Remote fault monitoring method and system for high-voltage frequency converter
By setting multiple monitoring points in the high-voltage inverter, constructing initial and revised operation models, and dynamically adjusting the monitoring strategy, efficient remote fault monitoring and early warning are achieved, solving the problem of low fault diagnosis efficiency in traditional detection methods and ensuring the safe operation of the high-voltage inverter.
Patent Information
- Application Number
- CN202510694063.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-27
- Publication Date
- 2025-09-19
AI Technical Summary
Fault detection of traditional high-voltage inverters relies on simple manual instruments and appearance observation, and is unable to deeply identify the operating status from multiple angles, resulting in low fault diagnosis efficiency and increased safety hazards.
By setting multiple monitoring points, building an initial operation model and monitoring sub-strategy, collecting feedback data packets, generating a fault risk value, and judging whether to generate a warning instruction based on the risk value, dynamically adjusting the monitoring sub-strategy to update and correct the operation model, remote fault monitoring of high-voltage inverters can be achieved.
It achieves efficient fault diagnosis and timely early warning, improves the safe operation reliability of high-voltage inverters, reduces the interference of environmental fluctuations and data errors on diagnosis, and improves the accuracy of fault diagnosis.
Smart Images
Figure CN120669013A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of high-voltage inverters, and in particular to a remote fault monitoring method and system for high-voltage inverters. Background Art
[0002] The high-voltage inverter itself contains a complex power electronic topology. When the components operate at high voltage for a long time, the probability of failure increases, which further leads to safety accidents and increases corporate costs.
[0003] Traditional inspection work relies too much on simple manual instrument inspection and appearance observation, and often cannot identify the operating status of high-voltage inverters from multiple angles and in depth, nor can it accurately evaluate high-voltage inverter faults in a timely manner. Summary of the Invention
[0004] The purpose of this application is to solve the above technical problems and provide a remote fault monitoring method and system for high-voltage inverters, aiming to improve the fault diagnosis efficiency of high-voltage inverters and ensure the safe operation of high-voltage inverters.
[0005] In some embodiments of the present application, a remote fault monitoring method for a high-voltage inverter is provided, comprising: Set multiple monitoring points based on equipment parameters and historical fault parameters; Construct the initial operation model and monitoring sub-strategy for each monitoring point, and collect feedback data packets from each monitoring point according to all monitoring sub-strategies; Generate a fault risk value for each monitoring point based on the feedback data package and the initial operation model, and determine whether to generate an early warning instruction based on the fault risk value; Among them, when setting multiple monitoring points, including: Establish a monitoring point sequence A, A=(a1,a2…a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
[0006] In some embodiments of the present application, when constructing the initial operation model of each monitoring point, the following steps are included: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point according to the historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point.
[0007] In some embodiments of the present application, when constructing a monitoring sub-strategy for each monitoring point, the following steps are included: Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; Setting a feedback time axis of the target monitoring point according to the monitoring sub-cycle duration t, wherein the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
[0008] In some embodiments of the present application, when generating the monitoring evaluation value c, the process includes: c=e1*Q1*[ β 1i *j i ]+e2*Q2*[ β 2i *w i ] Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; r1 is the number of monitoring sub-indicators of the target monitoring point; β 1i is the influencing factor of the i-th monitoring sub-indicator of the target monitoring point; j i is the fluctuation evaluation value of the i-th monitoring sub-indicator of the target monitoring point; r2 is the number of historical evaluation indicators; β 2i is the influencing factor of the i-th historical evaluation index of the target monitoring point; w i is the reference value of the i-th historical evaluation index of the target monitoring point.
[0009] In some embodiments of the present application, generating a fault risk value for each monitoring point includes: According to the number of monitoring points A, set a i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.
[0010] In some embodiments of the present application, constructing a modified operation model includes: Establish the monitoring sub-indicator sequence P of the monitoring point to be diagnosed, P=(p1, p2…p i …p r ), where p i is the ith monitoring sub-indicator of the monitoring point to be diagnosed; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; Generate the first-level operating value of each monitoring sub-indicator in the monitoring sub-indicator sequence P at the anchor time node; Generate a modified evaluation value h based on the fault risk value f' of the anchor time node and the monitoring evaluation value c' of the monitoring point to be diagnosed; Set the compensation coefficient g according to the corrected evaluation value h; A modified operation model is constructed based on the compensation coefficient g and all primary operation values.
[0011] In some embodiments of the present application, generating the fault risk value of the current feedback time node includes: f=e3*[ β 3i *(k i -k' i) 2 ]+e4*[ β 3i *g*(k i -k 1i) 2 ] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; β 3i The influencing factor of the monitoring sub-indicator of the monitoring point to be diagnosed; k i is the real-time monitoring value of the i-th monitoring sub-indicator of the monitoring point to be diagnosed at the current feedback time node; k' i is the standard reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed; k 1i It is the first-level reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed.
[0012] In some embodiments of the present application, a remote fault monitoring system for a high-voltage inverter is provided, comprising: Central control unit, used to set multiple monitoring points based on equipment parameters and historical fault parameters; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are arranged at each monitoring point; The monitoring unit is used to collect feedback data packets from each monitoring point; The central control unit includes: The first processing module is used to construct the initial operation model and monitoring sub-strategy of each monitoring point; The second processing module is used to obtain feedback data packets of each monitoring point according to all monitoring sub-strategies, and generate a fault risk value of each monitoring point according to the feedback data packets and the initial operation model; An early warning module is used to determine whether to generate an early warning instruction based on the fault risk value; The first processing module is also used to establish a monitoring point sequence A, A=(a1, a2...a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
[0013] In some embodiments of the present application, the first processing module is further configured to: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point according to the historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point; Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; Setting a feedback time axis of the target monitoring point according to the monitoring sub-cycle duration t, wherein the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
[0014] In some embodiments of the present application, the second processing module is further configured to: According to the number of monitoring points A, set a i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.
[0015] Compared with the prior art, the remote fault monitoring method and system for a high-voltage inverter according to the embodiment of the present application has the following beneficial effects: Based on the historical fault data of the high-voltage inverter, multiple monitoring points are set, and the corresponding initial operation model is constructed according to the fault characteristic parameters of each monitoring point. This can achieve comprehensive monitoring of the high-voltage inverter, timely warn of the abnormal operating status of the high-voltage inverter, and improve the diagnostic efficiency of potential faults of the high-voltage inverter.
[0016] By dynamically adjusting the monitoring sub-strategy of each monitoring point and periodically updating the corrected operation model of each monitoring point, interference in fault diagnosis caused by environmental fluctuations and monitoring data acquisition errors can be avoided, the fault diagnosis accuracy of the high-voltage inverter can be improved, and the safe operation of the high-voltage inverter can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 It is a flow chart of a remote fault monitoring method for a high-voltage inverter in the preferred embodiment of the present application. DETAILED DESCRIPTION
[0018] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0019] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.
[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.
[0021] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.
[0022] like Figure 1 As shown, a remote fault monitoring method for a high-voltage inverter according to a preferred embodiment of the present application includes: S101: Setting multiple monitoring points based on equipment parameters and historical fault parameters; S102: constructing an initial operation model and monitoring sub-strategy for each monitoring point, and collecting feedback data packets from each monitoring point according to all monitoring sub-strategies; S103: generating a fault risk value for each monitoring point based on the feedback data packet and the initial operation model, and determining whether to generate a warning instruction based on the fault risk value; Among them, when setting multiple monitoring points, including: Establish a monitoring point sequence A, A=(a1,a2…a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
[0023] Specifically, historical fault parameters and device parameters of the high-voltage inverter are analyzed to generate monitoring points and the required monitoring data for each type of high-voltage inverter fault. Based on the analysis results, multiple monitoring points are set. A single monitoring point can diagnose a single fault type or multiple fault types. In other words, if the current monitoring point experiences an operational anomaly, it indicates the corresponding fault type has occurred.
[0024] Specifically, for example, for faults such as IGBT module damage and explosion, output phase loss, overcurrent alarm, bus voltage fluctuation, capacitor bulging / leakage, input side short circuit / open circuit, low DC voltage, etc., corresponding monitoring points and monitoring data can be set. By establishing multiple monitoring points, fault diagnosis and fault location of the high-voltage inverter can be achieved.
[0025] Specifically, when constructing the initial operation model for each monitoring point, it includes: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point according to the historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point.
[0026] Specifically, by analyzing the fault data packet of the target monitoring point, the characteristic parameters of the fault type corresponding to the target fault monitoring point are generated, and the monitoring sub-indicators and corresponding standard operating values of the target monitoring point are set according to the characteristic parameters.
[0027] Specifically, the standard operating value refers to the operating value of each monitoring sub-indicator when no failure occurs at the target monitoring point.
[0028] Specifically, the monitoring sub-indicators can be set according to the actual parameters of the target monitoring point, including but not limited to temperature, current value, voltage value, drive signal, voltage spike, load, contact resistance and other parameters that can represent fault characteristics.
[0029] It can be understood that in the above embodiment, multiple monitoring points are set based on the historical fault data of the high-voltage inverter, and the corresponding initial operation model is constructed according to the fault characteristic parameters of each monitoring point, so as to realize comprehensive monitoring of the high-voltage inverter, timely warn of the abnormal operating status of the high-voltage inverter, and improve the diagnostic efficiency of potential faults of the high-voltage inverter.
[0030] In a preferred embodiment of the present application, when constructing a monitoring sub-strategy for each monitoring point, the following steps are included: Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; The feedback time axis of the target monitoring point is set according to the monitoring sub-cycle duration t, and the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
[0031] Specifically, the monitoring sub-cycle duration is the time interval between adjacent feedback time nodes. The larger the monitoring evaluation value, the greater the possibility of failure risk at the current monitoring point, and the smaller the corresponding time interval between adjacent feedback time nodes, thereby improving the fault monitoring efficiency of the high-voltage inverter.
[0032] Specifically, when generating the monitoring evaluation value c, it includes: c=e1*Q1*[ β 1i *j i ]+e2*Q2*[ β 2i *w i ] Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; r1 is the number of monitoring sub-indicators of the target monitoring point; β 1i is the influencing factor of the i-th monitoring sub-indicator of the target monitoring point; j i is the fluctuation evaluation value of the i-th monitoring sub-indicator of the target monitoring point; r2 is the number of historical evaluation indicators; β 2i is the influencing factor of the i-th historical evaluation index of the target monitoring point; w i is the reference value of the i-th historical evaluation index of the target monitoring point.
[0033] Specifically, the fluctuation evaluation value is set based on the historical monitoring data of the target monitoring point. The larger the fluctuation evaluation value, the greater the possibility of operational fluctuations in the corresponding monitoring sub-indicator.
[0034] Specifically, when the operating value of the monitoring sub-indicator is abnormal, the greater the possibility of failure risk at the target monitoring point, the greater the impact factor corresponding to the monitoring sub-indicator.
[0035] Specifically, depending on the different types of failure risks at different monitoring points, the values of the influencing factors of the corresponding monitoring sub-indicators are not exactly the same.
[0036] Specifically, historical evaluation indicators include but are not limited to parameters such as the number of failures at the target monitoring point, failure frequency, failure repair cost, and failure impact.
[0037] Specifically, the impact factor of each historical evaluation indicator is set according to its correlation with the failure risk. The greater the correlation, the greater the corresponding impact factor.
[0038] Specifically, the larger the reference value of the historical evaluation index, the greater the possibility of failure risk of the current high-voltage inverter.
[0039] Specifically, all parameters in the model are normalized by presetting a first fixed coefficient and a second fixed coefficient, so that each parameter in the model is within the same value range.
[0040] It can be understood that in the above embodiment, by dynamically adjusting the monitoring sub-strategy of each monitoring point and periodically updating the corrected operation model of each monitoring point, interference with fault diagnosis caused by environmental fluctuations and monitoring data acquisition errors can be avoided, the fault diagnosis accuracy of the high-voltage inverter can be improved, and the safe operation of the high-voltage inverter can be ensured.
[0041] In the preferred embodiment of the present application, the number of monitoring points A is set in sequence. i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.
[0042] Specifically, when building a correction operation model, it includes: Establish the monitoring sub-indicator sequence P of the monitoring point to be diagnosed, P=(p1, p2…p i …p r ), where p i is the ith monitoring sub-indicator of the monitoring point to be diagnosed; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; Generate the first-level operating value of each monitoring sub-indicator in the monitoring sub-indicator sequence P at the anchor time node; Generate a modified evaluation value h based on the fault risk value f' of the anchor time node and the monitoring evaluation value c' of the monitoring point to be diagnosed; Set the compensation coefficient g according to the corrected evaluation value h; A modified operation model is constructed based on the compensation coefficient g and all primary operation values.
[0043] Specifically, the first-level operating value refers to the real-time operating value of the monitoring sub-indicator of the monitoring point to be diagnosed at the anchor time node.
[0044] Specifically, the larger the corrected evaluation value is, the more unstable the operating status of the current monitoring point is. By setting the compensation coefficient, the prominence of potential fault characteristics is enhanced, thereby timely warning and diagnosing the potential fault risks of the target monitoring point.
[0045] Specifically, when generating the fault risk value of the current feedback time node, it includes: f=e3*[ β 3i *(k i -k' i) 2 ]+e4*[ β 3i *g*(k i -k 1i) 2 ] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; β 3i The influencing factor of the monitoring sub-indicator of the monitoring point to be diagnosed; k i is the real-time monitoring value of the i-th monitoring sub-indicator of the monitoring point to be diagnosed at the current feedback time node; k' i is the standard reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed; k 1i It is the first-level reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed.
[0046] Specifically, the larger the fault risk value, the greater the possibility that the monitoring point to be diagnosed has a potential fault risk.
[0047] Specifically, by comprehensively analyzing the operating parameters at the anchor time node and the operating parameters at the current feedback time node, a timely warning is issued regarding the development trend of abnormal operating conditions. Specifically, a fault risk value threshold is set based on historical parameters. When the real-time fault risk value of a monitoring point to be diagnosed exceeds the fault risk value threshold, the monitoring point to be diagnosed is marked and a corresponding maintenance strategy is generated to promptly eliminate the fault risk and ensure the safe operation of the high-voltage inverter.
[0048] Based on another preferred embodiment of a remote fault monitoring method for a high-voltage inverter in any of the above preferred embodiments, this preferred embodiment provides a remote fault monitoring method for a high-voltage inverter, comprising: Central control unit, used to set multiple monitoring points based on equipment parameters and historical fault parameters; The monitoring unit includes a plurality of monitoring submodules, and the monitoring submodules are arranged at each monitoring point; The monitoring unit is used to collect feedback data packets from each monitoring point; Specifically, the monitoring submodule is preferably various sensors and data acquisition devices, and the corresponding devices are selected according to the type of data required to be collected at its monitoring point.
[0049] The central control unit includes: The first processing module is used to construct the initial operation model and monitoring sub-strategy of each monitoring point; The second processing module is used to obtain feedback data packets of each monitoring point according to all monitoring sub-strategies, and generate a fault risk value of each monitoring point according to the feedback data packets and the initial operation model; An early warning module is used to determine whether to generate an early warning instruction based on the fault risk value; The first processing module is also used to establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
[0050] In a preferred embodiment of the present application, the first processing module is further configured to: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point according to the historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point; Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; The feedback time axis of the target monitoring point is set according to the monitoring sub-cycle duration t, and the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
[0051] In a preferred embodiment of the present application, the second processing module is further configured to: According to the number of monitoring points A, set a i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.
[0052] According to the first concept of the present application, multiple monitoring points are set based on the historical fault data of the high-voltage inverter, and the corresponding initial operation model is constructed according to the fault characteristic parameters of each monitoring point, so as to realize comprehensive monitoring of the high-voltage inverter, timely warn of the abnormal operating status of the high-voltage inverter, and improve the diagnostic efficiency of potential faults of the high-voltage inverter.
[0053] According to the second concept of the present application, by dynamically adjusting the monitoring sub-strategies of each monitoring point and periodically updating the corrected operation model of each monitoring point, interference in fault diagnosis caused by environmental fluctuations and monitoring data acquisition errors can be avoided, the fault diagnosis accuracy of the high-voltage inverter can be improved, and the safe operation of the high-voltage inverter can be ensured.
[0054] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.
Claims
1. A remote fault monitoring method for a high-voltage inverter, characterized in that: include: Set multiple monitoring points based on equipment parameters and historical fault parameters; Construct the initial operation model and monitoring sub-strategy for each monitoring point, and collect feedback data packets from each monitoring point according to all monitoring sub-strategies; Generate a fault risk value for each monitoring point based on the feedback data package and the initial operation model, and determine whether to generate an early warning instruction based on the fault risk value; Among them, when setting multiple monitoring points, including: Establish a monitoring point sequence A, A=(a1,a2…a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
2. The remote fault monitoring method for a high-voltage inverter according to claim 1, wherein: When constructing the initial operation model for each monitoring point, it includes: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point based on historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point.
3. The remote fault monitoring method for a high-voltage inverter according to claim 2, wherein: When constructing monitoring sub-strategies for each monitoring point, include: Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; Setting a feedback time axis of the target monitoring point according to the monitoring sub-cycle duration t, wherein the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
4. The remote fault monitoring method for a high-voltage inverter according to claim 3, wherein: When generating the monitoring evaluation value c, it includes: c=e1*Q1*[ β 1i *j i ]+e2*Q2*[ β 2i *w i ] Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; r1 is the number of monitoring sub-indicators of the target monitoring point; β 1i is the influencing factor of the i-th monitoring sub-indicator of the target monitoring point; j i is the fluctuation evaluation value of the i-th monitoring sub-indicator of the target monitoring point; r2 is the number of historical evaluation indicators; β 2i is the influencing factor of the i-th historical evaluation index of the target monitoring point; w i is the reference value of the i-th historical evaluation index of the target monitoring point.
5. The remote fault monitoring method for a high-voltage inverter according to claim 3, wherein: When generating the failure risk value for each monitoring point, the following are included: According to the number of monitoring points A, set a i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.
6. The remote fault monitoring method for a high-voltage inverter according to claim 5, characterized in that: When building a correction run model, include: Establish the monitoring sub-indicator sequence P of the monitoring point to be diagnosed, P=(p1, p2…p i …p r ), where p i is the ith monitoring sub-indicator of the monitoring point to be diagnosed; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; Generate the first-level operating value of each monitoring sub-indicator in the monitoring sub-indicator sequence P at the anchor time node; Generate a modified evaluation value h based on the fault risk value f' of the anchor time node and the monitoring evaluation value c' of the monitoring point to be diagnosed; Set the compensation coefficient g according to the corrected evaluation value h; A modified operation model is constructed based on the compensation coefficient g and all primary operation values.
7. The remote fault monitoring method for a high-voltage inverter according to claim 6, wherein: When generating the fault risk value at the current feedback time node, it includes: f=e3*[ β 3i *(k i -k' i) 2 ]+e4*[ β 3i *g*(k i -k 1i) 2 ] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; r is the number of monitoring sub-indicators of the monitoring point to be diagnosed; β 3i The influencing factor of the monitoring sub-indicator of the monitoring point to be diagnosed; k i is the real-time monitoring value of the i-th monitoring sub-indicator of the monitoring point to be diagnosed at the current feedback time node; k' i is the standard reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed; k 1i It is the first-level reference value of the ith monitoring sub-indicator of the monitoring point to be diagnosed.
8. A remote fault monitoring system for a high-voltage frequency converter, using the remote fault monitoring method for a high-voltage frequency converter according to any one of claims 1 to 7, characterized in that: include: Central control unit, used to set multiple monitoring points based on equipment parameters and historical fault parameters; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are arranged at each monitoring point; The monitoring unit is used to collect feedback data packets from each monitoring point; The central control unit includes: The first processing module is used to construct the initial operation model and monitoring sub-strategy of each monitoring point; The second processing module is used to obtain feedback data packets of each monitoring point according to all monitoring sub-strategies, and generate a fault risk value of each monitoring point according to the feedback data packets and the initial operation model; An early warning module is used to determine whether to generate an early warning instruction based on the fault risk value; The first processing module is also used to establish a monitoring point sequence A, A=(a1, a2...a i …a n ), where a i is the i-th monitoring point, and n is the number of monitoring points.
9. The remote fault monitoring system for a high-voltage inverter according to claim 8, wherein: The first processing module is further configured to: According to the number of monitoring points A, set a i is the target monitoring point; Extract the fault data packet of the target monitoring point according to the historical fault parameters; Generate multiple monitoring sub-indicators of the target monitoring point based on the fault data packet, and set the standard operating value of each monitoring sub-indicator; Construct the initial operation model of the target monitoring point based on all monitoring sub-indicators; Generate the initial operation model of each monitoring point in turn; Establish the initial running model sequence B, B=(b1,b2…b i …b n ), where b i is the initial operation model of the i-th monitoring point; Obtain historical monitoring data of target monitoring points; Generate monitoring evaluation value c based on historical monitoring data; According to the monitoring evaluation value c, the monitoring sub-cycle duration t of the target monitoring point is set; Setting a feedback time axis of the target monitoring point according to the monitoring sub-cycle duration t, wherein the feedback time axis includes multiple feedback time nodes; Obtain feedback data packets from target monitoring points according to preset feedback time nodes; Set the feedback timeline of each monitoring point in turn.
10. The remote fault monitoring system for a high-voltage inverter according to claim 9, characterized in that: The second processing module is further configured to: According to the number of monitoring points A, set a i It is a monitoring point to be diagnosed; Obtain the feedback data packet of the monitoring point to be diagnosed at the current feedback time node; Set the previous feedback time node of the current feedback time node as the anchor time node; Constructing a revised operation model based on the feedback data packet of the monitoring point to be diagnosed at the anchor time node; The fault risk value f of the monitoring point to be diagnosed at the current feedback time node is generated based on the initial operation model and the revised operation model.