Intelligent monitoring method for power transmission and transformation project
By integrating the historical fault group of the substation cabinet and real-time operating parameters, and identifying and comparing abnormal parameters, the problems of untimely and inaccurate fault warning in substation cabinet monitoring in the existing technology are solved, and accurate identification of fault warning types and identification of main fault warning types are achieved.
Patent Information
- Application Number
- CN202510349096.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-24
- Publication Date
- 2025-04-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art lacks timely and accurate fault warnings in substation cabinet monitoring, especially when the main fault warning types cannot be identified when there are various fault types.
By integrating the historical fault group of the substation cabinet and real-time operating parameters, the predicted abnormal parameters are identified and compared and analyzed to accurately identify the fault warning type of the substation cabinet. If the types of fault warnings are diverse, the main fault warning type is identified through parameter changes and analysis.
Accurate identification of the fault warning type of the substation cabinet and the identification of the main fault warning type, improving the timeliness and accuracy of monitoring.
Smart Images
Figure CN119853302A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of power transformation monitoring, in particular to an intelligent monitoring method for power transmission and transformation engineering. Background Art
[0002] The main task of power transmission and transformation projects is to transmit the electric energy generated by power plants to users and ensure the stability and reliability of power supply, including substations, transmission lines and substations. However, in practice, there are still many deficiencies in the monitoring of power transmission and transformation projects, such as inadequate and inaccurate monitoring. Therefore, it is of great significance to study an intelligent monitoring method for power transmission and transformation projects.
[0003] In the prior art, the monitoring of the substation is usually carried out by comparing the operating parameters of the substation with the set operating parameter thresholds, so as to achieve the early warning of the substation. The problem caused is that the monitoring and early warning of the substation are not timely, and the early warning monitoring of the substation is not carried out in advance through the prediction of the operating parameters. In addition, the prior art also lacks accurate monitoring and analysis of the substation, that is, there is a lack of prediction and analysis of the operating parameters of the substation to predict the abnormal operating parameters, and compare the predicted results with the operating parameters of the substation during historical failures, so as to more accurately and comprehensively analyze the fault warning type of the substation on the basis of timely monitoring of the substation. In addition, the prior art also lacks targeted identification of the main fault warning types when the fault warning types of the substation are diverse and it is impossible to identify the main fault warning types, that is, through trend similarity analysis of the predicted changes in the operating parameters and the changes in the operating parameters during historical failures, the main fault warning types of the substation are identified.
[0004] To this end, the present invention provides an intelligent monitoring method for power transmission and transformation projects. Summary of the invention
[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.
[0006] The technical solution adopted by the present invention to solve its technical problem is: In a first aspect, the present invention provides an intelligent monitoring method for a power transmission and transformation project, comprising: Step 1: Obtain the fault types and abnormal operation parameters of the substation during the historical monitoring period through the historical operation report of the substation, and integrate the fault types and abnormal operation parameters of the substation during the historical monitoring period to obtain the historical fault group; Step 2: During the monitoring period, the operating parameters of the substation are monitored in real time, and screening and analysis are performed to identify and predict abnormal parameters, and the predicted parameter group is integrated to compare the predicted parameter group with the historical fault group. According to the comparison results, the matching parameter group is screened in the historical fault data group, and the fault warning type of the substation is identified according to the matching parameter group; Step 3: Perform statistical analysis on the matching parameter group, and determine the diversity of fault warning types existing in the substation according to the statistical analysis results. If the diversity is high, generate a main identification signal; Step 4: Based on the main identification signal, perform parameter change comparison analysis on the predicted abnormal parameters in the prediction parameter group and the abnormal operation parameters in the matching parameter group, identify the target parameter group in the matching parameter group, and determine the main fault warning type of the substation according to the target parameter group.
[0007] In a second aspect, the present invention provides an intelligent monitoring system for power transmission and transformation projects, comprising: Historical fault group integration module: obtains the fault types and abnormal operation parameters of the substation during the historical monitoring period through the historical operation report of the substation, and integrates the historical fault groups according to the fault types and abnormal operation parameters of the substation during the historical monitoring period; Fault comparison and analysis module: During the monitoring period, the operating parameters of the substation are monitored in real time, and screening and analysis are performed to identify and predict abnormal parameters, and integrate them to obtain a prediction parameter group, compare the prediction parameter group with the historical fault group, and select a matching parameter group in the historical fault data group based on the comparison results, and identify the fault warning type of the substation based on the matching parameter group; Identification and analysis module: performs statistical analysis on the matching parameter group, and determines the diversity of fault warning types existing in the substation according to the statistical analysis results. If the diversity is high, a main identification signal is generated; Main fault identification module: Based on the main identification signal, the module compares and analyzes the parameter changes of the predicted abnormal parameters in the predicted parameter group and the abnormal operating parameters in the matching parameter group, identifies the target parameter group in the matching parameter group, and determines the main fault warning type of the substation according to the target parameter group.
[0008] The beneficial effects of the present invention are as follows: 1. The fault types that occurred in the substation during the historical monitoring period and the abnormal operating parameters when the fault occurred are integrated to obtain the historical fault group. During the monitoring period, the operating parameters of the substation are predicted and analyzed to identify the predicted abnormal parameters. After integration, they are compared and analyzed with the historical fault group, so that the fault warning type of the substation can be accurately identified and determined by comparing multiple operating parameters.
[0009] 2. Determine the diversity of fault warning types existing in the substation. If the diversity is high, perform parameter change comparison analysis on the predicted abnormal parameters in the predicted parameter group and the abnormal operating parameters in the matching parameter group, identify the target parameter group in the matching parameter group, and determine the main fault warning type of the substation according to the target parameter group. When the fault warning types of the substation are diverse and it is impossible to determine the main warning fault type, the present invention identifies the main fault warning type of the substation by analyzing the similarity of changes in the predicted abnormal parameters corresponding to multiple fault warning types. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The present invention will be further described below in conjunction with the accompanying drawings.
[0011] Figure 1 It is a flowchart of the steps of an intelligent monitoring method for power transmission and transformation engineering according to an embodiment of the present invention; Figure 2 It is a program flowchart of an intelligent monitoring system for power transmission and transformation projects described in an embodiment of the present invention. DETAILED DESCRIPTION
[0012] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods. Example 1
[0013] like Figure 1 As shown, an intelligent monitoring method for power transmission and transformation engineering according to an embodiment of the present invention includes: Step 1: Obtain the fault types and abnormal operation parameters of the substation during the historical monitoring period through the historical operation report of the substation, and integrate the fault types and abnormal operation parameters of the substation during the historical monitoring period to obtain the historical fault group; Specifically, the types of faults that occurred in the substation during the historical monitoring period include but are not limited to short circuit faults, overload faults, insulation faults, mechanical faults, etc.; the abnormal operating parameters when the fault occurs include electrical parameters and non-electrical parameters, wherein the electrical parameters include but are not limited to electrical parameters such as current, voltage, power factor, and electric energy, and the non-electrical parameters include but are not limited to non-electrical parameters such as temperature, humidity, gas concentration, and vibration; It should be noted that the abnormal operating parameters refer to operating parameters that exceed the operating parameter threshold when a fault occurs in the substation. For example, a short circuit fault occurs in the substation, and at this time, the current of the substation exceeds the rated current; The abnormal operation parameters when the transformer cabinet fails are integrated with the corresponding fault type to obtain a historical fault group. Regarding the method of obtaining the historical fault group, this application provides an exemplary description: For example, a short circuit occurs in the transformer cabinet. The abnormal operating parameters when the short circuit occurs include current, voltage and temperature. Then the integrated historical fault group is (short circuit, current-voltage-temperature). Step 2: During the monitoring period, the operating parameters of the substation are monitored in real time, and screening and analysis are performed to identify and predict abnormal parameters, and the predicted parameter group is integrated to compare the predicted parameter group with the historical fault group. According to the comparison results, the matching parameter group is screened in the historical fault data group, and the fault warning type of the substation is identified according to the matching parameter group; Specifically, real-time monitoring of the operating parameters of the substation cabinet is based on any operating parameter; Compare the operating parameters with the operating parameter warning values; If the operating parameter is less than or equal to the operating parameter warning value, no operation will be performed; If the operating parameter is greater than the operating parameter warning value, an analysis signal is generated; It should be noted that the operating parameter warning value is less than the operating parameter threshold value. For example, if the monitored operating parameter is current, the operating parameter warning value is less than the rated current. The operating parameter warning value is preset by those skilled in the art and is not specifically limited here. Based on the analysis signal, the operating parameter is subtracted from the operating parameter threshold and then the absolute value is taken to obtain the operating parameter approach value; Comparing the operating parameter convergence value with a preset operating parameter convergence threshold; If the operating parameter convergence value is less than or equal to the preset operating parameter convergence threshold, it means that the operating parameter at this time is close to the operating parameter threshold, and a prediction signal is generated; If the operating parameter convergence value is greater than the preset operating parameter convergence threshold, it means that the operating parameter at this time is not close to the operating parameter threshold, and no operation is performed; It should be noted that the meaning of the prediction signal is: because the operating parameter is close to the operating parameter threshold at this time, in order to predict in advance whether the operating parameter will exceed the operating parameter threshold, a prediction analysis is performed, the purpose of which is to make a prediction in advance and protect the safe operation of the substation; Based on the prediction signal, the analysis period is obtained by performing difference processing according to the time point when the operating parameter reaches the operating parameter warning value and the time point when the prediction signal is generated; Divide the analysis period into several time nodes, obtain the operating parameters at each time point, and construct an operating parameter group within the analysis period; The moving average method is used to process the operating parameter group and predict the operating parameters after the prediction signal is generated. The specific prediction process is as follows: S1, obtaining an operating parameter group, and preprocessing the operating parameter group, including but not limited to denoising, smoothing, etc.; S2, define the moving window size (W=3): determine the number of operating parameters contained in the window; define the step size (S=1): determine the step size of the window moving on the operating parameter group; S3, construct feature set and label set: For each window, the operating parameters in the operating parameter group are used as features; assuming that the operating parameter group is {x1, x2, x3, ..., xn}, Xn represents the operating parameter, n represents the number of operating parameters, the window size is W, and the step size is S, then the feature set of the first window is {x1, x2, ..., xW}; Label set: Each feature set corresponds to a label; the label is a running parameter after the window, for example, for the first window, the label is xW+1; For example, assuming that the operating parameter set is {1, 3, 5, 7, 9, 11, 13, 15, 17, 19}, the window size W=3, and the step size S=1, the moving window method can be used to construct the following feature set and label set: Feature set 1: {1, 3, 5}, label: 7 Feature set 2: {3, 5, 7}, label: 9 Feature set 3: {5, 7, 9}, label: 11 ... Feature set 8: {15, 17, 19}, label: none; S4, model training: using the feature set and the label set to train the neural network model, using the trained neural network model to process the operating parameter group, and within the monitoring period, predicting the operating parameters after the prediction signal is generated; During the monitoring period, the predicted abnormal parameters are identified based on the predicted results of the operating parameters after the prediction signal is generated, specifically: If the operating parameter after the prediction signal is generated exceeds the operating parameter threshold, the operating parameter is marked as a predicted abnormal parameter; If the operating parameters after the prediction signal is generated will not exceed the operating parameter threshold, no operation is performed; In the monitoring period, all predicted abnormal parameters are integrated into a predicted parameter group; Compare the prediction parameter group with the historical fault group. The specific process is as follows: The prediction parameter groups are integrated with all historical fault groups to obtain multiple control groups; It should be noted that each control group includes a prediction parameter group and a historical failure group, wherein the prediction parameter group in each control group is the same, but the historical failure group is different; Based on any control group; In the control group, the number of predicted abnormal parameters in the predicted parameter group and the number of abnormal operating parameters in the historical fault group are counted, and the difference is taken after the absolute value processing to obtain the parameter quantity difference, and the parameter quantity difference is processed with the number of abnormal operating parameters in the historical fault group to obtain the parameter quantity deviation value; In the prediction parameter group, the number of prediction abnormal parameters that are different from the abnormal operation parameter types in the historical fault group is counted, and the number is compared with the number of abnormal operation parameters in the historical fault group to obtain the parameter type deviation value; The parameter quantity deviation value is multiplied by the parameter type deviation value to obtain the parameter matching value CP; Preferably, the parameter matching value is compared with a parameter matching threshold; If the parameter matching value is greater than the parameter matching threshold, the historical fault group in the control group is marked as a non-matching parameter group; If the parameter matching value is less than or equal to the parameter matching threshold, the historical fault group in the control group is marked as a matching parameter group; The corresponding fault type in the matching parameter group is the fault warning type of the substation; The technical solution of the embodiment of the present invention is: by integrating the fault types that occurred in the substation during the historical monitoring period and the abnormal operating parameters when the fault occurred, a historical fault group is obtained; within the monitoring period, the operating parameters of the substation are predicted and analyzed, the predicted abnormal parameters are identified, and compared and analyzed with the historical fault group after integration, so as to accurately identify and judge the fault warning type of the substation by comparing multiple operating parameters. Example 2
[0014] like Figure 1 As shown, based on Example 1, an intelligent monitoring method for power transmission and transformation engineering according to an embodiment of the present invention includes: Step 3: Perform statistical analysis on the matching parameter group, and determine the diversity of fault warning types existing in the substation according to the statistical analysis results. If the diversity is high, generate a main identification signal; Specifically, according to the fault type in the matching parameter group, the fault warning type of the substation is obtained, the number of types of fault warning types of the substation is counted, and the ratio is processed with all fault types of the substation to obtain the fault warning ratio, which is marked as GZy; The parameter matching values of the matching parameter groups corresponding to the fault warning types of all different types of substations are integrated into a parameter matching sequence, and the variance is calculated to obtain the matching fluctuation value, which is marked as Ppb; It should be noted that if there are two or more types of the same fault warning type of the substation, when obtaining the parameter matching value of the corresponding matching parameter group, the parameter matching values of the matching parameter group corresponding to the same fault warning type are summed and averaged. For example, assuming that the fault warning types of different types of substations include short-circuit faults, mechanical faults, etc., but there are two groups of matching parameter groups for the short-circuit fault type, then the parameter matching values corresponding to the two groups of matching parameter groups are summed and averaged to obtain the parameter matching value of the matching parameter group corresponding to the short-circuit fault; The obtained fault warning ratio GZy and matching fluctuation value Ppb are processed by data, and the formula is: The fault warning diversity value DY is obtained, where s1 and s2 are both preset proportional coefficients, s1 is 1.26, and s2 is 1.47; comparing the fault warning diversity value with the fault warning diversity threshold; If the fault warning diversity value is greater than or equal to the fault warning diversity threshold, a primary identification signal is generated; If the fault warning diversity value is less than the fault warning diversity threshold, no operation is performed; It should be noted that the meaning of the main identification signal is: when analyzing the fault warning type of the substation, there are many different types of fault warning types of the substation, and the matching parameters corresponding to these fault warning types of the substation are similar in degree of consistency, which makes it impossible to determine the most likely fault warning type of the substation. Therefore, it is necessary to identify the main fault warning type; Step 4: Based on the main identification signal, perform parameter change comparison analysis on the predicted abnormal parameters in the predicted parameter group and the abnormal operation parameters in the matching parameter group, identify the target parameter group in the matching parameter group, and determine the main fault warning type of the substation according to the target parameter group; Specifically, for the predicted abnormal parameters in the prediction parameter group and the abnormal operation parameters in the matching parameter group, the predicted abnormal parameters and abnormal operation parameters at different time points in the analysis period are obtained, and the predicted abnormal parameters at different time points in the analysis period are integrated into the predicted abnormal group (X1, X2, X3...Xn), and the abnormal operation parameters at different time points in the analysis period are integrated into the historical abnormal group (Y1, Y2, Y3...Yn), where Xn represents the predicted abnormal parameter at the nth time node, Yn represents the abnormal operation parameter at the nth time node, and n represents the number of time nodes; By the Euclidean distance formula: The parameter deviation performance value D within the predicted abnormal group and the historical abnormal group is calculated; The predicted abnormal parameters and abnormal operation parameters with the same time node number in the predicted abnormal group and the historical abnormal group are integrated into a comparison group; Based on any comparison group, the trend types of the predicted abnormal parameters and abnormal operation parameters in the comparison group are identified respectively, where the trend types include growth type, decreasing type and stable type. The specific identification process is as follows: If the predicted abnormal parameter is greater than the previous predicted abnormal parameter within the predicted abnormal group, it means that the predicted abnormal parameter is of growth type; If the predicted anomaly parameter is equal to the previous predicted anomaly parameter within the predicted anomaly group, it means that the predicted anomaly parameter is stable; If the predicted abnormal parameter is less than the previous predicted abnormal parameter within the predicted abnormal group, it means that the predicted abnormal parameter is of decreasing type; Among them, the abnormal operation parameters are identified in the same way as the predicted abnormal parameters; If the trend type of the abnormal operation parameter and the predicted abnormal parameter is the same within the comparison group, the comparison group is marked as the same trend group; If the trend types of the abnormal operating parameters and the predicted abnormal parameters are different within the comparison group, the comparison group is marked as a counter-trend group; It should be noted that the first alignment grouping is not included in the identification of all alignment groups; Count the number of counter-trend groups and compare them with the number of comparison groups to obtain the trend deviation value; The change trend deviation value is multiplied by the parameter deviation performance value D to obtain the change contrast value FC; It should be noted that the meaning of the change contrast value is: by analyzing the predicted abnormal parameters and the change deviation of the abnormal operating parameters during the analysis period (the time period from when the operating parameters reach the operating parameter warning value to when the prediction signal appears), it reflects the consistency between the fault warning type of the substation and the historical fault type, which is conducive to more detailed judgment of the main fault warning type of the substation; By formula: The fault matching value WH is obtained, where z1 and z2 are both preset proportional coefficients, z1 is 1.341, and z2 is 1.496; Sort the matching parameter groups from large to small according to the corresponding fault matching values WH, and select the matching parameter group ranked first, which is the target parameter group. The fault type in the target parameter group is the main fault warning type; The technical solution of the embodiment of the present invention is: determine the diversity of fault warning types existing in the substation; if the diversity is high, perform parameter change comparison analysis on the predicted abnormal parameters in the predicted parameter group and the abnormal operating parameters in the matching parameter group, identify the target parameter group in the matching parameter group, and determine the main fault warning type of the substation according to the target parameter group. In the case that the fault warning types of the substation are diverse and it is impossible to determine the main warning fault type, the present invention realizes the identification of the main fault warning type of the substation by analyzing the similarity of the changes in the predicted abnormal parameters corresponding to multiple fault warning types. Example 3
[0015] like Figure 2 As shown, an intelligent monitoring system for power transmission and transformation engineering according to an embodiment of the present invention includes: Historical fault group integration module: obtains the fault types and abnormal operation parameters of the substation during the historical monitoring period through the historical operation report of the substation, and integrates the historical fault groups according to the fault types and abnormal operation parameters of the substation during the historical monitoring period; Fault comparison and analysis module: During the monitoring period, the operating parameters of the substation are monitored in real time, and screening and analysis are performed to identify and predict abnormal parameters, and integrate them to obtain a prediction parameter group, compare the prediction parameter group with the historical fault group, and select a matching parameter group in the historical fault data group based on the comparison results, and identify the fault warning type of the substation based on the matching parameter group; Identification and analysis module: performs statistical analysis on the matching parameter group, and determines the diversity of fault warning types existing in the substation according to the statistical analysis results. If the diversity is high, a main identification signal is generated; Main fault identification module: Based on the main identification signal, the module compares and analyzes the parameter changes of the predicted abnormal parameters in the predicted parameter group and the abnormal operating parameters in the matching parameter group, identifies the target parameter group in the matching parameter group, and determines the main fault warning type of the substation according to the target parameter group.
[0016] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. An intelligent monitoring method for power transmission and transformation engineering, characterized in that: The following steps are involved: Step 1: According to the fault types that occurred in the substation during the historical monitoring period and the abnormal operating parameters when the fault occurred, a historical fault group is obtained by integration; Step 2: During the monitoring period, the operating parameters of the substation are monitored in real time, and screening and analysis are performed to identify and predict abnormal parameters, and the predicted parameter group is integrated to compare the predicted parameter group with the historical fault group. According to the comparison results, the matching parameter group is screened in the historical fault data group, and the fault warning type of the substation is identified according to the matching parameter group; Step 3: Perform statistical analysis on the matching parameter group, and determine the diversity of fault warning types existing in the substation according to the statistical analysis results. If the diversity is high, generate a main identification signal; Step 4: Based on the main identification signal, perform parameter change comparison analysis on the predicted abnormal parameters in the prediction parameter group and the abnormal operation parameters in the matching parameter group, identify the target parameter group in the matching parameter group, and determine the main fault warning type of the substation according to the target parameter group.
2. The intelligent monitoring method for power transmission and transformation engineering according to claim 1, characterized in that: The identification method of the predicted abnormal parameters is: Monitor the operating parameters of the substation in real time. If the operating parameters are greater than the warning value of the operating parameters, an analysis signal is generated. Based on the analysis signal, the operating parameter is subtracted from the operating parameter threshold and then the absolute value is taken to obtain the operating parameter approach value; If the operating parameter convergence value is less than or equal to the preset operating parameter convergence threshold, a difference is made according to the time point when the operating parameter reaches the operating parameter warning value and the time point when the prediction signal is generated to obtain the analysis period; The analysis period is divided into several time nodes, the operating parameters at each time point are obtained, and the operating parameter group within the analysis period is constructed. The operating parameter group is processed using the moving average method, and the operating parameters are predicted. If the predicted operating parameter exceeds the operating parameter threshold, the operating parameter will be marked as a predicted abnormal parameter.
3. The intelligent monitoring method for power transmission and transformation engineering according to claim 2 is characterized in that: The process of predicting the operating parameters comprises: S1, obtaining an operating parameter group and preprocessing the operating parameter group, including denoising and smoothing; S2, define the moving window size: determine the number of operating parameters contained in the window; define the step size: determine the step size of the window moving on the operating parameter group; S3, construct feature sets and label sets: for each window, the operating parameters in the operating parameter group are used as features; each feature set corresponds to a label; the label is an operating parameter after the window; S4, model training: use the feature set and label set to train the neural network model, and use the trained neural network model to predict the operating parameters.
4. The intelligent monitoring method for power transmission and transformation engineering according to claim 1 is characterized in that: The screening process of the matching parameter group is as follows: The prediction parameter groups are integrated with all historical fault groups to obtain multiple control groups; According to the comparison and analysis results of the prediction parameter group and the historical fault group in the control group, the parameter quantity deviation value and the parameter type deviation value are output, and the product is processed to obtain the parameter matching value CP; If the parameter matching value is less than or equal to the parameter matching threshold, the historical fault group in the control group is marked as a matching parameter group.
5. The intelligent monitoring method for power transmission and transformation engineering according to claim 4 is characterized in that: The method for obtaining the parameter quantity deviation value is as follows: The number of predicted abnormal parameters in the prediction parameter group and the number of abnormal operating parameters in the historical fault group are counted, and the difference is taken after absolute value processing to obtain the parameter quantity difference, and the parameter quantity difference is ratio processed with the number of abnormal operating parameters in the historical fault group to obtain the parameter quantity deviation value.
6. The intelligent monitoring method for power transmission and transformation engineering according to claim 4 is characterized in that: The parameter type deviation value is obtained in the following way: In the prediction parameter group, the number of predicted abnormal parameters that are different from the abnormal operation parameter types in the historical fault group is counted, and the number is compared with the number of abnormal operation parameters in the historical fault group to obtain the parameter type deviation value.
7. The intelligent monitoring method for power transmission and transformation engineering according to claim 1, characterized in that: The main identification signal is generated in the following manner: According to the fault type in the matching parameter group, the fault warning type of the substation is obtained, the number of types of fault warning types of the substation is counted, and the ratio is processed with all fault types of the substation to obtain the fault warning ratio, which is marked as GZy; The parameter matching values of the matching parameter groups corresponding to the fault warning types of all different types of substations are integrated into a parameter matching sequence, and the variance is calculated to obtain the matching fluctuation value, which is marked as Ppb; The obtained fault warning ratio GZy and matching fluctuation value Ppb are processed by data, and the formula is: Obtain the fault warning multiple values DY, where s1 and s2 are both preset proportional coefficients; If the fault warning diversity value is greater than or equal to the fault warning diversity threshold, a primary identification signal is generated.
8. The intelligent monitoring method for power transmission and transformation engineering according to claim 1, characterized in that: The target parameter group is identified as follows: The predicted abnormal parameters at different time points in the analysis period are integrated into the predicted abnormal group (X1, X2, X3...Xn), and the abnormal operation parameters at different time points in the analysis period are integrated into the historical abnormal group (Y1, Y2, Y3...Yn), where Xn represents the predicted abnormal parameter at the nth time node, Yn represents the abnormal operation parameter at the nth time node, and n represents the number of time nodes; By the Euclidean distance formula: The parameter deviation performance value D within the predicted abnormal group and the historical abnormal group is calculated; The predicted abnormal parameters and abnormal operation parameters with the same time node number in the predicted abnormal group and the historical abnormal group are integrated into a comparison group; By comparing and analyzing the grouping, the change trend deviation value is obtained, and the change contrast value FC is obtained by multiplying it with the parameter deviation performance value D; By formula: Obtain the fault matching value WH, where z1 and z2 are both preset proportional coefficients; The matching parameter groups are sorted from large to small according to the corresponding fault matching values WH, and the matching parameter group ranked first is selected as the target parameter group. The fault type in the target parameter group is the main fault warning type.
9. The intelligent monitoring method for power transmission and transformation engineering according to claim 8, characterized in that: The variation trend deviation value is obtained in the following manner: Respectively identify the trend types of the predicted abnormal parameters and abnormal operating parameters in the comparison group, wherein the trend types include increasing type, decreasing type and stable type; If the trend types of the abnormal operating parameters and the predicted abnormal parameters are different within the comparison group, the comparison group is marked as a counter-trend group; The number of counter-trend groups is counted and compared with the number of comparison groups to obtain the deviation value of the change trend.
10. The intelligent monitoring method for power transmission and transformation engineering according to claim 9, characterized in that: The identification method of the trend type of the predicted abnormal parameters and abnormal operation parameters is as follows: If the predicted abnormal parameter is greater than the previous predicted abnormal parameter within the predicted abnormal group, it means that the predicted abnormal parameter is of growth type; If the predicted anomaly parameter is equal to the previous predicted anomaly parameter within the predicted anomaly group, it means that the predicted anomaly parameter is stable; If the predicted abnormal parameter is less than the previous predicted abnormal parameter within the predicted abnormal group, it means that the predicted abnormal parameter is of decreasing type; Among them, the identification method of abnormal operation parameters is the same as that of predicted abnormal parameters.