Charging pile remote monitoring method and system based on error model

Abstract

The invention discloses a charging pile remote monitoring method and system based on an error model, and the method employs multi-axis dynamic bifurcation mapping and rotation residual aggregation to construct an error model based on multi-dimensional operation parameters, and can effectively capture the coupling characteristics of a drift error and a transient disturbance error through multi-axis disturbance bifurcation mapping. The method is more sensitive to complex fault response in actual operation, has higher multi-dimensional fitting capability and error generalization capability compared with a traditional method, can simulate periodic response offset of various operating parameters under different disturbance frequencies through rotation residual aggregation, generates stable error signals with definite directivity, and has the advantages of being high in accuracy and high in reliability. According to the method, dynamic prediction and guiding correction of the error trend can be achieved through the built error model, overfitting and error overcompensation are effectively avoided, accurate correction of the multi-dimensional operation parameters of the charging pile is achieved, and the judgment accuracy and response efficiency of remote monitoring of the charging pile are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote monitoring of charging piles, and in particular to a remote monitoring method and system for charging piles based on an error model, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid adoption of new energy vehicles, remote monitoring of the operating status of charging piles, as core supporting infrastructure, has become a crucial component of smart energy systems, intelligent traffic management, and the IoT-enabled urban infrastructure. To ensure stable operation and efficient maintenance of charging piles, remote monitoring platforms typically need to collect and upload a large number of real-time operating parameters, including voltage, current, power, temperature, ambient humidity, plug status, fault codes, and other information, enabling monitoring centers to analyze and issue warnings about the health of charging piles. However, in practical applications, due to the variability of the charging pile operating environment, the limitations of sensor hardware accuracy, and the performance drift caused by long-term operation of electrical equipment, the collected data often contains systematic errors, random disturbance errors, and transient fluctuation errors. These errors are generally difficult to effectively identify and correct in current remote monitoring systems.

[0003] Traditional remote monitoring methods for charging piles often employ judgment logic and simple filtering algorithms based on fixed thresholds. These rely on the direct upload and display of collected data, ignoring the error evolution trends and nonlinear relationships between data during device operation. However, when sensors are subject to external interference (such as temperature drift, electromagnetic interference, and mechanical aging), data anomalies often manifest as slow offsets, periodic jitter, and sudden spikes. These issues can easily lead to false positives, missed negatives, and even misleading judgments using threshold judgment and static strategies, severely impacting the accuracy and response efficiency of remote monitoring of charging piles. Summary of the Invention

[0004] The present invention provides a charging pile remote monitoring method and system based on an error model, an electronic device, and a computer-readable storage medium, which realizes the precise correction of the multi-dimensional operating parameters of the charging pile, greatly improving the judgment accuracy and response efficiency of the charging pile remote monitoring.

[0005] According to one aspect of the present invention, a remote monitoring method for a charging pile based on an error model is provided, comprising the following contents:

[0006] Obtain the historical multi-dimensional operating parameters of the charging pile, and use multi-axis dynamic bifurcation mapping and rotation residual aggregation to build an error model based on the historical multi-dimensional operating parameters;

[0007] Collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information;

[0008] Error correction is performed on the current multidimensional operating parameters based on the error feedback information to obtain the corrected current multidimensional operating parameters.

[0009] Furthermore, the process of constructing an error model based on historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation includes the following:

[0010] Preprocess historical multi-dimensional operating parameters;

[0011] The pre-processed historical multi-dimensional operating parameters are embedded into a multi-axis dynamic bifurcation mapping structure to simulate the behavioral changes of the historical multi-dimensional operating parameters under the influence of electrical disturbances and environmental nonlinear fluctuations, and the axial mapping tensor of each type of operating parameter on each disturbance axis is obtained.

[0012] Perform rotation residual aggregation on the axial mapping tensors of each type of operating parameter on all perturbation axes to obtain the aggregated residual tensor;

[0013] Based on the residual tensor, self-excited backstepping correction processing is performed on each type of operating parameter to obtain the error offset value of each type of operating parameter.

[0014] Furthermore, the axial mapping tensor of each type of operating parameter on each perturbation axis is calculated based on the following formula:

[0015]

[0016] in, It represents the axial mapping tensor generated by the expansion of the i-th type of operating parameter at time t on the k-th perturbation axis after perturbation mapping. represents the i-th type of operating parameters after preprocessing at time t, represents the i-th type of operating parameters after preprocessing at time t-1, δ i represents the adjustment factor of the i-th type of operating parameters, η represents the perturbation constant, ω k represents the angular frequency of the kth disturbance axis, φ i represents the initial perturbation phase of the i-th type of operating parameters, γ ik It represents the nonlinear amplification index of the i-th type of operating parameter on the k-th disturbance axis.

[0017] Furthermore, the aggregated residual tensor is calculated based on the following formula:

[0018]

[0019] in, represents the residual tensor of the i-th type of operating parameters aggregated at time t, K represents the number of perturbation axes, α ik represents the aggregation weight coefficient of the i-th type of operating parameter on the k-th disturbance axis, represents the average mapping value of the axial mapping tensor generated by the expansion of the multidimensional operating parameters on the kth perturbation axis at time t after perturbation mapping, ψ ik It represents the disturbance frequency modulation factor of the i-th type operating parameter on the k-th disturbance axis.

[0020] Furthermore, the error offset value of each type of operating parameter is calculated based on the following formula:

[0021]

[0022] in, represents the error offset value of the i-th type operating parameter at time t, ζ i represents the error response coefficient of the i-th type of operating parameters, represents the second-order time derivative of the residual tensor of the i-th operating parameter at time t, represents the residual tensor of the i-th type of operating parameters aggregated at time t-1, κ represents the perturbation factor, represents the first-order difference term,

[0023] Furthermore, the corrected current multi-dimensional operating parameters are calculated based on the following formula:

[0024]

[0025] in, Indicates the Class running parameters at time The corrected value, Indicates the Class running parameters at time The preprocessed value, Indicates the Corrected response coefficients of class operating parameters, Indicates the Class running parameters at time The error offset value, represents the disturbance constant, represents the error offset change,

[0026] Furthermore, the following contents are also included:

[0027] The corrected current multi-dimensional operating parameters are compared with the preset threshold range of each type of operating parameters to determine whether they are abnormal.

[0028] In addition, the present invention also provides a charging pile remote monitoring system based on an error model, which adopts the charging pile remote monitoring method based on the error model described above, including:

[0029] The error model construction module is used to obtain the historical multi-dimensional operating parameters of the charging pile and construct an error model based on the historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation;

[0030] The error feedback information acquisition module is used to collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information;

[0031] The error correction module is used to perform error correction on the current multi-dimensional operating parameters based on the error feedback information to obtain the corrected current multi-dimensional operating parameters.

[0032] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0033] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for remotely monitoring a charging pile based on an error model, wherein the computer program executes the steps of the above-described method when running on a computer.

[0034] The present invention has the following beneficial effects:

[0035] The remote monitoring method of charging piles based on the error model of the present invention adopts multi-axis dynamic bifurcation mapping and rotation residual aggregation to construct an error model based on multi-dimensional operating parameters. The multi-axis disturbance bifurcation mapping can effectively capture the coupling characteristics of drift error and transient disturbance error. It is more sensitive to complex fault responses in actual operation and has higher multi-dimensional fitting ability and error generalization ability than traditional methods. The rotation residual aggregation can simulate the periodic response offset of various operating parameters at different disturbance frequencies, and generate a stable and directional error signal, so that the constructed error model can realize dynamic prediction and guided correction of error trends, effectively avoid overfitting and error overcompensation, and realize accurate correction of the multi-dimensional operating parameters of the charging pile, which greatly improves the judgment accuracy and response efficiency of remote monitoring of the charging pile.

[0036] In addition, the charging pile remote monitoring system based on the error model of the present invention also has the above advantages.

[0037] In addition to the above-described objects, features and advantages, the present invention has other objects, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0039] Figure 1 1 is a flow chart of a charging pile remote monitoring method based on an error model according to a preferred embodiment of the present application;

[0040] Figure 2 yes Figure 1 Schematic diagram of the sub-process of step S1;

[0041] Figure 3 This is another flowchart of the remote monitoring method for charging piles based on the error model according to the preferred embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of the module structure of a charging pile remote monitoring system based on an error model in another embodiment of the present application. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] Reference Figure 1 The preferred embodiment of the present application provides a remote monitoring method for charging piles based on an error model, including the following contents:

[0045] Step S1: Obtain the historical multidimensional operating parameters of the charging pile, and use multi-axis dynamic bifurcation mapping and rotation residual aggregation to build an error model based on the historical multidimensional operating parameters;

[0046] Step S2: Collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information;

[0047] Step S3: performing error correction on the current multi-dimensional operating parameters based on the error feedback information to obtain the corrected current multi-dimensional operating parameters.

[0048] It can be understood that the remote monitoring method of charging piles based on the error model of this embodiment adopts multi-axis dynamic bifurcation mapping and rotation residual aggregation to construct an error model based on multi-dimensional operating parameters. The multi-axis disturbance bifurcation mapping can effectively capture the coupling characteristics of drift error and transient disturbance error. In actual operation, it is more sensitive to complex faults (such as aging, short-term overheating, and low-voltage fluctuations). It has higher multi-dimensional fitting ability and error generalization ability than traditional methods. The rotation residual aggregation can simulate the periodic response offset of various operating parameters at different disturbance frequencies, and generate a stable and directional error signal, so that the constructed error model can realize dynamic prediction and guidance correction of error trends, effectively avoid overfitting and error overcompensation, and realize accurate correction of multi-dimensional operating parameters of charging piles, greatly improving the judgment accuracy and response efficiency of remote monitoring of charging piles.

[0049] In step S1, the historical multi-dimensional operating parameters of the charging pile are first obtained from the database. The multi-dimensional operating parameters include electrical parameters such as voltage, current, active power, reactive power, and power factor, environmental quantities such as shell temperature, ambient humidity, and wind speed, and state quantities such as start / stop status, plug-in status, and fault warning codes. Then, based on the historical multi-dimensional operating data, an error model is constructed using a multi-axis dynamic bifurcation mapping and rotational residual aggregation network algorithm to achieve error analysis of the multi-dimensional operating data of the charging pile. The multi-axis dynamic bifurcation mapping and rotational residual aggregation network algorithm aims to solve the error accumulation problem caused by sensor response nonlinearity, environmental disturbances, random fluctuations in the electrical system, and hardware aging in the multi-dimensional operating state of the charging pile, and establish an algorithm model that can adaptively learn the error evolution path based on historical operating data, and achieve multi-dimensional data joint modeling and dynamic feedback of error residuals.

[0050] Among them, such as Figure 2 As shown, the process of constructing an error model based on historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation includes the following:

[0051] Step S11: pre-processing historical multi-dimensional operating parameters;

[0052] Step S12: embedding the pre-processed historical multi-dimensional operating parameters into a multi-axis dynamic bifurcation mapping structure to simulate the behavior changes of the historical multi-dimensional operating parameters under the action of electrical disturbances and environmental nonlinear fluctuations, and obtaining the axial mapping tensor of each type of operating parameter on each disturbance axis;

[0053] Step S13: performing rotation residual aggregation on the axial mapping tensors of each type of operating parameter on all disturbance axes to obtain an aggregated residual tensor;

[0054] Step S14: performing self-excitation back-stepping correction processing on each type of operating parameter based on the residual tensor to obtain the error offset value of each type of operating parameter.

[0055] Specifically, assume that the historical multi-dimensional operating parameter data is: in, Represents the observed value of the i-th type of operating parameter at time t, such as charging voltage, current, device temperature, ambient temperature, output power, internal impedance, charging time, etc., n represents the total number of operating parameters, and T represents the time length of the data sequence. The historical multidimensional operating parameter data is preprocessed by standardization to eliminate the influence of different dimensions and magnitudes, and the preprocessed historical multidimensional operating parameter data is obtained.

[0056] Then, the pre-processed historical multi-dimensional operating parameter data is embedded in a multi-axis dynamic bifurcation mapping structure to simulate the behavioral changes of the historical multi-dimensional operating parameters under the influence of electrical disturbances and nonlinear environmental fluctuations, and the axial mapping tensor of each type of operating parameter on each disturbance axis is obtained. Among them, each type of operating parameter is expanded into K bifurcation channels, each bifurcation channel is a disturbance axis, and each bifurcation channel undergoes nonlinear changes according to the disturbance frequency, initial phase offset, and electromagnetic coupling strength to generate an axial mapping vector. Specifically, the axial mapping tensor of each type of operating parameter on each disturbance axis is calculated based on the following formula:

[0057]

[0058] in, It represents the axial mapping tensor generated by expanding the i-th type of operating parameter at time t on the k-th perturbation axis after perturbation mapping; represents the i-th type of operating parameters after preprocessing at time t; represents the i-th type of operating parameters after preprocessing at time t-1; δ i It represents the adjustment factor of the i-th type of operating parameter, which is used to characterize the disturbance coupling strength of the i-th type of operating parameter. It can control the response sensitivity of the current data to the historical state, that is, the "memory" of the fluctuation disturbance. It is determined according to the expert experience method. η represents the perturbation constant, which is used to prevent zero division or minimum value amplification and can control the stability of the denominator. Its value range is 10 -3 ~10 -6 , specifically determined according to expert experience; ω k represents the angular frequency of the kth disturbance axis, which is used to simulate the response of the charging pile to different external periodic interferences (such as 50Hz power supply noise, communication interference, etc.), and is determined based on expert experience; i It represents the initial disturbance phase of the i-th type of operating parameter, which is used to characterize the response start-up offset of the i-th type of operating parameter when it is disturbed. It reflects the physical inertia or measurement delay and is determined by analyzing and calculating the sensor response delay and the electromagnetic characteristics of the equipment. ik It represents the nonlinear amplification index of the i-th type of operating parameter on the k-th disturbance axis, which is used to control the nonlinear enhancement degree of the i-th type of operating parameter in the k-th disturbance axis mapping output. It is a key parameter for adjusting the local oscillation intensity in the error model. It is determined according to the expert experience method and the value range is [0.5, 3.0]. It can be understood that the pre-processed historical multi-dimensional operating parameter data After multi-axis dynamic bifurcation mapping processing, a third-order tensor is finally formed, which can be expressed as: This third-order tensor can capture the unstable bifurcation trends of each type of operating parameter on each perturbation axis (i.e., the axial mapping tensor), which is the basis for subsequent rotational residual aggregation. It can be understood that the present invention, through the multi-axis perturbation bifurcation mapping structure, can effectively capture the coupling characteristics of drift error and transient perturbation error. In actual operation, it is more sensitive to complex faults (such as aging, short-term overheating, and low-voltage fluctuations), and has higher multidimensional fitting capabilities and error generalization capabilities than traditional methods.

[0059] Next, after the axial mapping tensor is constructed, the rotational residual aggregation stage begins. This aims to perform nonlinear fusion on the output results of each perturbation axis and extract the potential high-dimensional cross-error field. This process not only aggregates the error signals between different dimensions but also simulates the error emergence path and frequency response behavior under a specific perturbation period. Specifically, the aggregated residual tensor is calculated based on the following formula:

[0060]

[0061] in, represents the residual tensor (i.e., residual response value) aggregated by the i-th type of operating parameters at time t, which serves as the intermediate representation of the error model and is used to reveal the potential error trend in the current state; K represents the number of disturbance axes, which is determined according to the specific scenario and is generally set to 8, 16, etc.; α ik The aggregation weight coefficient of the i-th type of operating parameter on the k-th disturbance axis represents the contribution of the bifurcation channel to the total residual. It is determined based on expert experience and is used to strengthen or weaken the impact of the response on a specific disturbance axis on the final residual, thereby forming a weighted aggregation mechanism. represents the average mapping value of the axial mapping tensor generated by the expansion of the multidimensional operating parameters on the k-th disturbance axis at time t after disturbance mapping, which is used as a reference value to measure the degree of deviation; ik It represents the disturbance frequency modulation factor on the kth disturbance axis to which the i-th type of operating parameter is subjected, which describes the sensitivity of the periodic response at this frequency, and is used to suppress the error surge during high-frequency jitter. It serves as a dynamic normalization factor to control excessive response to abnormal disturbances, and is specifically determined by experimental methods. In addition, the cubic exponent in the formula expresses the influence of the local offset amplification on the global error, the sine function introduced in the denominator expresses the periodicity of the disturbance response, and the entire logarithmic term represents the nonlinear enhancement of the residual output by the disturbance intensity, reflecting the coupling effect between different disturbance axes. It can be understood that the present invention can simulate the periodic response offset of various operating parameters at different disturbance frequencies by rotating the residual aggregation to generate a stable and directional error signal.

[0062] Finally, the aggregated residual tensor As an intermediate representation of error generation, it enters the next stage, the self-excited backpropagation correction stage. Its purpose is to use the residual trend of the previous stage to derive the current error offset trend. By coupling high-order derivatives with directions, a self-driven inversion estimation of the error is achieved, and an error offset estimation function is constructed. Specifically, the error offset value of each type of operating parameter is calculated based on the following formula:

[0063]

[0064] in, represents the error offset value of the i-th operating parameter at time t, that is, the output of the error model, which is used to guide subsequent dynamic correction; ζ i The error response coefficient of the i-th type of operating parameter is determined according to the expert experience method. It is used to control the weight of the error feedback on the final estimate and reflects the sensitivity of each operating parameter to error fluctuations. The second-order time derivative of the residual tensor of the i-th type of operating parameter at time t characterizes the acceleration of the error change and is used to detect whether the error is aggravated or slowed down. Δt represents the time step; represents the residual tensor of the i-th type of operating parameters aggregated at time t-1; κ represents the perturbation factor, which prevents the denominator from being zero and is used to enhance the numerical stability of the formula and simulate the minimum environmental interference; represents the first-order difference term, It characterizes the instantaneous variation of the error over time.

[0065] It can be understood that in the above formula, It is the second-order derivative multiplied by the nonlinear suppression term, which can describe the trend strength and direction of the error. Among them, the second-order time derivative is used to detect whether the error shows an aggravation or attenuation trend, and the inverse tangent function is used to gradually converge large errors to ensure robustness and nonlinear modulation capability. It is a cubic root residual offset modulation, which can nonlinearly control the coupling relationship between the instantaneous residual growth and the parameter value's response to the error, and modulate it into a gently changing valuation function to avoid the exponential explosion of error offsets caused by outliers; the self-excited backpropagation correction mechanism of the present invention realizes the dynamic prediction and guided correction of error trends, effectively avoiding overfitting and error overcompensation.

[0066] It can be understood that the present invention constructs a multi-axis state bifurcation tensor (i.e., multiple axial mapping tensors) by standardizing and time-perturbing the historical multi-dimensional operating data of the charging pile, and then relies on the nonlinear oscillation behavior between axes excited by the disturbance to guide the generation of rotational residual aggregation, and forms an error offset estimation function through multi-layer activation transformation (i.e., self-excited backpropagation correction mechanism). The output of this function is then used as a dynamic correction input and applied to the current operating parameter data of the charging pile to form a dynamic error correction value, thereby realizing high-precision remote monitoring.

[0067] Among them, in the step S2, the current multi-dimensional operating parameter data of the charging pile is collected by sensors such as voltage transformers, current transformers, Hall sensors, thermocouples, relays, etc. arranged on the charging pile and its periphery, and the collected current multi-dimensional operating parameter data is pre-processed such as denoising, outlier removal, normalization / standardization, and same-dimensional processing to obtain the pre-processed current multi-dimensional operating data. Among them, the specific pre-processing methods are technical means well known to those skilled in the art and will not be described in detail here. Then, the pre-processed current multi-dimensional operating parameter data is input into the error model constructed in step S1 to obtain the output result of the error model, that is, the error feedback information That is Class running parameters at time The error offset value.

[0068] In addition, in step S3, the error feedback information is used The error correction of the current multi-dimensional operating parameter data is performed to obtain the corrected current multi-dimensional operating parameter data and remotely display it. The corrected current multi-dimensional operating parameter is calculated based on the following formula:

[0069]

[0070] in, Indicates the Class running parameters at time Corrected value, representing the operating parameter value after applying the error model correction; Indicates the Class running parameters at time Preprocessed value; Indicates the The correction response coefficient of the class operating parameter is used to control the degree of effect of error correction on the parameter, characterizing the fault tolerance strength or correction sensitivity, and is determined based on expert experience; Indicates the Class running parameters at time The error offset value, that is, the output value of the error model; Represents a disturbance constant, used to prevent abnormal behavior with a denominator of 0; represents the error offset change, It characterizes the growth or convergence rate of the error in the time dimension and reflects the trend change.

[0071] As can be seen from the above formula, the error correction process of the present invention introduces an error change term combined with a periodic suppression term to form a dynamic nonlinear cancellation path, and establishes a nonlinear correction mapping between the error feedback and the original operating parameter data, which can avoid overadjustment under small errors and repair failure under large errors, and achieve a balanced transition between soft tolerance correction and forced correction.

[0072] In addition, if Figure 3 As shown, the charging pile remote monitoring method based on the error model also includes the following contents:

[0073] Step S4: Compare the corrected current multi-dimensional operating parameters with the preset threshold range of each type of operating parameters to determine whether there is an abnormality.

[0074] Specifically, after the corrected current multi-dimensional operating parameter data is sent to the cloud platform for remote display through MQTT, HTTPs, TCP and other protocols, the cloud platform compares the corrected current multi-dimensional operating parameters with the preset threshold range of each type of operating parameter to determine whether the current multi-dimensional operating parameter data is abnormal, thereby realizing remote monitoring.

[0075] In addition, if Figure 4 As shown, another embodiment of the present invention further provides a charging pile remote monitoring system based on an error model, preferably using the charging pile remote monitoring method based on the error model as described above, including:

[0076] The error model construction module is used to obtain the historical multi-dimensional operating parameters of the charging pile and construct an error model based on the historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation;

[0077] The error feedback information acquisition module is used to collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information;

[0078] The error correction module is used to perform error correction on the current multi-dimensional operating parameters based on the error feedback information to obtain the corrected current multi-dimensional operating parameters.

[0079] It can be understood that the error model-based charging pile remote monitoring system of this embodiment adopts multi-axis dynamic bifurcation mapping and rotation residual aggregation to construct an error model based on multi-dimensional operating parameters. The multi-axis disturbance bifurcation mapping can effectively capture the coupling characteristics of drift error and transient disturbance error. In actual operation, it is more sensitive to complex faults (such as aging, short-term overheating, and low-voltage fluctuations). It has higher multi-dimensional fitting ability and error generalization ability than traditional methods. The rotation residual aggregation can simulate the periodic response offset of various operating parameters at different disturbance frequencies, and generate a stable and directional error signal, so that the constructed error model can realize dynamic prediction and guidance correction of error trends, effectively avoid overfitting and error overcompensation, and realize accurate correction of multi-dimensional operating parameters of charging piles, greatly improving the judgment accuracy and response efficiency of remote monitoring of charging piles.

[0080] In addition, the charging pile remote monitoring system based on the error model also includes:

[0081] The abnormality diagnosis module is used to compare the corrected current multi-dimensional operating parameters with the preset threshold range of each type of operating parameters to determine whether there is an abnormality.

[0082] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0083] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for remotely monitoring a charging pile based on an error model, wherein the computer program executes the steps of the above-described method when running on a computer.

[0084] Common computer-readable storage media include: floppy disks, flexible disks, hard disks, magnetic tape, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash-erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. Instructions can further be transmitted or received via a transmission medium. The term transmission medium may include any tangible or intangible medium that can be used to store, encode, or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate communication of such instructions. Transmission media include coaxial cables, copper wire, and fiber optics, including the wires of a bus used to transmit a computer data signal.

[0085] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0089] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0090] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0091] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A remote monitoring method for charging piles based on an error model, characterized in that: Includes the following: Obtain the historical multi-dimensional operating parameters of the charging pile, and use multi-axis dynamic bifurcation mapping and rotation residual aggregation to build an error model based on the historical multi-dimensional operating parameters; Collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information; Error correction is performed on the current multidimensional operating parameters based on the error feedback information to obtain the corrected current multidimensional operating parameters.

2. The remote monitoring method for charging piles based on the error model according to claim 1, characterized in that: The process of constructing an error model based on historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation includes the following: Preprocess historical multi-dimensional operating parameters; The pre-processed historical multi-dimensional operating parameters are embedded into a multi-axis dynamic bifurcation mapping structure to simulate the behavioral changes of the historical multi-dimensional operating parameters under the influence of electrical disturbances and environmental nonlinear fluctuations, and the axial mapping tensor of each type of operating parameter on each disturbance axis is obtained. Perform rotation residual aggregation on the axial mapping tensors of each type of operating parameter on all perturbation axes to obtain the aggregated residual tensor; Based on the residual tensor, self-excited backstepping correction processing is performed on each type of operating parameter to obtain the error offset value of each type of operating parameter.

3. The remote monitoring method for charging piles based on the error model according to claim 2, characterized in that: The axial mapping tensor of each type of operating parameter on each perturbation axis is calculated based on the following formula: in, It represents the axial mapping tensor generated by the expansion of the i-th type of operating parameter at time t on the k-th perturbation axis after perturbation mapping. represents the i-th type of operating parameters after preprocessing at time t, represents the i-th type of operating parameters after preprocessing at time t-1, δ i represents the adjustment factor of the i-th type of operating parameters, η represents the perturbation constant, ω k represents the angular frequency of the kth disturbance axis, φ i represents the initial perturbation phase of the i-th type of operating parameters, γ ik It represents the nonlinear amplification index of the i-th type of operating parameter on the k-th disturbance axis.

4. The remote monitoring method for charging piles based on the error model according to claim 3, characterized in that: The aggregated residual tensor is calculated based on the following formula: in, represents the residual tensor of the i-th type of operating parameters aggregated at time t, K represents the number of perturbation axes, α ik represents the aggregation weight coefficient of the i-th type of operating parameter on the k-th disturbance axis, represents the average mapping value of the axial mapping tensor generated by the expansion of the multidimensional operating parameters on the kth perturbation axis at time t after perturbation mapping, ψ ik It represents the disturbance frequency modulation factor of the i-th type operating parameter on the k-th disturbance axis.

5. The remote monitoring method for charging piles based on the error model according to claim 4, characterized in that: The error offset value of each type of operating parameter is calculated based on the following formula: in, represents the error offset value of the i-th type operating parameter at time t, ζ i represents the error response coefficient of the i-th type of operating parameters, represents the second-order time derivative of the residual tensor of the i-th operating parameter at time t, represents the residual tensor of the i-th type of operating parameters aggregated at time t-1, κ represents the perturbation factor, represents the first-order difference term, 6. The remote monitoring method for charging piles based on an error model according to claim 1, characterized in that: The corrected current multi-dimensional operating parameters are calculated based on the following formula: in, Indicates the Class running parameters at time The corrected value, Indicates the Class running parameters at time The preprocessed value, Indicates the Corrected response coefficients of class operating parameters, Indicates the Class running parameters at time The error offset value, represents the disturbance constant, represents the error offset change, 7. The remote monitoring method for charging piles based on an error model according to claim 1, characterized in that: Also included: The corrected current multi-dimensional operating parameters are compared with the preset threshold range of each type of operating parameters to determine whether they are abnormal.

8. A charging pile remote monitoring system based on an error model, using the charging pile remote monitoring method based on an error model according to any one of claims 1 to 7, characterized in that: include: The error model construction module is used to obtain the historical multi-dimensional operating parameters of the charging pile and construct an error model based on the historical multi-dimensional operating parameters using multi-axis dynamic bifurcation mapping and rotation residual aggregation; The error feedback information acquisition module is used to collect the current multi-dimensional operating parameters of the charging pile and input them into the error model to obtain error feedback information; The error correction module is used to perform error correction on the current multi-dimensional operating parameters based on the error feedback information to obtain the corrected current multi-dimensional operating parameters.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium for storing a computer program for remote monitoring of charging piles based on an error model, characterized in that: When the computer program is run on a computer, the steps of the method according to any one of claims 1 to 7 are executed.

Images