Power equipment state monitoring method based on wireless sensor network

Abstract

The invention discloses a power equipment state monitoring method based on a wireless sensor network, particularly relates to the field of power equipment monitoring, and comprises sensor network planning, multimode sensor deployment, multi-protocol wireless transmission, data preprocessing, model performance evaluation and state evaluation. According to the invention, through accurate sensor network planning and multimode sensor deployment, comprehensive and real-time monitoring of the state of the power equipment is realized; secondly, the multi-protocol wireless transmission technology optimizes the data transmission efficiency and energy consumption, and improves the reliability and stability of data transmission; data preprocessing and model performance evaluation provide high-quality data basis and scientific basis for subsequent state evaluation; and finally, the state evaluation result is visual and accurate, the abnormal state of the power equipment can be early warned in time, powerful decision support is provided for operation and maintenance personnel, the accuracy and reliability of state monitoring of the power equipment are remarkably improved, and safe and stable operation of a power grid is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and more specifically, to a method for monitoring the state of power equipment based on a wireless sensor network. Background Art

[0002] With the increasing complexity of power systems and the increasing demand for intelligence, it is particularly important to monitor and accurately evaluate the operating status of power equipment in real time. Power equipment status monitoring technology can collect and analyze various parameters during the operation of equipment, so as to detect abnormal conditions of equipment in time and provide strong support for equipment maintenance and management.

[0003] The power equipment status monitoring method in the prior art usually includes two major links: data collection and data analysis. In the data collection stage, various sensors arranged around the power equipment, such as temperature sensors, vibration sensors, current and voltage sensors, etc., are used to collect the equipment's operating data in real time. These data include but are not limited to key parameters such as the equipment's temperature, vibration frequency, current and voltage fluctuations. The collected data are transmitted to the data processing center via wired or wireless means for subsequent analysis and processing. In the data analysis stage, various mathematical models and algorithms are used to process and analyze the collected data to extract characteristic information that can reflect the equipment's operating status, such as the equipment's health status, fault warnings, etc.

[0004] However, the existing technology still has some shortcomings in data collection and data analysis. In terms of data collection, due to the wide distribution of power equipment and the complex environment, the layout of sensors and the transmission of data are subject to many restrictions, such as electromagnetic interference, signal attenuation and other problems, which may lead to errors or omissions in the collected data. In terms of data analysis, although a variety of mathematical models and algorithms have been applied to power equipment status monitoring, these models and algorithms are often targeted at specific equipment or specific fault types, lacking versatility and accuracy. In addition, the existing technology for data analysis and processing mostly remains at the surface level, and it is difficult to deeply explore the potential laws and trends behind the data, thus affecting the accuracy and reliability of equipment status monitoring. Summary of the invention

[0005] In order to overcome the above defects of the prior art, an embodiment of the present invention provides a method for monitoring the state of electric power equipment based on a wireless sensor network, and solves the problems raised in the above background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for monitoring the state of power equipment based on a wireless sensor network, comprising:

[0007] Step 1: Sensor network planning: Determine the sensor layout and communication quality through electromagnetic field simulation analysis and wireless signal coverage test, and transmit to step 2;

[0008] Step 2: Multi-mode sensor deployment: used to deploy sensors according to the sensor layout position transmitted in step 2, to collect power transformer monitoring data, gas insulated switchgear monitoring data, high-voltage transmission line monitoring data and substation secondary equipment monitoring data, and transmit them to the local data aggregation node through step 3;

[0009] Step 3: Multi-protocol wireless transmission: used to determine the wireless communication protocol according to the distance between the deployment location of the sensor in step 2 and the local data aggregation node;

[0010] Step 4: Data preprocessing: used to perform wavelet denoising and data processing on the data transmitted in step 3, and transmit it to step 5;

[0011] Step 5: Model performance evaluation: used to establish a mathematical model to evaluate the performance of the data preprocessed in step 4, and transmit the calculation results to step 6;

[0012] Step 6: Status evaluation: used to calculate the abnormality index based on the evaluation value transmitted in step 5, and judge the abnormal status of the power equipment according to the set threshold value.

[0013] Preferably, the electromagnetic field simulation analysis uses COMSOL Multiphysics to perform electromagnetic field simulation to simulate the electromagnetic environment around the power equipment and determine the location with the least interference and the strongest signal.

[0014] Preferably, the wireless signal coverage test is conducted by using RF testing equipment to conduct field tests, draw a signal strength heat map, and determine signal blind spots and locations with optimal communication quality.

[0015] Preferably, the power transformer monitoring data includes partial discharge pulse spectrum distribution, winding deformation index, furfural concentration in oil and core magnetic flux density harmonic content, which are marked as Tp, Tw, Tf and Tc respectively; the gas insulated switchgear monitoring data includes partial discharge high-frequency signal amplitude, SF6 gas micro-water content, circuit breaker action speed curve and metal particle contamination degree, which are marked as Su, Sg, Sc and Sm respectively; the high-voltage transmission line monitoring data includes conductor surface electric field intensity distribution, tower foundation vibration spectrum, insulator string equivalent salt density adhesion density and corona discharge power loss, which are marked as Lc, Lt, Le and Ld respectively; the substation secondary equipment monitoring data includes protection device IEC61850 communication delay, merging unit synchronization accuracy, clock source phase noise and optical fiber channel bit error rate, which are marked as Cd, Cm, Cs and Cf respectively.

[0016] Preferably, the partial discharge pulse spectrum distribution is obtained by using a partial discharge detector to collect signals through a transformer bushing tap or a UHF sensor, and performing fast Fourier transform to obtain a spectrum. The winding deformation index is obtained by using a swept frequency response analyzer to perform a frequency scan on the transformer winding, and comparing the deviation of the obtained transfer function with a reference curve. The furfural concentration in the oil is analyzed by a chromatography-mass spectrometry to analyze transformer oil samples and quantitatively detect the concentration of derivatives such as 2-furfural. The harmonic content of the core magnetic flux density is measured by using a Hall effect sensor to measure the surface magnetic field of the core, and the harmonic content is calculated by a harmonic analyzer.

[0017] Preferably, the amplitude of the partial discharge high-frequency signal is measured by using a built-in UHF sensor and a dedicated digital oscilloscope to capture and measure the UHF electromagnetic wave signal in the GIS cavity. The micro-water content of SF6 gas is measured online by using a mirror condensation dew point meter or a capacitive humidity sensor. The circuit breaker action speed curve is recorded by using a high-speed digital displacement sensor to record the movement trajectory of the circuit breaker contacts, and the speed-time curve is drawn by a data acquisition system. The metal particle contamination degree is analyzed by using an optical particle counter or laser scattering technology to analyze the number of suspended metal particles in the GIS air chamber.

[0018] Preferably, the electric field intensity distribution on the conductor surface is measured by scanning along the conductor using an electric field meter, or calculated by electrostatic field numerical simulation software; the vibration spectrum of the tower foundation is measured by installing a three-axis acceleration sensor on the tower foundation and analyzing the frequency characteristics of the vibration signal by fast Fourier transform; the equivalent salt density adhesion density of the insulator string is calculated by using a portable insulator contamination tester and measuring the equivalent salt density through conductivity; the corona discharge power loss is calculated by locating the corona discharge point using ultrasonic or ultraviolet imaging equipment, and the power loss is calculated by special software in combination with line parameters and environmental factors.

[0019] Preferably, the IEC61850 communication delay of the protection device is measured by using a network analyzer and a dedicated time synchronization test device to measure the end-to-end transmission time of the GOOSE message, the synchronization accuracy of the merging unit is measured by using a high-precision clock comparator to measure the deviation between the sampling value message timestamp output by the merging unit and the system reference clock, the clock source phase noise is measured by using a phase noise analyzer to measure the short-term stability of the clock signal in the frequency domain, and the fiber channel bit error rate is measured by using an optical time domain reflectometer and a bit error rate tester to insert a known bit sequence in the fiber optic communication system and count the number of error bits at the receiving end.

[0020] Preferably, step 2 uses a time sliding window to determine the data collection time of the power equipment, which is marked as 1, 2...n in sequence, and the ratio of the window size to the sliding step is 6:1. The specific time is determined according to actual conditions.

[0021] Preferably, in step 3, when the distance between the sensor and the local data aggregation node is a near-field distance, ZigBee (IEEE 802.15.4 standard) or Bluetooth 5.0LE technology is used for low-power transmission; when the distance between the sensor and the local data aggregation node is a medium distance, LoRaWAN technology or enterprise-level Wi-Fi (IEEE 802.11ax) is used for transmission; when the distance between the sensor and the local data aggregation node is a long distance, a private LTE network is deployed or a public 5G network is used for transmission, and dynamic routing and load balancing between different protocols are realized through an SDN controller.

[0022] Preferably, the step 4 applies discrete wavelet transform to perform signal denoising, and uses the pandas library to perform data cleaning, interpolation and outlier processing.

[0023] Preferably, step 5 includes a power transformer monitoring data analysis model, a gas insulated switchgear monitoring data analysis model, a high-voltage transmission line monitoring data analysis model and a substation secondary equipment monitoring data analysis model.

[0024] Preferably, the power transformer monitoring data analysis model is used to analyze the power transformer monitoring data, which is specifically expressed as follows: ET i represents the transformer evaluation value of the i-th time window, Tp i represents the partial discharge pulse spectrum distribution in the i-th time window, Tw i represents the winding deformation index of the i-th time window, Tf i represents the furfural concentration in the oil in the i-th time window, Tc i Indicates the harmonic content of the core flux density in the i-th time window, Tf crit Indicates the critical value of furfural concentration in oil.

[0025] Preferably, the gas insulated switchgear monitoring data analysis model is used to analyze the gas insulated switchgear monitoring data, which is specifically expressed as: ES i represents the switchgear evaluation value in the i-th time window, Su i represents the amplitude of the partial discharge high-frequency signal in the i-th time window, Sg i Indicates the water content of SF6 gas in the i-th time window, Sc i Represents the circuit breaker action speed curve of the i-th time window, Sm i represents the metal particle contamination degree in the i-th time window, Su thr Indicates the partial discharge signal amplitude threshold, Sg max Indicates the maximum allowable trace water content of SF6 gas, t opeIndicates the circuit breaker operation time, Sc ref represents the reference circuit breaker speed curve, v max Indicates the maximum allowable speed deviation, Sm crit Indicates critical metal particle contamination level.

[0026] Preferably, the high-voltage transmission line monitoring data analysis model is used to analyze the high-voltage transmission line monitoring data, which is specifically expressed as: EL i represents the transmission line evaluation value of the i-th time window, Lc i represents the electric field intensity distribution on the conductor surface in the i-th time window, Lt i represents the tower foundation vibration spectrum of the i-th time window, Le i represents the equivalent salt density of the insulator string in the i-th time window, Ld i represents the corona discharge power loss in the i-th time window, Lc crit represents the critical conductor surface electric field strength, Lt ref represents the reference vibration spectrum, Le thr Indicates the equivalent salt density attachment density threshold, Ld rat Indicates the rated corona discharge power loss, Ld max Indicates the maximum allowable corona discharge power loss.

[0027] Preferably, the substation secondary equipment monitoring data analysis model is used to analyze the substation secondary equipment monitoring data, which is specifically expressed as: EC i represents the evaluation value of the substation secondary equipment in the i-th time window, Cd i represents the IEC61850 communication delay of the protection device in the i-th time window, Cm i represents the synchronization accuracy of the merging unit in the i-th time window, Cs i represents the clock source phase noise of the ith time window, Cf i represents the fiber channel bit error rate in the i-th time window, Cd max Indicates the maximum permissible communication delay, Cm max Indicates the maximum allowable synchronization accuracy error, Cs ref represents the reference phase noise level, Cf max Indicates the maximum allowable bit error rate.

[0028] Preferably, the specific steps of step 6 include:

[0029] A1: Weight allocation: Assign weights W1, W2, W3 and W4 to each evaluation value, and W1+W2+W3+W4=1;

[0030] A2: Weighted average: Weighted average S = w1 × ET i +w2×ES i +w3×EL i +w4×EC i ;

[0031] A3: Nonlinear mapping: Use nonlinear function for mapping: f(S) = 1-exp(-k×S), where k is an adjustable parameter;

[0032] A4: Time factor: introduce the time decay factor T = exp(-λ×t0), t0 represents the time since the last maintenance, λ is the decay rate;

[0033] A5: Final abnormality index: AI = f(S) × T;

[0034] A6: Abnormal judgment: Set a threshold θ. When AI>θ, it is judged as an abnormal state.

[0035] Technical effects and advantages of the present invention:

[0036] The present invention can accurately determine the layout position and communication quality of sensors through electromagnetic field simulation analysis and wireless signal coverage test of sensor network planning, ensure the effectiveness and reliability of the sensor network, reduce the problem of inaccurate or lost monitoring data due to improper sensor location or poor communication quality, and improve the overall performance of the monitoring system; through multi-mode sensor deployment, it can comprehensively collect monitoring data of power transformers, gas-insulated switchgear, high-voltage transmission lines and substation secondary equipment, provide a rich data source for subsequent data analysis and status evaluation, and the sensor deployment is flexible and can be expanded or adjusted according to actual needs, thereby improving the adaptability and flexibility of the monitoring system; through multi-protocol wireless transmission, the wireless communication protocol is determined according to the distance between the sensor and the local data aggregation node, which can optimize the transmission efficiency and energy consumption, improve the reliability and stability of data transmission, support multiple communication protocols, and can adapt to the data transmission needs in different scenarios, increasing It strengthens the versatility and compatibility of the monitoring system; through data preprocessing, wavelet denoising and data processing, it can effectively remove noise and outliers in the monitoring data, improve the accuracy and reliability of the data, and provide a high-quality data basis for subsequent data analysis and status evaluation, which helps to improve the overall performance of the monitoring system; through model performance evaluation, a mathematical model is established to evaluate the performance of the preprocessed data, which can accurately reflect the operating status and performance changes of the power equipment. Through model evaluation, potential failures and abnormal conditions of the power equipment can be discovered in time, providing a scientific basis for subsequent maintenance and management; through status evaluation, the abnormal index is calculated according to the evaluation value, and the abnormal state of the power equipment is judged according to the set threshold, which can realize real-time monitoring and early warning of the power equipment status. The status evaluation results are intuitive and accurate, which helps operation and maintenance personnel to take timely measures to deal with abnormal situations and ensure the normal operation of the power equipment and the safety and stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] refer to Figure 1 A method for monitoring the state of power equipment based on a wireless sensor network is shown, and the specific steps include:

[0040] Step 1: Sensor network planning: Determine the sensor layout and communication quality through electromagnetic field simulation analysis and wireless signal coverage test, and transmit to step 2.

[0041] The electromagnetic field simulation analysis uses COMSOL Multiphysics to perform electromagnetic field simulation, simulate the electromagnetic environment around the power equipment, and determine the location with the least interference and the strongest signal.

[0042] The wireless signal coverage test uses RF testing equipment to conduct field tests, draw a signal strength heat map, and determine signal blind spots and locations with optimal communication quality.

[0043] Step 2: Multi-mode sensor deployment: Used to deploy sensors according to the sensor layout position transmitted in step 2, to collect power transformer monitoring data, gas insulated switchgear monitoring data, high-voltage transmission line monitoring data and substation secondary equipment monitoring data, and transmit them to the local data aggregation node through step 3.

[0044] The power transformer monitoring data includes partial discharge pulse spectrum distribution, winding deformation index, furfural concentration in oil and core magnetic flux density harmonic content, which are marked as Tp, Tw, Tf and Tc respectively; the gas insulated switchgear monitoring data includes partial discharge high-frequency signal amplitude, SF6 gas micro-water content, circuit breaker action speed curve and metal particle contamination, which are marked as Su, Sg, Sc and Sm respectively; the high-voltage transmission line monitoring data includes conductor surface electric field intensity distribution, tower foundation vibration spectrum, insulator string equivalent salt density adhesion density and corona discharge power loss, which are marked as Lc, Lt, Le and Ld respectively; the substation secondary equipment monitoring data includes protection device IEC61850 communication delay, merging unit synchronization accuracy, clock source phase noise and optical fiber channel bit error rate, which are marked as Cd, Cm, Cs and Cf respectively.

[0045] The partial discharge pulse spectrum distribution is obtained by using a partial discharge detector to collect signals through a transformer bushing tap or a UHF sensor, and performing fast Fourier transform to obtain a spectrum. The winding deformation index is obtained by using a swept frequency response analyzer to perform a frequency scan on the transformer winding, and the deviation of the obtained transfer function is compared with that of a reference curve. The furfural concentration in the oil is analyzed by a chromatography-mass spectrometry to analyze transformer oil samples and quantitatively detect the concentration of derivatives such as 2-furfural. The harmonic content of the core magnetic flux density is measured by using a Hall effect sensor to measure the surface magnetic field of the core, and the harmonic content is calculated by a harmonic analyzer.

[0046] The amplitude of the partial discharge high-frequency signal is measured by using a built-in UHF sensor and a dedicated digital oscilloscope to capture and measure the UHF electromagnetic wave signal in the GIS cavity. The micro-water content of SF6 gas is measured online by using a mirror condensation dew point meter or a capacitive humidity sensor. The circuit breaker action speed curve is recorded by using a high-speed digital displacement sensor to record the movement trajectory of the circuit breaker contacts, and the speed-time curve is drawn through a data acquisition system. The metal particle contamination degree is analyzed by using an optical particle counter or laser scattering technology to analyze the number of suspended metal particles in the GIS gas chamber.

[0047] The electric field intensity distribution on the conductor surface is measured by scanning along the conductor using an electric field meter, or calculated using electrostatic field numerical simulation software. The vibration spectrum of the tower foundation is measured by installing a three-axis acceleration sensor on the tower foundation and analyzing the frequency characteristics of the vibration signal through fast Fourier transform. The equivalent salt density attachment density of the insulator string is calculated by using a portable insulator contamination tester and measuring the equivalent salt density through conductivity. The corona discharge power loss is calculated by locating the corona discharge point using ultrasonic or ultraviolet imaging equipment, and the power loss is calculated using special software in combination with line parameters and environmental factors.

[0048] The protection device IEC61850 communication delay is measured by using a network analyzer and a dedicated time synchronization test device to measure the end-to-end transmission time of the GOOSE message. The merging unit synchronization accuracy is measured by using a high-precision clock comparator to measure the deviation between the sampling value message timestamp output by the merging unit and the system reference clock. The clock source phase noise is measured by using a phase noise analyzer to measure the short-term stability of the clock signal in the frequency domain. The fiber channel bit error rate is measured by using an optical time domain reflectometer and a bit error rate tester to insert a known bit sequence in the fiber optic communication system and count the number of error bits at the receiving end.

[0049] The step 2 uses a time sliding window to determine the data collection time of the power equipment, which is marked as 1, 2...n in sequence. The ratio of the window size to the sliding step is 6:1, and the specific time is determined according to the actual situation.

[0050] It should be specifically explained in this embodiment that the first time window represents the initial state of the power equipment and does not participate in the actual analysis.

[0051] Step 3: Multi-protocol wireless transmission: used to determine the wireless communication protocol according to the distance between the deployment location of the sensor in step 2 and the local data aggregation node.

[0052] In step 3, when the distance between the sensor and the local data aggregation node is near field, ZigBee (IEEE 802.15.4 standard) or Bluetooth 5.0LE technology is used for low-power transmission; when the distance between the sensor and the local data aggregation node is medium distance, LoRaWAN technology or enterprise-level Wi-Fi (IEEE 802.11ax) is used for transmission; when the distance between the sensor and the local data aggregation node is long distance, a private LTE network is deployed or a public 5G network is used for transmission, and dynamic routing and load balancing between different protocols are realized through the SDN controller.

[0053] It should be specifically explained in this embodiment that the division of the near-field distance, the middle distance and the long distance in step 3 is determined according to actual conditions, and this embodiment does not make any specific limitation.

[0054] Step 4: Data preprocessing: used to perform wavelet denoising and data processing on the data transmitted in step 3, and transmit it to step 5.

[0055] In step 4, discrete wavelet transform is used to perform signal denoising, and the pandas library is used to perform data cleaning, interpolation, and outlier processing.

[0056] Step 5: Model performance evaluation: used to establish a mathematical model to evaluate the performance of the data preprocessed in step 4, and transmit the calculation results to step 6.

[0057] The step 5 includes a power transformer monitoring data analysis model, a gas insulated switchgear monitoring data analysis model, a high-voltage transmission line monitoring data analysis model and a substation secondary equipment monitoring data analysis model.

[0058] The power transformer monitoring data analysis model is used to analyze the power transformer monitoring data, which is specifically expressed as follows: ET i represents the transformer evaluation value of the i-th time window, Tp i represents the partial discharge pulse spectrum distribution in the i-th time window, Tw i represents the winding deformation index of the i-th time window, Tf i represents the furfural concentration in the oil in the i-th time window, Tc i Indicates the harmonic content of the core flux density in the i-th time window, Tf crit Indicates the critical value of furfural concentration in oil.

[0059] The gas-insulated switchgear monitoring data analysis model is used to analyze the gas-insulated switchgear monitoring data, which is specifically expressed as follows: ES i represents the switchgear evaluation value in the i-th time window, Su irepresents the amplitude of the partial discharge high-frequency signal in the i-th time window, Sg i Indicates the water content of SF6 gas in the i-th time window, Sc i Represents the circuit breaker action speed curve of the i-th time window, Sm i represents the metal particle contamination degree in the i-th time window, Su thr Indicates the partial discharge signal amplitude threshold, Sg max Indicates the maximum allowable trace water content of SF6 gas, t ope Indicates the circuit breaker operation time, Sc ref represents the reference circuit breaker speed curve, v max Indicates the maximum allowable speed deviation, Sm crit Indicates critical metal particle contamination level.

[0060] The high-voltage transmission line monitoring data analysis model is used to analyze the high-voltage transmission line monitoring data, which is specifically expressed as follows: EL i represents the transmission line evaluation value of the i-th time window, Lc i represents the electric field intensity distribution on the conductor surface in the i-th time window, Lt i represents the tower foundation vibration spectrum of the i-th time window, Le i represents the equivalent salt density of the insulator string in the i-th time window, Ld i represents the corona discharge power loss in the i-th time window, Lc crit represents the critical conductor surface electric field strength, Lt ref represents the reference vibration spectrum, Le thr Indicates the equivalent salt density attachment density threshold, Ld rat Indicates the rated corona discharge power loss, Ld max Indicates the maximum allowable corona discharge power loss.

[0061] The substation secondary equipment monitoring data analysis model is used to analyze the substation secondary equipment monitoring data, which is specifically expressed as follows: EC i represents the evaluation value of the substation secondary equipment in the i-th time window, Cd i represents the IEC61850 communication delay of the protection device in the i-th time window, Cm i represents the synchronization accuracy of the merging unit in the i-th time window, Cs i represents the clock source phase noise of the ith time window, Cf i represents the fiber channel bit error rate in the i-th time window, Cd max Indicates the maximum permissible communication delay, Cmmax Indicates the maximum allowable synchronization accuracy error, Cs ref represents the reference phase noise level, Cf max Indicates the maximum allowable bit error rate.

[0062] Step 6: Status evaluation: used to calculate the abnormality index based on the evaluation value transmitted in step 5, and judge the abnormal status of the power equipment according to the set threshold value.

[0063] The specific steps of step 6 include:

[0064] A1: Weight allocation: Assign weights W1, W2, W3 and W4 to each evaluation value, and W1+W2+W3+W4=1;

[0065] A2: Weighted average: Weighted average S = w1 × ET i +w2×ES i +w3×EL i +w4×EC i ;

[0066] A3: Nonlinear mapping: Use nonlinear function for mapping: f(S) = 1-exp(-k×S), where k is an adjustable parameter;

[0067] A4: Time factor: introduce the time decay factor T = exp(-λ×t0), t0 represents the time since the last maintenance, λ is the decay rate;

[0068] A5: Final abnormality index: AI = f(S) × T;

[0069] A6: Abnormal judgment: Set a threshold θ. When AI>θ, it is judged as an abnormal state.

[0070] The present invention can accurately determine the layout position and communication quality of sensors through electromagnetic field simulation analysis and wireless signal coverage test of sensor network planning, ensure the effectiveness and reliability of the sensor network, reduce the problem of inaccurate or lost monitoring data due to improper sensor location or poor communication quality, and improve the overall performance of the monitoring system; through multi-mode sensor deployment, it can comprehensively collect monitoring data of power transformers, gas-insulated switchgear, high-voltage transmission lines and substation secondary equipment, provide a rich data source for subsequent data analysis and status evaluation, and the sensor deployment is flexible and can be expanded or adjusted according to actual needs, thereby improving the adaptability and flexibility of the monitoring system; through multi-protocol wireless transmission, the wireless communication protocol is determined according to the distance between the sensor and the local data aggregation node, which can optimize the transmission efficiency and energy consumption, improve the reliability and stability of data transmission, support multiple communication protocols, and can adapt to the data transmission needs in different scenarios, increasing It strengthens the versatility and compatibility of the monitoring system; through data preprocessing, wavelet denoising and data processing, it can effectively remove noise and outliers in the monitoring data, improve the accuracy and reliability of the data, and provide a high-quality data basis for subsequent data analysis and status evaluation, which helps to improve the overall performance of the monitoring system; through model performance evaluation, a mathematical model is established to evaluate the performance of the preprocessed data, which can accurately reflect the operating status and performance changes of the power equipment. Through model evaluation, potential failures and abnormal conditions of the power equipment can be discovered in time, providing a scientific basis for subsequent maintenance and management; through status evaluation, the abnormal index is calculated according to the evaluation value, and the abnormal state of the power equipment is judged according to the set threshold, which can realize real-time monitoring and early warning of the power equipment status. The status evaluation results are intuitive and accurate, which helps operation and maintenance personnel to take timely measures to deal with abnormal situations and ensure the normal operation of the power equipment and the safety and stability of the power grid.

[0071] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0072] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the state of power equipment based on a wireless sensor network, characterized in that: include: Step 1: Sensor network planning: Determine the sensor layout and communication quality through electromagnetic field simulation analysis and wireless signal coverage test, and transmit to step 2; Step 2: Multi-mode sensor deployment: used to deploy sensors according to the sensor layout position transmitted in step 2, to collect power transformer monitoring data, gas insulated switchgear monitoring data, high-voltage transmission line monitoring data and substation secondary equipment monitoring data, and transmit them to the local data aggregation node through step 3; Step 3: Multi-protocol wireless transmission: used to determine the wireless communication protocol according to the distance between the deployment location of the sensor in step 2 and the local data aggregation node; Step 4: Data preprocessing: used to perform wavelet denoising and data processing on the data transmitted in step 3, and transmit it to step 5; Step 5: Model performance evaluation: used to establish a mathematical model to evaluate the performance of the data preprocessed in step 4, and transmit the calculation results to step 6; Step 6: Status evaluation: used to calculate the abnormality index based on the evaluation value transmitted in step 5, and judge the abnormal status of the power equipment according to the set threshold value.

2. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 1, characterized in that: The step 2 uses a time sliding window to determine the data collection time of the power equipment, which is marked as 1, 2...n in sequence, and the ratio of the window size to the sliding step size is 6:1; In step 3, when the distance between the sensor and the local data aggregation node is a near-field distance, ZigBee (IEEE802.15.4 standard) or Bluetooth 5.0LE technology is used for low-power transmission. When the distance between the sensor and the local data aggregation node is a medium distance, LoRaWAN technology or enterprise-level Wi-Fi (IEEE 802.11ax) is used for transmission. When the distance between the sensor and the local data aggregation node is a long distance, a private LTE network is deployed or a public 5G network is used for transmission, and dynamic routing and load balancing between different protocols are realized through an SDN controller; Step 4 applies discrete wavelet transform to perform signal denoising, and uses the pandas library to perform data cleaning, interpolation, and outlier processing; The step 5 includes a power transformer monitoring data analysis model, a gas insulated switchgear monitoring data analysis model, a high-voltage transmission line monitoring data analysis model and a substation secondary equipment monitoring data analysis model.

3. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 1, characterized in that: The power transformer monitoring data includes partial discharge pulse spectrum distribution, winding deformation index, furfural concentration in oil and core magnetic flux density harmonic content, which are marked as Tp, Tw, Tf and Tc respectively; the gas insulated switchgear monitoring data includes partial discharge high-frequency signal amplitude, SF6 gas micro-water content, circuit breaker action speed curve and metal particle contamination, which are marked as Su, Sg, Sc and Sm respectively; the high-voltage transmission line monitoring data includes conductor surface electric field intensity distribution, tower foundation vibration spectrum, insulator string equivalent salt density adhesion density and corona discharge power loss, which are marked as Lc, Lt, Le and Ld respectively; the substation secondary equipment monitoring data includes protection device IEC61850 communication delay, merging unit synchronization accuracy, clock source phase noise and optical fiber channel bit error rate, which are marked as Cd, Cm, Cs and Cf respectively.

4. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 2, characterized in that: The power transformer monitoring data analysis model is used to analyze the power transformer monitoring data, which is specifically expressed as follows: ET i represents the transformer evaluation value of the i-th time window, Tp i represents the partial discharge pulse spectrum distribution in the i-th time window, Tw i represents the winding deformation index of the i-th time window, Tf i represents the furfural concentration in the oil in the i-th time window, Tc i Indicates the harmonic content of the core flux density in the i-th time window, Tf crit Indicates the critical value of furfural concentration in oil.

5. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 2, characterized in that: The gas-insulated switchgear monitoring data analysis model is used to analyze the gas-insulated switchgear monitoring data, which is specifically expressed as follows: ES i represents the switchgear evaluation value in the i-th time window, Su i represents the amplitude of the partial discharge high-frequency signal in the i-th time window, Sg i Indicates the water content of SF6 gas in the i-th time window, Sc i Represents the circuit breaker action speed curve of the i-th time window, Sm i represents the metal particle contamination degree in the i-th time window, Su thr Indicates the partial discharge signal amplitude threshold, Sg max Indicates the maximum allowable trace water content of SF6 gas, t ope Indicates the circuit breaker operation time, Sc ref represents the reference circuit breaker speed curve, v max Indicates the maximum allowable speed deviation, Sm crit Indicates critical metal particle contamination level.

6. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 2, characterized in that: The high-voltage transmission line monitoring data analysis model is used to analyze the high-voltage transmission line monitoring data, which is specifically expressed as follows: EL i represents the transmission line evaluation value of the i-th time window, Lc i represents the electric field intensity distribution on the conductor surface in the i-th time window, Lt i represents the tower foundation vibration spectrum of the i-th time window, Le i represents the equivalent salt density of the insulator string in the i-th time window, Ld i represents the corona discharge power loss in the i-th time window, Lc crit represents the critical conductor surface electric field strength, Lt ref represents the reference vibration spectrum, Le thr Indicates the equivalent salt density attachment density threshold, Ld rat Indicates the rated corona discharge power loss, Ld max Indicates the maximum allowable corona discharge power loss.

7. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 2, characterized in that: The substation secondary equipment monitoring data analysis model is used to analyze the substation secondary equipment monitoring data, which is specifically expressed as follows: , E.C. i represents the evaluation value of the substation secondary equipment in the i-th time window, Cd i represents the IEC61850 communication delay of the protection device in the i-th time window, Cm i represents the synchronization accuracy of the merging unit in the i-th time window, Cs i represents the clock source phase noise of the ith time window, Cf i represents the fiber channel bit error rate in the i-th time window, Cd max Indicates the maximum permissible communication delay, Cm max Indicates the maximum allowable synchronization accuracy error, Cs ref represents the reference phase noise level, Cf max Indicates the maximum allowable bit error rate.

8. The method for monitoring the state of electric power equipment based on a wireless sensor network according to claim 1, characterized in that: The specific steps of step 6 include: A1: Weight allocation: Assign weights W1, W2, W3 and W4 to each evaluation value, and W1+W2+W3+W4=1; A2: Weighted average: Weighted average S = w1 × ET i +w2×ES i +w3×EL i +w4×EC i ; A3: Nonlinear mapping: Use nonlinear function for mapping: f(S) = 1-exp(-k×S), where k is an adjustable parameter; A4: Time factor: Introduce the time decay factor T = exp(-λ×t0), t0 represents the time since the last maintenance, and λ is the decay rate; A5: Final abnormality index: AI = f(S) × T; A6: Abnormal judgment: Set a threshold θ. When AI>θ, it is judged as an abnormal state.

Images