Method for monitoring and judging quality of real-time state data of hydroelectric equipment

Abstract

The invention discloses a hydroelectric equipment real-time state data quality monitoring and discriminating method, which belongs to the technical field of hydroelectric equipment monitoring, and comprises the following steps: collecting measuring point data and working condition related parameters, and carrying out classified storage; performing classification processing according to the number of the measuring points to obtain index category labels, and establishing a data quality discrimination model; establishing a communication state discrimination model to carry out silent condition detection processing to obtain a communication state discrimination result of each measuring point; if the communication is interrupted, pushing alarm information; if the communication is normal, triggering all the data quality discrimination models in parallel to obtain a data quality discrimination result; if yes, alarm information is pushed, and a database containing working condition related parameter labels is updated based on the corrected standard value of the measuring point data of the current abnormal measuring point; and if normal, pushing state information, and updating the database containing the working condition associated parameter tag. According to the invention, the problem of monitoring failure caused by unstable data quality and communication interruption in hydroelectric equipment operation in the prior art is solved.

Description

Technical Field

[0001] The invention relates to a method for monitoring and distinguishing the quality of real-time status data of hydropower equipment, and belongs to the technical field of hydropower equipment monitoring. Background Art

[0002] In the field of hydropower equipment operation monitoring, existing technologies typically use a multi-layered architecture to implement equipment status monitoring and data transmission. Core components include sensor networks deployed in key locations such as generators, transformers, and water pipelines to collect equipment operating parameters in real time. Data acquisition modules pre-process sensor signals and transmit data to a monitoring center via wired or wireless communication networks. The monitoring center stores, analyzes, and visualizes data based on a SCADA system or industrial IoT platform, and uses preset thresholds or simple algorithm models to provide anomaly warnings. Some advanced systems also introduce edge computing nodes for localized data filtering and preliminary diagnosis to reduce the burden on central servers. This architecture enables remote monitoring of the operating status of hydropower equipment through layered collaboration, providing data support for operation and maintenance decisions.

[0003] However, existing technologies still have significant drawbacks in the complex operating scenarios of hydropower equipment. First, sensors are susceptible to signal drift or noise interference due to strong electromagnetic interference from hydropower stations, humid environments, and equipment vibration, leading to distorted collected data. During data transmission, poor communication protocol compatibility or overly simplified compression algorithms can further cause the loss of critical information, such as vibration waveform distortion, making it difficult for monitoring centers to accurately restore the equipment's true status. Second, wired networks are prone to line interruptions due to geological disasters or aging equipment, while wireless networks are frequently disconnected due to coverage blind spots in the remote locations of hydropower stations and inclement weather. Existing technologies lack breakpoint resumption and local caching mechanisms. Once communication is interrupted, historical data is lost and real-time status cannot be updated, causing the monitoring system to enter a "blind spot." Operations and maintenance personnel are unable to respond to sudden failures in a timely manner, significantly increasing the risk of equipment damage and maintenance costs. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for monitoring and distinguishing the real-time status data quality of hydropower equipment. By collecting the measurement point data and working condition-related parameters of the hydropower operating equipment in real time, building a hierarchical database and implementing measurement point classification and multi-model dynamic discrimination, combined with communication status detection and data quality discrimination, the method solves the problem of unstable data quality and monitoring failure caused by communication interruption in the operation of hydropower equipment in the existing technology, thereby ensuring data accuracy and system operation reliability.

[0005] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions:

[0006] The present invention provides a method for monitoring and distinguishing the quality of real-time status data of hydropower equipment, comprising:

[0007] Real-time collection of measurement point data and working condition-related parameters corresponding to each measurement point of hydropower operating equipment;

[0008] The measuring point data includes switch quantity, state quantity and analog quantity, and the working condition related parameters include load rate, water head height and equipment operation mode;

[0009] The measurement point data is classified and stored according to the equipment-component-indicator-measurement point hierarchy and a database containing labels of working condition-related parameters is constructed;

[0010] According to the number of measurement points associated with each indicator, the indicator category label is obtained and a data quality discrimination model is established;

[0011] By establishing a communication status discrimination model, each measuring point is subjected to a silent condition detection process to obtain the communication status discrimination result of each measuring point;

[0012] If the communication status is judged as communication interruption, an alarm message will be pushed;

[0013] If the communication status judgment result is normal, the data quality judgment model corresponding to all indicator category labels is triggered in parallel to obtain the data quality judgment result;

[0014] If the data quality judgment result is abnormal, an alarm message is pushed, and the standard value of the measurement point data of the current abnormal measurement point is corrected. Based on the corrected standard value of the measurement point data of the current abnormal measurement point, the database containing the working condition related parameter tags is updated;

[0015] If the data quality judgment result is normal, the status information is pushed, and the database containing the working condition associated parameter tags is updated based on the measurement point data of all current measurement points.

[0016] Furthermore, the communication state discrimination model includes a first communication state discrimination model and a second communication state discrimination model;

[0017] The first communication status determination model is used to determine whether the communication status determination result is communication interruption or normal communication, including:

[0018] If the current measurement point satisfies , then the communication status of the current measuring point is judged to be communication interruption;

[0019] If the current measurement point does not meet , then the communication status of the current measuring point is judged to be normal;

[0020] in, Indicates the current time T i The actual measured value of measuring point A, Indicates the last moment Ti-a The actual measured value of measuring point A, 、 is a positive integer and satisfies ;

[0021] The second communication state discrimination model is used to perform a silent condition detection process on each measuring point to obtain a communication state discrimination result of each measuring point, including:

[0022] Based on the measurement point data corresponding to each measurement point, the state jump frequency and duration of the switch quantity, the data refresh cycle of the state quantity, and the numerical fluctuation amplitude of the analog quantity are monitored respectively within the preset time period;

[0023] Calculating a switch quantity quiet factor according to the actual state transition frequency and the rated state transition frequency of the switch quantity, wherein the switch quantity quiet factor = 1 - (actual state transition frequency / rated state transition frequency);

[0024] Calculate the state quantity quiet factor according to the actual data refresh cycle and the rated data refresh cycle of the state quantity, wherein the state quantity quiet factor=1-(actual data refresh cycle / rated data refresh cycle);

[0025] Calculating an analog quantity quiet factor according to an actual value fluctuation amplitude and a rated value fluctuation amplitude of the analog quantity, wherein the analog quantity quiet factor=1-(actual value fluctuation amplitude / rated value fluctuation amplitude);

[0026] Calculate a comprehensive silence index according to the switch quantity silence factor, the state quantity silence factor, and the analog quantity silence factor, wherein the comprehensive silence index=(switch quantity silence factor+state quantity silence factor+analog quantity silence factor) / 3;

[0027] When the comprehensive silence index is greater than a preset first threshold and the duration is greater than a preset second threshold, it is determined that the communication is interrupted; otherwise, it is determined that the communication is normal.

[0028] Furthermore, the indicator category labels include L1 indicators and L2 indicators, wherein:

[0029] If the number of measurement points associated with each indicator is greater than 2, it is determined to be an L1 indicator;

[0030] If the number of measurement points associated with each indicator is less than or equal to 2, it is judged to be an L2 indicator.

[0031] Furthermore, a first data quality discrimination model and a second data quality discrimination model are established according to the L1 index and the L2 index respectively;

[0032] The first data quality discrimination model includes a distance analysis module and a MAD optimization module;

[0033] The distance analysis module is used to calculate the Mahalanobis distance of the data distribution between the measuring points according to the measuring point data corresponding to all measuring points under a certain type of indicator to filter out abnormal measuring points;

[0034] The MAD optimization module is used to introduce the degradation coefficient into the median absolute deviation (MAD) to calculate the data quality judgment threshold of the measurement point data corresponding to all measurement points under a certain type of indicator, and to judge abnormal measurement points that exceed the indicator data quality judgment threshold as data quality abnormalities, thereby generating a data quality judgment result;

[0035] The second data quality discrimination model includes a working condition parameter extraction and matching module and a weighted range calculation module;

[0036] The operating condition parameter extraction and matching module is used to extract the operating condition associated parameters of the current measuring point from a database containing operating condition associated parameter tags and match them with a historical database containing operating condition associated parameter tags to obtain the normal value range and standard deviation of the operating condition associated parameters of the current measuring point;

[0037] The weighted range calculation module is used to calculate the allowable deviation range of the working condition associated parameters of the current measuring point based on the seasonal correction coefficient and the standard deviation of the working condition associated parameters of the current measuring point, and generate a data quality judgment result based on the normal value range of the working condition associated parameters of the current measuring point and the allowable deviation range of the working condition associated parameters of the current measuring point.

[0038] Furthermore, the Mahalanobis distance of the data distribution between the measuring points is calculated based on the measuring point data corresponding to all measuring points under a certain type of indicator to screen out abnormal measuring points, including:

[0039] Perform Z-score standardization on the actual measured values ​​of the measurement point data corresponding to all measurement points under a certain type of indicator to obtain the standardized measurement point data corresponding to all measurement points;

[0040] Based on the standardized measurement point data corresponding to all measurement points, a matrix between measurement points is constructed to calculate the Mahalanobis distance values ​​of all measurement points;

[0041] If the Mahalanobis distance value of the current measuring point data is greater than the preset distance value alarm threshold, the current measuring point will be marked as an abnormal measuring point.

[0042] Furthermore, the degradation coefficient is introduced into the median absolute deviation (MAD) to calculate the data quality judgment threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. Abnormal measurement points that exceed the indicator data quality judgment threshold are judged as data quality anomalies, and the data quality judgment results are generated, including:

[0043] The degradation coefficient is calculated based on the equipment operation time and the preset equipment life, wherein the calculation formula of the degradation coefficient is expressed as:

[0044]

[0045] Where, represents the unit degradation coefficient, Indicates the unit degradation coefficient of a certain type of indicator in the last overhaul cycle The maximum absolute value, Indicates the first appearance The corresponding moment, Indicates the unit degradation coefficient of a certain type of indicator at the time of resumption of production during the last overhaul cycle The initial value of Indicates the first appearance The time corresponding to the time, T represents the overhaul cycle, 、 They are The weight coefficient of

[0046] Extract the sliding time window of the measurement points under the health status of the equipment and calculate the median absolute deviation (MAD) of the measurement point data corresponding to all measurement points under a certain type of indicator within the sliding time window;

[0047] The degradation coefficient is introduced into the median absolute deviation (MAD) to calculate and generate the data quality discrimination threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. The calculation formula of the data quality discrimination threshold is expressed as follows:

[0048] ;

[0049] Where, represents the data quality judgment threshold, Indicates the median absolute deviation of the measurement point data corresponding to a certain measurement point;

[0050] Perform real-time quality judgment on the measurement point data corresponding to all measurement points under a certain type of indicator, including:

[0051] When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is greater than the data quality judgment threshold, the data quality judgment result is judged to be abnormal;

[0052] When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is less than or equal to the data quality judgment threshold, the data quality judgment result is judged to be normal.

[0053] Furthermore, the working condition-related parameters of the current measuring point are extracted from a database containing working condition-related parameter tags and matched with a historical database containing working condition-related parameter tags to obtain the normal value range and standard deviation of the working condition-related parameters of the current measuring point, including:

[0054] Extracting the working condition associated parameters of the current measuring point from a database containing working condition associated parameter tags;

[0055] According to the working condition associated parameters of the current measuring point, similarity matching is performed based on preset matching rules in a historical database containing the working condition associated parameters to filter the historical working condition associated parameters of the current measuring point;

[0056] According to the historical working condition related parameters of the current measuring point, the normal value range and standard deviation of the working condition related parameters of the current measuring point are calculated.

[0057] Furthermore, the allowable deviation range of the working condition-related parameters of the current measuring point is calculated based on the seasonal correction coefficient and the standard deviation of the working condition-related parameters of the current measuring point, and the data quality judgment result is generated based on the normal value range of the working condition-related parameters of the current measuring point and the allowable deviation range of the working condition-related parameters of the current measuring point, including:

[0058] Calculate the seasonal correction factor based on the difference between the current ambient temperature and the standard temperature;

[0059] Calculate the allowable deviation range of the working condition-related parameters of the current measuring point based on the standard deviation and seasonal correction coefficient of the working condition-related parameters of the current measuring point;

[0060] If the actual measured value of the working condition-related parameter of the current measuring point is within the normal value range, the data quality judgment result is judged to be normal;

[0061] If the actual measured value of the working condition associated parameter of the current measuring point is within the allowable deviation range but exceeds the normal value range, or the actual measured value exceeds the allowable deviation range, the data quality judgment result is judged to be abnormal.

[0062] Furthermore, the standard value of the measurement point data of the current abnormal measurement point is corrected, including:

[0063] Based on the actual measurement values ​​of all measuring points at the current moment from the last overhaul period of the unit and the time interval from the last inspection and repair to the current moment, the standard value of the measuring point data of the current abnormal measuring point is corrected to obtain the corrected standard value of the measuring point data of the current abnormal measuring point.

[0064] Furthermore, the standard value of the corrected measurement point data of the current abnormal measurement point is expressed as:

[0065] ;

[0066] Where, Indicates the corrected standard value of the measurement point data of the current abnormal measurement point. Indicates the standard value of the measurement point data of the current abnormal measurement point, Indicates the time period of the unit’s most recent overhaul. Indicates the time interval from the last inspection and restoration of the unit to the current moment. Indicates the The actual measurement value of the measuring point data corresponding to each measuring point at the current moment.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. The present invention achieves full coverage of the equipment operating status by synchronously collecting measuring point data such as switch quantities, state quantities, and analog quantities, and combining them with working condition related parameters such as load rate and head height, effectively solving the data island problem in traditional monitoring and improving the accuracy of data association analysis; the present invention also adopts a four-level hierarchical structure of equipment-component-indicator-measuring point to store data, and adds working condition parameter labels to make massive heterogeneous data traceable; the present invention innovatively classifies and models indicators according to the number of measuring points, and constructs dedicated quality discrimination models for different categories, reducing the misjudgment rate; the present invention identifies communication interruptions through silent detection, and innovatively adopts a parallel triggering multi-model discrimination strategy to improve the efficiency of data repair in the interrupted state, while ensuring the freshness of data in the continuous communication state through real-time database updates.

[0069] 2. The present invention divides the indicators into L1 and L2 indicators according to the number of measuring points, and constructs a first data quality discrimination model based on the Mahalanobis distance and the optimized MAD model, respectively, and a second data quality discrimination model based on the matching of working condition-related parameters and weighted range calculation. The L1 indicators use multi-measurement point collaborative analysis, combined with the Mahalanobis distance to eliminate abnormal data, and introduce the degradation coefficient to calculate the MAD threshold, thereby reducing the misjudgment rate during the equipment aging stage; the L2 indicators calculate the dynamic allowable range through historical working condition-related parameter matching and seasonal correction, solving the problem of false alarms under conditions with few measuring points and improving the reliability of single-measurement point data. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 The present invention provides a flow chart of a method for monitoring and distinguishing the quality of real-time status data of hydropower equipment. DETAILED DESCRIPTION

[0071] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0072] The term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Additionally, the character " / " generally indicates an "or" relationship between the related objects.

[0073] Example 1

[0074] like Figure 1 As shown, this embodiment introduces a method for monitoring and determining the quality of real-time status data of hydropower equipment, including:

[0075] Step 1: Collect the measurement point data and working condition-related parameters corresponding to each measurement point of the hydropower operation equipment in real time.

[0076] In the present invention, the measuring point data include switch quantity, state quantity and analog quantity, and the working condition related parameters include load rate, water head height and equipment operation mode.

[0077] The present invention realizes full-dimensional perception of the operating status of hydropower equipment and correlation analysis of the working environment by real-time collection of multiple types of measuring point data such as switch quantity, state quantity, analog quantity, as well as load rate, head height, and equipment operating mode, providing a high-granularity and strongly correlated original data basis for subsequent data analysis, significantly improving the integrity and accuracy of equipment status monitoring.

[0078] Step 2: Classify and store the measurement point data according to the equipment-component-indicator-measurement point hierarchy and build a database containing working condition-related parameter labels.

[0079] The present invention constructs a four-level structured database of equipment-component-indicator-measuring point and embeds working condition-related parameter tags to achieve standardized organization and multi-dimensional retrieval of data, effectively solving the fragmentation problem of traditional data storage. At the same time, it supports rapid data screening by equipment level or working condition, greatly improving data reuse efficiency and cross-scenario analysis capabilities.

[0080] Step 3: Classify the indicators according to the number of measurement points associated with each indicator to obtain the indicator category label and establish a data quality discrimination model.

[0081] The present invention implements a differentiated data quality verification strategy by dynamically classifying indicator labels based on the number of measuring points and constructing a targeted data quality discrimination model. It not only reduces the misjudgment rate of noise interference at a single measuring point, but also improves the logical rigor of collaborative analysis of multiple measuring points, significantly enhancing the accuracy and adaptability of data quality assessment.

[0082] Step 4: By establishing a communication status discrimination model, a silent condition detection process is performed on each measuring point to obtain the communication status discrimination result of each measuring point.

[0083] If the communication status is judged to be communication interruption, an alarm message will be pushed.

[0084] If the communication status judgment result is that the communication is normal, the data quality judgment models corresponding to all indicator category labels are triggered in parallel to obtain the data quality judgment result.

[0085] The present invention establishes a communication status discrimination model and performs silent condition detection on the measuring points to realize the identification and immediate alarm of communication interruption faults. At the same time, it triggers a multi-level data quality discrimination model in parallel for the normal communication measuring points. On the basis of ensuring communication reliability, the efficiency of data quality analysis is improved through parallel computing, effectively shortening the abnormality detection response cycle.

[0086] Step 5: Determine the status of data quality judgment results:

[0087] If the data quality judgment result is abnormal, an alarm message is pushed, and the standard value of the measurement point data of the current abnormal measurement point is corrected. Based on the corrected standard value of the measurement point data of the current abnormal measurement point, the database containing the working condition associated parameter label is updated.

[0088] If the data quality judgment result is normal, the status information is pushed, and the database containing the working condition associated parameter tags is updated based on the measurement point data of all current measurement points.

[0089] The present invention constructs a closed-loop correction mechanism driven by data quality results, dynamically corrects the standard values ​​of abnormal measurement point data and synchronously updates the database to ensure the real-time accuracy of data storage; for normal data, the timeliness of the data is maintained through full database updates, forming an automated operation and maintenance chain of "detection-correction-feedback", significantly reducing the cost of manual intervention and improving the system's self-healing capabilities.

[0090] Example 2

[0091] Based on the same inventive concept as Example 1, this example introduces a method for monitoring and distinguishing the quality of real-time status data of hydropower equipment, including the following steps:

[0092] Step 1: Collect the measurement point data and working condition-related parameters corresponding to each measurement point of the hydropower operation equipment in real time.

[0093] In this embodiment, the measurement point data include switch quantity, state quantity and analog quantity, and the working condition related parameters include load rate, water head height and equipment operation mode.

[0094] Step 2: Classify and store the measurement point data according to the equipment-component-indicator-measurement point hierarchy and build a database containing working condition-related parameter labels.

[0095] Step 3: Classify the indicators according to the number of measurement points associated with each indicator to obtain the indicator category label and establish a data quality discrimination model.

[0096] In this embodiment, the indicator category labels include L1 indicators and L2 indicators. If the number of measurement points associated with each indicator is greater than 2, it is determined to be an L1 indicator; if the number of measurement points associated with each indicator is less than or equal to 2, it is determined to be an L2 indicator.

[0097] In this embodiment, a first data quality discrimination model and a second data quality discrimination model are established according to the L1 index and the L2 index, respectively.

[0098] In this embodiment, the first data quality discrimination model includes a distance analysis module and a MAD optimization module; the distance analysis module is used to calculate the Mahalanobis distance of the data distribution between the measurement points based on the measurement point data corresponding to all measurement points under a certain type of indicator to screen out abnormal measurement points; the MAD optimization module is used to introduce the degradation coefficient into the median absolute deviation (MAD) to calculate the data quality discrimination threshold of the measurement point data corresponding to all measurement points under a certain type of indicator, and to discriminate abnormal measurement points that exceed the indicator data quality discrimination threshold as data quality anomalies, thereby generating a data quality discrimination result.

[0099] In this embodiment, the abnormal measuring points are screened out by calculating the Mahalanobis distance of the data distribution between measuring points based on the measuring point data corresponding to all measuring points under a certain type of indicator, including:

[0100] Perform Z-score standardization on the actual measured values ​​of the measurement point data corresponding to all measurement points under a certain type of indicator to obtain the standardized measurement point data corresponding to all measurement points;

[0101] Based on the standardized measurement point data corresponding to all measurement points, a matrix between measurement points is constructed to calculate the Mahalanobis distance values ​​of all measurement points;

[0102] If the Mahalanobis distance value of the current measuring point data is greater than the preset distance value alarm threshold, the current measuring point will be marked as an abnormal measuring point.

[0103] In this embodiment, the degradation coefficient is introduced into the median absolute deviation (MAD) to calculate the data quality judgment threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. Abnormal measurement points that exceed the indicator data quality judgment threshold are judged as data quality abnormalities, and the data quality judgment results are generated, including:

[0104] The degradation coefficient is calculated based on the equipment operation time and the preset equipment life, wherein the calculation formula of the degradation coefficient is expressed as:

[0105]

[0106] Where, represents the unit degradation coefficient, Indicates the unit degradation coefficient of a certain type of indicator in the last overhaul cycle The maximum absolute value, Indicates the first appearance The corresponding moment, Indicates the unit degradation coefficient of a certain type of indicator at the time of resumption of production during the last overhaul cycle The initial value of Indicates the first appearance The time corresponding to the time, T represents the overhaul cycle, 、 They are The weight coefficient of

[0107] Extract the sliding time window of the measurement points under the health status of the equipment and calculate the median absolute deviation (MAD) of the measurement point data corresponding to all measurement points under a certain type of indicator within the sliding time window;

[0108] The degradation coefficient is introduced into the median absolute deviation (MAD) to calculate and generate the data quality discrimination threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. The calculation formula of the data quality discrimination threshold is expressed as follows:

[0109] ;

[0110] Where, represents the data quality judgment threshold, Indicates the median absolute deviation of the measurement point data corresponding to a certain measurement point;

[0111] Perform real-time quality judgment on the measurement point data corresponding to all measurement points under a certain type of indicator, including:

[0112] When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is greater than the data quality judgment threshold, the data quality judgment result is judged to be abnormal;

[0113] When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is less than or equal to the data quality judgment threshold, the data quality judgment result is judged to be normal.

[0114] In this embodiment, the second data quality judgment model includes an operating condition parameter extraction and matching module and a weighted range calculation module; the operating condition parameter extraction and matching module is used to extract the operating condition-related parameters of the current measuring point from a database containing operating condition-related parameter labels and match the historical database containing operating condition-related parameter labels to obtain the normal value range and standard deviation of the operating condition-related parameters of the current measuring point; the weighted range calculation module is used to calculate the allowable deviation range of the operating condition-related parameters of the current measuring point based on the seasonal correction coefficient and the standard deviation of the operating condition-related parameters of the current measuring point, and generate a data quality judgment result based on the normal value range of the operating condition-related parameters of the current measuring point and the allowable deviation range of the operating condition-related parameters of the current measuring point.

[0115] In this embodiment, the working condition-related parameters of the current measuring point are extracted from a database containing working condition-related parameter tags and matched with a historical database containing working condition-related parameter tags to obtain the normal value range and standard deviation of the working condition-related parameters of the current measuring point, including:

[0116] Extracting the working condition associated parameters of the current measuring point from a database containing working condition associated parameter tags;

[0117] According to the working condition associated parameters of the current measuring point, similarity matching is performed based on preset matching rules in a historical database containing the working condition associated parameters to filter the historical working condition associated parameters of the current measuring point;

[0118] According to the historical working condition related parameters of the current measuring point, the normal value range and standard deviation of the working condition related parameters of the current measuring point are calculated.

[0119] In this embodiment, the allowable deviation range of the working condition-related parameter of the current measuring point is calculated based on the seasonal correction coefficient and the standard deviation of the working condition-related parameter of the current measuring point, and the data quality judgment result is generated based on the normal value range of the working condition-related parameter of the current measuring point and the allowable deviation range of the working condition-related parameter of the current measuring point, including:

[0120] Calculate the seasonal correction factor based on the difference between the current ambient temperature and the standard temperature;

[0121] Calculate the allowable deviation range of the working condition-related parameters of the current measuring point based on the standard deviation and seasonal correction coefficient of the working condition-related parameters of the current measuring point;

[0122] If the actual measured value of the working condition-related parameter of the current measuring point is within the normal value range, the data quality judgment result is judged to be normal;

[0123] If the actual measured value of the working condition associated parameter of the current measuring point is within the allowable deviation range but exceeds the normal value range, or the actual measured value exceeds the allowable deviation range, the data quality judgment result is judged to be abnormal.

[0124] Step 4: By establishing a communication status discrimination model, a silent condition detection process is performed on each measuring point to obtain the communication status discrimination result of each measuring point.

[0125] In this embodiment, the communication state determination model includes a first communication state determination model and a second communication state determination model.

[0126] In this embodiment, the first communication status determination model is used to determine whether the communication status determination result is communication interruption or normal communication. Taking measurement point A as an example, it includes:

[0127] If the current measurement point satisfies , then the communication status of the current measuring point is judged to be communication interruption;

[0128] If the current measurement point does not meet , then the communication status of the current measuring point is judged to be normal;

[0129] in, Indicates the current time T i The actual measured value of measuring point A, Indicates the last moment T i-a The actual measured value of measuring point A, 、 is a positive integer and satisfies ;

[0130] In this embodiment, the second communication status determination model is used to perform silence condition detection processing on each measuring point to obtain a communication status determination result of each measuring point, including:

[0131] Based on the measurement point data corresponding to each measurement point, the state jump frequency and duration of the switch quantity, the data refresh cycle of the state quantity, and the numerical fluctuation amplitude of the analog quantity are monitored respectively within the preset time period.

[0132] The switching quantity quiet factor is calculated according to the actual state transition frequency and the rated state transition frequency of the switching quantity, wherein the switching quantity quiet factor=1-(actual state transition frequency / rated state transition frequency).

[0133] The state quantity quiet factor is calculated according to the actual data refresh period and the rated data refresh period of the state quantity, wherein the state quantity quiet factor=1-(actual data refresh period / rated data refresh period).

[0134] The analog quantity quiet factor is calculated according to the actual value fluctuation amplitude and the rated value fluctuation amplitude of the analog quantity, wherein the analog quantity quiet factor=1-(actual value fluctuation amplitude / rated value fluctuation amplitude).

[0135] A comprehensive silence index is calculated based on the switch quantity silence factor, the state quantity silence factor, and the analog quantity silence factor, wherein the comprehensive silence index=(switch quantity silence factor+state quantity silence factor+analog quantity silence factor) / 3.

[0136] When the comprehensive silence index is greater than a preset first threshold and the duration is greater than a preset second threshold, it is determined that the communication is interrupted; otherwise, it is determined that the communication is normal.

[0137] If the communication status is judged to be communication interruption, an alarm message will be pushed.

[0138] If the communication status judgment result is that the communication is normal, the data quality judgment models corresponding to all indicator category labels are triggered in parallel to obtain the data quality judgment result.

[0139] Step 5: Determine the status of data quality judgment results:

[0140] If the data quality judgment result is abnormal, an alarm message is pushed, and the standard value of the measurement point data of the current abnormal measurement point is corrected. Based on the corrected standard value of the measurement point data of the current abnormal measurement point, the database containing the working condition associated parameter label is updated.

[0141] In this embodiment, the standard value of the measurement point data of the current abnormal measurement point is corrected, including:

[0142] Based on the actual measurement values ​​of all measuring points at the current moment from the last overhaul period of the unit and the time interval from the last inspection and repair to the current moment, the standard value of the measuring point data of the current abnormal measuring point is corrected to obtain the corrected standard value of the measuring point data of the current abnormal measuring point.

[0143] In this embodiment, the corrected standard value of the measurement point data of the current abnormal measurement point is expressed as:

[0144] ;

[0145] Where, Indicates the corrected standard value of the measurement point data of the current abnormal measurement point. Indicates the standard value of the measurement point data of the current abnormal measurement point, Indicates the time period of the unit’s most recent overhaul. Indicates the time interval from the last inspection and restoration of the unit to the current moment. Indicates the The actual measurement value of the measuring point data corresponding to each measuring point at the current moment.

[0146] If the data quality judgment result is normal, the status information is pushed, and the database containing the working condition associated parameter tags is updated based on the measurement point data of all current measurement points.

[0147] Example 3

[0148] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the steps of the method of the above-mentioned embodiment 1 or 2 are implemented.

[0149] Example 4

[0150] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of the method in the above-mentioned embodiment 1 or 2 are implemented.

[0151] In summary, the present invention achieves full coverage of the equipment operating status by synchronously collecting measuring point data such as switch quantity, state quantity, analog quantity, etc., and combining it with working condition related parameters such as load rate and head height, effectively solving the data island problem in traditional monitoring and improving the accuracy of data association analysis; the present invention also adopts a four-level hierarchical structure of equipment-component-indicator-measuring point to store data, and adds working condition parameter labels to make massive heterogeneous data traceable; the present invention innovatively classifies and models indicators according to the number of measuring points, constructs dedicated quality discrimination models for different categories, and reduces the misjudgment rate; the present invention identifies communication interruptions through silent detection, and innovatively adopts a parallel triggering multi-model discrimination strategy to improve the data repair efficiency in the interrupted state, and at the same time ensures the freshness of data in the continuous communication state through real-time database updates.

[0152] The present invention divides indicators into L1 and L2 categories based on the number of measurement points. A first data quality discrimination model is constructed based on the Mahalanobis distance and an optimized MAD model, respectively. A second data quality discrimination model is constructed based on operating condition-related parameter matching and weighted range calculation. L1 indicators utilize multi-measurement point collaborative analysis, combined with Mahalanobis distance to eliminate abnormal data, and a degradation coefficient is introduced to dynamically adjust the MAD threshold, reducing the false positive rate during the equipment aging phase. L2 indicators calculate a dynamic allowable range by matching historical operating condition-related parameters and seasonal correction, addressing the problem of false positives under conditions with few measurement points and improving the reliability of single-point data. Those skilled in the art will appreciate that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk drives, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0153] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0154] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0156] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.

Claims

1. A method for monitoring and judging the quality of real-time status data of hydropower equipment, characterized in that: include: Real-time collection of measurement point data and working condition-related parameters corresponding to each measurement point of hydropower operating equipment; The measuring point data includes switch quantity, state quantity and analog quantity, and the working condition related parameters include load rate, water head height and equipment operation mode; The measurement point data is classified and stored according to the equipment-component-indicator-measurement point hierarchy and a database containing labels of working condition-related parameters is constructed; According to the number of measurement points associated with each indicator, the indicator category label is obtained and a data quality discrimination model is established; By establishing a communication status discrimination model, each measuring point is subjected to a silent condition detection process to obtain the communication status discrimination result of each measuring point; If the communication status is judged as communication interruption, an alarm message will be pushed; If the communication status judgment result is normal, the data quality judgment model corresponding to all indicator category labels is triggered in parallel to obtain the data quality judgment result; If the data quality judgment result is abnormal, an alarm message is pushed, and the standard value of the measurement point data of the current abnormal measurement point is corrected. Based on the corrected standard value of the measurement point data of the current abnormal measurement point, the database containing the working condition related parameter tags is updated; If the data quality judgment result is normal, the status information is pushed, and the database containing the working condition associated parameter tags is updated based on the measurement point data of all current measurement points.

2. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 1, characterized in that: The communication state discrimination model includes a first communication state discrimination model and a second communication state discrimination model; The first communication status determination model is used to determine whether the communication status determination result is communication interruption or normal communication, including: If the current measurement point satisfies , then the communication status of the current measuring point is judged to be communication interruption; If the current measurement point does not meet , then the communication status of the current measuring point is judged to be normal; in, Indicates the current time T i The actual measured value of measuring point A, Indicates the last moment T i-a The actual measured value of measuring point A, 、 is a positive integer and satisfies ; The second communication state discrimination model is used to perform a silent condition detection process on each measuring point to obtain a communication state discrimination result of each measuring point, including: Based on the measurement point data corresponding to each measurement point, the state jump frequency and duration of the switch quantity, the data refresh cycle of the state quantity, and the numerical fluctuation amplitude of the analog quantity are monitored respectively within the preset time period; Calculating a switch quantity quiet factor according to the actual state transition frequency and the rated state transition frequency of the switch quantity, wherein the switch quantity quiet factor = 1 - (actual state transition frequency / rated state transition frequency); Calculate the state quantity quiet factor according to the actual data refresh cycle and the rated data refresh cycle of the state quantity, wherein the state quantity quiet factor=1-(actual data refresh cycle / rated data refresh cycle); Calculating an analog quantity quiet factor according to an actual value fluctuation amplitude and a rated value fluctuation amplitude of the analog quantity, wherein the analog quantity quiet factor=1-(actual value fluctuation amplitude / rated value fluctuation amplitude); Calculate a comprehensive silence index according to the switch quantity silence factor, the state quantity silence factor, and the analog quantity silence factor, wherein the comprehensive silence index=(switch quantity silence factor+state quantity silence factor+analog quantity silence factor) / 3; When the comprehensive silence index is greater than a preset first threshold and the duration is greater than a preset second threshold, it is determined that the communication is interrupted; otherwise, it is determined that the communication is normal.

3. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 1, characterized in that: The indicator category labels include L1 indicators and L2 indicators, where: If the number of measurement points associated with each indicator is greater than 2, it is determined to be an L1 indicator; If the number of measurement points associated with each indicator is less than or equal to 2, it is judged to be an L2 indicator.

4. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 3, characterized in that: Establishing a first data quality discrimination model and a second data quality discrimination model according to the L1 category index and the L2 category index respectively; The first data quality discrimination model includes a distance analysis module and a MAD optimization module; The distance analysis module is used to calculate the Mahalanobis distance of the data distribution between the measuring points according to the measuring point data corresponding to all measuring points under a certain type of indicator to filter out abnormal measuring points; The MAD optimization module is used to introduce the degradation coefficient into the median absolute deviation (MAD) to calculate the data quality judgment threshold of the measurement point data corresponding to all measurement points under a certain type of indicator, and to judge abnormal measurement points that exceed the indicator data quality judgment threshold as data quality abnormalities, thereby generating a data quality judgment result; The second data quality discrimination model includes a working condition parameter extraction and matching module and a weighted range calculation module; The operating condition parameter extraction and matching module is used to extract the operating condition associated parameters of the current measuring point from a database containing operating condition associated parameter tags and match them with a historical database containing operating condition associated parameter tags to obtain the normal value range and standard deviation of the operating condition associated parameters of the current measuring point; The weighted range calculation module is used to calculate the allowable deviation range of the working condition associated parameters of the current measuring point based on the seasonal correction coefficient and the standard deviation of the working condition associated parameters of the current measuring point, and generate a data quality judgment result based on the normal value range of the working condition associated parameters of the current measuring point and the allowable deviation range of the working condition associated parameters of the current measuring point.

5. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 4, characterized in that: Based on the measurement point data corresponding to all measurement points under a certain type of indicator, the Mahalanobis distance of the data distribution between the measurement points is calculated to screen out abnormal measurement points, including: Perform Z-score standardization on the actual measured values ​​of the measurement point data corresponding to all measurement points under a certain type of indicator to obtain the standardized measurement point data corresponding to all measurement points; Based on the standardized measurement point data corresponding to all measurement points, a matrix between measurement points is constructed to calculate the Mahalanobis distance values ​​of all measurement points; If the Mahalanobis distance value of the current measuring point data is greater than the preset distance value alarm threshold, the current measuring point will be marked as an abnormal measuring point.

6. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 4, characterized in that: The degradation coefficient is introduced into the median absolute deviation (MAD) to calculate the data quality judgment threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. Abnormal measurement points that exceed the indicator data quality judgment threshold are judged as data quality anomalies, and data quality judgment results are generated, including: The degradation coefficient is calculated based on the equipment operation time and the preset equipment life, wherein the calculation formula of the degradation coefficient is expressed as: ； Where, represents the unit degradation coefficient, Indicates the unit degradation coefficient of a certain type of indicator in the last overhaul cycle The maximum absolute value, Indicates the first appearance The corresponding moment, Indicates the unit degradation coefficient of a certain type of indicator at the time of resumption of production during the last overhaul cycle The initial value of Indicates the first appearance The time corresponding to the time, T represents the overhaul cycle, 、 They are The weight coefficient of Extract the sliding time window of the measurement points under the health status of the equipment and calculate the median absolute deviation (MAD) of the measurement point data corresponding to all measurement points under a certain type of indicator within the sliding time window; The degradation coefficient is introduced into the median absolute deviation (MAD) to calculate and generate the data quality discrimination threshold of the measurement point data corresponding to all measurement points under a certain type of indicator. The calculation formula of the data quality discrimination threshold is expressed as follows: ； Where, represents the data quality judgment threshold, Indicates the median absolute deviation of the measurement point data corresponding to a certain measurement point; Perform real-time quality judgment on the measurement point data corresponding to all measurement points under a certain type of indicator, including: When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is greater than the data quality judgment threshold, the data quality judgment result is judged to be abnormal; When the median absolute deviation of the measurement point data corresponding to a certain measurement point under a certain type of indicator is less than or equal to the data quality judgment threshold, the data quality judgment result is judged to be normal.

7. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 4, characterized in that: Extract the working condition-related parameters of the current measuring point from the database containing working condition-related parameter tags and match them with the historical database containing working condition-related parameter tags to obtain the normal value range and standard deviation of the working condition-related parameters of the current measuring point, including: Extracting the working condition associated parameters of the current measuring point from a database containing working condition associated parameter tags; According to the working condition associated parameters of the current measuring point, similarity matching is performed based on preset matching rules in a historical database containing the working condition associated parameters to filter the historical working condition associated parameters of the current measuring point; According to the historical working condition related parameters of the current measuring point, the normal value range and standard deviation of the working condition related parameters of the current measuring point are calculated.

8. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 7, characterized in that: The allowable deviation range of the working condition-related parameters of the current measuring point is calculated based on the seasonal correction coefficient and the standard deviation of the working condition-related parameters of the current measuring point. The data quality judgment result is generated based on the normal value range of the working condition-related parameters of the current measuring point and the allowable deviation range of the working condition-related parameters of the current measuring point, including: Calculate the seasonal correction factor based on the difference between the current ambient temperature and the standard temperature; Calculate the allowable deviation range of the working condition-related parameters of the current measuring point based on the standard deviation and seasonal correction coefficient of the working condition-related parameters of the current measuring point; If the actual measured value of the working condition-related parameter of the current measuring point is within the normal value range, the data quality judgment result is judged to be normal; If the actual measured value of the working condition associated parameter of the current measuring point is within the allowable deviation range but exceeds the normal value range, or the actual measured value exceeds the allowable deviation range, the data quality judgment result is judged to be abnormal.

9. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 1, characterized in that: Correct the standard value of the measurement point data of the current abnormal measurement point, including: Based on the actual measurement values ​​of all measuring points at the current moment from the last overhaul period of the unit and the time interval from the last inspection and repair to the current moment, the standard value of the measuring point data of the current abnormal measuring point is corrected to obtain the corrected standard value of the measuring point data of the current abnormal measuring point.

10. The method for monitoring and judging the quality of real-time status data of hydropower equipment according to claim 9, characterized in that: The standard value of the corrected measurement point data of the current abnormal measurement point is expressed as: ； Where, Indicates the corrected standard value of the measurement point data of the current abnormal measurement point. Indicates the standard value of the measurement point data of the current abnormal measurement point, Indicates the time period of the unit’s most recent overhaul. Indicates the time interval from the last inspection and restoration of the unit to the current moment. Indicates the The actual measurement value of the measuring point data corresponding to each measuring point at the current moment.

Images