A method and device for detecting the operating state of a pumped storage unit

Abstract

The embodiment of the application provides a kind of pumped storage unit operating state detection method and device, by obtaining the operating data of unit, feature parameter and working condition parameter are extracted from operating data, based on feature parameter and working condition parameter, using the preset health state standard model, determine degradation index, according to the degradation index in predetermined time, determine the degradation gradient current value of each feature parameter, according to the size relationship between each feature parameter and corresponding degradation gradient current value and the preset alarm threshold, each feature parameter and corresponding fault level, determine the current operating state of unit;Comprehensive current operating state and offline state evaluation result, determine the current operating state comprehensive evaluation result, based on the current operating state comprehensive evaluation result determines appropriate operation and maintenance scheme, can avoid the problem existing in planned maintenance, improve the safety and stability of unit operation.

Description

Technical Field

[0001] This application relates to the field of pumped storage technology, and in particular to a method and apparatus for detecting the operating status of a pumped storage unit. Background Technology

[0002] Currently, most pumped-storage hydroelectric units operate under a planned maintenance model, meaning that maintenance is carried out periodically. This model does not consider the actual operating status of the units, resulting in both insufficient and excessive maintenance. Insufficient maintenance refers to localized faults occurring before the scheduled maintenance period due to various reasons. Because these faults cannot be repaired in a timely manner, they continue to worsen, increasing maintenance costs and potentially causing accidents. Excessive maintenance refers to performing unnecessary maintenance on units in good operating condition according to the maintenance plan, resulting in lost effective operating time, increased maintenance costs, and possibly reduced equipment reliability. Given the shortcomings of planned maintenance, accurately detecting the actual operating status of the units to determine appropriate maintenance timing is a technical problem that needs to be solved in this field. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and apparatus for detecting the operating status of a pumped storage unit, so as to solve the problem of detecting the actual operating status of the unit.

[0004] To achieve the above objectives, this application provides a method for detecting the operating status of a pumped storage unit, comprising:

[0005] Acquire power generation operation data of the unit under steady-state operating conditions in the power generation direction;

[0006] Extract characteristic parameters of power generation direction and operating condition parameters from the power generation operation data;

[0007] Based on the characteristic parameters and operating parameters of the power generation direction, the degradation index of each characteristic parameter of the power generation direction is determined using a preset standard model of the health status of the power generation direction.

[0008] Based on the degradation index of each feature parameter within a predetermined time, determine the current value of the degradation gradient of each feature parameter;

[0009] Based on the relationship between the current values ​​of the characteristic parameters and corresponding degradation gradients in the power generation direction and the preset alarm threshold for the power generation direction, the characteristic parameters of the power generation direction and their corresponding fault levels are used to determine the current operating status of the unit in the power generation direction; and / or,

[0010] Acquire pumping operation data of the unit under steady-state conditions in the pumping direction;

[0011] Extract the characteristic parameters of the pumping direction and the operating parameters from the pumping operation data;

[0012] Based on the characteristic parameters and operating parameters of the pumping direction, the degradation index of each characteristic parameter of the pumping direction is determined using a preset standard model of the health status of the pumping direction.

[0013] Based on the degradation index of each feature parameter within a predetermined time, determine the current value of the degradation gradient of each feature parameter;

[0014] Based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the pumping direction and the preset alarm threshold in the pumping direction, the characteristic parameters in the pumping direction and the corresponding fault level are used to determine the current operating status of the unit in the pumping direction.

[0015] Optionally, the method further includes:

[0016] Using a pre-defined power generation direction trend prediction model, the future predicted values ​​of each characteristic parameter of the power generation direction are determined;

[0017] Based on the relationship between the future predicted value of the power generation direction and the alarm threshold of the power generation direction, the characteristic parameters of the power generation direction and the corresponding fault level, the operating status of the unit in the power generation direction after a predetermined time is determined; and / or,

[0018] Using a pre-defined pumping direction trend prediction model, the future predicted values ​​of each characteristic parameter of the pumping direction are determined;

[0019] Based on the relationship between the future predicted value of the pumping direction and the alarm threshold of the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level, the operating status of the unit after a predetermined time in the pumping direction is determined.

[0020] Optionally, based on the relationship between the characteristic parameters of the power generation direction and the corresponding current value of the degradation gradient, and a preset alarm threshold for the power generation direction, and the characteristic parameters of the power generation direction and the corresponding fault level, the current operating state of the unit in the power generation direction is determined, including:

[0021] The first score is determined based on the relationship between the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction;

[0022] The second score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction.

[0023] The third score is determined based on the relationship between each characteristic parameter in the set of characteristic parameters corresponding to the fault and the corresponding alarm threshold.

[0024] Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights, first score, second score, fault and the corresponding fault evaluation weights, third score, the current operating status result in the power generation direction is calculated.

[0025] Optionally, based on the relationship between the characteristic parameters of the pumping direction and the corresponding current value of the degradation gradient, and a preset alarm threshold for the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level are used to determine the current operating status of the unit in the pumping direction, including:

[0026] The fourth score is determined based on the relationship between the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction.

[0027] The fifth score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction.

[0028] The sixth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0029] Based on the characteristic parameters of the pumping direction and the corresponding characteristic evaluation weights, fourth score, and fifth score, as well as the fault and the corresponding fault evaluation weight and sixth score, the current operating status result in the pumping direction is calculated.

[0030] Optionally, the method further includes: determining the unit's operating status in the power generation direction after a predetermined time, based on the relationship between the future predicted value of the power generation direction and the alarm threshold of the power generation direction, the characteristic parameters of the power generation direction, and the corresponding fault level, including:

[0031] The seventh score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction.

[0032] The eighth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0033] Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights and seventh score, the fault and the corresponding fault evaluation weights and eighth score are used to calculate the operating status result of the power generation direction after a predetermined time.

[0034] Optionally, the method further includes: determining the unit's operating status in the pumping direction after a predetermined time based on the relationship between the future predicted value of the pumping direction and the alarm threshold of the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level, including:

[0035] The ninth score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction.

[0036] The tenth value is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0037] Based on the characteristic parameters of the pumping direction and the corresponding characteristic evaluation weights and the ninth score, the fault and the corresponding fault evaluation weights and the tenth score, the operating status results of the pumping direction after a predetermined time are calculated.

[0038] Optionally, the method further includes:

[0039] Based on the current operating status and the obtained offline status evaluation results, the comprehensive evaluation result of the unit's current operating status is determined.

[0040] Optionally, based on the current operating status and the acquired offline status evaluation results, a comprehensive evaluation result of the unit's current operating status is determined, including:

[0041] If the offline status evaluation result is normal, the current operating status comprehensive evaluation result is the current operating status;

[0042] If the offline status evaluation result is abnormal, the current operating status comprehensive evaluation result is the state corresponding to the more severe one between the current operating status and the offline status evaluation result.

[0043] Optionally, determining the current value of the degradation gradient of each feature parameter based on the degradation index of each feature parameter within a predetermined time period includes:

[0044] Based on the degradation index sequence and corresponding time series formed within a predetermined time period, select several data points that are closest to the current time.

[0045] A linear fit is performed on the selected data points to obtain the fitted straight line;

[0046] Determine the slope of the line and use that slope as the current value of the degradation gradient.

[0047] This application embodiment also provides an operating status detection device for a pumped storage unit, including:

[0048] The acquisition module is used to acquire power generation operation data of the unit under steady-state conditions in the power generation direction; and / or, to acquire pumping operation data of the unit under steady-state conditions in the pumping direction;

[0049] The extraction module is used to extract characteristic parameters of the power generation direction and operating condition parameters from the power generation operation data; and / or to extract characteristic parameters of the pumping direction and operating condition parameters from the pumping operation data.

[0050] The prediction module is used to determine the degradation index of each characteristic parameter of the power generation direction based on the characteristic parameters and operating parameters of the power generation direction and using a preset standard model of the health status of the power generation direction; and / or, based on the characteristic parameters and operating parameters of the pumping direction and using a preset standard model of the health status of the pumping direction, determine the degradation index of each characteristic parameter of the pumping direction.

[0051] The gradient determination module is used to determine the current value of the degradation gradient of each characteristic parameter in the power generation direction based on the degradation index of each characteristic parameter in the power generation direction within a predetermined time; and / or, to determine the current value of the degradation gradient of each characteristic parameter in the pumping direction based on the degradation index of each characteristic parameter in the pumping direction within a predetermined time.

[0052] The status determination module is used to determine the current operating status of the unit in the power generation direction based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the power generation direction and a preset alarm threshold in the power generation direction, and the characteristic parameters of the power generation direction and the corresponding fault level; and / or, based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the pumping direction and a preset alarm threshold in the pumping direction, and the characteristic parameters of the pumping direction and the corresponding fault level, determine the current operating status of the unit in the pumping direction.

[0053] As can be seen from the above, the pumped storage unit operation status detection method and device provided in this application acquires the unit's operation data, extracts characteristic parameters and operating condition parameters from the operation data, determines the degradation index of the characteristic parameters based on the characteristic parameters and operating condition parameters using a preset health status standard model, determines the current value of the degradation gradient of the characteristic parameters based on the degradation index of the characteristic parameters within a predetermined time, determines the current operation status of the unit based on the relationship between each characteristic parameter and its corresponding current value of degradation gradient and a preset alarm threshold, and determines the relationship between each characteristic parameter and its corresponding fault level; comprehensively evaluates the current operation status of the unit by combining the current operation status and offline status evaluation results, and determines a suitable operation and maintenance plan based on the comprehensive evaluation results of the current operation status, which can avoid the problems of planned maintenance and improve the safe and stable operation of the unit. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a schematic diagram of the method flow for power generation direction according to an embodiment of this application;

[0056] Figure 2 This is a schematic diagram of the method flow for the pumping direction in an embodiment of this application;

[0057] Figure 3 This is a schematic diagram of the linear fitting degradation gradient values ​​in an embodiment of this application;

[0058] Figure 4 This is a block diagram of the device structure according to an embodiment of this application;

[0059] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0061] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0062] As described in the background section, planned maintenance of generating units suffers from both under-maintenance and over-maintenance. Determining the appropriate timing for maintenance requires accurate monitoring of the unit's actual operating status. Related technologies employ methods such as visual inspection, flaw detection, preventative testing, and commissioning testing to acquire various status parameters of the unit, enabling offline monitoring and evaluation of the unit's status based on these parameters; and / or, utilizing a condition monitoring system to acquire the unit's vibration amplitude, comparing it with a set threshold, and using the comparison results for auxiliary online monitoring and evaluation of the unit's status. However, the aforementioned offline monitoring and evaluation methods suffer from problems such as unreal-time and incomplete data, and untimely evaluation. Online evaluation methods, on the other hand, suffer from limitations such as simplistic evaluation methods, insufficient utilization of unit operating data, and inability to predict operating status within a certain future timeframe, thus failing to effectively monitor and assess the unit's actual operating status.

[0063] In view of this, embodiments of this application provide a method for detecting the operating status of a pumped storage unit. Based on the characteristic parameters and operating parameters of the unit under steady-state conditions in the power generation and / or pumping directions, the current value of the degradation gradient of the characteristic parameters is determined. According to the relationship between the characteristic parameters and their corresponding current degradation gradient values ​​and preset alarm thresholds, and the relationship between each characteristic parameter and its corresponding fault level, the current operating status of the unit is determined. Furthermore, by integrating offline status evaluation results, a comprehensive evaluation result of the unit's current operating status is determined. Based on this comprehensive evaluation result, a suitable maintenance plan is formulated, which can avoid problems associated with planned maintenance and improve the safety and stability of the unit's operation.

[0064] The technical solution of this application will be further described in detail below through specific embodiments.

[0065] like Figure 1 , 2 As shown in the figure, this application provides a method for detecting the operating status of a pumped storage unit, including:

[0066] S101: Obtain the power generation operation data of the unit under steady-state operating conditions in the power generation direction;

[0067] In this embodiment, power generation operation data of the unit under steady-state operating conditions in the power generation direction is acquired from the unit condition monitoring system and the monitoring system. This power generation operation data includes unit vibration, main shaft runout, water pressure pulsation, temperature, air gap, magnetic flux density, and operating parameters. Specifically, it includes vibration data of the upper frame in the horizontal and vertical directions, the lower frame in the horizontal and vertical directions, the stator frame in the horizontal and vertical directions, the stator core in the horizontal and vertical directions, the top cover in the horizontal and vertical directions, the upper guide runout, and the lower guide runout. Temperature, water guide oscillation, volute inlet water pressure pulsation, bladeless zone water pressure pulsation, top cover water pressure pulsation, impeller and bottom ring water pressure pulsation, tailrace inlet water pressure pulsation, upper guide bearing bearing shell temperature and oil sump temperature, lower guide bearing bearing shell temperature and oil sump temperature, thrust bearing shell temperature and oil sump temperature, water guide bearing shell temperature and oil sump temperature, stator bar and stator core temperature, technical water supply cooling water inlet and outlet temperatures, stator and rotor air gap, magnetic flux density, active power, reactive power, guide vane opening, excitation voltage, excitation current, head, stator voltage, stator current, etc.

[0068] In some methods, considering the large amount of data for certain types of power generation operation data, such as the fact that the number of temperature measuring points for upper guide bearings, lower guide bearings, thrust bearings, and water guide bearings is usually greater than 10, and the number of temperature measuring points for stator cores and stator bars can reach hundreds, it is necessary to preprocess the temperature-type power generation operation data in order to reduce the amount of data and improve data processing efficiency. The preprocessing methods include: obtaining all temperature-type power generation operation data at a certain moment, filtering and classifying the power generation operation data according to different temperature types, and calculating the maximum value, average value, and coefficient of variation of the power generation operation data of the same temperature type after filtering, so as to obtain the preprocessed power generation operation data of the corresponding type.

[0069] For example, given the obtained and filtered upper guide bearing bush temperatures T1, T2, ..., Tn at a certain moment, where n is the number of temperature measurement points, the maximum value Tmax of the upper guide bearing bush temperature is selected. The average value Tavg of all upper guide bearing bush temperatures is calculated, and the coefficient of variation of the upper guide bearing bush temperatures is also calculated. The coefficient of variation is calculated by first calculating the standard deviation σ of the upper guide bearing bush temperatures, and then calculating the coefficient of variation C based on the average value Tavg and the standard deviation σ. V , is represented as:

[0070]

[0071] S102: Extract characteristic parameters of power generation direction and operating condition parameters from power generation operation data;

[0072] In this embodiment, after acquiring the unit's operating data under steady-state conditions in the power generation direction, characteristic parameters and operating condition parameters in the power generation direction are extracted based on the operating data in the power generation direction. In some methods, time-domain analysis, frequency-domain analysis, artificial intelligence data analysis, and big data processing methods can be used to extract characteristic parameters reflecting the unit's operating state from multiple dimensions such as time domain, frequency domain, signal entropy, and signal power, based on the operating data, as characteristic data for analyzing the unit's operating state.

[0073] The effective value of a vibration signal falls under the category of signal power. For velocity-type or acceleration-type vibration signals, the effective value is generally calculated to reflect the magnitude of the vibration. Let X be a vibration signal of a certain duration. i If the signal length of the vibration signal is n, then the effective value of the vibration signal is:

[0074]

[0075] For pumped storage hydroelectric power units, the commonly used entropy values ​​for vibration signals include approximate entropy, sample entropy, and permutation entropy. Entropy is a dimensionless index used to characterize the complexity of a signal sequence. The larger the entropy value, the greater the complexity of the signal, meaning the more complex the frequency components in the signal. Conversely, the smaller the entropy value, the more homogeneous the frequency components in the signal. If the entropy value of the vibration signal increases significantly, it indicates an increase in the frequency components in the vibration signal, which can reflect an anomaly in the unit, especially when the vibration amplitude of the unit has not increased significantly.

[0076] In some methods, approximate entropy is used as an example to illustrate the method of calculating the signal entropy of a vibration signal: Suppose that the time-domain waveform data of a vibration signal over a period of time is represented as a data sequence u(1), u(2), ..., u(N), with a total of N data points.

[0077] The data sequence {u(i)} is arranged in order to form an m-dimensional vector X(i), that is, an m-dimensional vector is formed from X(1) to X(N-m+1) in the order of the numbers, where: X(i)=[u(i),u(i+1),...,u(i+m-1)],i=1~N-m+1.

[0078] The distance d[X(i),X(j)] between the corresponding elements of X(i) and X(j) with the largest difference is defined as:

[0079]

[0080] Given a similarity tolerance r, for each value i, count the number Nr of d[X(i),X(j)] less than r, and the ratio of this number to the total number of distances. Represented as:

[0081]

[0082] First compare values Take the logarithm, and then calculate the average of the logarithms for all values ​​of i, expressed as:

[0083]

[0084] Increment the dimension by 1, i.e., m = m + 1 dimension, and repeat the above steps to calculate. and Therefore, the approximate entropy ApEn estimate of the vibration signal is:

[0085] ApEn(m,r,N)=φ m (r)-φ m+1 (r) (6)

[0086] The approximate entropy of the vibration signal is related to m and r. Generally, m = 2 and r = 0.1 to 0.25SD are taken, where SD is the standard deviation of the original signal.

[0087] In some implementations, the characteristic parameters of the power generation direction include: unit vibration amplitude, unit vibration effective value, unit vibration signal entropy, main shaft swing amplitude, main shaft swing signal entropy, water pressure pulsation amplitude, water pressure pulsation signal entropy, rotational frequency amplitude, unbalanced phase, blade overcurrent frequency amplitude, twice the blade overcurrent frequency amplitude, three times the blade overcurrent frequency amplitude, twice the rotational frequency amplitude, upper guide bearing temperature and oil tank temperature, thrust bearing temperature and oil tank temperature, water guide bearing temperature and oil tank temperature, maximum air gap value, minimum air gap value, air gap non-uniformity, stator core temperature, stator bar temperature, magnetic pole flux density, etc.

[0088] Optionally, the nth characteristic parameter in the power generation direction can be represented as GPn, where G represents Generator and P represents Parameter.

[0089] S103: Based on the characteristic parameters and operating parameters of the power generation direction, the degradation index of each characteristic parameter of the power generation direction is determined using a preset standard model of the health status of the power generation direction.

[0090] In this embodiment, using the characteristic parameters and operating parameters of the unit under steady-state operating conditions in the power generation direction as data samples, a standard model for the health status of the power generation direction is pre-trained and constructed to determine the degradation index corresponding to the characteristic parameters. After extracting the characteristic parameters of the power generation direction based on the currently acquired real-time power generation operation data, the characteristic parameters and operating parameters of the power generation direction are used as inputs to the standard model for the health status of the power generation direction. The standard model outputs the degradation index of the power generation direction. Optionally, the degradation index of the power generation direction can be represented as GiT0.

[0091] In some implementations, a nonlinear health state standard model is constructed by learning from the operating data of the unit during the initial stage of commissioning or a period after maintenance, and by associating characteristic parameters with operating condition parameters that have a significant impact on them. Let V... i Let V be the eigenvalue of the i-th characteristic parameter in a healthy state. i = f(x1,x2,...x m ), where x1, x2, ... x m These are operating parameters that have a significant impact on characteristic parameters, such as active power, head, excitation current, and cooling water inlet temperature.

[0092] During unit operation, the unit's operating data is acquired periodically, and the current operating parameters x1', x2', ... x are obtained based on the unit's operating data. m Using the standard health state model, the characteristic value Vh of the i-th characteristic parameter under the current operating condition in a healthy state can be obtained. The degradation index of this characteristic parameter can be calculated using the following formula:

[0093]

[0094] Where Vr represents the feature value of the current real-time feature parameters. ReLU is the activation function, expressed as:

[0095]

[0096] In some implementations, based on the characteristic parameters corresponding to different components in the unit, the standard model of the power generation direction health status can be divided into standard models of the health status corresponding to the corresponding structure according to the component structure. These models are used to determine the deterioration index of different components. Different models are obtained by pre-training based on the characteristic parameters and operating parameters corresponding to the component structure.

[0097] For example, active power, guide vane opening, head, and cooling water temperature have a significant impact on the characteristic parameters of pump-turbines. A standard health state model is established with active power, guide vane opening, head, and cooling water temperature as inputs and pump-turbine characteristic parameters as outputs. The training data samples of the model are pump-turbine characteristic parameters and operating condition parameters extracted from the operating data of the unit during the initial stage of commissioning or a period after maintenance.

[0098] For example, active power, guide vane opening, excitation current, and cooling water temperature have a significant impact on the characteristic parameters of the generator-motor. A standard health state model can be established, using active power, guide vane opening, excitation current, and cooling water temperature as inputs and the relevant characteristic parameters of the generator-motor as outputs. Optionally, the construction of the standard health state model can be based on a neural network model; the specific network structure is not described or limited.

[0099] S104: Determine the current value of the degradation gradient of each feature parameter based on the degradation index of each feature parameter within a predetermined time.

[0100] In this embodiment, during unit operation, as the operating time increases, a degradation index sequence GiTOS of characteristic parameters within a certain operating time can be obtained. For example... Figure 3 As shown, based on the degradation index sequence GiTOS and the time series GT of the acquired data, several data points (e.g., 3) closest to the current time are selected for linear fitting to obtain a fitted straight line. The slope of this line is determined and used as the current value of the degradation gradient of the feature parameter. The current value of the degradation gradient of the feature parameter reflects the rate of degradation of the feature parameter. If the feature parameter does not exceed the alarm threshold, but the current value of the degradation gradient of the feature parameter is large, it indicates that the feature parameter has a trend of accelerated degradation, which can reflect an abnormality in the unit's condition.

[0101] S105: Based on the relationship between the characteristic parameters of the power generation direction and the current value of the corresponding degradation gradient, and the preset alarm threshold of the power generation direction, as well as the characteristic parameters of the power generation direction and the corresponding fault level, determine the current operating status of the unit in the power generation direction.

[0102] In this embodiment, the characteristic parameters of the power generation direction and the corresponding current values ​​of the degradation gradient and alarm thresholds can be determined based on historical operating data analysis, and the specific relationships are shown in Table 1:

[0103] Table 1. Current and predicted values ​​of the degradation gradient of characteristic parameters of power generation direction, and corresponding alarm thresholds for power generation direction.

[0104]

[0105] In some embodiments, a specific fault corresponds to a corresponding set of feature parameters. Based on the feature values ​​of each feature parameter in the feature parameter set, it can be determined whether the corresponding fault has occurred. For example, fault A corresponds to feature parameter set A, which includes feature parameter 1, feature parameter 2, and feature parameter 3. When the feature values ​​of each feature parameter in feature parameter set A reach the corresponding fault threshold, it can be determined that fault A has occurred.

[0106] Based on the severity of the fault's impact on unit operation, faults can be classified into Level 1 faults and Level 2 faults. In some systems, Level 1 faults are those where the unit can continue operating with the fault until it is shut down or repaired; examples include slight dynamic imbalance in rotating parts or slight unevenness in the clearance of guide bearing bushes. Level 2 faults require the unit to be shut down for repair; otherwise, it will cause equipment damage and lead to an accidental shutdown; examples include severe inter-turn short circuits in the rotor magnetic poles or severe hydraulic imbalance.

[0107] Optionally, a first-level fault can be represented by F1i, where F represents fault, 1 represents a first-level fault, and i represents the i-th fault in the first-level fault; a second-level fault can be represented by F2j, where F represents fault, 2 represents a second-level fault, and j represents the j-th fault in the second-level fault.

[0108] Correspondingly, each level-one fault has a corresponding set of characteristic parameters, and each level-two fault has a corresponding set of characteristic parameters, as shown in Table 2:

[0109] Table 2. Correspondence between faults and characteristic parameter sets

[0110]

[0111]

[0112] As shown in Table 2, each Level 1 and Level 2 fault has a corresponding set of characteristic parameters for the power generation direction {GPi, GPj, ..., GPm} and a set of characteristic parameters for the pumping direction {PPi, PPj, ..., PPm}. The combinations of characteristic parameters in the characteristic parameter sets corresponding to different faults are different. Referring to Table 1, when the characteristic values ​​of all characteristic parameters in the characteristic parameter set corresponding to a specific fault are greater than the corresponding Level 1 alarm value, it can be determined that a specific fault has occurred.

[0113] In some embodiments, the current operating state of the unit in the power generation direction is determined based on the characteristic parameters of the power generation direction, the relationship between the current value of the degradation gradient of the characteristic parameters and the preset alarm threshold for the power generation direction, and the characteristic parameters of the power generation direction and the corresponding fault level. This includes:

[0114] The first score is determined based on the relationship between the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction;

[0115] The second score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction.

[0116] The third score is determined based on the relationship between each characteristic parameter in the set of characteristic parameters corresponding to the fault and the corresponding alarm threshold.

[0117] Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights, first score, second score, faults and their corresponding fault evaluation weights, third score, the current operating status result in the power generation direction is calculated.

[0118] In this embodiment, in the power generation direction, a first score is determined based on whether each characteristic parameter exceeds the corresponding first-level alarm value and second-level alarm value. A second score is determined based on whether the current value of the degradation gradient of the characteristic parameter is greater than the corresponding alarm value. A third score is determined based on whether the characteristic value of each characteristic parameter in the characteristic parameter set corresponding to the first-level fault and second-level fault is greater than the corresponding first-level alarm value. Then, based on the characteristic parameters and the corresponding characteristic evaluation weights, the determined first score, second score and third score, the current operating status result in the power generation direction is calculated.

[0119] In some methods, the deduction rules for the first, second, and third points can be set as follows:

[0120] When the characteristic value of a feature parameter exceeds the corresponding first-level alarm value, S1 points will be deducted.

[0121] When the characteristic value of a feature parameter exceeds the corresponding level 2 alarm value, S2 points will be deducted.

[0122] When the current value of the degradation gradient of the feature parameter is greater than the corresponding degradation gradient alarm value, deduct S1 points;

[0123] When the characteristic values ​​of all characteristic parameters in the characteristic parameter set corresponding to a Level 1 fault are greater than the corresponding Level 1 alarm value, the fault is determined to have occurred, and S3 points are deducted.

[0124] When the characteristic values ​​of all characteristic parameters in the characteristic parameter set corresponding to a level 2 fault are greater than the corresponding level 1 alarm value, the fault is determined to have occurred and S4 points are deducted.

[0125] If the feature value of a feature parameter exceeds the corresponding first-level alarm value, and the current value of the degradation gradient is greater than the corresponding degradation gradient alarm value, then S2 points will be deducted. If the feature value of the feature parameter exceeds the corresponding first-level alarm value, no further points will be deducted. If the current value of the degradation gradient of the feature parameter is greater than the corresponding degradation gradient alarm value, no further points will be deducted.

[0126] If the eigenvalue of the feature parameter exceeds the corresponding level 2 alarm value, and the current value of the degradation gradient is less than or equal to the degradation gradient alarm value, then S2 points will be deducted. If the eigenvalue of the feature parameter exceeds the corresponding level 1 alarm value, no further points will be deducted.

[0127] If the feature value of a feature parameter exceeds the corresponding level 2 alarm value, and the current value of the degradation gradient is greater than the degradation gradient alarm value, then S2 points will be deducted. If the feature value of the feature parameter exceeds the corresponding level 1 alarm value, no further points will be deducted. If the current value of the degradation gradient of the feature parameter is greater than the corresponding degradation gradient alarm value, no further points will be deducted.

[0128] If a Level 1 fault occurs, S3 points will be deducted. For all feature parameters in the feature parameter set corresponding to the Level 1 fault, if the feature value of any feature parameter exceeds the corresponding Level 1 alarm value or Level 2 alarm value, or if the current value of the degradation gradient of the feature parameter is greater than the corresponding degradation gradient alarm value, no additional points will be deducted.

[0129] If a Level 2 fault occurs, S4 points will be deducted. For all feature parameters in the feature parameter set corresponding to the Level 2 fault, if the feature value of any feature parameter exceeds the corresponding Level 1 alarm value or Level 2 alarm value, or if the current value of the degradation gradient of the feature parameter is greater than the corresponding alarm value, no further points will be deducted.

[0130] Based on the characteristic parameters of the power generation direction and their corresponding characteristic evaluation weights, first score, and second score, as well as the fault and its corresponding fault evaluation weight and third score, the current operating status result in the power generation direction is calculated. The calculation method is as follows:

[0131]

[0132] Wherein, H represents the current operating status result of the power generation direction; A1i is the first-level alarm logic variable for the i-th characteristic parameter. When the characteristic value of the i-th characteristic parameter exceeds the first-level alarm value, a first-level alarm occurs, and A1i takes the value of 1; when the characteristic value of the i-th characteristic parameter does not exceed the first-level alarm value, no first-level alarm occurs, and A1i takes the value of 0; GPiW is the characteristic evaluation weight of the i-th characteristic parameter; S1 is the first-level alarm deduction value; A2i is the second-level alarm logic variable for the i-th characteristic parameter. When the characteristic value of the i-th characteristic parameter exceeds the second-level alarm value, a second-level alarm occurs, and A2i takes the value of 1; when the characteristic value of the i-th characteristic parameter does not exceed the second-level alarm value, no second-level alarm occurs. A2i is 0, S2 is the second-level alarm deduction value; Li is the degradation alarm logic variable of the i-th feature parameter. When the current value of the degradation gradient corresponding to the i-th feature parameter is greater than the corresponding alarm value, Li is 1; when the current value of the degradation gradient corresponding to the i-th feature parameter is less than or equal to the corresponding alarm value, Li is 0; & represents a logical AND operation; F1i is the i-th first-level fault logic variable. When the i-th first-level fault occurs, F1i is 1; otherwise, it is 0; F1iW is the fault evaluation weight of the i-th first-level fault, S3 is the first-level fault deduction value; Lia is the degradation alarm logic variable of feature parameter a in the feature parameter set corresponding to the i-th first-level fault. When the current value of the degradation gradient corresponding to feature parameter a is greater than the corresponding alarm value, Lia is 1; when the current value of the degradation gradient corresponding to feature parameter a is less than or equal to the corresponding alarm value, Lia is 0. A1ia is the first-level alarm logic variable of feature parameter a in the feature parameter set corresponding to the i-th first-level fault. When the feature value of feature parameter a exceeds the first-level alarm value, A1ia is 1; otherwise, it is 0. A2ia is the second-level alarm logic variable of feature parameter a in the feature parameter set corresponding to the i-th first-level fault. When the feature value of feature parameter a exceeds the second-level alarm value, A2ia is 1; otherwise, it is 0. Lib is the first-level fault corresponding to the i-th first-level fault. The Lib variable is the degradation alarm logic variable for feature parameter b in the feature parameter set. When the current value of the degradation gradient of feature parameter b is greater than the corresponding alarm value, the Lib value is 1; when the current value of the degradation gradient of feature parameter b is less than or equal to the corresponding alarm value, the Lib value is 0. A1ib is the first-level alarm logic variable for feature parameter b in the feature parameter set corresponding to the i-th first-level fault. When the feature value of feature parameter b exceeds the first-level alarm value, A1ib is 1; otherwise, it is 0. A2ib is the second-level alarm logic variable for feature parameter b in the feature parameter set corresponding to the i-th first-level fault. When the feature value of feature parameter b exceeds the second-level alarm value, A2ib is 1; otherwise, it is 0.Lir is the degradation alarm logic variable of feature parameter r in the feature parameter set corresponding to the i-th level fault. Lir is 1 when the current value of the degradation gradient of feature parameter r is greater than the corresponding alarm value, and 0 when the current value of the degradation gradient of feature parameter r is less than or equal to the corresponding alarm value. A1ir is the level-one alarm logic variable of feature parameter r in the feature parameter set corresponding to the i-th level fault. A1ir is 1 when the feature value of feature parameter r exceeds the level-one alarm value, and 0 otherwise. A2ir is the level-two alarm logic variable of feature parameter r in the feature parameter set corresponding to the i-th level fault. A2ir is 1 when the feature value of feature parameter r exceeds the level-two alarm value, and 0 otherwise. The value is 0 when the i-th level 2 fault occurs; F2i is the logical variable for the i-th level 2 fault. When the i-th level 2 fault occurs, F2i is 1, and when it does not occur, it is 0; F2iW is the fault evaluation weight for the i-th level 2 fault; S4 is the deduction value for the level 2 fault; Lix is ​​the deterioration alarm logical variable for feature parameter x in the feature parameter set corresponding to the i-th level 2 fault. When the current value of the deterioration gradient of feature parameter x is greater than the corresponding alarm value, Lix is ​​1, and when it is not reached, it is 0; A1ix is ​​the first-level alarm logical variable for feature parameter x in the feature parameter set corresponding to the i-th level 2 fault. When the feature value of feature parameter x exceeds the first-level alarm value, A1ix is ​​1, and when it is not reached, it is 0; A2ix is ​​the logical variable for the i-th level 2 fault. The corresponding feature parameter set contains the secondary alarm logic variable for feature parameter x. A2ix takes the value 1 when the feature value of feature parameter x exceeds the secondary alarm value, and 0 otherwise. Liy is the degradation alarm logic variable for feature parameter y in the feature parameter set corresponding to the i-th secondary fault. Liy takes the value 1 when the current value of the degradation gradient of feature parameter y is greater than the corresponding alarm value, and 0 when the current value of the degradation gradient of feature parameter y is less than or equal to the corresponding alarm value. A1iy is the primary alarm logic variable for feature parameter y in the feature parameter set corresponding to the i-th secondary fault. A1iy takes the value 1 when the feature value of feature parameter y exceeds the primary alarm value, and 0 otherwise. A2iy is the... A2iy is the secondary alarm logic variable for feature parameter y in the feature parameter set corresponding to i secondary faults. When the feature value of feature parameter y exceeds the secondary alarm value, A2iy takes the value of 1, and when it does not exceed the value, it takes the value of 0. Liz is the degradation alarm logic variable for feature parameter z in the feature parameter set corresponding to the i-th secondary fault. When the current value of the degradation gradient of feature parameter z is greater than the corresponding alarm value, Liz takes the value of 1, and when the current value of the degradation gradient of feature parameter z is less than or equal to the corresponding alarm value, Liz takes the value of 0. A1iz is the primary alarm logic variable for feature parameter z in the feature parameter set corresponding to the i-th secondary fault. When the feature value of feature parameter z exceeds the primary alarm value, A1iz takes the value of 1, and when it does not exceed the value, it takes the value of 0.A2iz is the secondary alarm logic variable for characteristic parameter z in the characteristic parameter set corresponding to the i-th secondary fault. When the characteristic value of characteristic parameter z exceeds the secondary alarm value, A2iz takes the value of 1; otherwise, it takes the value of 0.

[0133] Optionally, the feature evaluation weights of characteristic parameters and the fault evaluation weights of faults can be determined comprehensively using the analytic hierarchy process (AHP) and principal component analysis (PCA). The specific values ​​of the feature evaluation weights and fault evaluation weights are not limited. The deduction values ​​for characteristic parameters and level 1 / 2 faults, and / or the feature evaluation weights and level 1 / 2 fault evaluation weights, can also be adjusted based on the offline evaluation results. For example, if the offline status evaluation result is more severe than the current operating status result, the relevant deduction values ​​and / or weights for the characteristic parameters and level 1 / 2 faults corresponding to the abnormal components in the offline status evaluation result can be appropriately increased to ensure that the current operating status result is consistent with the offline status evaluation result.

[0134] In some methods, after calculating the current operating status in the power generation direction using formula (9), the current operating status of the unit can be evaluated based on the current operating status result. For example, when the score of the calculated result is in the range of (80, 100], the current operating status is "healthy"; when the score is in the range of (60, 80], the current operating status is "sub-healthy"; when the score is in the range of (40 60], the current operating status is "abnormal"; and when the score is in the range of [0 40], the current operating status is "severe".

[0135] In some embodiments, after determining the current operating status of the unit in the power generation direction, the comprehensive evaluation result of the unit's current operating status can be determined by combining the obtained offline status evaluation results in the power generation direction. The offline status evaluation results can be obtained by acquiring various status parameters of the unit through methods such as visual inspection, flaw detection, preventative testing, and commissioning testing, and then performing offline evaluation based on these parameters.

[0136] In some methods, the comprehensive evaluation result of the unit's current operating status is determined based on the unit's current operating status and offline status evaluation results, including:

[0137] If the offline status evaluation result is normal, the current operating status comprehensive evaluation result is the current operating status.

[0138] If the offline status evaluation result is abnormal, the comprehensive evaluation result of the current operating status is the more severe state between the current operating status and the offline status evaluation result.

[0139] In this embodiment, the current operating status of the unit is comprehensively evaluated by combining the real-time determined current operating status and the acquired offline status evaluation results. If the offline status evaluation result is healthy or sub-healthy, the comprehensive evaluation result of the unit's current operating status is the current operating status. If the offline status evaluation result is abnormal or severe, and the current operating status is sub-healthy, abnormal, or severe, then the comprehensive evaluation result of the current operating status is the more severe state. For example, if the offline status evaluation result is abnormal and the current operating status is severe, then the comprehensive evaluation result of the current operating status is severe. In this way, by determining the comprehensive evaluation result of the unit's current operating status, corresponding handling measures or maintenance plans can be formulated in a timely manner. A suitable operation and maintenance scheme can be determined based on the actual operating status of the unit, avoiding problems that may be caused by improper maintenance and improving the safe and stable performance of the unit's operation.

[0140] S201: Obtain pumping operation data of the unit under steady-state conditions in the pumping direction;

[0141] S202: Extract characteristic parameters of the pumping direction and operating parameters from pumping operation data;

[0142] In this embodiment, pumping operation data of the unit under steady-state conditions in the pumping direction is obtained from the unit status monitoring system. Based on the obtained pumping operation data, characteristic parameters in the pumping direction are extracted, including unit vibration amplitude, unit vibration effective value, unit vibration signal entropy, main shaft swing amplitude, main shaft swing signal entropy, water pressure pulsation amplitude, water pressure pulsation signal entropy, rotational frequency amplitude, unbalance phase, blade overcurrent frequency amplitude, 2 times blade overcurrent frequency amplitude, 3 times blade overcurrent frequency amplitude, 2 times rotational frequency amplitude, upper guide bearing temperature and oil tank temperature, thrust bearing temperature and oil tank temperature, water guide bearing temperature and oil tank temperature, maximum air gap value, minimum air gap value, air gap non-uniformity, stator core temperature, stator bar temperature, magnetic pole flux density, etc.

[0143] Optionally, the characteristic parameters of the pumping direction can be represented as PP1, PP2, ..., PPn, where the first P represents the pump and the second P represents the characteristic parameter.

[0144] S203: Based on the characteristic parameters and operating parameters of the pumping direction, and using the preset standard model of the health status of the pumping direction, determine the deterioration index of each characteristic parameter of the pumping direction.

[0145] S204: Determine the current value of the degradation gradient of each feature parameter based on the degradation index of each feature parameter within a predetermined time.

[0146] In this embodiment, using the characteristic parameters and operating parameters of the unit under steady-state conditions in the pumping direction as data samples, a standard model for the pumping direction health status is pre-trained and constructed to determine the deterioration index corresponding to the characteristic parameters. After extracting the characteristic parameters and operating parameters of the pumping direction based on the currently acquired real-time pumping operation data, these parameters are used as inputs to the standard model for the pumping direction health status, which then outputs the deterioration index for the pumping direction. Optionally, the current deterioration trend value in the pumping direction can be represented as PjT0.

[0147] As the unit's operating time increases, a degradation index sequence PjT0S of characteristic parameters within a certain operating time can be obtained. Based on the degradation index sequence PjT0S and the time series PT of the acquired data, several data points closest to the current time are selected for linear fitting to obtain a fitted straight line. The slope of this straight line is determined and used as the current value of the degradation gradient of the characteristic parameters.

[0148] S205: Based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the pumping direction and the preset alarm threshold in the pumping direction, and the characteristic parameters and corresponding fault levels in the pumping direction, determine the current operating status of the unit in the pumping direction.

[0149] In this embodiment, the current value of the deterioration gradient in the pumping direction and the corresponding alarm threshold in the pumping direction can be determined based on historical operation data analysis, and the specific relationship is shown in Table 3:

[0150] Table 3. Current and predicted values ​​of the deterioration gradient in the pumping direction, and corresponding alarm thresholds for the pumping direction.

[0151]

[0152] Based on the relationship between the characteristic parameters of the pumping direction, the current value of the degradation gradient, and the preset alarm threshold for the pumping direction, and the characteristic parameters of the pumping direction and their corresponding fault levels, the current operating status of the unit in the pumping direction is determined, including:

[0153] The fourth score is determined based on the relationship between the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction.

[0154] The fifth score is determined based on the relationship between the current value of the deterioration gradient in the pumping direction and the alarm threshold in the pumping direction.

[0155] The sixth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0156] Based on the characteristic parameters of the pumping direction and their corresponding characteristic evaluation weights, fourth score, and fifth score, as well as the fault and its corresponding fault evaluation weight and sixth score, the current operating status result in the pumping direction is calculated.

[0157] In this embodiment, referring to Tables 2 and 3, in the pumping direction, the fourth score is determined based on whether each characteristic parameter exceeds the corresponding first-level alarm value and second-level alarm value; the fifth score is determined based on whether the current value of the degradation gradient corresponding to the characteristic parameter is greater than the corresponding degradation gradient alarm value; and the sixth score is determined based on whether the characteristic value of each characteristic parameter in the characteristic parameter set corresponding to the first-level fault and second-level fault is greater than the corresponding first-level alarm value. Then, based on the characteristic parameters and their corresponding characteristic evaluation weights, and the determined fourth, fifth, and sixth scores, the current operating status result in the pumping direction is calculated. The method for calculating the operating status result in the pumping direction can be calculated according to formula (11), where each parameter is a characteristic parameter, alarm value, etc. in the pumping direction, which will not be repeated here.

[0158] After determining the unit's current operating status in the pumping direction, the comprehensive evaluation result of the unit's current operating status can be determined by combining the obtained offline status evaluation results in the pumping direction. If the offline status evaluation result is normal, the comprehensive evaluation result of the current operating status is based on the current operating status; if the offline status evaluation result is abnormal, the comprehensive evaluation result of the current operating status is the more severe state between the current operating status and the offline status evaluation results. After determining the comprehensive evaluation result of the unit's current operating status, corresponding handling measures or maintenance plans can be formulated in a timely manner under pumping conditions.

[0159] In some embodiments, the method for detecting the operating status of pumped storage units further includes:

[0160] Using a pre-defined power generation direction trend prediction model, the future predicted values ​​of each characteristic parameter of the power generation direction are determined;

[0161] Based on the relationship between the future predicted values ​​of each characteristic parameter in the power generation direction and the alarm threshold in the power generation direction, and the characteristic parameters in the power generation direction and their corresponding fault levels, the operating status of the unit in the power generation direction after a predetermined time is determined; and / or,

[0162] The future predicted values ​​of each characteristic parameter of the pumping direction are determined by using the pumping direction trend prediction model;

[0163] Based on the relationship between the future predicted values ​​of each characteristic parameter in the pumping direction and the alarm threshold in the pumping direction, and the characteristic parameters in the pumping direction and their corresponding fault levels, the operating status of the unit in the pumping direction after a predetermined time is determined.

[0164] In this embodiment, regarding the power generation direction, feature parameters of the power generation direction can be extracted based on the currently acquired real-time power generation operation data. These feature parameters are then used as input to the power generation direction trend prediction model, which outputs the future predicted values ​​of each feature parameter. The future predicted values ​​include the feature parameter prediction values ​​for the next 3 days, 7 days, and 15 days. The future predicted value of the power generation direction can be represented as GiT1.

[0165] Based on the relationship between the future predicted values ​​of the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction, and the characteristic parameters of the power generation direction and their corresponding fault levels, the operating status of the unit in the power generation direction after a predetermined time is determined, including:

[0166] The seventh score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction.

[0167] The eighth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0168] Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights and seventh score, the fault and the corresponding fault evaluation weights and eighth score are used to calculate the operating status result of the power generation direction after a predetermined time.

[0169] In this embodiment, in the power generation direction, a seventh score is determined based on whether the future predicted value corresponding to each characteristic parameter exceeds the corresponding first-level alarm value and second-level alarm value. An eighth score is determined based on whether the characteristic value of each characteristic parameter in the characteristic parameter set corresponding to the first-level fault and second-level fault is greater than the corresponding first-level alarm value. Then, based on the characteristic parameters and their corresponding characteristic evaluation weights, the determined seventh score, and the eighth score, the operating status result of the power generation direction after a predetermined time is calculated. The calculation method is as follows:

[0170]

[0171] In terms of the pumping direction, feature parameters of the pumping direction can be extracted based on the currently acquired real-time pumping operation data. These feature parameters are then used as input to the pumping direction trend prediction model, which outputs the future predicted value of the pumping direction. The future predicted value of the pumping direction can be represented as PjT1.

[0172] Based on the relationship between the predicted future values ​​of the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction, and the characteristic parameters of the pumping direction and their corresponding fault levels, the operating status of the unit in the pumping direction after a predetermined time is determined, including:

[0173] The ninth score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction.

[0174] The tenth value is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold.

[0175] Based on the characteristic parameters of the pumping direction and the corresponding characteristic evaluation weights and the ninth score, the fault and the corresponding fault evaluation weights and the tenth score, the operating status results of the pumping direction after a predetermined time are calculated.

[0176] In this embodiment, in the pumping direction, the ninth score is determined based on whether the future predicted value of each characteristic parameter exceeds the corresponding first-level alarm value and second-level alarm value. The tenth score is determined based on whether the characteristic value of each characteristic parameter in the characteristic parameter set corresponding to the first-level fault and second-level fault is greater than the corresponding first-level alarm value. Then, based on the characteristic parameters and the corresponding characteristic evaluation weights, the determined ninth score and tenth score, the operating status result of the pumping direction after the predetermined time is calculated according to formula (10).

[0177] In some embodiments, after determining the operating status of the unit after a predetermined time in the direction of power generation or pumping, the operating status of the unit after a predetermined time in the future can be predicted, thereby allowing for advance inspection and handling of the unit to avoid deterioration of the unit's health status and the occurrence of accidents, and improving the safe and stable operation performance of the unit.

[0178] The pumped storage unit operation status detection method provided in this application acquires operation data during unit operation, extracts characteristic parameters and operating condition parameters from the operation data, determines the degradation index of each characteristic parameter using a health status standard model based on the characteristic parameters and operating condition parameters, determines the current value of the degradation gradient based on the degradation index, determines the current operation status of the unit based on the relationship between each characteristic parameter and the corresponding current value of the degradation gradient and the preset alarm threshold, and the characteristic parameters and their corresponding fault levels, and determines the comprehensive evaluation result of the current operation status of the unit by combining the current operation status and offline status evaluation results, and determines a suitable operation and maintenance plan based on the comprehensive evaluation result of the current operation status. This can avoid the problems of planned maintenance and improve the safety and stability of unit operation.

[0179] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0180] It should be noted that the above description describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0181] like Figure 4 As shown in the embodiment of this application, an operating status detection device for a pumped storage unit is also provided, comprising:

[0182] The acquisition module is used to acquire power generation operation data of the unit under steady-state conditions in the power generation direction; and / or, to acquire pumping operation data of the unit under steady-state conditions in the pumping direction;

[0183] The extraction module is used to extract characteristic parameters of the power generation direction and operating condition parameters from power generation operation data; and / or, to extract characteristic parameters of the pumping direction and operating condition parameters from pumping operation data.

[0184] The prediction module is used to determine the degradation index of each characteristic parameter of the power generation direction based on the characteristic parameters and operating parameters of the power generation direction and using a preset standard model of the health status of the power generation direction; and / or, based on the characteristic parameters and operating parameters of the pumping direction and using a preset standard model of the health status of the pumping direction, determine the degradation index of each characteristic parameter of the pumping direction.

[0185] The gradient determination module is used to determine the current value of the degradation gradient of each characteristic parameter in the power generation direction based on the degradation index of each characteristic parameter in the power generation direction within a predetermined time; and / or, to determine the current value of the degradation gradient of each characteristic parameter in the pumping direction based on the degradation index of each characteristic parameter in the pumping direction within a predetermined time.

[0186] The status determination module is used to determine the current operating status of the unit in the power generation direction based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the power generation direction and the preset alarm threshold in the power generation direction, as well as the characteristic parameters in the power generation direction and the corresponding fault level; and / or, based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the pumping direction and the preset alarm threshold in the pumping direction, as well as the characteristic parameters in the pumping direction and the corresponding fault level, to determine the current operating status of the unit in the pumping direction.

[0187] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware.

[0188] The apparatus described above is used to implement the corresponding methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0189] Figure 5 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0190] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0191] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0192] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0193] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0194] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0195] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0196] The electronic devices described above are used to implement the corresponding methods in the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0197] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0198] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0199] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0200] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0201] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this disclosure.

Claims

1. A method for detecting the operating status of a pumped storage unit, characterized in that, include: Acquire power generation operation data of the unit under steady-state operating conditions in the power generation direction; Extract characteristic parameters of power generation direction and operating condition parameters from the power generation operation data; Based on the characteristic parameters and operating parameters of the power generation direction, the degradation index of each characteristic parameter of the power generation direction is determined using a preset standard model of the health status of the power generation direction. Based on the degradation index of each feature parameter within a predetermined time, determine the current value of the degradation gradient of each feature parameter; Based on the relationship between the current values ​​of the characteristic parameters and corresponding degradation gradients in the power generation direction and the preset alarm threshold for the power generation direction, and the characteristic parameters and corresponding fault levels in the power generation direction, the current operating status of the unit in the power generation direction is determined, including: The first score is determined based on the relationship between the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction; The second score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction. The third score is determined based on the relationship between each characteristic parameter in the set of characteristic parameters corresponding to the fault and the corresponding alarm threshold. Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights, first score, second score, fault and the corresponding fault evaluation weights, third score, calculate the current operating status result in the power generation direction; And / or, Acquire pumping operation data of the unit under steady-state conditions in the pumping direction; Extract the characteristic parameters of the pumping direction and the operating parameters from the pumping operation data; Based on the characteristic parameters and operating parameters of the pumping direction, the degradation index of each characteristic parameter of the pumping direction is determined using a preset standard model of the health status of the pumping direction. Based on the degradation index of each feature parameter within a predetermined time, determine the current value of the degradation gradient of each feature parameter; Based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the pumping direction and the preset alarm threshold in the pumping direction, the characteristic parameters in the pumping direction and the corresponding fault level are used to determine the current operating status of the unit in the pumping direction.

2. The method according to claim 1, characterized in that, Also includes: Using a pre-defined power generation direction trend prediction model, the future predicted values ​​of each characteristic parameter of the power generation direction are determined; Based on the relationship between the future predicted value of the power generation direction and the alarm threshold of the power generation direction, the characteristic parameters of the power generation direction and the corresponding fault level, the operating status of the unit in the power generation direction after a predetermined time is determined; and / or, Using a pre-defined pumping direction trend prediction model, the future predicted values ​​of each characteristic parameter of the pumping direction are determined; Based on the relationship between the future predicted value of the pumping direction and the alarm threshold of the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level, the operating status of the unit after a predetermined time in the pumping direction is determined.

3. The method according to claim 1, characterized in that, Based on the relationship between the characteristic parameters of the pumping direction and the corresponding current value of the degradation gradient, and the preset alarm threshold for the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level are used to determine the current operating status of the unit in the pumping direction, including: The fourth score is determined based on the relationship between the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction. The fifth score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction. The sixth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold. Based on the characteristic parameters of the pumping direction and the corresponding characteristic evaluation weights, fourth score, and fifth score, as well as the fault and the corresponding fault evaluation weight and sixth score, the current operating status result in the pumping direction is calculated.

4. The method according to claim 2, characterized in that, Also includes: Based on the relationship between the future predicted value of the power generation direction and the alarm threshold of the power generation direction, the characteristic parameters of the power generation direction and the corresponding fault level are used to determine the operating status of the unit in the power generation direction after a predetermined time, including: The seventh score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction. The eighth score is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold. Based on the characteristic parameters of the power generation direction and the corresponding characteristic evaluation weights and seventh score, the fault and the corresponding fault evaluation weights and eighth score are used to calculate the operating status result of the power generation direction after a predetermined time.

5. The method according to claim 2, characterized in that, Also includes: Based on the relationship between the predicted future value of the pumping direction and the alarm threshold of the pumping direction, the characteristic parameters of the pumping direction and the corresponding fault level, the operating status of the unit in the pumping direction after a predetermined time is determined, including: The ninth score is determined based on the relationship between the future predicted value corresponding to the characteristic parameters of the pumping direction and the alarm threshold of the pumping direction. The tenth value is determined based on the relationship between each characteristic parameter in the fault and its corresponding characteristic parameter set and the corresponding alarm threshold. Based on the characteristic parameters of the pumping direction and the corresponding characteristic evaluation weights and the ninth score, the fault and the corresponding fault evaluation weights and the tenth score, the operating status results of the pumping direction after a predetermined time are calculated.

6. The method according to claim 1, characterized in that, Also includes: Based on the current operating status and the obtained offline status evaluation results, the comprehensive evaluation result of the unit's current operating status is determined.

7. The method according to claim 6, characterized in that, Based on the current operating status and the obtained offline status evaluation results, the comprehensive evaluation result of the unit's current operating status is determined, including: If the offline status evaluation result is normal, the current operating status comprehensive evaluation result is the current operating status; If the offline status evaluation result is abnormal, the current operating status comprehensive evaluation result is the state corresponding to the more severe one between the current operating status and the offline status evaluation result.

8. The method according to claim 1, characterized in that, The step of determining the current value of the degradation gradient of each feature parameter based on the degradation index of each feature parameter within a predetermined time includes: Based on the degradation index sequence and corresponding time series formed within a predetermined time period, select several data points that are closest to the current time. A linear fit is performed on the selected data points to obtain the fitted straight line; Determine the slope of the line and use that slope as the current value of the degradation gradient.

9. A device for detecting the operating status of a pumped storage unit, characterized in that, include: The acquisition module is used to acquire the power generation operation data of the unit under steady-state conditions in the power generation direction; And / or, obtain pumping operation data of the unit under steady-state conditions in the pumping direction; The extraction module is used to extract characteristic parameters of the power generation direction and operating condition parameters from the power generation operation data; and / or to extract characteristic parameters of the pumping direction and operating condition parameters from the pumping operation data. The prediction module is used to determine the degradation index of each characteristic parameter of the power generation direction based on the characteristic parameters and operating parameters of the power generation direction and using a preset standard model of the health status of the power generation direction; and / or, based on the characteristic parameters and operating parameters of the pumping direction and using a preset standard model of the health status of the pumping direction, determine the degradation index of each characteristic parameter of the pumping direction. The gradient determination module is used to determine the current value of the degradation gradient of each characteristic parameter in the power generation direction based on the degradation index of each characteristic parameter in the power generation direction within a predetermined time; and / or, to determine the current value of the degradation gradient of each characteristic parameter in the pumping direction based on the degradation index of each characteristic parameter in the pumping direction within a predetermined time. The status determination module is used to determine the current operating status of the unit in the power generation direction based on the relationship between the current value of each characteristic parameter and the corresponding degradation gradient in the power generation direction and a preset alarm threshold for the power generation direction, as well as the characteristic parameters of the power generation direction and their corresponding fault levels. This includes: The first score is determined based on the relationship between the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction; The second score is determined based on the relationship between the current value of the degradation gradient of the characteristic parameters of the power generation direction and the alarm threshold of the power generation direction. The third score is determined based on the relationship between each characteristic parameter in the set of characteristic parameters corresponding to the fault and the corresponding alarm threshold. Based on the characteristic parameters of the power generation direction and their corresponding characteristic evaluation weights, first score, and second score, the fault and its corresponding fault evaluation weight and third score, the current operating status result in the power generation direction is calculated; and / or, based on the relationship between the current value of each characteristic parameter and its corresponding degradation gradient in the pumping direction and the preset alarm threshold in the pumping direction, and the characteristic parameters of the pumping direction and their corresponding fault levels, the current operating status of the unit in the pumping direction is determined.

Images