Power grid equipment health management system and method based on big data

Abstract

The invention discloses a power grid equipment health management system and method based on big data, and relates to the technical field of power grid equipment health management, and the method specifically comprises the steps: 1, determining the range of power grid health management equipment, setting a power grid equipment sensing network, and patrolling the related data of the power grid equipment at regular time; the method comprises the steps of 1, establishing a power grid equipment health state evaluation index, 2, fusing related data of multi-source power grid equipment, and establishing a power grid equipment health state evaluation index, and 3, realizing real-time detection and health management of the power grid equipment health state based on the power grid equipment health state evaluation index. The system combines partial discharge signals and offset constants of vibration data to position fault sources, such as insulation material deterioration and mechanical part abrasion, provides a basis for precise maintenance, dynamically scores the equipment through power grid equipment health state evaluation indexes, divides health levels according to scoring results, and improves the power grid equipment health state evaluation accuracy. And real-time detection of the health state of the power grid equipment is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid equipment health management, and particularly relates to a power grid equipment health management system and method based on big data. Background Art

[0002] With the continuous expansion and complexity of the power grid scale, the safe and stable operation of power grid equipment is crucial for ensuring power supply. During the long-term operation of power grid equipment, it will be affected by various factors, such as environmental factors, electrical load changes, mechanical wear, etc. These factors may lead to a decline in equipment performance, faults, and even safety accidents. Therefore, conducting health management on power grid equipment, real-time monitoring of equipment status, evaluating equipment health status, and taking maintenance measures in a timely manner have become the key to ensuring the safe and stable operation of the power grid. Traditional power grid equipment monitoring and management methods often have problems such as incomplete data collection, single evaluation indicators, and lack of real-time performance, making it difficult to meet the requirements of modern power grids for equipment health management;

[0003] Traditional methods usually only collect partial operation data of equipment, such as voltage, current, etc., and pay less attention to other important data of equipment, such as partial discharge signals, vibration data, static electricity data, and historical work order data, resulting in an incomplete and inaccurate evaluation of equipment status. Traditional evaluation methods often only consider a single parameter of equipment, such as voltage, current, etc., lacking a comprehensive evaluation of the overall health status of equipment and being unable to accurately reflect the actual operation status of equipment;

[0004] Therefore, there is an urgent need for a power grid equipment health management method based on big data to solve the problems of traditional methods in data collection, evaluation, and real-time performance, and provide a more scientific and accurate solution for the health management of power grid equipment. Summary of the Invention

[0005] The purpose of the present invention is to provide a power grid equipment health management system and method based on big data, which is used to solve the technical problems of incomplete and inaccurate evaluation of equipment status and lack of comprehensive evaluation of the overall health status of equipment in the prior art.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0007] A power grid equipment health management method based on big data, comprising:

[0008] Step 1: Determine the scope of power grid health management equipment, set up a power grid equipment sensor network, and regularly inspect relevant data of power grid equipment;

[0009] Step 2: Integrate multi-source relevant data of power grid equipment and establish an evaluation index for the health status of power grid equipment;

[0010] Step 3: Based on the power grid equipment health status evaluation indicators, achieve real-time detection and health management of the power grid equipment health status.

[0011] Furthermore, determine the scope of the power grid health management equipment, set up the power grid equipment sensing network, and regularly inspect the relevant data of the power grid equipment. The specific method is as follows:

[0012] Identify the specific equipment that needs to be managed for power grid health, denoted as the equipment to be managed. Classify the equipment to be managed according to the type of the equipment to be managed, and systematically collect the relevant data of the power grid equipment. The relevant data of the power grid equipment includes the data of each equipment body, the static electricity data of the equipment, and the historical work order data. The collection of the equipment body data covers the real-time data of the power grid equipment, the partial discharge signal, and the vibration sensor data. Among them, the real-time data of the power grid equipment includes the voltage, current, temperature, and vibration data of the power grid equipment. By monitoring the static electricity potential on the working surface of the power grid equipment, extract the static electricity amplitude, rise time, and spectral peak parameters to obtain the equipment static electricity data. The historical work order data includes the model, commissioning date, maintenance records, and life status value of the equipment to be managed.

[0013] Furthermore, the life status value includes:

[0014] The life status value of the equipment to be managed is comprehensively obtained through the DP value, working duration, and average working temperature of the insulation layer of the equipment to be managed. Use the formula to represent the life status value, where t represents time t, DP represents the DP value of the insulation layer of the equipment to be managed, K is the reaction rate constant, reflecting the influence of material characteristics and environmental conditions on the aging rate, R is the gas constant, H(t) represents the temperature of the insulation layer of the equipment to be managed at time t, and E is the temperature sensitivity constant.

[0015] Furthermore, fuse the multi-source relevant data of the power grid equipment and establish the power grid equipment health status evaluation indicators. The specific method is as follows:

[0016] Divide the time period by X duration, extract the features of the relevant data of the power grid equipment in each time period, including obtaining the voltage harmonic distortion rate according to the fundamental wave voltage effective value and the harmonic voltage effective value, determining the current offset degree, determining the stable interval of the partial discharge signal pulse waveform amplitude of different types of power grid equipment, and the stable interval of the vibration acceleration signal amplitude of different types of power grid equipment. Normalize the voltage harmonic distortion rate and the current offset degree, and establish the power grid equipment health status evaluation indicators by combining the equipment static electricity data and the life status value of the power grid equipment in this time period. Use the formula JK(x) = D(x) × [mc(x) + zd(x) + a] × e -[Dy(x)+Dl(x)]×jd(x)Indicates the health status assessment index of power grid equipment. Among them, x represents the xth time period, mc(x) represents the offset constant of the partial discharge signal pulse amplitude of the power grid equipment in the xth time period, zd(x) represents the offset constant of the vibration acceleration signal amplitude of the power grid equipment in the xth time period, a represents the health benchmark constant, Dy(x) represents the voltage harmonic distortion rate of the power grid equipment in the xth time period, Dl(x) represents the current offset degree of the power grid equipment in the xth time period, jd(x) represents the electrostatic influence index of the power grid equipment in the xth time period, and D(x) represents the life status value of the power grid equipment in the xth time period.

[0017] Furthermore, the offset constant of the partial discharge signal pulse amplitude of the power grid equipment includes:

[0018] Using the formula Represents the offset constant of the partial discharge signal pulse amplitude of the power grid equipment. Among them, x represents the xth time period, k1 represents the weight coefficient of the partial discharge signal, mf(x) represents the average value of the partial discharge signal pulse amplitude of the power grid equipment in the xth time period, M represents the stable interval of the partial discharge signal pulse waveform amplitude of the power grid equipment, I[*] represents the conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. Represents the median of the stable interval of the partial discharge signal pulse waveform amplitude of the power grid equipment, and m1 represents the discharge signal benchmark constant.

[0019] Furthermore, the offset constant of the vibration acceleration signal amplitude of the power grid equipment includes:

[0020] Using the formula Represents the offset constant of the vibration acceleration signal amplitude of the power grid equipment. Among them, x represents the xth time period, k2 represents the weight coefficient of the vibration acceleration signal, zf(x) represents the average value of the vibration acceleration signal amplitude of the power grid equipment in the xth time period, F represents the stable interval of the vibration acceleration signal amplitude of the power grid equipment, I[*] represents the conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. Represents the median of the stable interval of the vibration acceleration signal amplitude of the power grid equipment, and m2 represents the vibration acceleration signal benchmark constant.

[0021] Furthermore, the electrostatic influence index includes:

[0022] The electrostatic influence index is represented by the formula jd(x) = k3×[Vp(x) + Fp(x)]÷S(x), where x represents the x-th time period, k3 represents the weight coefficient of the electrostatic influence index, Vp(x) represents the average value of the electrostatic amplitude in the x-th time period, Fp(x) represents the maximum frequency component of the electrostatic signal in the frequency domain in the x-th time period, and S(x) represents the time required for the static electricity to rise from the F1 amplitude to the F2 amplitude.

[0023] Furthermore, based on the power grid equipment health status evaluation index, the real-time detection and health management of the power grid equipment health status are realized. The specific method is as follows:

[0024] The equipment is dynamically scored through the power grid equipment health status evaluation index, and the health level is divided according to the scoring result, and the corresponding maintenance actions are triggered. The equipment with the health status evaluation index greater than or equal to Y1 is recorded as healthy equipment. This type of equipment operates normally, records data according to the regular monitoring frequency, and generates a periodic health report. The equipment with the health status evaluation index greater than or equal to Y2 and less than Y1 is recorded as sub-healthy equipment. This type of equipment has potential risks, optimizes the operation parameters, and increases the inspection frequency of this type of equipment. The equipment with the health status evaluation index greater than or equal to Y3 and less than Y2 is recorded as warning equipment. The performance of this type of equipment has decreased significantly. The system automatically generates a maintenance work order, purchases the required spare parts in advance, and arranges a maintenance plan. The equipment with the health status evaluation index less than Y3 is recorded as high-risk equipment. This type of equipment faces serious failure risks, immediately triggers the shutdown protection program, starts the emergency response for emergency repair, and synchronously notifies the associated equipment to adjust the operation mode.

[0025] The present invention also provides a power grid equipment health management system based on big data, which is applied to the power grid equipment health management method based on big data, including:

[0026] A power grid equipment related data collection module, which is used to determine the scope of power grid health management equipment, set up a power grid equipment sensing network, and regularly inspect the power grid equipment related data;

[0027] A power grid equipment health status evaluation index establishment module, which is used to fuse multi-source power grid equipment related data and establish a power grid equipment health status evaluation index;

[0028] A power grid equipment health status management module, which is used to realize the real-time detection and health management of the power grid equipment health status based on the power grid equipment health status evaluation index.

[0029] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are:

[0030] 1. By comprehensively considering multiple factors such as the DP value, working hours, and average working temperature of the insulation layer of the device to be managed, the present invention calculates the life status value of the device to be managed using a specific formula. This comprehensive evaluation method can more scientifically and accurately reflect the actual aging degree and remaining life of the device, providing a reliable basis for the maintenance and replacement decisions of the device;

[0031] 2. By clearly defining the scope of power grid health management devices and classifying them according to device types, the present invention makes the management more targeted and systematic, which helps to formulate personalized monitoring and management strategies according to the characteristics of different types of devices, systematically collect real-time data covering power grid devices, achieve comprehensive and accurate collection of data related to the health management of power grid devices, and scientific evaluation of the life status of devices, laying a solid foundation for the subsequent health status evaluation and management of power grid devices, and helping to detect potential problems of devices in a timely manner and take maintenance measures in advance;

[0032] 3. By integrating multi-source data related to power grid devices, the present invention breaks the limitations of a single data source, can comprehensively reflect the operating status of power grid devices from multiple dimensions, makes the evaluation results more accurate and reliable, and establishes a power grid device health status evaluation index by combining the static electricity data of the device and the life status value of the power grid device during this period. This index comprehensively considers multiple factors such as the electrical performance, mechanical performance, insulation performance, and aging degree of the device, and can comprehensively and accurately evaluate the health status of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0034] Figure 1 Shows the flowchart of the method for power grid device health management based on big data;

[0035] Figure 2 Shows the flowchart of the method for establishing the power grid device health status evaluation index;

[0036] Figure 3 Shows the block diagram of the power grid device health management system based on big data. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] Embodiment 1. The big data-based power grid equipment health management method as Figure 1 shown specifically includes the following steps:

[0039] Step 1. Determine the scope of power grid health management equipment, set up a power grid equipment sensing network, and regularly inspect relevant data of power grid equipment.

[0040] Identify the specific equipment that needs to be managed for power grid health, denoted as the equipment to be managed. Classify the equipment to be managed according to the type of the equipment to be managed, and systematically collect relevant data of power grid equipment. The relevant data of power grid equipment includes the data of each equipment body, equipment static electricity data, and historical work order data. The collection of equipment body data covers the real-time data of power grid equipment, partial discharge signals, and vibration sensor data. Among them, the real-time data of power grid equipment includes the voltage, current, temperature, and vibration data of power grid equipment. Connect to the SCADA interface of power grid equipment through the Modbus or IEC 61850 protocol and the equipment controller (such as RTU, PLC) to collect the voltage, current, and power parameters of power grid equipment, and deploy intelligent terminal units on power grid equipment to integrate temperature and pressure sensors to achieve embedded monitoring of temperature and pressure. The partial discharge signals of power grid equipment are captured by high-frequency current transformers, and the pulse waveform characteristics are extracted after filtering and noise reduction by a digital signal processor. The vibration sensor data of power grid equipment is obtained by installing vibration sensors on the surface of mechanical components of power grid equipment, collecting vibration acceleration signals, and converting them into spectrograms;

[0041] Install non-contact electrometers on the surface of the insulation layer and the connection of fittings of power grid equipment to monitor the static potential on the working surface of power grid equipment. Add a band-pass filter at the front end of the non-contact electrometer to suppress power frequency interference and extract parameters such as static electricity amplitude, rise time, and spectral peak value to obtain equipment static electricity data;

[0042] Extract the work order information of power grid equipment, record the model, commissioning date, maintenance records, and life status values of each equipment to be managed. Among them, the life status value of the equipment to be managed is comprehensively obtained through the DP value, working hours, and average working temperature of the insulation layer of the equipment to be managed. The specific formula for the life status value is as follows:

[0043]

[0044] Where, t represents the time t, DP represents the DP value of the insulating layer of the device to be managed, K is the reaction rate constant, which reflects the influence of material characteristics and environmental conditions on the aging rate, R is the gas constant, H(t) represents the temperature of the insulating layer of the device to be managed at time t, E is the temperature sensitivity constant. In this embodiment, it is assumed that the device to be managed is in a dry and sealed environment, the value of K is set to 0.15, and the value of E is set to 98.

[0045] Step 2: Integrate relevant data of multi-source power grid devices and establish an evaluation index for the health status of power grid devices.

[0046] Divide the time period by X duration, and extract features from the relevant data of power grid devices in each time period, including separating the fundamental wave and harmonic components from the voltage signal collected in a time period through Fourier transform, obtaining the voltage harmonic distortion rate according to the effective value of the fundamental wave voltage and the effective value of the harmonic voltage, determining the difference between the maximum current and the minimum current in a time period, and then dividing it by the average current in that time period to obtain the current offset degree in that time period, determining the stable interval of the pulse waveform amplitude of the partial discharge signal of different types of power grid devices, and the stable interval of the vibration acceleration signal amplitude of different types of power grid devices. Normalize the voltage harmonic distortion rate and the current offset degree, and establish an evaluation index for the health status of power grid devices by combining the static electricity data of the device and the life status value of the power grid device in that time period. The specific formula of the evaluation index for the health status of power grid devices is as follows:

[0047] JK(x) = D(x) × [mc(x) + zd(x) + a] × e -[Dy(x)+Dl(x)]×jd(x) ;

[0048] Where, x represents the xth time period, mc(x) represents the offset constant of the pulse amplitude of the partial discharge signal of the power grid device in the xth time period, zd(x) represents the offset constant of the vibration acceleration signal amplitude of the power grid device in the xth time period, a represents the health benchmark constant, Dy(x) represents the voltage harmonic distortion rate of the power grid device in the xth time period, Dl(x) represents the current offset degree of the power grid device in the xth time period, jd(x) represents the static electricity influence index of the power grid device in the xth time period, D(x) represents the life status value of the power grid device in the xth time period. In this embodiment, a is set to 1.5.

[0049] Furthermore, the specific calculation formula of the offset constant of the pulse amplitude of the partial discharge signal of the power grid device is as follows:

[0050]

[0051] Among them, x represents the x-th time period, k1 represents the weight coefficient of the partial discharge signal, mf(x) represents the average value of the pulse amplitude of the partial discharge signal of the power grid equipment in the x-th time period, M represents the stable interval of the pulse waveform amplitude of the partial discharge signal of the power grid equipment, I[*] represents a conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. represents the median of the stable interval of the pulse waveform amplitude of the partial discharge signal of the power grid equipment, m1 represents the discharge signal reference constant, and in this embodiment, m1 is set to 1.

[0052] Furthermore, the specific calculation formula of the amplitude offset constant of the vibration acceleration signal of the power grid equipment is as follows:

[0053]

[0054] Among them, x represents the x-th time period, k2 represents the weight coefficient of the vibration acceleration signal, zf(x) represents the average value of the amplitude of the vibration acceleration signal of the power grid equipment in the x-th time period, F represents the stable interval of the amplitude of the vibration acceleration signal of the power grid equipment, I[*] represents a conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. represents the median of the stable interval of the amplitude of the vibration acceleration signal of the power grid equipment, m2 represents the vibration acceleration signal reference constant, and in this embodiment, m2 is set to 0.8.

[0055] Furthermore, the specific calculation formula of the static electricity influence index is as follows:

[0056] jd(x) = k3 × [Vp(x) + Fp(x)] ÷ S(x);

[0057] Among them, x represents the x-th time period, k3 represents the weight coefficient of the static electricity influence index, Vp(x) represents the average value of the static electricity amplitude in the x-th time period, Fp(x) represents the maximum frequency component of the static electricity signal in the frequency domain in the x-th time period, S(x) represents the time required for the static electricity to rise from the F1 amplitude to the F2 amplitude, and in this embodiment, F1 is set to 10% and F2 is set to 90%.

[0058] Step 3: Based on the power grid equipment health status evaluation index, realize the real-time detection and health management of the power grid equipment health status.

[0059] Dynamically score the equipment based on the power grid equipment health status evaluation indicators, divide the health levels according to the scoring results, trigger corresponding maintenance actions, mark the equipment with health status evaluation indicators greater than or equal to Y1 as healthy equipment. Such equipment operates normally, records data according to the regular monitoring frequency and generates periodic health reports. Mark the equipment with health status evaluation indicators greater than or equal to Y2 and less than Y1 as sub-healthy equipment. Such equipment has potential risks and needs to optimize the operating parameters (such as reducing the load or adjusting the cooling system), and increase the inspection frequency of such equipment. Mark the equipment with health status evaluation indicators greater than or equal to Y3 and less than Y2 as warning equipment. The performance of such equipment has significantly declined. The system automatically generates maintenance work orders, purchases the required spare parts in advance (such as insulating bushings or shock pads), and arranges maintenance plans. Mark the equipment with health status evaluation indicators less than Y3 as high-risk equipment. Such equipment faces serious failure risks, immediately triggers the shutdown protection program, starts the emergency response for rush repair, and simultaneously notifies the associated equipment to adjust the operating mode.

[0060] When determining the abnormal state, the system combines the partial discharge signal and the offset constant of the vibration data to locate the root cause of the fault. For example: If the amplitude of the partial discharge signal exceeds the stable interval, it indicates that the insulating material may be deteriorated, and it is necessary to check the sleeve sealing or winding connection status first. If the amplitude of the vibration signal fluctuates abnormally, it indicates mechanical component wear (such as breaker spring fatigue or transformer core looseness), and targeted disassembly and inspection are required.

[0061] Example 2. As Figure 2 shown in the big data-based power grid equipment health management system, specifically includes the following:

[0062] Power grid equipment-related data collection module, clarify the specific equipment that needs to be managed for power grid health, denoted as equipment to be managed, classify the equipment to be managed according to the type of equipment to be managed, and systematically collect power grid equipment-related data. The power grid equipment-related data includes each equipment body data, equipment static electricity data and historical work order data. The collection of equipment body data covers power grid equipment real-time data, partial discharge signals and vibration sensor data. Among them, the power grid equipment real-time data includes the voltage, current, temperature and vibration data of the power grid equipment. Connect to the SCADA interface of the power grid equipment through the Modbus or IEC 61850 protocol with the equipment controller (such as RTU, PLC) to collect the voltage, current and power parameters of the power grid equipment, and deploy intelligent terminal units on the power grid equipment to integrate temperature and pressure sensors to achieve embedded monitoring of temperature and pressure. The partial discharge signal of the power grid equipment is captured by a high-frequency current transformer, and the pulse waveform characteristics are extracted after filtering and noise reduction by a digital signal processor. The vibration sensor data of the power grid equipment is obtained by installing the vibration sensor on the surface of the mechanical components of the power grid equipment, collecting the vibration acceleration signal and converting it into a spectrogram;

[0063] Install a non-contact electrometer on the surface of the insulation layer of the power grid equipment and at the connection of the metal fittings to monitor the static potential of the working surface of the power grid equipment. Add a band-pass filter at the front end of the non-contact electrometer to suppress power frequency interference and extract parameters such as static amplitude, rise time, and spectral peak value to obtain the static data of the equipment;

[0064] Extract the work order information of the power grid equipment, record the model, commissioning date, maintenance records, and life status values of each equipment to be managed. The life status value of the equipment to be managed is obtained by comprehensively considering the DP value of the insulation layer of the equipment to be managed, the working duration, and the average working temperature. The specific formula for the life status value is as follows:

[0065]

[0066] Among them, t represents time t, DP represents the DP value of the insulation layer of the equipment to be managed, K is the reaction rate constant, reflecting the influence of material characteristics and environmental conditions on the aging rate, R is the gas constant, H(t) represents the temperature of the insulation layer of the equipment to be managed at time t, E is the temperature sensitivity constant. In this embodiment, it is assumed that the equipment to be managed is in a dry and airtight environment, the K value is set to 0.15, and the E value is set to 98;

[0067] The power grid equipment health status evaluation index establishment module divides time periods by X duration, extracts features from the power grid equipment-related data in each time period, including separating the fundamental wave and harmonic components from the voltage signal collected in a time period through Fourier transform, obtaining the voltage harmonic distortion rate according to the effective value of the fundamental wave voltage and the effective value of the harmonic voltage, determining the current offset degree in a time period by dividing the difference between the maximum current and the minimum current in a time period by the average current in that time period, determining the steady-state interval of the pulse waveform amplitude of the partial discharge signal of different types of power grid equipment, and the steady-state interval of the vibration acceleration signal amplitude of different types of power grid equipment. Normalize the voltage harmonic distortion rate and the current offset degree, and establish a power grid equipment health status evaluation index by combining the equipment static data and the life status value of the power grid equipment in this time period. The specific formula for the power grid equipment health status evaluation index is as follows:

[0068] JK(x) = D(x) × [mc(x) + zd(x) + a] × e - Dy(x)+Dl(x) ×jd(x) ;

[0069] ​​Among them, x represents the x-th time period, mc(x) represents the offset constant of the partial discharge signal pulse amplitude of the power grid equipment in the x-th time period, zd(x) represents the offset constant of the vibration acceleration signal amplitude of the power grid equipment in the x-th time period, a represents the healthy reference constant, Dy(x) represents the voltage harmonic distortion rate of the power grid equipment in the x-th time period, Dl(x) represents the current offset degree of the power grid equipment in the x-th time period, jd(x) represents the electrostatic influence index of the power grid equipment in the x-th time period, D(x) represents the life state value of the power grid equipment in the x-th time period, and in this embodiment, a is set to be equal to 1.5.

[0070] Furthermore, the specific calculation formula for the offset constant of the partial discharge signal pulse amplitude of the power grid equipment is as follows:

[0071]

[0072] Among them, x represents the x-th time period, k1 represents the weight coefficient of the partial discharge signal, mf(x) represents the average value of the partial discharge signal pulse amplitude of the power grid equipment in the x-th time period, M represents the stable interval of the partial discharge signal pulse waveform amplitude of the power grid equipment, I[*] represents the conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. represents the median of the stable interval of the partial discharge signal pulse waveform amplitude of the power grid equipment, and m1 represents the discharge signal reference constant. In this embodiment, m1 is set to be equal to 1.

[0073] Furthermore, the specific calculation formula for the offset constant of the vibration acceleration signal amplitude of the power grid equipment is as follows:

[0074]

[0075] Among them, x represents the x-th time period, k2 represents the weight coefficient of the vibration acceleration signal, zf(x) represents the average value of the vibration acceleration signal amplitude of the power grid equipment in the x-th time period, F represents the stable interval of the vibration acceleration signal amplitude of the power grid equipment, I[*] represents the conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. represents the median of the stable interval of the vibration acceleration signal amplitude of the power grid equipment, and m2 represents the vibration acceleration signal reference constant. In this embodiment, m2 is set to be equal to 0.8.

[0076] Furthermore, the specific calculation formula for the electrostatic influence index is as follows:

[0077] jd(x) = k3 × [Vp(x) + Fp(x)] ÷ S(x);

[0078] Among them, x represents the x-th time period, k3 represents the weight coefficient of the static electricity influence index, Vp(x) represents the average value of the static electricity amplitude in the x-th time period, Fp(x) represents the maximum frequency component of the static electricity signal in the frequency domain, and S(x) represents the time required for the static electricity to rise from the F1 amplitude to the F2 amplitude. In this embodiment, F1 is set to 10% and F2 is set to 90%.

[0079] The power grid equipment health status management module dynamically scores the equipment through the power grid equipment health status evaluation index, divides the health level according to the scoring result, triggers corresponding maintenance actions, records the equipment with the health status evaluation index greater than or equal to Y1 as healthy equipment. This type of equipment operates normally, records data according to the regular monitoring frequency, and generates a periodic health report. Records the equipment with the health status evaluation index greater than or equal to Y2 and less than Y1 as sub-healthy equipment. This type of equipment has potential risks and needs to optimize the operating parameters (such as reducing the load or adjusting the cooling system), and increase the inspection frequency of this type of equipment. Records the equipment with the health status evaluation index greater than or equal to Y3 and less than Y2 as warning equipment. The performance of this type of equipment has significantly declined. The system automatically generates a maintenance work order, purchases the required spare parts in advance (such as insulating bushings or shock pads), and arranges a maintenance plan. Records the equipment with the health status evaluation index less than Y3 as high-risk equipment. This type of equipment faces a serious fault risk, immediately triggers the shutdown protection program, starts the emergency response for repair, and simultaneously notifies the associated equipment to adjust the operating mode.

[0080] When determining the abnormal state, the system locates the root cause of the fault by combining the offset constants of the partial discharge signal and the vibration data. For example: if the amplitude of the partial discharge signal exceeds the stable interval, it indicates that the insulating material may be deteriorated, and it is necessary to give priority to checking the sleeve seal or the winding connection state. If the amplitude of the vibration signal fluctuates abnormally, it indicates mechanical component wear (such as breaker spring fatigue or transformer core looseness), and targeted disassembly and inspection are required.

[0081] As mentioned above, it is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

[0082] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not elaborate on all the details, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A method for health management of power grid equipment based on big data, characterized in that Including: Step 1: Determine the scope of power grid health management equipment, set up a sensing network for power grid equipment, and regularly inspect relevant data of power grid equipment; Step 2: Integrate multi-source relevant data of power grid equipment and establish an evaluation index for the health status of power grid equipment; Step 3: Based on the evaluation index for the health status of power grid equipment, realize real-time detection and health management of the health status of power grid equipment.

2. The method for health management of power grid equipment based on big data according to claim 1, wherein Determine the scope of power grid health management equipment, set up a sensing network for power grid equipment, and regularly inspect relevant data of power grid equipment. The specific method is as follows: Identify the specific equipment that needs to be managed for power grid health, denoted as the equipment to be managed. Classify the equipment to be managed according to the type of the equipment to be managed, and systematically collect relevant data of power grid equipment. The relevant data of power grid equipment includes the data of each equipment body, equipment static electricity data, and historical work order data. The collection of equipment body data covers the real-time data of power grid equipment, partial discharge signals, and vibration sensor data. Among them, the real-time data of power grid equipment includes the voltage, current, temperature, and vibration data of power grid equipment. By monitoring the static potential on the working surface of power grid equipment, extract the static electricity amplitude, rise time, and spectral peak parameters to obtain equipment static electricity data. The historical work order data includes the model, commissioning date, maintenance records, and life status value of the equipment to be managed.

3. The method for health management of power grid equipment based on big data according to claim 2, wherein The life status value includes: The life state value of the device to be managed is obtained by comprehensively considering the DP value of the insulating layer of the device to be managed, the working duration, and the average working temperature, using the formula represents the life state value, where t represents time t, DP represents the DP value of the insulating layer of the device to be managed, K is the reaction rate constant, reflecting the influence of material characteristics and environmental conditions on the aging rate, R is the gas constant, H(t) represents the temperature of the insulating layer of the device to be managed at time t, and E is the temperature sensitivity constant.

4. The method for health management of power grid equipment based on big data according to claim 1, wherein Integrate multi-source relevant data of power grid equipment and establish an evaluation index for the health status of power grid equipment. The specific method is as follows: Divide the time period by X duration, and extract the features of the power grid equipment - related data in each time period, including obtaining the voltage harmonic distortion rate based on the effective value of fundamental wave voltage and the effective value of harmonic voltage, determining the degree of current deviation, determining the steady - state interval of the pulse waveform amplitude of the partial discharge signal of different types of power grid equipment, and the steady - state interval of the vibration acceleration signal amplitude of different types of power grid equipment. Normalize the voltage harmonic distortion rate and the current deviation degree, and establish an evaluation index for the health status of power grid equipment by combining the equipment static electricity data and the life status value of the power grid equipment in this time period. Use the formula JK(x) = D(x)×[mc(x)+zd(x)+a]×e -[Dy(x)+Dl(x)]×jd(x) represents the evaluation index for the health status of power grid equipment, where x represents the x - th time period, mc(x) represents the offset constant of the pulse amplitude of the partial discharge signal of the power grid equipment in the x - th time period, zd(x) represents the offset constant of the vibration acceleration signal amplitude of the power grid equipment in the x - th time period, a represents the health benchmark constant, Dy(x) represents the voltage harmonic distortion rate of the power grid equipment in the x - th time period, Dl(x) represents the current deviation degree of the power grid equipment in the x - th time period, jd(x) represents the static electricity influence index of the power grid equipment in the x - th time period, and D(x) represents the life status value of the power grid equipment in the x - th time period.

5. The method for health management of power grid equipment based on big data according to claim 4, wherein, The offset constant of the pulse amplitude of the partial discharge signal of power grid equipment includes: Using the formula represents the pulse amplitude offset constant of the partial discharge signal of the power grid equipment, where x represents the x-th time period, k1 represents the weight coefficient of the partial discharge signal, mf(x) represents the average value of the pulse amplitude of the partial discharge signal of the power grid equipment in the x-th time period, M represents the steady interval of the pulse waveform amplitude of the partial discharge signal of the power grid equipment, I[*] represents the conditional function, which is equal to 1 when the condition * is satisfied and equal to 0 when the condition * is not satisfied. represents the median of the steady interval of the pulse waveform amplitude of the partial discharge signal of the power grid equipment, and m1 represents the discharge signal reference constant.

6. The method for health management of power grid equipment based on big data according to claim 4, wherein, The offset constant of the amplitude of the vibration acceleration signal of power grid equipment includes: Using the formula represents the amplitude offset constant of the vibration acceleration signal of the power grid equipment, where x represents the x-th time period, k2 represents the weight coefficient of the vibration acceleration signal, zf(x) represents the average value of the amplitude of the vibration acceleration signal of the power grid equipment in the x-th time period, F represents the stationary interval of the amplitude of the vibration acceleration signal of the power grid equipment, I[*] represents the conditional function, I[*] equals 1 when the condition * is satisfied, and I[*] equals 0 when the condition * is not satisfied. represents the median of the stationary interval of the amplitude of the vibration acceleration signal of the power grid equipment, and m2 represents the reference constant of the vibration acceleration signal.

7. The method for health management of power grid equipment based on big data according to claim 4, characterized in that The static electricity influence index includes: Use the formula jd(x) = k3×[Vp(x)+Fp(x)]÷S(x) to represent the static electricity influence index, where x represents the xth time period, k3 represents the weight coefficient of the static electricity influence index, Vp(x) represents the average value of the static electricity amplitude in the xth time period, Fp(x) represents the maximum frequency component of the static electricity signal in the frequency domain in the xth time period, and S(x) represents the time required for the static electricity to rise from the F1 amplitude to the F2 amplitude.

8. The method for health management of power grid equipment based on big data according to claim 1, characterized in that Based on the evaluation index for the health status of power grid equipment, realize real-time detection and health management of the health status of power grid equipment. The specific method is as follows: Dynamically score the equipment through the evaluation index for the health status of power grid equipment, divide the health level according to the scoring result, and trigger corresponding maintenance actions. Record the equipment with the health status evaluation index greater than or equal to Y1 as healthy equipment. This type of equipment operates normally, records data according to the regular monitoring frequency, and generates a periodic health report. Record the equipment with the health status evaluation index greater than or equal to Y2 and less than Y1 as sub-healthy equipment. This type of equipment has potential risks, optimize the operation parameters, and increase the inspection frequency of this type of equipment. Record the equipment with the health status evaluation index greater than or equal to Y3 and less than Y2 as warning equipment. The performance of this type of equipment has decreased significantly. The system automatically generates a maintenance work order, purchases the required spare parts in advance, and arranges a maintenance plan. Record the equipment with the health status evaluation index less than Y3 as high-risk equipment. This type of equipment faces serious failure risks, immediately trigger the shutdown protection program, start the emergency response for repair, and synchronously notify the associated equipment to adjust the operation mode.

9. A power grid equipment health management system based on big data, which is applied to the power grid equipment health management method based on big data according to any one of claims 1-8, is characterized in that, Including: The power grid equipment related data collection module is used to determine the scope of power grid health management equipment, set up the power grid equipment sensing network, and regularly inspect the power grid equipment related data; The power grid equipment health status evaluation index establishment module is used to integrate multi-source power grid equipment related data and establish power grid equipment health status evaluation indexes; The power grid equipment health status management module is used to realize the real-time detection and health management of the power grid equipment health status based on the power grid equipment health status evaluation indexes.

Images