the operation failure of the charging pile equipment; The dynamic adjustment module 4 is used to issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

[0039] Specifically, the data acquisition module 1 is connected to the fault prediction module 3 via the fault analysis module 2 , and the fault prediction module 3 is connected to the dynamic adjustment module 4 .

[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging service platform data analysis method based on the Internet of Things, characterized in that: The charging service platform data analysis method comprises the following steps: S1. Based on the Internet of Things technology, obtain the real-time operation data of the charging service platform, pre-process the real-time operation data, and extract the key operation characteristic data of the charging service platform; S2. Analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; S3. Based on the abnormal operation data, a charging fault prediction model is established, and the charging fault prediction model is used to predict the operation status of the charging pile equipment at future times, and the key factors affecting the operation failure of the charging pile equipment are identified; S4. Issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

2. According to the data analysis method of a charging service platform based on the Internet of Things according to claim 1, it is characterized in that: The method of obtaining the real-time operation data of the charging service platform based on the Internet of Things technology, preprocessing the real-time operation data, and extracting the key operation characteristic data of the charging service platform includes the following steps: S11, obtaining corresponding duplicate data in the real-time operation data of the charging service platform, and performing denoising, filtering and smoothing on the duplicate data; S12, connecting the unprocessed data rows in the real-time operation data of the charging service platform to generate a new data table, associating different data tables through external key values, generating a complete data table, and obtaining an accurate data set; S13. Based on the obtained accurate data set, a key characteristic curve is constructed, and the change characteristic index of the operating state of the charging device is extracted by calculating the difference in the change amplitude of the characteristic curve at adjacent moments; S14, preset a threshold value of the amplitude, if the difference of the amplitude of change exceeds the threshold, then add a set of key operating moments; otherwise, retain the existing set of key moments; S15. Check the distribution of key operating moments. If the distribution is too dense, merge adjacent moments. Otherwise, retain the current key moment set as the key operating characteristic data of the charging service platform.

3. According to the data analysis method of a charging service platform based on the Internet of Things in claim 1, it is characterized in that: The method of analyzing the extracted key operating characteristic data by using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform includes the following steps: S21. Obtain the historical status record of the charging service platform from the extracted key operation feature data, count the abnormal frequency of the charging pile equipment in operation, and calculate the distribution ratio of various abnormalities at different times and for different charging pile equipment; S22. Use frequency statistics technology to conduct in-depth analysis of the abnormal distribution ratio in historical key operating characteristic data; based on the analysis results, build an abnormal data identification model for the charging service platform; S23. Deploy the abnormal data recognition model to the area where abnormalities of charging pile equipment are high. If the value in the high-incidence area is greater than the preset threshold, use the fault diagnosis algorithm to diagnose the current key operating characteristic data and mark the abnormal operating data in the current charging service platform.

4. The data analysis method of a charging service platform based on the Internet of Things according to claim 3 is characterized in that: The abnormal data recognition model is deployed to the abnormal high-incidence area of ​​the charging pile equipment. If the value of the high-incidence area is greater than the preset threshold, the fault diagnosis algorithm is used to diagnose the current key operation characteristic data, and the abnormal operation data in the current charging service platform is marked, which includes the following steps: S231, using a fault diagnosis algorithm to analyze the operating characteristic data, and screen out a preliminary characteristic parameter subset that affects the abnormality of the charging pile equipment as the core parameters; S232, initializing fault diagnosis algorithm parameters, performing binary conversion on each characteristic parameter, calculating the correlation and adaptability scores between characteristic parameters, and evaluating their importance to abnormality identification; S233, based on the decreasing method, calculating the step size scaling factor, and dynamically adjusting the change amplitude and feature weight of each abnormal feature parameter; S234, performing random disturbance adjustment on the operation characteristic parameters, and selecting the characteristic parameters with the highest adaptability score as the preferred characteristic parameters to form the core characteristic set of the area with high incidence of abnormal charging pile equipment; S235, performing chaos perturbation optimization on the preferred characteristic parameters, recalculating the adaptability score, and comparing the optimized score with the original preferred characteristic parameter score, and retaining the best abnormal characteristic parameters; S236: Determine whether the fault diagnosis algorithm has reached the maximum number of iterations. If so, output the best abnormal characteristic parameters as the operation abnormality data in the current charging service platform. Otherwise, return to step S232 to continue optimization.

5. The data analysis method of a charging service platform based on the Internet of Things according to claim 4 is characterized in that: The formula for calculating the step size scaling factor is: ； In the formula, η i Indicates i The step size scaling factor for the iteration; η 0 represents the initial step size scaling factor; λ represents the decay rate; k represents the nonlinear control index; e Represents a natural constant.

6. The data analysis method of a charging service platform based on the Internet of Things according to claim 4 is characterized in that: The random disturbance adjustment of the operating characteristic parameters and the selection of the characteristic parameters with the highest adaptability score as the preferred characteristic parameters to form the core characteristic set of the abnormal high-incidence area of ​​charging pile equipment include the following steps: S2341, perform random disturbance adjustment on the characteristic parameters, and increase diversity by changing the characteristic parameter values; S2342, the adaptive score of the perturbed feature parameters is calculated again to evaluate the importance of each feature parameter in anomaly identification; S2343. According to the recalculated adaptability score, the feature parameters with the best performance are selected to form a set of preferred feature parameters as core candidate features; S2344. Use the optimal feature parameter set to analyze abnormal high-incidence areas, and finally form a core feature set of abnormal high-incidence areas of charging pile equipment.

7. The data analysis method of a charging service platform based on the Internet of Things according to claim 1 is characterized in that: The method of establishing a charging fault prediction model based on the abnormal operation data, and using the charging fault prediction model to predict the operation status of the charging pile equipment at a future moment, and identifying the key factors affecting the operation failure of the charging pile equipment includes the following steps: S31, dividing the identified abnormal operation data set in the current charging service platform into a training set and a test set; S32, randomly initializing the parameters and the maximum number of iterations of the optimization algorithm, and setting the value range of the hyperparameters of the charging fault prediction model; S33, optimizing the hyperparameters of the charging fault prediction model by using an optimization algorithm to obtain optimal hyperparameters, and establishing a final charging fault prediction model based on the optimal hyperparameters; S34. Use the final charging fault prediction model to predict the operating status of the charging pile equipment at a future time, and identify key factors that affect the operating failure of the charging pile equipment.

8. The method for analyzing data of a charging service platform based on the Internet of Things according to claim 7, characterized in that: The method of optimizing the hyperparameters of the charging fault prediction model by using an optimization algorithm to obtain the optimal hyperparameters, and establishing the final charging fault prediction model based on the optimal hyperparameters includes the following steps: S331. Randomly generate an initial candidate configuration set from the hyperparameter space of the charging fault prediction model, and initialize key parameters of the optimization algorithm; S332, calculating the fitness value of each hyperparameter candidate configuration, and dividing the candidate configurations into different optimization groups based on the fitness value; S333. Adjust the distribution of alternative configurations of hyperparameters according to the adaptive optimization rule, concentrate the alternative configurations with high fitness in the key areas that affect the model performance, and gradually eliminate the alternative configurations with low fitness; S334. In each optimization group, a number of hyperparameter candidate configurations with the best fitness are selected through a competition mechanism and enter the next round of iteration as the main configuration; S335. Repeat steps S332 to S334 until the maximum number of iterations is reached, output the hyperparameters with the best fitness, and establish the final charging fault prediction model based on the optimal hyperparameters.

9. The method for analyzing data of a charging service platform based on the Internet of Things according to claim 8, characterized in that: The competition mechanism formula is: ； In the formula, P ( n ) indicates the n The number of hyperparameter candidate configurations selected as the main configuration to enter the next iteration in the optimization group; H max Indicates the maximum number of alternative hyperparameter configurations set; K ( n ) indicates the n The number of alternative hyperparameter configurations in an optimization group; sum ( K ) represents the sum of the number of alternative hyperparameter configurations in all optimization groups.

10. A charging service platform data analysis system based on the Internet of Things, used to implement the charging service platform data analysis method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The charging service platform data analysis system includes: The data acquisition module is used to obtain the real-time operation data of the charging service platform based on the Internet of Things technology, and pre-process the real-time operation data to extract the key operation characteristic data of the charging service platform; A fault analysis module is used to analyze the extracted key operating characteristic data using a fault diagnosis algorithm to identify abnormal operating data in the current charging service platform; A fault prediction module is used to establish a charging fault prediction model based on abnormal operation data, and use the charging fault prediction model to predict the operation status of the charging pile equipment at future moments, and identify key factors that affect the operation failure of the charging pile equipment; The dynamic adjustment module is used to issue fault warnings based on key fault factors, dynamically adjust the operating parameters of the charging pile equipment, and optimize the operation of the charging service platform in combination with real-time monitoring data.

Images