Early fault detection method and system for crack porcelain insulator in resonant grounding power distribution network

Abstract

The invention discloses an early fault detection method and system for a crack porcelain insulator in a resonance grounding power distribution network, and the method comprises the steps: collecting related data through a sensor, and recognizing the type of the crack porcelain insulator; establishing an equivalent circuit model, and monitoring circuit data in real time; based on the real-time circuit data, detecting whether the porcelain insulator has a fault, and judging the fault type; and observing the surface structure change of the faulted porcelain insulator, establishing a cumulative effect model, analyzing the fault evolution trend and predicting the residual life of the porcelain insulator. And the accuracy of porcelain insulator fault detection is improved. The real-time monitoring system and the data analysis capability enable maintenance personnel to timely warn potential faults, formulate preventive maintenance strategies, prolong the service life of equipment and reduce the maintenance cost. Complex mathematical tools and algorithms ensure the innovativeness and academic property of the model, a data visualization platform assists scientific decision making, the safety and reliability of the power system are improved, and resource configuration is optimized.

Description

Technical Field

[0001] The invention relates to the technical field of insulator detection and maintenance, and in particular to a method and system for detecting early faults of cracked porcelain insulators in a resonant grounding distribution network. Background Art

[0002] With the rapid development of power systems, the stable operation and safety of distribution networks have become important research topics in the field of power engineering. In the distribution system, porcelain insulators are important insulating and supporting components, and their performance and reliability directly affect the operation quality and safety of the power system. In recent years, with the development of high voltage and ultra-high voltage transmission technology, the manufacturing process and material properties of porcelain insulators have also been significantly improved, forming a variety of porcelain insulators including pin type, suspension type, column type, etc. In the design and manufacturing process of these insulators, advanced ceramic materials and manufacturing processes are used to improve the mechanical strength and electrical properties of the insulators, which can effectively resist various mechanical and electrical stresses in operation. However, even so, cracks will inevitably appear in porcelain insulators during long-term operation, especially in resonant grounding distribution systems. Due to the influence of system characteristics and environmental factors, cracked porcelain insulators are more prone to early failure.

[0003] Although the performance of porcelain insulators in modern power distribution systems has been significantly improved, the existing technology still has obvious deficiencies in early fault detection and damage assessment of cracked porcelain insulators. First of all, most of the current detection methods mainly rely on manual inspections and regular maintenance, which is not only time-consuming and labor-intensive, but also difficult to ensure detection accuracy and timeliness. Especially under severe weather conditions, the efficiency and safety of manual detection are greatly reduced. Secondly, the existing detection technologies are mostly based on macroscopic observations, which makes it difficult to accurately identify tiny cracks and their early damage accumulation effects, resulting in cracks being discovered only when they develop to a serious degree, and often the best time for maintenance has been missed. In addition, the existing detection equipment and technical means have limitations in real-time data collection and analysis, making it difficult to achieve online monitoring and dynamic evaluation of cracked porcelain insulators. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing technology faces multiple challenges in early fault detection of cracked porcelain insulators. The existing technology has deficiencies in detection accuracy and is difficult to accurately identify and locate tiny cracks, which may often cause serious faults at an early stage. It is also unable to effectively evaluate the development of cracks and the cumulative damage.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for detecting early faults of cracked porcelain insulators in a resonant grounding distribution network, comprising:

[0007] Collect relevant data through sensors to identify the type of cracked porcelain insulators;

[0008] Establish an equivalent circuit model and monitor circuit data in real time;

[0009] Based on real-time circuit data, detect whether the porcelain insulator is faulty and determine the fault type;

[0010] Observe the surface structural changes of faulty porcelain insulators, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of porcelain insulators.

[0011] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network of the present invention, the relevant data includes appearance and structure data of the porcelain insulator, identification and nameplate data of the porcelain insulator, physical characteristic data of the porcelain insulator, environmental data, electrical parameter data, arc characteristic data, accumulated damage data and historical data;

[0012] Types of porcelain insulators include suspension insulators, post insulators and pin insulators;

[0013] Collecting relevant data through sensors and identifying the type of cracked porcelain insulators includes: after identifying the type of cracked porcelain insulators through the collected data, considering the structural characteristics of the pin-type insulators, the frequency of faults and the difficulty of maintenance, selecting pin-type porcelain insulators for early fault detection.

[0014] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network described in the present invention, wherein: establishing an equivalent circuit model, collecting real-time circuit data includes installing a voltage sensor and a current sensor in the circuit to measure the voltage and current in the circuit in real time, and using a high-frequency data acquisition system to record the voltage waveform and the current waveform in real time, and the formula is expressed as follows:

[0015] Differential Equations:

[0016]

[0017] Capacitor voltage:

[0018]

[0019] Damping coefficient:

[0020]

[0021] Angular frequency:

[0022]

[0023] Fault phase voltage:

[0024] u ph =u c +e ph

[0025] The real-time capacitor voltage detection formula is expressed as:

[0026]

[0027] The real-time current detection formula is expressed as:

[0028]

[0029] The real-time system voltage is expressed as:

[0030]

[0031] Where L is the inductance, diL is the rate of change of the inductor current, dt is the time differential, and R L Represents resistance, I L is the current, u c represents the capacitor voltage, δ represents the damping coefficient, ω h represents the angular frequency, t represents the time, U C (0+) represents the initial capacitor voltage, I L (0+) indicates the initial current, C indicates the capacitance, e ph

[0032] represents the fault phase power supply potential, T represents the integral variable, M represents the state matrix, A k represents the transfer matrix, l_L(0) is the initial current, B(τ) represents the dynamic coefficient matrix, and N represents the number of summation terms.

[0033] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network of the present invention, the method comprises: detecting whether a porcelain insulator fails based on real-time circuit data, and judging the type of the fault, combining SVM and Bayesian classifier, extracting and classifying the features of real-time circuit data, and constructing a comprehensive fault detection formula expressed as:

[0034]

[0035] The fault classification function is expressed as:

[0036]

[0037] Among them, w represents the weight vector of the support vector machine, b represents the bias of the support vector machine, ξ i represents the slack variable, C represents the regularization parameter, N represents the number of samples, x i represents the i-th sample, yi represents the category label of the sample, P(C k |x) represents the posterior probability, P(x|C k ) represents the class conditional probability, P(C k ) represents the prior probability, P(x) represents the evidence, W represents the state matrix, A(τ) represents the transfer matrix, F(t) represents the fault classification function, K represents the number of categories, and T represents the upper limit of the integral;

[0038] The value threshold of is a real number set, and the value threshold of F(t) is a real number set;

[0039] when And when F(t)<0.5, no abnormality occurs;

[0040] when And when 0.5≤F(t)<1.0, there is slight fluctuation in the circuit;

[0041] when And when 1.0≤F(t)<1.5, the circuit complies with the single-phase grounding fault mode and needs further confirmation;

[0042] when When 1.5≤F(t)<2.0, the circuit meets the short-circuit fault mode and needs to be confirmed immediately;

[0043] when When 2.0≤F(t)<2.5, the circuit meets the open-circuit short-circuit fault mode and needs to be confirmed and processed immediately;

[0044] when And when F(t)≥2.5, there is a serious fault in the circuit and a comprehensive inspection should be carried out immediately.

[0045] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network described in the present invention, wherein: observing the surface structural changes of the faulty porcelain insulator, establishing a cumulative effect model, analyzing the fault evolution trend and predicting the remaining life of the porcelain insulator includes, in order to comprehensively consider the influence of voltage and current on the cumulative damage of the porcelain insulator, using historical data and collected real-time circuit data to build a cumulative effect model, thereby accurately describing the cumulative effect of the cracked porcelain insulator, analyzing the fault evolution trend of the porcelain insulator, and achieving a more accurate prediction of the remaining life of the cracked porcelain insulator;

[0046] The cumulative effect model is expressed as:

[0047]

[0048] Where D(t) represents the cumulative damage degree at time t, t represents the current time variable, α represents the voltage weight coefficient, and U C(τ) represents the capacitor voltage at time τ, U(τ) represents the integrated voltage at time τ, τ represents the integral variable, represents the cumulative effect of current within time τ, I L (ξ) represents the current at time ξ, ξ represents the internal integral variable, β represents the current weight coefficient, n represents the number of summation terms, and N represents the maximum number of terms in the current polynomial expansion;

[0049] The value threshold of D(t) is from 0 to positive infinity.

[0050] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network of the present invention, wherein: observing the surface structural changes of the faulty porcelain insulator, establishing a cumulative effect model, analyzing the fault evolution trend and predicting the remaining life of the porcelain insulator also includes predicting the remaining life of the porcelain insulator based on the porcelain insulator fault evolution trend analyzed under the cumulative effect model, and the prediction function is expressed as:

[0051]

[0052] Where L(t) represents the remaining life at time t, L0 represents the expected life of the porcelain insulator without damage, γ represents the attenuation coefficient, D(t) represents the result of the cumulative damage model, M represents the state matrix, and M -1 represents the inverse matrix of the state matrix, dτ represents the state transfer matrix, A represents the transfer matrix, exp(Aξ) represents the exponential function of the matrix, and ξ represents the integral variable;

[0053] The value threshold of L(t) is 0 to L0.

[0054] As a preferred solution of the method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network of the present invention, wherein: observing the surface structural changes of the faulty porcelain insulator, establishing a cumulative effect model, analyzing the fault evolution trend and predicting the remaining life of the porcelain insulator also includes: when 0≤D(t)<10, slight cracks appear on the surface of the porcelain insulator, and the degree of damage is low;

[0055] When 10≤D(t)<50, the surface cracks of the porcelain insulator increase and expand, and further monitoring is required;

[0056] When 50≤D(t)<100, the surface cracks of the porcelain insulator affect the insulator structure and require timely maintenance;

[0057] When D(t)≥100, the surface cracks of the porcelain insulator seriously affect the function of the insulator and should be replaced immediately;

[0058] When 0.8L0≤L(t)≤L0, the porcelain insulator is in good condition and has a long remaining life;

[0059] When 0.5L0 ≤ L(t) < 0.8L0, the porcelain insulator has certain damage but can still work properly for a period of time;

[0060] When 0.2L0 ≤ L(t) < 0.5L0, the porcelain insulator is severely damaged and needs to be replaced as planned;

[0061] When 0 < L(t) < 0.2L0, the porcelain insulator is about to fail and needs to be replaced immediately.

[0062] An early fault detection system for cracked porcelain insulators in a resonant grounded distribution network, wherein:

[0063] A data acquisition module that collects relevant data through sensors and identifies the types of cracked porcelain insulators;

[0064] A monitoring circuit module that establishes an equivalent circuit model and monitors circuit data in real time;

[0065] A fault detection module that detects whether a porcelain insulator fails based on real-time circuit data and determines the type of fault;

[0066] A fault observation module that observes the surface structure changes of faulty porcelain insulators, establishes an accumulation effect model, analyzes the fault evolution trend, and predicts the remaining life of the porcelain insulator.

[0067] A computer device, comprising: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method described in any one of the present inventions are implemented.

[0068] A computer-readable storage medium, on which a computer program is stored, characterized in that: when the computer program is executed by a processor, the steps of the method described in any one of the present inventions are implemented.

[0069] The beneficial effects of the present invention: Through the accumulation effect model and the remaining life prediction model, combined with the voltage and current data collected in real time, the accuracy of porcelain insulator fault detection is improved. The real-time monitoring system and data analysis capabilities enable maintenance personnel to timely warn of potential faults, formulate preventive maintenance strategies, extend the equipment life, and reduce maintenance costs. Complex mathematical tools and algorithms ensure the innovation and academic nature of the model, and the data visualization platform assists in scientific decision-making, improves the safety and reliability of the power system, and optimizes resource allocation. Description of the Drawings

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0071] Figure 1 An overall flow chart of a method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network provided by the first embodiment of the present invention;

[0072] Figure 2 An equivalent circuit diagram of the recovery process of a method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0074] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for detecting early faults of cracked porcelain insulators in a resonant grounding distribution network, comprising:

[0075] S1: Collect relevant data through sensors to identify the type of cracked porcelain insulators.

[0076] During the operation of 10kV distribution lines, pin-type, suspension-type, column-type and other porcelain insulators may develop cracks under the influence of adverse conditions such as electrical stress and mechanical stress. At this time, the insulators can still maintain their intact shape, and the cracks are highly concealed. During the inspection process, line patrol personnel need to spend a lot of extra effort to find cracked insulators.

[0077] Among the three types of porcelain insulators, suspension insulators have an advantage on rainy days because the iron cap can prevent rainwater from entering the cracks to a certain extent. In addition, suspension insulators are usually used in 10kV distribution networks in the form of two-piece insulator strings. Therefore, if only one of the pieces has a crack, no discharge will occur. The height of the post insulator can exceed 20cm, and it can maintain sufficient insulation capacity even if there are cracks. Therefore, the main failure mode of the post insulator is fracture rather than electrical discharge. For pin-type porcelain insulators, the thickness of the porcelain layer between the conductor and the metal pin is only 2 to 3cm. Since it has no iron cap, the crack will be completely exposed to the external environment. On rainy days, rainwater will accumulate in the conductor slot and flow into the crack, causing early failures.

[0078] S2: Establish an equivalent circuit model and monitor circuit data in real time.

[0079] The relevant data include the appearance and structure data of porcelain insulators, the identification and nameplate data of porcelain insulators, the physical characteristics data of porcelain insulators, environmental data, electrical parameter data, arc characteristic data, accumulated damage data and historical data.

[0080] Types of porcelain insulators include suspension insulators, post insulators and pin insulators.

[0081] Collecting relevant data through sensors and identifying the type of cracked porcelain insulators includes: after identifying the type of cracked porcelain insulators through the collected data, considering the structural characteristics of the pin-type insulators, the frequency of faults and the difficulty of maintenance, selecting pin-type porcelain insulators for early fault detection.

[0082] Install voltage sensors and current sensors in the circuit to measure the voltage and current in the circuit in real time, and use a high-frequency data acquisition system to record the voltage waveform and current waveform in real time. The formula is expressed as:

[0083] Differential Equations:

[0084]

[0085] Capacitor voltage:

[0086]

[0087] Damping coefficient:

[0088]

[0089] Angular frequency:

[0090]

[0091] Fault phase voltage:

[0092] u ph =uc +e ph

[0093] The real-time capacitor voltage detection formula is expressed as:

[0094]

[0095] The real-time current detection formula is expressed as:

[0096]

[0097] The real-time system voltage is expressed as:

[0098]

[0099] Where L is the inductance, diL is the rate of change of the inductor current, dt is the time differential, and R L Represents resistance, I L is the current, u c represents the capacitor voltage, δ represents the damping coefficient, ω h represents the angular frequency, t represents the time, U C (0+) represents the initial capacitor voltage, I L (0+) indicates the initial current, C indicates the capacitance, e ph represents the fault phase power supply potential, T represents the integral variable, M represents the state matrix, Ak represents the transfer matrix, lL(0) is the initial current, B(τ) represents the dynamic coefficient matrix, and N represents the number of summation items.

[0100] By installing voltage sensors, current sensors and temperature sensors on each porcelain insulator, it is ensured that real-time data in the circuit can be accurately collected. A high-frequency data acquisition system is set up to ensure the real-time and accuracy of the data.

[0101] S3: Based on real-time circuit data, detect whether the porcelain insulator is faulty and determine the fault type.

[0102] Combining SVM and Bayesian classifier, through feature extraction and classification of real-time circuit data, a comprehensive fault detection formula is constructed as follows:

[0103]

[0104] The fault classification function is expressed as:

[0105]

[0106] Among them, w represents the weight vector of the support vector machine, b represents the bias of the support vector machine, ξ i represents the slack variable, C represents the regularization parameter, N represents the number of samples, x irepresents the i-th sample, y i represents the category label of the sample, P(C k |x) represents the posterior probability, P(x|C k ) represents the class conditional probability, P(C k ) represents the prior probability, P(x) represents the evidence, W represents the state matrix, A(τ) represents the transfer matrix, F(t) represents the fault classification function, K represents the number of categories, and T represents the upper limit of the integral.

[0107] The value threshold of is a real number set, and the value threshold of F(t) is a real number set.

[0108] when And when F(t)<0.5, no abnormality occurs.

[0109] when And when 0.5≤F(t)<1.0, there is slight fluctuation in the circuit.

[0110] when And when 1.0≤F(t)<1.5, the circuit complies with the single-phase grounding fault mode and needs further confirmation.

[0111] when And when 1.5≤F(t)<2.0, the circuit meets the short-circuit fault mode and requires immediate confirmation.

[0112] when And when 2.0≤F(t)<2.5, the circuit meets the open circuit short circuit failure mode and needs to be confirmed and processed immediately.

[0113] when And when F(t)≥2.5, there is a serious fault in the circuit and a comprehensive inspection should be carried out immediately.

[0114] By establishing an equivalent circuit model for each sample and inputting initial parameters for simulation and verification, the accuracy and stability of the model are ensured, which provides a theoretical basis and calculation basis for subsequent fault detection and life prediction.

[0115] S4: Observe the surface structural changes of the faulty porcelain insulator, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of the porcelain insulator.

[0116] In order to comprehensively consider the influence of voltage and current on the cumulative damage of porcelain insulators, a cumulative effect model is constructed using historical data and collected real-time circuit data, so as to accurately describe the cumulative effect of cracked porcelain insulators and analyze the fault evolution trend of porcelain insulators, so as to achieve a more accurate prediction of the remaining life of cracked porcelain insulators.

[0117] The cumulative effect model is expressed as:

[0118]

[0119] Where D(t) represents the cumulative damage degree at time t, t represents the current time variable, α represents the voltage weight coefficient, and U C (τ) represents the capacitor voltage at time τ, U(τ) represents the integrated voltage at time τ, τ represents the integral variable, represents the cumulative effect of current within time τ, I L (ξ) represents the current at time ξ, ξ represents the internal integral variable, β represents the current weight coefficient, n represents the number of summation terms, and N represents the maximum number of terms in the current polynomial expansion.

[0120] The value threshold of D(t) is from 0 to positive infinity.

[0121] Based on the fault evolution trend of porcelain insulators analyzed under the cumulative effect model, the remaining life of porcelain insulators is predicted. The prediction function is expressed as:

[0122]

[0123] Where L(t) represents the remaining life at time t, L0 represents the expected life of the porcelain insulator without damage, γ represents the attenuation coefficient, D(t) represents the result of the cumulative damage model, M represents the state matrix, and M -1 represents the inverse matrix of the state matrix, represents the state transfer matrix, A represents the transfer matrix, exp(Aτ) represents the exponential function of the matrix, and τ represents the integral variable.

[0124] The value threshold of L(t) is 0 to L0.

[0125] When 0≤D(t)<10, slight cracks appear on the surface of the porcelain insulator and the degree of damage is low.

[0126] When 10≤D(t)<50, the surface cracks of the porcelain insulator increase and expand, and further monitoring is required.

[0127] When 50≤D(t)<100, the surface cracks of the porcelain insulator affect the insulator structure and require timely maintenance.

[0128] When D(t)≥100, the surface cracks of the porcelain insulator seriously affect the function of the insulator and should be replaced immediately.

[0129] When 0.8L0≤L(t)≤L0, the porcelain insulator is in good condition and has a long remaining life.

[0130] When 0.5L0≤L(t)<0.8L0, the porcelain insulator has some damage but can still work normally for a period of time.

[0131] When \(0.2L_0\leq L(t)\lt0.5L_0\), the porcelain insulator is severely damaged and needs to be replaced as planned.

[0132] When \(0\lt L(t)\lt0.2L_0\), the porcelain insulator is about to fail and needs to be replaced immediately.

[0133] By turning on the data acquisition system, voltage, current and temperature data are monitored in real time, and the cumulative damage is calculated and the remaining life is predicted. Through real-time data monitoring and calculation, potential faults can be detected and warned in time, improving the reliability and safety of the power system.

[0134] On the other hand, this embodiment also provides an early fault detection system for cracked porcelain insulators in a resonant grounded distribution network, which includes:

[0135] A data acquisition module, which collects relevant data through sensors and identifies the types of cracked porcelain insulators.

[0136] A monitoring circuit module, which establishes an equivalent circuit model and monitors circuit data in real time.

[0137] A fault detection module, which detects whether the porcelain insulator fails based on real-time circuit data and determines the type of fault.

[0138] A fault observation module, which observes the surface structure changes of the faulty porcelain insulator, establishes a cumulative effect model, analyzes the fault evolution trend and predicts the remaining life of the porcelain insulator.

[0139] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0140] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0141] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0142] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0143] Example 2

[0144] Cracked porcelain insulators of different types and states were selected as test objects, including 3 new insulators, 3 slightly cracked insulators, 3 moderately cracked insulators and 3 severely cracked insulators, for a total of 12 samples.

[0145] The initial state and appearance characteristics of each sample were recorded, and high-resolution photos were taken as a benchmark for subsequent comparative analysis.

[0146] Install voltage sensors, current sensors and temperature sensors on each porcelain insulator to ensure that the sensors are in close contact and can accurately collect data.

[0147] Connect the data acquisition system and set the sampling frequency to 100kHz to ensure real-time monitoring of voltage, current and temperature changes.

[0148] An equivalent circuit model is established for each sample, and initial parameters including capacitor voltage, integrated voltage, and current are input.

[0149] Each sample was simulated using modeling software to verify the accuracy and stability of the model.

[0150] Turn on the data acquisition system to monitor the voltage, current and temperature data of each sample in real time and record the data changes every minute.

[0151] The cumulative damage is calculated using the cumulative effect model, and the remaining life of the porcelain insulator is predicted based on the remaining life prediction model.

[0152] The surface structure of each sample was inspected every 24 hours, and crack changes were observed using a high-resolution microscope, and parameters such as the number, length and width of cracks were recorded.

[0153] Based on the observation results, the crack propagation trend is analyzed and the prediction accuracy of the cumulative effect model is verified.

[0154] The collected data are analyzed to verify the accuracy and reliability of the equivalent circuit model and cumulative effect model.

[0155] According to the experimental results, the model parameters are optimized to improve the prediction accuracy of the model.

[0156] The experimental results are shown in Table 1.

[0157] Table 1 Experimental data table

[0158]

[0159]

[0160] From the above table data, it can be seen that the present invention has significant innovation and advantages in porcelain insulator fault detection and remaining life prediction. First, by real-time acquisition of voltage, current and temperature data, and combining the cumulative effect model and the remaining life prediction model, the cumulative damage and remaining life of the porcelain insulator can be accurately calculated. From the table, it can be seen that the cumulative damage and remaining life of porcelain insulators with different crack degrees are significantly different, indicating that the model of the present invention can effectively distinguish porcelain insulators with different fault states.

[0161] Under the same initial voltage and current conditions, the predicted remaining life of samples S1 and S2 gradually decreases as the accumulated damage increases. The accumulated damage of sample S12 reaches 60, and its predicted remaining life is only 1 hour, indicating that the porcelain insulator is about to fail and needs to be replaced immediately. This accurate fault prediction capability significantly improves the reliability and safety of the power system and avoids power outages and equipment damage caused by sudden faults.

[0162] Compared with the prior art, the cumulative effect model and remaining life prediction model of the present invention are more complex and accurate. By comprehensively considering multiple factors such as voltage, current and temperature, a multi-dimensional fault detection and prediction system is established. Traditional methods can often only monitor a single parameter and cannot fully reflect the degree of damage and fault risk of porcelain insulators. The present invention realizes multi-parameter comprehensive evaluation through complex mathematical formulas and real-time data analysis, significantly improving detection accuracy and prediction reliability.

[0163] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network, characterized in that: include: Collect relevant data through sensors to identify the type of cracked porcelain insulators; Establish an equivalent circuit model and monitor circuit data in real time; Based on real-time circuit data, detect whether the porcelain insulator is faulty and determine the fault type; Observe the surface structural changes of faulty porcelain insulators, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of porcelain insulators.

2. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 1, characterized in that: The relevant data include the appearance and structure data of porcelain insulators, the identification and nameplate data of porcelain insulators, the physical characteristics data of porcelain insulators, environmental data, electrical parameter data, arc characteristic data, accumulated damage data and historical data; Types of porcelain insulators include suspension insulators, post insulators and pin insulators; Collecting relevant data through sensors and identifying the type of cracked porcelain insulators includes: after identifying the type of cracked porcelain insulators through the collected data, considering the structural characteristics of the pin-type insulators, the frequency of faults and the difficulty of maintenance, selecting pin-type porcelain insulators for early fault detection.

3. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 2, characterized in that: Establishing an equivalent circuit model and collecting real-time circuit data includes installing voltage sensors and current sensors in the circuit to measure the voltage and current in the circuit in real time, and using a high-frequency data acquisition system to record the voltage waveform and current waveform in real time. The formula is expressed as: Differential Equations: Capacitor voltage: Damping coefficient: Angular frequency: Fault phase voltage: in ph =in c +e ph The real-time capacitor voltage detection formula is expressed as: The real-time current detection formula is expressed as: The real-time system voltage is expressed as: Where L is the inductance, diL is the rate of change of the inductor current, dt is the time differential, and R L Represents resistance, I L is the current, u c represents the capacitor voltage, δ represents the damping coefficient, ω h represents the angular frequency, t represents the time, U C (0+) represents the initial capacitor voltage, I L (0+) indicates the initial current, C indicates the capacitance, e ph represents the fault phase power supply potential, τ represents the integral variable, M represents the state matrix, A k represents the transfer matrix, l_L(0) is the initial current, B(τ) represents the dynamic coefficient matrix, and N represents the number of summation terms.

4. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 3, characterized in that: Based on real-time circuit data, detect whether the porcelain insulator is faulty and judge the fault type. Combine SVM and Bayesian classifier, extract and classify the features of real-time circuit data, and construct a comprehensive fault detection formula expressed as: The fault classification function is expressed as: Among them, w represents the weight vector of the support vector machine, b represents the bias of the support vector machine, ξ i represents the slack variable, C represents the regularization parameter, N represents the number of samples, x i represents the i-th sample, y i represents the category label of the sample, P(C k |x) represents the posterior probability, P(x|C k ) represents the class conditional probability, P(C k ) represents the prior probability, P(x) represents the evidence, W represents the state matrix, A(τ) represents the transfer matrix, F(t) represents the fault classification function, K represents the number of categories, and T represents the upper limit of the integral; The value threshold of is a real number set, and the value threshold of F(t) is a real number set; when And when F(t)<0.5, no abnormality occurs; when And when 0.5≤F(t)<1.0, there is slight fluctuation in the circuit; when And when 1.0≤F(t)<1.5, the circuit complies with the single-phase grounding fault mode and needs further confirmation; when When 1.5≤F(t)<2.0, the circuit meets the short-circuit fault mode and needs to be confirmed immediately; when When 2.0≤F(t)<2.5, the circuit meets the open-circuit short-circuit fault mode and needs to be confirmed and processed immediately; when And when F9t)≥2.5, there is a serious fault in the circuit and a comprehensive inspection should be carried out immediately.

5. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 4, characterized in that: Observe the surface structural changes of the faulty porcelain insulator, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of the porcelain insulator, including: in order to fully consider the impact of voltage and current on the cumulative damage of the porcelain insulator, use historical data and collected real-time circuit data to build a cumulative effect model, so as to accurately describe the cumulative effect of cracked porcelain insulators, analyze the fault evolution trend of porcelain insulators, and achieve a more accurate prediction of the remaining life of cracked porcelain insulators; The cumulative effect model is expressed as: Where D(t) represents the cumulative damage degree at time t, t represents the current time variable, α represents the voltage weight coefficient, and U C (τ) represents the capacitor voltage at time τ, U(τ) represents the integrated voltage at time τ, τ represents the integral variable, represents the cumulative effect of current within time τ, I L (ξ) represents the current at time ξ, ξ represents the internal integral variable, β represents the current weight coefficient, n represents the number of summation terms, and N represents the maximum number of terms in the current polynomial expansion; The value threshold of D(t) is from 0 to positive infinity.

6. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 5, characterized in that: Observe the surface structural changes of the faulty porcelain insulator, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of the porcelain insulator. It also includes predicting the remaining life of the porcelain insulator based on the fault evolution trend of the porcelain insulator analyzed under the cumulative effect model. The prediction function is expressed as: Where L(t) represents the remaining life at time t, L0 represents the expected life of the porcelain insulator without damage, γ represents the attenuation coefficient, D(t) represents the result of the cumulative damage model, M represents the state matrix, and M -1 represents the inverse matrix of the state matrix, represents the state transfer matrix, A represents the transfer matrix, exp(Aτ) represents the exponential function of the matrix, and τ represents the integral variable; The value threshold of L(t) is 0 to L0.

7. The method for detecting early faults of cracked porcelain insulators in a resonant grounded distribution network according to claim 6, characterized in that: Observe the surface structural changes of the faulty porcelain insulator, establish a cumulative effect model, analyze the fault evolution trend and predict the remaining life of the porcelain insulator. It also includes that when 0≤D(t)<10, slight cracks appear on the surface of the porcelain insulator, and the degree of damage is low; When 10≤D(t)<50, the surface cracks of the porcelain insulator increase and expand, and further monitoring is required; When 50≤D(t)<100, the surface cracks of the porcelain insulator affect the insulator structure and require timely maintenance; When D(t) ≥ 100, the surface cracks of the porcelain insulator seriously affect the insulator function, and it shall be replaced immediately; When 0.8L0 ≤ L(t) ≤ L0, the porcelain insulator is in good condition and has a relatively long remaining life; When 0.5L0 ≤ L(t) < 0.8L0, the porcelain insulator has certain damage but can still work properly for a period of time; When 0.2L0 ≤ L(t) < 0.5L0, the porcelain insulator is severely damaged and needs to be replaced as planned; When 0 < L(t) < 0.2L0, the porcelain insulator is about to fail and shall be replaced immediately.

8. An early fault detection system for cracked porcelain insulators in a resonant grounded distribution network adopting the method as described in any one of claims 1 - 7, characterized in that: A data acquisition module, which collects relevant data through sensors and identifies the types of cracked porcelain insulators; A monitoring circuit module, which establishes an equivalent circuit model and monitors the circuit data in real time; A fault detection module, which detects whether the porcelain insulator fails based on the real - time circuit data and judges the type of the fault; A fault observation module, which observes the surface structure changes of the faulty porcelain insulator, establishes a cumulative effect model, analyzes the fault evolution trend and predicts the remaining life of the porcelain insulator.

9. A computer device comprising: A memory and a processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the early fault detection method for cracked porcelain insulators in a resonant grounded distribution network are realized.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the early fault detection method for cracked porcelain insulators in a resonant grounded distribution network are realized.

Images