Digital monitoring method for power transmission and transformation project

Abstract

The invention belongs to the technical field of power transmission and transformation project monitoring, and provides a power transmission and transformation project digital monitoring method, which comprises the following steps: in a power transmission and transformation project monitoring process, analyzing a dependency chain relationship between equipment groups, and extracting the dependency chain equipment groups with reverse monitoring in the monitoring process; analyzing the rationality of a reverse monitoring sequence corresponding to the reverse monitoring equipment group according to the relevance between the state data of two pieces of equipment in the reverse monitoring equipment group, the fault propagation consistency and the importance of the equipment, and judging whether the reverse monitoring is reasonable or not; if the reverse monitoring sequence is unreasonable, reverse monitoring is adjusted to be forward monitoring. By analyzing the dependency chain relationship of the equipment group, the reverse monitoring equipment group existing in the monitoring process can be effectively extracted, an unreasonable sequence monitored by the child equipment prior to that monitored by the parent equipment is defined, accurate targeting is provided for monitoring optimization, and the problem that the monitoring sequence of the dependency chain equipment is disordered in traditional monitoring is solved.

Description

Technical Field

[0001] The invention belongs to the technical field of power transmission and transformation project monitoring, in particular to a digital monitoring method for power transmission and transformation projects. Background Art

[0002] Digital monitoring of power transmission and transformation projects leverages digital technologies such as the Internet of Things, big data, and artificial intelligence to provide real-time monitoring of the status (e.g., temperature, vibration, partial discharge) and operating parameters (voltage, current, and power) of equipment such as transformers, circuit breakers, and busbars within substations. It also includes remote monitoring of the environment (e.g., temperature, humidity, and security) and auxiliary systems (e.g., fire protection and lighting). "Digitalization" refers to the collection of multi-source data through sensors and smart terminals, combined with edge computing and cloud computing analysis, to achieve equipment fault warnings, operational optimization, and intelligent decision-making, significantly improving operation and maintenance efficiency and grid reliability. When monitoring power transmission and transformation projects, two devices may have a dependency chain relationship, forming a dependency chain device group. During the actual monitoring process, due to the monitoring mechanism or other reasons, the monitoring order in the dependency chain device group may form a reverse monitoring sequence, first monitoring the child device and then the parent device. If the reverse monitoring is unreasonable, since the status of the child device is often affected by the parent device, if the child device is monitored first and an anomaly is found, the problem may be mistakenly attributed to the child device itself, while ignoring the fact that the parent device is the root cause. For example, if the parent device is a circuit breaker (which controls the on and off of the child device) and the child device is a line load, the reverse monitoring will first detect an abnormal line load current, and the line problem may be prioritized, when in fact it is the current fluctuation caused by poor contact of the circuit breaker, thus delaying the fault location time. To this end, the present invention provides a digital monitoring method for power transmission and transformation projects. Summary of the Invention

[0003] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a digital monitoring method for power transmission and transformation projects, comprising the following steps: In the process of monitoring power transmission and transformation projects, the dependency chain relationship between equipment groups is analyzed, and the dependency chain equipment groups with reverse monitoring in the monitoring process are extracted; Based on the correlation between the status data of two devices in the reverse monitoring device group, the consistency of fault propagation, and the importance of the devices, the rationality of the reverse monitoring sequence corresponding to the reverse monitoring device group is analyzed to determine whether the reverse monitoring is reasonable; If the reverse monitoring sequence is unreasonable, adjust the reverse monitoring to forward monitoring.

[0005] As a further solution of the present invention: the process of analyzing the dependency relationship between device groups is: Obtain the equipment involved in the power transmission and transformation project and build an equipment inventory library; convert the equipment operating status into Boolean data and use the Apriori algorithm to extract frequently co-occurring equipment status combinations; Set a time window and generate a transaction dataset if the device status changes. Treat a single device status as a 1-item set and generate high-frequency 2-item sets through concatenation and pruning. Calculate the support of each item set, and filter the item sets with support greater than or equal to the minimum support as frequent item sets; Calculate the confidence of each transaction and select the item sets with confidence greater than or equal to the minimum confidence as strong association rules; Based on the obtained strong association rules, by comparing the effectiveness of the identification rules, the rule corresponding to the maximum confidence value among the effective strong association rules is extracted as the maximum confidence association rule; Based on GOOSE signal interaction, the dependency direction of two devices in the maximum confidence association rule is determined, and the device group with dependency chain relationship is obtained.

[0006] As a further solution of the present invention: the process of extracting the device group of the dependency chain that has reverse monitoring during the monitoring process is: During the monitoring process, the response time of two devices in a dependent chain relationship is obtained, and the difference between the response times of the two devices is calculated and the absolute value is taken to obtain the response time difference; If the response time difference is greater than or equal to the response time difference limit, the direction consistency comparison process is triggered; If the response time difference is less than the response time difference limit, the data flow consistency comparison process is triggered.

[0007] As a further solution of the present invention: the directional consistency comparison process: Sort the devices in order of response time to get the response time sequence; Compare the consistency of response time sequence and dependency direction between dependency chain devices; If the response time sequence is inconsistent with the dependency direction between the dependency chain devices, it means that the monitoring sequence of the device group is reverse monitoring.

[0008] As a further solution of the present invention: the data flow consistency comparison process: By deploying a network packet capture tool on the switch mirror port to capture communication data packets between devices, combined with protocol analysis to clarify the relationship between the sending and receiving devices, the packet timestamp is recorded and the device time is synchronized with the monitoring platform. By comparing the logs to verify the timing, the data transmission path from the source device to the target device is determined. Obtain the timing of data flow between devices and obtain the data flow order; If the data flow order is inconsistent with the dependency direction between the dependency chain devices, it means that the monitoring order of the device group is reverse monitoring.

[0009] As a further solution of the present invention: the judgment of whether the reverse monitoring is reasonable: By analyzing the correlation and fault propagation direction consistency, the order judgment coefficient is output; If the order judgment coefficient is less than the order judgment coefficient limit, it is marked as unreasonable order.

[0010] As a further solution of the present invention: the process of obtaining the order judgment coefficient is as follows: The device relevance is obtained by analyzing the correlation, and the proportion of the number of sequences with consistent directions is obtained by analyzing the consistency of fault propagation. The device relevance is combined with the proportion of the number of sequences with consistent directions to output the sequence judgment coefficient. As a further solution of the present invention: the process of obtaining the correlation between the two device status data is as follows: Obtain all reverse-monitored device groups, and based on any reverse-monitored device group, collect the operating status data of two devices in the device group in real time; The correlation coefficient of the operating status data of two devices is calculated by the Pearson correlation coefficient to represent the degree of association between the data of the two devices; The correlation coefficients of all the operating status data of the two devices are averaged to obtain the device correlation.

[0011] As a further solution of the present invention: the process of obtaining the fault propagation consistency is: Analyze the time when two equipment failures occurred in historical failure events to obtain events to be grouped; Mark all events to be grouped in which two devices have the same time sequence of failure as one group, and obtain the first group and the second group respectively; Based on the reverse monitoring sequence, the groups corresponding to the equipment failure sequence with the same reverse monitoring sequence are extracted and marked as direction-consistent sequence groups. The number of direction-consistent sequence groups is counted and the ratio is calculated with the total number of historical failure events to obtain the proportion of direction-consistent sequence groups.

[0012] As a further solution of the present invention: the process of obtaining the events to be grouped is: Obtain historical fault events from the historical database, obtain the fault occurrence time of the two devices in each historical fault event, and calculate the difference between the fault occurrence time of the two devices, and obtain the absolute value of the difference as the fault occurrence time difference; Extract historical fault events whose fault occurrence time difference is greater than or equal to the minimum fault occurrence time difference as events to be grouped.

[0013] The beneficial effects of the present invention are as follows: By analyzing the dependency chain relationship of device groups, the present invention can effectively extract the reverse monitoring device groups existing in the monitoring process, clarify the unreasonable sequence in which child devices are monitored before parent devices, provide precise targeting for monitoring optimization, and solve the problem of disordered monitoring order of dependency chain devices in traditional monitoring. Through reasonable monitoring sequence and data association analysis, the present invention matches the timing logic of equipment operation status data with the fault propagation direction, thereby discovering potential equipment faults earlier, determining the fault propagation path, improving the timeliness of fault warning and the accuracy of fault location, and by optimizing the monitoring sequence, reducing the system chain reaction caused by the failure to discover the parent equipment fault in time, reducing the risk of power outages, and ensuring the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart of the steps of a digital monitoring method for power transmission and transformation projects of the present invention; Figure 2 This is a flow chart of the steps of identifying reverse monitoring in a digital monitoring method for power transmission and transformation projects of the present invention; Figure 3 This is an architectural diagram of a digital monitoring system for power transmission and transformation projects according to the present invention. DETAILED DESCRIPTION

[0016] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0017] Example 1:

[0018] See also Figure 1 and Figure 2 As shown, a digital monitoring method for power transmission and transformation projects according to an embodiment of the present invention includes the following steps: Step S10: During the monitoring of the power transmission and transformation project, the dependency chain relationship between the equipment groups is analyzed, and the equipment groups that are subject to reverse monitoring during the monitoring process are extracted; In some embodiments, among all the equipment in the power transmission and transformation project, equipment groups with dependency chain relationships are analyzed and extracted. The specific process is as follows: Obtain equipment involved in power transmission and transformation projects and build an equipment inventory library; the equipment includes but is not limited to: transformers, circuit breakers, disconnectors, sensors, controllers, and protection devices; The equipment list includes: equipment type, functional parameters, physical connection relationship, location in the system and subsystem to which it belongs; the subsystems to which it belongs include at least: transmission lines, substations, and distribution networks; For example, the device type (vacuum circuit breaker), functional parameters (rated voltage: 220kV; rated current: 2500A; breaking current: 40kA), physical connection relationship (one end connected to the 220kV transmission line, the other end connected to the substation 220kV bus), location in the system (220kV distribution device area A bay of the substation) and the subsystem to which it belongs (substation); Obtain historical operating data of any two devices and perform data cleaning. Data cleaning includes: using the forward filling method to complete missing data of device status and marking device status outliers based on the 3σ principle; Historical operation data is the real-time operation record of the equipment over a period of time, including but not limited to: multi-dimensional information of electrical quantities, status quantities, and environmental quantities; it is collected through SCADA monitoring systems or IoT sensors and stored in historical databases; Convert the device operating status into Boolean or enumeration data to facilitate association analysis, and use the Apriori algorithm to extract frequently co-occurring device status combinations; Set a time window and generate a transaction data set if the device status changes. The time window is set by technical personnel based on the frequency of historical operation data collection and industry experience. Treat a single device state as a 1-item set and generate high-frequency 2-item sets through concatenation and pruning; Calculate the support of each item set. The support is calculated as the ratio of the number of items in the item set to the total number of transactions. Set the minimum support and filter the item sets whose support is greater than or equal to the minimum support as frequent item sets; Calculate the confidence of each transaction. The confidence is the probability that the consequent (the latter part of the equipment state combination) of the item set occurs when the antecedent (the former part of the equipment state combination) of the corresponding item set occurs. Set the minimum confidence level and filter the item sets with confidence levels greater than or equal to the minimum confidence level as strong association rules; Based on the obtained strong association rules, by comparing the effectiveness of the identification rules of the "Power Grid Equipment Operation and Maintenance Regulations", the rule corresponding to the maximum confidence value among the effective strong association rules is extracted as the maximum confidence association rule; Based on GOOSE signal interaction, the dependency direction of two devices in the maximum confidence association rule is clarified; a list of dependency chain device groups is generated and the verification status is marked; For example, in a 220kV substation, the dependency chain relationship between the protection device (device A) and the circuit breaker (device B) is extracted; Obtain the "action signal" (0 = not actuated, 1 = actuated) of device A (protection device) and the "opening and closing position" (0 = open, 1 = closed) data of device B (circuit breaker) from the SCADA system; Set a 1-second time window and generate a transaction data set (partial example): Transaction 1: {Device A=1, Device B=0} (protection device actuated, circuit breaker opened); Transaction 2: {Device A=0, Device B=1} (protection device not actuated, circuit breaker closed); Initial candidate itemset: {Device A = 1}, {Device B = 0}; after concatenation and pruning, a 2-item set is generated: {Device A = 1, Device B = 0} (support = 0.15); Set the minimum support to 0.1 and retain itemsets with support ≥ 0.1 (e.g., {device A = 1, device B = 0}); Rule 1: Device A = 1 → Device B = 0 (protective device actuates → circuit breaker opens), confidence level = 0.9 (90% of protective device actuations are accompanied by circuit breaker opening). Rule 2: Device B = 1 → Device A = 0 (circuit breaker closed → protective device not operated), confidence level = 0.85 (85% of the time, the protective device will not operate when the circuit breaker is closed); Expert knowledge base verification: Rule 1 complies with the requirement of "opening the circuit breaker after protection action" in the "Power Grid Equipment Operation and Maintenance Regulations"; The protection device controls the circuit breaker to open via the GOOSE signal, and the fault propagation path is device A → device B; Device group ID: GROUP_001; Equipment pair: protection device_1#→circuit breaker_1#; Dependency chain type: control logic association; Verification status: passed (Rule 1 confidence = 0.9, in compliance with regulations); In some embodiments, a device group having a dependency chain relationship is obtained, and a device group having reverse monitoring during the monitoring process is extracted; What needs to be defined for reverse monitoring is that reverse monitoring means that the monitoring order of child devices takes precedence over that of their parent devices, that is, the sequence of child devices → parent devices. For example, a temperature and humidity sensor (child device) → an environmental controller (parent device) can provide early warning of controller failure by monitoring abnormal environmental parameters. During the monitoring process, the response time of two devices in a dependent chain relationship is obtained, and the difference between the response times of the two devices is calculated and the absolute value is taken to obtain the response time difference; If the response time difference is greater than or equal to the response time difference limit, the direction consistency comparison process is triggered; the devices are sorted according to the order of response time to obtain the response time order; The response time difference limit acts as a trigger in the monitoring method: when the response time difference between devices exceeds the threshold, the system automatically initiates the direction consistency comparison process, which is determined by technical personnel based on the frequency of historical operation data collection and industry experience. Compare the consistency of response time sequence and dependency direction between dependency chain devices; If the response time sequence is consistent with the dependency direction between the devices in the dependency chain, it means that the monitoring sequence of the device group is forward monitoring; If the response time sequence is inconsistent with the dependency direction between the devices in the dependency chain, it means that the monitoring sequence of the device group is reverse monitoring; If the response time difference is less than the response time difference limit, the data flow consistency comparison process is triggered; Obtain the data flow direction of the two devices. This is achieved by deploying a network packet capture tool to capture the communication data packets between the devices on the switch mirror port. Protocol analysis is then used to clarify the relationship between the sending and receiving devices. The data packet timestamps are recorded and the device and monitoring platform time are synchronized. Finally, the timing is verified by log comparison to determine the data transmission path from the source device to the target device. Use the above tools and technologies to obtain the timing of data flow between devices and obtain the data flow order; If the data flow order is consistent with the dependency direction between the dependency chain devices, it means that the monitoring order of the device group is forward monitoring; If the data flow order is inconsistent with the dependency direction between the devices in the dependency chain, it means that the monitoring order of the device group is reverse monitoring; For example, scenario 1: the response time of the protection device (parent device) is 200ms, and the response time of the circuit breaker (child device) is 100ms. If the response time difference is 100ms and is greater than or equal to the preset response time difference limit (50ms), a directional consistency comparison is performed. Response time sequence: circuit breaker first, then protection device (child → parent); dependency chain direction: protection device first, then circuit breaker (parent → child); if the sequence is inconsistent, it is determined to be reverse monitoring; Scenario 2: The response time of the environmental controller (parent device) is 140ms, and the response time of the temperature and humidity sensor (child device) is 50ms. The response time difference is 40ms, which is less than the preset response time difference limit (50ms). Therefore, a data flow consistency comparison is performed. The data packet from the temperature and humidity sensor arrives at the switch at 08:00:00.000, and the data packet from the environmental controller arrives at the platform at 08:00:00.050. Data flow order: temperature and humidity sensor first, then environment controller (child→parent); dependency chain direction: environment controller first, then temperature and humidity sensor (parent→child); if the order is inconsistent, it is determined to be reverse monitoring; Step S20: Analyze the rationality of the reverse monitoring sequence corresponding to the reverse monitoring device group based on the correlation between the status data of two devices in the reverse monitoring device group and the fault propagation consistency, and determine whether the reverse monitoring is reasonable; First, specifically, the process of obtaining the correlation between two pieces of device status data is as follows: Obtain all reverse-monitored device groups. Based on any reverse-monitored device group, collect real-time operating status data of two devices in the device group, including but not limited to: voltage, current, temperature, and switch status; The correlation coefficient of the operating status data of the two devices is calculated to represent the degree of association between the two device data, wherein the correlation coefficient is calculated by the Pearson correlation coefficient; The correlation coefficients of all the operating status data of the two devices are averaged to obtain the device correlation; For example, in a 220 kV substation, it is identified through the aforementioned step S10 that transformer A (main transformer) and transformer B (backup transformer) have a reverse monitoring relationship, and the collected parameters are voltage, current, and temperature; Device A voltage sequence: [220.5, 221.0, 219.8, 222.1, 220.3]; Device B voltage sequence: [218.7, 219.2, 217.9, 220.0, 218.5]; Substituting into Pearson's formula, the correlation coefficient is: 0.9928; Device A current sequence: [10.2, 10.5, 10.1, 10.3, 10.4]; Device B current sequence: [9.8, 10.0, 9.7, 9.9, 10.1]; Substituting into Pearson's formula, the correlation coefficient is: 0.9000; Device A temperature sequence: [35.6, 36.1, 35.8, 36.3, 35.9] Device B temperature sequence: [34.2, 34.7, 34.0, 34.5, 34.3] Substituting into Pearson's formula, the correlation coefficient is: 0.7260; The device correlation is 0.8729; The second specific process for obtaining the fault propagation consistency between two devices is as follows: By backtracking the historical fault data of the two devices, the fault propagation consistency is analyzed based on the temporal relationship of the fault occurrence; Obtain historical fault events from the historical database, obtain the fault occurrence time of the two devices in each historical fault event, and calculate the difference between the fault occurrence time of the two devices, and obtain the absolute value of the difference as the fault occurrence time difference; Extract historical fault events whose fault occurrence time difference is greater than or equal to the minimum fault occurrence time difference as events to be grouped; The minimum error value for a fault to occur is determined by those skilled in the art based on system characteristics. For example, based on the device response time, if a device fault requires 100ms to be detected by the system, the minimum error value for a fault to occur is ≥ 200ms. The reasons for setting a minimum difference between failure occurrences are: first, if the time interval between two device failures is too short, they may represent different devices responding to the same failure event; second, by setting a minimum interval, it is possible to clearly distinguish between a causal chain where device A fails first and device B fails later, and a parallel event where devices A and B fail independently; Mark all events to be grouped in which two devices have the same time sequence of failure as one group, and obtain the first group and the second group respectively; Based on the reverse monitoring sequence, we extract the groups corresponding to the equipment failure sequence that is the same as the reverse monitoring sequence and mark them as direction-consistent sequence groups. We count the number of direction-consistent sequence groups and calculate the ratio with the total number of historical failure events to obtain the proportion of direction-consistent sequence groups. The device relevance and the proportion of the number of sequences with consistent directions are added and integrated to output the sequence judgment coefficient; If the order judgment coefficient is greater than or equal to the order judgment coefficient limit, it means that the order of reverse monitoring is reasonable and marked as reasonable order; If the order judgment coefficient is less than the order judgment coefficient limit, it means that the order of reverse monitoring is unreasonable and is marked as unreasonable order; Among them, the sequence judgment coefficient limit is used to judge whether the reverse monitoring sequence is reasonable in actual monitoring application, and is set by technical personnel in this field based on historical data distribution and industry experience. The purpose of combining the correlation between the status data of two devices and the analysis of the fault propagation direction sequence is to identify the rationality of the reverse monitoring sequence. Its role is to: First, it is more comprehensive by making dual judgments on the correlation between devices and the consistency of fault propagation direction; Second, it provides effective support for fault early warning. When the device status data is highly correlated and the fault propagation direction is consistent with the reverse monitoring sequence, it means that reverse monitoring can detect potential faults of the parent device in advance through the child device status. This can strengthen the reverse monitoring mode to achieve accurate early warning. If the two are inconsistent, the failure risk of reverse monitoring in fault early warning can be identified in a timely manner, reducing early warning delays or missed reports caused by unreasonable monitoring sequences. Third, it provides a clear direction for optimizing the monitoring mechanism. By analyzing the degree of match between correlation and fault propagation direction, the root cause of an unreasonable reverse monitoring sequence can be identified. Is it because the actual correlation between devices is weak, making the monitoring sequence meaningless, or is there a disconnect between the fault propagation path and the monitoring sequence? This provides a concrete basis for adjusting monitoring priorities and optimizing data collection timing, helping to build a monitoring system that better aligns with the device dependency chain. Step S30: If the reverse monitoring sequence is unreasonable, adjust the reverse monitoring to forward monitoring; In some embodiments, if the reverse monitoring is unreasonable, the output in the aforementioned step S20 is the following, indicating that the reverse monitoring is unreasonable: If the order judgment coefficient is less than the order judgment coefficient limit, it is marked as unreasonable order; The process of identifying unreasonable reasons and adjusting reverse monitoring based on the identified reasons is as follows: If the output order is unreasonable, you need to adjust the reverse monitoring order to the forward monitoring order, and change the original monitoring of child devices first to monitoring parent devices first; This embodiment has at least the following effects: By analyzing the dependency chain relationships of device groups, we can effectively extract reverse monitoring device groups that exist during the monitoring process, clarify the unreasonable sequence in which child devices are monitored before parent devices, provide precise targeting for monitoring optimization, and solve the problem of disordered monitoring order of dependency chain devices in traditional monitoring. Combining the correlation of equipment status data and the consistency of fault propagation, the rationality of reverse monitoring is judged comprehensively from multiple dimensions, reducing misjudgments caused by a single indicator and making the judgment results more accurate. Optimize unreasonable reverse monitoring to reduce missed faults and misjudgments caused by disordered sequences, and improve monitoring response speed and accuracy; Through reasonable monitoring sequence and data correlation analysis, the timing logic of equipment operating status data is matched with the fault propagation direction, so that potential equipment faults can be discovered earlier, the fault propagation path can be determined, and the timeliness of fault warning and the accuracy of fault location can be improved; By optimizing the monitoring sequence, the system chain reaction caused by the failure of parent equipment to be discovered in time is reduced, the risk of power outage is reduced, and the stable operation of the power grid is guaranteed; Reduce ineffective maintenance of sub-devices due to unreasonable reverse monitoring, reduce the waste of manpower and material resources, and at the same time, by accurately locating the root cause of the fault (parent device), reduce the probability of large-scale shutdown maintenance, reduce operation and maintenance costs and power outage losses.

[0019] Example 2:

[0020] Based on the same inventive concept as the digital monitoring method for power transmission and transformation projects in the above embodiment, Figure 3 The present application provides a digital monitoring system for power transmission and transformation projects, wherein the system specifically includes: Reverse monitoring identification module: During the monitoring of power transmission and transformation projects, the module analyzes the dependency chains between equipment groups and extracts equipment groups that are subject to reverse monitoring during the monitoring process. Analyze the dependency chains of equipment in power transmission and transformation projects. By building an equipment inventory, extracting strong association rules, and combining them with fault propagation paths, we can identify the dependency directions of equipment groups. By calculating the difference in equipment response time or analyzing the data flow sequence and comparing them with the dependency directions, we can identify reverse monitoring equipment groups (i.e., groups where child equipment takes precedence over parent equipment) during monitoring. Reverse monitoring rationality analysis module: Based on the correlation between the status data of two devices in the reverse monitoring device group and the consistency of fault propagation, the module analyzes the rationality of the reverse monitoring sequence corresponding to the reverse monitoring device group and determines whether the reverse monitoring is reasonable; For the reverse monitoring equipment group, the rationality of its reverse monitoring sequence is analyzed from two dimensions: the device correlation is obtained by calculating the mean value of the Pearson correlation coefficient, which represents the relevance of the equipment status data; the proportion of consistent directions is statistically analyzed by grouping historical fault time differences, and the sequence judgment coefficient is integrated to reflect the consistency of fault propagation; Monitoring optimization module: If it is unreasonable, adjust the reverse monitoring order to forward monitoring.

[0021] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital monitoring method for power transmission and transformation projects, characterized by: The following steps are involved: In the process of monitoring power transmission and transformation projects, the dependency chain relationship between equipment groups is analyzed, and the dependency chain equipment groups with reverse monitoring in the monitoring process are extracted; Based on the correlation between the status data of two devices in the reverse monitoring device group, the consistency of fault propagation, and the importance of the devices, the rationality of the reverse monitoring sequence corresponding to the reverse monitoring device group is analyzed to determine whether the reverse monitoring is reasonable; If the reverse monitoring sequence is unreasonable, adjust the reverse monitoring to forward monitoring.

2. The digital monitoring method for power transmission and transformation projects according to claim 1, characterized in that: The process of analyzing the dependency relationship between device groups is as follows: Obtain the equipment involved in the power transmission and transformation project and build an equipment inventory library; convert the equipment operating status into Boolean data and use the Apriori algorithm to extract frequently co-occurring equipment status combinations; Set a time window and generate a transaction dataset if the device status changes. Treat a single device status as a 1-item set and generate high-frequency 2-item sets through concatenation and pruning. Calculate the support of each item set, and filter the item sets with support greater than or equal to the minimum support as frequent item sets; Calculate the confidence of each transaction and select the item sets with confidence greater than or equal to the minimum confidence as strong association rules; Based on the obtained strong association rules, by comparing the effectiveness of the identification rules, the rule corresponding to the maximum confidence value among the effective strong association rules is extracted as the maximum confidence association rule; Based on GOOSE signal interaction, the dependency direction of two devices in the maximum confidence association rule is determined, and the device group with dependency chain relationship is obtained.

3. The digital monitoring method for power transmission and transformation projects according to claim 1, characterized in that: The process of extracting the device group of the dependency chain that has reverse monitoring during the monitoring process is as follows: During the monitoring process, the response time of two devices in a dependent chain relationship is obtained, and the difference between the response times of the two devices is calculated and the absolute value is taken to obtain the response time difference; If the response time difference is greater than or equal to the response time difference limit, the direction consistency comparison process is triggered; If the response time difference is less than the response time difference limit, the data flow consistency comparison process is triggered.

4. A digital monitoring method for power transmission and transformation projects according to claim 3, characterized in that: The directional consistency comparison process: Sort the devices in order of response time to get the response time sequence; Compare the consistency of response time sequence and dependency direction between dependency chain devices; If the response time sequence is inconsistent with the dependency direction between the dependency chain devices, it means that the monitoring sequence of the device group is reverse monitoring.

5. The digital monitoring method for power transmission and transformation projects according to claim 3, characterized in that: The data flow consistency comparison process: By deploying a network packet capture tool on the switch mirror port to capture communication data packets between devices, combined with protocol analysis to clarify the relationship between the sending and receiving devices, the packet timestamp is recorded and the device time is synchronized with the monitoring platform. By comparing the logs to verify the timing, the data transmission path from the source device to the target device is determined. Obtain the timing of data flow between devices and obtain the data flow order; If the data flow order is inconsistent with the dependency direction between the dependency chain devices, it means that the monitoring order of the device group is reverse monitoring.

6. The digital monitoring method for power transmission and transformation projects according to claim 1, characterized in that: Determine whether the reverse monitoring is reasonable: By analyzing the correlation and fault propagation direction consistency, the order judgment coefficient is output; If the order judgment coefficient is less than the order judgment coefficient limit, it is marked as unreasonable order.

7. A digital monitoring method for power transmission and transformation projects according to claim 6, characterized in that: The process of obtaining the order judgment coefficient is as follows: The device relevance is obtained by analyzing the correlation, and the proportion of the number of sequences with consistent directions is obtained by analyzing the consistency of fault propagation. The device relevance is combined with the proportion of the number of sequences with consistent directions to output the sequence judgment coefficient.

8. The digital monitoring method for power transmission and transformation projects according to claim 1, characterized in that: The process of obtaining the correlation between the two device status data is as follows: Obtain all reverse-monitored device groups, and based on any reverse-monitored device group, collect the operating status data of two devices in the device group in real time; The correlation coefficient of the operating status data of two devices is calculated by the Pearson correlation coefficient to represent the degree of association between the data of the two devices; The correlation coefficients of all the operating status data of the two devices are averaged to obtain the device correlation.

9. The digital monitoring method for power transmission and transformation projects according to claim 1, characterized in that: The process of obtaining the fault propagation consistency is as follows: Analyze the time when two equipment failures occurred in historical failure events to obtain events to be grouped; Mark all events to be grouped in which two devices have the same time sequence of failure as one group, and obtain the first group and the second group respectively; Based on the reverse monitoring sequence, the groups corresponding to the equipment failure sequence with the same reverse monitoring sequence are extracted and marked as direction-consistent sequence groups. The number of direction-consistent sequence groups is counted and the ratio is calculated with the total number of historical failure events to obtain the proportion of direction-consistent sequence groups.

10. A digital monitoring method for power transmission and transformation projects according to claim 9, characterized in that: The process of obtaining the events to be grouped is as follows: Obtain historical fault events from the historical database, obtain the fault occurrence time of the two devices in each historical fault event, and calculate the difference between the fault occurrence time of the two devices, and obtain the absolute value of the difference as the fault occurrence time difference; Extract historical fault events whose fault occurrence time difference is greater than or equal to the minimum fault occurrence time difference as events to be grouped.

Images