A power transmission and transformation project digital monitoring method

Abstract

The present application belongs to the technical field of power transmission and transformation engineering monitoring, and provides a kind of power transmission and transformation engineering digital monitoring method, comprising the following steps: in the process of carrying out power transmission and transformation engineering monitoring, the dependence chain relationship between equipment group is analyzed, and the dependence chain equipment group existing reverse monitoring in the monitoring process is extracted;According to the correlation between the two equipment state data in the equipment group of reverse monitoring, the consistency of fault propagation and the importance of equipment, the rationality of the reverse monitoring sequence corresponding to the equipment group of reverse monitoring is analyzed, whether the reverse monitoring is reasonable is judged;If the reverse monitoring sequence is not reasonable, then adjust reverse monitoring to forward monitoring.The present application can effectively extract the reverse monitoring equipment group existing in the monitoring process by analyzing the dependence chain relationship of equipment group, and clearly the unreasonable sequence of monitoring the child equipment before the parent equipment, to provide accurate targeting for monitoring optimization, and optimize the problem of chaotic monitoring sequence of dependence chain equipment in traditional monitoring.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of power transmission and transformation engineering monitoring, and particularly relates to a power transmission and transformation engineering digital monitoring method. BACKGROUND

[0002] Power transmission and transformation engineering digital monitoring is based on digital technologies such as the Internet of Things, big data, and artificial intelligence to monitor the state (such as temperature, vibration, and partial discharge) and operating parameters (voltage, current, and power) of devices such as transformers, circuit breakers, and busbars in substations in real time, while covering remote monitoring of the environment (temperature and humidity, security) and auxiliary systems (firefighting, lighting). The “digitalization” refers to the collection of multi-source data through sensors and intelligent terminals, combined with edge computing and cloud computing analysis to realize device fault early warning, operation optimization, and intelligent decision-making, significantly improving operation and maintenance efficiency and power grid reliability.

[0003] When monitoring power transmission and transformation engineering, two devices may form a dependency chain device group due to the dependency chain relationship. In the actual monitoring process, the monitoring order in the dependency chain device group may form a reverse monitoring sequence with the child device monitored first and the parent device monitored later due to the monitoring mechanism or other reasons. If the reverse monitoring has unreasonable phenomena, the state of the child device is often affected by the parent device. If the child device is monitored first and an abnormality is found, the problem may be incorrectly attributed to the child device itself, and the case that the parent device failure is the root cause is ignored. For example, if the parent device is a circuit breaker (controls the on-off of the child device) and the child device is a line load, the line load current may be found to be abnormal during reverse monitoring, and the line problem may be prioritized for troubleshooting, while the actual cause is the poor contact of the circuit breaker, which delays the fault positioning time.

[0004] Therefore, the present application provides a power transmission and transformation engineering digital monitoring method. SUMMARY

[0005] In order to make up for the deficiencies of the prior art and solve at least one technical problem raised in the background art.

[0006] The technical solution adopted by the present application to solve its technical problems is: a power transmission and transformation engineering digital monitoring method, comprising the following steps:

[0007] In the process of monitoring power transmission and transformation engineering, the dependency chain relationship between device groups is analyzed, and dependency chain device groups with reverse monitoring in the monitoring process are extracted.

[0008] According to the correlation between the state data of the two devices in the reverse monitoring device group, the fault propagation consistency, and the importance of the devices, the rationality of the reverse monitoring order corresponding to the reverse monitoring device group is analyzed, and it is determined whether the reverse monitoring is reasonable.

[0009] If the reverse monitoring sequence is unreasonable, the reverse monitoring is adjusted to forward monitoring.

[0010] As a further scheme of the present application, the process of analyzing the dependency relationship between the device groups is:

[0011] Obtain the devices involved in the power transmission and transformation project, and construct a device list library; convert the device operating state quantity into Boolean type data, and extract the frequently co-occurring device state combination by using the Apriori algorithm;

[0012] Set a time window, and generate a transaction data set if the device state changes; take a single device state as a 1-item set, and generate a high-frequency 2-item set through connection and pruning;

[0013] Calculate the support degree of each item set, and screen the item sets with a support degree greater than or equal to a minimum support degree as frequent item sets;

[0014] Calculate the confidence degree of each transaction, and screen the item sets with a confidence degree greater than or equal to a minimum confidence degree as strong association rules;

[0015] Based on the obtained strong association rules, the effectiveness of the rules is compared and identified, the rule corresponding to the maximum confidence degree in the effective strong association rules is extracted as a maximum confidence degree association rule;

[0016] Based on GOOSE signal interaction, the dependency direction of the two devices in the maximum confidence degree association rule is determined, and the device group with a dependency chain relationship is obtained.

[0017] As a further scheme of the present application, the process of extracting the device group with a reverse monitoring dependency chain in the monitoring process is:

[0018] In the monitoring process, the response times of the two devices in the device with a dependency chain relationship are obtained, and the response times of the two devices are subjected to difference calculation and absolute value taking to obtain a response time difference;

[0019] If the response time difference is greater than or equal to a response time difference limit value, a direction consistency comparison process is triggered;

[0020] If the response time difference is less than the response time difference limit value, a data flow direction consistency comparison process is triggered.

[0021] As a further scheme of the present application, the direction consistency comparison process is:

[0022] According to the sequence of the response times, the devices are sorted to obtain a response time sequence;

[0023] The response time sequence is compared with the dependency direction between the devices in the dependency chain for consistency;

[0024] If the response time sequence is inconsistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is reverse monitoring.

[0025] As a further scheme of the present application, the data flow consistency comparison process is:

[0026] By deploying a network packet capture tool to capture the communication data packets between devices in the mirror port of the switch, the relationship between the sending and receiving devices is determined by protocol analysis, the data packet timestamp is recorded, the device and monitoring platform time are synchronized, the timing is verified by log comparison, and the transmission path of the data from the source device to the target device is determined.

[0027] Obtain the data flow sequence between devices.

[0028] If the data flow sequence is inconsistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is reverse monitoring.

[0029] As a further scheme of the present application, the determination of whether the reverse monitoring is reasonable:

[0030] By analyzing the correlation and the consistency of fault propagation direction, the sequence judgment coefficient is output.

[0031] If the sequence judgment coefficient is less than the sequence judgment coefficient limit value, it is marked as unreasonable.

[0032] As a further scheme of the present application, the sequence judgment coefficient acquisition process is:

[0033] By analyzing the correlation, the device relevance is obtained, and by analyzing the consistency of fault propagation, the proportion of the number of consistent sequences is obtained.

[0034] Fuse the device relevance and the proportion of the number of consistent sequences, and output the sequence judgment coefficient.

[0035] As a further scheme of the present application, the correlation between the two device state data is obtained as follows:

[0036] Obtain all reverse monitoring device groups, and based on any one reverse monitoring device group, real-time collect the running state data of two devices in the device group.

[0037] Calculate the correlation coefficient of the running state data of the two devices by Pearson correlation coefficient, which represents the correlation degree of the two device data.

[0038] The correlation coefficients of all running state data of the two devices are processed by mean value to obtain the device relevance.

[0039] As a further scheme of the present application, the fault propagation consistency acquisition process is:

[0040] analyzing the time of occurrence of two equipment failures in historical failure events to obtain events to be grouped;

[0041] marking events with the same time sequence of two equipment failures in all events to be grouped as a group to obtain a first group and a second group respectively;

[0042] based on the reverse monitoring sequence, extracting a group corresponding to the sequence of failures of the same equipment as the reverse monitoring sequence, marking as a direction consistent sequence group, counting the number of direction consistent sequence groups, and performing ratio calculation with the total number of historical failure events to obtain the proportion of the number of direction consistent sequences.

[0043] As a further scheme of the present application: the obtaining process of the events to be grouped is:

[0044] obtaining historical failure events from a historical database, obtaining the failure occurrence time of two equipment in each historical failure event, and performing difference calculation on the failure occurrence time of two equipment to obtain the absolute value of the failure occurrence time difference as the failure occurrence time difference;

[0045] extracting historical failure events with a failure occurrence time difference greater than or equal to a minimum failure occurrence difference as events to be grouped.

[0046] The beneficial effects of the present application are as follows:

[0047] The present application can effectively extract reverse monitoring equipment groups existing in the monitoring process by analyzing the dependency chain relationship of the equipment group, and clearly defines the unreasonable sequence of monitoring the child equipment before the parent equipment, providing precise targeting for monitoring optimization, and optimizing the problem of chaotic monitoring sequence of the dependency chain equipment in traditional monitoring;

[0048] The present application matches the time sequence logic of the equipment operation state data and the fault propagation direction relationship through reasonable monitoring sequence and data correlation analysis, so that potential equipment failures can be detected earlier, the fault propagation path can be determined, the timeliness of fault warning and the accuracy of fault positioning can be improved, the system chain reaction caused by the failure of the parent equipment is reduced through optimization of the monitoring sequence, the risk of power outage is reduced, and the stable operation of the power grid is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0049] The present application will be further described below with reference to the accompanying drawings.

[0050] Figure 1 is a step flow chart of a power transmission and transformation engineering digital monitoring method of the present application;

[0051] Figure 2 is a step flow chart of identifying reverse monitoring in a power transmission and transformation engineering digital monitoring method of the present application;

[0052] Figure 3 is a framework diagram of a power transmission and transformation engineering digital monitoring system. DETAILED DESCRIPTION

[0053] In order to make the technical means, creative features, purposes and effects of the present application easy to understand, the present application will be further described below in conjunction with specific embodiments.

[0054] Embodiment 1:

[0055] Please refer to Figure 1 and Figure 2 , the power transmission and transformation engineering digital monitoring method described in the embodiments of the present application includes the following steps:

[0056] Step S10: In the process of monitoring the power transmission and transformation engineering, analyze the dependency chain relationship between the device groups, and extract the device groups with reverse monitoring in the monitoring process;

[0057] In some embodiments, among all the devices of the power transmission and transformation engineering, the device groups with dependency chain relationship are analyzed and extracted, and the specific process is as follows:

[0058] Obtain the devices involved in the power transmission and transformation engineering, and construct a device list library; wherein the devices include but are not limited to: transformers, circuit breakers, disconnectors, sensors, controllers, protection devices;

[0059] The device list includes: device type, functional parameter, physical connection relationship, position in the system and belonging subsystem; the belonging subsystem at least includes: power transmission line, substation, distribution network;

[0060] For example, the device type (vacuum circuit breaker), the functional parameter (rated voltage: 220kV; rated current: 2500A; breaking current: 40kA), the physical connection relationship (one end connected to the 220kV power transmission line, the other end connected to the 220kV bus of the substation), the position in the system (interval A of the 220kV distribution device area of the substation), and the belonging subsystem (substation);

[0061] Obtain the historical operation data of any two devices, and perform data cleaning, which includes: using the forward filling method to complete the missing data of the device state, and marking the device state outliers based on the 3σ principle;

[0062] The historical operation data is the real-time operation record of the device in the past period of time, including but not limited to: electrical quantity, state quantity, environmental quantity multidimensional information; collected through the SCADA monitoring system or the Internet of Things sensor, and stored in the historical database;

[0063] The device running state quantity is converted into Boolean type or enumeration type data, which is convenient for association analysis, and the Apriori algorithm is used to extract the frequently co-occurring device state combinations;

[0064] A time window is set, and if the device state changes, a transaction data set is generated; the time window is set by a person skilled in the art according to the collection frequency of historical operation data combined with industry experience;

[0065] A single device state is taken as a 1-item set, and a high-frequency 2-item set is generated by connection and pruning;

[0066] The support of each item set is calculated, and the support is the ratio of the number of item sets to the total transactions;

[0067] The minimum support is set, and the item set with a support greater than or equal to the minimum support is selected as a frequent item set;

[0068] The confidence of each transaction is calculated, and the confidence is the probability of the occurrence of the item set consequent (the latter part of the device state combination) when the item set antecedent (the former part of the device state combination) occurs;

[0069] The minimum confidence is set, and the item set with a confidence greater than or equal to the minimum confidence is selected as a strong association rule;

[0070] Based on the obtained strong association rules, the effectiveness of the rules is identified by comparing the "power grid device operation regulations", and the rule corresponding to the maximum confidence value in the effective strong association rules is extracted as the maximum confidence association rule;

[0071] Based on the GOOSE signal interaction, the dependency direction of the two devices in the maximum confidence association rule is determined; a dependency chain device group list is generated, and a verification state is marked;

[0072] For example, in a certain 220kV substation, the dependency chain relationship between the protection device (device A) and the circuit breaker (device B) is extracted;

[0073] The "action signal" (0=not action, 1=action) of device A (protection device) and the "opening and closing position" (0=split, 1=close) of device B (circuit breaker) data are obtained from the SCADA system;

[0074] A 1-second time window is set, and a transaction data set (part of the example) is generated: transaction 1: {device A=1, device B=0} (protection device action, circuit breaker split); transaction 2: {device A=0, device B=1} (protection device not action, circuit breaker close);

[0075] Initial candidate item set: {Device A = 1}, {Device B = 0}; after connection and pruning, generate 2-item set: {Device A = 1, Device B = 0} (support = 0.15);

[0076] Set the minimum support 0.1, and retain the item set with support ≥ 0.1 (such as {Device A = 1, Device B = 0});

[0077] Rule 1: Device A = 1 → Device B = 0 (protection device action → circuit breaker tripping), confidence = 0.9 (90% of protection device actions are accompanied by circuit breaker tripping);

[0078] Rule 2: Device B = 1 → Device A = 0 (circuit breaker closing → protection device not acting), confidence = 0.85 (85% of circuit breaker closing times when the protection device does not act);

[0079] Expert knowledge base verification: Rule 1 meets the requirements of "protection device action followed by circuit breaker tripping" in the "Power Grid Equipment Operation and Maintenance Regulations";

[0080] The protection device controls the circuit breaker to trip through the GOOSE signal, and the fault propagation path is Device A → Device B;

[0081] Device group ID: GROUP_001;

[0082] Device pair: protection device_1# → circuit breaker_1#;

[0083] Dependency chain type: control logic association;

[0084] Verification status: passed (Rule 1 confidence = 0.9, in line with regulations);

[0085] In some embodiments, the device groups with dependency chain relationships are obtained, and the device groups with reverse monitoring in the monitoring process are extracted;

[0086] What needs to be defined for reverse monitoring is that the monitoring sequence of the child device is prior to its parent device, i.e. the sequence of child device → parent device,

[0087] For example, temperature and humidity sensor (child device) → environmental controller (parent device): early warning of controller failure by monitoring environmental parameter abnormalities;

[0088] In the monitoring process, the response times of two devices in the devices with dependency chain relationships are obtained, and the response times of the two devices are difference calculated and take the absolute value to obtain the response time difference;

[0089] If the response time difference is greater than or equal to the response time difference limit value, the direction consistency comparison process is triggered; according to the sequence of response times, the devices are sorted to obtain the response time sequence;

[0090] The response time difference limit value plays a role of a trigger in the monitoring method: when the response time difference between the devices exceeds the threshold value, the system will automatically start the direction consistency comparison process, which is determined by the person skilled in the art according to the collection frequency of historical operation data and industry experience;

[0091] The response time sequence is compared with the dependency direction between the devices in the dependency chain for consistency;

[0092] If the response time sequence is consistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is forward monitoring;

[0093] If the response time sequence is inconsistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is reverse monitoring;

[0094] If the response time difference is less than the response time difference limit value, the data flow direction consistency comparison process is triggered;

[0095] The data flow direction of the two devices is obtained by deploying a network packet capturing tool to capture the communication data packets between the devices at the mirror port of the switch, combining protocol analysis to determine the sending and receiving device relationship, recording the data packet timestamp and synchronizing the device and the monitoring platform time, and finally verifying the timing through log comparison to determine the transmission path of the data from the source device to the target device;

[0096] The data flow direction sequence is obtained by using the above tools and techniques to obtain the data flow direction timing between the devices;

[0097] If the data flow direction sequence is consistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is forward monitoring;

[0098] If the data flow direction sequence is inconsistent with the dependency direction between the devices in the dependency chain, it indicates that the monitoring sequence of the device group is reverse monitoring;

[0099] For example, scenario 1: the response time of the protection device (parent device) is 200 ms, and the response time of the circuit breaker (child device) is 100 ms; the response time difference is 100 ms, which is greater than or equal to the preset response time difference limit value (50 ms), so the direction consistency comparison is performed;

[0100] Response time sequence: first circuit breaker and then protection device (child→parent); dependency chain direction: first protection device and then circuit breaker (parent→child); the sequence is inconsistent, and it is determined as reverse monitoring;

[0101] Scenario 2: the response time of the environmental controller (parent device) is 140 ms, and the response time of the temperature and humidity sensor (child device) is 50 ms; the response time difference is 40 ms, which is less than the preset response time difference limit value (50 ms), so the data flow direction consistency comparison is performed

[0102] The time when the temperature and humidity sensor data packet arrives at the switch is 08:00:00.000, and the time when the environmental controller data packet arrives at the platform is 08:00:00.050;

[0103] Data flow order: temperature and humidity sensor first and environmental controller second (child→parent); dependency chain direction: environmental controller first and temperature and humidity sensor second (parent→child); the orders are inconsistent, and the reverse monitoring is determined;

[0104] Step S20: According to the correlation between the two device state data in the reverse monitoring device group and the fault propagation consistency, the rationality of the reverse monitoring order corresponding to the reverse monitoring device group is analyzed, and whether the reverse monitoring is reasonable is judged;

[0105] Firstly, the acquisition process of the correlation between the two device state data is as follows:

[0106] All reverse monitoring device groups are obtained, and the running state data of the two devices in the device group is collected in real time based on any one reverse monitoring device group, including but not limited to: voltage, current, temperature, switch state, etc.

[0107] The correlation coefficient of the running state data of the two devices is calculated to represent the correlation degree of the two device data, wherein the correlation coefficient is calculated by Pearson correlation coefficient;

[0108] The correlation coefficients of all running state data of the two devices are processed by mean value to obtain the device correlation degree;

[0109] For example, in a certain 220kV substation, transformer A (main transformer) and transformer B (backup transformer) are identified to have a reverse monitoring relationship through the foregoing step S10, and the collected parameters are voltage, current and temperature;

[0110] The voltage sequence of device A is: [220.5, 221.0, 219.8, 222.1, 220.3];

[0111] The voltage sequence of device B is: [218.7, 219.2, 217.9, 220.0, 218.5];

[0112] The correlation coefficient calculated by substituting the Pearson formula is: 0.9928;

[0113] The current sequence of device A is: [10.2, 10.5, 10.1, 10.3, 10.4];

[0114] The current sequence of device B is: [9.8, 10.0, 9.7, 9.9, 10.1];

[0115] The correlation coefficient calculated by substituting the Pearson formula is: 0.9000;

[0116] The device A temperature sequence is: [35.6, 36.1, 35.8, 36.3, 35.9]

[0117] The device B temperature sequence is: [34.2, 34.7, 34.0, 34.5, 34.3]

[0118] The correlation coefficient calculated by substituting the Pearson formula is: 0.7260;

[0119] The device correlation is 0.8729;

[0120] Secondly, the acquisition process of the fault propagation consistency of the two devices is:

[0121] The fault propagation consistency is analyzed according to the time sequence relationship of the faults by backtracking the historical fault data of the two devices;

[0122] The historical fault events are obtained from the historical database, the fault occurrence time of the two devices in each historical fault event is obtained, and the fault occurrence time of the two devices is calculated by difference, and the absolute value of the difference is the fault occurrence time difference;

[0123] The historical fault events with a fault occurrence time difference greater than or equal to the minimum fault occurrence difference are extracted as the events to be grouped;

[0124] The minimum fault occurrence difference is set by a person skilled in the art according to the characteristics of the system, for example, according to the device response time, if the device fault is detected by the system after 100 ms, then the minimum fault occurrence difference is greater than or equal to 200 ms;

[0125] The reason for setting the minimum fault occurrence difference is that: first, if the time interval of the faults of the two devices is too short, it may belong to the different device responses of the same fault time; second, by limiting the minimum interval, the causal chain of device A fault first and device B fault later can be distinguished from the parallel events of device A and B independent faults;

[0126] The events with the same time sequence of the faults of the two devices in all the events to be grouped are marked as a group, and the first group and the second group are obtained respectively;

[0127] Based on the reverse monitoring sequence, the group corresponding to the fault sequence of the devices with the same sequence is extracted, which is marked as the direction consistent sequence group, the number of the direction consistent sequence group is counted, and the ratio of the number of the direction consistent sequence group to the total number of the historical fault events is calculated to obtain the proportion of the number of the direction consistent sequence group;

[0128] Add and fuse the device correlation degree and the direction consistent order quantity proportion, and output the order judgment coefficient;

[0129] If the order judgment coefficient is greater than or equal to the order judgment coefficient limit value, it means that the order of reverse monitoring is reasonable, and is marked as order reasonable;

[0130] If the order judgment coefficient is less than the order judgment coefficient limit value, it means that the order of reverse monitoring is unreasonable, and is marked as order unreasonable;

[0131] The order judgment coefficient limit value is used to judge whether the reverse monitoring order is reasonable in actual monitoring application, and is set by a person skilled in the art through historical data distribution and industry experience;

[0132] The analysis of the correlation between the two device state data and the fault propagation direction order is combined mainly to identify the reasonableness of the order of reverse monitoring, which has the following effects:

[0133] Firstly, through the double judgment of the correlation between the devices and the consistency of the fault propagation direction, it is more comprehensive;

[0134] Secondly, it provides effective support for fault early warning. When the device state data correlation is high and the fault propagation direction is consistent with the reverse monitoring order, it means that reverse monitoring can capture potential parent device faults through child device state in advance, and the reverse monitoring mode can be strengthened to achieve accurate early warning. If the two are contradictory, the failure risk of reverse monitoring in fault early warning can be identified in time, and the delay or false alarm of early warning caused by unreasonable monitoring order can be reduced;

[0135] Thirdly, the monitoring mechanism optimization provides a clear direction. By analyzing the matching degree of correlation and fault propagation direction, the root cause of unreasonable reverse monitoring order can be located. Is the actual correlation between devices weak, resulting in meaningless monitoring order, or is the fault propagation path and the monitoring order out of sync? This provides specific basis for subsequent adjustment of monitoring priority and optimization of data collection timing, which helps to build a monitoring system that is more in line with the device dependency chain relationship;

[0136] Step S30: If the reverse monitoring order is unreasonable, adjust the reverse monitoring to forward monitoring;

[0137] In some embodiments, if the reverse monitoring is unreasonable, the following conditions are output in the foregoing step S20, indicating that the reverse monitoring is unreasonable:

[0138] If the order judgment coefficient is less than the order judgment coefficient limit value, it is marked as order unreasonable;

[0139] Identify the reason for being unreasonable, and adjust the process of reverse monitoring according to the identified reason:

[0140] If the output order is unreasonable, the reverse monitoring order needs to be adjusted to the forward monitoring order, and the originally monitored child device is modified to the monitored parent device;

[0141] This embodiment has at least the following effects:

[0142] By analyzing the dependency chain relationship of the device group, the reverse monitoring device group existing in the monitoring process can be effectively extracted, the unreasonable sequence of the child device monitoring the parent device first is clarified, precise targeting is provided for monitoring optimization, and the problem of chaotic monitoring order of the dependency chain device in the traditional monitoring is optimized;

[0143] In combination with the correlation of device state data and fault propagation consistency, the rationality of reverse monitoring is comprehensively judged in multiple dimensions, the misjudgment caused by a single index is reduced, and the judgment result is more accurate;

[0144] The unreasonable reverse monitoring is optimized, the fault omission and misjudgment caused by chaotic order are reduced, and the monitoring response speed and accuracy are improved;

[0145] Through reasonable monitoring order and data correlation analysis, the time sequence logic of the device operation state data is matched with the fault propagation direction relationship, so that potential device faults can be found earlier, the fault propagation path can be determined, and the timeliness of fault early warning and the accuracy of fault positioning are improved;

[0146] By optimizing the monitoring order, the system chain reaction caused by the failure of the parent device to be found in time is reduced, the risk of power outage is reduced, and the stable operation of the power grid is ensured;

[0147] The invalid maintenance of the child device caused by unreasonable reverse monitoring is reduced, the waste of human and material resources is reduced, the probability of large-scale shutdown maintenance is reduced by accurately positioning the fault source (parent device), and the operation and maintenance cost and power loss are reduced.

[0148] Embodiment 2:

[0149] Based on the same inventive concept as the power transmission and transformation engineering digital monitoring method in the foregoing embodiments, as Figure 3 Illustrated, the application provides a power transmission and transformation engineering digital monitoring system, wherein the system specifically comprises:

[0150] Reverse monitoring identification module: in the process of monitoring the power transmission and transformation engineering, the dependency chain relationship between the device groups is analyzed, and the device groups existing in the reverse monitoring in the monitoring process are extracted;

[0151] The dependency chain relationship of equipment in power transmission and transformation projects is analyzed, the dependency direction of equipment groups is determined by constructing an equipment list library, extracting strong association rules and combining fault propagation paths, and then the reverse monitoring equipment groups (i.e., the equipment groups in which the monitoring sequence of the child equipment is prior to that of the parent equipment) in the monitoring process are identified by comparing the response time difference of the equipment or the data flow direction sequence with the dependency direction;

[0152] The reverse monitoring rationality analysis module: according to the correlation between the state data of the two equipment in the reverse monitoring equipment group and the consistency of fault propagation, the rationality of the reverse monitoring sequence corresponding to the reverse monitoring equipment group is analyzed, and whether the reverse monitoring is reasonable is judged;

[0153] The rationality of the reverse monitoring sequence of the reverse monitoring equipment group is analyzed from two dimensions: the correlation degree of the equipment is obtained by calculating the mean of the Pearson correlation coefficient, which represents the correlation of the equipment state data; the sequence judgment coefficient is obtained by fusing the consistent direction proportion of the historical fault time difference grouping statistics, which reflects the consistency of fault propagation;

[0154] The monitoring optimization module: if it is not reasonable, the sequence of the reverse monitoring is adjusted to be forward monitoring.

[0155] The above shows and describes the basic principles, main features and advantages of the present application. It should be understood by those skilled in the art that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for digital monitoring of power transmission and transformation projects, characterized by: The method comprises the following steps: In the process of monitoring the power transmission and transformation project, the dependency chain relationship between the device groups is analyzed, and the device groups with reverse monitoring in the monitoring process are extracted; The process of extracting the device groups with reverse monitoring in the monitoring process is as follows: In the monitoring process, the response times of two devices with a dependency chain relationship are obtained, and the response times of the two devices are calculated by difference and absolute value to obtain the response time difference; If the response time difference is greater than or equal to the response time difference limit value, the direction consistency comparison process is triggered; If the response time difference is less than the response time difference limit value, the data flow direction consistency comparison process is triggered; The direction consistency comparison process is as follows: The devices are sorted according to the order of the response times to obtain the response time order; The response time order is compared with the dependency direction between the dependency chain devices for consistency; If the response time order is inconsistent with the dependency direction between the dependency chain devices, it indicates that the monitoring order of the device group is reverse monitoring; The rationality of the reverse monitoring order corresponding to the reverse monitoring device group is analyzed according to the correlation between the state data of the two devices in the reverse monitoring device group, the fault propagation consistency and the importance of the device, and it is judged whether the reverse monitoring is reasonable; If the reverse monitoring order is not reasonable, the reverse monitoring is adjusted to forward monitoring.

2. The method for digital monitoring of power transmission and transformation project according to claim 1, characterized in that: The process of analyzing the dependency relationship between the device groups is as follows: The devices involved in the power transmission and transformation project are obtained to construct a device list library; the device operating state quantity is converted into Boolean type data, and the Apriori algorithm is used to extract the frequently co-occurring device state combinations; A time window is set, and if the device state changes, a transaction data set is generated; a single device state is taken as a 1-item set, and a high-frequency 2-item set is generated through connection and pruning; The support of each item set is calculated, and the item set with a support greater than or equal to the minimum support is selected as a frequent item set; The confidence of each transaction is calculated, and the item set with a confidence greater than or equal to the minimum confidence is selected as a strong association rule; Based on the obtained strong association rules, the effectiveness of the rules is identified by comparison, the rule corresponding to the maximum confidence value in the effective strong association rules is extracted as the maximum confidence association rule; Based on the GOOSE signal interaction, the dependency direction of the two devices in the maximum confidence association rule is determined, and the device group with a dependency chain relationship is obtained.

3. The method for digital monitoring of power transmission and transformation project according to claim 1, characterized in that: The data flow direction consistency comparison process is as follows: A network packet capturing tool is deployed on the switch mirror port to capture the communication data packets between devices, the relationship between the sending and receiving devices is determined through protocol analysis, the data packet timestamps are recorded, the device and the monitoring platform time are synchronized, the time sequence is verified through log comparison, and the transmission path of data from the source device to the target device is determined; The data flow direction sequence is obtained; If the data flow direction sequence is inconsistent with the dependency direction between the dependency chain devices, it indicates that the monitoring order of the device group is reverse monitoring.

4. The method of claim 1, wherein: The judgment of whether the reverse monitoring is reasonable is as follows: The order judgment coefficient is output through the analysis of the correlation and the fault propagation direction consistency; If the order judgment coefficient is less than the order judgment coefficient limit value, it is marked as an unreasonable order.

5. The method of claim 4, wherein: The process of obtaining the order judgment coefficient is as follows: The device relevance is obtained by analyzing the relevance, and the direction consistent sequence proportion is obtained by analyzing the fault propagation consistency. The device relevance and the direction consistent sequence proportion are fused to output a sequence judgment coefficient.

6. The method of claim 1, wherein: The process of obtaining the relevance between the two device state data is as follows: All reverse monitoring device groups are obtained, and the running state data of two devices in the device group is collected in real time based on any one reverse monitoring device group. The correlation coefficient of the running state data of the two devices is calculated by Pearson correlation coefficient, representing the correlation degree of the two device data. The correlation coefficients of all running state data of the two devices are processed by mean value to obtain the device relevance.

7. The method of claim 1, wherein: The process of obtaining the fault propagation consistency is as follows: The time of two device faults in historical fault events is analyzed to obtain grouped events. Events in which the time sequence of two device faults is the same are marked as a group, and the first group and the second group are obtained. Based on the reverse monitoring sequence, the group corresponding to the sequence of the device faults is extracted, which is marked as the direction consistent sequence group, the number of the direction consistent sequence group is counted, and the ratio of the number of the direction consistent sequence group to the total number of historical fault events is calculated to obtain the direction consistent sequence proportion.

8. The method of claim 7, wherein: The process of obtaining the grouped events is as follows: The historical fault events are obtained from the historical database, the fault occurrence time of two devices in each historical fault event is obtained, and the difference value of the fault occurrence time of two devices is calculated to obtain the fault occurrence time difference. The historical fault events with the fault occurrence time difference greater than or equal to the minimum fault occurrence difference are extracted as the grouped events.

Images