A method and system for online monitoring and failure assessment of the pressure of sprite contacts in switchgear.

Abstract

This invention belongs to the field of power equipment condition monitoring and fault diagnosis technology, and discloses a method and system for online monitoring and failure assessment of the pressure of switchgear louver contacts. The method includes: real-time acquisition of temperature data and raw pressure data of the louver contacts; temperature compensation of the raw pressure data based on a temperature-pressure compensation model to obtain compensated pressure data; inputting the compensated pressure data into a KNN regression intelligent diagnostic model to calculate a comprehensive three-dimensional index H and determine the health status level. The system includes a sensing unit, a data transmission unit, and a monitoring and evaluation unit. This invention eliminates the interference of temperature on pressure measurement through temperature compensation, and combines multi-sensor three-dimensional pressure sensing with a KNN regression model to achieve accurate classification and early warning of the health status of the louver contacts, improving the accuracy and reliability of online monitoring.

Description

Technical Field

[0001] This invention belongs to the field of power equipment condition monitoring and fault diagnosis technology, specifically relating to a method and system for online monitoring and failure assessment of the pressure of switchgear plum blossom contacts. Background Technology

[0002] Switchgear is a critical piece of equipment in power transmission and distribution systems, and its operational reliability directly affects the safety and stability of the distribution system and its network. The sprite contact, as a core component of the switchgear, is an important part of the vacuum circuit breaker, ensuring reliable connection when closed. During long-term operation, the sprite contact will experience elastic decay, contact surface oxidation, and mechanical deformation due to electrical, thermal, and mechanical stresses, leading to increased contact resistance. This can cause localized overheating, and sustained overheating can result in serious failure. Insufficient contact finger pressure is a significant factor in sprite contact failure; accurate online pressure monitoring can effectively assess sprite contact performance.

[0003] Current methods for detecting the pressure of spline contactors primarily rely on periodic offline power outages for maintenance, measuring the contact finger pressure using a pressure testing instrument. The limitations of this offline method are: firstly, it cannot measure contact pressure changes online in real time; secondly, the detection cycle is long, making it difficult to detect gradual degradation in a timely manner; and thirdly, power outages affect power supply reliability. Therefore, real-time and accurate online monitoring and early warning of spline contact finger pressure is crucial for transforming switchgear from "periodic maintenance" to "condition-based maintenance," and is of great significance for improving the intelligence level of the power grid and the reliability of power supply.

[0004] However, existing technologies still have the following defects and shortcomings in practical applications:

[0005] First, the accurate online measurement of the contact finger pressure of a luffy contactor is mainly affected by temperature, the design and installation of the built-in sensor, and data processing methods, and there is a lack of effective solutions. When a large current flows through the luffy contact, heat is generated due to contact resistance, causing a significant temperature increase. This temperature rise causes the contact finger to expand. Since the coefficient of thermal expansion of the contact finger is much greater than that of the sensor's structural materials, the outward expansion of the contact finger reduces its tightness against the sensor probe. Existing methods fail to effectively address the impact of temperature changes on pressure monitoring, resulting in pressure test values ​​that do not reflect the true contact state of the contactor, thus affecting the accuracy of diagnosis.

[0006] Secondly, the plum blossom contact is a ring-shaped, multi-finged curved contact structure. Its unique structure makes it difficult to obtain comprehensive pressure data for different contacts and the entire device, especially given the lack of targeted sensor designs and installation solutions in current technology. On one hand, most existing pressure sensing technologies are rigid structures, which are ill-suited to the complex curved surface of the plum blossom contact, resulting in low measurement accuracy and poor installation reliability, sometimes affecting the opening and closing operation of the contact. On the other hand, online pressure measurement requires real-time, continuous monitoring, but existing sensors are insufficient in terms of high-voltage isolation, anti-interference, and long-term stability, failing to meet the needs of engineering applications.

[0007] Third, the plum blossom contacts are located inside the switch cabinet in a confined space. Traditional installation methods often damage the original structure of the contacts, affect electrical insulation performance, or fail to ensure sufficient contact between the sensor and the contact surface, resulting in insufficient representativeness of the measurement data. The lack of installation design limits the practical application and promotion of online pressure monitoring technology.

[0008] Fourth, there is a lack of unified evaluation standards and methods for using contact pressure to monitor the condition of contact points. Existing technologies rely solely on experience or simple statistical methods, which cannot deeply integrate pressure data, making it difficult to detect the deterioration process of contact pressure data and thus hindering early fault warning. For example, the reasonable range of pressure values ​​and the distribution of pressure among various contact fingers are not yet clearly related to the health status of the contact.

[0009] In summary, there is an urgent need for a method and system that can monitor the pressure of plum blossom contacts online, eliminate temperature interference, adapt to the curved surface structure of the contacts, and use pressure data for failure assessment. Summary of the Invention

[0010] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for online monitoring and failure assessment of the pressure of the sprite contacts in switchgear. This method and system can realize real-time online monitoring of the pressure of the sprite contacts, eliminate measurement errors caused by temperature changes, and accurately assess and classify the health status of the contacts.

[0011] The technical solution adopted by this invention to solve the technical problem is:

[0012] This invention provides a method for online monitoring and failure assessment of the pressure of the sprite contact in a switchgear, comprising the following steps:

[0013] Data sensing steps: Install pressure and temperature sensors on the contact fingers of the plum blossom contact to collect raw pressure and temperature data in real time during the contact's operation.

[0014] Temperature compensation step: Based on the pre-built temperature-pressure compensation model, the collected original pressure data is temperature compensated to eliminate measurement errors caused by temperature changes and obtain compensated pressure data.

[0015] Condition assessment steps: The compensated pressure data is input into the KNN regression intelligent diagnostic model based on multi-sensor three-dimensional pressure to calculate the comprehensive three-dimensional index H that characterizes the overall health status of the plum blossom contact. Based on the numerical range of the comprehensive three-dimensional index H, the health status level of the plum blossom contact is determined. The health status level includes normal, slight deterioration, moderate deterioration, and severe failure.

[0016] Furthermore, the temperature-pressure compensation model is constructed by conducting offline temperature rise tests and finite element simulations of the plum blossom contact, simulating pressure changes under different temperature rise levels, obtaining temperature-pressure coupling data, and then fitting the temperature-pressure compensation mathematical formula.

[0017] Furthermore, the mathematical formula for temperature-pressure compensation is as follows:

[0018]

[0019] in This represents the raw pressure value, i.e., the value directly measured by the sensor; The pressure value after compensation; For real-time temperature measurement; For reference temperature, , This is the temperature compensation coefficient.

[0020] Furthermore, the construction steps of the KNN regression intelligent diagnostic model include: preprocessing and extracting multi-dimensional features from the compensated pressure data to construct a feature vector; classifying the health status of the plum blossom contactor into four levels: normal, slightly deteriorated, moderately deteriorated, and severely faulty, and defining the mapping relationship between the comprehensive three-dimensional index H and each health status level; and determining the nearest neighbor number k value of the KNN model through cross-validation grid search.

[0021] Furthermore, the feature vector includes average contact pressure, pressure distribution uniformity, and pressure decay rate.

[0022] Furthermore, the comprehensive three-dimensional index H is mapped to the feature vector using a weighted method, and the function is expressed as:

[0023]

[0024] in , , These represent the corresponding weight coefficients. F n This represents the nth pressure feature vector. w n Representing then The weight coefficients corresponding to each pressure feature vector .

[0025] Furthermore, the criteria for determining the health status level are as follows: when H∈[0.8,1], it is a normal state; when H∈[0.5,0.8), it is a slight deterioration; when H∈[0.3,0.5), it is a moderate deterioration; and when H∈[0,0.3), it is a serious fault.

[0026] A second aspect of the present invention is to provide an online monitoring and failure assessment system for the pressure of the sprite-shaped contact of a switchgear for implementing the above-described method, comprising:

[0027] The sensing unit includes a pressure sensor and a temperature sensor installed on the finger of the plum blossom contact, which are used to collect raw pressure data and temperature data in real time during the operation of the contact.

[0028] A data transmission unit, connected to the sensing unit, is used to receive data collected by the sensing unit and upload it via a wireless transmission network;

[0029] The monitoring and evaluation unit, connected to the data transmission unit, is used to receive uploaded data, execute the temperature compensation step and the status evaluation step, and output health status evaluation results and early warning information.

[0030] Furthermore, the pressure sensor is a flexible thin-film pressure-sensitive array sensor, which includes a first pressure sensor ring fitted on the front end of the contact finger of the plum blossom contact and a second pressure sensor ring fitted on the rear end of the contact finger. Each pressure sensor ring is composed of three flexible thin-film pressure-sensitive array sensors, which are uniformly and symmetrically distributed around the contact axis at a spatial angle of 120 degrees.

[0031] Furthermore, the temperature sensor is a wireless temperature sensor, which includes a temperature sensor body, an alloy base, a latch, and a silicone pad. The silicone pad is placed on the surface of the touch finger, the alloy base is placed on the silicone pad, and the temperature sensor body is placed on the alloy base and fastened to the touch finger by the latch.

[0032] The advantages and positive effects of this invention are:

[0033] 1. This invention, through the temperature-pressure sensor installation design and temperature-pressure compensation design, uses temperature data to compensate for online contact pressure data, achieving real-time compensation and correction. This eliminates the influence of temperature, overcomes the problem of pressure measurement distortion caused by contact heating, and greatly improves the accuracy of online pressure monitoring data.

[0034] 2. This invention uses a flexible thin-film pressure-sensitive array sensor directly attached to the surface of the finger, achieving accurate perception of pressure distribution without altering the original contact structure or affecting its insulation and opening / closing performance; the wireless temperature sensor is directly fixed to key heat points via an alloy base and locking structure, ensuring optimal fit between the sensor and the monitoring point, thereby guaranteeing the accuracy of the collected data.

[0035] 3. This invention utilizes temperature-compensated, interference-free pressure data to construct a comprehensive three-dimensional perception of the pressure before and after the cloverleaf contact, thereby enabling a comprehensive assessment of the cloverleaf contact pressure status. A KNN regression intelligent diagnostic model based on multi-cloverleaf contact pressure data is constructed to analyze the deviation of pressure at each point from the normal state. This model can sensitively and accurately identify early deterioration caused by mechanical fatigue, elastic decay, etc., achieving precise grading and early warning of contact pressure status, significantly improving reliability. Attached Figure Description

[0036] Figure 1 This is an overall flowchart of the method of the present invention;

[0037] Figure 2 Installation diagram for a plum blossom contact temperature sensor;

[0038] Figure 3 Installation diagram for plum blossom contact pressure sensor;

[0039] Figure 4 A comparison chart of pressure compensation curves for plum blossom contactors;

[0040] Figure 5 This is a simulation diagram of finger pressure.

[0041] Figure 6 To refine the simulation diagram of finger pressure;

[0042] Figure 7 This is a graph showing the fitted temperature-pressure curve.

[0043] Figure 8 Here is a flowchart of the KNN regression module workflow;

[0044] Figure 9 The confusion matrix for the KNN model;

[0045] Figure 10 For each contact finger, see the pressure-temperature rise curve;

[0046] Figure 11 This is a finger safety rating chart.

[0047] Wherein 1-touch finger; 2-first temperature sensor body; 3-second temperature sensor body; 4-third temperature sensor body; 5-first temperature sensor latch; 6-second temperature sensor latch; 7-third temperature sensor latch; 8-first pressure sensor ring; 9-second pressure sensor ring; 8-1-first flexible thin film pressure-sensitive array sensor; 8-2-second flexible thin film pressure-sensitive array sensor; 8-3-third flexible thin film pressure-sensitive array sensor. Detailed Implementation

[0048] The present invention will be further described in detail below through specific embodiments. The following embodiments are merely descriptive and not limiting, and should not be used to limit the scope of protection of the present invention.

[0049] This invention provides a method and system for online monitoring and failure assessment of the pressure of the plum blossom contacts in switchgear. Through a progressive design of online sensing, temperature and pressure calibration, and algorithm diagnosis, it achieves real-time monitoring and health status assessment of the plum blossom contact pressure. The specific embodiments of this invention are described in detail below with reference to the accompanying drawings.

[0050] I. System Composition and Installation

[0051] The switchgear plum blossom contact pressure online monitoring and failure assessment system of the present invention mainly includes a sensing unit, a data transmission unit, and a monitoring and assessment unit.

[0052] The sensing unit includes a pressure sensor and a temperature sensor mounted on the pendant of the Phillips-shaped contact.

[0053] The physical structure of a temperature sensor should include a temperature sensor body, an alloy base, a power-generating alloy sheet, a latch, and a silicone pad.

[0054] Installation position and angle: The plum blossom contactor typically has 12 contact fingers 1. The first temperature sensor body 2 is installed on the first contact finger; the second temperature sensor body 3 is installed on the fifth contact finger; and the third temperature sensor body 4 is installed on the ninth contact finger to ensure coverage of the entire plum blossom contactor. The three temperature sensors essentially form an approximately uniform ring distribution with a 120-degree interval.

[0055] Specific installation location and steps: During installation, first place the silicone pad on the selected contact finger surface for insulation and cushioning; then place the alloy base on the silicone pad, aligning the base with the middle area of ​​the contact finger, such as... Figure 2As shown. The alloy base is used to conduct heat and fix the sensor body; finally, the temperature sensor body is placed on the alloy base, aligning the interface and fixing point. The sensor body should be tightly attached to the alloy base; finally, the locking structure is used to fasten the sensor body and alloy base to the contact finger (the first temperature sensor lock 5 is used to fix the first temperature sensor body 2, the second temperature sensor lock 6 is used to fix the second temperature sensor body 3, and the third temperature sensor lock 7 is used to fix the third temperature sensor body 4). The locks should apply sufficient pressure to ensure full contact between the sensor body and the contact finger surface, but without excessive compression to avoid damaging the sensor. Through the matching alloy sheet and locking structure, the sensor body is directly pressed tightly onto the designated heating point of the Phillips head contact.

[0056] Key physical parameters of the sensor: temperature measurement range -50℃ to 125℃, accuracy ±1℃, sampling period 15 seconds. Energy is obtained from the current flowing through the contacts via CT induction (starting current ≥5A), and the temperature data is transmitted via a 470MHz wireless band.

[0057] The physical structure of the pressure sensor, from top to bottom, includes a highly flexible pressure-sensitive dielectric film, flexible electrodes printed on the film, an electrode structure that arrays the sensing surfaces, and a shielding circuit for electromagnetic interference suppression.

[0058] Installation Position and Angle: A pressure sensor ring is installed on each side of the spring attachment of the plum blossom contact. The first pressure sensor ring 8 is fitted onto the front end of the plum blossom contact finger, and the second pressure sensor ring 9 is fitted onto the rear end of the plum blossom contact finger. Each pressure sensor ring consists of three flexible thin-film pressure-sensitive array sensors. For example, the first pressure sensor ring 8 consists of a first flexible thin-film pressure-sensitive array sensor 8-1, a second flexible thin-film pressure-sensitive array sensor 8-2, and a third flexible thin-film pressure-sensitive array sensor 8-3. The three flexible thin-film pressure-sensitive array sensors are evenly and symmetrically distributed around the contact axis at a spatial angle of 120 degrees, ensuring comprehensive capture of the pressure distribution along the circumference of the contact.

[0059] Specific installation location and steps: During installation, the first pressure sensor ring 8 and the second pressure sensor ring 9 utilize the flexible, adaptable shape of the contact's curved surface and are fixed using a special tool. They are fitted to the contact finger area near the fastening spring edges on both sides of the plum blossom contact, ensuring that their sensing surfaces are fully in contact with the contact surface. Figure 3 As shown. Simultaneously, pressure changes on the stationary contact side and spring pressure changes on the side furthest from the stationary contact are sensed. Pressure decay is one of the fundamental causes of increased contact resistance, and this measurement directly reflects the mechanical health of the contact.

[0060] The data from the temperature and pressure sensors is received by a transceiver, whose parameters are shown below:

[0061] Table 1 Transceiver Parameter Configuration

[0062]

[0063] The transceiver uploads data to the industrial control computer or server in the monitoring center via an RS485 industrial bus. The evaluation device consists of a monitoring host and intelligent evaluation software. The mobile terminal connects wirelessly to the monitoring host via a local area network to receive real-time status information and alarm push notifications.

[0064] II. Temperature Compensation Methods

[0065] To establish a temperature-pressure compensation model, data was collected under two scenarios during the experiment: first, temperature-pressure images when the temperature of the contact ring changes but the pressure sensor temperature remains constant; this data can be measured by adding a ceramic fiber pad as a heat insulation layer under the pressure sensor ring; second, temperature-pressure images when both the contact ring temperature and the pressure sensor temperature change accordingly, as shown in the figure. Figure 4 As shown, by comparing the temperature-pressure images under two scenarios, it can be seen that when the pressure sensor ring is measured without a heat insulation layer, temperature changes cause drift in the sensor output signal and zero-point drift, resulting in a pressure sensor reading higher than the actual value. Based on this pattern, a temperature-pressure compensation function is constructed to correct the pressure value when both the temperature of the contact point and the pressure sensor change simultaneously during actual operation, thereby eliminating temperature interference and achieving accurate temperature compensation.

[0066] Temperature-stress coupling analysis was performed using a finite element simulation model. The specific approach involved first calculating the temperature distribution of the contacts through thermoelectric coupling analysis, then using the temperature field as a load for thermo-stress coupling analysis to calculate the contact pressure between the moving and stationary contacts, obtaining the corresponding temperature and pressure images, such as... Figure 5 As shown in Figure 6, temperature and pressure probes were placed at the first, fifth, and ninth contact fingers, respectively, and three sets of temperature rise-pressure data were obtained. The contact material characteristic parameters are shown in the table below:

[0067] Table 2. Contact Material Property Parameters

[0068]

[0069] Based on the average value of three sets of simulated temperature-pressure data, a temperature-pressure scatter plot and a temperature-pressure curve fitting plot are constructed, as follows: Figure 7 As shown. Then, a temperature-pressure compensation function is constructed using the fitting function. For convenience, a quadratic function is chosen here, as follows:

[0070] (1)

[0071] in This represents the raw pressure value, i.e., the value directly measured by the sensor; The pressure value after compensation; For real-time temperature measurement; For reference temperature, this article sets it to 25. , , This is the temperature compensation coefficient. Based on the fitting function... With a residual norm of 4.98, the temperature compensation coefficient was obtained. It is -0.013. The value is 0.54. Therefore, the temperature-pressure compensation function is:

[0072] (2)

[0073] According to the temperature compensation formula, the measured temperature and the original pressure can be substituted into the above formula to obtain the compensated pressure value after eliminating the influence of temperature.

[0074] III. Failure Assessment Methods for Plum Blossom Contacts

[0075] A flexible thin-film pressure-sensitive array sensor detects real-time pressure information of the perforated contact, including data from both normal and abnormal operating conditions. The above process performs temperature compensation on six sets of raw pressure data (three sets from each ring). The compensation is performed on a host computer platform, which then preprocesses the curves and extracts multi-dimensional features. These pressure features include average contact pressure, pressure distribution uniformity, and pressure attenuation rate; these features constitute the input feature vector. For example: The average pressure of the first pressure sensor represents the first pressure sensor ring. The pressure distribution uniformity of the second pressure sensor, representing the first pressure sensor ring; The pressure attenuation rate represents the pressure decay rate of the third pressure sensor in the first pressure sensor ring. Each pressure sensor acquires three feature vectors, and the six sensors acquire a total of 18 feature vectors.

[0076] The pressure state of the Phillips-shaped contact is divided into four states: normal, slightly deteriorated, moderately deteriorated, and severely faulty. A comprehensive three-dimensional index H is defined. H values ​​in the range of 0-0.3 are defined as severely faulty, where the contact pressure is below 30% of the baseline value; 0.3-0.5 is defined as moderately deteriorated, where the pressure drops to 30%-50% of the baseline value; 0.5-0.8 is defined as slightly deteriorated, where the pressure is 50%-80% of the baseline value; and 0.8-1 is defined as normal, where the pressure remains above 80% of the baseline value and the contact is in good contact. To accurately reflect the multi-finger structure of the Phillips-shaped contact, i.e., if a moderate or severe fault occurs in any one of the multiple contact fingers, it will lead to a serious accident, a weighted method is used to construct the mapping relationship between the comprehensive three-dimensional index H and the feature vector, expressed as:

[0077] (3)

[0078] in , , These represent the corresponding weighting coefficients. F n This represents the nth pressure feature vector. w n Representing the n The weight coefficients corresponding to each pressure feature vector .

[0079] For samples with slight degradation, temperature or pressure parameters deviate slightly from the normal range but do not reach the danger threshold. For samples with moderate degradation, temperature increases significantly or pressure distribution is uneven, and the comprehensive three-dimensional index H deviates significantly from the normal range. For samples with severe failures, temperature or pressure parameters are severely abnormal, and the comprehensive three-dimensional index H is close to the failure cluster center.

[0080] To solve the comprehensive three-dimensional index H, an intelligent diagnostic model based on KNN regression was designed.

[0081] In terms of data preparation and preprocessing: an 8-dimensional feature vector was constructed, including statistical features such as mean, variance, standard deviation, skewness, and kurtosis; and pressure features such as average contact pressure, pressure distribution uniformity, and pressure decay rate. Simultaneously, 100 sets of measurement data were obtained based on the finite element simulation model, with 70 sets constituting the training set and 30 sets constituting the test set.

[0082] Regarding model training and parameter optimization: the nearest neighbor count k is determined through cross-validation grid search, and weighted Euclidean distance is chosen as the distance metric to calculate the distance between two sample points x and y, as shown in the following formula:

[0083] (4)

[0084] in Representative sample x and y The weighted Euclidean distance; This represents the total number of dimensions in the data. t The index is a feature dimension index, ranging from 1 to... T ; Representative sample x In the t Specific numerical values ​​of features in each dimension; Representative sample y In the t The specific numerical values ​​of the features in each dimension.

[0085] Since the worst-performing contact finger has a significant negative impact on the comprehensive three-dimensional index H, if even one contact finger enters the critical fault stage, it will pull the H value below 0.3, ensuring that the system immediately triggers an alarm. The feature weights are calculated by combining the mutual information of the above characteristics and the target variable, using the following formula:

[0086] (5)

[0087] in Representing the i The final weights calculated from each feature; Representing the i A specific feature; Represents the target variable; Representative characteristics With target variable Mutual information between them; The total number of dimensions representing the features. X j Representing the j A specific feature.

[0088] Regarding distance calculation and nearest neighbor selection: take the nearest neighbor point. k The distance metric was set to 5, and weighted Euclidean distance was selected as the distance metric. 100 sets of data were tested. For each sample to be tested... x Calculate its weighted Euclidean distance with all samples in the training set, and simultaneously select the sample with the smallest distance based on its feature weights. k Using training samples as the nearest neighbor set, the confusion moments of the KNN model are as follows: Figure 9 As shown.

[0089] In terms of regression prediction and post-processing: the pressure sensor data of the three pressure sensors of the front finger of the plum blossom contact are fed into the trained KNN model, and the continuous health index value H is obtained through prediction and mapped to the corresponding state level, such as... Figure 10 As shown in Figure 11: H ≥ 0.8 indicates normal condition, 0.5 ≤ H ≤ 0.8 indicates slight deterioration, 0.3 ≤ H < 0.5 indicates moderate deterioration, and H < 0.3 indicates severe failure. Among them, the pressure changes of the first and fifth contact fingers are normal, while the ninth contact finger, due to its lower pressure level, has a comprehensive three-dimensional index H that drops to 0.36, which is considered moderate deterioration.

[0090] When performing online monitoring and failure assessment, the pressure data obtained online can be substituted into equation (3) to complete accurate condition monitoring and failure assessment.

[0091] like Figure 1 As shown, the online monitoring and failure assessment method for switchgear contact pressure provided by the present invention includes the following steps:

[0092] S1: The temperature and raw pressure data under operating conditions are collected in real time and synchronously through the wireless temperature sensor and flexible thin film pressure array sensor installed on the plum blossom contact.

[0093] S2: A temperature-pressure compensation model is established using finite element simulation. The original pressure data is corrected using a temperature-pressure compensation function to obtain compensated pressure data that eliminates the influence of temperature.

[0094] S3: Features are extracted from the compensation pressure data, the feature vector weight relationship is determined according to the structural characteristics of the plum blossom contact, a comprehensive three-dimensional index H is constructed, and four state classifications are performed.

[0095] S4: Input the obtained feature vector into the intelligent diagnostic model based on KNN regression. This model performs regression prediction through distance weighting and finally outputs a comprehensive health status index H.

[0096] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the inventive concept, and these all fall within the protection scope of the present invention.

Claims

1. A method for online monitoring and failure assessment of the pressure of a switchgear's perforated contact, characterized in that, Includes the following steps: Data sensing steps: Install pressure and temperature sensors on the contact fingers (1) of the plum blossom contact to collect raw pressure and temperature data in real time during the operation of the contact. Temperature compensation step: Based on the pre-built temperature-pressure compensation model, the collected original pressure data is temperature compensated to eliminate measurement errors caused by temperature changes and obtain compensated pressure data. Condition assessment steps: The compensated pressure data is input into the KNN regression intelligent diagnostic model based on multi-sensor three-dimensional pressure to calculate the comprehensive three-dimensional index H that characterizes the overall health status of the plum blossom contact. Based on the numerical range of the comprehensive three-dimensional index H, the health status level of the plum blossom contact is determined. The health status level includes normal, slight deterioration, moderate deterioration, and severe failure.

2. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 1, characterized in that, The temperature-pressure compensation model is constructed by conducting offline temperature rise tests and finite element simulations of the plum blossom contact, simulating pressure changes under different temperature rise levels, obtaining temperature-pressure coupling data, and then fitting the temperature-pressure compensation mathematical formula.

3. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 2, characterized in that, The mathematical formula for temperature-pressure compensation is: in This represents the raw pressure value, i.e., the value directly measured by the sensor; The pressure value after compensation; For real-time temperature measurement; For reference temperature, , This is the temperature compensation coefficient.

4. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 1, characterized in that, The construction steps of the KNN regression intelligent diagnostic model include: preprocessing and extracting multi-dimensional features from the compensated pressure data to construct a feature vector; classifying the health status of the plum blossom contactor into four levels: normal, slightly deteriorated, moderately deteriorated, and severely faulty, and defining the mapping relationship between the comprehensive three-dimensional index H and each health status level; and determining the nearest neighbor number k value of the KNN model through cross-validation grid search.

5. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 4, characterized in that, The feature vector includes average contact pressure, pressure distribution uniformity, and pressure decay rate.

6. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 4, characterized in that, The comprehensive three-dimensional index H is mapped to the feature vector using a weighted method, and the function is expressed as: in , , These represent the corresponding weight coefficients. F n This represents the nth pressure feature vector. w n Representing the n The weight coefficients corresponding to each pressure feature vector .

7. The method for online monitoring and failure assessment of switchgear stud contact pressure according to claim 1, characterized in that, The criteria for determining the health status level are as follows: when H∈[0.8,1], it is a normal state; when H∈[0.5,0.8), it is a slight deterioration; when H∈[0.3,0.5), it is a moderate deterioration; and when H∈[0,0.3), it is a serious fault.

8. A system for online monitoring and failure assessment of the pressure of a switchgear sprite contact for implementing the method of any one of claims 1 to 7, characterized in that, include: The sensing unit includes a pressure sensor and a temperature sensor installed on the contact finger (1) of the plum blossom contact, which are used to collect raw pressure data and temperature data in real time during the operation of the contact. A data transmission unit, connected to the sensing unit, is used to receive data collected by the sensing unit and upload it via a wireless transmission network; The monitoring and evaluation unit, connected to the data transmission unit, is used to receive uploaded data, execute the temperature compensation step and the status evaluation step, and output health status evaluation results and early warning information.

9. The online monitoring and failure assessment system for switchgear sprite contact pressure according to claim 8, characterized in that, The pressure sensor is a flexible thin-film pressure-sensitive array sensor. The pressure sensor includes a first pressure sensor ring (8) fitted on the front end of the finger of the plum blossom contact and a second pressure sensor ring (9) fitted on the rear end of the finger. Each pressure sensor ring is composed of three flexible thin-film pressure-sensitive array sensors, which are uniformly and symmetrically distributed around the contact axis at a spatial angle of 120 degrees.

10. The online monitoring and failure assessment system for switchgear perforated contact pressure according to claim 8, characterized in that, The temperature sensor is a wireless temperature sensor, which includes a temperature sensor body, an alloy base, a buckle and a silicone pad. The silicone pad is placed on the surface of the touch finger (1), the alloy base is placed on the silicone pad, the temperature sensor body is placed on the alloy base and is fastened to the touch finger (1) by the buckle.

Images