Power equipment monitoring analysis early warning system

Abstract

The invention relates to the technical field of power transformers, in particular to a power equipment monitoring, analyzing and early warning system, which comprises a data acquisition module used for acquiring the operation state of power equipment, and the operation state comprises the work cycle and the operation data of the power equipment; the operation data comprises real-time load change information, operation temperature, overvoltage impact times, water content of insulating oil and dielectric loss angle tangent value of the insulating oil; the trend identification module is used for acquiring the fault characteristics of the power equipment in the corresponding operation state based on the operation state of the power equipment, identifying the fault trend of the power equipment, and calculating the fault coefficient of the power equipment according to the fault trend of the power equipment; the fault analysis module is used for generating a fault analysis tree corresponding to the power equipment based on the fault coefficient, and sequentially determining a fault relation coefficient, a data fault proportion and a fault period of the power equipment; reliability and accuracy of power equipment detection are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformers, and in particular to a power equipment monitoring, analysis and early warning system. Background Art

[0002] The stable operation of power equipment is crucial to the reliability of the power system. However, over long-term operation, power equipment is affected by a variety of factors, such as environmental conditions, load fluctuations, and aging. These factors can lead to performance degradation or even failure. Traditional power equipment maintenance relies primarily on regular inspections and empirical judgment, which is not only inefficient but also difficult to detect potential failure risks in a timely manner.

[0003] For example, Chinese patent publication number CN115936535A discloses a method, device, electronic device and storage medium for improving the service life of a power transformer. The method includes: constructing a health status index of the power transformer, calculating the indicator weight of the health status index, calculating the indicator membership of the health status index, performing a health status analysis on the power transformer, and obtaining a health analysis result of the power transformer; performing a fault analysis on the power transformer to obtain a fault analysis index, collecting historical risk data of the power transformer, and calculating the cycle loss degree and service life cost of the power transformer; performing a preventive risk analysis on the power transformer to obtain a risk analysis result; and performing a remaining cycle analysis on the power transformer to obtain a remaining analysis result.

[0004] For example, Chinese patent publication number CN117172555A discloses an intelligent generation system for power grid risk warning notifications, which includes a transformer information collection module, an environmental information collection module, a transformer overload risk analysis module, a transformer operating temperature risk analysis module, a transformer oil explosion risk analysis module, a transformer risk level confirmation module, a cloud database and a power grid risk warning notification generation terminal; the present invention calculates the transformer operation risk assessment index through the overload risk level, the operating temperature risk level and the oil explosion risk level, and confirms the risk level and risk cause of the transformer, thereby realizing multi-dimensional analysis of transformer warning notifications, improving the coverage of transformer warning notification analysis, and reducing the error of risk level and risk cause analysis.

[0005] The existing technology mainly describes the risk issues of cycles and transformer oil explosion. However, when evaluating the entire transformer, the control over the current transformer operating status is insufficient, and the current transformer current, voltage, temperature and corresponding insulating oil conditions cannot be identified in a timely manner. As a result, under conditions of overload and high temperature, the current transformer change trend cannot be predicted in a timely manner, resulting in the subsequent inability to identify the transformer status, resulting in reduced identification accuracy. Summary of the Invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: an electric power equipment monitoring, analysis and early warning system, including: a data acquisition module for obtaining the operating status of the electric power equipment, the operating status includes the working cycle and operating data of the electric power equipment; the operating data includes real-time load change information, operating temperature, number of overvoltage shocks, water content of insulating oil and tangent value of dielectric loss angle of insulating oil.

[0007] The trend identification module is used to obtain the fault characteristics of the power equipment under the corresponding operating state based on the operating state of the power equipment, identify the fault trend of the power equipment, and calculate the fault coefficient of the power equipment according to the fault trend of the power equipment.

[0008] The fault analysis module is used to generate a fault analysis tree corresponding to the power equipment based on the fault coefficient, and sequentially determine the fault relationship coefficient, data fault ratio and fault cycle of the power equipment.

[0009] The fault impact module is used to evaluate the fault loss of power equipment according to the fault cycle and calculate the fault impact coefficient of the power equipment in the corresponding fault cycle.

[0010] The impact range determination module is used to analyze the impact range coefficient of the operating data where the fault occurs based on the fault relationship coefficient and the data fault ratio.

[0011] The early warning assessment module is used to calculate the fault improvement coefficient of the power equipment under different cycle lengths and operating data values ​​based on the fault impact coefficient and the impact range coefficient, and obtain the current power equipment analysis and early warning results.

[0012] The beneficial effects of the present invention are as follows: the present invention collects the operating status of the power equipment in real time through the data acquisition module, including the working cycle and operating data, to ensure the timeliness and accuracy of the data; through the trend identification module, based on historical data and the current operating status, identifies the fault trend of the equipment, calculates the fault coefficient, and improves the accuracy of fault diagnosis; through the fault analysis module, generates a fault analysis tree, determines the fault relationship coefficient, data fault ratio and fault cycle, and provides a detailed fault cause analysis; through the fault impact module, evaluates the specific losses of the fault to the equipment and system, calculates the fault impact coefficient, and provides a basis for decision-making; through the impact range determination module, analyzes the impact range coefficient of the fault on other parts of the system to ensure the comprehensiveness of the maintenance measures; through the early warning evaluation module, calculates the fault improvement coefficient, generates the analysis and early warning results of the current power equipment, and provides scientific maintenance suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings and examples.

[0014] Figure 1It is a system framework diagram of a power equipment monitoring, analysis and early warning system.

[0015] Figure 2 The present invention is a system diagram of a power equipment monitoring, analysis and early warning system.

[0016] Figure 3 The present invention is a flow chart of a trend identification module of a power equipment monitoring, analysis and early warning system.

[0017] Figure 4 The present invention is a flow chart of a fault impact module of a power equipment monitoring, analysis and early warning system. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0019] See Figure 1 , an electric power equipment monitoring, analysis and early warning system, including: a data acquisition module, a trend identification module, a fault analysis module, a fault impact module, an impact range determination module, and an early warning evaluation module.

[0020] The data acquisition module obtains the operating status of the power equipment, including the working cycle and operating data, and outputs the data to the trend identification module; the trend identification module obtains the fault characteristics of the equipment based on the operating status of the power equipment and outputs them to the fault analysis module; the fault analysis module identifies the relevant data of the fault characteristics and outputs them to the fault impact module; the fault impact module evaluates the fault cycle and outputs the corresponding data to the impact range determination module; the impact range determination module analyzes the impact of the fault on other parts of the system and outputs it to the early warning assessment module; the early warning assessment module comprehensively considers the impact of the current fault and completes the analysis of the fault.

[0021] like Figure 2 As shown, the data acquisition module is used to obtain the operating status of the power equipment, which includes the working cycle and operating data of the power equipment; the operating data includes real-time load change information, operating temperature, number of overvoltage shocks, moisture content of insulating oil and dielectric loss tangent value of insulating oil.

[0022] The trend identification module is used to obtain the fault characteristics of the power equipment under the corresponding operating state based on the operating state of the power equipment, identify the fault trend of the power equipment, and calculate the fault coefficient of the power equipment according to the fault trend of the power equipment.

[0023] The fault analysis module is used to generate a fault analysis tree corresponding to the power equipment based on the fault coefficient, and sequentially determine the fault relationship coefficient, data fault ratio and fault cycle of the power equipment.

[0024] The fault impact module is used to evaluate the fault loss of power equipment according to the fault cycle and calculate the fault impact coefficient of the power equipment in the corresponding fault cycle.

[0025] The impact range determination module is used to analyze the impact range coefficient of the operating data where the fault occurs based on the fault relationship coefficient and the data fault ratio.

[0026] The early warning assessment module is used to calculate the fault improvement coefficient of the power equipment under different cycle lengths and operating data values ​​based on the fault impact coefficient and the impact range coefficient, and obtain the current power equipment analysis and early warning results.

[0027] The power equipment used at this time is a transformer. In the following text, all power equipment refers to transformers. The purpose of calculating faults is to analyze whether the transformer has experienced performance degradation during the overall use process, and what causes the performance degradation, so as to provide real-time early warning for the transformer. When the transformer performance degrades too quickly or the transformer has significantly low performance, the transformer should be replaced in time to improve the effect of power equipment analysis.

[0028] Transformer failures generally occur in situations of overload, overheating, and oil deterioration. When these two situations occur, the operating status can be identified to find out whether these abnormal operating conditions occur at this time. At the same time, the use time of the transformer can also cause a certain degree of performance degradation of the transformer. This is smaller than the impact of overload, overheating, and oil deterioration. Therefore, at this time, the main situation is to identify overload, overheating, and oil deterioration, and these situations are handled separately according to the identified cycles to verify how the performance of the transformer is affected when these problems occur.

[0029] Overload and overheating: A transformer overheats when subjected to loads exceeding its rated load current for extended periods. Overheating accelerates the wear of windings and insulation, leading to accelerated aging or damage of the transformer. Poor conductor contact, cooling system failures, or poor transformer heat dissipation can also cause overheating.

[0030] Oil deterioration: For oil-immersed transformers, the quality and performance of the oil are crucial to their proper operation. Improper operation or maintenance can lead to oil contamination, excessive levels of gas, moisture, and impurities, and thus deterioration. Degraded oil can reduce insulation performance, increase losses, and ultimately shorten the transformer's service life.

[0031] In one embodiment of the present invention, the data acquisition module is used to acquire the operating status of the power equipment, where the operating status includes the working cycle and operating data of the power equipment.

[0032] The duty cycle of a transformer usually refers to the time period from when it is put into operation to the current moment, as well as the load changes experienced by the transformer during this time period.

[0033] For transformers, operating data is an important basis for evaluating their status. In the present invention, in order to verify whether the transformer has performance degradation and failure problems at this time, the operating data will select the real-time operating parameters of the power equipment and the temperature data collected on the power equipment. The temperature data includes but is not limited to the winding hot spot temperature rise and the oil top layer temperature rise. These two sets of temperatures can represent the operating temperature of the power equipment to assist in verifying the changes in the current operating temperature.

[0034] Winding hot spot temperature rise: reflects the temperature change of the transformer winding during operation and is an important indicator for evaluating the thermal performance of the transformer.

[0035] Oil top layer temperature rise: reflects the temperature change of transformer oil during operation and is closely related to the heat dissipation performance of the winding.

[0036] After obtaining the operating temperature, it is also necessary to verify whether the equipment is overloaded. For example, the number of overvoltage shocks can be used to assess whether there are obvious problems at this time. The number of overvoltage shocks can assess the power equipment's ability to withstand voltage shocks at this time.

[0037] The operating data obtained at the same time may also include the water content of the insulating oil and the dielectric loss tangent value of the insulating oil, thereby reflecting the operating status of the power equipment that needs to be identified at present.

[0038] Water content in insulating oil: Water will reduce the resistance of insulating oil, increase dielectric loss, and pose a threat to the safe operation of the transformer.

[0039] Insulating oil dielectric loss tangent: reflects the loss characteristics of insulating oil under AC voltage and is an important indicator for evaluating insulating oil performance.

[0040] The operating data at this time is represented as real-time load change information, operating temperature, number of overvoltage shocks, water content of insulating oil and tangent value of dielectric loss angle of insulating oil; this verifies the operating status of the current power equipment under the conditions of overload, overheating and oil deterioration, so that the power equipment can be monitored in a timely manner and early warning can be issued when abnormal conditions are monitored.

[0041] Real-time load change information is typically obtained using load testing tools or system monitoring tools. These tools can simulate or monitor system load conditions and record load change information in real time. For example, they can monitor the system's current and voltage values ​​and record the current device's current and voltage change ratios as load change information, thus understanding the system's real-time load conditions. The current and voltage change ratios are the ratios of the current and voltage changes to the average values ​​of the current and voltage values ​​in historical data.

[0042] The operating temperature is usually measured by a thermometer or infrared thermometer. By using an infrared thermometer to irradiate the running motor, the instantaneous temperature of the motor winding can be directly measured.

[0043] The number of overvoltage surges is typically measured using dedicated overvoltage monitoring equipment or systems. These devices monitor overvoltage conditions in the power system in real time and record the number and magnitude of overvoltage surges. During the closing and opening of disconnectors, multiple breakdowns can occur. Counting the number of breakdown pulses during a single closing or opening cycle is considered a breakdown count; this helps assess the power system's ability to withstand overvoltage surges.

[0044] The following methods are commonly used to measure the moisture content of insulating oil: The Karl Fischer method: This involves reacting an insulating oil sample with a Karl Fischer reagent. The water reacts with the iodine in the reagent to produce hydrogen iodide, which is then titrated to determine the moisture content. This method is highly sensitive and accurate for trace amounts of moisture.

[0045] Electrochemical method: This method uses electrodes to chemically react with water in the insulating oil to detect moisture content. This method typically uses a dedicated electrochemical sensor or electrode to determine moisture content by measuring changes in current or voltage.

[0046] Infrared spectroscopy: This method determines moisture content by detecting the absorption characteristics of water molecules in the insulating oil. Water in the insulating oil absorbs specific wavelengths of the infrared spectrum, and the moisture content is calculated by measuring the intensity or ratio of the absorption peak.

[0047] The dielectric loss tangent of insulating oil is typically measured using a dedicated dielectric loss meter or a Schilling bridge. These instruments measure the dielectric constant and dissipation factor of the insulating oil, thereby calculating the dielectric loss tangent. Measurement methods include the balanced measurement method and the angular difference measurement method. The balanced measurement method measures the dielectric loss tangent by adjusting the bridge parameters to achieve equilibrium, while the angular difference measurement method calculates the dielectric loss tangent by directly measuring the angular difference between voltage and current.

[0048] At this time, after analyzing these five values ​​from the operating data, the current operating status of the power equipment can be effectively evaluated.

[0049] In one embodiment of the present invention, a trend identification module is used to obtain the fault characteristics of the power equipment in the corresponding operating state based on the operating state of the power equipment, identify the fault trend of the power equipment, and calculate the failure coefficient of the power equipment according to the failure trend of the power equipment.

[0050] In this module, the purpose of identifying the failure trend of power equipment is to identify the operating data in abnormal conditions and verify how many abnormal conditions exist in the current working cycle, or the frequency of occurrence of abnormal conditions, to quantify the failure trend of power equipment.

[0051] The fault characteristics of power equipment will be divided according to real-time load change information, operating temperature, number of overvoltage shocks, insulating oil moisture content and insulating oil dielectric loss tangent value. For example, insulation loss can be detected according to the change of insulating oil dielectric loss tangent value, and its load capacity and overload conditions can be detected according to real-time load change information. Whether high-temperature operation causes faults can be detected according to the operating temperature. The insulation and power tolerance capabilities can be detected according to the number of overvoltage shocks. Changes in the use of insulating oil in transformers can be detected according to the moisture content of insulating oil. After extracting these operating data as fault characteristics, the specific conditions of the operating data can be identified. At this time, the fault trend of the power equipment is used to divide these identified conditions according to the corresponding specific descriptions to identify whether the power equipment has corresponding fault trends.

[0052] like Figure 3 As shown, the processing method for identifying the fault trend of power equipment includes the following: based on the current working cycle, extracting a first indicator corresponding to the operating data, the first indicator is used to extract data that exceeds the average value of historical data from the operating data; obtaining a second indicator in a time period adjacent to the first indicator; the second indicator is when the first indicator is identified, selecting a time period adjacent to the first indicator, and is used to identify data in which abnormal conditions occur in the current operating data in the adjacent time period.

[0053] Based on the operating data corresponding to the first indicator and the second indicator, at least one fault feature corresponding to the operating data is obtained; the fault feature indicates that the performance of the system or equipment has declined or failed. In this case, the fault feature is obtained according to the corresponding data in the real-time load change information, operating temperature, number of overvoltage shocks, water content of the insulating oil and tangent value of the dielectric loss angle of the insulating oil, so as to identify the specific situation of these data when the fault occurs.

[0054] Calculate the first probability of the fault feature in the operating data corresponding to the first indicator and the second probability of the fault feature in the operating data corresponding to the second indicator; the first probability represents the probability of the fault feature appearing in the operating data corresponding to the first indicator, and the second probability represents the probability of the fault feature appearing in the operating data corresponding to the second indicator, that is, the possibility or frequency of the fault feature appearing in the adjacent time period of the first indicator.

[0055] The first probability and the second probability are compared to obtain the fault trend of the power equipment. At this time, the fault trend is identified by comparing the significance of the fault characteristics in the two time periods. For example, when the first probability corresponding to the first indicator takes the maximum value, whether the fault characteristics in the time period adjacent to the first indicator are also high-frequency or low-frequency problems, and the fault trends that these fault characteristics can represent. In the time period corresponding to the first indicator and the time period adjacent to the first indicator, the changing trend of the fault characteristics is an upward trend, a downward trend, or remains stable, so that the current fault characteristics can be clarified, and the fault coefficient related to the fault trend can be calculated; at this time, the first probability and the second probability will record the values ​​that change with the time period and output them as the changing trend of the power equipment.

[0056] The failure coefficient of the power equipment will be obtained based on the currently identified change trend. Therefore, the implementation method of the failure coefficient of the power equipment can be to calculate the change amount of the first probability and the second probability, and calculate the failure coefficient of the power equipment based on the change amount of the first probability and the second probability and using a quantitative analysis method of absolute change and relative change.

[0057] For example, the failure coefficient of the power equipment is expressed as ;in, represents the failure coefficient, represents the first probability, represents the second probability, represents the change in the first probability, It represents the change in the second probability, where the ratio of the change in the first probability to the change in the second probability represents comparing the change in the first probability and the change in the second probability to identify which probability is more obvious. At the same time, the fault coefficient set is mainly to identify the difference between the fault situation identified when the operating data obviously deviates from the normal operating value and the fault situation identified in the adjacent time period to describe the situation in which the power equipment may fail in the corresponding scenario; for the change in the first probability and the second probability at this time, the change in the first probability and the second probability at this time is obtained by comparing the first probability and the second probability with the average value of the first probability and the second probability in the historical data.

[0058] In one embodiment of the present invention, the fault analysis module is used to generate a fault analysis tree corresponding to the power equipment based on the fault coefficient, and sequentially determine the fault relationship coefficient, data fault ratio and fault cycle of the power equipment.

[0059] In this module, the fault analysis tree uses fault characteristics as intermediate nodes and power equipment as the starting point. The fault characteristics at this time represent the main aspects or stages of equipment failure, such as "insulation performance failure", "mechanical strength degradation", "thermal performance degradation", etc. The value of the leaf node of the intermediate node is represented by the fault coefficient. The edge of the leaf node is weighted according to the fault characteristics to construct the fault analysis tree corresponding to the current power equipment.

[0060] The fault analysis tree can be represented as follows: power equipment (root node): insulation performance failure (middle node): aging of insulation materials (leaf node, weight: 0.6), high humidity in the operating environment (leaf node, weight: 0.3), damaged insulation layer (leaf node, weight: 0.1); mechanical strength degradation (middle node): vibration and shock (leaf node, weight: 0.5), component wear (leaf node, weight: 0.3), loose fasteners (leaf node, weight: 0.2); thermal performance degradation (middle node): poor heat dissipation (leaf node, weight: 0.7), overload operation (leaf node, weight: 0.2), cooling system failure (leaf node, weight: 0.1); at this point, the current fault analysis tree can be analyzed according to the weight of the fault characteristics and the value of the leaf node to obtain values ​​such as the fault relationship coefficient, data failure ratio, and failure cycle.

[0061] The fault relationship coefficient is obtained by analyzing the leaf nodes of the fault analysis tree and calculating the Pearson correlation coefficient. The data failure ratio is used to obtain the ratio of the number of leaf nodes corresponding to the fault relationship coefficient to the total number of leaf nodes under the same value of the fault relationship coefficient. The failure cycle indicates the average interval time of each fault identification when the fault analysis tree is generated by the fault coefficient.

[0062] The analysis process of the fault relationship coefficient is as follows: based on all leaf nodes in the fault analysis tree, the fault coefficient and weight coefficient corresponding to each leaf node are obtained; the standardized covariance between the fault coefficient set and the weight coefficient set is calculated by a statistical analysis method to quantify the degree of linear correlation between the two, and the result obtained is the fault relationship coefficient.

[0063] Specific The calculation method of the failure relationship coefficient can be shown as follows: ;in, represents the fault relation coefficient, represents the failure coefficient corresponding to the i-th leaf node in the fault analysis tree, Indicates the standard value of the failure coefficient, Indicates the number of leaf nodes in the fault analysis tree. The value of i ranges from 1 to n. Indicates the weight coefficient corresponding to the i-th leaf node in the fault analysis tree, Indicates the standard value of the weight coefficient; at this time, the standard value of the fault coefficient and the standard value of the weight coefficient are both expressed by the corresponding fault coefficient in the historical data and the average value of the weight coefficient.

[0064] In one embodiment of the present invention, the fault impact module is used to evaluate the fault loss of the power equipment according to the fault cycle and calculate the fault impact coefficient of the power equipment in the corresponding fault cycle.

[0065] In this module, faults will be evaluated according to the average time of their occurrence. For example, the fault characteristics represented by each parameter in the operating data will be calculated separately, and the relative comprehensive value of the fault characteristics will be used as the fault impact coefficient output at this time. The purpose of calculating the fault impact coefficient is to identify the changes in the current power equipment in different cycles. At this time, the fault impact coefficient can be quantified by calculating the fault uniformity distribution and damage difference index.

[0066] like Figure 4 As shown, the fault influence coefficient is implemented by dividing the fault characteristics into the first fault characteristics and the second fault characteristics. At this time, each fault characteristic contains the content corresponding to the five numerical values ​​in the operating data. The first fault characteristics and the second fault characteristics are divided, that is, the original fault characteristics are separated according to the data of the median value. At this time, the number of the first fault characteristics and the second fault characteristics are the same, and the set serial numbers are also the same.

[0067] A fault uniformity degree related to the fault distribution is calculated according to the real-time load change information, the operating temperature, and the number of overvoltage shocks corresponding to the first fault feature.

[0068] According to the water content of the insulating oil and the dielectric loss tangent of the insulating oil corresponding to the second fault feature, the damage difference index related to the equipment damage is calculated.

[0069] Based on the fault uniformity distribution and damage difference index, the fault impact coefficient is obtained.

[0070] Assume that all fault features are in a one-to-one correspondence, the number of first fault features and second fault features is the same, and the arrangement order of these fault features is the same. There are J fault features at this time, and the sequence number of each fault feature is j. At this time, the number of first fault features and second fault features are both J, and the sequence numbers are also the same; then the uniform distribution of faults can be achieved in the following way.

[0071] The calculation process of the fault uniform distribution degree includes the following steps: A. normalizing the real-time load change information, operating temperature and overvoltage impact times corresponding to the first fault feature respectively.

[0072] B. Based on the normalization processing result, calculate the probability distribution of each parameter in the first fault feature.

[0073] C. For the probability distribution of each parameter, calculate its information entropy value as the uniform distribution degree of the parameter. The calculation of the information entropy value reflects the negative value of the sum of the probabilities of all possible states of the parameter and the products of their probability logarithms.

[0074] D. Perform a combined operation on the uniform distribution of the three parameters obtained in step C: first, perform an operation on each uniform distribution value as an exponent of a natural exponential function to obtain a corresponding exponential result; then, add the three exponential results together as the numerator; and simultaneously perform an operation on the sum of the three uniform distribution values ​​as an exponent of the natural exponential function to obtain a denominator; finally, divide the numerator by the denominator, and the result obtained is the fault uniform distribution.

[0075] The first fault characteristic includes three parameters: real-time load change information, operating temperature, and number of overvoltage shocks.

[0076] The uniform distribution degree of a parameter (information entropy value) reflects the uniformity of the probability distribution of the parameter in all its possible states. The larger the value, the more uniform the distribution.

[0077] Information entropy is expressed as: ;in, represents the value of information entropy, The probability value of the jth fault feature is represented. Based on the probability value of each fault feature at this time, the information entropy value in the current state is obtained.

[0078] The combined operation refers to a specific exponential processing and proportional calculation of the uniform distribution values ​​of the three parameters, which essentially reflects the weighted geometric mean relationship based on the exponential transformation.

[0079] For example, if the fault uniform distribution degree is expressed as follows, the real-time load change information, operating temperature, and number of overvoltage shocks corresponding to the first fault feature are normalized to calculate the probability of the first fault feature; the probability of the first fault feature is calculated according to the serial number of the fault feature to obtain the uniform distribution degree of the first fault feature; the uniform distribution degree of the first fault feature is combined according to the real-time load change information, operating temperature, and number of overvoltage shocks to calculate the fault uniform distribution degree.

[0080] The uniform distribution degree of the first fault feature is expressed as, ;in, represents the uniform distribution degree of the first fault feature, represents the probability of the first fault feature corresponding to the jth sequence number, Indicates the number of fault feature sequences, where j ranges from 1 to J. The probability of the first fault feature is expressed as the ratio of the number of values ​​corresponding to the real-time load change information, operating temperature, and number of overvoltage shocks in the current first fault feature to the total number of historical data.

[0081] The fault uniform distribution degree is expressed as follows: the uniform distribution degree of the first fault feature is divided into the uniform distribution degrees corresponding to the real-time load change information, the operating temperature, and the number of overvoltage shocks; the uniform distribution degrees corresponding to the real-time load change information, the operating temperature, and the number of overvoltage shocks are obtained, and the fault uniform distribution degree is calculated.

[0082] ;in, represents the uniform distribution of faults, Indicates the uniform distribution of real-time load change information. Indicates the uniform distribution of operating temperature. Indicates the uniform distribution of the number of overvoltage shocks, Represents an exponential constant.

[0083] The calculation process of the damage difference index includes the following steps: E1. normalizing the insulating oil moisture content index value and the insulating oil dielectric loss tangent index value included in the second fault feature respectively.

[0084] E2. For each test sample point, perform the following steps: calculate the deviation between the insulating oil moisture content index value at that sample point and its preset standard value, recorded as Deviation Value 1; calculate the deviation between the insulating oil dielectric loss tangent index value at that sample point and its preset standard value, recorded as Deviation Value 2; multiply Deviation Value 1 and Deviation Value 2 by their respective preset weight coefficients, and add the weighted deviation values ​​to obtain the weighted comprehensive deviation for that sample point.

[0085] E3. Perform the following steps on the weighted comprehensive deviation of all sample points: square the weighted comprehensive deviation value of each sample point; and calculate the sum of all squared values.

[0086] E4. Take the square root of the result obtained in step E3, and the ratio obtained by adding it to the weighted comprehensive deviation of the sample point is the damage difference index.

[0087] The second fault feature includes an insulating oil water content index value and an insulating oil dielectric loss tangent index value.

[0088] The preset standard value refers to the preset reference benchmark value of the insulating oil moisture content and the insulating oil dielectric loss tangent value.

[0089] The preset weight coefficient refers to a preset proportional factor that reflects the importance of the water content of the insulating oil and the dielectric loss tangent value of the insulating oil.

[0090] Sample points refer to data points at different detection times or different detection locations distinguished by sequence number j, and the total number of j is the total number of sample points.

[0091] The damage difference index is essentially a statistical dispersion measure calculated based on weighted comprehensive deviation and adjusted for sample degrees of freedom, reflecting the overall deviation of the index value from the standard value.

[0092] Exemplarily, the damage difference index is calculated by performing normalization processing on the water content of the insulating oil and the dielectric loss tangent value of the insulating oil corresponding to the second fault feature to obtain the damage difference index.

[0093] ;in, represents the damage difference index, Indicates the index value of the water content in the insulating oil in the second fault feature corresponding to the jth sequence number, The standard value of the index value indicating the water content of insulating oil, Indicates the index value of the insulating oil dielectric loss tangent value in the second fault feature corresponding to the jth sequence number, The standard value of the index value indicating the dielectric loss tangent of insulating oil. The weight coefficient representing the water content of insulating oil, Represents the weight coefficient of the dielectric loss tangent value of the insulating oil; the index value used at this time is obtained by extracting the specific values ​​corresponding to the insulating oil moisture content and the insulating oil dielectric loss tangent value from the second fault feature. The extracted index values ​​are all normalized to eliminate the dimension. At the same time, the standard value of the index value used is obtained by extracting the average value from the historical data.

[0094] Preferably, the weight coefficients corresponding to the water content of the insulating oil and the dielectric loss tangent value of the insulating oil are set to 0.5 and 0.5 respectively in the present invention, and are used to measure the difference between the second fault feature and the historical data.

[0095] The calculation process of the fault influence coefficient is as follows: summing the ratio of the fault uniform distribution degree to its preset standard value and the ratio of the damage difference index to its preset standard value to obtain a sum value, and multiplying the sum value with the preset weight coefficient of the fault uniform distribution degree and the preset weight coefficient of the damage difference index in turn, and the calculation result is used as the fault influence coefficient.

[0096] The two weight coefficients set here are different from those set previously. The weight coefficients of the fault uniform distribution and damage difference index are set by the ratio of the number of data corresponding to the current values ​​of the fault uniform distribution and damage difference index to the total number of historical data. At the same time, the standard values ​​of the fault uniform distribution and damage difference index are set using the standard deviation of the fault uniform distribution and damage difference index in the historical data.

[0097] In one embodiment of the present invention, the impact range determination module is configured to analyze the impact range coefficient of the operating data having the fault according to the fault relationship coefficient and the data fault ratio.

[0098] The impact range coefficient is used to assess the impact of the current fault on the device. Since the data failure ratio represents the ratio of the number of leaf nodes corresponding to the fault relationship coefficient to the total number of leaf nodes under the same value of the fault relationship coefficient, in the current scenario of calculating the impact range coefficient, the data failure ratio can also represent the ratio of the number of corresponding fault features to the total number of fault features under the corresponding fault relationship coefficient value.

[0099] At this time, the data corresponding to the fault relationship coefficient and the data fault ratio can be set to identify the impact range coefficient corresponding to the current operating data. For example, the current power equipment working cycle is added, combined with the fault relationship coefficient, data fault ratio and other values, to quantify the impact range coefficient.

[0100] The influence range coefficient finally calculated represents the relative distribution of fault characteristics corresponding to the fault relationship coefficient and the data fault ratio, and thus represents the correlation between the fault relationship coefficient and the actual distribution of faults.

[0101] The impact range coefficient can be expressed in the form of normal distribution by using the current fault relationship coefficient and the data fault ratio to obtain the affected range at this time.

[0102] For example, based on the fault relationship coefficient and the data fault ratio, the average value of the fault relationship coefficient and the standard deviation of the data fault ratio are calculated in sequence, and the influence range coefficient is calculated using a method similar to normal distribution analysis.

[0103] The influence range coefficient is expressed as, ;in, represents the influence range coefficient, represents the fault relation coefficient, represents the average value of the fault relation coefficient, represents the standard deviation of the data failure ratio, represents pi, Represents an exponential constant. At this time, the influence range coefficient can represent a specific value to evaluate the distribution of the current fault relationship coefficient under the corresponding data fault ratio. At the same time, the fault relationship coefficient and the data fault ratio do not have dimensions when calculated. At this time, in order to obtain more accurate values, the fault relationship coefficient and the data fault ratio will be standardized to make the value range of the two closer. When the influence range coefficient needs to output the corresponding range, the range corresponding to the fault relationship coefficient and the data fault ratio that need to be identified at this time can be quantified based on the average value of the current fault relationship coefficient and the standard deviation of the data fault ratio. This range value can be, ;in Indicates the adjustment coefficient. In this case, 1.96 can be selected as the value used at this time. At the same time, because the value represented by the data failure ratio is small, when using this range to identify the fault relationship coefficient and data failure ratio that currently require attention, the corresponding value can be accurately identified.

[0104] In one embodiment of the present invention, the early warning evaluation module is used to calculate the fault improvement coefficient of the power equipment under different cycle lengths and operating data values ​​based on the fault impact coefficient and the impact range coefficient, and obtain the current power equipment analysis and early warning results.

[0105] At this time, in order to quantify the failure promotion coefficient, the failure cycle corresponding to the power equipment is converted into a proportional value relative to the average failure cycle in the historical data, which is recorded as the cycle proportion value; and the ratio of the number of operating data in the corresponding failure cycle to the total data is recorded as the data proportion value; therefore, the failure promotion coefficient at this time is expressed as follows: the cycle proportion value of the failure cycle under different cycle lengths and the data proportion value of the operating data are obtained, and the failure promotion coefficient is calculated based on the data proportion value, cycle proportion value, failure impact coefficient and impact range coefficient.

[0106] ;in, represents the failure lift factor, represents the fault influence coefficient, represents the influence range coefficient, Represents the period ratio value, Indicates the data ratio value, 、 、 、 Represents the undetermined coefficient; the undetermined coefficient is set to -0.05, -0.1, 1, and 0.2 in sequence.

[0107] After the fault escalation coefficient is obtained, the current state of the power equipment is divided into multiple levels according to the value of the fault escalation coefficient at this time, for example, into five levels; low risk: >0.9; medium-low risk: 0.8≤ <0.9; medium risk: 0.6≤ <0.8; high risk: 0.5≤ <0.6; Very high risk: <0.5; these identified levels and fault improvement coefficients are output, so as to obtain the current power equipment analysis and early warning results.

[0108] By matching the current fault boost coefficient with the current specific status of the power equipment, it is possible to accurately identify the specific situation of the current power equipment when in use, promptly prevent unstable operation of the power equipment, and conduct timely analysis based on the current situation to improve the monitoring results of the power equipment operation status.

[0109] Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention, and these changes shall still be within the scope of protection of the present invention.

Claims

1. A power equipment monitoring, analysis and early warning system, characterized in that: include: A data acquisition module is used to acquire the operating status of the power equipment, including the working cycle and operating data of the power equipment; A trend identification module, based on the operating status of the power equipment, obtains the fault characteristics of the power equipment under the corresponding operating status, identifies the fault trend of the power equipment, and calculates the fault coefficient of the power equipment according to the fault trend of the power equipment; The fault analysis module generates a fault analysis tree corresponding to the power equipment based on the fault coefficient, and sequentially determines the fault relationship coefficient, data fault ratio and fault cycle of the power equipment; The fault impact module evaluates the power equipment failure loss based on the fault cycle and calculates the fault impact coefficient of the power equipment within the corresponding fault cycle; The impact range determination module analyzes the impact range coefficient of the operating data where the fault occurs based on the fault relationship coefficient and data fault ratio; The early warning assessment module calculates the fault improvement coefficient of the power equipment under different cycle lengths and operating data values ​​based on the fault impact coefficient and impact range coefficient, and obtains the current power equipment analysis and early warning results.

2. The power equipment monitoring, analysis and early warning system according to claim 1, characterized in that: Methods for identifying failure trends of power equipment include the following: Based on the current working cycle, extract the first indicator corresponding to the operating data and obtain the second indicator within the adjacent time period of the first indicator; Based on the operating data corresponding to the first indicator and the second indicator, obtaining at least one fault feature corresponding to the operating data; Calculate a first probability of the fault feature in the operating data corresponding to the first indicator and a second probability of the fault feature in the operating data corresponding to the second indicator; The first probability is compared with the second probability to obtain the failure trend of the power equipment.

3. The power equipment monitoring, analysis and early warning system according to claim 2, characterized in that: The fault coefficient of the power equipment is realized by calculating the variation of the first probability and the second probability, and obtaining the fault coefficient of the power equipment based on the variation of the first probability and the second probability by quantitative analysis of absolute change and relative change.

4. The power equipment monitoring, analysis and early warning system according to claim 1, characterized in that: The analysis process of the fault relationship coefficient is as follows: based on all leaf nodes in the fault analysis tree, the fault coefficient and weight coefficient corresponding to each leaf node are obtained; the standardized covariance between the fault coefficient set and the weight coefficient set is calculated by a statistical analysis method to quantify the degree of linear correlation between the two, and the result obtained is the fault relationship coefficient.

5. The power equipment monitoring, analysis and early warning system according to claim 1, characterized in that: The fault influence coefficient is implemented by dividing the fault characteristics into the first fault characteristics and the second fault characteristics; Calculating a fault uniformity degree related to the fault distribution based on the real-time load change information, operating temperature, and number of overvoltage shocks corresponding to the first fault feature; Calculate the damage difference index related to equipment damage based on the water content of the insulating oil and the dielectric loss tangent of the insulating oil corresponding to the second fault feature; Based on the fault uniformity distribution and damage difference index, the fault impact coefficient is obtained.

6. The power equipment monitoring, analysis and early warning system according to claim 5, characterized in that: The calculation process of the fault uniform distribution degree includes the following steps: A. normalize the real-time load change information, operating temperature, and overvoltage shock frequency corresponding to the first fault feature; B. calculating the probability distribution of each parameter in the first fault feature based on the normalization processing result; C. For the probability distribution of each parameter, calculate its information entropy value as the uniform distribution degree of the parameter, the information entropy ;in, represents the value of information entropy, represents the probability value of the jth fault feature. Based on the probability value of each fault feature at this time, the information entropy value in the current state is calculated; D. Perform a combined operation on the uniform distribution of the three parameters obtained in step C: first, perform an operation on each uniform distribution value as an exponent of a natural exponential function to obtain a corresponding exponential result; then, add the three exponential results together as the numerator; and simultaneously perform an operation on the sum of the three uniform distribution values ​​as an exponent of the natural exponential function to obtain a denominator; finally, divide the numerator by the denominator, and the result obtained is the fault uniform distribution.

7. The power equipment monitoring, analysis and early warning system according to claim 6, characterized in that: The calculation process of the damage difference index includes the following steps: E1. Normalize the insulating oil moisture content index and the insulating oil dielectric loss tangent index values ​​included in the second fault feature; E2. For each test sample point, perform the following steps: calculate the deviation of the insulating oil moisture content index value at the sample point from its preset standard value, recorded as Deviation Value 1; calculate the deviation of the insulating oil dielectric loss tangent index value at the sample point from its preset standard value, recorded as Deviation Value 2; multiply Deviation Value 1 and Deviation Value 2 by their respective preset weight coefficients, and add the weighted deviation values ​​to obtain the weighted comprehensive deviation of the sample point; E3. Perform the weighted comprehensive deviation calculation for all sample points: square the weighted comprehensive deviation value of each sample point; calculate the sum of all squared values; E4. Take the square root of the result obtained in step E3, and the ratio obtained by adding it to the weighted comprehensive deviation of the sample point is the damage difference index.

8. The power equipment monitoring, analysis and early warning system according to claim 7, characterized in that: The calculation process of the fault influence coefficient is as follows: summing the ratio of the fault uniform distribution degree to its preset standard value and the ratio of the damage difference index to its preset standard value to obtain a sum value, and multiplying the sum value with the preset weight coefficient of the fault uniform distribution degree and the preset weight coefficient of the damage difference index in turn, and the calculation result is used as the fault influence coefficient.

9. The power equipment monitoring, analysis and early warning system according to claim 1, characterized in that: The influence range coefficient is expressed as follows: According to the fault relationship coefficient and the data failure ratio, the average value of the fault relationship coefficient and the standard deviation of the data failure ratio are calculated in sequence, and the influence range coefficient is calculated using the normal distribution analysis method.

10. The power equipment monitoring, analysis and early warning system according to claim 1, characterized in that: The fault boost coefficient is expressed as follows: the cycle ratio value of the fault cycle under different cycle lengths and the data ratio value of the operating data are obtained. Based on the data ratio value, cycle ratio value, fault impact coefficient and impact range coefficient, the fault boost coefficient is obtained through multi-parameter fusion weighted calculation.

Images