Charging pile data intelligent monitoring method and system based on Internet of Things

Abstract

The invention discloses a charging pile data intelligent monitoring method and system based on the Internet of Things, and belongs to the technical field of dynamic monitoring. Based on the Internet of Things terminal, calling an equipment normal operation data log and an equipment abnormal operation data log of the charging pile, and respectively obtaining power jump time; establishing equipment operation power data normal and abnormal sensing jump time sets; constructing a normal and abnormal sensing jump time difference sequence of the equipment operation power data, and arranging the sequence into a normal and abnormal sensing jump time difference vector of the equipment operation power data; constructing a two-dimensional hopping characteristic matrix based on the normal and abnormal sensing hopping time difference vector of the equipment operation power data; on the basis of the two-dimensional jump feature matrix, the probability that the charging pile is abnormal is calculated; according to the intelligent monitoring method and system for the charging pile, the monitoring accuracy is improved, self-adaptive learning and optimization of the system are achieved, and the practical and intelligent process of intelligent monitoring of the charging pile is effectively promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic monitoring, and particularly to an intelligent monitoring method and system for charging pile data based on the Internet of Things. Background Technique

[0002] With the rapid popularization of new energy vehicles, charging piles, as one of their core infrastructure facilities, have shown an exponential growth trend in terms of quantity and usage frequency. In order to improve the operation efficiency and safety of charging piles, the state monitoring and data management technologies of charging equipment have been continuously developed. Currently, the Internet of Things technology is widely applied to the remote monitoring, status perception, and data collection links of charging piles, enabling the operation status of a large number of devices to be real-time feedback to the operation platform. In the traditional monitoring system, the operation status of charging piles is mainly judged by collecting basic operation data such as current, voltage, and power. However, in the face of the actual scenarios of large-scale deployment and dynamic operation, it is difficult to meet the accuracy and timeliness requirements of fault identification only by static or periodic data analysis. Especially in the initial stage of abnormal states or when instantaneous faults occur, traditional technologies are insufficient in terms of perception agility and response efficiency.

[0003] Existing charging pile monitoring methods mostly focus on the macroscopic judgment of equipment status or rough alarms based on abnormal thresholds, lacking the ability of in-depth modeling and intelligent identification of power fluctuation characteristics. Especially when intermittent and sudden operation abnormalities occur in charging piles, existing technologies are difficult to accurately identify their abnormal trends and evolution laws, and there are often problems such as missed alarms, false alarms, or response lags. In addition, most current methods fail to effectively utilize the historical data structures of charging piles in normal and abnormal operation states for comparative modeling, and cannot extract discriminative identification indicators from time series characteristics, resulting in a lack of refinement ability in abnormal prediction and early warning. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent monitoring method and system for charging pile data based on the Internet of Things to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: An intelligent monitoring method for charging pile data based on the Internet of Things, the method comprising the following steps: Step S1: Based on the Internet of Things terminal, retrieve the device normal operation data log and the device abnormal operation data log of the charging pile, and respectively obtain the power jump time; establish a normal and abnormal perception jump time set of the device operation power data; Step S2: Calculate the difference between every two consecutive times in the times included in the normal and abnormal perception jump time sets of the device operation power data respectively, and construct a normal and abnormal perception jump time difference sequence of the device operation power data; Step S3: Organize the normal and abnormal perception jump time difference sequence of the device operation power data into a normal and abnormal perception jump time difference vector of the device operation power data; based on the normal and abnormal perception jump time difference vector of the device operation power data, construct a two-dimensional jump feature matrix; Step S4: Based on the two-dimensional jump feature matrix, calculate the probability of the charging pile having an abnormality; preset a threshold value, analyze and give an early warning.

[0006] As a preferred solution of the intelligent monitoring method for charging pile data based on the Internet of Things according to the present invention, based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform, and according to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state; Retrieve the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state; According to the power jump times of the charging pile in the historical normal working state and the historical abnormal working state, establish a normal and abnormal perception jump time set of the device operation power data, and the time set is recorded in chronological order.

[0007] In the present invention, this step compresses and models the originally massive and continuous device operation data through the key feature point of "jump", and identifies the time nodes significantly related to the device state change. By focusing on the jump time, a large amount of invalid or redundant data is eliminated, providing more efficient data support for subsequent modeling and identification; through this step, the complex and huge operation data is simplified into a set of key jump events, thus significantly reducing the complexity of data processing, enhancing the sensitivity and identification efficiency of the monitoring model to abnormal states, and helping to improve the real-time early warning ability of the system.

[0008] As a preferred solution of the intelligent monitoring method for charging pile data based on the Internet of Things according to the present invention, the difference between every two consecutive times in the times respectively included in the normal and abnormal perception jump time sets of the device operating power data is calculated, and a normal perception jump time difference sequence and an abnormal perception jump time difference sequence of the device operating power data are obtained, which are respectively denoted as and , where represents the i-th difference obtained by calculating the difference between every two consecutive times in the times included in the normal perception jump time set of the device operating power data, and I represents the total number of differences obtained by calculating the difference between every two consecutive times in the times included in the normal perception jump time set of the device operating power data. represents the j-th difference obtained by calculating the difference between every two consecutive times in the times included in the abnormal perception jump time set of the device operating power data, and J represents the total number of differences obtained by calculating the difference between every two consecutive times in the times included in the abnormal perception jump time set of the device operating power data.

[0009] As a preferred solution of the intelligent monitoring method for charging pile data based on the Internet of Things according to the present invention, the normal perception jump time difference sequence and the abnormal perception jump time difference sequence of the device operating power data are respectively sorted into normal and abnormal perception jump time difference vectors of the device operating power data, which are denoted as and , where , ; Based on the normal and abnormal perception jump time difference vectors of the device operating power data, a two-dimensional jump feature matrix is constructed as follows: ; where represents the two-dimensional jump feature matrix, represents the (I + J)-th difference, represents the perception jump type of the (I + J)-th difference. Among them, if the (I + J)-th difference is within the normal perception jump time difference sequence of the device operating power data, the perception jump type of the (I + J)-th difference is a normal perception jump and is marked as 0. If the (I + J)-th difference is within the abnormal perception jump time difference sequence of the device operating power data, the perception jump type of the (I + J)-th difference is an abnormal perception jump and is marked as 1.

[0010] In the present invention, the time differences between normal and abnormal states are sorted into vectors and uniformly constructed into a two-dimensional jump feature matrix, which contains the magnitude of the difference and the labels of their respective categories (normal or abnormal); as a form of structured data representation, the matrix not only retains the time information of the jump differences, but also introduces category labels, which is conducive to further applying algorithms such as machine learning and statistical analysis for identification and classification processing; through this step, the transformation of unstructured time series difference data into a structured feature space is realized, the pattern learning ability of the system in dealing with complex state changes is enhanced, and the insight into the evolution trend of abnormal states is further improved.

[0011] As a preferred solution of the intelligent monitoring method for charging pile data based on the Internet of Things according to the present invention, based on the two-dimensional jump feature matrix, the probability of the charging pile being abnormal is calculated, and the calculation formula is as follows: ; Wherein, represents the jump time difference at the time point corresponding to the current operating power data of the charging pile, represents the probability of the charging pile being abnormal; a preset probability threshold, if the probability of the charging pile being abnormal is greater than or equal to the probability threshold, it is determined that the charging pile currently has an abnormality, and a warning is issued; The jump time difference at the time point corresponding to the current operating power data of the charging pile is updated to the two-dimensional jump feature matrix for dynamic update.

[0012] In the present invention, by using the constructed two-dimensional jump feature matrix, the abnormal probability corresponding to the current jump difference of the charging pile is calculated and compared with a preset threshold to determine whether to trigger a warning. At the same time, the current difference is dynamically updated to the matrix to achieve online learning and adaptive optimization. This step introduces a probability modeling method, which is different from the traditional single-point anomaly detection method based on threshold judgment, and can more comprehensively evaluate the degree of proximity between the current state of the charging pile and the historical normal / abnormal patterns, realizing a more flexible and intelligent warning mechanism. By dynamically calculating the abnormal probability and real-time updating the feature matrix, not only the timeliness and accuracy of charging pile fault detection are improved, but also the system has the ability of adaptive learning, can continuously optimize the monitoring accuracy, reduce the probability of false alarms and missed alarms, and enhance the intelligent level of the entire monitoring system.

[0013] An intelligent monitoring system for charging pile data based on the Internet of Things, the system includes: a data acquisition and time set construction module, a difference sequence construction module, a vector and matrix construction module, and a probability calculation and analysis warning module; The data acquisition and time set construction module: Based on the Internet of Things terminal, retrieve the device normal operation data log and device abnormal operation data log of the charging pile, and respectively obtain the power jump times; establish the normal and abnormal perception jump time sets of the device operation power data. The difference sequence construction module: Calculate the difference between every two consecutive times in the times included in the normal and abnormal perception jump time sets of the device operation power data respectively, and construct the normal and abnormal perception jump time difference sequences of the device operation power data. The vector and matrix construction module: Organize the normal and abnormal perception jump time difference sequences of the device operation power data into normal and abnormal perception jump time difference vectors of the device operation power data; based on the normal and abnormal perception jump time difference vectors of the device operation power data, construct a two-dimensional jump feature matrix. The probability calculation and analysis warning module: Based on the two-dimensional jump feature matrix, calculate the probability of the charging pile being abnormal; preset a threshold, analyze and issue a warning.

[0014] Further, the data acquisition and time set construction module includes a data acquisition unit and a time set construction unit; The data acquisition unit: Based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform, and according to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state; Retrieve the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state; The time set construction unit: According to the power jump times of the charging pile in the historical normal working state and historical abnormal working state, establish the normal and abnormal perception jump time sets of the device operation power data, and the time sets are recorded in chronological order.

[0015] Further, the difference sequence construction module includes a difference sequence construction unit; The difference sequence construction unit: Calculate the difference between every two consecutive times in the times included in the normal and abnormal perception jump time sets of the device operation power data respectively, and obtain the normal perception jump time difference sequence and abnormal perception jump time difference sequence of the device operation power data.

[0016] Further, the vector and matrix construction module includes a vector construction unit and a matrix construction unit; The vector construction unit: respectively organize the normal perception jump time difference sequence of the device operation power data and the abnormal perception jump time difference sequence of the device operation power data into the normal and abnormal perception jump time difference vectors of the device operation power data; The matrix construction unit: based on the normal and abnormal perception jump time difference vectors of the device operation power data, construct a two-dimensional jump feature matrix.

[0017] Further, the probability calculation and analysis warning module includes a probability calculation unit and an analysis warning unit; The probability calculation unit: based on the two-dimensional jump feature matrix, calculate the probability of the charging pile being abnormal; The analysis warning unit: preset a probability threshold. If the probability of the charging pile being abnormal is greater than or equal to the probability threshold, it is determined that the charging pile is currently abnormal, and a warning is issued; update the jump time difference at the time point corresponding to the current operation power data of the charging pile to the two-dimensional jump feature matrix for dynamic update.

[0018] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the intelligent monitoring method and system for charging pile data based on the Internet of Things provided by the present invention, the operation log of the charging pile is retrieved through the Internet of Things terminal, the power jump time is extracted, and the jump time set is constructed, effectively compressing the scale of the original data and improving the key state recognition efficiency. Subsequently, the adjacent jump time differences are calculated to form the difference sequences in the normal and abnormal states, further mining the operation stability and power fluctuation characteristics of the device. On this basis, the difference sequences are converted into vectors, and a two-dimensional jump feature matrix containing category labels is constructed to realize the conversion from unstructured time series to structured data and enhance the pattern recognition ability. Finally, the abnormal probability is calculated based on the feature matrix, and real-time warning is carried out in combination with the dynamic update mechanism, which not only improves the monitoring accuracy but also realizes the adaptive learning and optimization of the system. The overall solution has significant advantages such as high data processing efficiency, strong recognition sensitivity, and timely abnormal response, effectively promoting the practical and intelligent process of charging pile intelligent monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention.

[0020] Figure 1 is a step schematic diagram of an intelligent monitoring method for charging pile data based on the Internet of Things of the present invention; Figure 2It is a schematic structural diagram of an intelligent monitoring system for charging pile data based on the Internet of Things according to the present invention. Specific Embodiments

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] Please refer to Figure 1 , in the first embodiment: Provide an intelligent monitoring method for charging pile data based on the Internet of Things. The method includes the following steps: Step S1: Based on the Internet of Things terminal, retrieve the device normal operation data log and the device abnormal operation data log of the charging pile, and respectively obtain the power jump times; establish a set of normal and abnormal perception jump times for the device operation power data.

[0023] Specifically, based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform. According to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state; Obtain the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state; According to the power jump times of the charging pile in the historical normal working state and the historical abnormal working state, establish a set of normal and abnormal perception jump times for the device operation power data, and the time set is recorded in chronological order.

[0024] Step S2: Calculate the difference between every two consecutive times in the times included in the set of normal and abnormal perception jump times of the device operation power data respectively, and construct a difference sequence of the normal and abnormal perception jump times of the device operation power data.

[0025] Specifically, calculate the difference between every two consecutive times in the times included in the set of normal and abnormal perception jump times of the device operation power data respectively, to obtain a difference sequence of the normal perception jump times of the device operation power data and a difference sequence of the abnormal perception jump times of the device operation power data, which are respectively recorded as and , where represents the i-th difference obtained by calculating the difference between every two consecutive times in the set of times included in the normal perception jump time series of the device operating power data. I represents the total number of differences obtained by calculating the difference between every two consecutive times in the set of times included in the normal perception jump time series of the device operating power data. represents the j-th difference obtained by calculating the difference between every two consecutive times in the set of times included in the abnormal perception jump time series of the device operating power data. J represents the total number of differences obtained by calculating the difference between every two consecutive times in the set of times included in the abnormal perception jump time series of the device operating power data.

[0026] Step S3: Organize the normal and abnormal perception jump time difference sequences of the device operating power data into normal and abnormal perception jump time difference vectors of the device operating power data; based on the normal and abnormal perception jump time difference vectors of the device operating power data, construct a two-dimensional jump feature matrix.

[0027] Specifically, separately organize the normal perception jump time difference sequence of the device operating power data and the abnormal perception jump time difference sequence of the device operating power data into normal and abnormal perception jump time difference vectors of the device operating power data, denoted as and , where , ; Based on the normal and abnormal perception jump time difference vectors of the device operating power data, construct a two-dimensional jump feature matrix as follows: ; where represents the two-dimensional jump feature matrix, represents the (I + J)-th difference, represents the perception jump type of the (I + J)-th difference. Among them, if the (I + J)-th difference is within the normal perception jump time difference sequence of the device operating power data , then the perception jump type of the (I + J)-th difference is a normal perception jump and is marked as 0. If the (I + J)-th difference is within the abnormal perception jump time difference sequence of the device operating power data , then the perception jump type of the (I + J)-th difference is an abnormal perception jump and is marked as 1.

[0028] Step S4: Based on the two-dimensional jump feature matrix, calculate the probability of the charging pile having an abnormality; preset a threshold, analyze and issue a warning.

[0029] Specifically, based on the two-dimensional jump feature matrix, calculate the probability of the charging pile having an abnormality. The calculation formula is as follows: ; wherein, represents the jump time difference at the time point corresponding to the current operating power data of the charging pile, represents the probability of the charging pile having an abnormality; It should be noted that this formula uses the distance metric method to calculate the average absolute distance between the current difference and the historical normal difference (TN) and abnormal difference (TAN), and evaluates the abnormality probability through the ratio of the two; if is closer to the TN sequence (smaller numerator), then tends to 0 and is determined to be normal; if is closer to the TAN sequence, then tends to 1 and is determined to be abnormal; this formula can quantify the deviation degree between the current state and the normal / abnormal mode, avoiding the "one-size-fits-all" defect of the traditional threshold method. By dynamically updating the matrix (adding to the matrix), online learning of the model is realized. For example, after the charging pile runs for a long time, it can automatically adapt to the new normal / abnormal mode and reduce false alarms.

[0030] Preset a probability threshold. If the probability of the charging pile having an abnormality is greater than or equal to the probability threshold, it is determined that the charging pile currently has an abnormality, and a warning is issued; Update the jump time difference at the time point corresponding to the current operating power data of the charging pile to the two-dimensional jump feature matrix for dynamic update.

[0031] Please refer to Figure 2 , in the second embodiment: Provide an intelligent monitoring system for charging pile data based on the Internet of Things. The system includes: a data acquisition and time set construction module, a difference sequence construction module, a vector and matrix construction module, and a probability calculation and analysis warning module; The data acquisition and time set construction module: Based on the Internet of Things terminal, retrieve the device normal operation data log and device abnormal operation data log of the charging pile, and respectively obtain the power jump time; establish a device operation power data normal and abnormal perception jump time set; The difference sequence construction module: respectively calculate the difference between every two consecutive times in the times included in the device operation power data normal and abnormal perception jump time sets, and construct a device operation power data normal and abnormal perception jump time difference sequence; The vector and matrix construction module: organize the difference sequence of the normal and abnormal perception jump times of the device operating power data into a difference vector of the normal and abnormal perception jump times of the device operating power data; based on the difference vector of the normal and abnormal perception jump times of the device operating power data, construct a two-dimensional jump feature matrix. The probability calculation and analysis warning module: based on the two-dimensional jump feature matrix, calculate the probability of the charging pile being abnormal; preset a threshold, analyze and issue a warning.

[0032] Further, the data acquisition and time set construction module includes a data acquisition unit and a time set construction unit. The data acquisition unit: based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform, and according to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operating power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state. Obtain the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operating power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state. The time set construction unit: establish a set of normal and abnormal perception jump times of the device operating power data according to the power jump times of the charging pile in the historical normal working state and the historical abnormal working state, and the time set is recorded in chronological order.

[0033] Further, the difference sequence construction module includes a difference sequence construction unit. The difference sequence construction unit: respectively calculate the difference between every two consecutive times in the times included in the normal and abnormal perception jump time sets of the device operating power data to obtain a normal perception jump time difference sequence of the device operating power data and an abnormal perception jump time difference sequence of the device operating power data.

[0034] Further, the vector and matrix construction module includes a vector construction unit and a matrix construction unit. The vector construction unit: respectively organize the normal perception jump time difference sequence of the device operating power data and the abnormal perception jump time difference sequence of the device operating power data The matrix construction unit: constructs a two-dimensional jump feature matrix based on the difference vector of the normal and abnormal perception jump times of the device operating power data.

[0035] Furthermore, the probability calculation and analysis warning module includes a probability calculation unit and an analysis warning unit; The probability calculation unit: calculates the probability of the charging pile being abnormal based on the two-dimensional jump feature matrix; The analysis warning unit: presets a probability threshold. If the probability of the charging pile being abnormal is greater than or equal to the probability threshold, it is determined that the charging pile is currently abnormal, and a warning is issued; the jump time difference corresponding to the current operating power data time point of the charging pile is updated to the two-dimensional jump feature matrix for dynamic update.

[0036] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0037] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent monitoring method for charging pile data based on the Internet of Things, characterized in that, The method includes the following steps: Step S1: Based on the Internet of Things terminal, retrieve the device normal operation data log and the device abnormal operation data log of the charging pile, and respectively obtain the power jump times; establish a set of normal and abnormal perception jump times for the device operation power data; Step S2: Calculate the difference between every two consecutive times in the times included in the set of normal and abnormal perception jump times of the device operation power data respectively, and construct a difference sequence of normal and abnormal perception jump times of the device operation power data; Step S3: Organize the difference sequence of normal and abnormal perception jump times of the device operation power data into a difference vector of normal and abnormal perception jump times of the device operation power data; based on the difference vector of normal and abnormal perception jump times of the device operation power data, construct a two-dimensional jump feature matrix; Step S4: Based on the two-dimensional jump feature matrix, calculate the probability of the charging pile having an abnormality; preset a threshold, analyze and issue a warning.

2. The intelligent monitoring method for charging pile data based on the Internet of Things according to claim 1, characterized in that, The specific implementation process of the said Step S1 includes: Based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform. According to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state; Obtain the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operation power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state; According to the power jump times of the charging pile in the historical normal working state and the historical abnormal working state, establish a set of normal and abnormal perception jump times for the device operation power data, and the time set is recorded in chronological order.

3. The intelligent monitoring method for charging pile data based on the Internet of Things according to claim 2, characterized in that, The specific implementation process of the said Step S2 includes: Calculate the difference between every two consecutive times in the time sets of normal and abnormal perception jump times of the device operating power data respectively, to obtain the normal perception jump time difference sequence and abnormal perception jump time difference sequence of the device operating power data, denoted as and , respectively, where represents the i-th difference obtained by calculating the difference between every two consecutive times in the time set of normal perception jump times of the device operating power data, and I represents the total number of differences obtained by calculating the difference between every two consecutive times in the time set of normal perception jump times of the device operating power data, represents the j-th difference obtained by calculating the difference between every two consecutive times in the time set of abnormal perception jump times of the device operating power data, and J represents the total number of differences obtained by calculating the difference between every two consecutive times in the time set of abnormal perception jump times of the device operating power data.

4. The intelligent monitoring method for charging pile data based on the Internet of Things according to claim 3, characterized in that, The specific implementation process of the said Step S3 includes: The normal perception jump time difference sequence of the device operating power data and the abnormal perception jump time difference sequence of the device operating power data are sorted into the normal and abnormal perception jump time difference vectors of the device operating power data, denoted as and , where , ; Based on the difference vector of normal and abnormal perception jump times of the device operation power data, construct a two-dimensional jump feature matrix, specifically as follows: ； Among them, represents a two-dimensional jump feature matrix, represents the (I + J)-th difference, represents the perceived jump type of the (I + J)-th difference. Among them, if the (I + J)-th difference is within the normal perceived jump time difference sequence of the device operating power data , then the perceived jump type of the (I + J)-th difference is a normal perceived jump and is marked as 0. If the (I + J)-th difference is within the abnormal perceived jump time difference sequence of the device operating power data , then the perceived jump type of the (I + J)-th difference is an abnormal perceived jump and is marked as 1.

5. The intelligent monitoring method for charging pile data based on the Internet of Things according to claim 4, characterized in that, The specific implementation process of the said Step S4 includes: Based on the two-dimensional jump feature matrix, calculate the probability of the charging pile having an abnormality, and the calculation formula is as follows: ； Among them, represents the jump time difference of the time point corresponding to the current operating power data of the charging pile, represents the probability of the charging pile having an abnormality; A preset probability threshold. If the probability that the charging pile has an abnormality is greater than or equal to the probability threshold, it is determined that the charging pile currently has an abnormality, and a warning is issued. Update the jump time difference at the time point corresponding to the current operating power data of the charging pile to the two-dimensional jump feature matrix for dynamic update. ​ 6. An intelligent monitoring system for charging pile data based on the Internet of Things, which executes the intelligent monitoring method for charging pile data based on the Internet of Things according to any one of claims 1-5, characterized in that, The system includes: a data acquisition and time set construction module, a difference sequence construction module, a vector and matrix construction module, and a probability calculation and analysis warning module; The data acquisition and time set construction module: Based on the Internet of Things terminal, retrieve the device normal operation data log and the device abnormal operation data log of the charging pile, and respectively obtain the power jump times; establish a set of normal and abnormal perception jump times for the device operation power data; The difference sequence construction module: Calculate the difference between every two consecutive times in the times included in the set of normal and abnormal perception jump times of the device operation power data respectively, and construct a difference sequence of normal and abnormal perception jump times of the device operation power data; The vector and matrix construction module: organize the normal and abnormal perception jump time difference sequences of the device operating power data into a vector of normal and abnormal perception jump time differences of the device operating power data; based on the vector of normal and abnormal perception jump time differences of the device operating power data, construct a two-dimensional jump feature matrix; The probability calculation and analysis warning module: calculate the probability of the charging pile being abnormal based on the two-dimensional jump feature matrix; preset a threshold, analyze and issue a warning.

7. The intelligent monitoring system for charging pile data based on the Internet of Things according to claim 6, characterized in that: The data acquisition and time set construction module includes a data acquisition unit and a time set construction unit; The data acquisition unit: based on the Internet of Things terminal, retrieve the device normal operation data log of the charging pile in the historical normal working state from the charging pile operation management platform, according to the device normal operation data log, extract the time points corresponding to the maximum and minimum values of the device operating power data of the charging pile in the historical normal working state, and record the time points as the power jump times of the charging pile in the historical normal working state; Obtain the device abnormal operation data log of the charging pile in the historical abnormal working state; according to the device abnormal operation data log, extract the time points corresponding to the maximum and minimum values of the device operating power data of the charging pile in the historical abnormal working state, and record the time points as the power jump times of the charging pile in the historical abnormal working state; The time set construction unit: establish a set of normal and abnormal perception jump times of the device operating power data according to the power jump times of the charging pile in the historical normal working state and the historical abnormal working state, and the time set is recorded in chronological order.

8. An intelligent monitoring system for charging pile data based on the Internet of Things according to claim 7, characterized in that: The difference sequence construction module includes a difference sequence construction unit; The difference sequence construction unit: respectively calculate the difference between every two consecutive times in the times included in the normal and abnormal perception jump time sets of the device operating power data, to obtain a normal perception jump time difference sequence of the device operating power data and an abnormal perception jump time difference sequence of the device operating power data.

9. An intelligent monitoring system for charging pile data based on the Internet of Things according to claim 8, characterized in that: The vector and matrix construction module includes a vector construction unit and a matrix construction unit; The vector construction unit: respectively organize the normal perception jump time difference sequence of the device operating power data and the abnormal perception jump time difference sequence of the device operating power data into the normal and abnormal perception jump time difference vectors of the device operating power data; The matrix construction unit: construct a two-dimensional jump feature matrix based on the vector of normal and abnormal perception jump time differences of the device operating power data.

10. An intelligent monitoring system for charging pile data based on the Internet of Things according to claim 9, characterized in that: The probability calculation and analysis warning module includes a probability calculation unit and an analysis warning unit; The probability calculation unit: calculate the probability of the charging pile being abnormal based on the two-dimensional jump feature matrix; The analysis warning unit: preset a probability threshold, if the probability of the charging pile being abnormal is greater than or equal to the probability threshold, then determine that the charging pile currently has an abnormality, and issue a warning; update the jump time difference of the time point corresponding to the current operating power data of the charging pile to the two-dimensional jump feature matrix for dynamic update.

Images