Hydroelectric generating set health state assessment method and device and computer readable storage medium

Abstract

The invention relates to a hydroelectric generating set health state assessment method and device and a computer readable storage medium, and the method comprises the steps: obtaining the measurement point data of a plurality of monitoring points in the operation condition of any one hydroelectric generating set, analyzing the measurement point data through a measurement point scoring model, and obtaining a measurement point score, the measurement point scores represent health states of different monitoring points of the hydroelectric generating set under the current operation condition; according to the cooperative relation between the monitoring points, correlation analysis is carried out on all the monitoring point scores through a preset machine algorithm, a unit score is obtained, and the unit score represents the health state of the unit component; in any time of operation of the hydroelectric generating set, a historical comprehensive score of the hydroelectric generating set is obtained, according to a preset weight, the historical comprehensive score and the current comprehensive score are combined to obtain a final comprehensive score, the comprehensive score represents the overall health state of the hydroelectric generating set, and the historical comprehensive score is determined by a set score; and constructing a hydroelectric generating set health model based on the measurement point score, the set score and the comprehensive score, and determining the health state of the hydroelectric generating set according to the hydroelectric generating set health model. Through the method and the device, the health state of the hydroelectric generating set is scored, and the health state of the hydroelectric generating set is obtained.

Description

Technical Field

[0001] The present application relates to the field of hydropower unit monitoring, and in particular to a method, device and computer-readable storage medium for evaluating the health status of a hydropower unit. Background Art

[0002] Hydropower units have the characteristics of fast startup and flexible adjustment. Therefore, in the construction of new power systems, the flexibility of hydropower units will be used to adjust the supply and demand balance of the power system. However, the frequent start and stop and operating condition adjustment of hydropower units will affect the health of hydropower units. Therefore, power plants often overhaul hydropower units after they are shut down.

[0003] The health status of the hydropower unit can be judged, and then the staff can determine whether to overhaul the hydropower unit according to the health status. Therefore, how to accurately evaluate the health status of the hydropower unit has become an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a method, device and computer-readable storage medium for evaluating the health status of a hydropower unit, so as to at least solve the problem of how to accurately evaluate the health status of a hydropower unit in the related art.

[0005] In a first aspect, an embodiment of the present application provides a method for evaluating the health status of a hydropower unit, comprising:

[0006] According to the actual operating power of the hydropower unit, the operating conditions of the hydropower unit are divided. In any operating condition, the measuring point data of several monitoring points in the hydropower unit are obtained. According to the measuring point data, the measuring point score is obtained through the measuring point scoring model. The measuring point score represents the health status of different monitoring points of the hydropower unit under the current operating condition.

[0007] Through the preset machine algorithm, all the test point scores are correlated and analyzed to obtain the unit score, which represents the health status of the unit components;

[0008] During any operation of a hydropower unit, the historical comprehensive score of the hydropower unit is obtained, and the current comprehensive score is determined based on the current comprehensive score of the hydropower unit and the historical comprehensive score. The comprehensive score represents the overall health status of the hydropower unit, and the historical comprehensive score is determined by the unit score.

[0009] Based on the measuring point scores, unit scores and comprehensive scores, a hydropower unit health model is constructed, and the health status of the hydropower unit is determined according to the hydropower unit health model.

[0010] In one embodiment, the measurement point scoring model includes an interval scoring model, an abnormal change evaluation model, and an abnormality detection model. According to the measurement point data, the measurement point score is obtained by the measurement point scoring model, including:

[0011] Get historical measurement point data and the type of measurement point data, including fixed value type and mutation type;

[0012] If the measured point data is of fixed numerical type, a preset interval is obtained. In the interval scoring model, if the measured point data is within the preset interval, a full score is obtained for the measured point. If the measured point data is not within the preset interval, the full score is deducted according to the distance that the measured point data deviates from the preset interval to obtain the measured point score.

[0013] If the measured point data is of mutation type, in the abnormal change evaluation model, the difference between the measured point data and the historical measured point data is obtained, the difference is compared with the preset threshold, and points are deducted according to the gap between the difference and the preset threshold to determine the measuring point score.

[0014] According to the historical measurement point data, the long short-term memory network algorithm is used to determine the abnormal measurement points in the hydropower unit and obtain the measurement point score of each measurement point

[0015] In one embodiment, in the interval scoring model, if the measurement point data is within a preset interval, a full score measurement point score is obtained, which also includes:

[0016] Obtaining a physical threshold, which represents the upper limit of data obtained by monitoring points in a hydropower unit subject to physical condition monitoring;

[0017] In the interval scoring model, if the measurement point data is within the preset interval and the measurement point data is greater than the physical threshold, a measurement point score of zero is obtained;

[0018] If the measurement point data is within the preset range and the measurement point data is less than or equal to the physical threshold, a full score is obtained for the measurement point.

[0019] In one embodiment, according to the collaborative relationship between the monitoring points, a correlation analysis is performed on the scores of all the monitoring points through a preset machine algorithm to obtain a unit score, including:

[0020] The scores of all measuring points and the expert experience of the expert system are input into the aggregation model, and the correlation analysis of all measuring points is performed to obtain the unit score.

[0021] In one embodiment, the historical unit score of the hydropower unit is obtained, and in any operation of the hydropower unit, the comprehensive score of the hydropower unit is determined according to the unit score of the current unit and the historical unit score, including:

[0022] If the hydropower unit is operating for the first time, the current unit score will be used as the comprehensive score of the hydropower unit;

[0023] If the hydropower unit is not the first to be operated, the historical unit score of the hydropower unit is obtained. During any operation of the hydropower unit, the previous historical unit score and the current unit score are combined through the exponentially weighted moving average algorithm to obtain a comprehensive score;

[0024] The exponentially weighted moving average algorithm satisfies the following formula:

[0025] S new =α×S current +(1α)×S history

[0026] Among them, S new is the updated comprehensive score, S current is the current rating, S history is the historical score, and α is the weight coefficient.

[0027] In one embodiment, after obtaining the comprehensive score, the method further includes:

[0028] When the hydropower unit is overhauled, the measuring point score, unit score and comprehensive score are cleared.

[0029] In one embodiment, the operating conditions include a startup condition, a stable condition, a variable load condition, and a shutdown condition, and the operating conditions satisfy the following configurations:

[0030] The startup condition satisfies the requirement that the power of the hydropower unit increases from 0 to stable power. Stable power means that the power does not change within any period of time.

[0031] The stable operating condition satisfies that the power change of the hydropower unit is less than the preset change threshold;

[0032] Variable load conditions meet the frequent power changes of hydropower units;

[0033] The shutdown condition satisfies the requirement that the power of the hydropower unit gradually decreases until the power reaches 0.

[0034] In a second aspect, an embodiment of the present application provides a device for evaluating the health status of a hydropower unit, comprising:

[0035] The measuring point scoring module divides the operating conditions of the hydropower unit according to the actual operating power of the hydropower unit. In any operating condition, the measuring point data of several monitoring points in the hydropower unit are obtained. Based on the measuring point data, the measuring point score is obtained through the measuring point scoring model. The measuring point score represents the health status of different components of the hydropower unit under the current operating condition.

[0036] A unit scoring module performs correlation analysis on the scores of all the monitoring points through a preset machine algorithm according to the collaborative relationship between the monitoring points to obtain a unit score;

[0037] A comprehensive scoring module, in any operation of a hydropower unit, obtains a historical comprehensive score of the hydropower unit, and combines the historical comprehensive score with the current comprehensive score according to a preset weight to obtain a final comprehensive score, wherein the comprehensive score represents the overall health status of the hydropower unit, and the historical comprehensive score is determined by the unit score;

[0038] The unit health module constructs a hydropower unit health model based on the measurement point score, the unit score and the comprehensive score, and determines the health status of the hydropower unit according to the hydropower unit health model.

[0039] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for assessing the health status of a hydropower unit as described in the first aspect above is implemented.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for assessing the health status of a hydropower unit as described in the first aspect above.

[0041] The hydropower unit health status assessment method, device and computer-readable storage medium provided in the embodiments of the present application have at least the following technical effects.

[0042] The measuring point score, unit score and comprehensive score correspond to the three levels of unit components and overall unit respectively, and the health status of the hydropower unit is judged according to the comprehensive score. In the process of determining the health status of the hydropower unit, it is dynamically determined based on the measuring point score, unit score and historical score in each hydropower unit operation process, so that the hydropower unit can be scored accurately, and the health status of the hydropower unit can be judged according to the score.

[0043] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 is a flow chart of a method for evaluating the health status of a hydropower unit according to an exemplary embodiment;

[0046] Figure 2 is a flow chart of obtaining a measurement point score according to an exemplary embodiment;

[0047] Figure 3 is a flow chart of a method for evaluating the health status of a hydropower unit according to another exemplary embodiment;

[0048] Figure 4 is a block diagram of a device for evaluating the health status of a hydropower unit according to an exemplary embodiment;

[0049] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0051] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0052] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0053] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0054] In a first aspect, an embodiment of the present application provides a method for evaluating the health status of a hydropower unit. Figure 1 is a flow chart of a method for evaluating the health status of a hydropower unit according to an exemplary embodiment. Figure 1 As shown in the figure, the health status assessment method of hydropower unit includes:

[0055] Step S101: in the operating condition of any hydropower unit, obtain the measuring point data of several monitoring points, and analyze the measuring point data through a measuring point scoring model to obtain the measuring point scores, wherein the measuring point scores represent the health status of different monitoring points of the hydropower unit under the current operating condition.

[0056] In the operation of any hydropower unit, the operating conditions of the hydropower unit are divided according to the actual operating power of the hydropower unit. The operating conditions include startup conditions, stable conditions, variable load conditions and shutdown conditions. Among them, the startup condition satisfies the operating power of the hydropower unit rising from 0 to a stable power, and the stable power is that the operating power of the hydropower unit does not change within any period of time. The stable condition satisfies the operating power change of the hydropower unit less than the preset change threshold. It should be noted that the stable condition includes medium and low load conditions, medium load conditions and rated conditions. If the hydropower unit operates at 40% to 60% of the rated power, it is a medium and low load condition, if the hydropower unit operates at 60% to 80% of the rated power, it is a medium load condition, and if the hydropower unit operates at 80% to 105% of the rated power, it is a rated condition. The variable load condition satisfies the frequent changes in the operating power of the hydropower unit, that is, the operating power of the hydropower unit neither stops nor reaches a stable power. The shutdown condition satisfies the requirement that the operating power of the hydropower unit gradually decreases until the operating power drops to 0.

[0057] By dividing the different operating conditions according to the real-time power of the hydropower unit and dynamically monitoring the operating data of the unit, it is possible to quickly and accurately identify the different operating states of the hydropower unit and record its data, providing reliable data support for the subsequent scoring and feature presentation of the hydropower unit.

[0058] Since the data characteristics of each operating condition are different, for each operating condition, the point data of several monitoring points are obtained. For example, for the startup condition, the rising data and the stable time in the point data are obtained. For the stable condition, the mean and variance of the point data are obtained. For the variable load condition, the data with obvious fluctuations in the point data and the changing trend of the point data are obtained. For the shutdown condition, the speed at which the point data decreases is obtained. By obtaining the data characteristics in each condition, the health status of the hydropower unit under different conditions can be preliminarily judged, so that the scoring system can more flexibly adapt to the changes in the hydropower unit, thereby providing a more accurate score.

[0059] Sensors are set on the hydropower unit, and each sensor serves as a monitoring point. The sensors are used to monitor the data during the operation of the hydropower unit. Optionally, the monitored data include temperature, pressure, and vibration data of the hydropower unit. According to the obtained measuring point data, the measuring point score is obtained through the measuring point scoring model. Among them, the measuring point score characterizes the health status of the monitoring point of the hydropower unit. According to the size of the measuring point score, it can be judged whether the monitoring point has a fault. The measuring point score ranges from 0 to 100, and 100 means that the hydropower unit is running just right and in good health. The lower the measuring point score, the more abnormal the measuring point is. If the measuring point score is lower than the preset scoring threshold, it means that the monitoring point has a fault. If the measuring point score is higher than the preset scoring threshold, it means that the hydropower unit can operate normally and the health status of the monitoring point is good.

[0060] The measurement point scoring model specifically includes the interval scoring model, the abnormal change evaluation model and the anomaly detection model. The measurement point scores obtained through the measurement point scoring model specifically include:

[0061] The historical measuring point data and the type of measuring point data of the hydropower unit are obtained. The types of measuring point data include fixed value type, that is, the value of the measuring point data of the fixed value type does not change, and mutation type, that is, the measuring point data of the mutation type changes greatly and frequently.

[0062] For different types of measuring point data, different measuring point scoring models are selected to obtain measuring point scores. If the measuring point data is of fixed value type, the measuring point score is obtained through the interval scoring model. The preset interval of the interval evaluation model is obtained, wherein the preset interval includes the normal interval, the abnormal interval and the over-limit interval. The over-limit interval includes the abnormal interval, and the abnormal interval includes the normal interval. When the value of the measuring point data is within the normal interval, the measuring point score of the current measuring point data is full marks. If the measuring point data exceeds the normal interval and is in the abnormal interval, the points are subtracted according to the distance that the measuring point data deviates from the normal interval to obtain the measuring point score of the current measuring point data. And the farther the measuring point data deviates from the normal interval, the greater the subtracted points. If the value of the measuring point data is outside the over-limit interval, the current measuring data is abnormal data, and the current measuring point data does not participate in the evaluation. For example, the range of the over-limit interval is [0, 100], the range of the normal interval is [20, 60], and the range of the abnormal interval is [10, 90]. If the measuring point data is within the normal interval, the measuring point score is full marks. If the data of the measuring point is within the abnormal interval, the measuring point score is obtained according to the measuring point scoring formula. If the data of the measuring point is within the range of [0, 100], the data of the measuring point will not be included in the scoring.

[0063] In the interval scoring model, if the measurement point data is outside the normal interval range and within the abnormal interval range, the measurement point score is obtained through the evaluation formula, where the evaluation formula satisfies the following formula:

[0064]

[0065] Among them, Score1 is the score of the measurement point, Point_value is the measurement point data, normal_range is the margin value of the normal interval, and max_normal is the margin value of the abnormal interval. It should be noted that the abnormal interval is the maximum range of the measurement point data that can be obtained by the monitoring point.

[0066] In one embodiment, Figure 2 is a flow chart of obtaining a measurement point score according to an exemplary embodiment. Figure 2 As shown, obtain the measurement point data. If the measurement point data is not within the normal interval and the measurement point data is greater than the upper limit of the normal interval, then in the scoring formula, the margin value of the normal interval is taken as the upper limit of the normal interval, and the margin value of the abnormal interval is taken as the upper limit of the abnormal interval, and the measurement point score is obtained. If the measurement point data is not within the normal interval and the measurement point data is less than the lower limit of the normal interval, then in the scoring formula, the margin value of the normal interval is taken as the lower limit of the normal interval, and the margin value of the abnormal interval is taken as the lower limit of the abnormal interval, and the measurement point score is obtained. If the measurement point data is within the normal interval, the measurement point score is full marks.

[0067] In the interval scoring model, the scoring of the measurement points that obtain full marks also needs to consider the limitations of the physical conditions of the corresponding monitoring points. Therefore, the threshold scoring model is introduced in the interval scoring model. In the threshold scoring model, the physical threshold is obtained. The physical threshold is the upper limit of the data obtained by the monitoring point of the hydropower unit subject to physical condition monitoring. If the measurement point data is within the preset interval and the measurement point data is greater than the physical threshold, it means that the current monitoring data exceeds the constraints of the physical conditions, so the measurement point score is 0. If the measurement point data is within the normal interval and the measurement point data is less than or equal to the physical threshold, it means that the current monitoring data is within the constraints of the physical conditions, so the measurement point score is full marks. The scoring formula for obtaining the measurement point score in the threshold scoring model satisfies the following formula:

[0068]

[0069] Among them, Score is the test point score.

[0070] If the measurement point data is of mutation type, the measurement point score is obtained through the abnormal change model. The abnormal change model mainly focuses on the measurement point data of jump and mutation. The mutation data is compared with the historical data. If the change range of the measurement point data of mutation and jump exceeds the preset threshold, the measurement point score is deducted, including:

[0071] Obtain the difference between the measured point data and the historical measured point data. On the basis of the full score, deduct points according to the difference between the difference and the preset threshold. The greater the difference between the difference and the preset threshold, the more points will be deducted. If the difference between the difference and the preset threshold is smaller, the deduction will be less. The evaluation formula of the abnormal change evaluation model satisfies the following formula:

[0072]

[0073] Among them, Score is the measurement point score, Point_value is the current measurement point data, historical_average is the average of the historical measurement point scores, and tolerance is the preset threshold.

[0074] For measuring points or equipment in hydropower units that frequently experience abnormal conditions, the LSTM model is used to score the measuring points. In the LSTM model, the long short-term memory network algorithm is used to monitor and analyze the operating status data of the hydropower unit. The LSTM model includes memory units and gating mechanisms. The gating mechanism includes input gates, forget gates, and output gates. Through memory units and gating mechanisms, the memory ability of long-term dependencies can be maintained, so that abnormalities in the operation of the hydropower unit can be identified, and a measuring point score can be generated for each measuring point or equipment. The LSTM model for measuring point scoring specifically includes:

[0075] The input layer is used to receive the time series data of the hydropower unit. Each time series data includes data features of multiple dimensions. For example, a data storage data includes the vibration data, temperature and power of the hydropower unit.

[0076] The LSTM layer is used to extract features. It uses memory cells to capture feature information over a period of time and predicts the future operating status of the hydropower unit based on the measurement point data at the current time point. Based on the multi-layer stacked LSTM grid structure, deep features are gradually proposed.

[0077] The fully connected layer is used to map the features extracted by the LSTM layer to a specific score. The score obtained in the fully connected layer represents the health status of the unit at the current time point.

[0078] The output layer is used to output the measurement point score. The value range of the measurement point score is 0 to 100. The higher the measurement point score, the more normal the measurement point or equipment operates. If the measurement point score is low, it indicates a potential fault or abnormality.

[0079] Before dividing the operating conditions of the hydropower unit, it is also necessary to generate the start and stop records of the hydropower unit. In the process of starting and stopping the hydropower unit, the speed data is one of the most direct and critical data. Therefore, by continuously monitoring the speed data, the start and stop time of the unit can be obtained. The specific steps include:

[0080] Step S100: obtain the real-time speed data of the hydropower unit from the computer monitoring system, and pre-process the speed data. The pre-processing includes denoising, missing value filling and time alignment methods.

[0081] Step S200, setting a speed threshold according to the rated speed of the hydropower unit. The speed threshold includes a shutdown speed threshold and a startup speed threshold. If the real-time speed data of the hydropower unit is less than the shutdown speed threshold, it means that the hydropower unit is shut down. If the real-time speed data of the hydropower unit is greater than the startup speed threshold, it means that the hydropower unit starts to start. Optionally, the shutdown speed threshold includes 4PRM, 5PRM, and 6PRM. The startup speed threshold includes 95PRM, 100PRM, and 105PRM.

[0082] Step S300: According to the monitored real-time speed data changes of the hydropower unit, if the real-time speed of the hydropower unit gradually increases from a lower speed and is greater than the startup speed threshold, the hydropower system records the time of the real-time speed data rising process as the startup time. If the real-time speed of the hydropower unit drops significantly from the rated speed, and the real-time speed data is lower than the shutdown speed threshold for a period of time, the time of this drop process is recorded as the shutdown time.

[0083] Through the above steps S100 to S300, all the start-up time and downtime records of the hydropower unit before maintenance are obtained. And the computer system obtains the historical data of the monitoring points during each shutdown and startup of the hydropower unit. The historical data obtained by the computer system is used to calculate the measurement point score.

[0084] According to the content described in the above step S101, the operating conditions are divided according to the actual operating power of the hydropower unit, providing reliable data support for the subsequent measurement point scoring. In addition, different measurement point scoring models are used to obtain measurement point scores for different measurement point data types, so that the health status of the measurement point can be judged more accurately, providing a basis for subsequent scoring.

[0085] Continue to refer to Figure 1 , execute step S102 after step S101.

[0086] Step S102: According to the collaborative relationship between the monitoring points, a correlation analysis is performed on the scores of all the monitoring points through a preset machine algorithm to obtain a unit score, which represents the health status of the unit components.

[0087] Obtain all the measurement point scores in step S101, input all the measurement point scores into the aggregation model, and analyze them in the aggregation model in combination with the expert experience of the expert system and the historical operation data to obtain the unit score. More specifically, the expert experience of the expert system is used to perform correlation analysis on all the measurement point scores. For example, when the scores of multiple related measurement points are all below the threshold, the unit score is lowered based on expert experience to indicate the potential risk of failure. In addition, the expert system is used to set key measurement point rules, and the weights of the measurement point scores are adjusted according to the key measurement point rules, so as to ensure an accurate assessment of the unit health status. Among them, the clustering model includes random forests and support vector machines.

[0088] Based on the scores of all measuring points and the expert system, the unit score of the hydropower unit is obtained through the clustering model. The unit score represents the health status of each component in the hydropower unit. The unit score is a further refinement based on the measuring point score. In other words, the correlation between the monitoring points leads to a problem at one monitoring point, and the monitoring points associated with the problematic monitoring point will also have problems. Therefore, it is possible to further judge whether the component or hydropower unit as a whole will have problems based on the correlation of its measuring point scores. Therefore, the unit score reflects the health status of the components in the hydropower unit. Compared with the measuring point score, which represents a single score of scattered measuring points, the unit score reflects the overall operating status of the hydropower unit or its components.

[0089] Based on the measurement point scores and expert experience, the unit score is obtained. The unit score reflects the overall operating status of the hydropower unit or its components, and is the health status of the component level. Therefore, the health status evaluation of the hydropower unit is more accurate.

[0090] Step S103: During any operation of the hydropower unit, the historical comprehensive score of the hydropower unit is obtained. According to the preset weight, the historical comprehensive score is combined with the current comprehensive score to obtain the final comprehensive score. The comprehensive score represents the overall health status of the hydropower unit. The historical comprehensive score is determined by the unit score.

[0091] The health status of the hydropower unit needs to be continuously and dynamically updated. After the hydropower unit has been run for many times, the health judgment of the hydropower unit is particularly important. Therefore, the score of the health status of the hydropower unit also needs to be continuously updated so that the health status of the hydropower unit can be determined through the score. During any operation of the hydropower unit, the historical comprehensive score of the hydropower unit is obtained. If the hydropower unit is running for the first time and there is no historical comprehensive score, the unit score obtained in step S102 is used as the comprehensive score for this operation. During the first operation of the hydropower unit, the comprehensive score of the hydropower unit is obtained without the need for the historical comprehensive score to participate in the update.

[0092] If the hydropower unit is not running for the first time and has a historical comprehensive score, the comprehensive score should be updated based on the current comprehensive score and the current comprehensive score. That is, when the hydropower unit obtains the current initial comprehensive score, the current initial comprehensive score and the historical score are calculated through the exponentially weighted moving average algorithm to obtain an updated comprehensive score. The updated comprehensive score can reflect the overall health status of the hydropower unit. Among them, the exponentially weighted moving average algorithm satisfies the following formula:

[0093] S new =α×S curret +(1α)×S history

[0094] Among them, s new is the updated comprehensive score, S current is the current rating, S history is the historical score, and α is the weight coefficient.

[0095] The exponentially weighted moving average algorithm can ensure the smoothness of the comprehensive score and avoid drastic fluctuations in the comprehensive score due to a certain performance score that is too high or too low. A comprehensive score is generated for each operation of the hydropower unit, and the comprehensive score is updated based on the historical comprehensive score of the hydropower unit, thereby ensuring the instantaneity of the comprehensive score of the hydropower unit, as well as the smooth update of the comprehensive score and the reference value of the comprehensive score. Thus, false alarms or excessive interventions caused by abnormalities in a single operation of the hydropower unit are avoided.

[0096] Step S104: construct a health model of the hydropower unit based on the measurement point scores, the unit scores and the comprehensive scores, and determine the health status of the hydropower unit according to the health model of the hydropower unit.

[0097] Based on the measurement point scores, unit scores and comprehensive scores obtained in steps S101 to S103, a hydropower unit health model is constructed, and the health status of the hydropower unit can be determined according to the comprehensive score obtained through the hydropower unit health model.

[0098] In addition, after the hydropower unit has been overhauled, the health status of the hydropower unit has changed significantly. Therefore, all measurement point scores, unit scores and comprehensive scores will be cleared, and the health status of the hydropower unit needs to be re-evaluated.

[0099] Figure 3 is a flow chart of a method for evaluating the health status of a hydropower unit according to another exemplary embodiment. Figure 3As shown in the figure, the data of the hydropower unit is obtained through the monitoring system, the condition monitoring system and the protection system, and the obtained data is connected to the start-stop identification module and the working condition identification module to determine the start-stop records and different working conditions. Based on the start-stop module and the working condition identification module, the health evaluation model of the hydropower unit constructed by the measurement point score, unit score and comprehensive score is obtained. Based on the health model of the hydropower unit, health scores of different levels are obtained.

[0100] The health model of the hydropower unit obtains the scores of the three levels of measuring points, components and overall units during the operation of the hydropower unit, and generates an accurate comprehensive score in combination with the historical comprehensive score. The dynamic scoring mechanism can more accurately reflect the health status of the hydropower unit and the comprehensive evaluation of the equipment status. And according to the scoring results of each level, targeted maintenance is carried out on the hydropower unit to improve the safety and operation efficiency of the hydropower unit. Through the above method, the health model of the hydropower unit is applied to the large-scale hydropower unit equipment management, which can improve the operation efficiency and safety of large-scale hydropower unit equipment, and also provide reliable data support for equipment management and self-iHu strategy.

[0101] In summary, the method for evaluating the health status of a hydropower unit provided in the embodiment of the present application obtains scores at three levels, namely, measuring points, components, and the entire unit, through the method of operating condition division, feature extraction, and dynamic scoring, and determines the health status of the hydropower unit based on the scores. It is an intelligent and precise method for evaluating the health status of a hydropower unit. The method for evaluating the health status of a motor unit performs feature analysis on the data in a single operation of the hydropower unit to smooth out data fluctuations. In addition, the evaluation is also combined with the changes in the operating conditions of the hydropower unit to achieve an accurate score for the health status of the hydropower unit, reduce the false alarm rate of the health status of the hydropower unit, and accurately judge the health status of the unit, thereby optimizing the maintenance plan of the hydropower unit, reducing unnecessary downtime for maintenance, and improving the operating efficiency of the equipment.

[0102] In a second aspect, an embodiment of the present application provides a device for assessing the health status of a hydropower unit. Figure 4 FIG. 1 is a block diagram of a device for evaluating the health status of a hydropower unit according to an exemplary embodiment. Figure 4 As shown, the hydropower unit health status assessment device includes:

[0103] The measuring point scoring module is used to obtain the measuring point data of several monitoring points in the operating conditions of any hydropower unit, and analyze the measuring point data through the measuring point scoring model to obtain the measuring point score. The measuring point score represents the health status of different monitoring points of the hydropower unit under the current operating conditions;

[0104] The unit scoring module is used to perform correlation analysis on the scores of all the measuring points based on the synergistic relationship between the monitoring points through a preset machine algorithm to obtain the unit score, which represents the health status of the unit components;

[0105] The comprehensive scoring module is used to obtain the historical comprehensive score of the hydropower unit during any operation of the hydropower unit. According to the preset weight, the historical comprehensive score is combined with the current comprehensive score to obtain the final comprehensive score. The comprehensive score represents the overall health status of the hydropower unit. The historical comprehensive score is determined by the unit score.

[0106] The unit health module is used to build a hydropower unit health model based on the measurement point score, unit score and comprehensive score, and determine the health status of the hydropower unit according to the hydropower unit health model.

[0107] In summary, the hydropower unit health status assessment device provided by this application has measurement point scores, unit scores and comprehensive scores corresponding to the three levels of unit components and overall units respectively, and the health status of the hydropower unit is judged based on the comprehensive score. In the process of determining the health status of the hydropower unit, it is dynamically determined based on the measurement point scores, unit scores and historical scores during each hydropower unit operation process, so that the hydropower unit can be accurately scored, and the health status of the hydropower unit can be judged based on the scores.

[0108] In one embodiment, the measuring point scoring model in the measuring point scoring module includes an interval scoring model, an abnormal change evaluation model and an abnormal detection model. The measuring point score is obtained by analyzing the measuring point data through the measuring point scoring model, including: an acquisition unit, an interval scoring unit, an abnormal change scoring unit, and an LSTM scoring unit.

[0109] An acquisition unit is used to acquire historical measurement point data and the type of measurement point data, which includes fixed value type and mutation type;

[0110] An interval scoring unit is used to obtain a preset interval if the measuring point data is a fixed numerical type. In the interval scoring model, if the measuring point data is within the preset interval, a full score is obtained for the measuring point. If the measuring point data is not within the preset interval, the full score is reduced according to the distance that the measuring point data deviates from the preset interval to obtain a measuring point score.

[0111] The abnormal change scoring unit is used to obtain the difference between the measured point data and the historical measured point data in the abnormal change evaluation model if the measured point data is of mutation type, compare the difference with the preset threshold, deduct points according to the gap between the difference and the preset threshold, and determine the measured point score.

[0112] The LSTM scoring unit is used to determine abnormal measuring points in the hydropower unit based on historical measuring point data using the LSTM model and obtain the measuring point score of each measuring point

[0113] In one embodiment, in the interval scoring model, if the measurement point data is within a preset interval, a full score measurement point score is obtained, and further includes an acquisition subunit, a first physical threshold comparison subunit, a second physical threshold comparison subunit,

[0114] An acquisition subunit is used to acquire a physical threshold value, which represents the upper limit of data obtained by monitoring points in a hydropower unit subject to physical condition monitoring;

[0115] A first physical threshold comparison subunit is used to obtain a zero score for a measurement point if the measurement point data is within a preset interval and the measurement point data is greater than a physical threshold in an interval scoring model;

[0116] The second physical threshold comparison subunit is used to obtain a full score for the measurement point if the measurement point data is within a preset interval and the measurement point data is less than or equal to the physical threshold.

[0117] In one embodiment, the unit scoring module performs correlation analysis on all the scores of the monitoring points according to the synergistic relationship between the monitoring points through a preset machine algorithm to obtain the unit score, including an analysis unit,

[0118] The analysis unit is used to input the scores of all measuring points and the expert experience of the expert system into the aggregation model, perform correlation analysis on all measuring points, and obtain the unit score.

[0119] In one embodiment, the comprehensive scoring module includes a first obtaining subunit and a second obtaining subunit.

[0120] A first obtaining subunit is used for taking the current unit score as the comprehensive score of the hydropower unit if the hydropower unit is running for the first time;

[0121] The second obtaining subunit is used to obtain the historical unit score of the hydropower unit if the hydropower unit is not in the first operation, and to obtain a comprehensive score by using an exponentially weighted moving average algorithm to calculate the previous historical unit score and the current unit score during any operation of the hydropower unit;

[0122] The exponentially weighted moving average algorithm satisfies the following formula:

[0123] S new =α×S cutrent +(1α)×S history

[0124] Among them, S new is the updated comprehensive score, S current is the current rating, S history is the historical score, and α is the weight coefficient.

[0125] In one embodiment, the comprehensive scoring module further includes a clearing module.

[0126] When the hydropower unit is overhauled, the measuring point score, unit score and comprehensive score are cleared.

[0127] In one embodiment, the measuring point module further includes a startup condition unit, a stable condition unit, a variable load condition unit and a shutdown condition unit.

[0128] The startup condition unit is to meet the requirement that the power of the hydropower unit rises from 0 to stable power. Stable power means that the power does not change within any period of time.

[0129] The stable operating condition unit is to meet the power change of the hydropower unit less than the preset change threshold

[0130] The variable load condition unit is used to meet the frequent power changes of the hydropower unit.

[0131] The shutdown condition unit is when the power of the hydropower unit gradually decreases until the power reaches 0.

[0132] In summary, the hydropower unit health status assessment device provided by the present application, in summary, the hydropower unit health status method provided in the embodiment of the present application, obtains scores at three levels: measuring points, components, and the unit as a whole through working condition division, feature extraction, and dynamic scoring methods, and determines the health status of the hydropower unit based on the scores. It is an intelligent and precise hydropower unit health status assessment, which realizes accurate scoring of the health status of the hydropower unit, and can further judge the health status of the hydropower unit.

[0133] It should be noted that the hydropower unit health status assessment device provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the device described in the above embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0134] In a third aspect, an embodiment of the present application provides an electronic device, Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device may include a processor 81 and a memory 82 storing computer program instructions.

[0135] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0136] Among them, the memory 82 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0137] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0138] The processor 81 implements any one of the methods for assessing the health status of a hydropower unit in the above-mentioned embodiments by reading and executing computer program instructions stored in the memory 82 .

[0139] In one embodiment, the hydropower unit health status assessment device may further include a communication interface 83 and a bus 80. Figure 5 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0140] The communication interface 83 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 83 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0141] The bus 80 includes hardware, software or both, and couples the components of the hydropower unit health status assessment device to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0142] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the method for assessing the health status of a hydropower unit provided in the first aspect is implemented.

[0143] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0144] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the hydropower unit health status assessment method provided in the first aspect.

[0145] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0146] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating the health status of a hydropower unit, characterized in that: include: In the operating condition of any hydropower unit, the measuring point data of several monitoring points are obtained, and the measuring point scores are obtained by analyzing the measuring point data through the measuring point scoring model, wherein the measuring point scores represent the health status of different monitoring points of the hydropower unit under the current operating condition; According to the collaborative relationship between the monitoring points, a correlation analysis is performed on the scores of all the monitoring points through a preset machine algorithm to obtain a unit score, wherein the unit score represents the health status of the unit components; During any operation of a hydropower unit, a historical comprehensive score of the hydropower unit is obtained, and the historical comprehensive score is combined with the current comprehensive score according to a preset weight to obtain a final comprehensive score, wherein the comprehensive score represents the overall health status of the hydropower unit, and the historical comprehensive score is determined by the unit score; Based on the measuring point scores, the unit scores and the comprehensive scores, a hydropower unit health model is constructed, and the health status of the hydropower unit is determined according to the hydropower unit health model.

2. The method for evaluating the health status of a hydropower unit according to claim 1, characterized in that: The measuring point scoring model includes an interval scoring model, an abnormal change evaluation model and an abnormality detection model. The measuring point scoring is obtained by analyzing the measuring point data through the measuring point scoring model, including: Acquire historical measurement point data and the type of the measurement point data, the type including fixed value type and mutation type; If the measuring point data is of a fixed numerical type, a preset interval is obtained. In the interval scoring model, if the measuring point data is within the preset interval, a full score measuring point score is obtained. If the measuring point data is not within the preset interval, the full score is deducted according to the distance that the measuring point data deviates from the preset interval to obtain the measuring point score. If the measuring point data is of mutation type, in the abnormal change evaluation model, the difference between the measuring point data and the historical measuring point data is obtained, the difference is compared with a preset threshold, points are deducted according to the gap between the difference and the preset threshold, and the measuring point score is determined. According to the historical measuring point data, the LSTM model is used to determine abnormal measuring points in the hydropower unit, and the measuring point score of each measuring point is obtained.

3. The method for evaluating the health status of a hydropower unit according to claim 2, characterized in that: In the interval scoring model, if the measurement point data is within the preset interval, a full score measurement point score is obtained, which also includes: Obtaining a physical threshold, wherein the physical threshold represents an upper limit of data obtained by monitoring points in the hydropower unit subject to physical condition monitoring; In the interval scoring model, if the measurement point data is within the preset interval and the measurement point data is greater than the physical threshold, a measurement point score of zero is obtained; If the measurement point data is within the preset interval and the measurement point data is less than or equal to the physical threshold, a full score measurement point score is obtained.

4. The method for evaluating the health status of a hydropower unit according to claim 1, characterized in that: According to the collaborative relationship between the monitoring points, the scores of all the monitoring points are analyzed by a preset machine algorithm to obtain the unit score, including: The scores of all the measuring points and the expert experience of the expert system are input into the aggregation model, and the correlation analysis is performed on all the measuring points to obtain the unit score.

5. The method for evaluating the health status of a hydropower unit according to claim 1, characterized in that: In any operation of the hydropower unit, the historical comprehensive score of the hydropower unit is obtained, and the historical comprehensive score is combined with the current comprehensive score according to the preset weight to obtain the final comprehensive score, including: If the hydropower unit is running for the first time, the current unit score is used as the comprehensive score of the hydropower unit; If the hydropower unit is not in the first operation, the historical unit score of the hydropower unit is obtained, and during any operation of the hydropower unit, the previous historical unit score and the current unit score are combined by an exponentially weighted moving average algorithm to obtain a comprehensive score; The exponentially weighted moving average algorithm satisfies the following formula: S new =α×S current +(1-a)×S history Among them, S new is the updated comprehensive score, S current is the current rating, S history is the historical score, and α is the weight coefficient.

6. The method for evaluating the health status of a hydropower unit according to claim 1, characterized in that: After obtaining the comprehensive score, it also includes: After the hydroelectric unit is overhauled, the measuring point score, the unit score and the comprehensive score are cleared.

7. The method for evaluating the health status of a hydropower unit according to claim 1, characterized in that: The operating conditions include startup conditions, stable conditions, variable load conditions and shutdown conditions, and the operating conditions meet the following configurations: The startup condition satisfies that the power of the hydropower unit increases from 0 to a stable power, and the stable power indicates that the power does not change within any period of time; The stable operating condition satisfies that the power change of the hydropower unit is less than a preset change threshold; The variable load condition satisfies the frequent power changes of the hydroelectric unit; The shutdown condition satisfies that the power of the hydroelectric unit gradually decreases until the power is 0.

8. A device for evaluating the health status of a hydropower unit, characterized in that: include: A measuring point scoring module is used to obtain measuring point data of several monitoring points in the operating condition of any hydropower unit, and analyze the measuring point data through a measuring point scoring model to obtain a measuring point score, wherein the measuring point score represents the health status of different monitoring points of the hydropower unit under the current operating condition; A unit scoring module is used to perform correlation analysis on the scores of all the monitoring points through a preset machine algorithm according to the collaborative relationship between the monitoring points to obtain a unit score, wherein the unit score represents the health status of the unit components; The comprehensive scoring module is used to obtain the historical comprehensive score of the hydropower unit during any operation of the hydropower unit, and combine the historical comprehensive score with the current comprehensive score according to the preset weight to obtain the final comprehensive score. The comprehensive score represents the overall health status of the hydropower unit. The historical comprehensive score is determined by the unit score. The unit health module is used to construct a hydropower unit health model based on the measurement point score, the unit score and the comprehensive score, and determine the health status of the hydropower unit according to the hydropower unit health model.

9. An electronic device, characterized in that: It comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for assessing the health status of a hydropower unit as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for assessing the health status of a hydropower unit according to any one of claims 1 to 7 is implemented.

Images