Inverter operation state intelligent monitoring method and system

Abstract

The invention relates to the technical field of inverter monitoring, in particular to an inverter operation state intelligent monitoring method and system. Comprising the steps that a simulation monitoring model of the inverter is constructed, and the simulation monitoring model comprises a simulation sub-model and a disturbance sub-model; setting a plurality of monitoring points according to the simulation sub-model, and acquiring a monitoring data packet of each monitoring point according to a preset feedback time node; a state deviation value is generated according to the simulation monitoring model and all the monitoring data packets, and whether an early warning instruction is generated or not is judged according to the state deviation value; according to the method, the expected operation state of the inverter is periodically predicted by setting a plurality of monitoring points and a simulation monitoring model, meanwhile, the operation state of the inverter is analyzed and monitored by collecting multi-dimensional data in the operation process of the inverter, early warning maintenance is carried out on the abnormal operation state in time, and efficient and safe operation of the inverter is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of inverter monitoring, and in particular to a method and system for intelligently monitoring the operating status of an inverter. Background Art

[0002] An inverter is a power electronic device that converts direct current (DC) into alternating current (AC). It is widely used in fields such as solar power generation, electric vehicles, UPS (uninterruptible power supplies), and industrial control. Its core function is to generate AC power that meets load requirements through the rapid on-off operation of semiconductor switching devices (such as IGBTs and MOSFETs) combined with filtering circuits.

[0003] During long-term operation, inverters are prone to various faults such as IGBT short circuit, open circuit or aging. Especially in harsh external operating environments, the failure rate of inverter equipment exceeds 70%. However, the accuracy of inverter status monitoring and fault diagnosis is not high at this stage. Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides an intelligent monitoring method and system for the operating status of an inverter, aiming to improve the monitoring efficiency of the inverter and ensure the efficient and safe operation of the inverter.

[0005] In some embodiments of the present application, a method for intelligently monitoring the operating status of an inverter is provided, comprising: Constructing a simulation monitoring model for the inverter, wherein the simulation monitoring model includes a simulation sub-model and a disturbance sub-model; Set multiple monitoring points according to the simulation sub-model, and obtain monitoring data packets of each monitoring point according to the preset feedback time node; Generate a state deviation value based on the simulation monitoring model and all monitoring data packets, and determine whether to generate an early warning instruction based on the state deviation value; The preset feedback time nodes include: Establish a monitoring cycle sequence P, P=(p1, p2…p i …p m ), where p i is the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node.

[0006] In some embodiments of the present application, when constructing a simulation monitoring model, the following steps are included: Obtain the device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

[0007] In some embodiments of the present application, determining whether to generate a warning instruction based on a state deviation value includes: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

[0008] In some embodiments of the present application, generating a primary evaluation model for a target monitoring period includes: Obtain monitoring data packets of all monitoring points at the previous feedback time node of the target monitoring period; Generate the initial expected values of each monitoring indicator within the target monitoring period based on the simulation sub-model and all monitoring data packets; Determine whether to generate an adjustment instruction based on all initial expected values; Generate the first-level expected value of each monitoring indicator based on the judgment results; Generate a first-level evaluation model for the target monitoring period based on all first-level expected values.

[0009] In some embodiments of the present application, when setting the first-level compensation strategy for the target monitoring period, the following steps are included: According to the disturbance sub-scenario sequence A, set ai The target perturbation sub-scenario; Generate a similarity evaluation value b between the first-level disturbance scenario and the target disturbance sub-scenario; b=U×[ β i × (d i -d 1i ) 2 ] Among them, U is the conversion coefficient; θ1 is the number of operating disturbance indicators; β i is the influencing factor of the i-th operation disturbance index; d i is the reference value of the i-th operation disturbance index in the first-level disturbance scenario; d 1i is the reference value of the i-th operating disturbance index in the target disturbance sub-scenario; Generate similarity evaluation values of the first-level disturbance scenario and each disturbance sub-scenario in sequence; Establish similar evaluation value sequence B, B=(b1, b2…b i …b n ), where bi is the similarity evaluation value between the first-level disturbance scenario and the i-th target disturbance sub-scenario; m is the number of disturbance sub-scenarios; Set the maximum value b in the similarity evaluation value sequence B max The compensation sub-strategy corresponding to the disturbance sub-scenario is a first-level compensation strategy; According to the similarity evaluation value b max Set the correction factor g.

[0010] In some embodiments of the present application, generating the state deviation value f of the current feedback time node includes: f=e1×Q1×[ η i ×(c i -c 1i ) 2 ]+e2×Q2×g×[ η i ×(c i -r i ×c' i ) 2 ]; Wherein, 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; θ2 is the number of monitoring indicators; c i Generate the real-time reference value of the i-th monitoring indicator based on the evaluation data package; c 1i is the first-level expected value of the i-th monitoring indicator within the target monitoring period; c' i is the standard reference value of the i-th monitoring indicator in the standard sub-model; g is the correction coefficient; r iis the compensation coefficient for the i-th monitoring indicator based on the first-level compensation strategy; η i is the influencing factor of the i-th monitoring indicator.

[0011] In some embodiments of the present application, when a feedback time node is preset, it includes: Generate the monitoring evaluation value h of the current feedback time node; h= k i ×j i ; Among them, θ3 is the number of monitoring and evaluation indicators; k i is the influencing factor of the i-th monitoring and evaluation indicator; j i is the real-time reference value of the i-th monitoring and evaluation indicator at the current feedback time node; The duration of the next monitoring cycle is set according to the monitoring evaluation value h.

[0012] In some embodiments of the present application, a system for intelligently monitoring the operating status of an inverter is provided, comprising: A central control unit, configured to construct a simulation monitoring model for the inverter, wherein the simulation monitoring model includes a simulation sub-model and a disturbance sub-model; The central control unit is further used to set multiple monitoring points according to the simulation sub-model; 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 generate a monitoring data packet for each monitoring point according to a preset feedback time node; The central control unit includes: The first processing module is used to establish a monitoring period sequence P, P = (p1, p2...p i …p m ), where p i is the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node; The second processing module is used to generate a state deviation value according to the simulation monitoring model and all monitoring data packets. The second processing module is also used to determine whether to generate an early warning instruction according to the state deviation value.

[0013] In some embodiments of the present application, the central control unit further includes: A third processing module is used to obtain device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

[0014] In some embodiments of the present application, the second processing module is further configured to: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

[0015] Compared with the prior art, the method and system for intelligently monitoring the operating status of an inverter in the embodiment of the present application have the following beneficial effects: By setting multiple monitoring points and simulation monitoring models, the expected operating status of the inverter is periodically predicted. At the same time, by collecting multi-dimensional data during the operation of the inverter, the operating status of the inverter is analyzed and monitored, and abnormal operating conditions are promptly warned and repaired to ensure the efficient and safe operation of the inverter.

[0016] By establishing multiple disturbance sub-scenarios based on different external operating environments and setting corresponding compensation parameters for different disturbance environments, the early warning efficiency of inverter abnormal conditions is improved, and the interference of operating environment fluctuations on inverter status monitoring and fault diagnosis is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of an intelligent monitoring method for the operating status of an inverter in a 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 method for intelligently monitoring the operating status of an inverter according to a preferred embodiment of the present application includes: S101: Constructing a simulation monitoring model of the inverter, where the simulation monitoring model includes a simulation sub-model and a disturbance sub-model; S102: setting multiple monitoring points according to the simulation sub-model, and obtaining monitoring data packets of each monitoring point according to a preset feedback time node; S103: Generate a state deviation value based on the simulation monitoring model and all monitoring data packets, and determine whether to generate an early warning instruction based on the state deviation value; The preset feedback time nodes include: Establish a monitoring cycle sequence P, P=(p1, p2…p i …p m ), where p iis the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node.

[0023] Specifically, a simulation monitoring model is constructed based on the historical operating parameters and device parameters of the inverter. Its simulation sub-model can perform simulation analysis based on the collected real-time monitoring data of the inverter, thereby generating the expected operating status of the inverter within a single monitoring cycle.

[0024] Specifically, multiple monitoring points are established based on the simulation sub-model combined with equipment parameters and historical fault parameters (for example, at key components, multiple locations where ambient temperature can be collected, DC input side, AC output side, locations where operational risks are likely to occur, etc.) and the type of data required to be collected at each monitoring point is set. The data types required to be collected at the monitoring points include but are not limited to: input / output voltage and current, power parameters, key component temperature, ambient temperature, gate drive signal and voltage, IGBT conduction voltage drop, cooling fan speed and vibration, ambient grayscale and humidity, and other parameters.

[0025] Specifically, when building a simulation monitoring model, it includes: Obtain the device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

[0026] Specifically, the operating disturbance indicators include but are not limited to the system's required operating power, ambient temperature, total equipment operating time, ambient humidity, ambient grayscale, equipment loss and other parameters. By quantifying each operating disturbance indicator, multiple value ranges of each operating disturbance indicator are generated, and multiple disturbance sub-scenarios are constructed through random combinations of each value range.

[0027] Specifically, the compensation sub-strategy includes compensation coefficients for the safety thresholds of each monitoring indicator in the current disturbance sub-scenario. By dynamically adjusting the safety thresholds of each monitoring indicator, the significance of abnormal operating conditions is increased, and the effectiveness of early warning of abnormal inverter conditions is improved.

[0028] In a preferred embodiment of the present application, when determining whether to generate a warning instruction according to the state deviation value, the method includes: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

[0029] Specifically, preprocessing all monitoring data packets refers to cleaning and fusion analysis of the data in all monitoring data packets, thereby generating real-time values of various monitoring indicators.

[0030] Specifically, the state deviation value threshold can be set according to historical parameters.

[0031] Specifically, the larger the state deviation value, the greater the possibility that the current inverter has an abnormal operating state and potential faults. If the real-time state deviation value f is greater than the preset state deviation value threshold, the inverter device needs to be repaired in time.

[0032] Specifically, when generating the first-level evaluation model for the target monitoring cycle, it includes: Obtain monitoring data packets of all monitoring points at the previous feedback time node of the target monitoring period; Generate the initial expected values of each monitoring indicator within the target monitoring period based on the simulation sub-model and all monitoring data packets; Determine whether to generate an adjustment instruction based on all initial expected values; Generate the first-level expected value of each monitoring indicator based on the judgment results; Generate a first-level evaluation model for the target monitoring period based on all first-level expected values.

[0033] Specifically, the simulation sub-model simulates and analyzes all the actual operating parameters of the inverter during the previous monitoring cycle to generate initial expected values for each monitoring indicator during the current monitoring cycle. A comprehensive analysis of all these initial expected values is performed to determine whether the current inverter is inefficient. If so, the corresponding adjustment parameters are generated and the first-level expected values of each monitoring indicator are predicted based on the adjustment parameters to ensure the inverter's operating efficiency. Specifically, when setting the first-level compensation strategy for the target monitoring period, it includes: According to the disturbance sub-scenario sequence A, set a i The target perturbation sub-scenario; Generate a similarity evaluation value b between the first-level disturbance scenario and the target disturbance sub-scenario; b=U×[ β i × (d i -d 1i ) 2 ] Among them, U is the conversion coefficient; θ1 is the number of operating disturbance indicators; β i is the influencing factor of the i-th operation disturbance index; d i is the reference value of the i-th operation disturbance index in the first-level disturbance scenario; d 1i is the reference value of the i-th operating disturbance index in the target disturbance sub-scenario; Generate similarity evaluation values of the first-level disturbance scenario and each disturbance sub-scenario in sequence; Establish similar evaluation value sequence B, B=(b1, b2…b i …b n ), where bi is the similarity evaluation value between the first-level disturbance scenario and the i-th target disturbance sub-scenario; m is the number of disturbance sub-scenarios; Set the maximum value b in the similarity evaluation value sequence B max The compensation sub-strategy corresponding to the disturbance sub-scenario is a first-level compensation strategy; According to the similarity evaluation value b max Set the correction factor g.

[0034] Specifically, the larger the similarity evaluation value is, the smaller the correction coefficient is, and the value of the correction coefficient is always greater than 1. By dynamically adjusting the correction coefficient, the efficiency of identifying abnormal operating conditions of the inverter is enhanced.

[0035] Specifically, when generating the state deviation value f of the current feedback time node, it includes: f=e1×Q1×[ η i ×(c i -c 1i )2 ]+e2×Q2×g×[ η i ×(c i -r i ×c' i ) 2 ]; Wherein, 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; θ2 is the number of monitoring indicators; c i Generate the real-time reference value of the i-th monitoring indicator based on the evaluation data package; c 1i is the first-level expected value of the i-th monitoring indicator within the target monitoring period; c' i is the standard reference value of the i-th monitoring indicator in the standard sub-model; g is the correction coefficient; r i is the compensation coefficient for the i-th monitoring indicator based on the first-level compensation strategy; η i is the influencing factor of the i-th monitoring indicator.

[0036] 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.

[0037] It can be understood that in the above embodiment, the expected operating status of the inverter is periodically predicted by setting multiple monitoring points and simulation monitoring models. At the same time, the operating status of the inverter is analyzed and monitored by collecting multi-dimensional data during the operation of the inverter, and abnormal operating conditions are warned and repaired in time to ensure efficient and safe operation of the inverter.

[0038] In a preferred embodiment of the present application, when the feedback time node is preset, it includes: Generate the monitoring evaluation value h of the current feedback time node; h= k i ×j i ; Among them, θ3 is the number of monitoring and evaluation indicators; k i is the influencing factor of the i-th monitoring and evaluation indicator; j i is the real-time reference value of the i-th monitoring and evaluation indicator at the current feedback time node; The duration of the next monitoring cycle is set according to the monitoring evaluation value h.

[0039] Specifically, the monitoring and evaluation indicators include, but are not limited to, the number of historical failures, the frequency of abnormal conditions, the average value and development trend of the state deviation value within the historical monitoring period, and other parameters.

[0040] Specifically, the larger the monitoring evaluation value, the greater the possibility that the inverter will experience abnormal operating conditions in the future, and the shorter the duration of the next monitoring cycle, thereby improving the monitoring efficiency of the inverter.

[0041] Based on another preferred embodiment of an intelligent monitoring method for inverter operation status in any of the above preferred embodiments, this preferred embodiment provides an intelligent monitoring method for inverter operation status, including: The central control unit is used to build a simulation monitoring model for the inverter. The simulation monitoring model includes a simulation sub-model and a disturbance sub-model. The central control unit is also used to set multiple monitoring points according to the simulation sub-model; 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 generate monitoring data packets for each monitoring point according to the preset feedback time node; The central control unit includes: The first processing module is used to establish a monitoring period sequence P, P = (p1, p2...p i …p m ), where p i is the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node; The second processing module is used to generate a state deviation value according to the simulation monitoring model and all monitoring data packets. The second processing module is also used to determine whether to generate an early warning instruction according to the state deviation value.

[0042] Specifically, the monitoring submodule is preferably various types of data sensors, and different collection devices are selected according to the type of data to be collected at the monitoring point.

[0043] In a preferred embodiment of the present application, the central control unit further includes: A third processing module is used to obtain device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

[0044] Specifically, the second processing module is further configured to: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

[0045] According to the first concept of the present application, the expected operating status of the inverter is periodically predicted by setting multiple monitoring points and simulation monitoring models. At the same time, the operating status of the inverter is analyzed and monitored by collecting multi-dimensional data during the operation of the inverter, and abnormal operating status is warned and repaired in time to ensure efficient and safe operation of the inverter.

[0046] According to the second concept of the present application, by establishing multiple disturbance sub-scenarios based on different external operating environments and setting corresponding compensation parameters for different disturbance environments, the early warning efficiency of the inverter abnormal state is improved, and the interference of operating environment fluctuations on inverter status monitoring and fault diagnosis is reduced.

[0047] 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. An intelligent monitoring method for inverter operation status, characterized in that: include: Constructing a simulation monitoring model for the inverter, wherein the simulation monitoring model includes a simulation sub-model and a disturbance sub-model; Set multiple monitoring points according to the simulation sub-model, and obtain monitoring data packets of each monitoring point according to the preset feedback time node; Generate a state deviation value based on the simulation monitoring model and all monitoring data packets, and determine whether to generate an early warning instruction based on the state deviation value; The preset feedback time nodes include: Establish a monitoring cycle sequence P, P=(p1, p2…p i …p m ), where p i is the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node.

2. The method for intelligently monitoring the inverter operating status according to claim 1, wherein: When building a simulation monitoring model, include: Obtain the device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

3. The method for intelligently monitoring the inverter operating status according to claim 2, wherein: When judging whether to generate an early warning instruction based on the state deviation value, it includes: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

4. The method for intelligently monitoring the inverter operating status according to claim 3, wherein: When generating the first-level evaluation model for the target monitoring cycle, include: Obtain monitoring data packets of all monitoring points at the previous feedback time node of the target monitoring period; Generate the initial expected values of each monitoring indicator within the target monitoring period based on the simulation sub-model and all monitoring data packets; Determine whether to generate an adjustment instruction based on all initial expected values; Generate the first-level expected value of each monitoring indicator based on the judgment results; Generate a first-level evaluation model for the target monitoring period based on all first-level expected values.

5. The method for intelligently monitoring the inverter operating status according to claim 4, wherein: When setting the first-level compensation strategy for the target monitoring period, include: According to the disturbance sub-scenario sequence A, set a i Perturb the target sub-scenario; Generate a similarity evaluation value b between the first-level disturbance scenario and the target disturbance sub-scenario; b=U×[ b i ×(d) i -d 1i ) 2 ] Among them, U is the conversion coefficient; θ1 is the number of operating disturbance indicators; β i is the influencing factor of the i-th operation disturbance index; d i is the reference value of the i-th operation disturbance index in the first-level disturbance scenario; d 1i is the reference value of the i-th operating disturbance index in the target disturbance sub-scenario; Generate similarity evaluation values of the first-level disturbance scenario and each disturbance sub-scenario in sequence; Establish similar evaluation value sequence B, B=(b1, b2…b i …b n ), where bi is the similarity evaluation value between the first-level disturbance scenario and the i-th target disturbance sub-scenario; m is the number of disturbance sub-scenarios; Set the maximum value b in the similarity evaluation value sequence B max The compensation sub-strategy corresponding to the disturbance sub-scenario is a first-level compensation strategy; According to the similarity evaluation value b max Set the correction factor g.

6. The method for intelligently monitoring the inverter operating status according to claim 5, wherein: When generating the state deviation value f of the current feedback time node, it includes: f=e1×Q1×[ or i ×(c i -c 1i ) 2 ]+e2×Q2×g×[ or i ×(c i -r i ×c' i ) 2 ]; Wherein, 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; θ2 is the number of monitoring indicators; c i Generates the real-time reference value of the i-th monitoring indicator based on the evaluation data package; c 1i is the first-level expected value of the i-th monitoring indicator within the target monitoring period; c' i is the standard reference value of the i-th monitoring indicator in the standard sub-model; g is the correction coefficient; r i is the compensation coefficient for the i-th monitoring indicator based on the first-level compensation strategy; η i is the influencing factor of the i-th monitoring indicator.

7. The method for intelligently monitoring the inverter operating status according to claim 6, wherein: When presetting feedback time nodes, include: Generate the monitoring evaluation value h of the current feedback time node; h= k i ×j i ; Among them, θ3 is the number of monitoring and evaluation indicators; k i is the influencing factor of the i-th monitoring and evaluation indicator; j i is the real-time reference value of the i-th monitoring and evaluation indicator at the current feedback time node; The duration of the next monitoring cycle is set according to the monitoring evaluation value h.

8. An intelligent monitoring system for inverter operation status, adopting the intelligent monitoring method for inverter operation status according to any one of claims 1 to 7, characterized in that: include: A central control unit, configured to construct a simulation monitoring model for the inverter, wherein the simulation monitoring model includes a simulation sub-model and a disturbance sub-model; The central control unit is further used to set multiple monitoring points according to the simulation sub-model; 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 generate a monitoring data packet for each monitoring point according to a preset feedback time node; The central control unit includes: The first processing module is used to establish a monitoring period sequence P, P = (p1, p2...p i …p m ), where p i is the i-th monitoring period; m is the duration of the monitoring period; Set the end time node of each monitoring cycle as the feedback time node; The second processing module is used to generate a state deviation value according to the simulation monitoring model and all monitoring data packets. The second processing module is also used to determine whether to generate an early warning instruction according to the state deviation value.

9. The intelligent monitoring system for inverter operation status according to claim 8, characterized in that: The central control unit also includes: A third processing module is used to obtain device parameters and historical operating parameters of the inverter; Generate training data packets and multiple running perturbation indicators; Construct a simulation sub-model based on the training data package, and set multiple monitoring indicators based on the simulation sub-model; Establish a standard sub-model based on all monitoring indicators; Set multiple disturbance sub-scenarios based on all operational disturbance indicators; Establish a perturbation sub-scenario sequence A, A=(a1,a2…a i …a n ), where a i is the i-th disturbance sub-scenario; n is the number of disturbance sub-scenarios; Set the compensation sub-strategy of the standard sub-model in each disturbance sub-scenario; The disturbance sub-model is set according to the overall compensation sub-strategy.

10. The intelligent monitoring system for inverter operation status according to claim 8, characterized in that: The second processing module is further configured to: Set the monitoring period corresponding to the current feedback time node as the target monitoring period; Obtain all monitoring data packets of the current feedback time node and pre-process all monitoring data packets; Generate evaluation data packets and first-level disturbance scenarios for the target monitoring period based on the preprocessing results; Generate a first-level evaluation model for the target monitoring cycle based on the simulation sub-model; Set a first-level compensation strategy for the target monitoring period according to the first-level disturbance scenario, and generate a second-level evaluation model for the target monitoring period based on the first-level compensation strategy; Construct evaluation sub-models based on the first-level evaluation model and the second-level evaluation model; Generate the state deviation value f of the current feedback time node based on the evaluation sub-model and evaluation data packet; Preset state deviation threshold F1; If f>F1, the current feedback time node generates a first-level warning instruction.

Images