A monitoring system alarm signal automatic extraction method and system

Through intermittent access to the historical server and adaptive keyword settings, the monitoring system's automatic alarm signal extraction efficiency and signal integrity problems are solved, and the complete signal extraction and automated monitoring in the case of network delay is realized, saving labor costs.

CN118585406BActive Publication Date: 2024-11-22SANXIA JINSHAJIANG YUNCHUAN HYDROPOWER DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411070107.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-22
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

The existing monitoring system automatic alarm signal extraction method is inefficient and cannot guarantee the integrity of the signal in the historical server. It is especially prone to signal omissions in the case of network delay or network shutdown.

Method used

Intermittent access to the historical server is adopted to ensure the integrity of signal extraction through timestamp judgment and secondary inspection model, and to introduce adaptive keyword settings to reduce manual participation and improve extraction accuracy.

Benefits of technology

In the case of network delay or network shutdown, prevent signal omission by checking access time points, reduce calculation intensity, automatic monitoring reduces manual participation, saves labor costs, and reduces the burden of reporting production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118585406B_ABST
    Figure CN118585406B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for automatically extracting alarm signals of a monitoring system, which relates to the technical field of signal extraction, and includes the following steps: setting up a history server, intermittently accessing the history server, and extracting signals from the history server; retrieving the extracted history server signals to determine whether keywords exist; generating an alarm briefing or a common briefing based on the judgment result, and feeding the briefing back to the staff. In the case of network delay or network outage, the host computer will check according to the last access time point, and when the check is successful, the signal will be extracted from the history server to prevent omissions, ensure the integrity of the extracted history server, and intermittent calculations do not require continuous access to the history server, which can reduce the intensity of calculations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of signal extraction, and in particular to a method and system for automatically extracting alarm signals of a monitoring system. Background Art

[0002] In the daily operation of the hydropower station, due to the large number of hydropower station units and their auxiliary equipment, the monitoring system will report three signals per second on average. Especially during the annual maintenance period, there are more operations on the monitoring system and more signals will be reported. In addition to normal start and stop, annual maintenance and experimental operations, more important alarm signals need to be recorded in detail in the duty log of the power production management system according to the daily management regulations of the hydropower station. The relevant alarms and processing processes need to be recorded in detail in the duty log of the power production management system. In the event of a major accident, it is also necessary to submit a briefing to the superior unit and the company's 24-hour duty, which will occupy the originally tight duty human resources to do simple copying and recording, which is not conducive to improving work efficiency.

[0003] The current method of extracting briefings is to use a host computer to extract signals from the history server in real time. However, this method may cause omissions of signals in the history server in the event of network delays or network outages. Therefore, the integrity of the signals extracted from the history server cannot be guaranteed. Secondly, the real-time calculation method requires a large amount of calculation, which will result in a long running time. Summary of the invention

[0004] In view of the existing automatic extraction of alarm signals of monitoring systems and the problems existing in the systems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the efficiency of extracting signals from the history server is low and the integrity of the signals in the history server cannot be guaranteed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for automatically extracting alarm signals from a monitoring system, which comprises the following steps:

[0008] Set up a history server, intermittently access the history server, and extract signals from the history server;

[0009] Search the extracted historical server signals to determine whether there are keywords;

[0010] Generate an alarm briefing or a normal briefing based on the judgment results, and feed the briefing back to the staff.

[0011] As a preferred solution of the method for automatically extracting alarm signals from a monitoring system according to the present invention, the method for extracting signals from a history server includes:

[0012] The host computer intermittently accesses the history server, and the interval is S seconds. The time period is set for the signal in the history server. The time period is [ 0 , S + 1 ] , and the seconds as identification parameters, and then The signal in the history server of seconds is judged. When the signal in the historical server of the second is the same as the signal in the historical server of the first second of the next time, the signal in the historical server of the set time period is extracted and the historical server is judged to be complete. When the input result is different from the input result of the first second of the next time, the secondary verification model is entered.

[0013] As a preferred solution of the automatic extraction method of alarm signals of the monitoring system of the present invention, the inspection method of the secondary inspection model includes:

[0014] Introduce a timestamp judgment model to obtain the time of the first second of this judgment and the time of the last judgment. The time difference of seconds is calculated, and the two time difference values ​​are calculated. The calculation formula is expressed as:

[0015] ,

[0016] In the formula, L represents the difference between two time values. It represents the time of the first second of this judgment. Indicates the last judgment Seconds of time;

[0017] Then the time difference L is judged, and the judgment method is expressed as:

[0018] When the time difference L is a positive number, a new seconds, and the new seconds to replace the old The signal is extracted from the historical server of the set time period again, and the calculation method is:

[0019] ,

[0020] When the time difference L is a negative number, a new seconds, and the new seconds to replace the old The signal is extracted from the historical server of the set time period again, and the calculation method is:

[0021] ,

[0022] In the formula, Represented as the new Seconds of time.

[0023] As a preferred solution of the method for automatically extracting alarm signals from a monitoring system according to the present invention, the inspection method of the secondary inspection model further includes:

[0024] Set an unexpected number threshold Z. Within 24 hours, when the calculation times of the secondary inspection model are greater than the threshold Z, the alarm system is activated and the staff is reminded to conduct a full inspection, collect the time period of the error, and determine the type of problem in the time period of the error.

[0025] Within 24 hours, when the number of calculations of the quadratic test model is not greater than the threshold Z, return to the step of extracting the signal from the history server;

[0026] Among them, the method for determining the type of problem in the time period of the error report includes:

[0027] The number of times all keywords appear during the search period is counted, and they are arranged in order of number. The keywords with the most appearances are extracted and set as question types. When there are two or more keywords with the most appearances, the parallel keywords are extracted together and set as question types.

[0028] As a preferred solution of the method for automatically extracting alarm signals from a monitoring system according to the present invention, the method for retrieving the extracted historical server signals includes:

[0029] Preset keywords, then determine whether the extracted historical server signal contains the keywords. If the keywords do not exist, re-access the historical server. If the keywords exist, analyze whether the built-in conditions are met at the same time. If they are met at the same time, output an alarm briefing. If they are not met at the same time, output a normal briefing.

[0030] The keyword setting method includes initial setting and adaptive setting;

[0031] The initial setting method is as follows: the staff inputs the keyword into the upper computer, and judges the repeatability of the keyword. If the keyword does not exist, the input is successful. If the keyword exists, a keyword repeat instruction is output;

[0032] The adaptive setting method is: each time it is determined whether a keyword exists, the existing keyword is marked, and when the keyword appears repeatedly, the marking times are increased, and it is determined whether the marking times of the same keyword is greater than the set value P. When it is not greater than the set value P, no additional keyword is added. When it is greater than the set value P, the timestamp of the keyword is obtained, and similar words of the keyword are retrieved. Each similar word retrieved is re-identified. When similar words exist in the history server, the similar words are input into the upper computer as keywords. When similar words do not exist in the history server, no additional keywords are added.

[0033] As a preferred solution of the automatic extraction method of alarm signals of the monitoring system of the present invention, wherein: the built-in conditions include switch action, the change in active power of the unit exceeds 100MW, and protection action;

[0034] When the history server meets the built-in conditions at the same time, the timestamp is introduced, the alarm briefing is generated in chronological order, and an alarm is issued to remind the staff;

[0035] When the built-in conditions are not met simultaneously in the history server, a normal briefing is output;

[0036] The alarm brief includes a number, time information, and problem type.

[0037] As a preferred solution of the automatic extraction method of alarm signals of the monitoring system of the present invention, after the briefing is fed back to the staff, the type of the briefing is judged by the following method:

[0038] When the briefing is an alarm briefing, the options to be operated are automatically output. The staff confirms the contents of the alarm briefing, inputs the operation steps into the options to be operated, and after verification and confirmation, cancels the alarm state and generates a one-key copy option.

[0039] When the briefing is a normal briefing, a one-click copy option is generated.

[0040] In a second aspect, an embodiment of the present invention provides a monitoring system alarm signal automatic extraction system, which includes an access extraction module, an information verification module, a keyword setting module, and a briefing output module;

[0041] The access and extraction module is responsible for intermittently accessing the history server, extracting signals from the history server, setting a time period for data extraction, and using identification parameters to ensure data integrity;

[0042] The information verification module is used to search for keywords, determine whether to perform built-in condition judgment based on the results of whether the keywords exist, and take corresponding actions based on the final judgment results;

[0043] The keyword setting module includes two submodules: initial setting and adaptive setting. The initial setting enables the staff to input new keywords, and the adaptive setting can automatically update the keyword library according to the frequency of keyword appearance;

[0044] The briefing output module outputs an alarm briefing or a common briefing according to the judgment result, so that the staff can copy the briefing content with one click.

[0045] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned method for automatically extracting alarm signals from a monitoring system is implemented.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned method for automatically extracting alarm signals from a monitoring system is implemented.

[0047] The beneficial effects of the present invention are as follows: in the case of network delay or network outage, the host computer will check according to the last access time point, and when the check is successful, the signal will be extracted from the history server to prevent omissions and ensure the integrity of the extracted history server, and intermittent calculations do not require continuous access to the history server, which can reduce the intensity of calculations;

[0048] The use of adaptive keyword setting can prevent failures that cannot be queried in time, and automated monitoring reduces manual involvement, which can significantly save labor costs in the long run. Secondly, it reduces the burden of manual report preparation and allows operators to focus on more important tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0050] Figure 1 The figure is a flow chart of the automatic extraction method of alarm signals of monitoring system.

[0051] Figure 2 Schematic diagram of the timeline of intermittent access for the automatic extraction method of alarm signals in the monitoring system.

[0052] Figure 3 A schematic diagram of the timeline update of the automatic extraction method of alarm signals from the monitoring system. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0057] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0058] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] Example 1

[0060] Reference Figure 1~Figure 3 , which is the first embodiment of the present invention, provides a method for automatically extracting alarm signals from a monitoring system, comprising the following steps:

[0061] S1. Establish a history server, intermittently access the history server, and extract signals from the history server.

[0062] Among them, the method of extracting signals from the history server includes:

[0063] The host computer intermittently accesses the history server, and the interval is S seconds. The time period is set for the signal in the history server. The time period is [ 0 , S + 1 ] , and the seconds as identification parameters, and then The signal in the history server of seconds is judged. If the signal in the history server of the second is the same as the signal in the history server of the first second of the next time, the signal in the history server of the set time period is extracted and the history server is judged to be complete. If the input result is different from the result of the first second of the next time, the secondary inspection model is entered;

[0064] like Figure 2 As shown, 24 hours are expressed in seconds, and the interval length is set to 20 seconds, then the time period is [ 0 , 21 ] , and the 21st second is the identification parameter. When the host computer visits the history server for the first time, it judges the signal within 0-20 seconds to check whether there is a keyword. When it visits the history server for the second time, [ 20 , 41 ] The signal access of seconds, first the first second of this access to the history server (i.e. the 21st second) and the last second of the previous access to the history server (i.e. the seconds) input results, if the judgment results are the same, it means that the time axis is complete, that is, there is no omission.

[0065] The testing method of the secondary test model includes:

[0066] Introduce a timestamp judgment model to obtain the time of the first second of this judgment and the time of the last judgment. The time difference of seconds is calculated, and the two time difference values ​​are calculated. The calculation formula is expressed as:

[0067] ,

[0068] In the formula, L represents the difference between two time values. It represents the time of the first second of this judgment. Indicates the last judgment Seconds of time;

[0069] Then the time difference L is judged, and the judgment method is expressed as:

[0070] When the time difference L is a positive number, a new seconds, and the new seconds to replace the old The signal is extracted from the historical server of the set time period again, and the calculation method is:

[0071] ,

[0072] When the time difference L is a negative number, a new seconds, and the new seconds to replace the old The signal is extracted from the historical server of the set time period again, and the calculation method is:

[0073] ,

[0074] In the formula, Represented as the new Seconds of time;

[0075] like Figure 3 As shown, when network delay occurs, during the 7th access, the time period is [ 140 , 161 ] , so the time of the first second during the 7th visit is the 141st second, and the last time (i.e. the 6th visit) the time of the first second is the 141st second. The second is the 121st second, so the two time points are different. The two time difference values ​​L are calculated by the formula, that is, 121-141=-20 seconds. The time difference L is -20 seconds, which is a negative number. The new time calculation formula is set as , and set the 121st second as the new Seconds to ensure the integrity of the timeline.

[0076] The testing method of the secondary test model also includes:

[0077] Set an unexpected number threshold Z. Within 24 hours, when the calculation times of the secondary inspection model are greater than the threshold Z, the alarm system is activated and the staff is reminded to conduct a full inspection, collect the time period of the error, and determine the type of problem in the time period of the error.

[0078] Within 24 hours, when the number of calculations of the quadratic test model is not greater than the threshold Z, return to the step of extracting the signal from the history server;

[0079] Among them, the method for determining the type of problem in the time period of the error report includes:

[0080] The number of times all keywords appear in the search time period is sorted in order of the number of times, and the keyword with the most occurrences is extracted and set as the question type. When there are two or more keywords with the most occurrences, the parallel keywords are extracted together and set as the question type;

[0081] Set the accident number threshold Z to 5;

[0082] Table 1: Effects of setting different thresholds Z

[0083] ,

[0084] It can be seen from Table 1 that the value of the full inspection result is the number of faulty devices found in each full inspection. The number of tests is 10, and the average of the results of 10 times is taken. The stronger the work intensity, the more frequently the staff conducts full inspections. When the threshold is set to 2, 3 or 4, the number of faulty devices detected each time is 3-4, which accounts for a small proportion in the huge equipment group of the hydropower station. There are also small problems that can be ignored, such as dust on the surface of the equipment, so frequent inspections will occur. When the threshold is set to 5, the work intensity of the staff can be reduced, and compared with the case where the threshold is 4, the number of faults detected is significantly increased. When the threshold is set to 6 or 7, although the work intensity is reduced, the number of equipment failures detected each time increases significantly, and safety cannot be guaranteed.

[0085] S2. Search the extracted historical server signals to determine whether there are keywords.

[0086] The method for retrieving the extracted historical server signal includes:

[0087] Preset keywords, then determine whether the extracted historical server signal contains the keywords. If the keywords do not exist, re-access the historical server. If the keywords exist, analyze whether the built-in conditions are met at the same time. If they are met at the same time, output an alarm briefing. If they are not met at the same time, output a normal briefing.

[0088] The keyword setting method includes initial setting and adaptive setting;

[0089] The initial setting method is as follows: the staff inputs the keyword into the upper computer, and judges the repeatability of the keyword. If the keyword does not exist, the input is successful. If the keyword exists, a keyword repeat instruction is output;

[0090] The method of the adaptive setting is as follows: each time it is determined whether a keyword exists, the existing keyword is marked, and when the keyword appears repeatedly, the marking times are increased, and it is determined whether the marking times of the same keyword is greater than a set value P. When it is not greater than the set value P, no additional keyword is added. When it is greater than the set value P, the timestamp of the keyword is obtained, and the similar words of the keyword are retrieved, and each similar word retrieved is re-identified. When the similar words exist in the history server, the similar words are input as keywords to the upper computer. When the similar words do not exist in the history server, no additional keywords are added.

[0091] Taking P as 3 as an example, each time the keyword is extracted, if the keyword "fault" appears 5 times, "alarm" appears 2 times, and "overlimit" appears 1 time, because the keyword "fault" appears more than the set value P, similar words of the keyword "fault" are automatically retrieved, and the retrieved similar words are "stained", "accident" and "damaged". Then the similar words "stained", "accident" and "damaged" are searched. When similar words exist in the history server, the corresponding similar words are changed to keywords and added to the host computer.

[0092] The built-in conditions include switch action, unit active power change exceeding 100MW, and protection action;

[0093] When the history server meets the built-in conditions at the same time, the timestamp is introduced, the alarm briefing is generated in chronological order, and an alarm is issued to remind the staff;

[0094] When the built-in conditions are not met simultaneously in the history server, a normal briefing is output;

[0095] The alarm brief includes a number, time information, and problem type.

[0096] S3. Generate an alarm briefing or a normal briefing based on the judgment result, and feed the briefing back to the staff.

[0097] After the briefing is fed back to the staff, the type of briefing is determined by:

[0098] When the briefing is an alarm briefing, the options to be operated are automatically output. The staff confirms the contents of the alarm briefing, inputs the operation steps into the options to be operated, and after verification and confirmation, cancels the alarm state and generates a one-key copy option.

[0099] When the briefing is a normal briefing, a one-click copy option is generated.

[0100] In summary, in the event of network delays or network outages, the host computer will check based on the last access time point. When the check is successful, it will extract the signal from the history server to prevent omissions and ensure the integrity of the extracted history server. Intermittent calculations do not require continuous access to the history server, which can reduce the intensity of calculations. The use of adaptive keyword setting can prevent failures that cannot be queried in time, and automated monitoring reduces manual participation. In the long run, it can significantly save labor costs. Secondly, it reduces the burden of manual report preparation, allowing operators to focus on more important tasks.

[0101] Example 2

[0102] On the basis of the first embodiment, this embodiment further provides a monitoring system alarm signal automatic extraction system, including an access extraction module, an information inspection module, a keyword setting module, and a briefing output module;

[0103] The access and extraction module is responsible for intermittently accessing the history server, extracting signals from the history server, setting a time period for data extraction, and using identification parameters to ensure data integrity;

[0104] The information verification module is used to search for keywords, determine whether to perform built-in condition judgment based on the results of whether the keywords exist, and take corresponding actions based on the final judgment results;

[0105] The keyword setting module includes two submodules: initial setting and adaptive setting. The initial setting enables the staff to input new keywords, and the adaptive setting can automatically update the keyword library according to the frequency of keyword appearance;

[0106] The briefing output module outputs an alarm briefing or a common briefing according to the judgment result, so that the staff can copy the briefing content with one click.

[0107] This embodiment also provides a computer device, which is suitable for the automatic extraction method of the monitoring system alarm signal, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the automatic extraction method of the monitoring system alarm signal proposed in the above embodiment.

[0108] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0109] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for automatically extracting alarm signals from a monitoring system as proposed in the above embodiment is implemented.

[0110] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0111] Example 3

[0112] On the basis of the previous two embodiments, this embodiment provides a method for automatically extracting alarm signals from a monitoring system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0113] Table 2: Schematic diagram of the effects of different extraction methods

[0114] ,

[0115] Comparative Example 1 uses manual recording;

[0116] Comparative Example 2 uses a host computer to access the history server in real time, and uses staff to input keywords;

[0117] It can be seen from Table 2 that Example 1 requires greater work intensity and relies on the high level of patents of the staff, while in Example 2, because it is impossible to adaptively add keywords, keyword omissions may occur, which in turn leads to a decrease in search accuracy, and the real-time access method cannot guarantee the integrity of the signal.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatically extracting alarm signals from a monitoring system, characterized in that: The following steps are included: Set up a history server, intermittently access the history server, and extract signals from the history server; Search the extracted historical server signals to determine whether there are keywords; Generate alarm briefings or general briefings based on the judgment results, and feed the briefings back to the staff; Methods for extracting signals from the history server include: The host computer intermittently accesses the history server with an interval of S seconds. The time period is set for the signal in the history server, and the time period is [0, S+1]. The S+1 second is set as the identification parameter. Then, the signal in the history server in the S+1 second is judged. When the signal in the history server in the S+1 second is the same as the signal in the history server in the first second of the next time, the signal in the history server in the set time period is extracted, and the history server is judged to be complete. When the input result is different from the result of the first second of the next time, the secondary inspection model is entered. The testing method of the secondary test model includes: The timestamp judgment model is introduced to obtain the time difference between the first second of this judgment and the S+1 second of the previous judgment, and the two time differences are calculated. The calculation formula is expressed as: L=S ONE -S +1 In the formula, L represents the difference between two time values, S ONE It represents the time of the first second of this judgment, S +1 It represents the time of the last judgment S+1 seconds; Then the time difference L is judged, and the judgment method is expressed as: When the time difference L is a positive number, a new time of S+1 second is set, and the new time of S+1 second replaces the old time of S+1 second, and the signal in the history server of the set time period is extracted again, wherein the calculation method is: When the time difference L is a negative number, a new S+1 second time is set, and the new S+1 second time replaces the old S+1 second time, and the signal in the history server of the set time period is extracted again, wherein the calculation method is: In the formula, Represented as the new time of S+1 second.

2. The method for automatically extracting alarm signals from a monitoring system according to claim 1, characterized in that: The testing method of the secondary test model also includes: Set an unexpected number threshold Z. Within 24 hours, when the calculation times of the secondary inspection model are greater than the threshold Z, the alarm system is activated and the staff is reminded to conduct a full inspection, collect the time period of the error, and determine the type of problem in the time period of the error. Within 24 hours, when the number of calculations of the secondary test model is not greater than the threshold Z, return to the step of extracting the signal from the history server; Among them, the method for determining the type of problem in the time period of the error report includes: The number of times all keywords appear during the search period is counted, and they are arranged in order of number. The keywords with the most appearances are extracted and set as question types. When there are two or more keywords with the most appearances, the parallel keywords are extracted together and set as question types.

3. The method for automatically extracting alarm signals from a monitoring system according to claim 2, characterized in that: The method for retrieving the extracted historical server signal includes: Preset keywords, then determine whether the extracted historical server signal contains the keywords. If the keywords do not exist, re-access the historical server. If the keywords exist, analyze whether the built-in conditions are met at the same time. If they are met at the same time, output an alarm briefing. If they are not met at the same time, output a normal briefing. The keyword setting method includes initial setting and adaptive setting; The initial setting method is as follows: the staff inputs the keyword into the upper computer, and judges the repeatability of the keyword. If the keyword does not exist, the input is successful. If the keyword exists, a keyword repeat instruction is output; The adaptive setting method is: each time it is determined whether a keyword exists, the existing keyword is marked, and when the keyword appears repeatedly, the marking times are increased, and it is determined whether the marking times of the same keyword is greater than the set value P. When it is not greater than the set value P, no additional keyword is added. When it is greater than the set value P, the timestamp of the keyword is obtained, and similar words of the keyword are retrieved. Each similar word retrieved is re-identified. When similar words exist in the history server, the similar words are input into the upper computer as keywords. When similar words do not exist in the history server, no additional keywords are added.

4. The method for automatically extracting alarm signals from a monitoring system according to claim 3, characterized in that: The built-in conditions include switch action, unit active power change exceeding 100MW, and protection action; When the history server meets the built-in conditions at the same time, the timestamp is introduced, the alarm briefing is generated in chronological order, and an alarm is issued to remind the staff; When the built-in conditions are not met simultaneously in the history server, a normal briefing is output; The alarm brief includes a number, time information, and problem type.

5. The method for automatically extracting alarm signals from a monitoring system according to claim 4, characterized in that: After the briefing is fed back to the staff, the type of briefing is determined by: When the briefing is an alarm briefing, the options to be operated are automatically output. The staff confirms the contents of the alarm briefing, inputs the operation steps into the options to be operated, and after verification and confirmation, cancels the alarm state and generates a one-key copy option. When the briefing is a normal briefing, a one-click copy option is generated.

6. A monitoring system alarm signal automatic extraction system, based on the monitoring system alarm signal automatic extraction method according to any one of claims 1 to 5, characterized in that: It includes access extraction module, information verification module, keyword setting module, and briefing output module; The access and extraction module is responsible for intermittently accessing the history server, extracting signals from the history server, setting a time period for data extraction, and using identification parameters to ensure data integrity; The information verification module is used to search for keywords, determine whether to perform built-in condition judgment based on the results of whether the keywords exist, and take corresponding actions based on the final judgment results; The keyword setting module includes two submodules: initial setting and adaptive setting. The initial setting enables the staff to input new keywords, and the adaptive setting can automatically update the keyword library according to the frequency of keyword appearance; The briefing output module outputs an alarm briefing or a common briefing according to the judgment result, so that the staff can copy the briefing content with one click.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for automatically extracting alarm signals from a monitoring system according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for automatically extracting alarm signals from a monitoring system according to any one of claims 1 to 5 are implemented.