DC system monitoring method and device, computer equipment and storage medium

Abstract

The invention discloses a DC system monitoring method and device, computer equipment and a storage medium, and the method comprises the steps: training an intelligent monitoring tool through the knowledge base data, training data and man-machine interaction of a DC system; obtaining abnormal log data of the direct current system and inputting the abnormal log data to the trained intelligent monitoring tool; performing fault analysis on the direct current system by using the trained intelligent monitoring tool according to the abnormal log data; and outputting a fault analysis result to a user, the fault analysis result comprising a fault cause and / or a corresponding solution. According to the invention, multi-layer training is carried out on the intelligent monitoring tool in different modes, so that the intelligent monitoring tool can accurately identify a complex fault mode, and the precision and accuracy of monitoring the DC system are remarkably improved. Fault analysis is carried out in real time, early warning is given out in time, and fault response time is shortened. Through intelligent early warning and decision support, the operation reliability of the direct current system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power system monitoring, and in particular to a monitoring method, device, computer equipment and storage medium for a direct current system. Background Art

[0002] With the rapid development of power systems, DC transmission technology plays an increasingly important role in energy transmission and distribution due to its high efficiency and flexibility. However, the complexity of DC systems and the diversity of failure modes pose great challenges to their monitoring and data processing.

[0003] At present, the monitoring of DC systems mainly relies on traditional dispatching and monitoring systems, which are difficult to adapt to the fault prediction and diagnosis needs under different operating conditions and have low monitoring accuracy. Summary of the invention

[0004] Based on this, it is necessary to address the technical problem of low accuracy of fault monitoring of DC systems in the prior art and propose a monitoring method, device, computer equipment and storage medium for a DC system.

[0005] On the one hand, the present application provides a monitoring method for a DC system, which is applied to an intelligent monitoring system for a DC system. The monitoring method for the DC system includes:

[0006] Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0007] Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0008] Through human-computer interaction with the intelligent monitoring tool, the third level of training is performed on the intelligent monitoring tool;

[0009] According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained;

[0010] Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0011] Use trained intelligent monitoring tools to perform fault analysis on DC systems based on abnormal log data;

[0012] The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0013] In a second aspect, the present application provides a monitoring device for a DC system, the monitoring device for the DC system comprising:

[0014] A first training module, used for inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0015] A second training module is used to input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs a second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0016] A third training module, used for performing third-level training on the intelligent monitoring tool through human-computer interaction with the intelligent monitoring tool;

[0017] A training completion module, used to obtain a trained intelligent monitoring tool according to the first-layer training, the second-layer training and the third-layer training;

[0018] An abnormal log data input module is used to obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0019] A fault analysis module is used to use the trained intelligent monitoring tool to perform fault analysis on the DC system based on abnormal log data;

[0020] The result output module is used to output the fault analysis result to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0021] To achieve the above-mentioned purpose, the third aspect of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor performs the following steps:

[0022] Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0023] Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0024] Through human-computer interaction with the intelligent monitoring tool, the third level of training is performed on the intelligent monitoring tool;

[0025] According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained;

[0026] Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0027] Use intelligent monitoring tools to analyze DC system faults based on abnormal log data;

[0028] The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0029] To achieve the above-mentioned purpose, the fourth aspect of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0030] Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0031] Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0032] Through human-computer interaction with the intelligent monitoring tool, the third level of training is performed on the intelligent monitoring tool;

[0033] According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained;

[0034] Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0035] Use intelligent monitoring tools to analyze DC system faults based on abnormal log data;

[0036] The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0037] This application uses different methods to perform multi-layer training on intelligent monitoring tools, so that the intelligent monitoring tools can accurately identify complex fault modes, significantly improving the precision and accuracy of DC system monitoring. This application performs real-time fault analysis to quickly identify abnormal situations, issue warnings in a timely manner, and shorten fault response time. This application effectively prevents the occurrence of potential faults and improves the operational reliability of the DC system through intelligent early warning and decision support. This application can convert fault logs into more user-recognizable fault analysis results, reducing the requirements for user expertise and having a wide range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] in:

[0040] Figure 1 is a flow chart of a method for monitoring a DC system in one embodiment;

[0041] Figure 2 is a structural block diagram of a monitoring device for a DC system in one embodiment;

[0042] Figure 3 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] For DC system monitoring issues, existing technologies often rely on traditional programming methods and fixed logical judgments, which are difficult to adapt to the complex and changeable DC system fault modes and operating conditions, resulting in low monitoring accuracy, slow response speed and insufficient data processing capabilities. In addition, these tools usually lack intelligent learning and self-optimization capabilities, and cannot automatically adjust monitoring strategies and parameter settings based on historical data and real-time information.

[0045] Existing DC system monitoring and data processing solutions usually include data acquisition: collecting the operating parameters and status information of the DC system through sensors and measuring equipment; data transmission: transmitting the collected data to the monitoring center through the communication network; data processing: using a fixed algorithm model to process and analyze the received data to determine the operating status of the system and possible faults. Such methods lack certain accuracy.

[0046] Based on this, the present application provides a monitoring method for a DC system.

[0047] like Figure 1 As shown, in one embodiment, a monitoring method for a DC system is provided, and the monitoring method for a DC system includes the following steps:

[0048] S100: inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer of training according to the knowledge base data.

[0049] Specifically, the monitoring method of the DC system of the present application is applied to the intelligent monitoring system of the DC system, and the intelligent monitoring system of the DC system includes an intelligent monitoring tool, which is a monitoring tool built according to an artificial intelligence algorithm. The TensorFlow language can be used to develop intelligent monitoring tools based on deep learning models, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), etc. In addition to TensorFlow, other deep learning frameworks such as PyTorch and Keras can also be used to build intelligent monitoring tools based on AI models. In actual applications, the appropriate framework is selected according to the specific application scenarios and requirements, and this application does not limit this.

[0050] Among them, TensorFlow: is a symbolic mathematics system based on dataflow programming, which is widely used in the programming implementation of various machine learning algorithms.

[0051] Tensorflow has a multi-layer structure and can be deployed on various servers, PC terminals, and web pages. It supports high-performance numerical calculations on GPUs and TPUs and is widely used in Google's internal product development and scientific research in various fields.

[0052] The knowledge base data is the basic data of the DC system. For example, the knowledge base data includes documents such as the substation DC power system operation and maintenance management business guide and accident handling guidelines.

[0053] The pre-trained smart monitoring tool can learn the basics of the DC system based on the knowledge base data for the first level of training.

[0054] S200: Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes multiple training samples, each training sample includes sample log data and corresponding labels, and the labels include sample fault analysis results.

[0055] Specifically, the training data is log data obtained by data cleaning from the actual operation monitoring data (background data) of the DC system.

[0056] Sample log data 1 is: Background information:

[0057] ①15:59:11: 101 switch SF6 low pressure lockout

[0058] ②15:59:31: 110kVⅠ bus differential protection action

[0059] ③15:59:31: The first time limit of the phase impedance I stage of the 1st and 2nd protection II side of the No. 1 main transformer was actuated

[0060] ④15:59:31: The second time limit of the phase impedance I stage of the No. 1 main transformer No. 1 and No. 2 protection II side is actuated

[0061] ⑤15:59:31: The phase-to-phase impedance stage I three-time limit of the No. 1 main transformer No. 1 and No. 2 protection sets II side was actuated

[0062] ⑥15:59:32: The first time limit of the phase impedance II section of the 1st and 2nd protection sets II side of the No. 1 main transformer was actuated

[0063] ⑦15:59:33: Capacitor No. 2 tripped due to undervoltage

[0064] Tripping circuit breaker: 155, 153, 151, 112, 113, 124, 201, 301, 341

[0065] Undervoltage circuit breaker: 156, 154, 152, 101 (refuse to operate), 381.

[0066] Tag 1 is:

[0067] On-site inspection: Take personal safety protection measures (or wear a gas mask) and stand at the upwind side for inspection, including primary equipment inspection (refusing equipment), secondary equipment inspection (simultaneous), tripped circuit breakers, pressure-loss circuit breakers, and equipment within the protection action range;

[0068] Preliminary judgment of the accident: 110kVⅠbus BC phase-to-phase short circuit fault, 110kVⅠbus differential protection tripped Ⅰbus, 101 circuit breaker SF6 low pressure locked (refused to operate), No. 1 main transformer backup protection action, phase-to-phase impedance Ⅰ stage Ⅰ time limit tripped 113 (tripped), Ⅱ time limit tripped 112 (tripped), Ⅲ time limit tripped 101 (refused to operate), Ⅱ stage Ⅰ time limit tripped 201, 101 (refused to operate), 301;

[0069] Isolation measures: One-time isolation:

[0070] ① Neutral point switching: Close the 1020 and 2020 grounding switches in sequence and check, and open the 2010 and 1010 grounding switches in sequence and check;

[0071] ②Disconnect the undervoltage circuit breaker: 156, 154, 152, 101, 381 and check

[0072] ③Disconnect the air switch of the 101 circuit breaker control power supply, apply for accident unlocking, pull open the 1016 and 1011 isolation switches in turn and check;

[0073] ④ Pull open the 1556, 1551, 1536, 1531, 1516, 1511 isolation switches in sequence and check

[0074] ⑤Disconnect the 110kVⅠ female PT secondary circuit breaker

[0075] ⑥ Pull out the 1901 isolating switch and check

[0076] Secondary Isolation

[0077] ① Exit the No. 1 main transformer cabinet A: 1LP12, 1LP14, 1LP16, 1LP21

[0078] ② Exit the No. 1 main transformer cabinet B: 1LP12, 1LP14, 1LP16, 1LP21

[0079] Report the isolation situation to the dispatcher

[0080] 3. Restore trouble-free equipment operation:

[0081] 1. Close 124 pairs of 110kVⅡ mother charging and check;

[0082] 2. Close circuit breakers 156, 154, and 152 to supply power to the line and check;

[0083] 3. Close the isolation switches 1556, 1552, 1536, 1532, 1516, and 1512 in sequence and check;

[0084] 4. Close circuit breakers 155, 153, and 151 to supply power to the line and check.

[0085] Sample log data 2 is: Background information:

[0086] (1) Position change information: 201, 301, 124, 113, 341 opening

[0087] (2) Protection information: ① 09:17:50: 101 switch SF6 low pressure lockout

[0088] ②09:18:25: The first and second sets of protection of No. 1 main transformer were differentially actuated, and the main body heavy gas was actuated

[0089] ③09:18:26: The first time limit of the phase-to-phase impedance I stage of the 1st and 2nd protection II side of the No. 2 main transformer was actuated

[0090] ④09:18:26: Capacitor No. 2 tripped due to undervoltage.

[0091] Tag 2 is:

[0092] 1. Preliminary assessment of the accident situation:

[0093] There is an AB phase-to-phase short circuit fault inside the oil tank of the 220kV No. 1 main transformer. The protection of No. 1 main transformer trips 201, 101 (refuses to operate), 301, and the SF6 low pressure of 101 circuit breaker is locked (refuses to operate). The backup protection phase-to-phase impedance Section I time limit of No. 2 main transformer trips 124, 113.

[0094] 2. Isolation fault:

[0095] 1. Primary isolation:

[0096] ① Neutral point switching: Close the 1020 and 2020 grounding switches in sequence and check, and open the 2010 and 1010 grounding switches in sequence and check;

[0097] ②Disconnect the undervoltage circuit breaker: 156, 155, 154, 153, 152, 151, 112, 381 and check

[0098] ③Disconnect the air switch of the 101 circuit breaker control power supply, apply for accident unlocking, pull open the 1016 and 1011 isolation switches in turn and check;

[0099] ④ Open the isolation switches 3011, 3016, 3014, 2011, and 2016 in sequence and check

[0100] ⑤Disconnect the secondary circuit breaker of the voltage transformer PT on the 220kV side of the 220kV No. 1 main transformer

[0101] ⑥Disconnect the secondary circuit breaker of the voltage transformer PT on the 110kV side of the 220kV No. 1 main transformer

[0102] 2. Secondary isolation

[0103] ① Exit the No. 1 main transformer cabinet A: 1LP3, 1LP12, 1LP14, 1LP16, 1LP21, 1LP28, 1LP30

[0104] ② Exit the No. 1 main transformer cabinet B: 1LP3, 1LP12, 1LP14, 1LP16, 1LP21, 1LP28, 1LP30 report the isolation situation to the dispatcher

[0105] 3. Restore trouble-free equipment operation:

[0106] 1. Close 124 pairs of 110kVⅡ mother charging and check;

[0107] 2. Close 112 and charge the 110kVⅡ mother, and check;

[0108] 3. Close the 113 circuit breaker and check;

[0109] 4. Close circuit breakers 156, 155, 154, 153, 152, and 151 to energize the lines and check;

[0110] Report the recovery situation to the dispatcher.

[0111] Sample log data 3 is: Background information:

[0112] (1) Transformation information: 162, 161, 160, 159, 158, 157, 102, 124, 113 combined variation

[0113] (2) Protect information:

[0114] 15:52:33 134 switch SF6 low pressure locked, control circuit disconnected

[0115] 15:52:48

[0116] 1) 621ms 110kVBP-2CⅢ bus differential protection action, tripping 113, 157 / 159 / 161

[0117] 2) 851ms 110kVBP-2C bus coupling failure, IV bus differential action, trip 124 / 102, 158, 160 / 162

[0118] (3) Overload and other information: No overload.

[0119] Label 3 is: 1. Preliminary judgment of the accident situation:

[0120] 110kV III bus B phase grounding fault, III bus differential protection action tripped: 113 / 157 / 159 / 161, bus tie 134 circuit breaker SF6 low pressure locked (refuses to operate), 134 failure protection tripped 124 / 158 / 160 / 162 / 102, fault isolation.

[0121] 2. Isolate faults: Perform the following isolation under the dispatch instruction (permission)

[0122] 1. One-time isolation

[0123] (1) Neutral point switching: None;

[0124] (2) Disconnect the undervoltage circuit breaker: None;

[0125] (3) Refuse to operate the circuit breaker: disconnect the control power supply of circuit breaker 134, confirm that there is no pressure on the 110KV III and IV busbars, apply for accident unlocking, and open 1343 and 1344 in turn;

[0126] (4) Open 1616, 1613, 1596 / 1593 / 1573 / 1133 / 1131 in sequence

[0127] (5) Disconnect the secondary circuit breaker of the 110kVⅢ voltage transformer and open 1903

[0128] 2. Secondary isolation:

[0129] (1) Exit 110kV busbar protection: 113, 134 failure (pressure plate number)

[0130] (2) Exit main transformer protection: 113, 134 failure (pressure plate number)

[0131] The quarantine situation has been reported to the dispatcher

[0132] 3. Restoring trouble-free equipment operation: Perform accident recovery under dispatch order

[0133] 1. Close 124 and charge the 110KV IV mother to check if the charging is normal;

[0134] 2. Close 2020 and 1020 in sequence

[0135] 3. Combine 102

[0136] 4. Open 1020 and 2020 in sequence

[0137] 5. Close 162 / 160 / 158 in sequence and check that the current is normal;

[0138] 6. Close 1614 / 1616 / 1594 / 1596 / 1574 / 1576 in sequence

[0139] 7. Close 161 / 159 / 157 in sequence and check that the line flow is normal.

[0140] The recovery situation has been reported to the dispatcher.

[0141] Sample log data 4 is: Background information:

[0142] (1) Transformation information: 253, 251, 212, 101, 301, 342 combined transformation

[0143] (2) Protection information: Started at 16:18:23 (previously 201 switch SF6 was locked due to low gas pressure)

[0144] 220kV#1 main transformer protection (first set, second set) differential, differential quick-break, ratio differential, power frequency variation differential action; #1 main transformer non-electrical body heavy gas action (trip 201, 101, 301, 201 refuses to act)

[0145] 220kV busbar protection (first set, second set) failure protection, I busbar failure protection action (253, 251, 212)

[0146] 35kV#2 capacitor undervoltage trip (trip 342)

[0147] Others: 220kV#1 main transformer overload alarm, station power ATS switching action

[0148] (3) Overload information: 220kV No. 2 main transformer overload

[0149] Label 4 is: 1. Preliminary judgment of the accident situation:

[0150] There is an internal fault in the oil tank of 220kV No.1 main transformer. The differential protection and main body gas protection of 220kV No.1 main transformer are actuated and circuit breakers 201, 101 and 301 are tripped. The SF6 gas pressure of 201 circuit breaker is low and locked out. The failure protection of 201 circuit breaker is actuated. The 220kV busbar protection failure protection and bus I failure protection are actuated and circuit breakers 253, 251 and 212 are tripped. The undervoltage trip of 35kV#2 capacitor protection causes circuit breaker 344 to trip. The station power ATS is actuated and switches to 35kV station power supply No.2.

[0151] 2. Isolate faults: Perform the following isolation under the dispatch instruction

[0152] 1. Neutral point switching: close the 1020 and 2020 neutral point grounding switches in sequence;

[0153] 2. Disconnect the undervoltage circuit breaker: 381;

[0154] 3. Confirm that the 220kV No. 1 main transformer has no power, and open the 3016, 3011, 1016, and 1011 isolating switches in sequence.

[0155] 4. Apply to disconnect the control power supply of the circuit breaker that refuses to operate: disconnect the air switches Ⅰ and Ⅱ of the control power supply of the 201 circuit breaker;

[0156] 5. Apply for accident unlocking and open the 2016 and 2011 isolation switches in sequence;

[0157] 6. Secondary isolation:

[0158] Disconnect the secondary air switches of the voltage transformers on the high and medium voltage sides of the 220kV No. 1 main transformer; remove the 1LP3, 1LP12, 1LP14, 1LP16, 1LP21, 1LP28, and 1LP30 connectors of the 220kV No. 1 main transformer protection A and B cabinets;

[0159] The isolation situation has been reported to the dispatcher.

[0160] 3. Restoring trouble-free equipment operation: Perform accident recovery under dispatch order

[0161] 1. Close 212 pairs of 220kVⅠbuses, and charging is normal; (busbars have no faults, no maintenance work, and no need to put into charging protection)

[0162] 2. Close the 253 and 251 circuit breakers to supply power to the line, and the power supply is normal;

[0163] 3. Open the 2010 and 1020 neutral point grounding switches in sequence;

[0164] 4. Switch the station power ATS to manual mode

[0165] The recovery situation has been reported to the dispatcher.

[0166] Sample log data 5 is: background information or alarm window information:

[0167] (1) Position change information: 201, 301, 124, 113, 341 opening

[0168] (2) Protection information: ① 09:17:50: 101 switch SF6 low pressure lockout

[0169] ②09:18:25: The first and second sets of protection of No. 1 main transformer were differentially actuated, and the main body heavy gas was actuated

[0170] ③09:18:26: The first time limit of the phase-to-phase impedance I stage of the 1st and 2nd protection II side of the No. 2 main transformer was actuated

[0171] ④09:18:26: Capacitor No. 2 tripped due to undervoltage

[0172] (3) Overload: None.

[0173] Tag 5 is:

[0174] 1. Preliminary assessment of the accident situation:

[0175] There is a short circuit between phases AB in the oil tank of the 220kV No. 1 main transformer. The protection of No. 1 main transformer trips 201, 101 (refused to operate), 301, and the SF6 pressure of the 101 circuit breaker is low and locked (refused to operate). The backup protection of the No. 2 main transformer trips 124, 113 due to the phase impedance I stage I time limit.

[0176] 2. Isolation fault:

[0177] 1. Primary isolation:

[0178] ① Neutral point switching: Close the 1020 and 2020 grounding switches in sequence and check, and open the 2010 and 1010 grounding switches in sequence and check;

[0179] ②Disconnect the undervoltage circuit breaker: 156, 155, 154, 153, 152, 151, 112, 381 and check

[0180] ③Disconnect the air switch of the 101 circuit breaker control power supply, apply for accident unlocking, pull open the 1016 and 1011 isolation switches in turn and check;

[0181] ④ Open the isolation switches 3011, 3016, 3014, 2011, and 2016 in sequence and check

[0182] ⑤Disconnect the secondary circuit breaker of the voltage transformer PT on the 220kV side of the 220kV No. 1 main transformer

[0183] ⑥Disconnect the secondary circuit breaker of the voltage transformer PT on the 110kV side of the 220kV No. 1 main transformer

[0184] 2. Secondary isolation

[0185] ① Exit the No. 1 main transformer cabinet A: 1LP3, 1LP12, 1LP14, 1LP16, 1LP21, 1LP28, 1LP30

[0186] ② Exit the No. 1 main transformer cabinet B: 1LP3, 1LP12, 1LP14, 1LP16, 1LP21, 1LP28, 1LP30 report the isolation situation to the dispatcher

[0187] 3. Restore trouble-free equipment operation:

[0188] 1. Close 124 pairs of 110kVⅡ mother charging and check;

[0189] 2. Close 112 and charge the 110kVⅡ mother, and check;

[0190] 3. Close the 113 circuit breaker and check;

[0191] 4. Close circuit breakers 156, 155, 154, 153, 152, and 151 to energize the lines and check;

[0192] Report the recovery situation to the dispatcher.

[0193] Sample log data 6 is: Alarm window information:

[0194] August 16, 15:29

[0195] (1) 158 switch SF6 is locked due to low gas pressure, and the control circuit is disconnected;

[0196] (2) 110kV Longliu I loop phase distance I and II stages of operation;

[0197] (3) 220kV#2 main transformer (set 1 and 2) medium voltage side phase impedance I stage 1, 2, 3 time limit actions;

[0198] (3) The first, second and third time limit actions of the phase-to-phase impedance stage I on the medium voltage side of the 220kV#1 main transformer (the first and second sets).

[0199] Tag 6 is:

[0200] 1. Preliminary assessment of the accident situation:

[0201] There was a phase-to-phase short circuit fault on the AB loop of the 110kV Longliu I circuit, the SF6 gas pressure in phase B of the 158 circuit breaker was low and locked out (the control circuit was broken), the backup protection in the No. 1 and No. 2 main transformers tripped sections 113 and 124, and the backup protection in the No. 2 main transformer tripped sections 134 and 102.

[0202] 2. Isolate faults: Perform the following isolation under the dispatch instruction

[0203] One quarantine:

[0204] 1. Neutral point switching: None;

[0205] 2. Disconnect the undervoltage circuit breaker: 157, 159, 160, 161, 162;

[0206] 3. Apply to disconnect the control power supply of the circuit breaker that refuses to operate: disconnect the control power supply of the circuit breaker 158 and check that the line has no pressure;

[0207] 4. Apply for emergency unlocking and pull open the 1586 and 1584 isolation switches in sequence;

[0208] Secondary isolation: None.

[0209] Report the isolation situation to the dispatcher

[0210] 3. Restoring trouble-free equipment operation: Perform accident recovery under dispatch order

[0211] 1. Close 113 to charge the 110kVⅢ mother, and the charging is normal;

[0212] 2. Close 134 to charge the 110kV IV mother, and the charging is normal;

[0213] 3. Use 124 circuit breaker to close the loop;

[0214] 4. Close the 2020 and 1020 neutral point grounding switches in sequence;

[0215] 5. Close the 102 circuit breaker;

[0216] 6. Open the 1020 and 2020 neutral point grounding switches in sequence;

[0217] 7. Close the 302 circuit breaker to charge the 35kVⅡ mother, and the charging is normal;

[0218] 8. Charge the lines 157, 159, 160, 161, and 162 and check that the current is normal;

[0219] The recovery situation has been reported to the dispatcher.

[0220] Sample log data 7 is: Alarm window information:

[0221] (1) Transformation information: 161, 134, 159, 157, 101, 155, 153, 112, 151 combined transformation

[0222] (2) Protect information:

[0223] 15:41:54 113 switch SF6 low pressure locked, control circuit disconnected

[0224] 15:43:04

[0225] 1) 744ms 110kVBP-2CⅢ bus differential protection action, trip 134 / 161 / 159 / 157

[0226] 2) 964ms 110kVBP-2C segment failure action, trip 101 / 155 / 153 / 112 / 151

[0227] (3) Overload and other information: The high and medium voltage side of the 220kV No. 2 main transformer is overloaded.

[0228] Tag 7 is:

[0229] 1. Preliminary assessment of the accident situation:

[0230] 110kV III bus B phase grounding fault, III bus differential protection action trips: 134, 157, 159, 161, section 113 circuit breaker SF6 low pressure locked (refuses to operate), 113 failure protection trips 101 / 112 / 155 / 151, fault isolation.

[0231] 2. Isolate faults: Perform the following isolation under the scheduling instruction (permission)

[0232] 1. One-time isolation

[0233] (1) Neutral point switching: 2020 / 1020;

[0234] (2) Disconnect the undervoltage circuit breaker: None;

[0235] (3) Refusal to operate the circuit breaker: disconnect the control power supply of the 113 circuit breaker, confirm that there is no pressure on 110KVⅠ and Ⅲ, apply for accident unlocking and open 1133 / 1131 in sequence;

[0236] (4) Open 1343 / 1344 / 1616 / 1613 / 1596 / 1593 / 1576 / 1573 in sequence

[0237] (5) Disconnect the secondary circuit breaker of the 110kVⅢ voltage transformer and open 1903

[0238] 2. Secondary isolation:

[0239] (1) Exit 110kV busbar protection: 113, 134 failure (pressure plate number)

[0240] (2) Exit main transformer protection: 113, 134 failure (pressure plate number)

[0241] The quarantine situation has been reported to the dispatcher

[0242] 3. Restoring trouble-free equipment operation: Perform accident recovery under dispatch order

[0243] 1. Combine 112 to charge 110KVⅠ mother;

[0244] 2. Combine 101,

[0245] 3. Open 1020 / 2020

[0246] 4. Combine 155 / 153 / 151 and check that the current is normal;

[0247] 5. Close 1614 / 1616 / 1594 / 1596 / 1574 / 1576 in sequence

[0248] 6. Close 161 / 159 / 157 in sequence and check that the line flow is normal.

[0249] The recovery situation has been reported to the dispatcher.

[0250] Of course, it should be noted that the above-mentioned labels 1 to 7 are only exemplary descriptions. The labels of the training samples may also be in other text description forms, and this application does not limit this.

[0251] S300: Perform the third-level training on the intelligent monitoring tool through human-computer interaction with the intelligent monitoring tool.

[0252] Specifically, users can log in to the intelligent monitoring system of the DC system and conduct human-computer dialogue interaction with the intelligent monitoring tool. For example, users ask questions or provide abnormal log data, and the intelligent monitoring tool provides analysis results. Users comment on the analysis results, such as confirming that the analysis results are correct or correcting the analysis results to correct or supplement the analysis results of the intelligent monitoring tool on the abnormal log data, thereby performing third-level training on the intelligent monitoring tool through dialogue interaction.

[0253] S400: Obtain a trained intelligent monitoring tool according to the first-layer training, the second-layer training, and the third-layer training.

[0254] Specifically, it should be noted that during the initial training, the first layer training and the second layer training are performed before the third layer training. If the trained intelligent monitoring tool is to be retrained, any one or more of the first layer training, the second layer training and the third layer training can be performed during the retraining.

[0255] S500: Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool.

[0256] Specifically, the abnormal log data of the DC system is obtained from the dispatching monitoring system of the DC system. The dispatching monitoring system is the original monitoring system of the DC system, which is a rough monitoring system of the DC system and generates log data. The intelligent monitoring system of the DC system of this embodiment further analyzes the faults of the DC system in detail based on the log data.

[0257] S600: Use trained intelligent monitoring tools to perform fault analysis on DC systems based on abnormal log data.

[0258] Specifically, the fault analysis includes fault cause analysis and / or fault solution matching, etc.

[0259] S700: Outputting the fault analysis result to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0260] Specifically, the dispatching and monitoring system can send abnormal information to the information sending and receiving tool, wherein the abnormal information carries abnormal log data. The information sending and receiving tool inputs the abnormal information to the trained intelligent monitoring tool (AI tool) through the AI ​​dispatching interface of the intelligent monitoring system of the DC system. The trained intelligent monitoring tool analyzes the cause of the fault according to the abnormal information, gives scientific solution suggestions, and sends the obtained fault analysis results to the information sending and receiving tool. The information sending and receiving tool sends the fault analysis results to the user.

[0261] The information sending and receiving tool may be, for example, a text message sending and receiving tool or a message sending and receiving tool.

[0262] The user who receives the fault analysis result may be the person currently on duty.

[0263] The intelligent monitoring system of the DC system can obtain the communication information of the current on-duty personnel according to the DC system's shift schedule, and send the fault analysis result to the current on-duty personnel according to the communication information. For example, the fault analysis result is sent to the current on-duty personnel by email, text message, system message, etc., which are not limited to these.

[0264] In addition, this embodiment uses the intelligent monitoring system of the DC system to further analyze the abnormal log data. Compared with the abnormal log data, the obtained analysis results are more intuitive, have lower requirements on the professionalism of users, and can be convenient for more users to view.

[0265] This embodiment improves the intelligence level of monitoring by introducing artificial intelligence technology, realizes efficient and accurate data processing and fault prediction, and thus improves the operational reliability and safety of the DC system.

[0266] This embodiment uses different methods to perform multi-layer training on the intelligent monitoring tool, so that the intelligent monitoring tool can accurately identify complex fault modes, significantly improving the precision and accuracy of DC system monitoring. This embodiment performs real-time fault analysis, which can quickly identify abnormal situations, issue warnings in a timely manner, and shorten the fault response time. This embodiment effectively prevents the occurrence of potential faults and improves the operational reliability of the DC system through intelligent warning and decision support. This embodiment can convert fault logs into more user-recognizable fault analysis results, reducing the requirements for user expertise and having a wide range of applications.

[0267] In one embodiment, in step S300, the third-level training of the intelligent monitoring tool is performed by human-computer interaction with the intelligent monitoring tool, including:

[0268] Respond to the user's human-computer dialogue start operation and display the human-computer dialogue interface;

[0269] Receive and display user input data through the human-computer dialogue interface, and input the input data to the intelligent monitoring tool;

[0270] Receive response data output by the intelligent monitoring tool based on input data, and display the response data to the user through a human-computer dialogue interface;

[0271] If feedback data input by the user according to the answer data is received, or self-answer data input by the user is received, the feedback data or self-answer data is displayed through the human-computer dialogue interface, wherein the feedback data is used to indicate that the answer data is correct or the feedback data is the correction data made by the user for the answer data, and the self-answer data is input by the user when the intelligent monitoring tool does not respond to the input data;

[0272] If correction data or self-answer data exists, the correction data or self-answer data is used to train the intelligent monitoring tool or for the intelligent monitoring tool to call.

[0273] Specifically, the intelligent monitoring system has a visual interface. Users can log in to the intelligent monitoring system and start the human-computer dialogue in the intelligent monitoring system. The human-computer dialogue start operation is equivalent to issuing a start instruction to the intelligent monitoring system. When the user starts the human-computer dialogue, he first enters the intelligent monitoring homepage, and then clicks on the "Dialogue Option" on the intelligent monitoring homepage to enter the human-computer dialogue interface or creates a new dialogue on the intelligent monitoring homepage to enter the human-computer dialogue interface.

[0274] Among them, the smart monitoring homepage has multiple options to choose from, for example, an option for creating a "new conversation", a history list option for viewing "historical conversations", setting options, search options, etc. are not limited to these.

[0275] The human-computer dialogue interface can be displayed on the same page with various options. For example, various options are displayed on the left side of the smart monitoring homepage, and the human-computer dialogue interface is displayed on the right side.

[0276] In the human-computer dialogue interface, the user can input various inputs, for example, the input data is abnormal log data; the input data is equivalent to the user's question data.

[0277] In addition, the input data can be voice data or text data. If the input data is voice data, the intelligent monitoring system can also convert the voice data into text data and display it on the human-computer dialogue interface.

[0278] The intelligent monitoring system inputs textual input data to the intelligent monitoring tool, which responds to the input data based on the learned knowledge and outputs response data. The response data is the fault analysis result output by the intelligent monitoring tool.

[0279] The response data is output data given by the intelligent monitoring tool based on the input data, and specifically may be the cause of the fault and / or solution or resolution strategy given by the intelligent monitoring tool.

[0280] The intelligent monitoring system receives the response data from the intelligent monitoring tool and displays the response data to the user.

[0281] The user can review whether the response data is accurate. If it is accurate, the user can give feedback data indicating that the response data is correct. If the user believes that the response data is inaccurate or wrong, the user can give correction data, which can be a supplementary explanation of the response data or a modification of the response data. If the intelligent monitoring tool is unable to make a corresponding response to the input data, the user can provide self-answer data.

[0282] Correction data is the correct fault cause and / or solution given by the user based on the input data.

[0283] If there is correction data or self-answer data, the correction data or self-answer data is used to train the intelligent monitoring tool or is used by the intelligent monitoring tool. That is, the correction data or self-answer data is used to perform the third-level training on the intelligent monitoring tool.

[0284] This embodiment can test or verify the fault analysis capability of the intelligent monitoring tool for the DC system based on abnormal log data through human-computer dialogue. When the response data given by the intelligent monitoring tool is incomplete or erroneous, the user can supplement or correct it to guide or train the intelligent monitoring tool in a positive direction, so that the fault analysis capability of the intelligent monitoring tool is more robust and accurate. This embodiment enables the intelligent monitoring tool to continuously adapt to new operating conditions and fault modes through self-learning and optimization functions, thereby improving the level of intelligence.

[0285] In one embodiment, using the correction data or the self-answer data to train the intelligent monitoring tool or for the intelligent monitoring tool to call includes:

[0286] Inputting the input data and the corresponding correction data or self-answer data to the intelligent monitoring tool to retrain the intelligent monitoring tool;

[0287] and / or,

[0288] If an archiving instruction from the user is received, the conversation content of the human-computer dialogue interface will be archived, and the obtained archived data will be stored in the data center for reference and call when the intelligent monitoring tool monitors the DC system.

[0289] Specifically, the corrected data or self-answered data is used as a label, and the input data is used as sample log data. The input data and the corrected data are combined into a training sample, or the input data and the self-answered data are combined into a training sample and input into the intelligent monitoring tool to retrain the intelligent monitoring tool.

[0290] and / or,

[0291] On the homepage of smart monitoring, there is a history list option for viewing "historical conversations". Through the history list option, users can select any target history conversation option or current conversation option. Each conversation option has a variety of operational options, such as one or more of pinning, renaming, copying, archiving, sharing, deleting, adding tags, etc.

[0292] By clicking the "Archive" option, the user is sending an archiving instruction to the intelligent monitoring system, instructing the intelligent monitoring system to archive the corresponding conversation and store it in the data center for reference and call by the intelligent monitoring tool when monitoring the DC system.

[0293] This embodiment uses an AI dialog box question format to interact with the intelligent monitoring tool, guides the intelligent monitoring tool to answer questions, and corrects the intelligent monitoring tool when the answer is wrong, composes new training samples to train the intelligent monitoring tool, or archives the conversation chat and stores it in the data center for the intelligent monitoring tool to relearn and call, corrects the errors or inaccuracies of the intelligent monitoring tool, and improves the accuracy of the intelligent monitoring tool's fault analysis.

[0294] In one embodiment, the DC system monitoring method further includes:

[0295] In response to the user's login operation, enter and display the intelligent monitoring homepage, wherein the intelligent monitoring homepage is provided with a dialogue option list, and the dialogue option list includes historical dialogue options and current dialogue options;

[0296] In response to a target operation of a user on any target dialogue option selected in a dialogue option list, properties of the target dialogue option are changed or the dialogue option list is changed, wherein the target operation is any one of pinning, renaming, copying, archiving, sharing, deleting, and adding tags.

[0297] Specifically, each dialogue option includes all dialogue contents displayed on a human-computer dialogue interface. The dialogue contents can be displayed by clicking on the dialogue option or expanding the dialogue option.

[0298] This embodiment can manage historical conversations and current conversations in a variety of ways, and is highly practical.

[0299] In one embodiment, step S100 of inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool includes:

[0300] Respond to the user's upload interface entry operation, enter and display the data upload interface;

[0301] In response to a user's data upload operation on the data upload interface, the knowledge base data uploaded by the user is input into a pre-trained intelligent monitoring tool; or, in response to a user's data query operation on the data upload interface, the query results are displayed, and the knowledge base data queried and selected by the user from the query results is input into the pre-trained intelligent monitoring tool.

[0302] Specifically, the intelligent monitoring system has a visual interface. The user can log in to the intelligent monitoring system, enter the upload interface in the intelligent monitoring system, and enter and display the data upload interface; the upload interface entry operation is equivalent to sending an interface jump entry instruction to the intelligent monitoring system. When the user enters the upload interface, he first enters the intelligent monitoring homepage, and then clicks the "data upload option" on the intelligent monitoring homepage to enter the data upload interface. Alternatively, a "workspace" option is set on the intelligent monitoring homepage. After the user clicks the "workspace" option, he enters the workspace interface. The workspace interface has one or more options such as "model", "prompt word", "document", "tool", "function", etc. The user clicks the "document" option to enter the data upload interface.

[0303] On the data upload interface, the user clicks the "+" button or the "+" option to select the documents to be uploaded locally. The intelligent monitoring system will display the selected documents to be uploaded on the data upload interface. Next to each document to be uploaded, there will be an icon indicating "delete" and / or an icon indicating "edit".

[0304] The user can delete any one or more documents to be uploaded by using the icon indicating "delete", or change the properties of the documents to be uploaded by using the icon indicating "edit", for example, renaming the documents to be uploaded, setting category labels for the documents to be uploaded, etc. This application does not impose any restrictions on this.

[0305] There is also an "Upload" button or an "OK" button on the data upload interface. The user clicks the "Upload" button or the "OK" button to input the document to be uploaded as knowledge base data into the pre-trained intelligent monitoring tool.

[0306] In addition, a search box and a search button are provided on the data upload interface. Users can perform data query operations on the data upload interface. Specifically, users can enter search text in the search box and click the search button to send a search instruction to the intelligent monitoring system. The intelligent monitoring system queries the specified document in the database according to the search instruction and displays the query results. Users can select the target document from the query results. The intelligent monitoring system inputs the target document selected by the user as knowledge base data to the pre-trained intelligent monitoring tool.

[0307] Among them, the intelligent monitoring system will store various documents uploaded historically, waiting for users to call them at any time.

[0308] In addition, the documents corresponding to the knowledge base data can be stored in the knowledge base or database of the intelligent monitoring system, and the index mode of the knowledge base can be set, such as setting a mixed mode retrieval (vector retrieval + full-text retrieval), etc. This application does not impose any restrictions on this.

[0309] The documents corresponding to the knowledge base data can be in various forms such as word, Excel, xml, etc., and this application does not impose any restrictions on this.

[0310] This embodiment can facilitate users to upload new knowledge base data or call existing knowledge base data through a visual interface to conduct targeted training for the intelligent monitoring tool. Moreover, the knowledge base data can be updated at any time, and the training of the intelligent monitoring tool can be a long-term and continuous improvement process, which increases the reliability of the intelligent monitoring tool for fault analysis.

[0311] In one embodiment, one or more options such as "Settings", "Archived Conversations", "Administrator Panel", "Logout" or "Exit" are also provided on the smart monitoring homepage. The user name of the current online user can also be displayed on the smart monitoring homepage.

[0312] The user clicks "Administrator Panel" to enter the administrator panel interface, which displays the number and information of all users, such as at least one of the names, email addresses, last online time, creation time, etc. of administrators and ordinary users.

[0313] In one embodiment, the training data includes at least one of sample log data generated by the dispatching and monitoring system of the DC system when an abnormal alarm occurs in the measurement and control protection device of the DC system, sample log data corresponding to a failure of the energy storage power supply, sample log data corresponding to a failure of the air conditioner in the control cabinet, sample log data corresponding to the failure of the switch spring to store energy, sample log data corresponding to a control loop disconnection, sample log data corresponding to a communication interruption, sample log data corresponding to a fire alarm, sample log data corresponding to an abnormal alarm of a small current grounding line selection device, sample log data corresponding to a failure of the DC system lightning arrester, and sample log data corresponding to a grounding failure of the DC system.

[0314] In one embodiment, if the training data includes sample log data generated by the dispatching monitoring system of the corresponding DC system when a measurement and control protection device timing abnormality alarm occurs in the DC system, the label of the measurement and control protection device timing abnormality alarm includes a general solution to the measurement and control protection device timing abnormality alarm and / or a solution to the measurement and control protection device timing abnormality alarm in different timing modes, wherein the solution to the measurement and control protection device timing abnormality alarm in different timing modes includes at least one of a solution to broadcast message timing failure, a solution to pulse timing failure, and a solution to IRIG-B code timing failure;

[0315] If the training data includes sample log data corresponding to an energy storage power supply failure in the DC system, the label of the energy storage power supply failure includes the cause of the circuit breaker energy storage power supply failure and / or the solution to the circuit breaker energy storage power supply failure, wherein the cause of the circuit breaker energy storage power supply failure includes at least one of an intelligent controller failure, a pressure loss release failure, an energy storage motor failure, a spring mechanism problem, and a control circuit problem;

[0316] If the training data includes sample log data corresponding to a failure of an air conditioner in a control cabinet in a DC system, the label of the air conditioner failure in the control cabinet includes the cause of the failure and / or the solution to the failure, wherein the cause of the failure includes at least one of a power supply problem and a sensor failure.

[0317] If the training data includes sample log data corresponding to the DC system when the switch spring does not store energy, the label when the switch spring does not store energy includes a solution for the switch spring not storing energy;

[0318] If the training data includes sample log data corresponding to a control loop disconnection in a DC system, the label of the control loop disconnection includes the fault cause causing the control loop disconnection and / or the solution to the control loop disconnection, wherein the fault cause causing the control loop disconnection includes at least one of a control loop power supply or air switch failure, a TWJ or HWJ relay and a node failure, an automation system or signal loop failure, a loop wiring looseness or a terminal failure, a switch mechanism opening and closing coil and an auxiliary contact failure, and various locking contact failures that may exist in the switch control loop;

[0319] If the training data includes sample log data corresponding to when a communication interruption occurs in the DC system, the label of the communication interruption includes a solution that causes the communication interruption;

[0320] If the training data includes sample log data corresponding to a fire alarm occurring in the DC system, the label of the fire alarm includes a solution to the fire alarm;

[0321] If the training data includes sample log data corresponding to an abnormal alarm of a small current grounding line selection device in a DC system, the label of the abnormal alarm of the small current grounding line selection device includes a fault cause causing the abnormal alarm of the small current grounding line selection device and / or a solution to the abnormal alarm of the small current grounding line selection device;

[0322] If the training data includes sample log data corresponding to a DC system lightning arrester failure in the DC system, the label of the DC system grounding fault includes the fault cause of the DC system lightning arrester failure and / or the solution to the DC system lightning arrester failure, wherein the fault cause of the DC system lightning arrester failure includes at least one of power supply voltage exceeding the rated voltage, long-term operation thermal damage, power supply short circuit or overload, excessive humidity or water ingress, and installation error;

[0323] If the training data includes sample log data corresponding to when a DC system grounding fault occurs in the DC system, the label of the DC system grounding fault includes a solution to the DC system grounding fault.

[0324] Specifically, A. abnormal timing alarm of the measurement and control protection device, that is, abnormal timing alarm of the measurement and control protection device of the equipment in the DC system;

[0325] The solutions or processing methods for abnormal alarms of the measurement and control protection device are as follows:

[0326] (1) Check the system log to see if there are any system failures or other abnormalities;

[0327] (2) Check the network connection to ensure that the network is unobstructed and the disk space is sufficient;

[0328] (3) Check the clock generator. If it is found to be faulty, replace it with a new one.

[0329] The solutions or processing methods for abnormal timing alarms of measurement, control and protection devices using different timing methods are as follows:

[0330] (1) Handling broadcast message timing failure:

[0331] ① The broadcast message synchronization method of the measurement and control device mainly uses the message synchronization format agreed in the communication protocol to synchronize the time. If the communication of the measurement and control device is normal, after receiving the synchronization message, it will process it according to the communication protocol and correct its own time to achieve the purpose of synchronization. If the communication is abnormal, the broadcast message synchronization will fail.

[0332] ② When the communication mode is RS-485 or field bus, check whether the communication cable has poor contact or open circuit. If so, replace the communication cable or make it contact reliably. If there is no problem with the cable, check whether the communication parameters of the measurement and control device are correct. If they are correct, the problem lies in the communication plug-in of the measurement and control device, which needs to be replaced.

[0333] ③When the communication mode is network, connect the network cable connected to the measurement and control device on the switch to another network port with normal indicator light. If the communication is restored, it is a problem with the switch port, otherwise it is a problem with the device network card.

[0334] (2) Processing of pulse timing failure:

[0335] ① Ensure that the timing method is selected correctly.

[0336] There are two common pulse timing modes: split pulse and second pulse. The measurement and control device accepts split pulse timing. When connecting the timing pulse, be careful not to connect it to the second pulse by mistake. Similarly, the second pulse timing cannot be connected to the component pulse by mistake.

[0337] ② Determine whether the timing node is active or passive.

[0338] Whether it is pulse-by-pulse time synchronization or pulse-by-second time synchronization, either the empty node method or the active contact method can be adopted. The active contact voltage must be negotiated and coordinated with the manufacturers to determine whether to choose DC24V or DC220V, so as to ensure the accuracy of time synchronization.

[0339] ③The cables of the timing nodes must not be connected incorrectly.

[0340] A measurement and control device can support multiple synchronization modes. The nodes of each synchronization mode are different. Be careful not to make mistakes when wiring. In addition, the "+" terminal of the active synchronization cannot be connected in reverse.

[0341] ④The timing method of the measurement and control device must be selected correctly.

[0342] Since the measurement and control device supports multiple timing modes, there is a bit code switch inside the device to select whether it is 5~24V active timing mode or RS-485 timing mode.

[0343] (3) Processing of IRIG-B code synchronization failure:

[0344] ①The cables of the timing nodes must not be connected incorrectly.

[0345] There are "+" wiring differences when synchronizing the IRIG-B code, so make sure you do not connect them incorrectly.

[0346] ②The timing method of the measurement and control device must be selected correctly.

[0347] There is a bit code switch inside the measurement and control device to select the IRIG-B code timing mode.

[0348] B. Energy storage power supply failure means that the energy storage power supply of the equipment in the DC system fails;

[0349] Possible causes of circuit breaker energy storage power failure:

[0350] (1) Intelligent controller failure: When an intelligent controller fails, it may be possible to close the circuit manually but not electrically, and the three-stage protection function and other protection functions may fail. This failure is usually caused by burning due to excessive voltage. In actual operation, the voltage may exceed the rated working voltage (such as 400V), especially when the power consumption decreases. The transformer without voltage regulation may cause the voltage to reach 420V or above, thereby burning the intelligent controller.

[0351] (2) Failure of undervoltage release: The circuit breaker trips inexplicably without a short circuit or grounding. This is usually due to a failure of the undervoltage release or controller. The failure of the undervoltage release is usually caused by a burnt power module. The power module may fail if it is energized for a long time.

[0352] (3) Energy storage motor failure: The energy storage motor is a key component that provides power to store energy in the spring mechanism. If the motor is damaged or the power supply is insufficient, it will directly affect the energy storage process.

[0353] (4) Spring mechanism problems: Failures in the spring mechanism itself, such as spring damage or deformation, can also affect the energy storage effect. In addition, problems with the connection between the spring mechanism and the motor can also lead to energy storage failure.

[0354] (5) Control loop problems: Faults in the control loop, such as incorrect wiring, poor contact, or damage to control components, will affect the transmission and execution of energy storage instructions.

[0355] The solutions or treatment methods for circuit breaker energy storage power supply failure are as follows:

[0356] (1) Cut off the power supply: First, ensure safety and cut off the power supply of the circuit breaker to prevent accidents during maintenance.

[0357] (2) Check the power supply voltage: Use a voltmeter or multimeter to check whether the power supply voltage meets the voltage standard required by the energy storage device. If the voltage is insufficient, the power supply may need to be adjusted or replaced.

[0358] (3) Check the energy storage device: Check whether the energy storage device (such as the spring device) is intact and has no mechanical damage or wear. If damage is found, the energy storage device may need to be replaced or repaired.

[0359] (4) Check the control circuit: Ensure that the wiring of the control circuit is firm and not loose or short-circuited. Use an insulation tester to test the insulation resistance of each section of the line to ensure that it meets the standard requirements.

[0360] (5) Check the motor and relay: If the circuit breaker relies on the motor to store energy, check whether the motor is running normally and there is no abnormal sound or vibration. At the same time, check whether the energy storage relay is working correctly and replace or repair it if necessary.

[0361] (6) Restart and test: After completing the above inspections and necessary repairs or replacements, restart the circuit breaker to see if it can store energy normally. If the problem persists, further inspection of the control logic or other related components may be required.

[0362] C. Failure of air conditioner in control cabinet means that the equipment in DC system has air conditioner failure in control cabinet;

[0363] Analysis of the causes of the air conditioning failure in the control cabinet:

[0364] (1) Power supply problem: If there is a problem with the power supply, the air conditioner will not work properly and abnormal conditions will occur.

[0365] (2) Sensor failure: The sensor is an important component of the air conditioner of the control cabinet. Once the sensor fails, it will cause abnormal temperature.

[0366] (3) Fault in the air conditioner itself: The air conditioner itself may also have faults, resulting in the inability to control the temperature normally.

[0367] The solutions or treatment methods for the failure of the air conditioner in the control cabinet are as follows:

[0368] (1) Power on and restart: If the air conditioner malfunctions, you can try powering on and restarting the device to see if the problem can be solved.

[0369] (2) Replace the sensor: If there is a problem with the sensor, it is necessary to replace the sensor in time to ensure normal temperature control.

[0370] (3) Replace the air conditioner itself: If there is a problem with the air conditioner itself and it cannot be repaired, it needs to be replaced in time to ensure the normal operation of the entire equipment.

[0371] (4) Check the power supply voltage: The working voltage of the air conditioner is single-phase AC220V. If any abnormal situation occurs, it is necessary to check whether the power supply voltage meets the specifications.

[0372] D. The switch spring has not stored energy, that is, the switch spring of the equipment in the DC system has not stored energy;

[0373] The solution or handling process for the circuit breaker spring failure to store energy is as follows:

[0374] (1) Preliminary fault diagnosis

[0375] Observe the circuit breaker status indicator lights for clear indication that the spring is not charged.

[0376] Check the control circuit to see if there are any abnormal signals or alarms.

[0377] (2) Check the energy storage power supply

[0378] Confirm whether the energy storage power supply is supplied normally and check whether the power line is broken or short-circuited.

[0379] Measure the supply voltage to ensure it is within the specified range.

[0380] (3) Check the spring components

[0381] Carefully open the casing of the circuit breaker and check whether the spring is deformed, broken or fallen off.

[0382] Check the spring connections to make sure they are secure and not loose.

[0383] (4) Inspection of mechanical transmission components

[0384] Check the mechanical transmission parts related to the spring, such as connecting rods, gears, etc., to see if there is any binding, wear or damage.

[0385] Check the lubrication condition of the transmission parts and add appropriate amount of lubricating oil if necessary.

[0386] (5) Control circuit inspection

[0387] Check the electrical circuit that controls the spring energy storage, including relays, contactors, circuit breaker auxiliary contacts, etc.

[0388] Check whether the relevant control components are working normally and whether there is any damage or poor contact.

[0389] (6) Testing and repair

[0390] After completing the above inspections and possible repairs, perform a manual energy storage test to observe the energy storage of the spring.

[0391] If manual energy storage is normal, perform the electric energy storage test to ensure that the fault has been eliminated.

[0392] (7) Resume operation

[0393] After confirming that the fault is completely eliminated, restore the circuit breaker to normal operation.

[0394] Closely observe the status of the circuit breaker during operation to ensure its stable and reliable operation.

[0395] E. Control circuit disconnection means that the control circuit of the equipment in the DC system is disconnected;

[0396] The disconnection signal of the switch control circuit is generally composed of the normally closed contact of the trip relay (TWJ) and the normally closed contact of the closing relay (HWJ) in series. When the normally closed contacts of TWJ and HWJ are closed, the positive power supply of the signal circuit will pass through the normally closed contacts of TWJ and HWJ to enter the corresponding measurement and control unit, and send out the "control circuit disconnection" signal.

[0397] The reasons for the control loop disconnection signal are generally:

[0398] (1) Fault in the control circuit power supply or its air switch

[0399] (2) TWJ or HWJ relay and its node failure

[0400] (3) Automation system or signal circuit failure

[0401] (4) Loose circuit wiring or terminal failure

[0402] (5) Failure of the switch mechanism's opening and closing coil and its auxiliary contacts

[0403] (6) Various possible locking contact faults in the switch control circuit

[0404] (7) Others

[0405] The solution or processing steps for the control loop disconnection fault are as follows:

[0406] (1) Confirm that the primary equipment is in cold standby or maintenance status, and narrow the search scope of the control circuit disconnection fault based on the fault message, indicator light, pressure plate, set value, control word, etc. of the protection device. Check the background automation system signal and narrow the search scope of the fault point based on the status of the secondary equipment. Then determine the fault of the control circuit based on the input quantity of the measurement and control device and the voltage of the relevant terminals of the measurement signal circuit.

[0407] (2) Find the fault range: When the switch control circuit is disconnected, the switch control circuit outlet voltage is abnormal. By measuring the control circuit outlet terminal voltage, the fault point search range can be narrowed down. Mainly measure the protection screen terminal block and the switch mechanism box terminal block.

[0408] (3) Check common abnormalities. Common abnormal points in the control loop are:

[0409] Control circuit power circuit breaker failure:

[0410] ① Check whether the circuit breaker of the control circuit power supply is missing or tripped;

[0411] ② Check whether there are obvious signs of burning;

[0412] ③ When the circuit breaker is in normal working condition, use a multimeter to measure whether the voltage at the upper and lower ends is normal to determine whether the circuit breaker is faulty.

[0413] Switch control switching handle failure:

[0414] For switches of 110kV and above in operation, the control handle of the mechanism box should be in the remote position, otherwise it may cause the control circuit to break.

[0415] Switch mechanism energy storage power supply circuit breaker failure:

[0416] ①Whether the energy storage power supply circuit breaker is missing or tripped;

[0417] ② Check whether there are obvious signs of burning;

[0418] ③ When the circuit breaker is in normal working condition, use a multimeter to measure whether the voltage at the upper and lower ends is normal to determine whether the circuit breaker is faulty.

[0419] (4) If no common abnormalities are found, it is necessary to search from the power supply side of the switch control circuit backwards according to the site and the drawings. Check whether the drawings are consistent and measure whether the voltage of the relevant terminals is normal or loose.

[0420] (5) After finding the fault, carry out targeted fault elimination. After eliminating the fault, it is necessary to confirm that the switch opening and closing are normal and there are no abnormal signals.

[0421] F. Communication interruption means that the communication of the equipment in the DC system is interrupted;

[0422] The solutions or treatment methods for substation communication interruption problems are as follows:

[0423] (1) Preliminary inspection

[0424] Check whether the power supply of the communication equipment is normal, including whether the power cord is firmly connected and whether the power indicator light is on.

[0425] Check the communication lines, including optical fibers, network cables, etc., to see if they are damaged, disconnected, or loose.

[0426] Check the hardware status of the communication equipment, such as whether the network card, interface, etc. have abnormal indicators or error messages.

[0427] (2) Device restart

[0428] Try restarting related communication devices, such as switches, routers, communication management machines, etc. Sometimes the device may have a temporary failure, and restarting it can solve the problem.

[0429] When restarting devices, follow the correct order: restart the terminal device first, then restart the intermediate device, and finally restart the core device.

[0430] (3) Software configuration check

[0431] Check the configuration files of the communication device, including whether the IP address, subnet mask, gateway, etc. are set correctly.

[0432] Review the configuration of firewalls and access control lists to ensure that necessary communication flows are not blocked.

[0433] Check whether the configuration of the communication protocol, such as Modbus, IEC 61850, etc., matches that of the peer device.

[0434] (4) Troubleshoot external interference

[0435] Check whether there are new sources of electromagnetic interference around the substation, such as the startup of large electrical equipment, the construction of wireless communication base stations, etc.

[0436] For devices that use wireless communication, check the signal strength and quality, and whether there is any signal obstruction or interference.

[0437] (5) Contact superior departments and manufacturers

[0438] If the problem cannot be solved after the above steps, report the communication interruption to the superior dispatch department in a timely manner and take corresponding measures according to the emergency plan.

[0439] Contact the manufacturer's technical support staff of the communication equipment, provide detailed fault information, and seek professional help and guidance.

[0440] (6) Data backup and recovery

[0441] When dealing with communication interruption issues, be sure to back up important data to prevent data loss.

[0442] If possible, try restoring a previous backup configuration to see if communication can be restored.

[0443] G. Fire alarm

[0444] The solutions or handling methods for substation fire alarm are as follows:

[0445] (1) When a fire alarm sounds, on-site personnel should promptly and appropriately report the actual situation. If a fire really occurs, determine the scale and nature of the fire and immediately press the fire alarm button.

[0446] At the same time, the fire situation is reported to the on-duty person in charge of the patrol and maintenance center through the internal communication system (such as telephone, intercom, etc.), including key information such as the location of the fire, the size of the fire, and the burning materials.

[0447] (2) Initial firefighting

[0448] While waiting for the fire brigade to arrive, you should attempt to carry out initial firefighting:

[0449] If it is a small fire that has just started and the on-site personnel are capable of handling it, they can use fire extinguishers, fire extinguishing sand and other fire-fighting equipment available nearby to put out the fire.

[0450] However, during the firefighting process, be sure to ensure your own safety and avoid acting blindly when the fire is out of control.

[0451] (3) Emergency power off

[0452] The person in charge on duty should quickly arrange for personnel to cut off the power supply to the fire area and related equipment to prevent further expansion of the electrical accident.

[0453] Power-off operations should be carried out strictly in accordance with operating procedures to ensure the accuracy and safety of the operation.

[0454] (4) Organizing evacuation

[0455] If the fire threatens people's lives, evacuation should be organized immediately.

[0456] During the evacuation process, you must remain calm, evacuate in an orderly manner according to the predetermined evacuation route, and avoid crowding and trampling.

[0457] Ensure that evacuation routes are unobstructed and close doors, windows and equipment that may affect evacuation.

[0458] (5) Fire brigade response

[0459] Arrange special personnel to meet the fire brigade at the entrance of the substation and provide them with accurate fire information and guidance.

[0460] Assist the fire brigade to understand the layout and equipment of the substation so that they can quickly launch fire-fighting operations.

[0461] (6) On-site cooperation

[0462] Substation staff should actively cooperate with the fire brigade in fire-fighting work while ensuring their own safety.

[0463] Provide necessary technical support and material assistance, such as the location of fire water sources and how to use fire-fighting facilities.

[0464] (7) Post-fire treatment

[0465] After the fire is extinguished, the fire scene must be protected and wait for relevant departments to investigate and handle the matter.

[0466] Assess and repair damaged equipment and facilities to restore normal operation of the substation as soon as possible.

[0467] Conduct in-depth investigation and analysis of the causes of the fire, summarize experience and lessons, and improve fire emergency plans and measures.

[0468] H. Small current grounding line selection device abnormal alarm: the equipment in the DC system has a small current grounding line selection device abnormal alarm;

[0469] Analysis of the causes of abnormal alarms in the small current grounding line selection device:

[0470] (1) Abnormal ground resistance

[0471] In a low-current grounding system, grounding resistance is an important parameter, and its value directly affects the distribution of grounding current and ground potential. If the grounding resistance of the system is too small, it will cause the low-current grounding line selection device to alarm. At this time, it is necessary to inspect and maintain the system to check whether there is a missing grounding resistance or a poor connection, and perform repairs in a timely manner.

[0472] (2) External interference

[0473] The low-current grounding line selection device may also be subject to external interference during operation. For example, electromagnetic interference caused by high-voltage cables nearby, surge current caused by lightning, etc., will cause the low-current grounding line selection device to alarm. At this time, the device needs to be adjusted or replaced, and a device with anti-interference capability should be selected.

[0474] The solutions or processing methods for abnormal alarms of the small current grounding line selection device are as follows:

[0475] (1) Check the grounding resistance: Check and maintain the system in a timely manner to see if there is any grounding resistance missing or poor connection, and perform repairs in a timely manner.

[0476] (2) Replace equipment with anti-interference capabilities: When installing equipment, select equipment with anti-interference capabilities and pay attention to the external connections of the equipment to avoid electromagnetic interference.

[0477] (3) Strengthen lightning protection measures: When installing equipment, you should strengthen the lightning protection measures for the equipment, select equipment with certain lightning protection capabilities, and take appropriate grounding measures to avoid equipment damage caused by lightning strikes.

[0478] (4) Filtering the input signal: Use a low-pass filter or a band-pass filter to filter the input signal to reduce the impact of external interference.

[0479] I. DC system lightning arrester failure means that the DC system lightning arrester failure occurs in the equipment in the DC system;

[0480] Failure analysis of DC system lightning arrester failure:

[0481] (1) The power supply voltage exceeds the rated voltage: The DC power supply surge protector can only withstand voltages within a certain range. If the voltage exceeds the rated value, the surge protector may be damaged.

[0482] (2) Long-term thermal damage: DC power supply lightning arresters will generate a certain amount of heat when running for a long time. If the internal heat dissipation of the lightning arrester is not good or the heat dissipation holes are blocked, it will cause the components to overheat and be damaged.

[0483] (3) Power supply short circuit or overload: If the load connected to the DC power surge protector is too large or a short circuit occurs, the surge protector may also be damaged.

[0484] (4) Excessive humidity or water ingress: If the DC power surge protector is in a humid environment or soaked in water, the internal components may become damp and damaged.

[0485] (5) It will affect its normal work.

[0486] (6) Installation error: Improper installation, such as incorrect wiring, poor grounding, etc., will also affect the protection effect of the DC power supply lightning arrester and cause failure.

[0487] The solutions or treatment methods for DC system lightning arrester failure are as follows:

[0488] (1) Failure of DC lightning arrester: You can replace the power lightning arrester and find out the cause to avoid the failure again.

[0489] (2) The power supply lightning arrester is not properly grounded: Check the grounding line to ensure that the grounding is in good condition.

[0490] (3) Short circuit of the power supply lightning arrester: Check the internal structure of the power supply lightning arrester and eliminate the short circuit.

[0491] (4) Power supply lightning arrester breakdown: The power supply lightning arrester can be replaced, and at the same time, check whether the power supply voltage meets the requirements and whether there are other causes of the fault.

[0492] J. DC system grounding fault means that the DC power supply of the equipment in the DC system fails;

[0493] The solutions or treatments for DC system grounding are as follows:

[0494] (1) Determine the polarity of the ground fault. Check the DC busbar (or DC distribution panel) microcomputer DC insulation monitoring device to determine the faulty busbar and faulty line number, and determine the grounding polarity and grounding degree.

[0495] If the positive pole of the DC system is grounded, the relay protection and automatic devices may malfunction;

[0496] Negative grounding in the DC system will cause relay protection and automatic devices to fail to operate.

[0497] If the positive and negative poles of the DC system are grounded at one point, a short circuit will occur, causing the fuse to blow and the protection and automatic devices to lose power.

[0498] (2) According to the fault bus and fault line numbers displayed by the microcomputer DC insulation monitoring device, search along the line.

[0499] (3) Ask if anyone is working on the circuit or if there is any equipment being tested or repaired. If so, stop the work and turn on the power supply to see if the signal is eliminated.

[0500] (4) Check whether there is any newly opened equipment or any equipment that has accidentally fallen into the water. Special attention should be paid to any suspicious equipment systems.

[0501] (5) Use the pull-through method to find the DC grounding fault (signal first, then control, secondary load first, then important load, outdoor first, then indoor). Cut off the power supply to each air switch. If the DC grounding phenomenon disappears after the power outage, it means that the grounding voltage is in the lower circuit controlled by the air switch. If there is no air switch to pull at the lower level, the grounding point can only be determined by untying the cable core. If the DC power supply line is not grounded, it means that the DC bus is grounded. The DC load should be switched to the non-grounded bus and the faulty bus should be powered off.

[0502] (6) When the grounding point is inside the protective screen, unplug the device plug-ins one by one and measure the insulation resistance of the terminal block grounding electrode to the ground. If the insulation is restored, it means that the grounding point is in the corresponding plug-in. If the insulation does not change, it means that the grounding point is located in the terminal block of the protective screen, the DC cable between the terminal block and the wiring inside the screen. Use a megohmmeter to measure the insulation of each terminal of the DC circuit inside the screen, find the grounded terminals, and carefully check the metal parts of the terminals and the connecting wires to find the grounding points.

[0503] It should be noted that the fault cause and solution of this embodiment and the fault analysis results of labels 1 to 7 in the above embodiment are presented in two different forms. In practical applications, the fault analysis results presented in this embodiment can be used according to actual conditions, or the fault analysis results presented in a form similar to labels 1 to 7 can be used, and this application does not limit this.

[0504] refer to Figure 2 The present application also provides a monitoring device for a DC system, the monitoring device for a DC system comprising:

[0505] A first training module 100 is used to input the knowledge base data of the DC system to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs a first-level training according to the knowledge base data;

[0506] A second training module 200 is used to input training data to a pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0507] The third training module 300 is used to perform third-level training on the intelligent monitoring tool by performing human-computer interaction with the intelligent monitoring tool;

[0508] A training completion module 400 is used to obtain a trained intelligent monitoring tool according to the first layer training, the second layer training and the third layer training;

[0509] The abnormal log data input module 500 is used to obtain the abnormal log data of the DC system from the dispatching monitoring system of the DC system and input it into the trained intelligent monitoring tool;

[0510] A fault analysis module 600 is used to perform fault analysis on the DC system according to abnormal log data using an intelligent monitoring tool;

[0511] The result output module 700 is used to output the fault analysis result to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0512] In one embodiment, the third training module 300 includes:

[0513] A human-computer dialogue start module is used to respond to the user's human-computer dialogue start operation and display the human-computer dialogue interface;

[0514] A first receiving module is used to receive and display the user's input data through the human-computer dialogue interface, and input the input data to the intelligent monitoring tool;

[0515] The second receiving module is used to receive the response data output by the intelligent monitoring tool according to the input data, and display the response data to the user through the human-computer dialogue interface;

[0516] A third receiving module is used to display the feedback data or the self-answering data through the human-computer dialogue interface if feedback data input by the user according to the answering data is received, or self-answering data input by the user is received, wherein the feedback data is used to indicate that the answering data is correct or the feedback data is the correction data made by the user for the answering data, and the self-answering data is input by the user when the intelligent monitoring tool does not respond to the input data;

[0517] The feedback module is used to train the intelligent monitoring tool or provide the intelligent monitoring tool with the correction data or self-answer data if there is any.

[0518] In one embodiment, the feedback module includes:

[0519] A retraining module, used for inputting input data and corresponding correction data or self-answer data into the intelligent monitoring tool to retrain the intelligent monitoring tool;

[0520] and / or,

[0521] The storage module is used to archive the conversation content of the human-computer dialogue interface if it receives the user's archiving instruction, and store the obtained archived data in the data center for reference and call when the intelligent monitoring tool monitors the DC system.

[0522] In one embodiment, the monitoring device of the DC system further includes:

[0523] A login module, which is used to respond to the user's login operation, enter and display the intelligent monitoring homepage, wherein the intelligent monitoring homepage is provided with a dialogue option list, and the dialogue option list includes historical dialogue options and current dialogue options;

[0524] The conversation list management module is used to respond to the user's target operation on any target conversation option selected in the conversation option list, change the properties of the target conversation option or change the conversation option list, where the target operation is any one of pinning, renaming, copying, archiving, sharing, deleting and adding tags.

[0525] In one embodiment, the first training module 100 includes:

[0526] The upload interface entry module is used to respond to the user's upload interface entry operation, enter and display the data upload interface;

[0527] The data upload module is used to respond to the user's data upload operation on the data upload interface, and input the knowledge base data uploaded by the user into the pre-trained intelligent monitoring tool; or, respond to the user's data query operation on the data upload interface, display the query results, and input the knowledge base data queried and selected by the user from the query results into the pre-trained intelligent monitoring tool.

[0528] This application uses different methods to perform multi-layer training on the intelligent monitoring tool, so that the intelligent monitoring tool can accurately identify complex fault modes, significantly improving the precision and accuracy of DC system monitoring. This application performs real-time fault analysis to quickly identify abnormal situations, issue warnings in a timely manner, and respond quickly, shortening the fault response time. This application effectively prevents the occurrence of potential faults and improves the operational reliability of the DC system through intelligent early warning and decision support. This application can adaptively retrain the intelligent monitoring tool so that the monitoring function of the intelligent monitoring tool is continuously improved and improved to accurately identify various faults in the DC system.

[0529] Figure 3 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 3 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement the monitoring method of the DC system. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement the monitoring method of the DC system. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0530] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0531] Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0532] Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0533] Through human-computer interaction with the intelligent monitoring tool, the third level of training is performed on the intelligent monitoring tool;

[0534] According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained;

[0535] Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0536] Use trained intelligent monitoring tools to perform fault analysis on DC systems based on abnormal log data;

[0537] The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0538] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the processor performs the following steps:

[0539] Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data;

[0540] Input the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result;

[0541] Through human-computer interaction with the intelligent monitoring tool, the third level of training is performed on the intelligent monitoring tool;

[0542] According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained;

[0543] Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool;

[0544] Use trained intelligent monitoring tools to perform fault analysis on DC systems based on abnormal log data;

[0545] The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

[0546] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0547] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0548] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A monitoring method for a DC system, applied to an intelligent monitoring system for a DC system, characterized in that: The monitoring method of the DC system comprises: Inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs the first layer training according to the knowledge base data; Inputting the training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result; Performing third-level training on the intelligent monitoring tool by performing human-computer interaction with the intelligent monitoring tool; According to the first-layer training, the second-layer training and the third-layer training, a trained intelligent monitoring tool is obtained; Obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool; Using the trained intelligent monitoring tool to perform fault analysis on the DC system according to the abnormal log data; The fault analysis result is output to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

2. The monitoring method of a DC system according to claim 1, characterized in that: The third-level training of the intelligent monitoring tool by human-computer interaction with the intelligent monitoring tool includes: Respond to the user's human-computer dialogue start operation and display the human-computer dialogue interface; Receive and display the user's input data through the human-computer dialogue interface, and input the input data to the intelligent monitoring tool; Receiving response data output by the intelligent monitoring tool according to the input data, and displaying the response data to the user through the human-computer dialogue interface; If feedback data input by the user according to the response data is received, or self-answer data input by the user is received, the feedback data or self-answer data is displayed through the human-computer dialogue interface, wherein the feedback data is used to indicate that the response data is correct or the feedback data is correction data made by the user for the response data, and the self-answer data is input by the user when the intelligent monitoring tool does not respond to the input data; If correction data or self-answer data exists, the correction data or self-answer data is used to train the intelligent monitoring tool or is called by the intelligent monitoring tool.

3. The monitoring method of a DC system according to claim 2, characterized in that: The using of the correction data or the self-answer data to train the intelligent monitoring tool or for the intelligent monitoring tool to call includes: Inputting the input data and corresponding correction data or self-answer data into the intelligent monitoring tool to retrain the intelligent monitoring tool; and / or, If an archiving instruction from the user is received, the conversation content of the human-machine dialogue interface is archived, and the obtained archived data is stored in a data center for reference and calling by the intelligent monitoring tool when monitoring the DC system.

4. The monitoring method of a DC system according to claim 3, characterized in that: The monitoring method of the DC system also includes: In response to the user's login operation, enter and display the smart monitoring homepage, wherein the smart monitoring homepage is provided with a dialogue option list, and the dialogue option list includes historical dialogue options and current dialogue options; In response to the user's target operation on any target dialogue option selected in the dialogue option list, attributes of the target dialogue option are changed or the dialogue option list is changed, wherein the target operation is any one of pinning, renaming, copying, archiving, sharing, deleting and adding tags.

5. The monitoring method of a DC system according to claim 1, characterized in that: The step of inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool includes: Respond to the user's upload interface entry operation, enter and display the data upload interface; In response to the user's data uploading operation on the data uploading interface, the knowledge base data uploaded by the user is input into the pre-trained intelligent monitoring tool; or, in response to the user's data query operation on the data uploading interface, the query results are displayed, and the knowledge base data queried and selected by the user from the query results is input into the pre-trained intelligent monitoring tool.

6. The method for monitoring a DC system according to claim 1, characterized in that: The training data includes at least one of sample log data generated by the dispatching and monitoring system of the DC system when an abnormal alarm occurs in the measurement and control protection device of the DC system, sample log data corresponding to a failure of the energy storage power supply, sample log data corresponding to a failure of the air conditioner in the control cabinet, sample log data corresponding to the failure of the switch spring to store energy, sample log data corresponding to a control loop disconnection, sample log data corresponding to a communication interruption, sample log data corresponding to a fire alarm, sample log data corresponding to an abnormal alarm of a small current grounding line selection device, sample log data corresponding to a failure of the DC system lightning arrester, and sample log data corresponding to a grounding failure in the DC system.

7. The method for monitoring a DC system according to claim 6, characterized in that: If the training data includes sample log data generated by the dispatching and monitoring system of the corresponding DC system when the DC system generates an abnormal timing alarm of the measurement and control protection device, the label of the abnormal timing alarm of the measurement and control protection device includes a general solution to the abnormal timing alarm of the measurement and control protection device and / or a solution to the abnormal timing alarm of the measurement and control protection device with different timing modes, wherein the solution to the abnormal timing alarm of the measurement and control protection device with different timing modes includes at least one of a solution to the failure of broadcast message timing, a solution to the failure of pulse timing and a solution to the failure of IRIG-B code timing; If the training data includes sample log data corresponding to an energy storage power supply failure in the DC system, the label of the energy storage power supply failure includes the cause of the circuit breaker energy storage power supply failure and / or the solution to the circuit breaker energy storage power supply failure, wherein the cause of the circuit breaker energy storage power supply failure includes at least one of an intelligent controller failure, a pressure loss release failure, an energy storage motor failure, a spring mechanism problem, and a control circuit problem; If the training data includes sample log data corresponding to a control cabinet air conditioner failure in the DC system, the label of the control cabinet air conditioner failure includes the cause of the control cabinet air conditioner failure and / or a solution to the control cabinet air conditioner failure, wherein the cause of the control cabinet air conditioner failure includes at least one of a power supply problem and a sensor failure; If the training data includes sample log data corresponding to the DC system when the switch spring fails to store energy, the label when the switch spring fails to store energy includes a solution to the switch spring failing to store energy; If the training data includes sample log data corresponding to a control loop disconnection in the DC system, the label of the control loop disconnection includes the fault cause causing the control loop disconnection and / or the solution to the control loop disconnection, wherein the fault cause causing the control loop disconnection includes at least one of a control loop power supply or air switch failure, a TWJ or HWJ relay and a node failure, an automation system or signal loop failure, a loose loop connection or a terminal failure, a switch mechanism opening and closing coil and an auxiliary contact failure, and various locking contact failures that may exist in the switch control loop; If the training data includes sample log data corresponding to when communication interruption occurs in the DC system, the label of the communication interruption includes a solution causing the communication interruption; If the training data includes sample log data corresponding to a fire alarm occurring in the DC system, the label of the fire alarm includes a solution to the fire alarm; If the training data includes sample log data corresponding to an abnormal alarm of a small current grounding line selection device in the DC system, the label of the abnormal alarm of the small current grounding line selection device includes the fault cause causing the abnormal alarm of the small current grounding line selection device and / or a solution to the abnormal alarm of the small current grounding line selection device; If the training data includes sample log data corresponding to a DC system lightning arrester failure in the DC system, the label of the DC system grounding fault includes the fault cause of the DC system lightning arrester failure and / or the solution to the DC system lightning arrester failure, wherein the fault cause of the DC system lightning arrester failure includes at least one of a power supply voltage exceeding the rated voltage, thermal damage due to long-term operation, a power supply short circuit or overload, excessive humidity or water ingress, and installation error; If the training data includes sample log data corresponding to when a DC system grounding fault occurs in the DC system, the label of the DC system grounding fault includes a solution to the DC system grounding fault.

8. A monitoring device for a DC system, characterized in that: The monitoring device of the DC system comprises: A first training module, used for inputting the knowledge base data of the DC system into the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs a first layer of training according to the knowledge base data; A second training module, used for inputting training data to the pre-trained intelligent monitoring tool, so that the pre-trained intelligent monitoring tool performs second-level training according to the training data, wherein the training data includes a plurality of training samples, each training sample includes sample log data and a corresponding label, and the label includes a sample fault analysis result; A third training module, used for performing third-layer training on the intelligent monitoring tool by performing human-computer interaction with the intelligent monitoring tool; A training completion module, used to obtain a trained intelligent monitoring tool according to the first layer training, the second layer training and the third layer training; An abnormal log data input module is used to obtain abnormal log data of the DC system and input it into the trained intelligent monitoring tool; A fault analysis module, used to perform fault analysis on the DC system according to the abnormal log data using the trained intelligent monitoring tool; The result output module is used to output the fault analysis result to the user, wherein the fault analysis result includes the fault cause and / or the corresponding solution.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor executes the steps of the method for monitoring a DC system as claimed in any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the monitoring method of the DC system according to any one of claims 1 to 7.

Images