An operation and maintenance diagnosis method and system of an integrated energy system

Abstract

This application discloses a method and system for operation and maintenance diagnosis of an integrated energy system, relating to the field of new energy technology. The method utilizes the characteristic that linear regression coefficients can reflect the correlation and importance between independent and dependent variables. By analyzing the correlation between the total power generation of the entire integrated energy system and each port, a longitudinal analysis of the correlation coefficients of each detection is performed across time processes. Coefficients with obvious outliers are identified as non-correlated anomalous coefficients and marked. The ports corresponding to these anomalous coefficients are marked as anomalous ports. There is a strong correlation between the coefficients. Changes in power generation caused by environmental changes usually affect multiple coefficients. Since environmental changes are continuous, the coefficients also have uniformity and continuity after longitudinal comparison. The coefficients of two consecutive natural days will also have similarity. It is sensitive only to significant changes in a single coefficient, ensuring the accuracy of operation and maintenance diagnosis.

Description

Technical Field

[0001] This application relates to the field of new energy technology, and in particular to a method and system for operation and maintenance diagnosis of an integrated energy system. Background Technology

[0002] Because the resources used in thermal power generation are non-renewable and thermal power causes serious environmental pollution, in recent years, wind, solar and hydropower generation have become the means of supplying new energy sources and have accounted for an increasing proportion in new power systems. Conventional hydropower units are also shifting more from being primarily power generation units to being power generation units that also serve as regulators.

[0003] An integrated energy system composed of three mainstream clean energy sources—wind, solar, and hydro—has become the main force in new energy power generation. This system utilizes the characteristics of rapid start-up and shutdown, flexible adjustment, and stable output of hydropower units to suppress and smooth grid fluctuations caused by the randomness of wind and solar power.

[0004] Currently, the operation and maintenance monitoring of integrated energy systems is usually achieved through manual inspection and data statistics. Manual inspection is mainly used to monitor the external integrity of system equipment and its heat dissipation, while data statistics are mainly used to monitor the internal hardware condition of system equipment.

[0005] The aforementioned operation and maintenance monitoring mainly relies on manual inspection and judgment, as well as manual meter reading and analysis, which inevitably introduces subjective experience errors. Summary of the Invention

[0006] The main objective of this application is to provide a method and system for the operation and maintenance diagnosis of integrated energy systems, so as to solve the problem of subjective experience error in the operation and maintenance monitoring of integrated energy systems in the prior art.

[0007] To achieve the above objectives, this application provides the following technical solution:

[0008] A method for operation and maintenance diagnosis of an integrated energy system, wherein the integrated energy system includes energy systems with at least two different power generation methods, each energy system including at least one power generation terminal, at least one transformer terminal, and at least one energy storage terminal, and the operation and maintenance diagnosis method includes:

[0009] Step S1: Based on the preset detection interval, obtain the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end.

[0010] Step S2: Obtain the power generation of the energy system based on the preset detection interval;

[0011] Step S3: Based on the same preset detection interval, the relationship between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment is analyzed by multiple linear regression.

[0012] Step S4: Obtain all known linear regression coefficients for each preset detection interval, and obtain a coefficient matrix based on a preset detection interval;

[0013] Step S5: Obtain the pairwise norm differences between all coefficient matrices with the same natural day timestamp;

[0014] Step S6: Mark the coefficient matrix corresponding to the pairwise norm difference that is greater than the preset difference threshold as an anomaly matrix;

[0015] Step S7: Obtain the data similarity of all elements at the same position in all anomaly matrices;

[0016] Step S8: Determine whether the current element position has an outlier based on the data similarity of the current element position. If so, proceed to step S9.

[0017] Step S9: Define the end with the most outliers as the possible fault end.

[0018] As a further improvement to this application, step S9 defines the end with the most frequent outlier occurrences as the possible fault end, followed by:

[0019] Step S10: Obtain the duration of the outlier that appears most frequently at the faulty end;

[0020] Step S20: Determine whether the duration exceeds a preset duration threshold. If so, proceed to step S30.

[0021] Step S30: Define the fault-probable end as the fault-determining end.

[0022] As a further improvement to this application, step S30 defines the fault-probable end as the fault-determining end, and then includes:

[0023] Step S100: Obtain the regional map of the integrated energy system;

[0024] Step S200: Obtain the port number corresponding to the faulty end or the fault-determined end;

[0025] Step S300: Query the geographical location of the port number on the area map;

[0026] Step S400: Generate an inspection request signal based on the geographical location;

[0027] Step S500: Send the inspection request signal to the external monitoring terminal.

[0028] As a further improvement to this application, step S1, acquiring the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end based on a preset detection interval, includes:

[0029] Step S11: Define the infrared emissivity based on the outer surface material of the current power generation terminal;

[0030] Step S12: Obtain the current infrared radiation intensity of the power generation terminal through an external infrared detector based on a preset detection interval;

[0031] Step S13: Calculate the current temperature value of the power generation terminal based on the radiation law using the current infrared emissivity and the current infrared radiation intensity;

[0032] Step S14: Define the current temperature value at the power generation terminal as the current power generation equipment temperature at the power generation terminal;

[0033] Step S15: Repeat steps S11 to S14 with the current substation as the execution subject to obtain the temperature of the substation equipment at the current substation.

[0034] Step S16: Repeat steps S11 to S14 with the current energy storage terminal as the execution subject to obtain the energy storage device temperature of the current energy storage terminal.

[0035] As a further improvement to this application, step S3, based on the same preset detection interval, uses multiple linear regression to analyze the relationship between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment, respectively, including:

[0036] Step S31: Define the power generation of all preset detection intervals as known dependent variables, and define the temperatures of all power generation equipment, all power transformation equipment, and all energy storage equipment as known independent variables.

[0037] Step S32: Define a linear regression equation for the known dependent variable and known independent variable with the same preset detection interval using multiple linear regression.

[0038] Step S33: Integrate all the linear regression equations of the preset detection intervals into a set of linear regression equations.

[0039] Step S34: Solve for all unknown linear regression coefficients of the linear regression equation system using the least squares method;

[0040] Step S35: Substitute all the known linear regression coefficients obtained from the solution into the linear regression equation system to obtain the interrelationship.

[0041] As a further improvement to this application, step S5, obtaining the pairwise norm difference between all coefficient matrices with the same natural day timestamp, includes:

[0042] Step S51: Assign a natural day timestamp based on a preset detection interval using a 24-hour time system for a natural day;

[0043] Step S52, calculate the pairwise norm difference between all coefficient matrices with the same natural day timestamp using equation (1):

[0044] (1);

[0045] in, For pairwise norm differences, and Given two coefficient matrices with the same natural day timestamp, For matrix The Middle Line number Column elements, For matrix The Middle Line number Column elements, index For one of the calendar days, the subscript This represents the F-norm.

[0046] As a further improvement to this application, step S7 involves obtaining the data similarity of all elements at the same element position in all anomaly matrices, including:

[0047] Step S71: Obtain the average value of all elements at the same position in all anomaly matrices;

[0048] Step S72: Obtain the Euclidean distance between each element and the average value;

[0049] Step S73: Add 1 to the Euclidean distance of the current element and then take the reciprocal to obtain the data similarity of the current element.

[0050] To achieve the above objectives, this application also provides the following technical solutions:

[0051] An operation and maintenance diagnostic system for an integrated energy system, wherein the operation and maintenance diagnostic system is applied to the operation and maintenance diagnostic method described above, and the operation and maintenance diagnostic system includes:

[0052] The energy system heat generation data acquisition module is used to acquire the temperature of the power generation equipment at each power generation end, the temperature of the power generation equipment at each power substation end, and the temperature of the energy storage equipment at each energy storage end based on a preset detection interval.

[0053] An energy system power generation acquisition module is used to acquire the power generation of the energy system based on the preset detection interval;

[0054] The data interrelationship acquisition module is used to analyze the interrelationships between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment through multiple linear regression based on the same preset detection interval.

[0055] The cross-relation coefficient matrix acquisition module is used to obtain all known linear regression coefficients for each preset detection interval, and to obtain a coefficient matrix based on a preset detection interval.

[0056] The matrix pairwise norm difference acquisition module is used to obtain the pairwise norm difference between all coefficient matrices with the same natural day timestamp;

[0057] The anomaly matrix marking module is used to mark the coefficient matrix corresponding to pairwise norm differences greater than a preset difference threshold as an anomaly matrix;

[0058] The matrix element similarity acquisition module is used to obtain the data similarity of all elements at the same element position in all abnormal matrices.

[0059] The element outlier detection module is used to determine whether the current element position has an outlier based on the data similarity of the current element position.

[0060] The fault-probability end definition module is used to define the end with the most outliers as the fault-probability end if the condition is met.

[0061] To achieve the above objectives, this application also provides the following technical solutions:

[0062] An electronic device includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the operation and maintenance diagnosis method described above.

[0063] To achieve the above objectives, this application also provides the following technical solutions:

[0064] A storage medium storing program instructions, which, when executed by a processor, enable the operation and maintenance diagnosis method described above.

[0065] This application acquires the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end based on a preset detection interval; acquires the power generation of the energy system based on the preset detection interval; analyzes the relationship between the power generation and the temperatures of the power generation equipment, the power transmission equipment, and the energy storage equipment respectively through multiple linear regression based on the same preset detection interval; acquires all known linear regression coefficients for each preset detection interval, and obtains a coefficient matrix based on a preset detection interval; acquires the pairwise norm difference between all coefficient matrices with the same natural day timestamp; marks the coefficient matrices corresponding to pairwise norm differences greater than a preset difference threshold as anomaly matrices; acquires the data similarity of all elements at the same element position in all anomaly matrices; determines whether the current element position has an outlier based on the data similarity of the current element position, and if so, defines the end with the most frequent occurrences of the outlier as the possible fault end. This application utilizes the characteristic that linear regression coefficients can reflect the correlation and importance between independent and dependent variables. By analyzing the correlation between the overall power generation of the entire integrated energy system and each port, and performing longitudinal analysis of the correlation coefficients for each detection across time processes, coefficients with obvious outliers are identified as non-correlated anomalous coefficients and marked. Simultaneously, the ports corresponding to these anomalous coefficients are marked as anomalous ports. The coefficients in this application exhibit strong correlations. Changes in power generation caused by environmental changes often affect multiple or even all coefficients. Due to the vast scope and continuity of environmental changes, the coefficients also exhibit uniformity and continuity after longitudinal comparison. Coefficients from two consecutive natural days will also show similarity, making misjudgment unlikely. This application is sensitive only to significant changes in a single coefficient, ensuring the accuracy of operation and maintenance diagnosis. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating the steps of an embodiment of the operation and maintenance diagnosis method for the integrated energy system of this application.

[0067] Figure 2 This is a schematic diagram of functional modules of an embodiment of the operation and maintenance diagnostic system for the integrated energy system of this application.

[0068] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of this application;

[0069] Figure 4 This is a schematic diagram of the structure of one embodiment of the storage medium of this application. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0071] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movement of components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0072] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0073] like Figure 1 As shown, this embodiment provides an example of an operation and maintenance diagnosis method for an integrated energy system. In this embodiment, the integrated energy system includes at least two energy systems with different power generation methods, and each energy system includes at least one power generation terminal, at least one transformer terminal, and at least one energy storage terminal.

[0074] Preferably, the integrated energy system may include a wind power station, a photovoltaic power station, and a hydropower station, each power station including a power generation terminal, a transformer terminal, and an energy storage terminal, as an example.

[0075] Specifically, this operation and maintenance diagnostic method includes the following steps:

[0076] Step S1: Based on the preset detection interval, obtain the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end.

[0077] Preferably, the preset detection interval is set using a strategy that is divisible by the calendar day, so that the same timestamp can be selected when analyzing across calendar days. For example, if the time is 2 PM every day and a calendar day is 24 hours, the preset detection interval can be set to 1 hour.

[0078] Step S2: Obtain the power generation of the energy system based on the preset detection interval.

[0079] Preferably, the total power generation of the integrated energy system is used as the standard. If the power generation of a single power station is used, the multiple linear regression in the following text is changed to univariate linear regression. After the univariate linear regression of each power station, the coefficients are summarized and a coefficient matrix is ​​formed based on a preset detection interval.

[0080] Step S3: Based on the same preset detection interval, the relationship between power generation and the temperature of power generation equipment, power transmission equipment, and energy storage equipment is analyzed by multiple linear regression.

[0081] For example, linear regression can be performed based on all parameters at 2 PM each day.

[0082] Step S4: Obtain all known linear regression coefficients for each preset detection interval, and obtain a coefficient matrix based on a preset detection interval.

[0083] Preferably, in step S3, the dependent and independent variables are known, and all unknown coefficients are solved. After step S4, the coefficients become known quantities because of the solution.

[0084] Step S5: Obtain the pairwise norm differences between all coefficient matrices with the same natural day timestamp.

[0085] Preferably, the norm used in this embodiment is the F-norm, i.e., the Frobenius norm.

[0086] Step S6: Mark the coefficient matrix corresponding to the pairwise norm difference that is greater than the preset difference threshold as an abnormal matrix.

[0087] Preferably, the theoretical limit of the pairwise norm difference is 0, that is, the two matrices are the same, but there is no clear range of values ​​for the upper limit. The upper limit depends on the absolute value of the matrix elements. Therefore, the preset difference threshold can be set as a certain proportion of the maximum value of all pairwise norm differences, such as 80% of the maximum value.

[0088] Step S7: Obtain the data similarity of all elements at the same position in all anomaly matrices.

[0089] Step S8: Determine whether the current element position has an outlier based on the data similarity of the current element position. If so, proceed to step S9.

[0090] Step S9: Define the end with the most outliers as the possible fault end.

[0091] Preferably, the coefficients are strongly correlated. Changes in power generation caused by environmental changes usually affect multiple or even all coefficients. Because the scope of environmental changes is huge and continuous, the coefficients also have uniformity and continuity after longitudinal comparison. The coefficients of two consecutive natural days will also have similarity.

[0092] Further, in step S9, the endpoint with the most outlier occurrences is defined as the endpoint with the most potential faults. Following this, the following steps are also included:

[0093] Step S10: Obtain the duration of the outlier that appears most frequently at the faulty end.

[0094] Preferably, if outliers persist on the same port, it indicates that the device has malfunctioned.

[0095] Step S20: Determine whether the duration exceeds the preset duration threshold. If so, proceed to step S30.

[0096] Preferably, the preset duration threshold can be set according to the preset detection interval. Generally, the preset duration threshold is set to an integer multiple of the preset detection interval. For example, if the preset detection interval is one hour, the preset duration threshold can be set to one of 3 hours, 6 hours, or 12 hours.

[0097] Step S30: Define the fault-probable end as the fault-determined end.

[0098] Further, in step S30, the fault-probable end is defined as the fault-determined end, and then the following steps are also included:

[0099] Step S100: Obtain the regional map of the integrated energy system.

[0100] Step S200: Obtain the port number corresponding to the faulty end or the fault-determined end.

[0101] Step S300: Query the geographical location of the port number on the regional map.

[0102] Step S400: Generate an inspection request signal based on geographical location.

[0103] Step S500: Send the inspection request signal to the external monitoring terminal.

[0104] Preferably, steps S100 to S500 are designed to facilitate maintenance personnel in quickly defining faulty equipment.

[0105] Further, step S1 involves acquiring the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end based on a preset detection interval. This specifically includes the following steps:

[0106] Step S11: Define the infrared emissivity based on the outer surface material of the current power generation terminal.

[0107] Preferably, emissivity is the ratio of the thermal energy radiated from the material surface to the thermal energy radiated by a blackbody under the same conditions, and can be directly obtained by consulting existing technologies, for example:

[0108] Aluminum, bright (170℃): 0.04.

[0109] Cotton (20℃): 0.77.

[0110] Concrete (25℃): 0.93.

[0111] Ice, smooth (0℃): 0.97.

[0112] Iron, corundum (20℃): 0.24.

[0113] Cast iron (100℃): 0.80.

[0114] Rolled surface iron (20℃): 0.77.

[0115] Gypsum (20℃): 0.90.

[0116] Glass (90℃): 0.94.

[0117] Hard rubber (23℃): 0.94.

[0118] Rubber, light gray (23℃): 0.89.

[0119] Wood (70℃): 0.94.

[0120] Cork (20℃): 0.70.

[0121] Radiator, black anodized (50℃): 0.98.

[0122] Copper, slightly discolored (20℃): 0.04.

[0123] Copper, oxide (130℃): 0.76.

[0124] Plastics: PE, PP, PVC (20℃): 0.94.

[0125] Brass, oxidation (200℃): 0.61.

[0126] Paper (20℃): 0.97.

[0127] Ceramics (20℃): 0.92.

[0128] Black paint, matte (80℃): 0.97.

[0129] Steel, heat-treated surface (200℃): 0.52.

[0130] Steel, oxidation (200℃): 0.79.

[0131] Clay, fired (70℃): 0.91.

[0132] Transformer paint (70℃): 0.94.

[0133] Brick, mortar, plaster (20℃): 0.93.

[0134] Alternatively, the material sample can be heated to a known temperature using a precision sensor, and then the temperature can be measured with an infrared instrument. The emissivity value can then be adjusted to ensure accurate display. For lower temperatures, the emissivity of a tape with an emissivity of 0.95 can be measured, and the emissivity adjusted accordingly. For high-temperature measurements, holes can be drilled in the object, the temperature of the holes measured, and the emissivity adjusted. If the material can be painted, a dark paint with an emissivity close to 1.0 can be applied, and the temperature of the painted area measured and adjusted. Standardized emissivity values ​​for most materials can be looked up in a reference table and entered into the instrument to estimate the emissivity value.

[0135] Step S12: Obtain the infrared radiation intensity of the current power generation terminal through an external infrared detector based on a preset detection interval.

[0136] Preferably, the acquisition of infrared radiation intensity is a prior art technique.

[0137] Step S13: Calculate the current temperature value of the power generation terminal based on the radiation law using the current infrared emissivity and the current infrared radiation intensity.

[0138] Preferably, the radiation intensity can be converted into a temperature value using Planck's blackbody radiation law or the Stefan-Boltzmann law, with the simplified formula being: ,in, This is the temperature value. The current infrared radiation intensity, For Stefan-Boltzmann constant, Infrared emissivity.

[0139] Step S14: Define the current temperature value of the generator terminal as the current temperature of the generator equipment at the generator terminal.

[0140] Step S15: Repeat steps S11 to S14 with the current substation as the execution subject to obtain the temperature of the substation equipment at the current substation.

[0141] Step S16: Repeat steps S11 to S14 with the current energy storage terminal as the execution subject to obtain the energy storage device temperature of the current energy storage terminal.

[0142] Preferably, when electrical equipment in an integrated energy system ages or malfunctions, the main phenomenon is almost always abnormal heating. However, the causes of heating vary, such as aging of mechanical parts, electrical system problems, control system failures, and decreased system efficiency. Therefore, this embodiment starts from the result and detects abnormal heating.

[0143] Further, step S3 involves analyzing the relationship between power generation and the temperatures of the power generation equipment, power transmission equipment, and energy storage equipment using multiple linear regression based on the same preset detection interval. This specifically includes the following steps:

[0144] Step S31: Define the power generation of all preset detection intervals as known dependent variables, and define the temperatures of all power generation equipment, all power transformation equipment, and all energy storage equipment as known independent variables.

[0145] Step S32: Define a linear regression equation for the known dependent variable and known independent variable with the same preset detection interval using multiple linear regression.

[0146] Preferably, this embodiment uses lasso linear regression.

[0147] Step S33: Integrate all the linear regression equations of the preset detection intervals into a set of linear regression equations.

[0148] Step S34: Solve for all unknown linear regression coefficients of the linear regression equation system using the least squares method.

[0149] Step S35: Substitute all the known linear regression coefficients obtained from the solution into the linear regression equation system to obtain the interrelationships.

[0150] Further, step S5, obtaining the pairwise norm differences between all coefficient matrices with the same natural day timestamp, specifically includes the following steps:

[0151] Step S51: Assign a natural day timestamp based on a preset detection interval using a 24-hour time system for a natural day.

[0152] For example, if the above method is used to detect once per hour, then the natural day timestamp of each detection will be the hour of each day.

[0153] Step S52, calculate the pairwise norm difference between all coefficient matrices with the same natural day timestamp using equation (1):

[0154] (1).

[0155] in, For pairwise norm differences, and Given two coefficient matrices with the same natural day timestamp, For matrix The Middle Line number Column elements, For matrix The Middle Line number Column elements, index For one of the calendar days, the subscript This represents the F-norm.

[0156] Further, step S7 involves obtaining the data similarity of all elements at the same position in all anomaly matrices, specifically including the following steps:

[0157] Step S71: Obtain the average value of all elements at the same position in all abnormal matrices.

[0158] Step S72: Obtain the Euclidean distance between each element and the average value.

[0159] Step S73: Add 1 to the Euclidean distance of the current element and then take the reciprocal to obtain the data similarity of the current element.

[0160] This embodiment acquires the temperatures of the power generation equipment at each power generation end, the power transmission equipment at each power transmission end, and the energy storage equipment at each energy storage end based on preset detection intervals; it acquires the power generation of the energy system based on preset detection intervals; it analyzes the relationship between power generation and the temperatures of the power generation equipment, power transmission equipment, and energy storage equipment through multiple linear regression based on the same preset detection interval; it acquires all known linear regression coefficients for each preset detection interval, and obtains a coefficient matrix based on a preset detection interval; it acquires the pairwise norm differences between all coefficient matrices with the same natural day timestamp; it marks the coefficient matrices corresponding to pairwise norm differences greater than a preset difference threshold as anomaly matrices; it acquires the data similarity of all elements at the same element position in all anomaly matrices; it determines whether the current element position has an outlier based on the data similarity of the current element position, and if so, it defines the end with the most outlier occurrences as the possible fault end. This embodiment utilizes the characteristic that linear regression coefficients can reflect the correlation and importance between independent and dependent variables. By analyzing the correlation between the overall power generation of the entire integrated energy system and each port, and performing longitudinal analysis of the correlation coefficients for each detection across time processes, coefficients with obvious outliers are identified as non-correlated anomalous coefficients and marked. Simultaneously, the ports corresponding to these anomalous coefficients are marked as anomalous ports. The coefficients in this embodiment exhibit strong correlations. Changes in power generation caused by environmental changes often affect multiple or even all coefficients. Due to the vast scope and continuity of environmental changes, the coefficients also exhibit uniformity and continuity after longitudinal comparison. Coefficients from two consecutive natural days will also show similarity, making misjudgment difficult. This embodiment is sensitive only to significant changes in a single coefficient, ensuring the accuracy of operation and maintenance diagnosis.

[0161] like Figure 2 As shown, this embodiment provides an example of an operation and maintenance diagnosis system for an integrated energy system. In this embodiment, the operation and maintenance diagnosis system is applied to the operation and maintenance diagnosis method as described in the above embodiment.

[0162] Specifically, the operation and maintenance diagnostic system includes, in sequence, an energy system heat generation data acquisition module 1, an energy system power generation acquisition module 2, a data interrelationship acquisition module 3, an interrelationship coefficient matrix acquisition module 4, a matrix pairwise norm difference acquisition module 5, an anomaly matrix marking module 6, a matrix element similarity acquisition module 7, an element outlier judgment module 8, and a fault possibility definition module 9.

[0163] The system includes: an energy system heat generation data acquisition module 1, which acquires the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end, based on a preset detection interval; an energy system power generation acquisition module 2, which acquires the power generation of the energy system based on a preset detection interval; a data interrelationship acquisition module 3, which analyzes the interrelationship between power generation and the temperatures of the power generation equipment, power transmission equipment, and energy storage equipment, respectively, using multiple linear regression within the same preset detection interval; and an interrelationship coefficient matrix acquisition module 4, which acquires all known linear regression coefficients for each preset detection interval, based on a preset detection... A coefficient matrix is ​​obtained at intervals; the pairwise norm difference acquisition module 5 is used to obtain the pairwise norm difference between all coefficient matrices with the same natural day timestamp; the abnormal matrix marking module 6 is used to mark the coefficient matrix corresponding to the pairwise norm difference greater than the preset difference threshold as an abnormal matrix; the matrix element similarity acquisition module 7 is used to obtain the data similarity of all elements at the same element position in all abnormal matrices; the element outlier judgment module 8 is used to determine whether the current element position has an outlier based on the data similarity of the current element position; the fault possibility end definition module 9 is used to define the end with the most outlier occurrences as the fault possibility end if the outlier occurs.

[0164] Furthermore, the operation and maintenance diagnostic system also includes a duration acquisition module, a duration judgment module, and a fault determination end definition module that are electrically connected in sequence; the duration acquisition module is electrically connected to the fault possibility end definition module 9.

[0165] Among them, the duration acquisition module is used to acquire the duration of the outlier occurrence most frequently at the faulty end; the duration judgment module is used to determine whether the duration exceeds the preset duration threshold; and the fault determination end definition module is used to define the faulty end as the fault determination end if the duration exceeds the preset duration threshold.

[0166] Furthermore, the operation and maintenance diagnostic system also includes a regional map acquisition module, a fault port number acquisition module, a fault geographical location query module, an inspection request signal generation module, and an inspection request signal sending module, which are electrically connected in sequence; the regional map acquisition module is electrically connected to the fault determination end definition module.

[0167] The system includes: a regional map acquisition module for acquiring a regional map of the integrated energy system; a fault port number acquisition module for acquiring the port number corresponding to a faulty or confirmed faulty port; a fault geographic location query module for querying the geographic location of a port number on the regional map; an inspection request signal generation module for generating an inspection request signal based on the geographic location; and an inspection request signal sending module for sending the inspection request signal to an external monitoring terminal.

[0168] Furthermore, the energy system heat generation data acquisition module 1 specifically includes a first energy system heat generation data acquisition unit, a second energy system heat generation data acquisition unit, a third energy system heat generation data acquisition unit, a fourth energy system heat generation data acquisition unit, a fifth energy system heat generation data acquisition unit, and a sixth energy system heat generation data acquisition unit, which are connected in sequence. The fifth energy system heat generation data acquisition unit is electrically connected to the first energy system heat generation data acquisition unit, the sixth energy system heat generation data acquisition unit is electrically connected to the first energy system heat generation data acquisition unit, and the sixth energy system heat generation data acquisition unit is electrically connected to the energy system power generation acquisition module 2.

[0169] The system comprises the following components: a first energy system heat data acquisition unit defines infrared emissivity based on the outer surface material of the current power generation terminal; a second energy system heat data acquisition unit acquires infrared radiation intensity of the current power generation terminal through an external infrared detector based on a preset detection interval; a third energy system heat data acquisition unit calculates the temperature value of the current power generation terminal based on the radiation law using the current infrared emissivity and current infrared radiation intensity; a fourth energy system heat data acquisition unit defines the temperature value of the current power generation terminal as the temperature of the power generation equipment at the current power generation terminal; a fifth energy system heat data acquisition unit repeats the process from the first to the fourth energy system heat data acquisition unit with the current substation terminal as the executing entity to obtain the temperature of the substation equipment at the current substation terminal; and a sixth energy system heat data acquisition unit repeats the process from the first to the fourth energy system heat data acquisition unit with the current energy storage terminal as the executing entity to obtain the temperature of the energy storage equipment at the current energy storage terminal.

[0170] Furthermore, the data interrelationship acquisition module 3 specifically includes a first data interrelationship acquisition unit, a second data interrelationship acquisition unit, a third data interrelationship acquisition unit, a fourth data interrelationship acquisition unit, and a fifth data interrelationship acquisition unit that are electrically connected in sequence; the first data interrelationship acquisition unit is electrically connected to the energy system power generation acquisition module 2, and the fifth data interrelationship acquisition unit is electrically connected to the interrelationship coefficient matrix acquisition module 4.

[0171] The system comprises five data interrelationship acquisition units: the first unit defines the power generation of all preset detection intervals as known dependent variables, and the temperatures of all power generation equipment, all power transformation equipment, and all energy storage equipment as known independent variables; the second unit defines the known dependent and independent variables of the same preset detection interval as a linear regression equation using multiple linear regression; the third unit integrates the linear regression equations of all preset detection intervals into a system of linear regression equations; the fourth unit solves for all unknown linear regression coefficients of the system of linear regression equations using the least squares method; and the fifth unit substitutes all the known linear regression coefficients obtained from the solution into the system of linear regression equations to obtain the interrelationships.

[0172] Furthermore, the pairwise norm difference acquisition module 5 is specifically used to include a first pairwise norm difference acquisition unit and a second pairwise norm difference acquisition unit that are electrically connected in sequence; the first pairwise norm difference acquisition unit is electrically connected to the mutual correlation coefficient matrix acquisition module 4, and the second pairwise norm difference acquisition unit is electrically connected to the abnormal matrix marking module 6.

[0173] The first matrix pairwise norm difference acquisition unit is used to assign a natural day timestamp based on a preset detection interval using a 24-hour time system for a natural day.

[0174] The second matrix pairwise norm difference acquisition unit is used to calculate the pairwise norm difference between all coefficient matrices with the same natural day timestamp using equation (1):

[0175] (1).

[0176] in, For pairwise norm differences, and Given two coefficient matrices with the same natural day timestamp, For matrix The Middle Line number Column elements, For matrix The Middle Line number Column elements, index For one of the calendar days, the subscript This represents the F-norm.

[0177] Furthermore, the matrix element similarity acquisition module 7 specifically includes a first matrix element similarity acquisition unit, a second matrix element similarity acquisition unit, and a third matrix element similarity acquisition unit that are electrically connected in sequence; the first matrix element similarity acquisition unit is electrically connected to the abnormal matrix marking module 6, and the third matrix element similarity acquisition unit is electrically connected to the element outlier judgment module 8.

[0178] The first matrix element similarity acquisition unit is used to obtain the average value of all elements at the same element position in all abnormal matrices; the second matrix element similarity acquisition unit is used to obtain the Euclidean distance between each element and the average value; the third matrix element similarity acquisition unit is used to add 1 to the Euclidean distance of the current element and then take the reciprocal to obtain the data similarity of the current element.

[0179] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For additional content such as preferred options, extensions, limitations, and examples, please refer to the above method embodiment. This embodiment will not repeat them here.

[0180] This embodiment acquires the temperatures of the power generation equipment at each power generation end, the power transmission equipment at each power transmission end, and the energy storage equipment at each energy storage end based on preset detection intervals; it acquires the power generation of the energy system based on preset detection intervals; it analyzes the relationship between power generation and the temperatures of the power generation equipment, power transmission equipment, and energy storage equipment through multiple linear regression based on the same preset detection interval; it acquires all known linear regression coefficients for each preset detection interval, and obtains a coefficient matrix based on a preset detection interval; it acquires the pairwise norm differences between all coefficient matrices with the same natural day timestamp; it marks the coefficient matrices corresponding to pairwise norm differences greater than a preset difference threshold as anomaly matrices; it acquires the data similarity of all elements at the same element position in all anomaly matrices; it determines whether the current element position has an outlier based on the data similarity of the current element position, and if so, it defines the end with the most outlier occurrences as the possible fault end. This embodiment utilizes the characteristic that linear regression coefficients can reflect the correlation and importance between independent and dependent variables. By analyzing the correlation between the overall power generation of the entire integrated energy system and each port, and performing longitudinal analysis of the correlation coefficients for each detection across time processes, coefficients with obvious outliers are identified as non-correlated anomalous coefficients and marked. Simultaneously, the ports corresponding to these anomalous coefficients are marked as anomalous ports. The coefficients in this embodiment exhibit strong correlations. Changes in power generation caused by environmental changes often affect multiple or even all coefficients. Due to the vast scope and continuity of environmental changes, the coefficients also exhibit uniformity and continuity after longitudinal comparison. Coefficients from two consecutive natural days will also show similarity, making misjudgment difficult. This embodiment is sensitive only to significant changes in a single coefficient, ensuring the accuracy of operation and maintenance diagnosis.

[0181] like Figure 3 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0182] The memory 102 stores program instructions for implementing the operation and maintenance diagnosis method of the integrated energy system in any of the above embodiments.

[0183] The processor 101 is used to execute program instructions stored in the memory 102 to perform operation and maintenance diagnosis of the integrated energy system.

[0184] The processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with data processing capabilities. The processor 101 can also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0185] Furthermore, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of this application. The storage medium 11 of this embodiment stores program instructions 111 capable of implementing all the above methods. These program instructions 111 can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0186] In the several embodiments provided in this application, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0187] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0188] The specific embodiments of this application have been described in detail above, but they are only examples, and this application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to this application are also within the scope of this application. Therefore, all equivalent changes, modifications, and improvements made without departing from the spirit and principles of this application should be covered within the scope of this application.

Claims

1. A method for operation and maintenance diagnosis of an integrated energy system, wherein the integrated energy system comprises energy systems with at least two different power generation methods, each energy system comprising at least one power generation terminal, at least one transformer terminal, and at least one energy storage terminal, characterized in that, The operation and maintenance diagnostic methods include: Step S1: Based on the preset detection interval, obtain the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end. Step S2: Obtain the power generation of the energy system based on the preset detection interval; Step S3: Based on the same preset detection interval, the relationship between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment is analyzed by multiple linear regression. Step S4: Obtain all known linear regression coefficients for each preset detection interval, and obtain a coefficient matrix based on a preset detection interval; Step S5: Obtain the pairwise norm differences between all coefficient matrices with the same natural day timestamp; Step S6: Mark the coefficient matrix corresponding to the pairwise norm difference that is greater than the preset difference threshold as an anomaly matrix; Step S7: Obtain the data similarity of all elements at the same position in all anomaly matrices; Step S8: Determine whether the current element position has an outlier based on the data similarity of the current element position. If so, proceed to step S9. Step S9: Define the end with the most outliers as the possible fault end.

2. The operation and maintenance diagnosis method according to claim 1, characterized in that, Step S9: Define the endpoint with the most frequent outliers as the potential fault endpoint. Following this, the following steps are included: Step S10: Obtain the duration of the outlier that appears most frequently at the faulty end; Step S20: Determine whether the duration exceeds a preset duration threshold. If so, proceed to step S30. Step S30: Define the fault-probable end as the fault-determining end.

3. The operation and maintenance diagnosis method according to claim 2, characterized in that, Step S30: Define the possible fault end as the fault-determining end, then include: Step S100: Obtain the regional map of the integrated energy system; Step S200: Obtain the port number corresponding to the faulty end or the fault-determined end; Step S300: Query the geographical location of the port number on the area map; Step S400: Generate an inspection request signal based on the geographical location; Step S500: Send the inspection request signal to the external monitoring terminal.

4. The operation and maintenance diagnosis method according to claim 1, characterized in that, Step S1, based on a preset detection interval, acquire the temperature of the power generation equipment at each power generation end, the temperature of the power transmission equipment at each power transmission end, and the temperature of the energy storage equipment at each energy storage end, including: Step S11: Define the infrared emissivity based on the outer surface material of the current power generation terminal; Step S12: Obtain the current infrared radiation intensity of the power generation terminal through an external infrared detector based on a preset detection interval; Step S13: Calculate the current temperature value of the power generation terminal based on the radiation law using the current infrared emissivity and the current infrared radiation intensity; Step S14: Define the current temperature value at the power generation terminal as the current power generation equipment temperature at the power generation terminal; Step S15: Repeat steps S11 to S14 with the current substation as the execution subject to obtain the temperature of the substation equipment at the current substation. Step S16: Repeat steps S11 to S14 with the current energy storage terminal as the execution subject to obtain the energy storage device temperature of the current energy storage terminal.

5. The operation and maintenance diagnosis method according to claim 1, characterized in that, Step S3, based on the same preset detection interval, analyzes the relationship between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment using multiple linear regression, including: Step S31: Define the power generation of all preset detection intervals as known dependent variables, and define the temperatures of all power generation equipment, all power transformation equipment, and all energy storage equipment as known independent variables. Step S32: Define a linear regression equation for the known dependent variable and known independent variable with the same preset detection interval using multiple linear regression. Step S33: Integrate all the linear regression equations of the preset detection intervals into a set of linear regression equations. Step S34: Solve for all unknown linear regression coefficients of the linear regression equation system using the least squares method; Step S35: Substitute all the known linear regression coefficients obtained from the solution into the linear regression equation system to obtain the interrelationship.

6. The operation and maintenance diagnosis method according to claim 1, characterized in that, Step S5, obtain the pairwise norm differences between all coefficient matrices with the same natural day timestamp, including: Step S51: Assign a natural day timestamp based on a preset detection interval using a 24-hour time system for a natural day; Step S52, calculate the pairwise norm difference between all coefficient matrices with the same natural day timestamp using equation (1): （1）； in, For pairwise norm differences, and Given two coefficient matrices with the same natural day timestamp, For matrix The Middle Line 1 Column elements, For matrix The Middle Line 1 Column elements, index For one of the calendar days, the subscript This represents the F-norm.

7. The operation and maintenance diagnosis method according to claim 1, characterized in that, Step S7: Obtain the data similarity of all elements at the same position in all anomaly matrices, including: Step S71: Obtain the average value of all elements at the same position in all anomaly matrices; Step S72: Obtain the Euclidean distance between each element and the average value; Step S73: Add 1 to the Euclidean distance of the current element and then take the reciprocal to obtain the data similarity of the current element.

8. An operation and maintenance diagnostic system for an integrated energy system, wherein the operation and maintenance diagnostic system is applied to the operation and maintenance diagnostic method as described in any one of claims 1 to 7, characterized in that, The operation and maintenance diagnostic system includes: The energy system heat generation data acquisition module is used to acquire the temperature of the power generation equipment at each power generation end, the temperature of the power generation equipment at each power substation end, and the temperature of the energy storage equipment at each energy storage end based on a preset detection interval. An energy system power generation acquisition module is used to acquire the power generation of the energy system based on the preset detection interval; The data interrelationship acquisition module is used to analyze the interrelationships between the power generation and the temperature of the power generation equipment, the temperature of the power transmission equipment, and the temperature of the energy storage equipment through multiple linear regression based on the same preset detection interval. The cross-relation coefficient matrix acquisition module is used to obtain all known linear regression coefficients for each preset detection interval, and to obtain a coefficient matrix based on a preset detection interval. The matrix pairwise norm difference acquisition module is used to obtain the pairwise norm difference between all coefficient matrices with the same natural day timestamp; The anomaly matrix marking module is used to mark the coefficient matrix corresponding to pairwise norm differences greater than a preset difference threshold as an anomaly matrix; The matrix element similarity acquisition module is used to obtain the data similarity of all elements at the same element position in all abnormal matrices; The element outlier detection module is used to determine whether the current element position has an outlier based on the data similarity of the current element position. The fault-probability end definition module is used to define the end with the most outlier occurrences as the fault-probability end if the condition is met.

9. An electronic device, characterized in that, The method includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the operation and maintenance diagnosis method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores program instructions, which, when executed by a processor, can implement the operation and maintenance diagnosis method as described in any one of claims 1 to 7.

Images