Real-time monitoring and warning system and method for operation and maintenance of power station

Abstract

The invention relates to the technical field of power station operation and maintenance, and discloses a power station operation and maintenance real-time monitoring alarm system and method, and the system comprises a construction module which is used for constructing a plurality of alarm grade-information mapping tables, and building an alarm analysis model according to all alarm grade-information mapping tables; the analysis module is used for acquiring a real-time alarm information set of each power station, generating an analysis result of all the real-time alarm information sets based on an alarm analysis model and generating an operation and maintenance instruction according to the analysis result, and the operation and maintenance instruction comprises an operation and maintenance sequence and operation and maintenance waiting time; and the judgment module is used for setting an information acquisition strategy of the power station to be operated and maintained, acquiring real-time information change characteristics of the power station to be operated and maintained based on the information acquisition strategy, generating a change risk value, judging whether to correct the operation and maintenance instruction or not according to the change risk value, timely discovering the insufficiency of the operation and maintenance instruction, continuously adjusting the operation and maintenance sequence and improving the operation and maintenance efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of power station operation and maintenance, and in particular to a real-time monitoring and alarm system and method for power station operation and maintenance. Background Art

[0002] Virtual power plants integrate photovoltaic power stations, wind farms, distributed power sources, energy storage systems, etc. into a controllable whole. However, there are still many problems with overall operation and maintenance. For example, operation and maintenance can only be carried out in sequence according to the alarm time, and a comprehensive assessment of the real-time alarm information of each power station cannot be performed. This leads to a slow response to alarm information with high alarm levels, and may also cause equipment damage or system crashes, etc., increasing operation and maintenance costs and reducing operation and maintenance efficiency. Summary of the Invention

[0003] In order to solve the above technical problems, the present application provides a real-time monitoring and alarm system and method for power plant operation and maintenance. By constructing an alarm analysis model, the real-time alarm information of multiple power plants is analyzed, operation and maintenance instructions are generated according to the analysis results, and the change risk value of the power plant to be operated and maintained is calculated. It is determined whether to correct the operation and maintenance instructions based on the change risk value, and a comprehensive evaluation is performed on the real-time alarm information of multiple power plants. The accuracy of the alarm level is improved and a reasonable operation and maintenance sequence is formulated. The deficiencies in the operation and maintenance instructions are discovered in a timely manner and the operation and maintenance sequence is continuously adjusted to improve the operation and maintenance efficiency.

[0004] In some embodiments of the present application, a real-time monitoring and alarm system for power plant operation and maintenance is provided, comprising: A construction module is used to construct multiple alarm level-information mapping tables and establish an alarm analysis model based on all alarm level-information mapping tables; An analysis module is configured to obtain a real-time alarm information set for each power station, generate analysis results of all real-time alarm information sets based on an alarm analysis model, and generate operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; The judgment module is used to set the information collection strategy of the power station to be operated and maintained, obtain the real-time information change characteristics of the power station to be operated and maintained based on the information collection strategy, generate the change risk value of the power station to be operated and maintained according to the real-time information change characteristics, and judge whether to modify the operation and maintenance instructions.

[0005] In some embodiments of the present application, multiple alarm level-feature information mapping tables are constructed, including: Pre-set several alarm levels; Obtain historical alarm information of each alarm level based on the historical alarm log of each power station, wherein the historical alarm information includes historical alarm data, historical alarm device, historical alarm time, and historical alarm urgency; According to the accuracy of historical alarms in historical alarm logs, the corresponding historical alarm information is divided into high-accuracy alarm information, medium-accuracy alarm information and low-accuracy alarm information, and mapped with corresponding historical credibility labels and corresponding historical operation and maintenance measures respectively; Construct an alarm level-information mapping table for each alarm level by combining the high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each alarm level of each power station with the mapped historical credibility labels and historical operation and maintenance measures; The high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each power plant corresponding to all alarm levels in the all alarm level-information mapping table are used as the training input dataset, and the mapped alarm levels, historical credibility labels, and historical operation and maintenance measures are used as the training output dataset; The neural network is trained based on the training input data set and the training output data set to obtain an alarm analysis model.

[0006] In some embodiments of the present application, generating analysis results of all real-time alarm information sets based on the alarm analysis model and generating operation and maintenance instructions based on the analysis results include: Receive real-time alarm information from each power station and construct a real-time alarm information set for the corresponding power station, wherein the real-time alarm information set includes real-time alarm equipment, real-time alarm data, real-time alarm time, and real-time alarm urgency; Input the real-time alarm information set into the alarm analysis model to obtain the predicted alarm level of the corresponding power station, the corresponding prediction credibility label and the predicted operation and maintenance measures; Generate a corrected alarm level for the corresponding power station based on the predicted alarm level and the corresponding prediction credibility label; Sorting all power plants according to their corrected alarm levels, and generating an operation and maintenance sequence based on the sorting results, wherein the operation and maintenance sequence includes a number of power plants to be operated and maintained and predicted operation and maintenance measures for the power plants to be operated and maintained; Forecast the operation and maintenance time for each power station to be operated and maintained, and set the operation and maintenance waiting time for the next adjacent power station to be operated and maintained according to the prediction results; Generate operation and maintenance instructions based on the operation and maintenance sequence and operation and maintenance waiting time.

[0007] In some embodiments of the present application, setting an information collection strategy for a power station to be operated and maintained includes: Presetting a number of change evaluation indicators and a number of equipment evaluation indicators; Calculate the similarity between the real-time alarm information set and the historical alarm information of each power station to be operated and maintained, and filter out similar alarm information based on the similarity; The historical collection time is set based on the operation and maintenance waiting time of each power station to be operated and maintained, a number of similar alarm information in the historical inspection time is collected, and a number of change evaluation indicators and reference evaluation values of a number of equipment evaluation indicators are generated; Generate a collection evaluation value corresponding to the power station to be operated and maintained based on a number of reference evaluation values; The calculation formula of the acquisition evaluation value is: ; Among them, P is the collection evaluation value, a1 is the weight coefficient of the reference evaluation value of several change evaluation indicators, p1 is the first collection evaluation conversion coefficient, a2 is the weight coefficient of the reference evaluation value of several equipment evaluation indicators, p2 is the second collection evaluation conversion coefficient, n1 is the number of change evaluation indicators, is the reference evaluation value of the i1th change evaluation index, is the weight coefficient of the i1th change evaluation index, n2 is the number of equipment evaluation indicators, is the reference evaluation value of the i2th equipment evaluation index, is the weight coefficient of the i2th equipment evaluation index; An information collection strategy for the power station to be operated and maintained is set according to the collection evaluation value of each power station to be operated and maintained. The information collection strategy includes the amount of information collected and the time interval between collection time nodes.

[0008] In some embodiments of the present application, an information collection strategy for a power station to be operated and maintained is set according to the collection evaluation value of each power station to be operated and maintained, including: Presetting a first preset collection evaluation value interval, a second preset collection evaluation value interval, a third preset collection evaluation value interval and a fourth preset collection evaluation value interval; When the collection evaluation value of the power station to be operated and maintained is within the first preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the first preset collection amount, and the time interval between the collection time nodes is set to the fourth preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the second preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the second preset collection amount, and the time interval between the collection time nodes is set to the third preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the third preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the third preset collection amount, and the time interval between the collection time nodes is set to the second preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the fourth preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the fourth preset collection amount, and the time interval between the collection time nodes is set to the first preset time interval; Calculating the weight coefficient of each real-time alarm data in the real-time alarm information of the power station to be operated and maintained, sorting the real-time alarm data according to the weight coefficient, and obtaining a real-time alarm data sequence; The data to be collected in the real-time alarm data sequence is filtered according to the information collection quantity in the information collection strategy of each power station to be operated and maintained, and the data to be collected is collected according to the time interval between the collection time nodes to obtain the real-time information change characteristics of the corresponding power station to be operated and maintained during the operation and maintenance waiting time.

[0009] In some embodiments of the present application, before generating the change risk value of the power station to be operated and maintained according to the real-time information change characteristics, the method further includes: The real-time information change characteristics include the change trend, change rate and change value of several data to be collected; Generate a change coefficient for the corresponding data to be collected according to the change trend, change rate and change value of each data to be collected, and obtain the absolute value of the change coefficient; Pre-set coefficient of variation threshold; If the absolute value of the coefficient of variation of the data to be collected is greater than the coefficient of variation threshold, a number of associated data corresponding to the data to be collected are screened out, and a set of associated data corresponding to the data to be collected is constructed; Collect the real-time data of each associated data in the associated data set at the corresponding collection node and input it into the alarm analysis model to obtain the predicted alarm level and prediction credibility label of the corresponding associated data, and generate the corrected alarm level of the corresponding associated data; A selection coefficient of a variation coefficient corresponding to the data to be collected is generated according to the number of associated data in the associated data set whose modified alarm levels are greater than the modified alarm levels of the corresponding data to be collected and the difference in the modified levels.

[0010] In some embodiments of the present application, generating a change risk value of a power station to be operated and maintained based on the real-time information change characteristics includes: Classify the variation coefficients of several data to be collected for the same power station to be operated and maintained, and obtain a set of positive variation coefficients, a set of negative variation coefficients, and a set of no variation coefficients; Generate a change risk value for the power station to be operated and maintained based on the number of positive change coefficient sets, the number of negative change coefficient sets, the number of no change coefficient sets, the weight coefficient of the data to be collected in the negative change coefficient set, the corresponding change coefficient, and the selection coefficient; The calculation formula of the change risk value is: ; Among them, F is the change risk value, m2 is the number of negative change coefficient sets, m1 is the number of positive change coefficient sets, and m3 is the number of no change coefficient sets. is the first weight coefficient, w2 is the second weight coefficient, f1 is the first change risk conversion coefficient, f2 is the second change risk conversion coefficient, is the selection coefficient of the sth data to be collected in the positive variation coefficient set, is the difference between the absolute value of the variation coefficient of the sth data to be collected and the variation coefficient threshold, q1s is the weight coefficient of the sth data to be collected, is the selection coefficient of the vth data to be collected in the negative variation coefficient set, is the difference between the absolute value of the variation coefficient of the vth data to be collected and the variation coefficient threshold, and q2v is the weight coefficient of the vth data to be collected.

[0011] In some embodiments of the present application, determining whether to modify the operation and maintenance instruction includes: Generating a compensation coefficient for the revised alarm level corresponding to the power station to be operated and maintained according to the change risk value, and re-correcting the revised alarm level according to the compensation coefficient to obtain a secondary revised alarm level; Generate the secondary revised alarm level of each power station to be operated and maintained in sequence; Compare the secondary correction alarm levels of multiple power plants to be operated and maintained, and determine whether to adjust the operation and maintenance sequence based on the comparison results. If so, modify the operation and maintenance instructions based on the adjustment results.

[0012] In some embodiments of the present application, a method for real-time monitoring and alarming of power plant operation and maintenance is also included: Construct multiple alarm level-information mapping tables, and establish an alarm analysis model based on all alarm level-information mapping tables; Obtaining a real-time alarm information set for each power station, generating analysis results of all real-time alarm information sets based on an alarm analysis model, and generating operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; An information collection strategy for the power plant to be operated and maintained is set, and the real-time information change characteristics of the power plant to be operated and maintained are obtained based on the information collection strategy. A change risk value of the power plant to be operated and maintained is generated according to the real-time information change characteristics, and it is determined whether the operation and maintenance instructions should be modified.

[0013] The real-time monitoring and alarm system and method for power plant operation and maintenance according to the present application have the following advantages compared with the prior art: By building an alarm analysis model, analyzing the real-time alarm information of multiple power plants, generating operation and maintenance instructions based on the analysis results, calculating the change risk value of the power plant to be operated and maintained, judging whether to revise the operation and maintenance instructions based on the change risk value, and conducting a comprehensive assessment of the real-time alarm information of multiple power plants, the accuracy of the alarm level is improved and a reasonable operation and maintenance sequence is formulated. Insufficient operation and maintenance instructions are discovered in a timely manner and the operation and maintenance sequence is continuously adjusted to improve operation and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a schematic diagram of a real-time monitoring and alarm system for power station operation and maintenance according to an embodiment of the present application; Figure 2 It is a flow chart of a method for real-time monitoring and alarming of power station operation and maintenance in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0016] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0017] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0018] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0019] like Figure 1 As shown, a real-time monitoring and alarm system for power plant operation and maintenance according to an embodiment of the present application includes: A construction module is used to construct multiple alarm level-information mapping tables and establish an alarm analysis model based on all alarm level-information mapping tables; An analysis module is configured to obtain a real-time alarm information set for each power station, generate analysis results of all real-time alarm information sets based on an alarm analysis model, and generate operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; The judgment module is used to set the information collection strategy of the power station to be operated and maintained, obtain the real-time information change characteristics of the power station to be operated and maintained based on the information collection strategy, generate the change risk value of the power station to be operated and maintained according to the real-time information change characteristics, and judge whether to modify the operation and maintenance instructions.

[0020] In some embodiments of the present application, multiple alarm level-feature information mapping tables are constructed, including: Pre-set several alarm levels; Obtain historical alarm information of each alarm level based on the historical alarm log of each power station, wherein the historical alarm information includes historical alarm data, historical alarm device, historical alarm time, and historical alarm urgency; According to the accuracy of historical alarms in historical alarm logs, the corresponding historical alarm information is divided into high-accuracy alarm information, medium-accuracy alarm information and low-accuracy alarm information, and mapped with corresponding historical credibility labels and corresponding historical operation and maintenance measures respectively; Construct an alarm level-information mapping table for each alarm level by combining the high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each alarm level of each power station with the mapped historical credibility labels and historical operation and maintenance measures; The high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each power plant corresponding to all alarm levels in the all alarm level-information mapping table are used as the training input dataset, and the mapped alarm levels, historical credibility labels, and historical operation and maintenance measures are used as the training output dataset; The neural network is trained based on the training input data set and the training output data set to obtain an alarm analysis model.

[0021] In this embodiment, the historical credibility label is set according to the accuracy of each historical alarm information with respect to the historical alarm level, that is, the credibility of each historical alarm information.

[0022] In this embodiment, when the accuracy of historical alarms decreases from high to low, the corresponding historical alarm information is divided into high-accuracy alarm information, medium-accuracy alarm information and low-accuracy alarm information respectively. When the urgency of historical alarms decreases from high to low, the corresponding alarm level is set from high to low.

[0023] In this embodiment, by constructing an alarm analysis model, an initial judgment of the alarm level is made for subsequent real-time alarm information, and an operation and maintenance sequence and operation and maintenance instructions are determined, thereby achieving timely operation and maintenance and efficient alarm level judgment.

[0024] In some embodiments of the present application, generating analysis results of all real-time alarm information sets based on the alarm analysis model and generating operation and maintenance instructions based on the analysis results include: Receive real-time alarm information from each power station and construct a real-time alarm information set for the corresponding power station, wherein the real-time alarm information set includes real-time alarm equipment, real-time alarm data, real-time alarm time, and real-time alarm urgency; Input the real-time alarm information set into the alarm analysis model to obtain the predicted alarm level of the corresponding power station, the corresponding prediction credibility label and the predicted operation and maintenance measures; Generate a corrected alarm level for the corresponding power station based on the predicted alarm level and the corresponding prediction credibility label; Sorting all power plants according to their corrected alarm levels, and generating an operation and maintenance sequence based on the sorting results, wherein the operation and maintenance sequence includes a number of power plants to be operated and maintained and predicted operation and maintenance measures for the power plants to be operated and maintained; Forecast the operation and maintenance time for each power station to be operated and maintained, and set the operation and maintenance waiting time for the next adjacent power station to be operated and maintained according to the prediction results; Generate operation and maintenance instructions based on the operation and maintenance sequence and operation and maintenance waiting time.

[0025] In some embodiments of the present application, setting an information collection strategy for a power station to be operated and maintained includes: Presetting a number of change evaluation indicators and a number of equipment evaluation indicators; Calculate the similarity between the real-time alarm information set and the historical alarm information of each power station to be operated and maintained, and filter out similar alarm information based on the similarity; The historical collection time is set based on the operation and maintenance waiting time of each power station to be operated and maintained, a number of similar alarm information in the historical inspection time is collected, and a number of change evaluation indicators and reference evaluation values of a number of equipment evaluation indicators are generated; Generate a collection evaluation value corresponding to the power station to be operated and maintained based on a number of reference evaluation values; The calculation formula of the acquisition evaluation value is: ; Among them, P is the collection evaluation value, a1 is the weight coefficient of the reference evaluation value of several change evaluation indicators, p1 is the first collection evaluation conversion coefficient, a2 is the weight coefficient of the reference evaluation value of several equipment evaluation indicators, p2 is the second collection evaluation conversion coefficient, n1 is the number of change evaluation indicators, is the reference evaluation value of the i1th change evaluation index, is the weight coefficient of the i1th change evaluation index, n2 is the number of equipment evaluation indicators, is the reference evaluation value of the i2th equipment evaluation index, is the weight coefficient of the i2th equipment evaluation index; An information collection strategy for the power station to be operated and maintained is set according to the collection evaluation value of each power station to be operated and maintained. The information collection strategy includes the amount of information collected and the time interval between collection time nodes.

[0026] In this embodiment, the change evaluation indicators include but are not limited to the change frequency, change degree, change value and the degree to which the corresponding modified alarm level is changed of similar alarm information of multiple real-time alarm information of the power station to be operated and maintained during the operation and maintenance waiting time.

[0027] In this embodiment, the equipment evaluation indicators include but are not limited to the importance of the real-time alarm equipment, the number of associated equipment, the impact of the fault caused by the real-time alarm content, the frequency of faults of the associated equipment, and other indicators.

[0028] In this embodiment, similar alarm information refers to information whose similarity with the real-time alarm content and real-time alarm equipment in the real-time alarm information is greater than a preset similarity threshold. By obtaining similar alarm information in the historical collection time, the frequency of information changes and the degree of influence of equipment failures in the power station to be operated and maintained during the operation and maintenance waiting time are predicted, that is, the collection evaluation value. When the reference evaluation values of several change evaluation indicators and the reference evaluation values of several equipment evaluation indicators are larger, it means that the frequency of information changes and the degree of influence of equipment failures are greater, and the collection evaluation value is larger, and vice versa.

[0029] In this embodiment, the first acquisition conversion coefficient and the second acquisition conversion coefficient refer to the reference evaluation value of the change evaluation index and the reference evaluation value of the equipment evaluation index converted into numerical values of the same dimension as the acquisition evaluation value. When the more reference evaluation values of the change evaluation index and the larger the reference evaluation value of the equipment evaluation index, the larger the corresponding acquisition evaluation value, and vice versa.

[0030] In this embodiment, when the collection evaluation value is larger, the time interval of the collection time node in the information collection strategy is shorter and the amount of information collected is larger. On the contrary, by dynamically setting the information collection strategy of each power station to be operated and maintained, the amount of information collected is reduced and the efficiency of information collection is improved while ensuring the accuracy of alarm information collection, thereby improving the overall operation and maintenance rationality and efficiency of multiple power stations.

[0031] In some embodiments of the present application, an information collection strategy for a power station to be operated and maintained is set according to the collection evaluation value of each power station to be operated and maintained, including: Presetting a first preset collection evaluation value interval, a second preset collection evaluation value interval, a third preset collection evaluation value interval and a fourth preset collection evaluation value interval; When the collection evaluation value of the power station to be operated and maintained is within the first preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the first preset collection amount, and the time interval between the collection time nodes is set to the fourth preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the second preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the second preset collection amount, and the time interval between the collection time nodes is set to the third preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the third preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the third preset collection amount, and the time interval between the collection time nodes is set to the second preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the fourth preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the fourth preset collection amount, and the time interval between the collection time nodes is set to the first preset time interval; Calculating the weight coefficient of each real-time alarm data in the real-time alarm information of the power station to be operated and maintained, sorting the real-time alarm data according to the weight coefficient, and obtaining a real-time alarm data sequence; The data to be collected in the real-time alarm data sequence is filtered according to the information collection quantity in the information collection strategy of each power station to be operated and maintained, and the data to be collected is collected according to the time interval between the collection time nodes to obtain the real-time information change characteristics of the corresponding power station to be operated and maintained during the operation and maintenance waiting time.

[0032] In this embodiment, the first preset collection evaluation value interval < the second preset collection evaluation value interval < the third preset collection evaluation value interval < the fourth preset collection evaluation value interval, the first preset collection amount < the second preset collection amount < the third preset collection amount < the fourth preset collection amount, and the first preset time interval < the second preset time interval < the third preset time interval < the fourth preset time interval.

[0033] In this embodiment, when the collection evaluation value is larger, it means that the frequency of information changes and the impact of equipment failure are greater, so the time interval of the collection time nodes in the information collection strategy is shorter and the amount of information collected is greater, and vice versa.

[0034] In this embodiment, the information collection strategy for each power station to be operated and maintained is generated by calculating the collection evaluation value, thereby improving the accuracy and efficiency of information collection, laying the foundation for the subsequent calculation of the change risk value of each power station to be operated and maintained, and improving the rationality of operation and maintenance.

[0035] In some embodiments of the present application, before generating the change risk value of the power station to be operated and maintained according to the real-time information change characteristics, the method further includes: The real-time information change characteristics include the change trend, change rate and change value of several data to be collected; Generate a change coefficient for the corresponding data to be collected according to the change trend, change rate and change value of each data to be collected, and obtain the absolute value of the change coefficient; Pre-set coefficient of variation threshold; If the absolute value of the coefficient of variation of the data to be collected is greater than the coefficient of variation threshold, a number of associated data corresponding to the data to be collected are screened out, and a set of associated data corresponding to the data to be collected is constructed; Collect the real-time data of each associated data in the associated data set at the corresponding collection node and input it into the alarm analysis model to obtain the predicted alarm level and prediction credibility label of the corresponding associated data, and generate the corrected alarm level of the corresponding associated data; A selection coefficient of a variation coefficient corresponding to the data to be collected is generated according to the number of associated data in the associated data set whose modified alarm levels are greater than the modified alarm levels of the corresponding data to be collected and the difference in the modified levels.

[0036] In this embodiment, when the fluctuation degree of the change trend is large, the change rate is faster and the change value is larger, the corresponding change coefficient is larger, and vice versa. The change coefficient is positive or negative and is set according to the change trend. When the change trend is slow, slightly fluctuating, or drastically fluctuating up / down, the change coefficient is positive / negative.

[0037] In this embodiment, the selection coefficient has a value range of (0.75, 1.25), and the more the number of times the corrected alarm level of the associated data is greater than the corrected alarm level of the corresponding data to be collected and the greater the difference in the corrected levels, the smaller the corresponding selection coefficient, and vice versa.

[0038] In this embodiment, associated data refers to data that changes as the data to be collected changes. By calculating the corrected alarm level of the associated data, it is determined whether there is other alarm information or whether the alarm level has changed during the operation and maintenance waiting time of the power station to be operated and maintained, so as to appropriately adjust the operation and maintenance waiting time and the operation and maintenance sequence, thereby improving the operation and maintenance efficiency and operation and maintenance costs.

[0039] In some embodiments of the present application, generating a change risk value of a power station to be operated and maintained based on the real-time information change characteristics includes: Classify the variation coefficients of several data to be collected for the same power station to be operated and maintained, and obtain a set of positive variation coefficients, a set of negative variation coefficients, and a set of no variation coefficients; Generate a change risk value for the power station to be operated and maintained based on the number of positive change coefficient sets, the number of negative change coefficient sets, the number of no change coefficient sets, the weight coefficient of the data to be collected in the negative change coefficient set, the corresponding change coefficient, and the selection coefficient; The calculation formula of the change risk value is: ; Among them, F is the change risk value, m2 is the number of negative change coefficient sets, m1 is the number of positive change coefficient sets, and m3 is the number of no change coefficient sets. is the first weight coefficient, w2 is the second weight coefficient, f1 is the first change risk conversion coefficient, f2 is the second change risk conversion coefficient, is the selection coefficient of the sth data to be collected in the positive variation coefficient set, is the difference between the absolute value of the variation coefficient of the sth data to be collected and the variation coefficient threshold, q1s is the weight coefficient of the sth data to be collected, is the selection coefficient of the vth data to be collected in the negative variation coefficient set, is the difference between the absolute value of the variation coefficient of the vth data to be collected and the variation coefficient threshold, and q2v is the weight coefficient of the vth data to be collected.

[0040] In this embodiment, the positive change coefficient set refers to a set of data to be collected whose change coefficient is positive, the no change coefficient set refers to a set of data to be collected whose change coefficient approaches 0, and the negative change coefficient set refers to a set of data to be collected whose change trend is negative.

[0041] In this embodiment, when When ≤0, 1. When 0 o'clock, ,when When ≤0, 1. When 0 o'clock, .

[0042] In this embodiment, the first change risk conversion coefficient refers to converting the change coefficient, weight coefficient and corresponding selection coefficient of each data to be collected in the positive change coefficient set into a numerical value of the same dimension as the change risk value; the second change risk conversion coefficient refers to converting the change coefficient, weight coefficient and corresponding selection coefficient of each data to be collected in the negative change coefficient set into a numerical value of the same dimension as the change risk value. When the change coefficient, weight coefficient and selection coefficient of each data to be collected in the positive change coefficient set are larger, and the change coefficient, weight coefficient and selection coefficient of each data to be collected in the negative change coefficient set are larger, the corresponding change risk value is larger, and vice versa.

[0043] In some embodiments of the present application, determining whether to modify the operation and maintenance instruction includes: Generating a compensation coefficient for the revised alarm level corresponding to the power station to be operated and maintained according to the change risk value, and re-correcting the revised alarm level according to the compensation coefficient to obtain a secondary revised alarm level; Generate the secondary revised alarm level of each power station to be operated and maintained in sequence; Compare the secondary correction alarm levels of multiple power plants to be operated and maintained, and determine whether to adjust the operation and maintenance sequence based on the comparison results. If so, modify the operation and maintenance instructions based on the adjustment results.

[0044] In this embodiment, by calculating the change risk value in the operation and maintenance waiting time, the foundation is laid for the subsequent continuous correction of the alarm level according to the change risk value, thereby realizing the subsequent continuous adjustment of the operation and maintenance sequence and improving the rationality and efficiency of operation and maintenance.

[0045] In some embodiments of the present application, Figure 2 As shown, a real-time monitoring and alarm method for power station operation and maintenance is also included: Step S201: construct multiple alarm level-information mapping tables, and establish an alarm analysis model based on all alarm level-information mapping tables; Step S202: obtaining a real-time alarm information set of each power station, generating analysis results of all real-time alarm information sets based on an alarm analysis model, and generating operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; Step S203: Set an information collection strategy for the power plant to be operated and maintained, obtain real-time information change characteristics of the power plant to be operated and maintained based on the information collection strategy, generate a change risk value of the power plant to be operated and maintained according to the real-time information change characteristics, and determine whether to modify the operation and maintenance instructions.

[0046] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A real-time monitoring and alarm system for power station operation and maintenance, characterized in that: include: A construction module is used to construct multiple alarm level-information mapping tables and establish an alarm analysis model based on all alarm level-information mapping tables; An analysis module is configured to obtain a real-time alarm information set for each power station, generate analysis results of all real-time alarm information sets based on an alarm analysis model, and generate operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; The judgment module is used to set the information collection strategy of the power station to be operated and maintained, obtain the real-time information change characteristics of the power station to be operated and maintained based on the information collection strategy, generate the change risk value of the power station to be operated and maintained according to the real-time information change characteristics, and judge whether to modify the operation and maintenance instructions.

2. The power plant operation and maintenance real-time monitoring and alarm system according to claim 1, characterized in that: Construct multiple alarm level-feature information mapping tables, including: Pre-set several alarm levels; Obtain historical alarm information of each alarm level based on the historical alarm log of each power station, wherein the historical alarm information includes historical alarm data, historical alarm device, historical alarm time, and historical alarm urgency; According to the accuracy of historical alarms in historical alarm logs, the corresponding historical alarm information is divided into high-accuracy alarm information, medium-accuracy alarm information and low-accuracy alarm information, and mapped with corresponding historical credibility labels and corresponding historical operation and maintenance measures respectively; Construct an alarm level-information mapping table for each alarm level by combining the high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each alarm level of each power station with the mapped historical credibility labels and historical operation and maintenance measures; The high-accuracy alarm information, medium-accuracy alarm information, and low-accuracy alarm information of each power plant corresponding to all alarm levels in the all alarm level-information mapping table are used as the training input dataset, and the mapped alarm levels, historical credibility labels, and historical operation and maintenance measures are used as the training output dataset; The neural network is trained based on the training input data set and the training output data set to obtain an alarm analysis model.

3. The power plant operation and maintenance real-time monitoring and alarm system according to claim 2, characterized in that: Generate analysis results of all real-time alarm information sets based on the alarm analysis model, and generate operation and maintenance instructions based on the analysis results, including: Receive real-time alarm information from each power station and construct a real-time alarm information set for the corresponding power station, wherein the real-time alarm information set includes real-time alarm equipment, real-time alarm data, real-time alarm time, and real-time alarm urgency; Input the real-time alarm information set into the alarm analysis model to obtain the predicted alarm level of the corresponding power station, the corresponding prediction credibility label and the predicted operation and maintenance measures; Generate a corrected alarm level for the corresponding power station based on the predicted alarm level and the corresponding prediction credibility label; Sorting all power plants according to their corrected alarm levels, and generating an operation and maintenance sequence based on the sorting results, wherein the operation and maintenance sequence includes a number of power plants to be operated and maintained and predicted operation and maintenance measures for the power plants to be operated and maintained; Forecast the operation and maintenance time for each power station to be operated and maintained, and set the operation and maintenance waiting time for the next adjacent power station to be operated and maintained according to the prediction results; Generate operation and maintenance instructions based on the operation and maintenance sequence and operation and maintenance waiting time.

4. The power plant operation and maintenance real-time monitoring and alarm system according to claim 3, characterized in that: Set up information collection strategies for power plants to be operated and maintained, including: Presetting a number of change evaluation indicators and a number of equipment evaluation indicators; Calculate the similarity between the real-time alarm information set and the historical alarm information of each power station to be operated and maintained, and filter out similar alarm information based on the similarity; The historical collection time is set based on the operation and maintenance waiting time of each power station to be operated and maintained, a number of similar alarm information in the historical inspection time is collected, and a number of change evaluation indicators and reference evaluation values of a number of equipment evaluation indicators are generated; Generate a collection evaluation value corresponding to the power station to be operated and maintained based on a number of reference evaluation values; The calculation formula of the acquisition evaluation value is: ； Among them, P is the collection evaluation value, a1 is the weight coefficient of the reference evaluation value of several change evaluation indicators, p1 is the first collection evaluation conversion coefficient, a2 is the weight coefficient of the reference evaluation value of several equipment evaluation indicators, p2 is the second collection evaluation conversion coefficient, n1 is the number of change evaluation indicators, is the reference evaluation value of the i1th change evaluation index, is the weight coefficient of the i1th change evaluation index, n2 is the number of equipment evaluation indicators, is the reference evaluation value of the i2th equipment evaluation index, is the weight coefficient of the i2th equipment evaluation index; An information collection strategy for the power station to be operated and maintained is set according to the collection evaluation value of each power station to be operated and maintained. The information collection strategy includes the amount of information collected and the time interval between collection time nodes.

5. The power plant operation and maintenance real-time monitoring and alarm system according to claim 4, characterized in that: According to the collection evaluation value of each power station to be operated and maintained, the information collection strategy for the corresponding power station to be operated and maintained is set, including: Presetting a first preset collection evaluation value interval, a second preset collection evaluation value interval, a third preset collection evaluation value interval and a fourth preset collection evaluation value interval; When the collection evaluation value of the power station to be operated and maintained is within the first preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the first preset collection amount, and the time interval between the collection time nodes is set to the fourth preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the second preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the second preset collection amount, and the time interval between the collection time nodes is set to the third preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the third preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the third preset collection amount, and the time interval between the collection time nodes is set to the second preset time interval; When the collection evaluation value of the power station to be operated and maintained is within the fourth preset collection evaluation value interval, the information collection amount in the information collection strategy is set to the fourth preset collection amount, and the time interval between the collection time nodes is set to the first preset time interval; Calculating the weight coefficient of each real-time alarm data in the real-time alarm information of the power station to be operated and maintained, sorting the real-time alarm data according to the weight coefficient, and obtaining a real-time alarm data sequence; The data to be collected in the real-time alarm data sequence is filtered according to the information collection quantity in the information collection strategy of each power station to be operated and maintained, and the data to be collected is collected according to the time interval between the collection time nodes to obtain the real-time information change characteristics of the corresponding power station to be operated and maintained during the operation and maintenance waiting time.

6. The power plant operation and maintenance real-time monitoring and alarm system according to claim 5, characterized in that: Before generating the change risk value of the power station to be operated and maintained based on the real-time information change characteristics, the following steps are also included: The real-time information change characteristics include the change trend, change rate and change value of several data to be collected; Generate a change coefficient for the corresponding data to be collected according to the change trend, change rate and change value of each data to be collected, and obtain the absolute value of the change coefficient; Pre-set coefficient of variation threshold; If the absolute value of the coefficient of variation of the data to be collected is greater than the coefficient of variation threshold, a number of associated data corresponding to the data to be collected are screened out, and a set of associated data corresponding to the data to be collected is constructed; Collect the real-time data of each associated data in the associated data set at the corresponding collection node and input it into the alarm analysis model to obtain the predicted alarm level and prediction credibility label of the corresponding associated data, and generate the corrected alarm level of the corresponding associated data; A selection coefficient of a variation coefficient corresponding to the data to be collected is generated according to the number of associated data in the associated data set whose modified alarm levels are greater than the modified alarm levels of the corresponding data to be collected and the difference in the modified levels.

7. The power plant operation and maintenance real-time monitoring and alarm system according to claim 6, characterized in that: Generate the risk value of the power plant to be operated and maintained based on the real-time information change characteristics, including: Classify the variation coefficients of several data to be collected for the same power station to be operated and maintained, and obtain a set of positive variation coefficients, a set of negative variation coefficients, and a set of no variation coefficients; Generate a change risk value for the power station to be operated and maintained based on the number of positive change coefficient sets, the number of negative change coefficient sets, the number of no change coefficient sets, the weight coefficient of the data to be collected in the negative change coefficient set, the corresponding change coefficient, and the selection coefficient; The calculation formula of the change risk value is: ； Among them, F is the change risk value, m2 is the number of negative change coefficient sets, m1 is the number of positive change coefficient sets, and m3 is the number of no change coefficient sets. is the first weight coefficient, w2 is the second weight coefficient, f1 is the first change risk conversion coefficient, f2 is the second change risk conversion coefficient, is the selection coefficient of the sth data to be collected in the positive variation coefficient set, is the difference between the absolute value of the variation coefficient of the sth data to be collected and the variation coefficient threshold, q1s is the weight coefficient of the sth data to be collected, is the selection coefficient of the vth data to be collected in the set of negative variation coefficients, is the difference between the absolute value of the variation coefficient of the vth data to be collected and the variation coefficient threshold, and q2v is the weight coefficient of the vth data to be collected.

8. The power plant operation and maintenance real-time monitoring and alarm system according to claim 7, characterized in that: Determine whether to modify the operation and maintenance instructions, including: Generating a compensation coefficient for the revised alarm level of the power station to be operated and maintained according to the change risk value, and re-correcting the revised alarm level according to the compensation coefficient to obtain a secondary revised alarm level; Generate the secondary revised alarm level of each power station to be operated and maintained in sequence; Compare the secondary correction alarm levels of multiple power plants to be operated and maintained, and determine whether to adjust the operation and maintenance sequence based on the comparison results. If so, modify the operation and maintenance instructions based on the adjustment results.

9. A real-time monitoring and alarm method for power station operation and maintenance, characterized in that: include: Construct multiple alarm level-information mapping tables, and establish an alarm analysis model based on all alarm level-information mapping tables; Obtaining a real-time alarm information set for each power station, generating analysis results of all real-time alarm information sets based on an alarm analysis model, and generating operation and maintenance instructions based on the analysis results, wherein the operation and maintenance instructions include an operation and maintenance sequence and an operation and maintenance waiting time; An information collection strategy for the power plant to be operated and maintained is set, and based on the information collection strategy, real-time information change characteristics of the power plant to be operated and maintained are obtained. A change risk value of the power plant to be operated and maintained is generated according to the real-time information change characteristics, and it is determined whether the operation and maintenance instructions should be modified.

Images