Power Equipment Fault Prediction Method Based on Support Vector Regression

Abstract

The present invention discloses a power equipment fault prediction method based on support vector regression, which relates to the technical field of equipment faults. By real-time monitoring the arc state and its changes in the circuit breaker, the arc concentration effect can be detected early, and a danger instruction can be issued in time, thereby improving the operation safety of power equipment and further avoiding the spread of faults; accurate fault assessment: by combining electrical and mechanical parameter analysis, the fault isolation coefficient Ggxs and the recovery impact coefficient Hyxs can be further scientifically calculated, making the fault assessment more accurate and providing an important basis for maintenance decisions; support vector regression model optimized prediction: using support vector regression technology to construct a fault prediction model can effectively handle complex relationships, and combine the fault isolation coefficient and the recovery impact coefficient for prediction, providing an accurate fault prediction score Gfz, improving the accuracy and timeliness of fault warning.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment failure, and in particular to a method for predicting power equipment failure based on support vector regression. Background Art

[0002] With the increasing complexity of power systems and the increase in equipment operating loads, the frequency and severity of power equipment failures are also on the rise. How to accurately predict power equipment failures and improve their reliability and safety has become an important research direction in current power engineering. In this field, support vector regression (SVR), as a common machine learning method, has been widely used in fault prediction and health management. Support vector regression can accurately predict the state changes of power equipment by constructing a regression model in a high-dimensional space. Therefore, the power equipment fault prediction method based on support vector regression aims to predict the potential failure risk of the equipment by accurately modeling the working state of the power equipment and combining the change information of various parameters.

[0003] At present, in the fault prediction of power equipment, traditional methods usually rely on the experience of maintenance personnel and regular inspection and maintenance, which has certain limitations. Through the service life of the equipment, appearance inspection and preset fault mode, the fault of the equipment is often discovered only when it occurs suddenly, which increases the difficulty and cost of repair. In complex equipment such as multi-circuit circuit breakers, the working conditions of power equipment (such as circuit breakers) are complex, and the occurrence of faults is often sudden and hidden, which is difficult to predict in time through traditional methods. For example, during the opening and closing process, the extinction state and generation risk of the arc are not effectively monitored and analyzed. Due to the lack of accurate real-time fault assessment, many faults are often discovered when the equipment is damaged or seriously abnormal, resulting in the risk of production interruption or equipment damage. If such faults are not discovered in time, they may cause the equipment to fail completely, thereby affecting the stability of the entire power system. For example, when the arc concentration effect of the circuit breaker occurs, if it is not identified in advance and appropriate measures are not taken, the arc may exist for a long time, causing contact damage, serious burning of electrical equipment, and even fire and other serious safety accidents. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method for predicting power equipment faults based on support vector regression, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented by the following technical scheme: a method for predicting power equipment faults based on support vector regression, comprising the following steps:

[0006] S1. Monitor the on / off working status in the circuit breaker in real time, so as to monitor the arc state in the arc extinguishing chamber in the circuit breaker during the opening and closing processes, obtain relevant formation change data information in each area of the arc, and judge whether there is a concentration effect in the arc based on the relevant formation change data information in each area of the arc. If there is, issue a danger instruction.

[0007] S2. Receive the danger instruction, monitor relevant electrical parameters and relevant mechanical parameters during the opening and closing processes, and analyze the extinguishing situation of the arc during the opening process and the risk of generating an arc during the closing process according to the relevant electrical parameters and relevant mechanical parameters, so as to calculate the fault isolation coefficient Ggxs and the recovery impact coefficient Hyxs.

[0008] S3. Use the support vector regression technology to construct a fault assessment and prediction model, combine the fault isolation coefficient Ggxs and the recovery impact coefficient Hyxs, input the fault isolation coefficient Ggxs and the recovery impact coefficient Hyxs into the fault assessment and prediction model, and after dimensionless processing, fit and output the fault prediction score Gfz.

[0009] S4. Preset a qualified range , by comparing and analyzing the fault prediction score Gfz with the qualified range , comprehensively judge the damage situation of the current circuit breaker, and take corresponding warning measures based on the judgment result.

[0010] Preferably, the specific steps of S1 include:

[0011] S11. Install limit switches on the moving parts of the contacts in the circuit breaker in advance to feedback the on / off fault status, and transmit the feedback content to the control center through a circuit. After receiving the feedback content, the control center classifies the feedback content to classify the opening state and the closing state.

[0012] S12. After performing the classification operation, monitor the arc state in the arc extinguishing chamber of the circuit breaker in real time, divide the arc into regions, respectively obtain the arc anode region, the arc column region and the arc cathode region, and through marking each region of the arc, based on the arc anode region, the arc column region and the arc cathode region, obtain relevant formation change data information in each region of the arc. Among them, the relevant formation change data information includes the temperature value in each region , the contact gap and the current density .

[0013] Preferably, the specific steps of S1 also include:

[0014] S13. Based on the relevant formation change data information in each region of the electric arc, by correlating the temperature value Wdz, the current density Dmd, and the contact gap Cjj, and after dimensionless processing, the presentation coefficient Cxxs is calculated and obtained. The presentation coefficient Cxxs is obtained through the following formula:

[0015] ;

[0016] In the formula, n represents the number of regions of the electric arc, and i represents the number of each region of the electric arc. represents the temperature value in the i-th region. represents the average temperature value of the electric arc. represents the current density in the i-th region. represents the average current density of the electric arc. represents the contact gap in the i-th region. represents the average contact gap of the electric arc. , and are all weight values, and the specific values are set by the user according to the situation.

[0017] Preferably, the specific steps of S1 further include:

[0018] S14. By comparing and analyzing the presentation coefficient Cxxs with a preset safety threshold Q, it is judged whether there is a concentration effect in the generation of the electric arc. The specific comparison content is as follows:

[0019] If the presentation coefficient Cxxs exceeds the preset safety threshold Q, it is judged that there is a concentration effect in the generation of the electric arc at this time, and a danger instruction is triggered to further analyze the damage effect of the current electric arc on the circuit breaker;

[0020] If the presentation coefficient Cxxs does not exceed the preset safety threshold Q, it is judged that there is no concentration effect in the generation of the electric arc at this time, and the danger instruction is not triggered temporarily.

[0021] Preferably, the specific steps of S2 include:

[0022] S21. After receiving the danger instruction triggered by S14, monitor the relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Among them, the relevant electrical parameters include the breaking current , the arc voltage , the arc extinction duration , the opening speed and the current frequency during the opening process, and the closing voltage , the closing speed and the closing current ; The relevant mechanical parameters include the opening time of each contact at the break during the opening process and the opening time of each contact at the break during the closing process ;

[0023] S22. Based on the relevant mechanical parameters during the opening process and the relevant mechanical parameters during the closing process, extract the opening timestamps and closing timestamps of the contacts at several groups of breaks in the circuit breaker, and analyze the isolation differences and connection differences of the circuit breaker in different power circuits according to the opening timestamps and closing timestamps of the contacts at several groups of breaks in the circuit breaker, so as to obtain the opening action difference factor and the closing action difference factor , which are specifically obtained through the following formula:

[0024] ;

[0025] In the formula, m represents the number of breaks, j represents the corresponding break number, represents the opening time at the j-th break, represents the average opening time, represents the closing time at the j-th break, represents the average closing time.

[0026] Preferably, the specific steps of S2 further include:

[0027] S23. According to the relevant electrical parameters and relevant mechanical parameters during the opening process, and combined with the opening action difference factor obtained in S22 , analyze the extinguishing situation of the arc in the circuit breaker in different power circuits during the opening process, and after dimensionless processing, obtain the fault isolation coefficient Ggxs. The fault isolation coefficient Ggxs is obtained through the following formula:

[0028] ;

[0029] In the formula, represents the arc extinguishing duration, represents the breaking current, represents the arc voltage, represents the current frequency, represents the opening speed, , 2, 3, 4, 5 and 6 respectively represent the arc extinguishing duration , the breaking current , the arc voltage , the current frequency , the difference factor of opening operation and the opening speed The weight values are specifically set by the user according to the situation.

[0030] Preferably, the specific steps of S2 further include:

[0031] S24. According to the relevant electrical parameters and relevant mechanical parameters during the closing process, and in combination with the closing action difference factor obtained in S22 , analyze the risk of the circuit breaker generating electric arcs in different power circuits during the closing process, and after dimensionless processing, obtain the recovery influence coefficient Hyxs. The recovery influence coefficient Hyxs is obtained through the following formula:

[0032] ;

[0033] In the formula, represents the closing current, represents the closing voltage, represents the closing speed, , , and respectively represent the weight values of the closing current , the closing voltage , the closing action difference factor and the closing speed The weight values are specifically set by the user according to the situation.

[0034] Preferably, the specific steps of S3 include:

[0035] S31. Use the support vector regression technology to construct an initial model, and train and test the initial model with the relevant formation change data information in each area of the electric arc, as well as the relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Then use the trained initial model as the state recognition model, respectively obtain the characteristic information in the state recognition model, and train and test the state recognition model with the obtained characteristic information. In combination with the danger instruction triggered in S14, use the trained state recognition model as the fault assessment and prediction model, and after dimensionless processing, fit and output the fault prediction score Gfz.

[0036] Preferably, the specific steps of S3 further include:

[0037] S32. The fault prediction score Gfz is obtained through the following formula:

[0038] ;

[0039] In the formula, and All are weight values. represents a correction constant, ln is represented as a logarithmic function, where 0 < < 1, 0 < < 1, and the specific values are set by the user according to the situation.

[0040] Preferably, the specific steps of S4 include:

[0041] S41. By comparing and analyzing the fault prediction score Gfz with the qualified range to comprehensively judge the damage condition of the current circuit breaker. The specific judgment content is as follows:

[0042] If the fault prediction score Gfz falls within the qualified range at this time, it will be comprehensively judged that the current circuit breaker is in a safe state, and the operation state of the circuit breaker will continue to be monitored, and the currently obtained fault prediction score Gfz will be saved as historical data;

[0043] If the fault prediction score Gfz does not fall within the qualified range at this time, it will be comprehensively judged that the current circuit breaker is not in a safe state, and the current circuit breaker will be temporarily deactivated, switched to the standby equipment, and at the same time, the fault alarm system will be activated to send a warning notice to the maintenance personnel and arrange for multiple circuit breakers to work in parallel.

[0044] The present invention provides a power equipment fault prediction method based on support vector regression, which has the following beneficial effects:

[0045] (1) Real-time monitoring and early warning: By real-time monitoring the arc state and its changes in the circuit breaker, the arc concentration effect can be detected early, and a danger instruction can be issued in time, thereby improving the operation safety of power equipment and further avoiding the spread of faults; Accurate fault assessment: Combining electrical and mechanical parameter analysis, the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs can be further scientifically calculated, making the fault assessment more accurate and providing an important basis for maintenance decision-making. Support vector regression model optimization prediction: Using support vector regression technology to construct a fault prediction model can effectively handle complex relationships, combine the fault isolation coefficient and the recovery influence coefficient for prediction, provide an accurate fault prediction score Gfz, and improve the accuracy and timeliness of fault warning. Precise warning and efficient maintenance: By comparing the fault prediction score with the preset qualified range, a multi-faceted assessment of the equipment damage condition is realized, ensuring the timeliness and pertinence of warning and maintenance measures, thereby optimizing the operation and maintenance management of power equipment and further extending the service life of the equipment. In short, this method not only improves the fault prediction accuracy of power equipment, but also effectively reduces the potential losses and safety hazards caused by power equipment faults.

[0046] (2) By correlating multi-dimensional parameters in each region of the electric arc and calculating the presentation coefficient Cxxs after dimensionless processing, this multi-dimensional data processing method can comprehensively consider the temperature, intensity, and contact state of the electric arc in different regions, fully reflecting the changes in the electric arc in different regions and avoiding the errors that may be brought by single-parameter analysis. The dimensionless process ensures the balance of the influence of each parameter on the final result, thus improving the accuracy of the fault prediction and evaluation model. By introducing the presentation coefficient Cxxs for quantitative analysis of the electric arc state, it is possible to effectively judge whether there is a concentration effect in the electric arc. The concentration effect reflects the degree of heat and energy aggregation of the electric arc in different regions, which is crucial for evaluating the danger of the electric arc. If the presentation coefficient Cxxs exceeds the preset safety threshold Q, the system will promptly judge that the electric arc has a concentration effect and trigger a danger instruction. This concentration effect judgment mechanism enables the system to quickly discover potential dangers at the initial stage of the electric arc generation, take preventive measures in a timely manner, and reduce the risk of equipment damage and failure.

[0047] (3) By extracting the opening timestamps and closing timestamps of the contacts at each break in the circuit breaker, the present invention can comprehensively understand the operating state of the circuit breaker in a multi-loop situation. The advantage of this method is that it can separately monitor the opening and closing processes of each power loop, identify the behavioral differences of each break during the operation, and provide a basis for further analyzing the multi-loop performance and isolation of the circuit breaker. This detailed timestamp analysis mechanism enables the system to discover possible operation inconsistencies between power loops. Since too large a time difference may cause some breaks to bear excessive current or arc energy, potential faults can be further avoided. By quantifying the difference factor and comparing it with the preset standard, the system can effectively improve the fault warning and equipment maintenance efficiency, ensuring the safety and reliability of power equipment.

[0048] (4) During the closing process, the present invention combines electrical and mechanical parameters such as closing current, closing voltage, and closing speed, as well as the closing action difference factor, to analyze the risk of arc generation during closing in different power loops. By calculating the recovery influence coefficient Hyxs, the system can quantitatively evaluate the closing risk of each loop, identify possible arc generation risks in advance, and reduce the possibility of power equipment damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic flow chart of the power equipment fault prediction method based on support vector regression of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0051] Embodiment 1: Please refer to Figure 1 , the present invention provides a power equipment fault prediction method based on support vector regression, including the following steps

[0052] S1. Monitor the on-off working state in the circuit breaker in real time, and during the opening and closing processes of the on-off operation, monitor the arc state in the arc extinguishing chamber in the circuit breaker to obtain relevant formation change data information in each area of the arc. Based on the relevant formation change data information in each area of the arc, determine whether there is a concentration effect in the arc. If so, issue a danger instruction.

[0053] S2. Receive the danger instruction, and monitor relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. According to the relevant electrical parameters and relevant mechanical parameters, analyze the extinguishing situation of the arc during the opening process and the risk of generating an arc during the closing process, so as to calculate the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs.

[0054] S3. Use the support vector regression technology to construct a fault evaluation and prediction model, combine the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs, and input the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs into the fault evaluation and prediction model. After dimensionless processing, fit and output the fault prediction score Gfz.

[0055] S4. Preset a qualified range , by comparing and analyzing the fault prediction score Gfz with the qualified range , comprehensively judge the damage situation of the current circuit breaker, and take corresponding warning measures based on the judgment result.

[0056] In this embodiment, the method monitors the arc state in the circuit breaker in real time, discovers the arc concentration effect in time, and thus issues a danger instruction before the electrical equipment fails. By combining the relevant data in the arc area to form a change trend and monitoring the electrical and mechanical parameters during the opening and closing processes, this method improves the accuracy of early fault identification and enhances the fault warning ability. Compared with the traditional method, the present invention can take preventive measures in advance, reduce equipment damage and outage time, and improve the safety and reliability of power equipment. The present invention uses the support vector regression technology to construct a fault assessment and prediction model. As a powerful machine learning algorithm, SVR can perform efficient fitting and prediction in complex non-linear relationships. By inputting the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs, after dimensionless processing, the fault prediction score Gfz is output by fitting. This model can provide accurate fault prediction scores according to different historical data and working conditions, so as to provide data support for judging the damage degree of the circuit breaker and taking corresponding maintenance measures. Through the comparison and analysis of the preset qualified range and the fault prediction score Gfz, the present invention provides an effective fault assessment method, which can judge the damage condition of the current circuit breaker in real time and accurately. Compared with the traditional regular inspection method, the evaluation mechanism of the present invention is more intelligent and automated, reduces the interference of human factors, and provides a dynamic and real-time fault assessment system. It can take corresponding warning means according to the scoring results, issue warnings in time, and prevent the further expansion of faults. Since potential faults can be detected early, the system can take maintenance or isolation measures in advance, avoid serious damage to the equipment due to faults, and reduce the equipment downtime and maintenance costs caused by sudden faults. In addition, through intelligent monitoring and prediction, the present invention can reduce the frequency of manual inspections and effectively improve the operation efficiency of the system and the long-term stability of the equipment.

[0057] Embodiment 2: Please refer to Figure 1 , specifically: The specific steps of S1 include:

[0058] S11. A limit switch is pre-installed on the moving part of the inner contact of the circuit breaker to feedback the fault state of opening and closing, and the feedback content is transmitted to the control center through a circuit. After receiving the feedback content, the control center classifies the feedback content to classify the opening state and the closing state;

[0059] S12. After performing the classification operation, the arc state in the arc extinguishing chamber of the circuit breaker is monitored in real time, and the arc is divided into regions to respectively obtain the arc anode region, the arc column region and the arc cathode region. By marking each region of the arc, based on the arc anode region, the arc column region and the arc cathode region, the relevant formation change data information in each region of the arc is obtained. Among them, the relevant formation change data information includes the temperature value in each region , contact gap and current density 。

[0060] In this embodiment, the method pre-sets a limit switch on the moving part of the inner contact of the circuit breaker to timely feedback the fault state of opening and closing. This real-time feedback of the fault state can not only reflect the working state of the circuit breaker in time, but also transmit the information to the control center through the circuit for further classification operations. By classifying the opening and closing states, the operating conditions of the circuit breaker in different working states can be clearly distinguished, the operating state where the fault occurs can be accurately identified, the maintenance mistakes and equipment damage caused by misjudgment are effectively reduced, and the fault diagnosis accuracy of the circuit breaker is improved. After performing the classification operation, the method monitors the arc state in the arc extinguishing chamber of the circuit breaker in real time and divides the arc into an anode region, an arc column region, and a cathode region. Through this precise arc region division, the monitoring of the arc process can be refined to ensure that the arc state in each region is effectively tracked. The precise division of the anode region, arc column region, and cathode region of the arc helps to grasp the propagation and change of the arc in real time, providing a more detailed basis for subsequent fault assessment. Based on the relevant formation change data information in each region of the arc, the method collects multiple parameters including temperature value, contact gap, and current density. These multi-dimensional data can comprehensively reflect the arc state and its change trend, and thus help to accurately analyze the stability and danger of the arc. For example, the temperature value can reflect the thermal state of the arc, and the contact gap and current density help to judge the intensity of the arc and the risk of overload. The collection and analysis of this multi-dimensional data enhance the reliability and accuracy of the fault prediction model. Through the marking process and data collection of each region of the arc, the method can detect abnormal changes in time at the initial stage of arc formation and respond quickly. Different from the traditional global monitoring method, the present invention adopts a local area monitoring method, which can detect any subtle changes at the early stage of arc generation, further improving the sensitivity of the system to potential faults, giving early fault warnings, and avoiding equipment damage or shutdown caused by arc faults. By inputting data such as the temperature value, contact gap, and current density of each region of the arc into the subsequent prediction model, the system can automatically analyze the stability and risk of the arc, monitor the working state of the circuit breaker in real time without manual intervention. This intelligent and automated working mode maximally improves the reliability of the equipment and effectively reduces the workload of manual inspection and the risk of misjudgment.

[0061] Embodiment 3: Please refer to Figure 1 Specifically, the specific steps of S1 further include:

[0062] S13. Based on the relevant formation change data information in each region of the electric arc, by correlating the temperature value Wdz, the current density Dmd, and the contact gap Cjj, and after dimensionless processing, the presentation coefficient Cxxs is calculated and obtained. The presentation coefficient Cxxs is obtained through the following formula:

[0063] ;

[0064] In the formula, n represents the number of regions of the electric arc, and i represents the number of each region of the electric arc. represents the temperature value in the i-th region. represents the average temperature value of the electric arc. represents the current density in the i-th region. represents the average current density of the electric arc. represents the contact gap in the i-th region. represents the average contact gap of the electric arc. , and are all weight values. Among them, 0 < < 1, 0 < < 1, 0 < < 1. The specific values are set by the user according to the situation.

[0065] The temperature values in the above-mentioned regions are monitored and obtained through a temperature sensor;

[0066] The contact gap refers to the physical distance between the breaker contacts (including the fixed contact and the moving contact). During the opening and closing processes of the breaker, the contact gap changes. The size of the contact gap affects the quality of current interruption or connection, and is directly related to the generation and extinction effects of the electric arc. Usually, a displacement sensor (such as a laser displacement sensor or a capacitive displacement sensor) can be used to monitor the change of the contact gap.

[0067] The current density refers to the amount of current passing through a unit cross-sectional area, and is usually used to evaluate the pressure of the conductive material during current flow. Excessive current density may cause overheating, damage or too long electric arc of the breaker contacts. Usually, the current passing through the circuit can be measured through a current sensor (such as a Hall effect sensor), and then the current density can be calculated;

[0068] The specific steps of S1 also include:

[0069] S14. By comparing and analyzing the presentation coefficient Cxxs with a pre-set safety threshold Q, to judge whether there is a concentration effect in the generation of the electric arc. The specific comparison content is as follows:

[0070] When the presentation coefficient Cxxs exceeds the pre-set safety threshold Q, it is determined at this time that the generation of the arc has a concentration effect, and a danger instruction is triggered to further analyze the damage effect of the current arc on the circuit breaker;

[0071] When the presentation coefficient Cxxs does not exceed the pre-set safety threshold Q, it is determined at this time that the generation of the arc does not have a concentration effect temporarily, and the danger instruction is not triggered temporarily.

[0072] In this embodiment, by performing non-dimensional processing on the temperature value, contact gap, and current density and calculating the presentation coefficient Cxxs, the present invention can comprehensively analyze multi-dimensional data in each region of the arc. Relevant data in each region can be fully considered. This method can not only reflect the changes in a single variable but also capture the interaction effects of various variables within the arc region. By integrating and calculating these key parameters, the present invention can more accurately evaluate the state and development trend of the arc, further improving the accuracy and reliability of arc monitoring. By comparing and analyzing the presentation coefficient Cxxs with the pre-set safety threshold Q, the present invention can determine whether the arc has a concentration effect. If the presentation coefficient Cxxs exceeds the safety threshold Q, a danger instruction will be triggered, thus timely warning and further evaluating the risk of the arc. This judgment method based on comparison and analysis makes the discovery of the arc concentration effect more efficient and accurate. By judging the concentration effect, the system can identify in advance the hazards that the arc may cause to the circuit breaker, prevent the equipment from suffering serious failures due to the arc concentration effect, and improve the safety of the equipment. Throughout the process, the system continuously monitors the formation and change of the arc and updates the data in real time to ensure a real-time reflection of the arc state. Different from the traditional periodic inspection method, the present invention can continuously monitor the arc state and make dynamic responses based on real-time data. This continuous and real-time monitoring method can adjust and optimize the operation strategy at any time to ensure that preventive or response measures can be taken promptly when the arc state is abnormal, improving the system's response speed and processing ability to faults.

[0073] Example 4: Please refer to Figure 1 , specifically: The specific steps of S2 include:

[0074] S21. After receiving the danger instruction triggered by S14, monitor the relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Among them, the relevant electrical parameters include the breaking current during the opening process , arc voltage , arc extinction duration , opening speed and current frequency , and during the closing process, the closing voltage , closing speed and closing current ; The relevant mechanical parameters include the opening time of each contact at the break during the opening process and the opening time of each contact at the break during the closing process ;

[0075] S22. Based on the relevant mechanical parameters during the opening process and the relevant mechanical parameters during the closing process, extract the opening timestamps and closing timestamps of the contacts at several groups of breaks in the circuit breaker, and analyze the isolation differences and connection differences of the circuit breaker in different power circuits (multi-breaks) according to the opening timestamps and closing timestamps of the contacts at several groups of breaks in the circuit breaker, so as to obtain the opening action difference factor and the closing action difference factor , which are specifically obtained through the following formula:

[0076] ;

[0077] In the formula, m represents the number of breaks, j represents the corresponding break number, represents the opening time at the j-th break, represents the average opening time, represents the closing time at the j-th break, represents the average closing time.

[0078] The above-mentioned opening action difference factor and the closing action difference factor are used to quantify the time dispersion of closing and opening of each break, and further reflect the closing and opening performance of the circuit breaker;

[0079] The opening time of each break during the above-mentioned opening process and the opening time of each break during the closing process can both be measured and obtained through a time sensor (such as a high-precision timer).

[0080] Different power circuits usually mean that each power circuit will correspond to an independent break. In a multi-break circuit breaker, each break carries a current circuit. When the circuits in the power system need to be opened or closed, the current of each circuit will be processed through its respective break. In a multi-break circuit breaker, a break usually corresponds to a power circuit, and the function of each break is to independently open or close a current circuit.

[0081] In this embodiment, the present invention can quantify the action differences of each breaker contact during opening and closing processes by recording and analyzing the opening time and closing time of each breaker contact in detail. By analyzing the isolation differences and connection differences between different breaker contacts (i.e., different power circuits), the opening and closing performance of each circuit can be accurately evaluated. This analysis helps to detect action delays or inconsistencies in different circuits, and thus provides a basis for fault diagnosis and equipment optimization to ensure the reliability of the system in complex working environments. By extracting the contact opening timestamp and closing timestamp at each breaker contact and using a formula to calculate the opening action difference factor and closing action difference factor, the time dispersion degree of each breaker contact during opening and closing processes can be quantified. This method can effectively evaluate the opening and closing time differences of each breaker contact in the power circuit and identify potential performance imbalance problems.

[0082] Embodiment 5: Please refer to Figure 1 , specifically: The specific steps of S2 further include:

[0083] S23. According to the relevant electrical parameters and relevant mechanical parameters during the opening process, and in combination with the opening action difference factor obtained in S22 , analyze the arc extinction situation of the circuit breaker in different power circuits during the opening process. After dimensionless processing, obtain the fault isolation coefficient Ggxs, and the fault isolation coefficient Ggxs is obtained through the following formula:

[0084] ;

[0085] In the formula, represents the arc extinction duration, represents the breaking current, represents the arc voltage, represents the current frequency, represents the opening speed, 、 2、 3、 4、 5 and 6 respectively represent the weight values of the arc extinction duration , breaking current , arc voltage , current frequency , opening action difference factor and opening speed , where 0 < < 1, 0 < 2 < 1, 0 < 3 < 1, 0 < 4 < 1, 0 < 5 < 1, 0 < 6 < 1, and the specific value is set by the user according to the situation.

[0086] The above-mentioned arc extinction duration refers to the time required for the arc to be completely extinguished after the breaking current passes through the circuit breaker. Usually, the presence and disappearance of the arc can be monitored by an arc sensor (such as a photoelectric sensor or an infrared sensor), and the arc extinction duration can be obtained by monitoring the duration of the arc;

[0087] Breaking current refers to the current intensity cut off by the circuit breaker during the opening process. The magnitude of the breaking current determines the characteristics of the arc. An excessive breaking current may cause the arc to fail to extinguish. The magnitude of the current can be measured by a current sensor, and the change of the current can be monitored;

[0088] Arc voltage refers to the voltage value when the arc exists. The arc voltage is usually relatively high. During the arc extinction process, the arc voltage will gradually decrease, and its value can be monitored and obtained by a voltage sensor;

[0089] Current frequency refers to the change rate of the current, indicating the fluctuation frequency of the current. During the opening or closing process, the change of the current frequency will affect the characteristics of the arc; its value can be measured by a frequency sensor or a current sensor to measure the frequency of the current and monitor the fluctuation of the current.

[0090] Opening speed refers to the speed at which the contacts of the circuit breaker open during the opening process, which can be measured by a displacement sensor or a speed sensor.

[0091] The specific steps of S2 also include:

[0092] S24. According to the relevant electrical parameters and relevant mechanical parameters during the closing process, and combined with the closing action difference factor obtained in S22 , analyze the risk of the circuit breaker generating an arc in different power circuits during the closing process, and after dimensionless processing, obtain the recovery influence coefficient Hyxs. The recovery influence coefficient Hyxs is obtained through the following formula:

[0093] ;

[0094] In the formula, represents the closing current, represents the closing voltage, represents the closing speed, , , and respectively represent the closing current , the closing voltage , closing action difference factor and closing speed of the weight values, where 0 < < 1, 0 < < 1, 0 < < 1, 0 < < 1, and the specific values are set by the user according to the situation.

[0095] The above-mentioned closing current refers to the current allowed to flow during the closing process of the circuit breaker. The magnitude of the closing current will affect the generation and extinction of the arc during the closing process and can be monitored and obtained through a current sensor;

[0096] Closing voltage refers to the voltage applied to the circuit when the circuit breaker closes. The magnitude of the voltage will affect the impact force of the closing current and the generation of the arc and can be monitored and obtained through a voltage sensor;

[0097] Closing speed refers to the closing speed of the contacts during the closing process of the circuit breaker and can be measured by a displacement sensor or a speed sensor.

[0098] In this embodiment, the present invention calculates the fault isolation coefficient Ggxs by analyzing the arc extinction situation of the circuit breaker in different power circuits during the opening process, combining relevant electrical and mechanical parameters and the opening action difference factor. This analysis method provides data support for evaluating the efficiency of arc extinction and the reliability of circuit isolation. Especially in multi-break circuit breakers, it can accurately identify the arc extinction state and ensure the safety and stability of electrical equipment. Through dimensionless processing, the dimensional differences between different parameters can be eliminated, making the data comparable and consistent, thus ensuring the more scientific and accurate calculation of the fault isolation coefficient. By calculating the fault isolation coefficient Ggxs, the present invention can effectively evaluate the isolation effect of different circuit breaks in the power line, provide an accurate basis for the stable operation and fault warning of electrical equipment, and effectively improve the safety and reliability of the power system. In short, by analyzing the arc extinction situation and the risk of arc generation, the system provides an efficient and real-time monitoring and evaluation tool for the power circuit, can timely detect and respond to potential risks, and improve the safety and stability of the power system.

[0099] Example 6: Please refer to Figure 1 , specifically: The specific steps of S3 include:

[0100] S31. Construct an initial model using support vector regression technology, and train and test the initial model with the relevant formation change data information in each area of the electric arc, as well as the relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Then, use the trained initial model as the state recognition model, respectively obtain the feature information in the state recognition model, and train and test the state recognition model with the obtained feature information. Combining with the dangerous instruction triggered in S14, use the trained state recognition model as the fault assessment and prediction model. After dimensionless processing, fit and output the fault prediction score Gfz.

[0101] The specific steps of S3 also include:

[0102] S32. The fault prediction score Gfz is obtained through the following formula:

[0103] ;

[0104] In the formula, and are both weight values, represents a correction constant, ln represents a logarithmic function, where, 0 < < 1, 0 < < 1, and the specific values are set by the user according to the situation.

[0105] The specific steps of S4 include:

[0106] S41. By comparing and analyzing the fault prediction score Gfz with the qualified range , comprehensively judge the damage situation of the current circuit breaker. The specific judgment content is as follows:

[0107] If the fault prediction score Gfz falls within the qualified range , at this time, it will be comprehensively judged that the current circuit breaker is in a safe state, and continue to monitor the operating state of the circuit breaker to ensure that the equipment is regularly inspected and maintained under normal conditions, such as checking the contact wear, lubrication system, and insulation situation, etc., and save the currently obtained fault prediction score Gfz as historical data for subsequent analysis. At the same time, record and archive the relevant data for long-term trend analysis;

[0108] If the fault prediction score Gfz does not fall within the qualified range , at this time, it will be comprehensively judged that the current circuit breaker is not in a safe state, and take measures to temporarily deactivate the current circuit breaker and switch to the standby equipment to prevent major failures. At the same time, activate the fault alarm system, send a warning notice to the maintenance personnel, and arrange for multiple circuit breakers to work in parallel to further ensure the continuous operation of the system and avoid the complete failure of the system due to a single circuit breaker failure in the future.

[0109] The above-mentioned qualified range is set as follows: Based on historical data, a number of groups of fault prediction scores Gfz are obtained, and combined with statistical algorithms, the average fault prediction score and the standard deviation of the fault prediction score are calculated respectively, and based on the average fault prediction score and the standard deviation of the fault prediction score , the qualified range is set as: ; where is a constant, usually taking values from 1 to 3, corresponding to different confidence levels respectively, and the specific value is set by the user (according to the actual situation). Similarly, the setting method of the above-mentioned safety threshold Q is similar to that of the qualified range .

[0110] In this embodiment, the present invention effectively obtains the change information in each area of the electric arc by constructing an initial model using the support vector regression (SVR) technology and combining the electrical and mechanical parameters during the opening and closing processes. The establishment of such a model makes the fault prediction of the circuit breaker more accurate. Through dimensionless processing, the trained state recognition model can fit and output a fault prediction score Gfz, which can be used to measure the current state of the circuit breaker. This method further improves the accuracy of fault prediction, helps to identify potential problems in a timely manner, and thus prevents the performance degradation of the equipment before a fault occurs. Through the multi-dimensional data fusion method, not only the accuracy of the state recognition model is improved, but also the system can capture the precursors of fault risks more comprehensively, so as to predict and evaluate the operating state of the circuit breaker more effectively. When the fault prediction score falls within the qualified range, the system will determine that the circuit breaker is in a safe state and continue to monitor it to ensure that the equipment is maintained on schedule under normal conditions. This process not only ensures the continuous operation of the equipment, but also provides historical data support for long-term trend analysis. If the fault prediction score does not fall within the qualified range, the system can trigger a fault alarm in a timely manner, send a warning notice to the maintenance personnel, and take emergency measures such as switching to standby equipment and parallel operation to avoid the failure of the entire system due to the failure of a single circuit breaker. When the system detects that the fault prediction score of the circuit breaker deviates from the qualified range, the system will automatically start the warning mechanism, deactivate the faulty circuit breaker in a timely manner and switch to the standby equipment. This mechanism effectively avoids the outage or catastrophic failure of the power system caused by the failure of a single device. Through this intelligent decision-making process, the system can ensure the continuous operation of power facilities and the stability of power supply, and reduce the outage time and fault repair time of the system. In short, the fault prediction score Gfz of this system provides an accurate equipment evaluation index, effectively prevents the system outage caused by equipment failure, and provides important support for the maintenance and management of equipment. Through adaptive parameter setting and historical data analysis, the system can continuously optimize its operation and improve the safety, stability and reliability of the power system.

[0111] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power equipment fault prediction method based on support vector regression, characterized in that: Including the following steps, S1. Monitor the opening and closing working states in the circuit breaker in real time. During the opening and closing processes of the circuit breaker, monitor the arc state in the arc extinguishing chamber in the circuit breaker to obtain relevant formation change data information in each area of the arc, and based on the relevant formation change data information in each area of the arc, judge whether there is a concentration effect in the arc. If so, issue a danger instruction; S2. Receive the danger instruction, monitor relevant electrical parameters and relevant mechanical parameters during the opening and closing processes, and analyze the extinguishing situation of the arc during the opening process and the risk of generating an arc during the closing process according to the relevant electrical parameters and relevant mechanical parameters, so as to calculate the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs; S3. Use the support vector regression technology to construct a fault assessment and prediction model, combine the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs, input the fault isolation coefficient Ggxs and the recovery influence coefficient Hyxs into the fault assessment and prediction model, and after dimensionless processing, fit and output the fault prediction score Gfz; S4. Preset a qualified range , by comparing and analyzing the fault prediction score Gfz with the qualified range , comprehensively judge the damage condition of the current circuit breaker, and take corresponding warning measures based on the judgment result.

2. The power equipment fault prediction method based on support vector regression according to claim 1, characterized in that: The specific steps of S1 include: S11. Pre-install limit switches on the moving parts of the inner contacts in the circuit breaker to feedback the fault states of opening and closing, and transmit the feedback content to the control center through a circuit. After receiving the feedback content, the control center classifies the feedback content to classify the opening state and the closing state; S12. After performing the classification operation, the arc state in the arc extinguishing chamber of the circuit breaker is monitored in real time, and the arc is divided into regions to separately obtain the arc anode region, the arc column region, and the arc cathode region. By marking each region of the arc, relevant formation change data information within each region of the arc is obtained based on the arc anode region, the arc column region, and the arc cathode region. Among them, the relevant formation change data information includes the temperature value , contact gap and current density .

3. The power equipment fault prediction method based on support vector regression according to claim 2, characterized in that: The specific steps of S1 also include: S13. According to the relevant formation change data information in each area of the arc, by correlating the temperature value Wdz, the current density Dmd and the contact gap Cjj, and after dimensionless processing, calculate and obtain the presentation coefficient Cxxs. The presentation coefficient Cxxs is obtained through the following formula: ； In the formula, n represents the number of regions of the arc, and i represents the numbering of each region of the arc. represents the temperature value in the i-th region. represents the average temperature value of the arc. represents the current density in the i-th region. represents the average current density of the arc. represents the contact gap in the i-th region. represents the average contact gap of the arc. , and are all weight values, and the specific values are set by the user according to the situation.

4. The power equipment fault prediction method based on support vector regression according to claim 3, characterized in that: The specific steps of S1 also include: S14. By comparing and analyzing the presentation coefficient Cxxs with a pre-set safety threshold Q, judge whether there is a concentration effect in the generation of the arc. The specific comparison content is as follows: If the presentation coefficient Cxxs exceeds the pre-set safety threshold Q, it will be judged that there is a concentration effect in the generation of the arc at this time, and a danger instruction will be triggered to further analyze the damage impact of the current arc on the circuit breaker; If the presentation coefficient Cxxs does not exceed the pre-set safety threshold Q, it will be judged that there is no concentration effect in the generation of the arc at this time, and the danger instruction will not be triggered temporarily.

5. The power equipment fault prediction method based on support vector regression according to claim 4, characterized in that: The specific steps of S2 include: S21. After receiving the danger instruction triggered by S14, monitor relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Among them, the relevant electrical parameters include the breaking current during the opening process , the arc voltage , the arc extinction duration , the opening speed and the current frequency , as well as the closing voltage during the closing process , the closing speed and the closing current ; the relevant mechanical parameters include the opening time at each contact during the opening process and the opening time at each contact during the closing process ; S22. Based on the relevant mechanical parameters during the opening process and the relevant mechanical parameters during the closing process, extract the opening timestamps and closing timestamps of the contacts at several sets of breaker contacts, and analyze the isolation differences and connection differences of the breaker in different power circuits according to the opening timestamps and closing timestamps of the contacts at several sets of breaker contacts, so as to obtain the opening action difference factor and the closing action difference factor , which are obtained specifically through the following formula: ； In the formula, m represents the number of fracture surfaces, and j represents the corresponding fracture surface number. represents the opening time at the j-th fracture surface. represents the average opening time. represents the closing time at the j-th fracture surface. represents the average closing time.

6. The power equipment fault prediction method based on support vector regression according to claim 5, characterized in that: The specific steps of S2 also include: S23. According to the relevant electrical parameters and relevant mechanical parameters during the opening process, and in combination with the opening action difference factor obtained in S22 , analyze the extinguishing situation of the arc of the circuit breaker in different power circuits during the opening process, and after dimensionless processing, obtain the fault isolation coefficient Ggxs. The fault isolation coefficient Ggxs is obtained through the following formula: ； In the formula, represents the arc extinction duration, represents the breaking current, represents the arc voltage, represents the current frequency, represents the opening speed, and 2, 3, 4, 5 and 6 respectively represent the arc extinction duration , the breaking current , the arc voltage , the current frequency , the opening operation difference factor and the opening speed weight values, and the specific values are set by the user according to the situation.

7. The power equipment fault prediction method based on support vector regression according to claim 5, characterized in that: The specific steps of S2 also include: S24. According to the relevant electrical parameters and relevant mechanical parameters during the closing process, and in combination with the closing action difference factor obtained in S22 , analyze the risk of the circuit breaker generating an arc in different power circuits during the closing process, and after dimensionless processing, obtain the recovery influence coefficient Hyxs. The recovery influence coefficient Hyxs is obtained through the following formula: ； In the formula, represents the closing current, represents the closing voltage, represents the closing speed, , , and respectively represent the weights of the closing current , the closing voltage , the closing action difference factor and the closing speed , and the specific values are set by the user according to the situation.

8. The power equipment fault prediction method based on support vector regression according to claim 4, characterized in that: The specific steps of S3 include: S31. Use the support vector regression technology to construct an initial model, and train and test the initial model with the relevant formation change data information in each area of the arc, as well as the relevant electrical parameters and relevant mechanical parameters during the opening and closing processes. Take the trained initial model as the state recognition model, respectively obtain the characteristic information in the state recognition model, and train and test the state recognition model with the obtained characteristic information. Combine the danger instruction triggered in S14, and take the trained state recognition model as the fault assessment and prediction model. After dimensionless processing, fit and output the fault prediction score Gfz.

9. The power equipment fault prediction method based on support vector regression according to claim 8, wherein: The specific steps of S3 also include: S32. The failure prediction score Gfz is obtained through the following formula: ； In the formula, and are both weight values, represents a correction constant, and ln represents a logarithmic function, where 0 < < 1, 0 < < 1, and the specific values are set by the user according to the situation.

10. The power equipment fault prediction method based on support vector regression according to claim 1, wherein: The specific steps of S4 include: S41. By comparing and analyzing the fault prediction score Gfz with the qualified range to comprehensively judge the damage condition of the current circuit breaker. The specific judgment content is as follows: If the fault prediction score Gfz falls within the qualified range At this time, it will be comprehensively judged that the current circuit breaker is in a safe state, and the operating state of the circuit breaker will continue to be monitored, and the currently obtained fault prediction score Gfz will be saved as historical data; If the fault prediction score Gfz does not fall within the qualified range At this time, it will be comprehensively judged that the current circuit breaker is not in a safe state, and the current circuit breaker will be temporarily deactivated, switched to the standby equipment, and at the same time the fault alarm system will be activated to send a warning notice to the maintenance personnel, and arrangements will be made to use multiple circuit breakers in parallel.

Images