An Adaptive Cooperative Transmission Line Fault Monitoring System

Abstract

The present invention discloses an adaptive collaborative power transmission line fault monitoring system, which relates to the technical field of power grid fault monitoring. Compared with the previous power transmission line fault monitoring systems, the present invention solves the problems that the information provided by a single sensor is limited; the traditional monitoring system lacks the ability of adaptive adjustment; and the coordination among different monitoring devices and functional modules is poor. By integrating the data collected by multiple sensors through a sensor network and using intelligent diagnostic algorithms for fusion analysis, the diagnostic accuracy can be greatly improved. The system has the ability of adaptive adjustment, can optimize the monitoring strategy in real time according to the development trend of faults, can adaptively adjust the sensor sampling frequency according to the real-time operating state of the line and the fault risk, can dynamically allocate monitoring resources and intelligently transfer the monitoring focus according to factors such as the aging degree of the line, the geographical environment, and the historical fault distribution, and the modules of the system cooperate with each other and adapt to each other, which can reduce misjudgment and missed judgment and improve the overall stability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault monitoring, and particularly to an adaptive collaborative transmission line fault monitoring system. Background Art

[0002] With the rapid development of the economy, the demand for electricity continues to climb. As a key infrastructure for power transmission, the stable operation of transmission lines is crucial for ensuring the normal order of social production and life. Traditional means of monitoring transmission line faults have gradually revealed many limitations when faced with an increasingly complex operating environment and growing reliability requirements, which provides an opportunity for the birth of an adaptive collaborative transmission line fault monitoring system.

[0003] In the early days, the fault monitoring of transmission lines mainly relied on manual inspections. With the progress of technology, sensor-based monitoring technologies began to be applied. A single type of sensor was installed on the transmission line, such as only monitoring the change of line current through a current sensor to judge faults. However, the types of transmission line faults are complex and diverse, including short-circuit faults, open-circuit faults, grounding faults, insulator flashovers, etc. The information provided by a single sensor is limited and often can only reflect abnormalities in one aspect, unable to diagnose faults comprehensively and accurately. For example, when a fault caused by local overheating occurs in the line, it may not be detected only by a current sensor because the current change may not be significant, and the collaborative monitoring of a temperature sensor is required to accurately locate the problem.

[0004] Traditional monitoring systems lack the ability of adaptive adjustment. Whether it is the sampling frequency of sensors or the key monitoring areas, they are usually set fixedly. It is obviously unreasonable to adopt the same monitoring strategy under normal operating conditions and special working conditions such as bad weather and high load. For example, in stormy weather, the line is affected by factors such as wind and rain erosion, and the probability of faults increases significantly. If the conventional low sampling frequency is still maintained at this time, some key fault precursor information may be missed; similarly, during the long-term stable operation period of the transmission line, continuously maintaining a high sampling frequency will cause energy waste and data redundancy, increasing the system operation and maintenance costs.

[0005] The coordination between different monitoring devices and functional modules is poor. After the data collected by sensors is transmitted to the background, the data analysis, fault diagnosis and other links work independently and do not fully share information and work collaboratively. This easily leads to inaccurate diagnosis results, and misjudgments and missed judgments often occur. Take a simple example. When the current sensor detects abnormal current fluctuations, if it does not perform real-time collaborative analysis with voltage sensors and temperature sensors and only judges faults based on the single current information, it is very likely to draw an incorrect diagnosis conclusion and delay the emergency repair time.

[0006] To solve the above problems, the present invention proposes an adaptive collaborative transmission line fault monitoring system. Summary of the Invention

[0007] The purpose of the present invention is to propose an adaptive collaborative power transmission line fault monitoring system to solve the problems raised in the background technology:

[0008] The information provided by a single sensor is limited; traditional monitoring systems lack the ability of adaptive adjustment; the coordination between different monitoring devices and functional modules is poor.

[0009] To achieve the above object, the present invention adopts the following technical solutions:

[0010] An adaptive collaborative power transmission line fault monitoring system, comprising:

[0011] Network construction module: used to build a sensor network for the power transmission line based on several types of sensors;

[0012] Data acquisition and transmission module: used to acquire data based on the sensor network and perform transmission;

[0013] The data acquisition and transmission module includes:

[0014] Data acquisition unit: used to collect the original data monitored by each sensor, and convert the analog signal into digital monitoring data through an edge device;

[0015] Data transmission unit: used to transmit the acquired digital monitoring data to the background control center through a combination of several communication methods;

[0016] Analysis and processing module: used to receive the data transmitted by the data communication module, and perform preprocessing and fault diagnosis on the data;

[0017] The analysis and processing module includes:

[0018] Data preprocessing unit: used to perform denoising and normalization preprocessing on the received digital monitoring data;

[0019] Feature extraction unit: used to extract the operation state and environmental conditions of the power transmission line from the preprocessed data;

[0020] Fault diagnosis unit: used to perform fault diagnosis on the power transmission line based on the extracted operation state of the power transmission line and based on an intelligent diagnosis algorithm, and obtain a fault diagnosis result and the severity of the fault;

[0021] Adaptive collaborative control module: used to dynamically control the collaborative work between sensors and different functional modules based on an adaptive adjustment mechanism according to the real-time operation state, environmental conditions, fault diagnosis results and severity of the fault of the power transmission line.

[0022] Preferably, the sensor network consists of a number of current sensors, voltage sensors, temperature sensors, humidity sensors, vibration sensors, wind speed sensors, wind direction sensors, tower inclination sensors, and insulator leakage current sensors.

[0023] Preferably, the operating states of the transmission line extracted by the feature extraction unit include the amplitude, peak value, and period corresponding to the current signal collected by the current sensor; the amplitude, peak value, and period corresponding to the voltage signal collected by the voltage sensor; the temperature change trend and temperature change gradient of the transmission line temperature data collected by the temperature sensor; the acceleration, velocity, displacement, and frequency of the transmission line vibration signal collected by the vibration sensor; the lateral inclination angle and longitudinal inclination angle of the tower collected by the tower inclination sensor, and the insulator leakage current collected by the insulator leakage current sensor; the environmental conditions include the ambient temperature collected by the temperature sensor, the ambient humidity collected by the humidity sensor, the wind speed collected by the wind speed sensor, and the wind direction angle collected by the wind direction sensor.

[0024] Preferably, the intelligent diagnosis algorithm is as follows:

[0025] Define a fuzzy set F for each operating state, and define a membership function μ F (x) for each fuzzy set F. The membership function μ F (x) is as follows:

[0026]

[0027] where x is the operating state in the fuzzy set F, x0 and x1 are membership function parameters. When μ F (x) ≥ A, it is determined that a fault has occurred, where A is a preset fault threshold;

[0028] Substitute the operating state into the membership function to calculate the membership degree of each operating state belonging to each fuzzy set, and obtain the membership degree matrix

[0029] Construct a fuzzy rule base consisting of preconditions and fault conclusions based on historical fault data and expert experience;

[0030] According to the membership degree matrix Judge whether the preconditions of each rule in the fuzzy rule base are satisfied, that is, whether the membership degree of each fuzzy set reaches the preset membership degree threshold; if satisfied, trigger the fault conclusion corresponding to the fuzzy rule;

[0031] Determine each triggered rule R k corresponding fault subset F k , and calculate the basic probability assignment function m k according to the rule credibility c k; Specifically as follows:

[0032]

[0033] Assign corresponding probability values to other fault subsets in the fault set Θ that contain the fault subset F k , and the sum of the probability values of all fault subsets in the fault set Θ is 1;

[0034] Use the Dempster combination rule for fusion:

[0035] For two bodies of evidence m a and m b constituted by the basic probability assignment function, perform fusion to obtain the fused body of evidence m ab . For the basic probability assignment of the fault subset D corresponding to the fused body of evidence m [[ID=2i]] ab calculate as follows:

[0036]

[0037] [[ID=2B]]Where is the conflict coefficient, indicating the degree of conflict between the evidences; D is the fault subset corresponding to the fused body of evidence m ab ; B is the fault subset corresponding to the body of evidence m a ; C is the fault subset corresponding to the body of evidence m b ;

[0038] After several fusions, obtain the fused comprehensive body of evidence m final ;

[0039] Based on the fused comprehensive body of evidence m final calculate the belief function Bel(G) as follows:

[0040]

[0041] Where m final (H) is the basic probability assignment for the fault subset H in the fused body of evidence;

[0042] According to the maximum confidence criterion, select the fault subset with the largest belief function value as the diagnosis result:

[0043]

[0044] Where F diagmosis is the fault diagnosis result;

[0045] After determining the fault diagnosis result, through defuzzification operation, convert the fault diagnosis result into a fault diagnosis description, and input the fault diagnosis description into the adaptive cooperative control module.

[0046] Preferably, in the fault diagnosis unit, the fault severity is further divided according to the fault credibility through a trapezoidal membership function.

[0047] Preferably, the adaptive adjustment mechanism is specifically as follows:

[0048] Define the intelligent agent, and define the fault diagnosis unit containing the intelligent diagnosis algorithm as the intelligent agent;

[0049] defining a state space S, wherein a state vector s in the state space S includes an operating state of the transmission line, environmental conditions, a fault diagnosis result, and a fault severity;

[0050] Define the action space A, which contains the action vector a={a 11 ,Λ,a 1u ,Λ,a 1U , a 21 ,Λ,a 2v ,Λ,a 2V , a 31 ,Λ,a 3k ,Λ,a 3L};a 1u Corresponding sampling frequency proportional coefficient adjustment action; a 2v Corresponding sensor monitoring range adjustment action; a 3k Adjustment actions for computing and communication resources corresponding to the fault type;

[0051] The reward function R(s,a) is defined as follows:

[0052] R(s,a)=w1R accuracy (s,a)+w2R energy (s,a)+w3R response (s,a)

[0053] Among them, w1, w2 and w3 are weight coefficients; R accuracy (s,a) is the fault diagnosis accuracy reward; R energy (s,a) is the energy consumption reward; R response (s,a) is the fault response timeliness reward;

[0054]

[0055] Among them, k1 is the accuracy importance coefficient; p acc To take action a to make the next fault diagnosis accuracy; p acc0 is the fault accuracy rate before taking action a;

[0056]

[0057] Among them, k2 is the importance coefficient of energy consumption; E0 is the energy consumption before taking action a; E is the energy consumption after taking action a;

[0058]

[0059] Among them, k3 is the importance coefficient of timeliness; t d0 is the first fault detection time before taking action a; t d is the first fault detection time after taking action a;

[0060] Use the Q-learning algorithm to learn the optimal strategy, and initialize the Q-value function as a table. The rows of the table correspond to different environmental states, and the columns correspond to different actions;

[0061] Adopt the ε-greedy strategy to select actions:

[0062]

[0063] Among them, ε is the exploration rate; is the maximum Q-value corresponding to all possible actions in the environmental state s t ;

[0064] The agent executes the selected action a in the system t , and the system state transfers to the next state s according to the physical laws of line operation, environmental changes and the influence of actions t+1 , and at the same time, calculate and feedback the reward value R to the agent according to the reward function R(s,a) t ;

[0065] Based on the Q-learning algorithm update formula, use the newly obtained experience (s t ,a t ,R t ,s t+1 ) to update the Q-value:

[0066]

[0067] Among them: Q'(s t ,a t ) is the updated Q-value; Q(s t ,a t ) is the Q-value of taking action a t in the environmental state s t ; α is the learning rate; γ is the discount factor; a' is the optimal action among all possible actions in the next environmental state s t+1 ; is the next environmental state s t+1The maximum Q-value corresponding to all possible actions below, that is, after transferring from the current environmental state to the next environmental state, the maximum expected cumulative reward obtained among all optional actions;

[0068] Repeat the update of the Q-value function until the Q-value converges to obtain the corresponding optimal Q-value function. When the fault diagnosis unit detects a fault in the transmission line, the agent selects and executes the optimal action from the action space using the optimal Q-value function according to the state vector.

[0069] Compared with the prior art, the present invention provides an adaptive collaborative transmission line fault monitoring system, which has the following beneficial effects:

[0070] The present invention integrates data collected by various sensors such as current, voltage, temperature, vibration, and humidity through a sensor network and performs fusion analysis using an intelligent diagnosis algorithm. It can greatly improve the diagnosis accuracy rate. The system has an adaptive adjustment ability and can optimize the monitoring strategy in real time according to the development trend of the fault; it can adaptively adjust the sensor sampling frequency according to the real-time operating state and fault risk of the line; it dynamically allocates monitoring resources and intelligently transfers the monitoring focus according to factors such as the aging degree of the line, geographical environment, and historical fault distribution; the various modules of the system cooperate with each other and are mutually adapted; it can reduce misjudgment and missed judgment and improve the overall stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] [[ID=;14]] Figure 1 It is the system block diagram mentioned in Embodiment 1 of the present invention;

[0072] Figure 2 It is the architecture diagram of the adaptive adjustment mechanism mentioned in Embodiment 1 of the present invention.

[0073] Meanings of the marks in the figure:

[0074] 100, network construction module; 200, acquisition and transmission module; 210, data acquisition unit; 220, data transmission unit; 300, analysis and processing module; 310, data preprocessing unit; 320, feature extraction unit; 330, fault diagnosis unit; 400, adaptive collaborative control module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0075] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0076] The present invention integrates data collected by various sensors such as current, voltage, temperature, vibration, humidity, etc. through a sensor network, and performs fusion analysis using intelligent diagnostic algorithms. It can significantly improve the diagnostic accuracy rate. The system has an adaptive adjustment ability, can optimize the monitoring strategy in real time according to the development trend of faults; can adaptively adjust the sensor sampling frequency according to the real-time operating state and fault risk of the line; dynamically allocate monitoring resources and intelligently transfer the monitoring focus based on factors such as the aging degree of the line, geographical environment, and historical fault distribution; the various modules of the system cooperate with each other and are mutually adapted; it can reduce misjudgments and missed judgments and improve the overall stability of the system. The specific contents are as follows.

[0077] Embodiment 1:

[0078] Please refer to Figure 1 , an adaptive collaborative power transmission line fault monitoring system of the present invention, includes:

[0079] Network construction module 100: used to build a sensor network for the power transmission line based on several types of sensors;

[0080] The sensor network consists of various types of sensors and is widely distributed at key positions of the power transmission line, such as positions of poles, conductors, insulators, etc. It includes

[0081] Current sensor: It monitors the magnitude and change of the current in the power transmission line in real time, and converts the current signal into an electrical signal through a high-precision induction device for subsequent acquisition and analysis. Once the current shows abnormal fluctuations, such as a sudden increase (which may indicate a short-circuit fault) or a sharp decrease (which may be a situation such as a line break), the corresponding signal can be captured in time, providing a key basis for fault judgment.

[0082] Voltage sensor: responsible for measuring the voltage values at different nodes of the power transmission line. Its working principle is based on electromagnetic induction or voltage division principle, etc., and converts the line voltage into a weak electrical signal for processing. Abnormal voltage changes, such as voltage dips, overvoltages, etc. are often closely related to line faults (such as voltage surges caused by lightning strikes, voltage abnormalities caused by line insulation damage, etc.). The voltage sensor can accurately sense these changes and feedback them to the system.

[0083] Temperature sensor: installed at easily heated parts such as conductors and connection points, as well as on poles, to detect the real-time temperature and ambient temperature of these positions. Because in the case of faults such as overload operation and poor contact of the power transmission line, the local temperature will rise. The temperature sensor can keenly detect the abnormal rise in temperature and assist in judging whether there are potential hidden dangers of line overheating faults, such as problems like increased resistance and heat generation caused by loose wire joints.

[0084] Vibration sensor: It monitors the vibration conditions of the transmission line caused by external forces such as wind vibration and galloping, including acceleration, velocity, displacement, and frequency. Under normal circumstances, the vibration of the line is within a certain range. When a fault occurs (such as broken wire strands, loose tower foundations, etc.), the vibration characteristics will change. By collecting vibration signals, the vibration sensor can help determine whether there is an abnormality in the line structure.

[0085] Humidity sensor: It monitors the environmental humidity, which is an important factor affecting the external insulation performance of the transmission line. A high-humidity environment may reduce the insulation performance of the insulator and increase the risk of insulator flashover. By monitoring the environmental humidity with a humidity sensor, it can provide an important basis for evaluating the external insulation state of the transmission line. When the humidity exceeds a certain threshold, the system can strengthen the monitoring of relevant parameters such as the leakage current of the insulator and give early warnings about faults caused by humidity. At the same time, humidity changes may also be related to the corrosion situation of the line. For transmission line structures with more metal components, the data of the humidity sensor helps analyze the corrosion risk of the line.

[0086] Wind speed sensor: It is used to monitor the environmental wind speed. The impact of wind speed on the transmission line is mainly reflected in the wind load. Strong winds may cause problems such as conductor galloping and tower inclination of the transmission line. Real-time monitoring of the wind speed can provide data support for judging whether the line will have a wind deviation fault. When the wind speed exceeds the allowable wind speed range designed for the line, the system can timely adjust the monitoring focus, such as increasing the monitoring frequency of the conductor vibration amplitude and tower stability, and can further analyze the direction of the wind load that the line may be affected by in combination with the wind direction information, and take preventive measures in advance to prevent line faults, such as adjusting the line tension, etc.

[0087] Wind direction sensor: It is used to monitor the environmental wind direction. Combining the wind direction and wind speed information can more accurately evaluate the impact of wind on the transmission line. It is particularly important for the prediction and analysis of wind deviation faults. Different wind directions will cause the conductor to be subjected to wind loads in different directions. When the wind direction is perpendicular to the line direction, the risk of wind deviation faults may increase. Through the information provided by the wind direction sensor, the system can accurately calculate the direction of the wind load, and combined with the structural parameters of the transmission line, predict the swinging direction and amplitude of the conductor, and discover potential wind deviation fault risks in advance, so as to take targeted protection measures, such as installing anti-wind deviation devices, etc.

[0088] Tower inclination sensor: It is used to monitor the inclination angle of the tower. The tower is an important supporting structure of the transmission line. The tower inclination may be caused by reasons such as foundation settlement, soil loosening, external force damage (such as vehicle collision, landslide, etc.). The tower inclination sensor can monitor the inclination state of the tower in real time. Once the inclination angle exceeds the set threshold, it can send an alarm in time to prompt the operation and maintenance personnel to check and repair the tower. At the same time, the tower inclination data can also be combined with other sensor data (such as wind speed, vibration, etc.) to comprehensively analyze the cause of the tower inclination and judge whether there are other potential fault risks, such as unbalanced line tension, etc.

[0089] Insulator leakage current sensor: It is used to measure the magnitude of the leakage current. The insulator leakage current sensor is usually wound around the grounding lead of the insulator. When there is a leakage current passing through the grounding lead, according to the law of electromagnetic induction, an induced current will be generated in the secondary winding of the sensor. By measuring this induced current, the magnitude of the insulator leakage current can be obtained. The insulator leakage current is a key parameter reflecting the insulation performance of the insulator. Under normal circumstances, the leakage current of the insulator is very small. When the insulator surface is affected by pollution, moisture or aging, etc., the leakage current will increase. By monitoring the insulator leakage current, the degradation of the insulator insulation performance can be detected in time, which is an important means to predict the insulator flashover fault. When the leakage current exceeds a certain safety threshold, the system can judge that there are fault hazards in the insulator and notify the operation and maintenance personnel in time to carry out maintenance measures such as cleaning and replacement to avoid power outages of the transmission line caused by insulator flashover.

[0090] The data collected by the sensor network can be referred to Table 1:

[0091] Table 1 Data Collected by the Sensor Network

[0092]

[0093]

[0094] Acquisition and transmission module 200: It is used to collect data based on the sensor network and perform transmission;

[0095] The acquisition and transmission module 200 includes:

[0096] Data acquisition unit 210: It is used to collect the original data monitored by each sensor, and has functions such as sampling, quantization and encoding of analog signals, converting the continuously changing analog signals output by the sensors into digital monitoring data for subsequent storage, processing and transmission. At the same time, this unit regularly obtains data according to the set sampling frequency, which can ensure the accuracy and real-time nature of the collected data.

[0097] Data transmission unit 220: It is used to transmit the collected digital monitoring data to the background control center by combining several communication methods; it transmits the collected digital monitoring data to the background monitoring center, and its transmission method can be selected according to the actual application scenario as wired transmission (such as optical fiber communication, which has advantages such as high transmission rate and strong anti-interference ability, and is suitable for long-distance and large-capacity data transmission requirements) or wireless transmission (such as wireless communication technologies such as ZigBee, GPRS, 4G / 5G, etc., which are applicable to transmission line areas with difficult wiring and complex geographical environments and are convenient for flexible networking). Through the above transmission methods, the stability and integrity of data transmission can be ensured, data loss or errors can be avoided, and the monitoring center can be guaranteed to receive accurate on-site monitoring data in a timely manner.

[0098] Analysis and processing module 300: It is used to receive the data transmitted by the data communication module and perform preprocessing and fault diagnosis on the data;

[0099] The analysis and processing module 300 includes:

[0100] Data preprocessing unit 310: It is used to perform preprocessing operations such as denoising and normalization on the received original monitoring data. Since the sensor may be affected by external electromagnetic interference, environmental noise and other factors during the data acquisition process, resulting in certain noise components in the data, these interference information is removed through denoising algorithms such as filtering and smoothing to improve the data quality. The normalization operation is to unify data of different magnitudes and ranges into a specific standard range, which is convenient for subsequent unified analysis and comparison. For example, data such as voltage, current, and temperature collected by various sensors are all mapped into the interval [0,1].

[0101] Feature extraction unit 320: It is used to extract key information that can reflect the operating state and fault characteristics of the transmission line from the preprocessed data. It includes using time-domain analysis methods to extract features such as the amplitude, peak value, and period of current and voltage signals, and using frequency-domain analysis (such as fast Fourier transform, etc.) to obtain features such as vibration frequency and spectral amplitude from vibration signals, and analyzing the change trend and change gradient of temperature data. These extracted features will be used as important bases for subsequent fault diagnosis.

[0102] Fault diagnosis unit 330: It is used to perform fault diagnosis on the transmission line based on the extracted feature information by using intelligent diagnosis algorithms, and obtain the fault diagnosis results and the severity of the faults.

[0103] The intelligent diagnosis algorithm is specifically as follows:

[0104] Define a fuzzy set F for each operating state, and define a membership function μ F (x) for each fuzzy set F, and the membership function μ F (x) is specifically as follows:

[0105]

[0106] Among them, x is the operating state in the fuzzy set F, x0 and x1 are the parameters of the membership function. When μ F (x) ≥ A, it is determined that a fault has occurred, where A is a preset fault threshold.

[0107] Substitute the operating state into the membership function to calculate the membership degree of each operating state belonging to each fuzzy set, and obtain the membership degree matrix Defining fuzzy sets for each operating state and determining the membership function is the basis for converting accurate sensor data into fuzzy information. By reasonably setting the membership function parameters, the membership degree of different operating states in each fuzzy set can be accurately reflected. For example, when judging whether the current is abnormal, the current value can be fuzzified into states such as "normal", "slightly high", "too high", etc. according to the set membership function, providing more practical information for subsequent fault judgment.

[0108] Construct a fuzzy rule base consisting of preconditions and fault conclusions based on historical fault data and expert experience. The rule form is: IF (preconditions composed of fuzzy language variables) THEN (fault conclusion); construct a fuzzy rule base based on historical fault data and expert experience, covering various possible fault scenarios, such as "IF (the current is slightly high and the temperature rises) THEN (the possibility of a short - circuit fault is high)" and other rules. Judge whether the preconditions of the rules are satisfied according to the calculated membership degree matrix. When satisfied, trigger the corresponding fault conclusion. This reasoning logic based on knowledge and experience helps to quickly locate possible fault types and improve the diagnosis efficiency.

[0109] According to the membership degree matrix Judge whether the preconditions of each rule in the fuzzy rule base are satisfied, that is, whether the membership degree of each fuzzy set reaches the preset membership degree threshold; if satisfied, trigger the fault conclusion corresponding to the fuzzy rule;

[0110] Determine each triggered rule R k corresponding fault subset F k , and calculate the basic probability assignment function m k according to the rule credibility c k and the membership degree of the operating state; specifically as follows:

[0111]

[0112] For the fault subset F kAssign corresponding probability values to other fault subsets in the fault set Θ, and the sum of the probability values of all fault subsets in the fault set Θ is 1; the types of faults set in the fault set Θ generally include short - circuit faults, grounding faults, lightning faults, wind - deflection faults, and icing faults.

[0113] Fuse using the Dempster combination rule:

[0114] For two evidence bodies m a and m b obtained from basic probability assignment functions, fuse them to get the fused evidence body m ab . For the basic probability assignment of the fault subset D corresponding to the fused evidence body m ab , it is calculated as follows:

[0115]

[0116] where is the conflict coefficient, representing the degree of conflict between evidences; D is the fault subset corresponding to the fused evidence body m ab ; B is the fault subset corresponding to the evidence body m a ; C is the fault subset corresponding to the evidence body m b .

[0117] After several fusions, obtain the fused comprehensive evidence body m final ;

[0118] Based on the fused comprehensive evidence body m final , calculate the belief function Bel(G) as follows:

[0119]

[0120] where m final (H) is the basic probability assignment for the fault subset H in the fused evidence body; calculate the basic probability assignment function according to the credibility of the trigger rule and the membership degree of the operating state, assign probabilities to different fault subsets, and then fuse multiple evidence bodies using the Dempster combination rule, which fully considers the contributions of different information sources (i.e., different fuzzy rules) to fault diagnosis, can continuously fuse to reduce information uncertainty, and enhance the diagnostic credibility of this fault type.

[0121] According to the maximum - confidence criterion, select the fault subset with the largest belief - function value as the diagnostic result:

[0122]

[0123] where F diagmosis is the fault - diagnosis result.

[0124] After determining the fault diagnosis result, through defuzzification operation, the fault diagnosis result is converted into a fault diagnosis description, and then input into the adaptive collaborative control module 400, thus completing the entire intelligent diagnosis process. Calculating the trust function and determining the diagnosis result according to the maximum trust degree criterion, and finally converting the result into a clear fault diagnosis description through defuzzification operation can make the diagnosis result have practical application value. The fault severity is further divided according to the fault credibility through the trapezoidal membership function, which can further provide data support for the later adaptive adjustment mechanism.

[0125] In the fault monitoring of transmission lines, the data obtained by sensors often has uncertainty. The fuzzy algorithm can fuzzify these inaccurate data, and the DS evidence theory can fuse and reason about these fuzzified information, effectively dealing with the fuzziness and uncertainty of fault features, and more accurately judging whether a fault occurs and the type of the fault. The diagnostic algorithm combining the DS evidence theory and the fuzzy algorithm can analyze the fault meticulously by constructing a reasonable fuzzy rule base and evidence fusion mechanism. By fusing the evidence bodies corresponding to each fuzzy rule, calculating the trust function, and according to the maximum trust degree criterion, it can more accurately determine whether the fault type is a short-circuit fault or other types of faults, and can locate the approximate area where the fault occurs, such as the line segment between several transmission towers.

[0126] Adaptive collaborative control module 400: Used to dynamically control the collaborative work between sensors and different functional modules based on the adaptive adjustment mechanism, according to the real-time operating state, environmental conditions, fault diagnosis result and fault severity of the transmission line. Refer to Figure 2 , the adaptive adjustment mechanism is specifically as follows:

[0127] Define an agent, and define the adaptive collaborative control module 400 as an agent;

[0128] Define the state space S, and the state vector s in the state space S includes the operating state, environmental conditions, fault diagnosis result and fault severity of the transmission line;

[0129] Define the action space A, and the action space A contains the action vector a = {a 11 , Λ, a 1u , Λ, a 1U , a 21 , Λ, a 2v , Λ, a 2V , a 31 , Λ, a 3k , Λ, a 3L}; a 1u corresponds to the action of adjusting the sampling frequency proportionality coefficient to the u-th sampling frequency proportionality coefficient; a 2vThe action of adjusting the monitoring range of the corresponding sensor to the v-th range; a 3k The action of adjusting the computing resources and communication resources corresponding to the fault type to the k-th adjustment method;

[0130] Define the reward function R(s,a) as follows:

[0131] R(s,a) = w1R accuracy (s,a) + w2R energy (s,a) + w3R response (s,a)

[0132] where, w1, w2 and w3 are weight coefficients; R accuracy (s,a) is the reward for fault diagnosis accuracy; R energy (s,a) is the reward for energy consumption; R response (s,a) is the reward for fault response timeliness;

[0133]

[0134] where, k1 is the importance degree coefficient of accuracy; p acc is the next fault diagnosis accuracy rate when taking action a; p acc0 is the fault accuracy rate before taking action a;

[0135]

[0136] where, k2 is the importance degree coefficient of energy consumption; E0 is the energy consumption before taking action a; E is the energy consumption after taking action a;

[0137]

[0138] where, k3 is the importance degree coefficient of timeliness; t d0 is the first fault detection time before taking action a; t d is the first fault detection time after taking action a;

[0139] Use the Q-learning algorithm to learn the optimal policy, and initialize the Q-value function as a table. The rows of the table correspond to different environmental states, and the columns correspond to different actions;

[0140] Adopt the ε-greedy strategy to select actions:

[0141]

[0142] where, ε is the exploration rate; is the maximum Q-value corresponding to all possible actions in the environmental state s t ; [[ID=6\7]]

[0143] The agent executes the selected action a in the systemt , the system state transfers to the next state s according to the physical laws of line operation, environmental changes, and action impacts t+1 , and at the same time, the reward value R is calculated according to the reward function R(s,a) and fed back to the agent t .

[0144] Based on the Q-learning algorithm update formula, use the newly obtained experience (s t ,a t ,R t ,s t+1 ) to update the Q value:

[0145]

[0146] where: Q'(s t ,a t ) is the updated Q value; Q(s t ,a t ) is the Q value of taking action a t in the environmental state s t ; α is the learning rate; γ is the discount factor; a' is the optimal action among all possible actions in the next environmental state s t+1 ; is the maximum value of the corresponding Q values among all possible actions in the next environmental state s t+1 , that is, the maximum expected cumulative reward obtained among all optional actions after transferring from the current environmental state to the next environmental state.

[0147] Repeat updating the Q value function until the Q value converges to obtain the corresponding optimal Q value function. When the fault diagnosis unit 330 detects a fault in the transmission line, the agent selects and executes the optimal action from the action space according to the state vector.

[0148] Apply the above system to the actual detection of transmission lines. The specific adaptive adjustment mechanism can be referred to Table 2:

[0149] Table 2 Adaptive Adjustment Mechanism of Transmission Lines

[0150]

[0151]

[0152] The adaptive adjustment mechanism can timely increase the sampling frequency, so as to capture the line state changes more precisely and ensure not to miss any possible fault precursors; it can reasonably allocate monitoring resources, improve the pertinence and effectiveness of fault monitoring; it can also provide more accurate data support for the diagnostic algorithm according to the preliminary signs of faults and the current system state. It can guide the monitoring system to focus on the key parameters and areas related to faults and reduce the interference of irrelevant information.

[0153] As described above, it is only the preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, shall be covered by the protection scope of the present invention.

Claims

1. An adaptive collaborative transmission line fault monitoring system, characterized in that: include: A network building module (100) is used to build a sensor network for the power transmission line based on several types of sensors; Collection and transmission module (200): used for collecting data based on the sensor network and transmitting it; The acquisition and transmission module (200) comprises: Data acquisition unit (210): used to collect raw data monitored by each sensor and convert analog signals into digital monitoring data through edge devices; Data transmission unit (220): used for transmitting the collected digital monitoring data to the background control center by combining several communication modes; Analysis and processing module (300): used for receiving data transmitted by the data communication module and performing pre-processing and fault diagnosis on the data; The analysis and processing module (300) includes: Data pre-processing unit (310): used for performing denoising and normalization pre-processing on the received digital monitoring data; Feature extraction unit (320): used for extracting the transmission line operation status and environmental conditions from the pre-processed data; A fault diagnosis unit (330) is used to perform fault diagnosis on the transmission line based on the extracted transmission line operation status and an intelligent diagnosis algorithm, and obtain a fault diagnosis result and a fault severity; Adaptive collaborative control module (400): used to dynamically control the collaborative work between sensors and different functional modules based on an adaptive adjustment mechanism according to the real-time operating status, environmental conditions, fault diagnosis results and fault severity of the transmission line; the adaptive adjustment mechanism is specifically as follows: An intelligent agent is defined, wherein a fault diagnosis unit (330) including an intelligent diagnosis algorithm is defined as the intelligent agent; defining a state space S, wherein a state vector s in the state space S includes an operating state of the transmission line, environmental conditions, a fault diagnosis description, and a fault severity; Define the action space A, which contains the action vector a={a 11 ,Λ,a 1u ,Λ,a 1U , a 21 ,Λ,a 2v ,Λ,a 2V , a 31 ,Λ,a 3k ,Λ,a 3L };a 1u Corresponding sampling frequency proportional coefficient adjustment action; a 2v Corresponding sensor monitoring range adjustment action; a 3k Adjustment actions for computing and communication resources corresponding to the fault type; The reward function R(s,a) is defined as follows: R(s,a)=w1R accuracy (s,a)+w2R energy (s,a)+w3R response (s,a) Among them, w1, w2 and w3 are weight coefficients; R accuracy (s,a) is the fault diagnosis accuracy reward; R energy (s,a) is the energy consumption reward; R response (s,a) is the fault response timeliness reward; Among them, k1 is the accuracy importance coefficient; p acc To take action a to make the next fault diagnosis accuracy; p acc0 is the fault accuracy rate before taking action a; Among them, k2 is the energy consumption importance coefficient; E0 is the energy consumption before taking action a; E is the energy consumption after taking action a; Among them, k3 is the timeliness importance coefficient; t d0 is the time of first fault detection before taking action a; t d is the first fault detection time after taking action a; Use the Q learning algorithm to learn the optimal strategy, initialize the Q value function as a table, the rows of the table correspond to different environmental states, and the columns correspond to different actions; Use the ε-greedy strategy to select actions: Among them, ε is the exploration rate; is the environmental state s t The maximum Q value corresponding to all possible actions; The agent performs the selected action a in the system t The system state transfers to the next state s according to the physical laws of line operation, environmental changes and action influences t+1 At the same time, the reward value R is calculated and fed back to the agent based on the reward function R(s,a) t ; Based on the Q learning algorithm, the updated formula is used to update the newly acquired experience (s t ,a t ,R t ,s t+1 )Update the Q value: Where: Q'(s t ,a t ) is the updated Q value; Q(s t ,a t ) is the environmental state s t Next take action a t Q value; α is the learning rate; γ is the discount factor; a' is the next environment state s t+1 The best action among all possible actions; is the next environment state s t+1 The maximum Q value corresponding to all possible actions is the maximum expected cumulative reward obtained from all optional actions after transferring from the current environment state to the next environment state; The Q value function is repeatedly updated until the Q value converges to obtain a corresponding optimal Q value function. When the fault diagnosis unit (330) detects that a fault exists in the transmission line, the intelligent agent uses the optimal Q value function to select and execute an optimal action from the action space according to the state vector.

2. The adaptive coordinated transmission line fault monitoring system according to claim 1, characterized in that: The sensor network is composed of a number of current sensors, voltage sensors, temperature sensors, humidity sensors, vibration sensors, wind speed sensors, wind direction sensors, tower tilt sensors and insulator leakage current sensors.

3. The adaptive coordinated transmission line fault monitoring system according to claim 1, characterized in that: The operating status of the transmission line extracted by the feature extraction unit (320) includes the amplitude, peak value and period corresponding to the current signal collected by the current sensor; the amplitude, peak value and period corresponding to the voltage signal collected by the voltage sensor; the temperature change trend and temperature change gradient of the transmission line temperature data collected by the temperature sensor; the acceleration, velocity, displacement and frequency of the transmission line vibration signal collected by the vibration sensor; the horizontal tilt angle and vertical tilt angle of the tower collected by the tower tilt sensor, and the insulator leakage current collected by the insulator leakage current sensor; and the environmental conditions include the ambient temperature collected by the temperature sensor, the ambient humidity collected by the humidity sensor, the wind speed collected by the wind speed sensor, and the wind direction angle collected by the wind direction sensor.

4. The adaptive coordinated transmission line fault monitoring system according to claim 3, characterized in that: The intelligent diagnosis algorithm is specifically as follows: For each operating state, define a fuzzy set F and define a membership function μ for each fuzzy set F F (x), the membership function μ F (x) The details are as follows: Among them, x is the operating state in the fuzzy set F, x0 and x1 are the membership function parameters, when μ F When (x)≥A, it is determined that a fault has occurred, where A is the preset fault threshold; Substitute the running state into the membership function, calculate the membership degree of each running state to each fuzzy set, and obtain the membership matrix Construct a fuzzy rule base consisting of preconditions and fault conclusions based on historical fault data and expert experience; Based on the membership matrix Determine whether the prerequisites of each rule in the fuzzy rule base are met, that is, whether the membership of each fuzzy set reaches the preset membership threshold; if so, trigger the fault conclusion corresponding to the fuzzy rule; Determine each rule R that is triggered k The corresponding fault subset F k , and according to the rule credibility c k The basic probability distribution function m is calculated based on the membership degree of the running state k ; The details are as follows: For the fault subset F k The other fault subsets in the fault set Θ are assigned corresponding probability values, and the sum of the probability values of all fault subsets in the fault set Θ is 1; Fusion using Dempster's synthesis rule: For two evidence bodies m consisting of basic probability distribution functions a and m b Perform fusion to obtain the fused evidence body m ab , for the fused evidence body m ab The basic probability distribution of the corresponding fault subset D is calculated as follows: in, is the conflict coefficient, which indicates the degree of conflict between evidences; D is the evidence body m after fusion ab The corresponding fault subset; B is the evidence body m a The corresponding fault subset; C is the evidence body m b corresponding fault subset; After several fusions, the fused comprehensive evidence body m is obtained. final ; Based on the comprehensive evidence m obtained after fusion final The trust function Bel(G) is calculated as follows: Among them, m final (H) is the weight of evidence after fusion, the basic probability distribution for the fault subset H; According to the maximum trust criterion, the fault subset with the largest trust function value is selected as the diagnosis result: Among them, F diagmosis is the fault diagnosis result; After the fault diagnosis result is determined, the fault diagnosis result is converted into a fault diagnosis description through a defuzzification operation, and the fault diagnosis description is input into the adaptive cooperative control module (400).

5. The adaptive coordinated transmission line fault monitoring system according to claim 4, characterized in that: In the fault diagnosis unit (330), the fault severity is further divided according to the fault credibility through a trapezoidal membership function.

Images