Power grid visual diagnosis system and method based on multi-source data fusion

Abstract

The invention discloses a power grid visual diagnosis system based on multi-source data fusion, and relates to the field of power grid diagnosis systems. The system comprises an information acquisition module, an electrical fault alarm module, a non-electrical quantity fault alarm module, a fault discrimination module, a communication module and a fault recording module. Firstly, information of a power grid is collected through the information collection module, then the information is transmitted to the electrical fault alarm module and the non-electrical fault alarm module for monitoring, corresponding actions are made when abnormity occurs, then the information is transmitted to the fault judgment module, input information is analyzed, and the fault type is obtained; meanwhile, the fault recording module records and broadcasts the power grid; the communication module collects information of other modules in the system and exchanges information with the monitoring system. According to the method, the abnormal information of the power grid is monitored and alarmed in combination with the multi-source data, and the fault type is judged through the data model, so that the omnibearing monitoring of the power grid is realized, and data support is provided for a subsequent maintenance plan.

Description

Technical Field

[0001] The invention relates to a power grid diagnosis system, and in particular to a power grid visualization diagnosis system and method based on multi-source data fusion. Background Art

[0002] With the development of the economy, the scale of the power system continues to expand, and the grid structure is becoming increasingly complex. Traditional manual inspections and simple monitoring methods can no longer meet the needs of comprehensive and real-time monitoring of the operation status of the power grid. It is necessary to use advanced diagnostic systems to improve the efficiency and accuracy of fault detection and diagnosis. Nowadays, the reliability of power supply is extremely high, and power outages may cause huge losses to production and life. The power grid diagnostic system can promptly detect potential faults, quickly locate the fault location, and shorten the fault repair time, thereby improving the reliability and continuity of power supply. Similarly, the construction of smart grids is the development trend of the power industry, which emphasizes the intelligence, automation and informatization of power grids. As an important part of the smart grid, the power grid diagnostic system can realize the real-time collection, analysis and processing of power grid operation data, and provide technical support for the optimized operation and self-healing control of the smart grid.

[0003] Chinese patent CN114252716A discloses a method and device for diagnosing power grid faults. First, the alarm information of the power grid is obtained, and the alarm information is processed to obtain its wavelet packet time-frequency spectrum grayscale image. Then, a preset CNN-SVM fusion model is called as a fault diagnosis model to perform feature recognition on the wavelet packet time-frequency spectrum grayscale image to obtain the type of power grid fault. Finally, the type of power grid fault is pushed to a maintenance terminal for visual display. Through the present invention, the technical problems of low efficiency of traditional power grid fault diagnosis and failure to handle power grid faults in a timely manner can be solved. Summary of the invention

[0004] The technical problem to be solved by the present invention is how to provide a power grid diagnosis system and method with more comprehensive monitoring data and more intelligent fault type judgment.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A visual diagnosis system for power grid based on multi-source data fusion, comprising the following parts: information acquisition module, electrical fault alarm module, non-electrical fault alarm module, fault identification module, communication module, fault recording module;

[0007] The information collection module collects electrical quantities and non-electrical quantities.

[0008] 1) Electrical quantity collection: The information collection module collects the voltage and current signals in the power grid in real time, converts the signals into weak current signals through the AC plug-in, and outputs electrical quantity signals after being processed by the CPU inside the module;

[0009] 2) Non-electrical quantity collection: The information collection module collects the physical information collected by each sensor and plug-in in the system in real time, and outputs non-electrical quantity signals after being processed by the CPU inside the module;

[0010] The electrical fault alarm module receives the electrical quantity signal output by the information acquisition module and judges the electrical quantity through a preset logic, and issues an alarm when an abnormality occurs;

[0011] The non-electrical fault alarm module receives the non-electrical quantity signal output by the information acquisition module and makes a judgment according to the preset control word and preset logic, and issues an alarm when an abnormality occurs;

[0012] When an alarm occurs, the fault identification module receives fault information, identifies the fault type, and outputs the fault type;

[0013] The communication module exchanges information in the system with the power grid monitoring system in real time and displays it visually through the human-machine interface and the power grid monitoring system;

[0014] The fault recording module records the fault electrical quantity data after the electrical quantity is abnormal and is determined to be a fault.

[0015] The information collection module collects electrical quantities and non-electrical quantities of the monitored power grid;

[0016] The electrical quantity information is collected by receiving the original analog signal of the monitoring point through the measuring device and converting it into a low-current and low-voltage AC signal. The measuring device includes a voltage transformer and a current transformer, and then converting it into a unidirectional sinusoidal signal through a signal conditioning circuit. The analog-to-digital conversion module collects the electrical signal output from the signal conditioning circuit in real time, and performs analog-to-digital conversion to output the electrical signal to the CPU plug-in. The CPU plug-in processes the electrical signal according to a preset logic and outputs an electrical quantity parameter signal. The electrical quantity signal includes voltage, current, and frequency, power factor, active power, reactive power signal, differential current, zero-sequence current, and negative-sequence current obtained after calculation and processing by the information collection system;

[0017] The electrical quantity information is collected by receiving the physical information collected by the sensor and the plug-in, and then the analog information received in the sensor is converted into a digital signal through the analog-to-digital conversion module, and the digital signal and the signal received from the plug-in are transmitted to the CPU plug-in. After processing, the non-electrical parameter signal is output, and the non-electrical quantity signal includes transformer temperature, oil level, gas concentration and transformer internal air pressure.

[0018] The electrical fault alarm module warns of various electrical quantity abnormalities, including but not limited to differential quick-break alarm protection, ratio differential alarm protection, differential current excessive alarm protection, overcurrent one stage, overcurrent two stage, overcurrent three stage alarm protection, overload protection function PT line break alarm protection, overvoltage alarm protection, undervoltage alarm protection, CT line break alarm, single-phase grounding alarm, zero-sequence current alarm protection, and negative-sequence current alarm protection.

[0019] The non-electrical quantity fault alarm module controls the function activation and deactivation, control output delay and trip alarm status selection according to the preset control word; and provides alarm protection for various non-electrical quantity abnormalities, including but not limited to heavy gas action tripping, light gas action alarm, SF6 gas pressure abnormality alarm, transformer high temperature alarm, transformer ultra-high temperature tripping, and transformer low oil level alarm.

[0020] The fault identification module analyzes and identifies the fault information through the fault identification data model. The specific steps are as follows:

[0021] 1) Define parameter attribute sets and membership functions for input parameters;

[0022] 2) Calculate the membership value of the input variable;

[0023] 3) Build a rule base based on the failure mechanism;

[0024] 4) Fault type identification;

[0025] 5) Output fault type.

[0026] The communication module is connected to each module in the system to collect information, including digital signals processed by the information collection system. The electrical quantity information in the digital signal includes voltage, current, and frequency, power factor, active power, reactive power differential current, zero-sequence current, and negative-sequence current information obtained after calculation and processing by the information collection system; non-electrical quantity signals include switch quantity signals collected by the plug-in and physical information collected by the sensor; and the operating status information of the electrical fault alarm module, the non-electrical quantity fault alarm module, and the fault discrimination module is collected, including the parameters of the protection action, the operating status of the system's own plug-in, and the fault type output by the fault alarm module when the system operates abnormally.

[0027] The communication module is provided with a human-machine interface, which provides a control user interface; and the communication module supports multiple communication protocols, including IEC60870-5-101, IEC60870-5-104, Modbus, CDT, 9702 and private protocols, and is connected to the power station monitoring system through network transmission to complete the functions of sending system information and receiving external commands.

[0028] The starting conditions of the fault recording module include overcurrent start, undervoltage start, and differential trip start. When these starting conditions are met, the device records the corresponding electrical quantities and records the changes in the power grid system parameters in the period before and after the fault occurs, which is convenient for fault analysis and accident recall.

[0029] A power grid visualization diagnosis method based on multi-source data fusion, the method using the power grid visualization diagnosis method according to any one of claims 1 to 8, comprising the following steps:

[0030] 1) In the information collection stage, the system monitors the power system to collect electrical and non-electrical quantity signals, and processes the signals into digital signals, which are then processed by the CPU plug-in;

[0031] 2) In the fault alarm stage, the electrical fault alarm module and the non-electrical fault alarm module receive the information output by the information acquisition module, and perform corresponding alarm protection or tripping protection operations when an abnormality occurs through preset control words and logic;

[0032] 3) Fault identification stage: after a fault alarm occurs, the fault information is input into the fault identification module. The fault parameters are calculated for membership through the fault identification data model. Combined with the preset rule base, the possible field faults are determined. The correlation between the fault parameters and the field faults is sorted and output according to the rule strength.

[0033] 4) During the fault recording stage, when a fault occurs and the overcurrent start, undervoltage start, and differential trip start conditions are met, the fault recording module records the changes in the grid system parameters monitored by the system before and after the fault occurs.

[0034] The beneficial effects of adopting the above technical solution are:

[0035] The present invention uses sensors and plug-ins to collect all-round information on both electrical and non-electrical parameters for the operation status of the power grid, providing a rich data basis for subsequent fault diagnosis.

[0036] The present invention is equipped with an alarm module around electrical quantity and non-electrical quantity parameters, which can execute alarm and tripping actions when an abnormality occurs, and can effectively prevent the expansion of the fault range.

[0037] The fault discrimination data model proposed in the present invention defines the membership degree for the range of parameters and then performs fault discrimination based on the membership degree. Compared with the traditional threshold discrimination, it is more detailed and intelligent in critical data discrimination, and reduces the risk of misjudgment and missed judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0039] Figure 1 It is a system diagram of a power grid visualization diagnosis system based on multi-source data fusion proposed by the present invention, excluding the communication module;

[0040] Figure 2 It is a system diagram of information collection and visualization by a communication module in a power grid visualization diagnosis system based on multi-source data fusion proposed by the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purpose, features and advantages of the present invention more obvious and easy to understand, the technical scheme in the embodiments of the present invention will be clearly and completely described below in combination with the drawings and specific implementation methods 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.

[0042] The present invention provides a power grid visualization diagnosis system based on multi-source data fusion, such as Figure 1 It includes the following parts: information collection module, electrical fault alarm module, non-electrical fault alarm module, fault identification module, communication module, and fault recording module.

[0043] (I) Information collection module

[0044] 1. Electrical quantity collection

[0045] The information acquisition module realizes accurate acquisition of electrical quantities by designing circuits and processing procedures. At the power grid monitoring point, the voltage transformer (PT) and the current transformer (CT) work closely together to linearly convert the high-voltage and high-current original power grid analog signals into low-current and low-voltage AC signals suitable for subsequent processing by means of high-precision electromagnetic induction. In actual use, the common 110kV voltage level line can be converted into a 100V standard secondary voltage signal by PT, and the CT converts the current of several thousand amperes into a secondary current signal of 5A or 1A according to the transformation ratio. Subsequently, the signal conditioning circuit optimizes these AC signals. First, the complex high-frequency noise interference and low-frequency fluctuation components in the power grid are effectively filtered out by the filtering function, and only the pure sinusoidal waveform signal components that can accurately reflect the electrical characteristics of the power grid are retained; at the same time, the signal amplitude is accurately adjusted to the optimal input range of the analog-to-digital conversion module (ADC) by using the amplification or attenuation function. In actual use, the signal conditioning circuit can amplify the weak AC signal with an amplitude fluctuation of several millivolts to several volts to the standard range of 0V-5V, ensuring the high accuracy and stability of ADC conversion.

[0046] As a key link in the digitization of electrical quantities, the analog-to-digital conversion module uses a high-speed, high-resolution ADC chip, and uses a sampling frequency of up to several MSPS (millions of samples per second) to collect the unidirectional sinusoidal signal output by the signal conditioning circuit in real time, and converts the continuous analog electrical signal into a discrete digital encoding signal according to the preset quantization accuracy. The specific quantization accuracy is determined according to the specific grid parameters and the required accuracy for judgment. The discrete digital signal is transmitted to the high-performance CPU plug-in inside the module. The CPU plug-in performs in-depth processing on the digital signal of electrical quantities according to the preset logic program. In specific use, the frequency component, amplitude and phase information of the signal are usually accurately calculated through the fast Fourier transform (FFT) algorithm; based on circuit principles such as Ohm's law and Kirchhoff's law, combined with the grid topology parameters, the voltage effective value, current effective value, active power, reactive power, power factor and other key electrical quantity parameter signals of the monitoring point are calculated in real time. The parameter signals obtained after calculation provide a solid data foundation for subsequent detection and fault diagnosis.

[0047] 2. Non-electrical quantity collection

[0048] The information acquisition module collects non-electrical quantities by collecting analog information collected by various sensors in the acquisition system (such as temperature sensors, pressure sensors, liquid level sensors, etc.), as well as switch signals collected by plug-ins, and then performs targeted processing respectively.

[0049] For analog information transmitted by sensors, such as transformer temperature information, transformer oil temperature sensor outputs 4-20mA current signal or 0-5V voltage signal which is linearly related to oil temperature, this analog signal is converted into digital signal by analog-to-digital conversion circuit; at the same time, the switch quantity signal collected by the plug-in is directly transmitted in the form of digital level. The digital signal converted from the sensor and the switch quantity signal of the plug-in are transmitted to the CPU plug-in together. The CPU plug-in analyzes, integrates and processes these non-electrical quantity signals according to the preset program logic, and finally outputs non-electrical quantity parameter signals such as transformer oil temperature value, SF6 gas pressure value, equipment switch status, etc., to provide data support for subsequent power grid monitoring and fault identification.

[0050] (II) Electrical fault alarm module

[0051] The electrical fault alarm module has built a complete and sophisticated electrical quantity abnormality alarm mechanism. Its core lies in setting strict thresholds and logical judgment criteria for various electrical quantity parameters, covering the core electrical quantity indicators of power grid operation.

[0052] 1. Differential quick-break alarm protection, according to key parameters such as power grid equipment capacity and short-circuit impedance, combined with past experience of experts, sets a reasonable differential current quick-break threshold; compares the measured differential current with this threshold, and performs AND operation on the differential quick-break protection input at the same time, so that when the measured differential current exceeds the differential current quick-break threshold, the system immediately triggers the differential quick-break alarm and executes the protection tripping action, ensuring a millisecond-level rapid response to severe internal short-circuit faults, and effectively preventing the fault scope from expanding.

[0053] 2. Ratio differential alarm protection is based on the principle of second harmonic braking ratio differential. Through dynamic correlation analysis of differential current and braking current, the action boundary under different operating conditions is accurately defined. When the ratio of differential current to braking current exceeds the preset curve boundary, the system quickly issues a ratio differential alarm to accurately identify hidden faults such as minor inter-turn short circuits and ground short circuits inside transformers, lines and other equipment, and ensure the safe and stable operation of the equipment. Specifically, it involves a variety of situations, including: when the differential current is greater than the differential protection action setting value, and the braking current is less than the braking current setting value, and the ratio of the two is greater than the proportional braking coefficient setting value, an alarm operation is performed; the CT line break alarm is activated and the CT line break duration exceeds 400ms to trigger the system protection alarm action; when any phase differential current is in the differential action area, the CT line break lockout differential protection is not activated, the CT line break alarm is activated, and the ratio of the second harmonic current of any phase differential current to the differential current is greater than the harmonic coefficient, the same alarm is issued and the protection tripping operation is performed.

[0054] 3. At the overcurrent protection level, for the first, second and third stage overcurrent alarm protection, full consideration is given to the line thermal stability limit, the coordination margin of the upper and lower protections and the load fluctuation characteristics, and multi-stage overcurrent thresholds and corresponding action delays are set respectively. The first stage overcurrent is used as a quick-break protection, and the threshold setting is generally much higher than the rated current, which is several times to dozens of times the rated current of the line. The action delay is extremely short, generally set to 0 seconds or only tens of milliseconds, and is mainly used to quickly cut off serious short-circuit faults at the near end; the second stage overcurrent threshold is moderate, and the delay is set between 0.3s-0.5s to protect most areas of the entire length of the line from faults; the third stage overcurrent is used as a backup protection, and the threshold is slightly higher than the rated current, and the delay is set to 1s, to ensure that in extremely complex fault scenarios, such as when the upper protection refuses to operate or the fault is not completely removed, it can still reliably protect the line and equipment to prevent overload damage.

[0055] 4. Overload alarm protection: when the protection current of any phase is greater than the overload protection current setting and the overload protection is activated, the system will execute the protection alarm action after the load time limit delay. This protection is aimed at the short-term overload condition of the transformer to prevent overheating damage.

[0056] 5. PT line break alarm protection. When the PT line break control word is activated, and the positive sequence voltage is less than 6V and the protection current of any phase is less than 0.5A or the negative sequence voltage is greater than 6V, the system executes the protection alarm action after the state lasts for 3s. This protection monitors the abnormal voltage of the secondary circuit to ensure accurate voltage measurement and reliable protection function.

[0057] 6. Overvoltage alarm protection: when the voltage of any line is greater than the overvoltage protection voltage setting and the overvoltage protection is activated, after the voltage protection time limit delay, the system executes the protection tripping action and sends out a protection alarm signal. This protection prevents the transformer from overvoltage shock caused by grid voltage fluctuations and prevents insulation damage.

[0058] 7. Undervoltage alarm protection: when the voltage of any line is lower than the undervoltage protection voltage setting value and the undervoltage protection is activated and the switch position is in the closed position, after the undervoltage protection time limit delay, the system executes the protection tripping action and sends out a protection alarm signal. This protection prevents the grid voltage from being too low and affecting the normal operation of the transformer and load, and prevents equipment abnormalities.

[0059] 8. CT line break protection. When the CT line break protection is activated, if the current of one phase suddenly changes to less than 0.2A, and the other five phases have no sudden change and are greater than 0.3A for 0.5S, the system will execute the protection alarm action. This protection monitoring circuit current is abnormal, ensuring that the current sampling of the protection device is accurate and the action is reliable.

[0060] 9. Single-phase grounding alarm protection, the zero-sequence voltage is greater than the single-phase grounding protection zero-sequence voltage setting and the single-phase grounding protection is activated. After the single-phase grounding time limit delay, the system executes the protection alarm action. This protection detects single-phase grounding faults in the three-phase four-wire connection mode on the low-voltage side to prevent the fault from expanding.

[0061] 10. Negative sequence current alarm protection, the negative sequence current is greater than the negative sequence first stage protection current setting and the negative sequence first stage protection is put into operation. After the negative sequence first stage protection time limit value delay, the system executes the protection alarm action; the negative sequence current is greater than the negative sequence second stage protection current setting and the negative sequence second stage protection is put into operation. After the negative sequence second stage protection time limit value delay, the system executes the protection tripping action. The negative sequence current is calculated based on the high-voltage side phase current, for the transformer non-grounding asymmetric fault.

[0062] This module formulates strict judgment logic and threshold standards for many abnormal situations of key electrical quantities based on the grid operation procedures, equipment tolerance and a large amount of actual operation experience data. Once the electrical quantity parameters deviate from the normal operating range and touch the alarm threshold or violate the preset logic rules, the module immediately and accurately triggers the corresponding alarm signal, and informs the operation and maintenance personnel of the hidden dangers of the grid fault in a timely manner through multiple methods such as sound and light alarms and uploading alarm information through communication interfaces, so as to save every minute for fault investigation and repair, and greatly reduce the risk of power outage losses and equipment damage caused by the fault.

[0063] (III) Non-electrical quantity fault alarm module

[0064] The non-electrical quantity fault alarm module realizes precise function control and intelligent fault alarm based on preset control words. The preset control words comprehensively control function activation and deactivation, output delay and trip alarm status selection.

[0065] In terms of function activation and deactivation control, operation and maintenance personnel can flexibly set control words through the communication module on the host computer interface or on-site debugging tools according to factors such as the operating conditions of power grid equipment, maintenance plans and seasonal characteristics, and selectively enable or disable specific non-electrical quantity protection functions. In actual operation, the heavy gas tripping function can be temporarily disabled during the no-load trial operation phase after the transformer is overhauled, and the light gas action alarm function can be turned on at the same time to closely monitor potential signs of minor faults inside the transformer to avoid false tripping interfering with the test process; after the transformer is officially put into operation and has been running stably for a certain period of time, the control word can be accurately switched according to the equipment status and power grid needs, and key protection functions such as heavy gas tripping can be restored to the normal operation state, so as to fully guarantee the safety and reliability of the transformer at different operation stages.

[0066] The export delay setting is optimized based on the characteristics of the equipment, the law of fault development, and the grid fault handling process. For non-urgent but timely attention-requiring fault types such as transformer high temperature alarms, a relatively moderate export delay of about 10-30S is set. This delay can not only give the equipment a buffer period for self-recovery in a short period of time or for the operation and maintenance personnel to confirm the fault on site, avoiding false alarms caused by instantaneous interference factors; it can also ensure that when the temperature of the equipment continues to rise abnormally and the fault situation intensifies, an alarm signal is issued in time, leaving sufficient time for the operation and maintenance personnel to take countermeasures such as checking the cooling system and adjusting the load distribution. For emergency and serious fault scenarios such as transformer ultra-high temperature tripping, the export delay is strictly controlled within a very short time to ensure that the system quickly cuts off the power supply at the critical moment when the equipment is about to suffer irreversible damage, and preserves the overall equipment asset safety of the power grid at the expense of sacrificing local power supply, and prevents catastrophic accident chain reactions.

[0067] At the same time, the tripping alarm status selection provides the system with multiple flexible configuration modes. According to the importance classification of power grid equipment, fault consequence assessment and operation and maintenance strategy differences, operation and maintenance personnel can accurately set certain non-electrical quantity abnormalities to alarm-only mode, which is convenient for continuous monitoring of fault development trends and arranging planned inspections and maintenance at appropriate times; for fault situations that seriously endanger the safety of equipment and power grids, including heavy gas action, ultra-high temperature action, etc., it is configured as tripping + alarm mode to ensure that the fault trips instantly to isolate the faulty equipment. At the same time, detailed alarm information is sent to the operation and maintenance monitoring center to assist in rapid fault location and emergency repair and restoration operations, minimize the duration of power outages, reduce the scope of power outages, enhance the power grid's fault response and self-healing capabilities, and ensure the achievement of power supply continuity and reliability indicators.

[0068] In terms of specific alarm actions, for a series of typical non-electrical quantity abnormal conditions such as heavy gas action tripping, light gas action alarm, SF6 gas pressure abnormal alarm, transformer high temperature alarm, transformer ultra-high temperature tripping, transformer low oil level alarm, etc., this module builds accurate and reliable judgment logic based on various sensor feedback signals, equipment physical characteristics and operating experience threshold standards, including but not limited to: For heavy gas protection, based on the gas generation rate, gas accumulation and oil flow surge characteristics of the internal fault of the transformer, real-time monitoring is carried out through high-precision gas detection and oil flow sensing elements installed in the gas relay. When the gas volume or oil flow rate exceeds the preset serious fault threshold, the trip command is triggered immediately; for the light gas action alarm, when a trace amount of gas is detected (such as a small amount of gas escaped due to slow aging and decomposition of insulating paper) and the heavy gas action conditions have not yet been reached, an early warning signal is issued in time to remind the operation and maintenance personnel to pay attention to the potential health hazards of the equipment, provide key decision-making basis for the formulation and implementation of preventive maintenance strategies, and optimize the balance between the operation and maintenance cost and efficiency of the equipment throughout its life cycle.

[0069] (IV) Fault Identification Module

[0070] This module proposes a new fault identification data model, which analyzes the grid parameters when a fault occurs and identifies the fault type. The improved data model specifically includes:

[0071] 1. Define parameter attribute set and membership function

[0072] For key fault parameters, a scientific and reasonable parameter attribute set and membership function system are constructed based on a large amount of historical fault data statistical analysis, equipment fault physical model research and field operation experience accumulation. When analyzing line short-circuit faults, this system divides the short-circuit current amplitude into three parameter attributes: "high", "medium" and "low", and establishes parameter attribute sets for these three parameter attributes. Furthermore, the membership function adopts a triangular function form to accurately determine the function parameters based on the line rated current, short-circuit current calculation boundary and current characteristics of different short-circuit types. For some 10kV lines, if the three-phase short-circuit current amplitude exceeds 5kA, it is defined as a "high" parameter attribute set with a membership of 1. In the 2-5kA range, the membership increases linearly from 0 to 1 and belongs to the "medium" parameter attribute set. If it is less than 2kA, the membership decreases linearly from 1 to 0 and is included in the "low" parameter attribute set. The function is specifically expressed as:

[0073] The small current membership function is:

[0074]

[0075] The current membership function is:

[0076]

[0077] The high current membership function is:

[0078]

[0079] Among them, I is the input current, I1 is the current near 2kA and slightly less than 2kA, I2 is the current near 2kA and slightly greater than 2kA, I3 is the intermediate current of 2-5kA, I4 is the current near 5kA and slightly greater than 5kA, and I5 is the current near 5kA and slightly less than 5kA. The specific parameters have a certain overlap in the three parameter attribute sets. Compared with the simple threshold method, this method of dividing parameters is more accurate and intelligent. It is more meticulous when processing critical data, reducing the risk of misjudgment and missed judgment.

[0080] By analogy, exclusive parameter data sets and membership functions are constructed for key parameters such as voltage drop amplitude, power fluctuation, fault duration, etc. according to their physical meaning and fault diagnosis importance, and the cross-boundaries and degree change laws of fault characteristic parameters are adjusted, laying a solid foundation for subsequent intelligent reasoning and calculation.

[0081] 2. Calculate the membership value of the input variable

[0082] At the moment of power grid fault, the real-time collected electrical and non-electrical data are input into the system as input variables. According to the predefined membership function, the membership value of each input variable relative to different parameter data sets is accurately calculated point by point through linear interpolation. When the measured short-circuit current of the line is 3.5kA at a certain moment, according to the above short-circuit current membership function, its membership in the "medium" parameter data set is about 1, and the membership in the "high" and "low" parameter data sets is close to 0. The same calculation process is performed synchronously for other input variables such as voltage and power to obtain the complete membership value distribution vector of each variable, providing a multi-dimensional quantitative indicator system for comprehensive and integrated evaluation of the fault status, effectively mining the deep implicit fault feature information in the data, overcoming the defects of traditional binary logic judgment that easily misses and misjudges the details of fault features, and improving the integrity and accuracy of fault diagnosis information.

[0083] 3. Build a rule base

[0084] In-depth analysis of the fault mechanism of the power grid, starting from the multi-dimensional interaction of circuit theory, equipment structure characteristics, electromagnetic transient process and operating conditions, excavating the causal correlation logic between fault parameter changes and fault types, further integrating the fault case diagnosis experience, expert knowledge and simulation test results in long-term on-site operation and maintenance practice, and building a rule base with rich content and rigorous logic. Including but not limited to: if the short-circuit current amplitude membership is "high", the voltage drop amplitude membership is "high" and the fault duration membership is "short", it is judged as a metallic three-phase short-circuit fault near the line; when the transformer oil temperature membership is "high", the oil level membership is "low" and the light gas alarm signal is triggered, it is judged that the transformer is overheated internally with slight insulation damage and gas accumulation. The rule base is composed of many such rule statements to form a complete knowledge base, presented in the "IF-THEN" logic paradigm, covering common fault scenarios and complex fault combination modes of various types of power grid equipment, providing accurate and reliable knowledge rule support for fault reasoning, and ensuring the scientificity and authority of the diagnosis decision-making process.

[0085] 4. Fault type identification

[0086] Based on the calculated input variable membership value and the rule base, the fault type is identified. The system uses the Mamdani reasoning method to traverse the membership of the input variable in order through each rule in the rule base. For the current rule, the minimum membership value of the input variable in the corresponding rule premise condition is first taken as the rule activation strength; then, according to the fault type data set defined by the rule epigenetic event, the epigenetic event data set is filtered with the activation strength as the weight to generate an intermediate result set; after traversing all rules and completing the above operations, the fault types in the intermediate result set are sorted, and the fault types are output from small to large according to the rule strength. This order can be regarded as the correlation coefficient with the fault cause from small to large. The output results are combined with the location and specific type, such as accurately determining the specific fault types such as the line A phase single-phase grounding short circuit fault, bus B phase short circuit fault or a certain transformer internal winding short circuit fault, which provides a precise and targeted basis for the subsequent fault isolation, repair and power grid restoration strategy formulation, significantly improving the accuracy of fault diagnosis and decision-making efficiency, and reducing the risk of misjudgment and missed judgment.

[0087] (V) Communication module

[0088] 1. Data collection and integration

[0089] like Figure 2The communication module collects various types of data processed by the information acquisition system and builds a panoramic data of the power grid operation status. The electrical quantity signal includes the real-time monitoring values ​​of voltage and current, as well as the derived key parameters such as frequency, power factor, active power, reactive power, etc. obtained through complex calculations by the information acquisition system. These electrical quantity data are derived from monitoring points at all levels of the power grid, and are gathered here after strict collection, conversion and calculation processes, fully presenting the power quality, power flow distribution and dynamic change characteristics of the load of the power grid.

[0090] At the level of non-electrical quantity signals, the switch signals collected by the plug-in record the instant of mechanical state change of the power grid equipment, such as discrete events such as the opening and closing action of the circuit breaker and the change of the switch switching state. The level jump edge accurately marks the moment of equipment state conversion, providing key clues for dynamic perception of the power grid topology and fault event location. The physical information collected by the sensor deeply reflects the internal operating conditions of the power grid equipment. From multi-dimensional physical quantity data such as transformer oil temperature, winding temperature gradient changes, SF6 insulating gas pressure changes, and equipment casing vibration amplitude spectrum characteristics, it monitors the health status of the equipment in an all-round and real-time manner, laying a solid foundation for early warning of potential fault hazards.

[0091] Similarly, the collection of the system's own protection and operating status information is also indispensable. The protection action parameters record in detail the start-up time and action type of each protection device, including: differential protection action, overcurrent protection action and its corresponding action threshold, action time series and other key elements, to provide first-hand and accurate information for analyzing the nature of the fault and evaluating the performance and reliability of the protection device; the system plug-in operation status data real-time feedback of various functional plug-ins such as CPU plug-in, analog-to-digital conversion plug-in, communication plug-in, etc., working voltage, temperature, data transmission bit error rate and other core indicators to ensure that the health of the system hardware is fully transparent and monitorable; when the system is running abnormally, the fault type information output by the fault alarm module is used as the key carrier of the system fault diagnosis decision result, which is uploaded at high speed through the communication module and seamlessly connected to the fault handling process of the power grid monitoring center, driving the operation and maintenance team to accurately and efficiently formulate and execute emergency response strategies, ensuring that power grid faults are quickly isolated and repaired, and stable operation order is quickly restored.

[0092] 2. Human-machine interface design

[0093] The carefully crafted human-machine interface of the communication module, as the core hub for interaction between the system and the user, creates a simple, intuitive, powerful and easy-to-use user control interface. The interface layout adheres to the principle of information stratification and grading, and highlights the key points. It is based on visual graphic elements, supplemented by simple text label annotations, to ensure that users can quickly locate key information in the complex power grid data maze and accurately grasp the core pulse of the power grid operation situation.

[0094] The operating logic is deeply optimized, following the user's natural operating habits and cognitive psychological models, and widely adopts one-click quick operation, intelligent interaction guidance and multi-channel interactive collaborative design strategies, which greatly reduces the user's operation complexity and learning cost, allowing users to focus on core operation and maintenance tasks, comprehensively improving operational efficiency and experience fluency, reducing the risk of human error operations, and safeguarding the safe operation and maintenance of the power grid.

[0095] 3. Communication protocol support and network connection

[0096] With its powerful software protocol stack and hardware adaptation capabilities, the communication module is fully compatible with international general power industry communication standard protocols and private customized protocols such as IEC60870-5-101, IEC60870-5-104, Modbus, CDT, 9702, etc., seamlessly connecting the data interaction needs between equipment from different manufacturers and heterogeneous systems, breaking down the barriers of information islands, and building a unified integrated power grid monitoring ecosystem.

[0097] In terms of network connection architecture, the module is compatible with multiple network communication media and topological structures such as industrial Ethernet, fiber optic ring network, and wireless private network, and can be flexibly networked according to the scale of the power grid, geographical distribution, and communication reliability requirements. In the substation, the station communication backbone network is built based on high-bandwidth, low-latency industrial Ethernet to achieve high-density data and high-speed real-time interactive sharing of equipment in the station; in the wide area, the regional communication trunk line of the power grid is built with the help of the fiber optic ring network to ensure the long-distance and reliable transmission of cross-station and cross-regional power grid operation data; in remote and scattered distribution substations or mobile operation and maintenance scenarios, 4G / 5G wireless private networks are introduced to achieve flexible equipment access and remote monitoring and management, expand the breadth and depth of power grid communication coverage, and build a solid communication infrastructure support for the all-round, all-time and space data interconnection and interoperability of the intelligent operation and maintenance of the power grid, ensure real-time perception of the power grid status, reliable issuance of precise control instructions, and improve the intelligent and refined level of power grid operation and management.

[0098] (VI) Fault recording module

[0099] The startup mechanism of the fault recording module is closely designed around the abnormal state of key electrical quantities in the power grid. The overcurrent startup is based on the rated current parameters and overload capacity characteristics of the line or equipment, and multiple overcurrent thresholds are set in layers and grades (such as 1.2 times the rated current for light overload, 1.5 times the rated current for moderate overload, and more than 5 times the rated current for severe short-circuit faults) and corresponding action delay logic (a few seconds delay for light overload and instant startup for short-circuit faults) to ensure accurate capture of the fault spectrum from short-term current shocks to continuous overloads to severe short-circuit full current overloads; the undervoltage startup is based on the power grid voltage level and the allowable voltage fluctuation range specifications, combined with The undervoltage tolerance characteristics of the equipment set multi-stage voltage drop amplitude thresholds (such as 80% rated voltage mild voltage loss alarm, 60% rated voltage moderate voltage loss start recording, 30% rated voltage severe voltage loss emergency handling) and duration judgment conditions to sensitively respond to grid voltage fluctuation fault events; the differential trip start deeply integrates the transformer and line differential protection principles and fault characteristics, and uses the differential current calculation value breaking through the action threshold and the protection device output trip signal as the triggering double insurance mechanism, accurately recording the panoramic waveform of the electrical quantity mutation at the moment of differential protection action, providing key clues for analyzing the root cause of the internal short-circuit fault of the equipment.

[0100] At the moment of module startup, high-density sampling of fault-related electrical quantities is carried out at a high sampling frequency. The sampling frequency is dynamically adjustable according to the performance of the fault recording device and the needs of power grid fault analysis, and comprehensively covers the three-phase voltage and current instantaneous value, effective value, phase information, and zero-sequence current, negative-sequence current components and other key derived electrical quantity data of the fault line or equipment. Through high-precision analog-to-digital conversion and large-capacity data caching technology, the continuous dynamic change trajectory of electrical quantities from a few cycles before the fault occurs to the stable operation period after the fault is cleared is recorded to form a complete fault electrical quantity waveform data set, and its data accuracy can reach microsecond time resolution and amplitude resolution of more than one thousandth of the rated value, providing a massive, high-precision, and high-fidelity original data treasure house for post-fault in-depth analysis, accurate location of accident causes, protection device action performance evaluation, and power grid operation optimization strategy formulation.

[0101] 3. Overall workflow of the system

[0102] like Figure 1 The power grid visualization diagnosis method based on multi-source data fusion proposed in the present invention includes four stages: information collection stage, fault alarm stage, fault identification stage and fault recording stage.

[0103] (I) Information Collection Stage

[0104] After the system is powered on and initialized, the information acquisition module immediately enters the full-time and full-domain monitoring state, and synchronously drives the electrical quantity acquisition and non-electrical quantity acquisition sub-processes to run in high-speed parallel operation. At the electrical quantity acquisition end, PT and CT capture the original signals of grid voltage and current in real time, and output accurate electrical quantity parameter signals through signal conditioning, analog-to-digital conversion, and CPU processing pipeline operations; in the non-electrical quantity acquisition sub-process, sensors and plug-ins work together, and sensors digitize analog signals of physical quantities such as oil temperature, air pressure, and liquid level, and plug-ins directly collect switch quantity signals. The two converge to generate non-electrical parameter signals through CPU plug-in calculations. The two types of data are updated in real time with millisecond-level synchronization accuracy, building an instantaneous holographic data snapshot of the grid operation status, injecting high-timeliness and high-precision data kinetic energy into the subsequent fault diagnosis process, and laying the foundation for accurate diagnosis of the system.

[0105] (II) Fault Alarm Stage

[0106] The electrical fault alarm module and the non-electrical fault alarm module subscribe to the data update events of the information collection module in real time, and deeply analyze and judge the electrical and non-electrical quantity signals according to the preset logic with a sub-second response speed. Once the electrical quantity signal exceeds the thresholds of differential quick break, overcurrent, overvoltage, etc. or violates the complex logic rules (such as excessive zero-sequence current imbalance, sudden change of power factor), the electrical fault alarm module immediately triggers the sound and light alarm, and the communication interface uploads the alarm event package, which contains key information such as the fault type, occurrence time, and electrical quantity parameter extreme value; the non-electrical quantity signal deviates from the normal range to trigger the non-electrical fault alarm module alarm, such as the transformer gas relay light gas action, SF6 gas pressure low limit alarm, and determines only the alarm or tripping action according to the preset control word, and reports the abnormal details of the non-electrical quantity to the monitoring system at the same time, so as to ensure that the fault information is transmitted to the operation and maintenance monitoring terminal without delay and omission with the double alarm mechanism, and activate the operation and maintenance emergency response plan.

[0107] (III) Fault identification stage

[0108] The fault identification module is activated instantly when the fault alarm is triggered. The module uses real-time data of electrical and non-electrical quantities as input to drive the core process of the fault identification model to run at high speed. First, the fault parameter characteristics such as short-circuit current amplitude, voltage drop depth, and abnormal increase in equipment temperature are accurately quantified according to the membership function of the predefined parameter attribute set; then the rule base is searched, and the fault characteristics and rules are efficiently matched by the Mamdani reasoning method. After the rule strength calculation, the fault type is output in sequence; finally, the diagnosis results are pushed to the communication module and distributed to the upper computer monitoring system in multiple channels, providing key decision-making basis for the operation and maintenance team to formulate repair strategies, realizing a leap from fault phenomenon monitoring to accurate judgment of the nature of the fault, improving the timeliness and accuracy of fault handling, and reducing the duration and loss of power outages caused by power grid faults.

[0109] (IV) Fault recording stage

[0110] The fault recording module is started at the moment of fault electrical quantity determination, and is accurately triggered according to the starting conditions such as overcurrent, loss of voltage, and differential tripping. The sampling frequency is instantly increased to sample the fault electrical quantity in a panoramic and high-density manner. Tracing back from the baseline of the steady-state electrical quantity of the power grid before the fault, the electrical quantity waveform of the entire process from the transient state of the fault impact, the continuous process of the fault to the dynamic recovery of the power grid after the fault is removed is completely captured, forming a high-fidelity electrical quantity data archive that deeply covers the entire life cycle of the fault. The data is stored in a local large-capacity storage medium in a standard format, and is uploaded to the monitoring center in real time through the communication module, providing irreplaceable data support for fault backtracking analysis, protection action verification, and power grid planning and design optimization, helping to improve the power grid's fault defense and operation optimization capabilities, and safeguarding the long-term reliable operation of the power grid.

Claims

1. A power grid visualization diagnosis system based on multi-source data fusion, characterized in that: It includes the following parts: information collection module, electrical fault alarm module, non-electrical fault alarm module, fault identification module, communication module, fault recording module; The information collection module collects electrical quantities and non-electrical quantities. 1) Electrical quantity collection: The information collection module collects the voltage and current signals in the power grid in real time, converts the signals into weak current signals through the AC plug-in, and outputs electrical quantity signals after being processed by the CPU inside the module; 2) Non-electrical quantity collection: The information collection module collects the physical information collected by each sensor and plug-in in the system in real time, and outputs non-electrical quantity signals after being processed by the CPU inside the module; The electrical fault alarm module receives the electrical quantity signal output by the information acquisition module and judges the electrical quantity through a preset logic, and issues an alarm when an abnormality occurs; The non-electrical fault alarm module receives the non-electrical quantity signal output by the information acquisition module and makes a judgment according to the preset control word and preset logic, and issues an alarm when an abnormality occurs; When an alarm occurs, the fault identification module receives fault information, identifies the fault type, and outputs the fault type; The communication module exchanges information in the system with the power grid monitoring system in real time and displays it visually through the human-machine interface and the power grid monitoring system; The fault recording module records the fault electrical quantity data after the electrical quantity is abnormal and is determined to be a fault.

2. A power grid visualization diagnosis system based on multi-source data fusion according to claim 1, characterized in that: The information collection module collects electrical quantities and non-electrical quantities of the monitored power grid; The electrical quantity information is collected by receiving the original analog signal of the monitoring point through the measuring device and converting it into a low-current and low-voltage AC signal. The measuring device includes a voltage transformer and a current transformer, and then converting it into a unidirectional sinusoidal signal through a signal conditioning circuit. The analog-to-digital conversion module collects the electrical signal output from the signal conditioning circuit in real time, and performs analog-to-digital conversion to output the electrical signal to the CPU plug-in. The CPU plug-in processes the electrical signal according to a preset logic and outputs an electrical quantity parameter signal. The electrical quantity signal includes voltage, current, and frequency, power factor, active power, reactive power signal, differential current, zero-sequence current, and negative-sequence current obtained after calculation and processing by the information collection system; The electrical quantity information is collected by receiving the physical information collected by the sensor and the plug-in, and then the analog information received in the sensor is converted into a digital signal through the analog-to-digital conversion module, and the digital signal and the signal received from the plug-in are transmitted to the CPU plug-in. After processing, the non-electrical parameter signal is output, and the non-electrical quantity signal includes transformer temperature, oil level, gas concentration and transformer internal air pressure.

3. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The electrical fault alarm module warns of various electrical quantity abnormalities, including but not limited to differential quick-break alarm protection, ratio differential alarm protection, differential current excessive alarm protection, overcurrent one stage, overcurrent two stage, overcurrent three stage alarm protection, overload protection function PT line break alarm protection, overvoltage alarm protection, undervoltage alarm protection, CT line break alarm, single-phase grounding alarm, zero-sequence current alarm protection, and negative-sequence current alarm protection.

4. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The non-electrical quantity fault alarm module controls the function activation and deactivation, control output delay and trip alarm status selection according to the preset control word; and provides alarm protection for various non-electrical quantity abnormalities, including but not limited to heavy gas action tripping, light gas action alarm, SF6 gas pressure abnormality alarm, transformer high temperature alarm, transformer ultra-high temperature tripping, and transformer low oil level alarm.

5. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The fault identification module analyzes and identifies the fault information through the fault identification data model. The specific steps are as follows: 1) Define parameter attribute sets and membership functions for input parameters; 2) Calculate the membership value of the input variable; 3) Build a rule base based on the failure mechanism; 4) Fault type identification; 5) Output fault type.

6. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The communication module is connected to each module in the system to collect information, and collects digital signals processed by the information collection system. The electrical quantity information in the digital signal includes voltage, current, and frequency, power factor, active power, reactive power, differential current, zero-sequence current, and negative-sequence current information obtained after calculation and processing by the information collection system; Non-electrical quantity signals include switch quantity signals collected by plug-ins and physical information collected by sensors; And collect the operating status information of the electrical fault alarm module, non-electrical fault alarm module and fault identification module, including the parameters of the protection action, the operating status of the system's own plug-in and the fault type output by the fault alarm module when the system operates abnormally.

7. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The communication module is provided with a human-machine interface, and a control user interface is provided through the human-machine interface; and The communication module supports multiple communication protocols, including IEC60870-5-101, IEC60870-5-104, Modbus, CDT, 9702 and private protocols, and is connected to the power station monitoring system through network transmission to complete the functions of sending system information and receiving external commands.

8. The power grid visualization diagnosis system based on multi-source data fusion according to claim 1 is characterized in that: The starting conditions of the fault recording module include overcurrent start, undervoltage start, and differential trip start. When these starting conditions are met, the device records the corresponding electrical quantities and records the changes in the power grid system parameters in the period before and after the fault occurs, which is convenient for fault analysis and accident recall.

9. A visual diagnosis method for a power grid based on multi-source data fusion, the method using the visual diagnosis method for a power grid according to any one of claims 1 to 8, characterized in that: The steps include: 1) In the information collection stage, the system monitors the power system to collect electrical and non-electrical quantity signals, and processes the signals into digital signals, which are then processed by the CPU plug-in; 2) In the fault alarm stage, the electrical fault alarm module and the non-electrical fault alarm module receive the information output by the information acquisition module, and perform corresponding alarm protection or tripping protection operations when an abnormality occurs through preset control words and logic; 3) Fault identification stage: after a fault alarm occurs, the fault information is input into the fault identification module. The fault parameters are calculated for membership through the fault identification data model. Combined with the preset rule base, the possible field faults are determined. The correlation between the fault parameters and the field faults is sorted and output according to the rule strength. 4) During the fault recording stage, when a fault occurs and the overcurrent start, undervoltage start, and differential trip start conditions are met, the fault recording module records the changes in the grid system parameters monitored by the system before and after the fault occurs.

Images