Power equipment state monitoring method and system based on multi-source data

Abstract

The invention relates to the technical field of power equipment monitoring, in particular to a power equipment state monitoring method and system based on multi-source data. Comprising the steps of setting a plurality of equipment points based on power equipment parameters and constructing a state evaluation model; generating a state abnormal value of each equipment point according to the state evaluation model, and setting a diagnosis strategy according to the state abnormal value; generating operation risk parameters of each equipment point according to the diagnosis strategy, and judging whether an early warning instruction is generated or not according to the operation risk parameters; a plurality of equipment buying points are established according to historical data of power equipment, a corresponding evaluation sub-model is established according to the category of data acquired by each equipment point, real-time abnormal data of the equipment points are analyzed through the evaluation sub-models, and a data acquisition strategy of each equipment point is dynamically adjusted, so that real-time online monitoring of the power equipment is realized. The monitoring and early warning efficiency of various types of power equipment is improved, and the overall monitoring operation and maintenance cost is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment monitoring, and in particular to a method and system for monitoring the status of power equipment based on multi-source data. Background Art

[0002] In the power system, the normal and stable operation of equipment such as transformers, reactors, and disconnectors is the basis for the safe operation of the system. As the installed power capacity and transmission energy are increasing, the failure and shutdown of a single power equipment will have a huge impact on the stability of the system. Therefore, real-time monitoring of the operating status of power equipment is particularly important.

[0003] As the equipment's operating period increases, its performance and reliability gradually decline, and the equipment failure rate gradually increases, which may endanger the safe operation of the system. The operating status of these devices must be monitored. Currently, the detection methods for the operation of power equipment are mostly manual inspections. Manual inspections have certain limitations and are often only based on observations of the electrical appearance. It is difficult to detect internal problems of the equipment in a timely manner. Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a method and system for monitoring the status of power equipment based on multi-source data, aiming to improve the early warning efficiency of potential faults of power equipment and ensure the safe operation of power equipment.

[0005] In some embodiments of the present application, a method for monitoring the status of power equipment based on multi-source data is provided, comprising: Set multiple equipment points based on power equipment parameters and build a status assessment model; Generate abnormal status values for each device point based on the status assessment model, and set diagnostic strategies based on the abnormal status values; Generate operational risk parameters for each equipment point based on the diagnostic strategy, and determine whether to generate an early warning instruction based on the operational risk parameters; When setting multiple equipment points, it includes: Create a device point array A, A=(a1,a2…a i …a n ), where a i is the i-th device point; n is the number of device points.

[0006] In some embodiments of the present application, establishing a state assessment model includes: Set a in sequence according to the device point column A i is the target device point; Generate multiple training data packets based on the historical operating data of the target equipment point; Establish an evaluation sub-model for the target device point based on all training data packets; Generate the monitoring evaluation value b of the target device point; Set the evaluation cycle duration w of the target device point according to the monitoring evaluation value; Set the evaluation time axis of the target device point according to the evaluation cycle duration w, and multiple evaluation time nodes are included on the evaluation time axis; Generate the evaluation sub-model and evaluation time axis of each device point in sequence; Establish a state evaluation model according to all evaluation sub-models and all evaluation time axes.

[0007] In some embodiments of the present application, when generating the monitoring evaluation value b of the target device point, it includes: Obtain the historical operation data of the target device point; Generate the monitoring evaluation value b of the target device point according to the historical operation data; b = β i * k i ; Where, θ1 is the number of historical evaluation indicators; β i is the influence factor of the i-th historical evaluation indicator; k i is the reference value of the i-th historical evaluation indicator in the target device point.

[0008] In some embodiments of the present application, when generating the state anomaly value of each device point according to the state evaluation model, it includes: Set a i as the device point to be evaluated in sequence according to the device point sequence A; Set the evaluation sub-model of the device point to be evaluated as the first-level evaluation model; Obtain the monitoring data packet of the current evaluation time node based on the evaluation time axis of the device point to be evaluated; Generate the state anomaly value f of the device point to be evaluated at the current evaluation time node according to the monitoring data packet and the first-level evaluation model; Preset the first anomaly evaluation value threshold F1; If f < F1, generate a first-level transmission instruction for the device point to be evaluated at the current evaluation time node, and generate a sub-data packet of the device point to be evaluated according to the first-level transmission instruction; If f > F1, generate a second-level transmission instruction for the device point to be evaluated at the current evaluation time node.

[0009] In some embodiments of the present application, when generating the state anomaly value f of the current evaluation time node, it includes: f = η i * (d i - d' i ) 2 ; Among them, θ2 is the number of monitoring indicators of the device point to be evaluated; η i is the influence factor of the i-th monitoring indicator of the device point to be evaluated; d i is the reference value of the i-th monitoring indicator of the device point to be evaluated at the current evaluation time node; d' i is the standard reference value of the i-th monitoring indicator of the device point to be evaluated.

[0010] In some embodiments of the present application, when setting the diagnosis strategy according to the status outlier value, it includes: Establish multiple monitoring cycles; Judge whether there is a secondary transmission instruction for each device point within the current monitoring cycle; If it exists, generate a primary sub-strategy; If it does not exist, generate a secondary sub-strategy; The secondary sub-strategy includes: Obtain the feedback data packet of each device point according to the end time node of the current monitoring cycle; Generate the potential risk value of each device point according to all the feedback data packets; Establish a potential risk value sequence H, H=(h1, h2…h i …h n ), where h i is the potential risk value of the i-th device point; n is the number of device points; Preset a potential risk value threshold H1; If h i >H1, generate a secondary warning instruction for the i-th device point.

[0011] In some embodiments of the present application, the primary sub-strategy includes: If the i-th device point has a secondary transmission instruction, set the i-th device point as a risk device point; Obtain the real-time operation parameters of the risk device point; Generate the operation risk value g of the risk device point according to the preset diagnosis model and the real-time operation parameters; Preset an operation risk value threshold G1; If g>G1, generate a primary warning instruction for the risk device point; If g<G1, do not generate a warning instruction. [[ID=�4]]

[0012] In some embodiments of the present application, when generating the potential risk value of each device point according to all the feedback data packets, it includes: Set a i as the device point to be diagnosed in turn according to the device point sequence A; Obtain the feedback data packet of the device point to be diagnosed, and the feedback data packet includes multiple sub-data packets; Establish multiple time intervals within the current monitoring cycle according to the evaluation cycle length w' of the device point to be diagnosed; Generate abnormal evaluation values in each time interval and establish abnormal evaluation value series F, F=(f'1,f'2…f' i …f' m ), where f' i is the abnormal evaluation value in the i-th time interval; m is the number of time intervals set for the device point to be diagnosed in the current monitoring cycle; h=e1*Q1*[ f' i ]+e2*Q2*[ α i *j i ]; Among them, e1 is the preset third weight coefficient; e2 is the preset fourth weight coefficient; Q1 is the preset third fixed coefficient; Q2 is the preset fourth fixed coefficient; θ3 is the number of risk assessment indicators; α i is the influencing factor of the i-th risk assessment indicator; j i is the reference value of the i-th risk assessment index generated based on the feedback data packet of the device point to be diagnosed; Generate the potential risk value of each equipment point in turn.

[0013] In some embodiments of the present application, a power equipment status monitoring system based on multi-source data is provided, comprising: The central control unit sets multiple equipment points based on power equipment parameters and builds a status assessment model; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are provided at each equipment point, and the monitoring unit is used to generate a state abnormality value of each equipment point according to a state assessment model; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; A second processing module is used to set a diagnosis strategy according to the abnormal state value; The third processing module is used to generate operation risk parameters for each equipment point and determine whether to generate an early warning instruction based on the operation risk parameters.

[0014] In some embodiments of the present application, the central control unit further includes: The fourth processing module is used to set a in sequence according to the device point sequence A. i is the target device point; Generate multiple training data packets based on the historical operating data of the target equipment point; Establish an evaluation sub-model for the target device point based on all training data packets; Obtain historical operation data of target equipment points; Generate monitoring evaluation value b of target equipment point based on historical operation data; b=[ β i *k i ]; Among them, θ1 is the number of historical evaluation indicators; β i is the impact factor of the i-th historical evaluation index; k i is the reference value of the i-th historical evaluation index in the target device point Set the evaluation cycle duration w of the target equipment point according to the monitoring evaluation value; Setting an evaluation timeline for the target device point according to the evaluation cycle length w, wherein the evaluation timeline includes multiple evaluation time nodes; Generate the evaluation sub-model and evaluation timeline for each equipment point in sequence; A status assessment model is established based on all assessment sub-models and the entire assessment timeline.

[0015] Compared with the prior art, the method and system for monitoring the status of electric power equipment based on multi-source data in the embodiment of the present application have the following advantages: Based on the historical data of power equipment, multiple equipment buying points are established, and corresponding evaluation sub-models are established according to the data collection categories of each equipment point. The real-time abnormal data of the equipment point is analyzed through the evaluation sub-model, and the data collection strategy of each equipment point is dynamically adjusted to achieve real-time online monitoring of power equipment, improve the monitoring and early warning efficiency of various types of power equipment, and reduce the overall monitoring and operation and maintenance costs.

[0016] By setting up multiple equipment points and evaluation sub-models for each equipment point, the overall system is monitored in multiple dimensions. By integrating and analyzing the monitoring data of each equipment point, early warning and maintenance are carried out in a timely manner for equipment points with operational risks to ensure the stable operation of each power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for monitoring the status of electric power equipment based on multi-source data 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, electrical connections; direct connections, 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 monitoring the state of electric power equipment based on multi-source data according to a preferred embodiment of the present application includes: S101: Setting multiple equipment points based on power equipment parameters and building a status assessment model; S102: Generate state abnormality values for each device point according to the state assessment model, and set a diagnosis strategy based on the state abnormality values; S103: Generate the operation risk parameters of each equipment point according to the diagnosis strategy, and determine whether to generate an early warning instruction based on the operation risk parameters When setting multiple equipment points, it includes: Create a device point array A, A=(a1,a2…a i …a n ), where a i is the i-th device point; n is the number of device points.

[0023] Specifically, multiple equipment points are established according to different power equipment such as transformers, reactors, and disconnectors.

[0024] Specifically, according to the equipment type corresponding to different equipment points, the monitoring index parameters of each equipment point are dynamically adjusted, and the corresponding evaluation sub-model is constructed to realize multi-source data collection and analysis of each equipment point, and timely early warning of abnormal operating status of each equipment point.

[0025] Specifically, when establishing a status assessment model, it includes: Set a in sequence according to the device point column A i is the target device point; Generate multiple training data packets based on the historical operating data of the target equipment point; Establish an evaluation sub-model for the target device point based on all training data packets; Generate monitoring evaluation value b of target equipment point; Set the evaluation cycle duration w of the target equipment point according to the monitoring evaluation value; Setting an evaluation timeline for the target device point according to the evaluation cycle length w, wherein the evaluation timeline includes multiple evaluation time nodes; Generate the evaluation sub-model and evaluation timeline for each equipment point in sequence; A status assessment model is established based on all assessment sub-models and the entire assessment timeline.

[0026] Specifically, the time interval between adjacent evaluation time nodes is the length of a single evaluation cycle.

[0027] Specifically, the training data package contains various fault characteristic parameters generated by screening the historical fault data of the target equipment point, setting the monitoring indicators corresponding to the target equipment point based on all the fault characteristic parameters, and setting the evaluation sub-model of the target equipment point based on each monitoring indicator.

[0028] Specifically, the monitoring indicators include but are not limited to current, voltage, high-frequency pulse current or electromagnetic waves, winding / coil temperature (transformer, motor), joint / contact temperature (switch cabinet, cable joint), operating voltage, operating current, temperature, humidity, vibration, displacement, contact resistance and other parameters associated with the fault of the target equipment point. By quantifying each monitoring indicator, a target equipment point evaluation sub-model is constructed.

[0029] Specifically, when generating the monitoring evaluation value b of the target equipment point, it includes: Obtain historical operation data of target equipment points; Generate monitoring evaluation value b of target equipment point based on historical operation data; b=[ β i *k i ]; Among them, θ1 is the number of historical evaluation indicators; β iis the influence factor of the i-th historical evaluation index; k i is the reference value of the i-th historical evaluation index among the target device points.

[0030] Specifically, the historical evaluation indexes include but are not limited to the historical risk times of the current device, the frequency of operation anomalies, the fault impact degree and other parameters. By quantifying each historical evaluation index, a monitoring evaluation value corresponding to the target device point is generated.

[0031] Specifically, the larger the monitoring evaluation value is, the greater the possibility that the current device point is in an abnormal operation state, and the smaller the corresponding data evaluation cycle duration w is.

[0032] It can be understood that in the above embodiments, the evaluation cycle duration of each device point is dynamically adjusted according to the monitoring evaluation values of each device point, so as to reduce the monitoring and operation and maintenance costs on the basis of ensuring the recognition efficiency of the abnormal states of each device point, and timely warn of the abnormal states of each device point.

[0033] In the preferred embodiment of the present application, when generating the state abnormal value of each device point according to the state evaluation model, it includes: Set a[[ID=1十七]] i as the device point to be evaluated in sequence according to the device point sequence A; Set the evaluation sub-model of the device point to be evaluated as the primary evaluation model; Obtain the monitoring data packet of the current evaluation time node based on the evaluation time axis of the device point to be evaluated; Generate the state abnormal value f of the device point to be evaluated at the current evaluation time node according to the monitoring data packet and the primary evaluation model; Preset the first abnormal evaluation value threshold F1; If f < F1, generate a primary transmission instruction for the device point to be evaluated at the current evaluation time node, and generate a sub-data packet for the device point to be evaluated according to the primary transmission instruction; If f > F1, generate a secondary transmission instruction for the device point to be evaluated at the current evaluation time node.

[0034] Specifically, the first abnormal evaluation value threshold can be set according to historical parameters.

[0035] Specifically, the primary transmission instruction means generating a sub-data packet according to the operation data collected during the current evaluation cycle, first storing it in the monitoring sub-module, and forming a feedback data packet with all the sub-data packets according to the preset time node and sending it to the central control unit.

[0036] Specifically, the secondary transmission instruction means transmitting the operation data of the current device point to the central control unit in real time for analysis, generating a corresponding operation risk value, so as to timely warn of the fault risk of the device point.

[0037] Specifically, when generating the state abnormal value f of the current evaluation time node, it includes: f=[ η i *(d i -d' i ) 2 ]; Among them, θ2 is the number of monitoring indicators of the equipment point to be evaluated; η i is the influencing factor of the i-th monitoring indicator of the equipment point to be evaluated; d i is the reference value of the i-th monitoring indicator of the equipment point to be evaluated at the current evaluation time node; d' i is the standard reference value of the i-th monitoring indicator of the equipment point to be evaluated.

[0038] Specifically, the larger the abnormality evaluation value, the greater the deviation between the current operating state of the equipment point and the normal state, and the greater the possibility of potential failure risk.

[0039] Specifically, the standard reference value of each monitoring indicator can be set according to the historical monitoring parameters of the equipment point to be evaluated.

[0040] It is understood that in the above embodiment, the evaluation sub-model is used to identify and analyze real-time abnormal data of equipment points, dynamically adjust the diagnosis strategy of each equipment point, reduce the overall monitoring and maintenance costs, and achieve real-time monitoring of power equipment.

[0041] In a preferred embodiment of the present application, when setting a diagnostic strategy based on a state abnormality value, it includes: Establish multiple monitoring cycles; Determine whether there is a secondary transmission instruction at each device point within the current monitoring cycle; If it exists, generate a first-level sub-strategy; If it does not exist, generate a secondary sub-strategy; The secondary sub-strategies include: Obtain feedback data packets from each device point based on the end time node of the current monitoring cycle; Generate potential risk values for each device point based on all feedback data packets; Establish a potential risk value series H, H=(h1,h2…h i …h n ), where h i is the potential risk value of the i-th equipment point; n is the number of equipment points; Preset potential risk value threshold H1; If h i >H1, generate the secondary warning instruction for the i-th equipment point.

[0042] Specifically, the first-level sub-strategies include: If there is a secondary transmission instruction for the i-th device point, set the i-th device point as a risk device point; Obtain the real-time operating parameters of the risk device point; Generate an operating risk value g for the risk device point according to a preset diagnostic model and the real-time operating parameters; Preset an operating risk value threshold G1; If g > G1, generate a first-level warning instruction for the risk device point; If g < G1, do not generate a warning instruction.

[0043] Specifically, the real-time operating parameters are the real-time parameters of each monitoring index in the evaluation sub-model corresponding to the risk device point.

[0044] Specifically, the potential risk value threshold can be set according to historical parameters.

[0045] Specifically, the operating risk value threshold G1 can be set according to historical parameters.

[0046] Specifically, through a preset risk analysis model, the real-time operating parameters are fused and analyzed to generate the operating risk value of the risk device point. The larger the operating risk value, the greater the possibility that the current risk device point has a fault risk.

[0047] Specifically, the first-level warning instruction means that the current risk device point is in operation and needs to be repaired in time.

[0048] Specifically, when generating the potential risk value of each device point according to all feedback data packets, it includes: Set a i as the device point to be diagnosed in sequence according to the device point sequence A; Obtain the feedback data packet of the device point to be diagnosed, and the feedback data packet includes multiple sub-data packets; Establish multiple time intervals within the current monitoring period according to the evaluation cycle duration w' of the device point to be diagnosed; Generate an abnormal evaluation value for each time interval, and establish an abnormal evaluation value sequence F, F = (f'1, f'2…f' i …f' m ), where f' i is the abnormal evaluation value in the i-th time interval; m is the number of time intervals set for the device point to be diagnosed within the current monitoring period; h = e1*Q1* f' i +e2*Q2* α i *j i ; Among them, e1 is the preset third weight coefficient; e2 is the preset fourth weight coefficient; Q1 is the preset third fixed coefficient; Q2 is the preset fourth fixed coefficient; θ3 is the number of risk assessment indicators; α i is the influencing factor of the i-th risk assessment indicator; j i is the reference value of the i-th risk assessment index generated based on the feedback data packet of the device point to be diagnosed; Generate the potential risk value of each equipment point in turn.

[0049] Specifically, risk assessment indicators include but are not limited to Specifically, a second-level warning instruction means that there is a potential failure risk at the current equipment point. It is necessary to formulate a maintenance plan in combination with all second-level warning instructions to eliminate all potential risks in a timely manner and ensure the safe operation of power equipment.

[0050] Specifically, risk assessment indicators include but are not limited to the stability of various operating parameters of the monitoring point, the changing trend of abnormal evaluation values over time, and other parameters. The larger the potential risk value, the more unstable the operating status of the current equipment point is, and the greater the possibility of potential failure risk.

[0051] It can be understood that in the above embodiment, by setting multiple equipment points and evaluation sub-models for each equipment point, the overall system is monitored in multiple dimensions, and through the fusion analysis of the monitoring data of each equipment point, early warning and maintenance are carried out in time for equipment points with operation risks to ensure the stable operation of each power equipment.

[0052] 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 in the same value range.

[0053] Based on another preferred embodiment of a method for monitoring the state of an electric power device based on multi-source data in any of the above preferred embodiments, this preferred embodiment provides a method for monitoring the state of an electric power device based on multi-source data, comprising: The central control unit sets multiple equipment points based on power equipment parameters and builds a status assessment model; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are provided at each equipment point, and the monitoring unit is used to generate a state abnormality value of each equipment point according to a state assessment model; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; A second processing module is used to set a diagnosis strategy according to the abnormal state value; The third processing module is used to generate operation risk parameters for each equipment point and determine whether to generate an early warning instruction based on the operation risk parameters.

[0054] Specifically, the monitoring submodule is preferably various types of sensors, and the corresponding sensor equipment parameters are set according to the types of monitoring indicators that need to be collected by the monitoring points corresponding to the monitoring submodel.

[0055] In a preferred embodiment of the present application, the central control unit further includes: The fourth processing module is used to set a in sequence according to the device point sequence A. i is the target device point; Generate multiple training data packets based on the historical operating data of the target equipment point; Establish an evaluation sub-model for the target device point based on all training data packets; Obtain historical operation data of target equipment points; Generate monitoring evaluation value b of target equipment point based on historical operation data; b=[ β i *k i ]; Among them, θ1 is the number of historical evaluation indicators; β i is the impact factor of the i-th historical evaluation index; k i is the reference value of the i-th historical evaluation index in the target device point Set the evaluation cycle duration w of the target equipment point according to the monitoring evaluation value; Setting an evaluation timeline for the target device point according to the evaluation cycle length w, wherein the evaluation timeline includes multiple evaluation time nodes; Generate the evaluation sub-model and evaluation timeline for each equipment point in sequence; A status assessment model is established based on all assessment sub-models and the entire assessment timeline.

[0056] According to the first concept of the present application, multiple equipment buying points are established based on the historical data of the power equipment, and corresponding evaluation sub-models are established according to the data categories collected at each equipment point. The real-time abnormal data of the equipment point is analyzed through the evaluation sub-model, and the data collection strategy of each equipment point is dynamically adjusted to realize real-time online monitoring of the power equipment, improve the monitoring and early warning efficiency of various types of power equipment, and reduce the overall monitoring and operation and maintenance costs.

[0057] According to the second concept of this application, by setting multiple equipment points and evaluation sub-models for each equipment point, the overall system is monitored in multiple dimensions, and through the fusion analysis of the monitoring data of each equipment point, early warning and maintenance are carried out in time for equipment points with operational risks to ensure the stable operation of each power equipment.

[0058] 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 method for monitoring the status of power equipment based on multi-source data, characterized in that: It includes: Set multiple device points based on power equipment parameters and construct a state evaluation model; Generate state anomaly values for each device point according to the state evaluation model, and set a diagnosis strategy based on the state anomaly values; Generate operation risk parameters for each device point according to the diagnosis strategy, and determine whether to generate a warning instruction based on the operation risk parameters; Among them, when setting multiple device points, it includes: Create a device point array A, A=(a1,a2…a i …a n ), where a i is the i-th device point; n is the number of device points.

2. The method for monitoring the state of electric power equipment based on multi-source data according to claim 1, characterized in that: When establishing a state evaluation model, it includes: Set a in sequence according to the device point column A i is the target device point; Generate multiple training data packets based on the historical operation data of the target device point; Establish an evaluation sub-model of the target device point based on all the training data packets; Generate a monitoring evaluation value b of the target device point; Set the evaluation cycle duration w of the target device point according to the monitoring evaluation value; Set the evaluation time axis of the target device point according to the evaluation cycle duration w, and the evaluation time axis includes multiple evaluation time nodes; Generate the evaluation sub-model and evaluation time axis of each device point in sequence; Establish a state evaluation model based on all the evaluation sub-models and all the evaluation time axes.

3. The method for monitoring the state of electric power equipment based on multi-source data according to claim 2, characterized in that: When generating the monitoring evaluation value b of the target device point, it includes: Obtain the historical operation data of the target device point; Generate the monitoring evaluation value b of the target device point according to the historical operation data; b=[ b i *k i ]; Among them, θ1 is the number of historical evaluation indicators; β i is the impact factor of the i-th historical evaluation index; k i is the reference value of the i-th historical evaluation index in the target device point.

4. The method for monitoring the state of electric power equipment based on multi-source data according to claim 2, characterized in that: When generating state anomaly values for each device point according to the state evaluation model, it includes: Set a in sequence according to the device point column A i The equipment point to be evaluated; Set the evaluation sub-model of the device point to be evaluated as the primary evaluation model; Obtain the monitoring data packet of the current evaluation time node based on the evaluation time axis of the device point to be evaluated; Generate the state anomaly value f of the device point to be evaluated at the current evaluation time node according to the monitoring data packet and the primary evaluation model; Preset the first anomaly evaluation value threshold F1; If f < F1, generate a primary transmission instruction for the device point to be evaluated at the current evaluation time node, and generate a sub-data packet of the device point to be evaluated according to the primary transmission instruction; If f > F1, generate a secondary transmission instruction for the device point to be evaluated at the current evaluation time node.

5. The method for monitoring the state of electric power equipment based on multi-source data according to claim 4, characterized in that: When generating the state anomaly value f of the current evaluation time node, it includes: f=[ or i *(d i -d' i ) 2 ]; Among them, θ2 is the number of monitoring indicators of the equipment point to be evaluated; η i is the influencing factor of the i-th monitoring indicator of the equipment point to be evaluated; d i is the reference value of the i-th monitoring indicator of the equipment point to be evaluated at the current evaluation time node; d' i is the standard reference value of the i-th monitoring indicator of the equipment point to be evaluated.

6. The method for monitoring the state of electric power equipment based on multi-source data according to claim 5, characterized in that: When setting a diagnosis strategy according to the state anomaly value, it includes: Establish multiple monitoring cycles; Judge whether there is a secondary transmission instruction for each device point within the current monitoring cycle; If it exists, generate a primary sub-strategy; If it does not exist, generate a secondary sub-strategy; The secondary sub-strategy includes: Obtain the feedback data packets of each device point according to the end time node of the current monitoring cycle; Generate the potential risk value of each device point according to all the feedback data packets; Establish a potential risk value series H, H=(h1,h2…h i …h n ), where h i is the potential risk value of the i-th equipment point; n is the number of equipment points; Preset the potential risk value threshold H1; If h i >H1, generate the secondary warning instruction for the i-th equipment point.

7. The method for monitoring the state of electric power equipment based on multi-source data according to claim 6, characterized in that: The primary sub-strategy includes: If the i-th device point has a secondary transmission instruction, set the i-th device point as a risk device point; Obtain the real-time operation parameters of the risk device point; Generate the operation risk value g of the risk device point according to the preset diagnosis model and the real-time operation parameters; Preset the operation risk value threshold G1; If g > G1, generate a primary warning instruction for the risk device point; If g < G1, do not generate a warning instruction.

8. The method for monitoring the state of electric power equipment based on multi-source data according to claim 7, characterized in that: When generating the potential risk value of each device point according to all the feedback data packets, it includes: Set a in sequence according to the device point column A i The device point to be diagnosed; Obtain the feedback data packet of the device point to be diagnosed, and the feedback data packet includes multiple sub-data packets; Establish multiple time intervals within the current monitoring cycle according to the evaluation cycle duration w' of the device point to be diagnosed; Generate abnormal evaluation values in each time interval and establish abnormal evaluation value series F, F=(f'1,f'2…f' i …f' m ), where f' i is the abnormal evaluation value in the i-th time interval; m is the number of time intervals set for the device point to be diagnosed in the current monitoring cycle; h=e1*Q1*[ f' i ]+e2*Q2*[ α i *j i ]; Among them, e1 is the preset third weight coefficient; e2 is the preset fourth weight coefficient; Q1 is the preset third fixed coefficient; Q2 is the preset fourth fixed coefficient; θ3 is the number of risk assessment indicators; α i is the influencing factor of the i-th risk assessment indicator; j i is the reference value of the i-th risk assessment index generated based on the feedback data packet of the device point to be diagnosed; Generate the potential risk value of each device point in sequence.

9. A power equipment status monitoring system based on multi-source data, adopting the power equipment status monitoring method based on multi-source data according to any one of claims 1 to 8, characterized in that: It includes: The central control unit sets multiple equipment points based on power equipment parameters and builds a status assessment model; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are provided at each equipment point, and the monitoring unit is used to generate a state abnormality value of each equipment point according to a state assessment model; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; A second processing module is used to set a diagnosis strategy according to the abnormal state value; The third processing module is used to generate operation risk parameters for each equipment point and determine whether to generate an early warning instruction based on the operation risk parameters.

10. The power equipment status monitoring system based on multi-source data according to claim 9, characterized in that: The central control unit further includes: The fourth processing module is used to set a in sequence according to the device point sequence A. i is the target device point; Generate multiple training data packets based on the historical operating data of the target equipment point; Establish an evaluation sub-model for the target device point based on all training data packets; Obtain historical operation data of target equipment points; Generate monitoring evaluation value b of target equipment point based on historical operation data; b=[ b i *k i ]; Among them, θ1 is the number of historical evaluation indicators; β i is the impact factor of the i-th historical evaluation index; k i is the reference value of the i-th historical evaluation index in the target device point Set the evaluation cycle duration w of the target equipment point according to the monitoring evaluation value; Setting an evaluation timeline for the target device point according to the evaluation cycle length w, wherein the evaluation timeline includes multiple evaluation time nodes; Generate the evaluation sub-model and evaluation timeline for each equipment point in sequence; A status assessment model is established based on all assessment sub-models and the entire assessment timeline.

Images