A method and system for evaluating the state of a hydroelectric generating unit based on vibration signals

Abstract

The application provides a kind of water turbine unit state evaluation method and system based on vibration signal, it is related to hydroelectric generation technical field, the method comprises: the history vibration signal in the history of water turbine unit is obtained in the previous history running process, obtains historical vibration signal set;The feature extraction is carried out to historical vibration signal, obtains multiple historical vibration signal feature set;The correlation between multiple historical vibration signal feature set and water turbine unit operation stability is analyzed, according to the correlation, obtain at least two vibration signal features with the highest correlation, as sensitive vibration signal feature;According to sensitive vibration signal feature, construct water turbine unit state evaluation space;Real-time vibration signal of current water turbine unit is collected and obtained, input water turbine unit state evaluation space, obtain water turbine unit state evaluation result, achieve accurate water turbine unit state evaluation result and realize the technical effect of safety early warning to water turbine unit, reduce economic loss and personnel casualty.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hydroelectric power generation, in particular to a method and system for evaluating the state of a hydroelectric generating set based on vibration signals. BACKGROUND

[0002] Hydroelectric power generation is an important part of China's energy, and as a clean energy, vigorously developing hydroelectric power generation project construction meets the requirements of China's economic and environmental development.

[0003] Hydroelectric generating sets are key equipment in the construction of hydropower stations, and have a major impact on the stable operation of the entire power station and even the entire power grid. With the continuous development of units towards large-scale and complex, the degree of integration is increasingly high, and the structure is becoming increasingly complex. The importance of maintenance, repair and vibration state analysis of the cylinder is gradually emerging. In order to ensure the safe and stable operation of the hydroelectric generating set, improve equipment utilization, and avoid major economic losses and personnel casualties, the operating state of the hydroelectric generating set must be reasonably monitored and evaluated.

[0004] Through research on the method of monitoring the state of the hydroelectric generating set provided by the prior art, it is found that the influence of the unit operating condition is often ignored in the process of evaluating the state of the hydroelectric generating set, and the historical data of the unit are not effectively utilized, which leads to low reliability of the state evaluation result. The current fault diagnosis method of the hydroelectric generating set focuses on the judgment when the unit fails, and cannot reflect the evolution process of the unit from normal to failure, and cannot provide active and effective fault warning protection for the hydroelectric generating set. SUMMARY

[0005] The purpose of the present application is to provide a method and system for evaluating the state of a hydroelectric generating set based on vibration signals, which solves the technical problems of low reliability of the state evaluation result of the hydroelectric generating set in the prior art and the inability to provide effective fault warning, and achieves dynamic and real-time monitoring of the evolution process of the hydroelectric generating set from normal state to failure state in the case of improving the state evaluation result, thereby achieving safety warning of the hydroelectric generating set and reducing economic losses and personnel casualties.

[0006] In view of the above problems, the present application provides a method and system for evaluating the state of a hydroelectric generating set based on vibration signals.

[0007] In a first aspect, the present application provides a method for evaluating the state of a hydroelectric generating set based on vibration signals, the method comprising: collecting historical vibration signals during the operation of the hydroelectric generating set in the past history to obtain a set of historical vibration signals; extracting multi-dimensional historical vibration signal feature information in the historical vibration signals according to the set of historical vibration signals to obtain a plurality of sets of historical vibration signal features; analyzing the correlation between the plurality of sets of historical vibration signal features and the operation stability of the hydroelectric generating set to obtain a first set of correlation degrees; obtaining at least two vibration signal features with the highest correlation degrees as sensitive vibration signal features according to the first set of correlation degrees; obtaining a corresponding set of sensitive historical vibration signal features according to the sensitive vibration signal features to construct a hydroelectric generating set state evaluation space; collecting real-time vibration signals of the hydroelectric generating set to input the hydroelectric generating set state evaluation space to obtain a hydroelectric generating set state evaluation result.

[0008] In a second aspect, the present application provides a system for evaluating the state of a hydroelectric generating set based on vibration signals, the system comprising: a first obtaining unit configured to collect historical vibration signals during the operation of the hydroelectric generating set in the past history to obtain a set of historical vibration signals; a first processing unit configured to extract multi-dimensional historical vibration signal feature information in the historical vibration signals according to the set of historical vibration signals to obtain a plurality of sets of historical vibration signal features; a second processing unit configured to analyze the correlation between the plurality of sets of historical vibration signal features and the operation stability of the hydroelectric generating set to obtain a first set of correlation degrees; a second obtaining unit configured to obtain at least two vibration signal features with the highest correlation degrees as sensitive vibration signal features according to the first set of correlation degrees; a first constructing unit configured to obtain a corresponding set of sensitive historical vibration signal features according to the sensitive vibration signal features to construct a hydroelectric generating set state evaluation space; and a third processing unit configured to collect real-time vibration signals of the hydroelectric generating set to input the hydroelectric generating set state evaluation space to obtain a hydroelectric generating set state evaluation result.

[0009] In a third aspect, the present application provides a system for evaluating the state of a hydroelectric generating set based on vibration signals, comprising: a processor coupled with a memory, the memory being configured to store a program, when the program is executed by the processor, the system is caused to perform the steps of the method according to the first aspect.

[0010] In a fourth aspect, the present application provides a computer readable storage medium, the storage medium storing a computer program, when the computer program is executed by a processor, the steps of the method according to the first aspect are implemented.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0012] This application provides a method and system for assessing the condition of a hydropower unit based on vibration signals. The method involves: acquiring historical vibration signals from the hydropower unit's previous operation to obtain a historical vibration signal set; extracting multi-dimensional historical vibration signal feature information from the historical vibration signal set to obtain multiple historical vibration signal feature sets; analyzing the correlation between the multiple historical vibration signal feature sets and the operational stability of the hydropower unit to obtain a first correlation set; identifying at least two vibration signal features with the highest correlation based on the first correlation set as sensitive vibration signal features; obtaining corresponding sensitive historical vibration signal feature sets based on the sensitive vibration signal features to construct a hydropower unit condition assessment space; acquiring the current real-time vibration signal of the hydropower unit and inputting it into the hydropower unit condition assessment space to obtain the hydropower unit condition assessment result. This application addresses the technical problems of low reliability of hydropower unit condition assessment results and inability to provide effective fault early warning in the prior art by applying historical data of hydropower units and constructing a hydropower unit assessment space. It achieves the technical effect of dynamic real-time monitoring of the evolution process of hydropower units from normal state to fault state while improving condition assessment results, thereby achieving safety early warning of hydropower units and reducing economic losses and casualties.

[0013] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0014] Figure 1 A schematic flowchart of a method for assessing the condition of a hydropower unit based on vibration signals is provided in this application;

[0015] Figure 2 A schematic diagram of the process for constructing the hydropower unit condition assessment space in a method for assessing the condition of a hydropower unit based on vibration signals provided in this application;

[0016] Figure 3 This is a flowchart illustrating the process of acquiring the real-time vibration signal of the hydropower unit and inputting it into the hydropower unit status assessment space in a method for assessing the status of a hydropower unit based on vibration signals provided in this application.

[0017] Figure 4 This application provides a schematic diagram of a system structure for hydropower unit condition assessment based on vibration signals;

[0018] Figure 5 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0019] Explanation of reference numerals in the attached drawings: First obtaining unit 11, first processing unit 12, second processing unit 13, second obtaining unit 14, first building unit 15, third processing unit 16, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. Detailed Implementation

[0020] This application provides a method and system for assessing the condition of hydropower units based on vibration signals. This method addresses the technical problems of low reliability of condition assessment results and the inability to provide effective fault warnings in the prior art. It aims to improve the condition assessment results and achieve dynamic real-time monitoring of the evolution process of hydropower units from normal to faulty states. This results in safety warnings for hydropower units and reduces economic losses and casualties.

[0021] To address the aforementioned technical problems, the overall approach of the technical solution provided in this application is as follows:

[0022] The method provided in this application embodiment acquires historical vibration signals from the previous operation of the hydropower unit to obtain a historical vibration signal set; extracts multi-dimensional historical vibration signal feature information from the historical vibration signal set to obtain multiple historical vibration signal feature sets; analyzes the correlation between the multiple historical vibration signal feature sets and the operational stability of the hydropower unit to obtain a first correlation set; based on the first correlation set, obtains at least two vibration signal features with the highest correlation as sensitive vibration signal features; obtains corresponding sensitive historical vibration signal feature sets based on the sensitive vibration signal features to construct a hydropower unit state assessment space; acquires the current real-time vibration signal of the hydropower unit, inputs it into the hydropower unit state assessment space, and obtains the hydropower unit state assessment result.

[0023] After introducing the basic principles of this application, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0024] Example 1

[0025] like Figure 1 As shown, this application provides a method for assessing the condition of a hydropower unit based on vibration signals, the method comprising:

[0026] S100: Collects historical vibration signals from the previous operation of the hydropower unit and obtains a set of historical vibration signals;

[0027] Specifically, the vibration signal is generated by the hydraulic, mechanical, and electromagnetic coupling vibration of the hydropower unit. Historical operating data of the hydropower unit has a significant impact on the assessment of its condition. The operating condition of the hydropower unit can be assessed by referring to this historical operating data. In this embodiment, the hydropower unit control system stores parameter records involved in the operation of the hydropower unit. Historical vibration signals from the historical operation of the hydropower unit can be obtained from the control system, forming a historical vibration signal set. This historical data is then used to achieve the purpose of assessing the condition of the hydropower unit.

[0028] S200: Based on the set of historical vibration signals, extract multi-dimensional historical vibration signal feature information from the historical vibration signals to obtain multiple sets of historical vibration signal features;

[0029] Specifically, information is extracted from the obtained historical vibration signal set of the hydropower unit to obtain multi-dimensional historical vibration signal feature information. The multi-dimensional historical vibration signal feature information includes the mean, standard deviation, frequency, root mean square deviation, peak value, kurtosis, skewness, peak-to-peak value, and other feature information of the vibration signal within a preset time period, thereby forming a historical vibration signal feature set within multiple preset time periods.

[0030] S300: Analyze the correlation between multiple sets of historical vibration signal features and the operational stability of hydropower units to obtain a first set of correlation.

[0031] S400: Based on the first set of correlation degrees, obtain at least two vibration signal features with the highest correlation degree as sensitive vibration signal features;

[0032] Specifically, different vibration signal characteristics have different degrees of influence on the operating state of hydropower units. By calculating the correlation between the change of each historical vibration information feature in the multi-dimensional historical vibration signal feature information and the change of the operating stability of the hydropower unit, the correlation degree is the degree of influence of the change of each historical vibration information feature on the change of the operating state of the hydropower unit. A first correlation degree set is obtained, which is the correlation set between the multi-dimensional historical vibration signal feature information and the operating stability of the hydropower unit.

[0033] Furthermore, regarding the process of evaluating the operating status of hydropower units using historical vibration signal features from the historical vibration signal feature set, the selection of the number of historical vibration signal features is problematic. If only one historical vibration signal feature with the highest correlation is selected, the influence of other valuable historical vibration signal features on the hydropower unit's status may be overlooked. If multiple historical vibration signal features are selected, historical vibration signal features with low correlation may be excluded, increasing the data processing burden and reducing data processing efficiency. In this embodiment, based on the calculated first correlation set, at least two vibration signal features with the highest correlation are obtained, preferably three vibration signal features, as sensitive vibration signal features. The determination of the sensitive features is based on the magnitude of the correlation, which improves data processing efficiency while ensuring the accuracy of hydropower unit status evaluation.

[0034] S500: Based on the sensitive vibration signal characteristics, obtain the corresponding set of sensitive historical vibration signal characteristics, and construct the hydropower unit state assessment space;

[0035] S600: Collect the real-time vibration signal of the current hydropower unit, input it into the hydropower unit status assessment space, and obtain the hydropower unit status assessment result.

[0036] Specifically, after obtaining the sensitive vibration signal characteristics, a set of sensitive vibration signal characteristics corresponding to the sensitive vibration signal characteristics is obtained. The set of sensitive historical vibration signal characteristics is a set of historical vibration signal characteristics corresponding to multiple sensitive vibration signal characteristics obtained from the hydropower unit control system based on multiple sensitive vibration signal characteristics. The set of sensitive historical vibration signal characteristics is used to construct the hydropower unit state assessment space.

[0037] Preferably, in this embodiment, the hydropower unit status assessment space is implemented using the KNN (K Nearest Neighbors) classification algorithm. The KNN algorithm is a supervised learning classification algorithm. It constructs a coordinate system, calculates the distance between the object to be classified and other objects, counts the K nearest neighbors, and determines the class of the object to be classified based on the class with the most nearest neighbors. Further, real-time vibration signals of the hydropower unit are acquired and input into the hydropower unit status assessment space. Based on the distance between the coordinate points corresponding to the real-time vibration signals and the coordinate points corresponding to the hydropower unit's operating state, the hydropower unit status assessment result is obtained through analysis of the real-time vibration signals. By applying the sensitive historical vibration signal feature set and the KNN classification algorithm, accurate status assessment results of the hydropower unit are obtained, achieving dynamic real-time monitoring of the evolution process from a normal state to a fault state. This results in safety early warning for the hydropower unit, reducing economic losses and personnel casualties.

[0038] The method provided in this application obtains a set of historical vibration signals from the previous operation of a hydropower unit. Based on this set, multi-dimensional historical vibration signal feature information is extracted to obtain multiple sets of historical vibration signal features. The correlation between these multiple sets of historical vibration signal features and the operational stability of the hydropower unit is analyzed to obtain a first correlation set. Based on the first correlation set, at least two vibration signal features with the highest correlation are selected as sensitive vibration signal features. A corresponding set of sensitive historical vibration signal features is obtained based on these sensitive vibration signal features, and a hydropower unit state assessment space is constructed. Real-time vibration signals of the current hydropower unit are acquired and input into the hydropower unit state assessment space to obtain the hydropower unit state assessment result. This application solves the technical problems of low reliability and inability to provide effective fault warnings in existing hydropower unit state assessment results by applying historical data of hydropower units and constructing a hydropower unit assessment space. It achieves dynamic real-time monitoring of the evolution process of a hydropower unit from a normal state to a fault state while improving the state assessment results, thereby achieving the technical effect of providing safety warnings for hydropower units and reducing economic losses and casualties.

[0039] Step S100 in the method provided in this application embodiment includes:

[0040] S110: Set the preset time period to be obtained;

[0041] S120: Based on the current hydropower unit, obtain multiple hydropower units of the same family;

[0042] S130: Collect historical vibration signals of the current hydropower unit and multiple hydropower units of the same family within a preset time period in multiple historical periods, and obtain the set of historical vibration signals.

[0043] Specifically, to obtain a set of historical vibration signals, a time period is first preset. This time period can be set as needed, such as hour, day, week, or month. Based on the type of the current hydropower unit and its operating environment, multiple hydropower units of the same family are obtained. These family-based hydropower units are other hydropower units of the same type as the current hydropower unit that operate in the same hydropower station or the same area. Obtaining family-based hydropower units increases the sample size and improves the accuracy of the hydropower unit status assessment results. From the large amount of operational data stored in the hydropower unit control system, historical vibration signals of the current hydropower unit and multiple family-based hydropower units within multiple preset historical time periods are obtained to form the set of historical vibration signals, providing a data foundation for subsequent hydropower unit status assessments.

[0044] Step S300 in the method provided in this application embodiment further includes:

[0045] S310: Collect and obtain the operational stability data of the current hydropower unit and multiple hydropower units of the same family within the preset time period in multiple historical periods, and obtain an operational stability data set;

[0046] S320: Set the operational stability data set as the main sequence;

[0047] S330: The multiple sets of historical vibration signal features are used as multiple influence sequences;

[0048] S340: Normalize the data in the main sequence and the multiple affected sequences to obtain the processing result;

[0049] S350: Based on the processing results, calculate the correlation between the main sequence and the multiple affected sequences.

[0050] Specifically, operational stability data of the current hydropower unit and its family of hydropower units over multiple historical preset periods are obtained from the hydropower unit control system. This operational stability can be represented by the stability of the hydropower unit's power generation. For example, stability can be determined by calculating the root mean square error of the power generation over a preset time period, or by calculating the ratio of the power generation at different times to a preset standard power generation, and determining stability based on how close the ratio is to 1. The set of operational stability data of the current hydropower unit and its family of hydropower units over multiple historical preset periods constitutes an operational stability data set.

[0051] In this embodiment, a grey relational analysis method is preferentially used to analyze the influence of historical vibration information features in the historical vibration information feature set on the operational stability of the hydropower unit. In this analysis method, the operational stability data sets of the current hydropower unit and multiple hydropower units in the same family within multiple historical preset time periods are set as the main sequence, which is a data sequence that reflects the operational stability of the hydropower unit. Multiple historical vibration signal feature sets are used as multiple influence sequences, which are data sequences composed of multiple historical vibration information features that affect the operational stability of the hydropower unit. To improve the speed and accuracy of data processing, before data processing... The data in the main sequence and multiple influence sequences are normalized to remove dimensions and unify all features into a roughly the same numerical range, making the features between different dimensions comparable in numerical terms, thereby improving the accuracy of data processing. In this embodiment, the mean of each indicator can be calculated first, and then each element in the indicator can be divided by its mean to achieve the normalization of the data in the main sequence and multiple influence sequences. Finally, the correlation between the main sequence and multiple influence sequences is calculated based on the processing results, thereby analyzing the strength of the influence of historical vibration signal characteristics on the operational stability of hydropower units, and providing data support for the subsequent construction of the hydropower unit state assessment space.

[0052] Step S350 in the method provided in this application embodiment further includes:

[0053] S351: Based on the data in the main sequence and the multiple influence sequences, calculate the influence correlation coefficients between the multiple influence sequences and the main sequence using the following formula to obtain a set of influence correlation coefficients;

[0054]

[0055] Where R(k) is the influence correlation coefficient between the kth data in the i-th influence sequence and the kth data in the main sequence, and ρ is an adjustable calculation coefficient;

[0056] S352: Based on the set of influence correlation coefficients, calculate the influence correlation degree of multiple influence sequences on the main sequence to obtain the first correlation degree set.

[0057] Specifically, after normalizing the data in the main sequence and multiple influencing sequences, the influence of historical vibration signal characteristics on the operational stability of hydropower units is analyzed using the influence correlation coefficient calculation formula. The influence correlation coefficient calculation formula is as follows:

[0058]

[0059] Where R(k) is the influence correlation coefficient between the kth data in the i-th influence sequence and the kth data in the main sequence, and ρ is an adjustable calculation coefficient; multiple influence sequences composed of multiple sets of historical vibration signal features are substituted into the above formula to calculate the influence relationship coefficients of multiple influence sequences. Based on the influence relationship coefficients, a first correlation set is obtained. The first correlation set is the correlation set between multi-dimensional historical vibration signal feature information and the operational stability of hydropower units.

[0060] like Figure 2 As shown, step S500 in the method provided in this application embodiment further includes:

[0061] S510: Construct a coordinate space based on the characteristics of multiple sensitive vibration signals;

[0062] S520: Input the multiple sets of features of the sensitive historical vibration signals into the coordinate space to obtain multiple coordinate points;

[0063] S530: Based on the operating status of the hydropower unit, cluster the multiple coordinate points to obtain multiple clustering results;

[0064] S540: Based on the multiple clustering results and the coordinate space, obtain the state evaluation space of the hydropower unit.

[0065] Specifically, in the KNN classification algorithm, a crucial calculation is distance calculation. In this embodiment, a coordinate space is constructed using multiple sensitive vibration signal features, with at least two, preferably three, features. A three-dimensional coordinate space is built. Based on the information from multiple sets of sensitive historical vibration signal features (each set representing a preset time period), these features are input into the coordinate space to obtain multiple coordinate points. Each coordinate point corresponds to one of the three sensitive historical vibration signal features within a preset time period. Preferably, based on historical testing experience of hydropower units, the data range of three sensitive vibration signal features corresponding to different operating states of the hydropower unit is obtained. Then, the multiple coordinate points are clustered to obtain multiple clustering results. Finally, the construction of the hydropower unit state assessment space is completed based on the multiple clustering results and the coordinate space.

[0066] Step S530 in the method provided in this application embodiment further includes:

[0067] S531: Collect and acquire multiple different operating states of the hydropower unit in history, including normal, fault-prone, and fault-occurring;

[0068] S532: Collect and acquire the characteristics of sensitive historical vibration signals under different time periods corresponding to the historical operating states, and obtain multiple corresponding coordinate points;

[0069] S533: Cluster the coordinate points corresponding to different operating states to obtain multiple clustering results.

[0070] Specifically, based on historical data from previous maintenance and repair of the hydropower units, multiple different operating states of the hydropower units within a historical period are obtained, such as normal operation, fault-prone operation, and fault-occurring operation. Sensitive historical vibration signal characteristics for the corresponding time periods of these different operating states are collected from the hydropower unit control system. Multiple coordinate points are obtained based on these corresponding time periods. Cluster analysis is performed on the coordinate points corresponding to the different operating states to obtain multiple clustering results. During the clustering analysis, two coordinate points with an Euclidean distance less than a certain threshold can be clustered, or all coordinate points under different operating states can be clustered.

[0071] like Figure 3 As shown, step S600 in the method provided in this application embodiment further includes:

[0072] S610: Acquire the real-time vibration signal of the current hydropower unit;

[0073] S620: Perform feature extraction based on the real-time vibration signal to obtain real-time sensitive vibration signal feature data;

[0074] S630: Input the real-time sensitive vibration signal feature data into the hydropower unit state assessment space to obtain the corresponding real-time coordinate points;

[0075] S640: Calculate multiple Euclidean distances between the real-time coordinate points and multiple clustering result centers;

[0076] S650: Based on the magnitudes of the multiple Euclidean distances, perform weight allocation to obtain a first weight allocation result;

[0077] S660: Using the first weight allocation result, the multiple Euclidean distances are weighted and adjusted;

[0078] S670: Based on the adjusted multiple Euclidean distances, obtain the operating state corresponding to the clustering result corresponding to the smallest Euclidean distance, and use it as the state evaluation result of the hydropower unit.

[0079] Specifically, the real-time vibration signal of the hydropower unit is obtained from the hydropower unit control system. Based on the sensitive vibration signal characteristics determined in the aforementioned steps, real-time sensitive vibration signal feature data corresponding to the real-time vibration signal is obtained. Using the hydropower unit state assessment space, the real-time sensitive vibration signal feature data is input into the hydropower unit state assessment space to obtain the coordinate points corresponding to the real-time sensitive vibration signal feature data. That is, the real-time coordinate points are used to calculate multiple Euclidean distances between the real-time coordinate points and multiple cluster result centers using the distance calculation formula between two points in a three-dimensional spatial coordinate system. Further, a weight allocation is performed based on the magnitude of the Euclidean distances to obtain a first weight allocation result. The redistribution can be performed using any weighting method in the existing technology. The weighted adjustment of the multiple Euclidean distances is carried out using the first weighting result to obtain the operating state corresponding to the clustering result with the smallest Euclidean distance, which is determined as the result of the hydropower unit status assessment. In this embodiment, based on obtaining multiple distances between the coordinate points corresponding to the real-time sensitive vibration signal feature data and the centers of multiple clustering results, the weighting is performed to adjust the distance size, thereby obtaining a more accurate hydropower unit status assessment result. This enables dynamic real-time monitoring of the evolution process of the hydropower unit from a normal state to a fault state, thereby achieving the technical effect of providing safety warnings for the hydropower unit and reducing economic losses and casualties.

[0080] In summary, the embodiments of this application have at least the following technical effects:

[0081] 1. This application provides a method for assessing the condition of a hydropower unit based on vibration signals. The method involves collecting historical vibration signals from the hydropower unit's previous operation to obtain a set of historical vibration signals; extracting multi-dimensional historical vibration signal feature information from the historical vibration signal set to obtain multiple sets of historical vibration signal features; analyzing the correlation between these multiple sets of historical vibration signal features and the operational stability of the hydropower unit to obtain a first correlation set; identifying at least two vibration signal features with the highest correlation as sensitive vibration signal features based on the first correlation set; obtaining corresponding sensitive historical vibration signal feature sets based on the sensitive vibration signal features to construct a hydropower unit condition assessment space; collecting real-time vibration signals from the current hydropower unit and inputting them into the hydropower unit condition assessment space to obtain the hydropower unit condition assessment result. This method solves the technical problems of low reliability and inability to provide effective fault warnings in existing hydropower unit condition assessment results. It achieves dynamic real-time monitoring of the evolution process of a hydropower unit from a normal state to a fault state while improving the condition assessment results, thereby achieving safety warnings for the hydropower unit and reducing economic losses and casualties.

[0082] 2. This application utilizes historical operating data of hydropower units, compares real-time operating data with historical operating data to assess the status of hydropower units, thereby making full use of historical data of hydropower units and improving the accuracy of hydropower unit status assessment results.

[0083] 3. This application uses the KNN classification algorithm to compare the coordinates of the feature data of real-time sensitive vibration signals with the multiple distances between the clustering results centers to determine the state assessment results of the hydropower unit. Furthermore, the Euclidean distance is weighted and adjusted to further ensure the accuracy of the state assessment results of the hydropower unit.

[0084] Example 2

[0085] Based on the same inventive concept as the method for assessing the condition of a hydropower unit based on vibration signals in the foregoing embodiments, such as Figure 4 As shown, this application provides a system for assessing the condition of a hydropower unit based on vibration signals, wherein the system includes:

[0086] The first acquisition unit 11 is used to collect historical vibration signals during the operation of the hydropower unit in the previous history and obtain a set of historical vibration signals.

[0087] The first processing unit 12 is configured to extract multi-dimensional historical vibration signal feature information from the historical vibration signal set to obtain multiple historical vibration signal feature sets.

[0088] The second processing unit 13 is used to analyze the correlation between multiple sets of historical vibration signal features and the operational stability of the hydropower unit to obtain a first correlation set.

[0089] The second obtaining unit 14 is used to obtain at least two vibration signal features with the highest correlation based on the first correlation set, as sensitive vibration signal features.

[0090] The first construction unit 15 is used to obtain a set of corresponding sensitive historical vibration signal features based on the sensitive vibration signal features, and to construct a hydropower unit state assessment space.

[0091] The third processing unit 16 is used to acquire the real-time vibration signal of the current hydropower unit, input it into the hydropower unit status assessment space, and obtain the hydropower unit status assessment result.

[0092] Furthermore, the system also includes:

[0093] The third obtaining unit is used to set a preset time period for obtaining;

[0094] The fourth obtaining unit is used to obtain multiple hydropower units of the same family based on the current hydropower unit;

[0095] The fifth obtaining unit is used to collect historical vibration signals of the current hydropower unit and multiple hydropower units of the same family within a preset time period in multiple historical periods, and obtain the set of historical vibration signals.

[0096] Furthermore, the system also includes:

[0097] The sixth obtaining unit is used to collect and obtain the operational stability data of the current hydropower unit and multiple hydropower units of the same family within a preset time period in multiple historical periods, and obtain an operational stability data set;

[0098] The fourth processing unit is used to set the operational stability data set as the main sequence;

[0099] The fifth processing unit is used to treat the multiple sets of historical vibration signal features as multiple influence sequences;

[0100] The sixth processing unit is used to normalize the data in the main sequence and the multiple affected sequences to obtain the processing result;

[0101] A seventh processing unit is used to calculate the correlation between the main sequence and multiple influencing sequences based on the processing results.

[0102] Furthermore, the system also includes:

[0103] The eighth processing unit is used to calculate the influence correlation coefficients between the multiple influence sequences and the main sequence based on the data in the main sequence and the multiple influence sequences, and obtain a set of influence correlation coefficients.

[0104]

[0105] Where R(k) is the influence correlation coefficient between the kth data in the i-th influence sequence and the kth data in the main sequence, and ρ is an adjustable calculation coefficient;

[0106] The ninth processing unit is used to calculate the influence correlation degree of multiple influence sequences on the main sequence based on the influence correlation coefficient set, and obtain the first correlation degree set.

[0107] Furthermore, the system also includes:

[0108] The second construction unit is used to construct a coordinate space based on the multiple sensitive vibration signal features;

[0109] The tenth processing unit is used to input multiple sets of sensitive historical vibration signal features into the coordinate space to obtain multiple coordinate points;

[0110] The eleventh processing unit is used to cluster multiple coordinate points according to the operating status of the hydropower unit to obtain multiple clustering results.

[0111] The twelfth processing unit is used to obtain the hydropower unit state evaluation space based on multiple clustering results and the coordinate space.

[0112] Furthermore, the system also includes:

[0113] The thirteenth processing unit is used to collect and acquire multiple different operating states of the hydropower unit in history, including normal, fault tendency, and fault occurrence.

[0114] The fourteenth processing unit is used to collect and acquire the characteristics of sensitive historical vibration signals under different time periods corresponding to the different operating states in history, and obtain multiple corresponding coordinate points.

[0115] The fifteenth processing unit is used to cluster the coordinate points corresponding to different operating states to obtain multiple clustering results.

[0116] Furthermore, the system also includes:

[0117] The seventh acquisition unit is used to acquire the real-time vibration signal of the current hydropower unit;

[0118] The sixteenth processing unit is used to extract features based on the real-time vibration signal to obtain real-time sensitive vibration signal feature data.

[0119] The seventeenth processing unit is used to input the real-time sensitive vibration signal feature data into the hydropower unit state assessment space to obtain the corresponding real-time coordinate points.

[0120] The eighteenth processing unit is used to calculate multiple Euclidean distances between the real-time coordinate point and multiple clustering result centers;

[0121] The nineteenth processing unit is used to perform weight allocation based on the magnitude of the multiple Euclidean distances to obtain a first weight allocation result;

[0122] The twentieth processing unit is used to perform weighted adjustment on the multiple Euclidean distances using the first weight allocation result.

[0123] The 21st processing unit is used to obtain the operating status corresponding to the clustering result corresponding to the smallest Euclidean distance based on the adjusted multiple Euclidean distances, and use it as the state evaluation result of the hydropower unit.

[0124] Example 3

[0125] Based on the same inventive concept as the method for assessing the condition of a hydropower unit based on vibration signals in the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in Embodiment 1.

[0126] Exemplary electronic devices

[0127] The following is for reference. Figure 5 To describe the electronic device of this application,

[0128] Based on the same inventive concept as the method for assessing the condition of a hydropower unit based on vibration signals in the foregoing embodiments, this application also provides a system for assessing the condition of a hydropower unit based on vibration signals, comprising: a processor coupled to a memory for storing a program, wherein when the program is executed by the processor, the system performs the steps of the method described in Embodiment 1.

[0129] The electronic device 300 includes a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, processor 302, and memory 301 can be interconnected via the bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus architecture 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0130] Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits used to control the execution of programs according to the present application.

[0131] Communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0132] Memory 301 can be ROM or other types of static storage devices capable of storing static information and instructions, RAM or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory can exist independently and be connected to the processor via bus architecture 304. Memory can also be integrated with the processor.

[0133] The memory 301 stores computer execution instructions for implementing the scheme of this application, and the processor 302 controls the execution. The processor 302 executes the computer execution instructions stored in the memory 301, thereby realizing the method for assessing the state of a hydropower unit based on vibration signals provided in the above embodiments of this application.

[0134] Those skilled in the art will understand that the various numerical designations, such as "first," "second," etc., used in this application are merely for descriptive convenience and are not intended to limit the scope of this application, nor do they indicate a chronological order. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one" refers to one or more. "At least two" refers to two or more. "At least one," "any one," or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0135] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0136] The various illustrative logic units and circuits described in this application may be implemented or operate the described functions using a general-purpose processor, digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor may be a microprocessor, and optionally, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented using a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0137] The steps of the methods or algorithms described in this application can be directly embedded in hardware, a software unit executed by a processor, or a combination of both. The software unit can be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other storage medium of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be disposed in an ASIC, which can be disposed in a terminal. Optionally, the processor and storage medium can also be disposed in different components within the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0138] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative examples of this application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for assessing the condition of a hydropower unit based on vibration signals, characterized in that, The method includes: Historical vibration signals from the previous operation of the hydropower unit were collected to obtain a set of historical vibration signals. Based on the set of historical vibration signals, multi-dimensional historical vibration signal feature information is extracted from the historical vibration signals to obtain multiple sets of historical vibration signal features. The correlation between multiple sets of historical vibration signal features and the operational stability of hydropower units is analyzed to obtain a first correlation set; Based on the first set of correlation degrees, at least two vibration signal features with the highest correlation degree are obtained as sensitive vibration signal features; Based on the characteristics of the sensitive vibration signals, a set of corresponding sensitive historical vibration signals is obtained, and a state assessment space for hydropower units is constructed. The real-time vibration signal of the current hydropower unit is collected and input into the hydropower unit status assessment space to obtain the hydropower unit status assessment result; The constructed hydropower unit state assessment space includes: A coordinate space is constructed based on the characteristics of the aforementioned sensitive vibration signals; Multiple sets of sensitive historical vibration signal features are input into the coordinate space to obtain multiple coordinate points; Based on the operating status of the hydropower unit, multiple coordinate points are clustered to obtain multiple clustering results; Based on the multiple clustering results and the coordinate space, the state evaluation space of the hydropower unit is obtained; The process of acquiring the real-time vibration signal of the hydropower unit and inputting it into the hydropower unit state evaluation space includes: Collect and acquire the real-time vibration signal of the current hydropower unit; Feature extraction is performed on the real-time vibration signal to obtain real-time sensitive vibration signal feature data; The real-time sensitive vibration signal feature data is input into the hydropower unit state assessment space to obtain the corresponding real-time coordinate points; Calculate multiple Euclidean distances between the real-time coordinate points and multiple cluster result centers; Based on the magnitudes of the multiple Euclidean distances, weights are assigned to obtain a first weight assignment result; The weighted adjustment is performed on the multiple Euclidean distances using the first weight allocation result; Based on the adjusted Euclidean distances, the operating state corresponding to the clustering result with the smallest Euclidean distance is obtained, which is used as the state evaluation result of the hydropower unit.

2. The method according to claim 1, characterized in that, The historical vibration signals acquired during the previous operation of the hydropower unit include: Set the preset time period to obtain; Based on the current hydropower units, multiple hydropower units of the same family are obtained; Historical vibration signals of the current hydropower unit and multiple hydropower units of the same family are collected within a preset time period in multiple historical periods to obtain the set of historical vibration signals.

3. The method according to claim 2, characterized in that, The analysis of the correlation between multiple sets of historical vibration signal features and the operational stability of hydropower units includes: Collect and obtain operational stability data of the current hydropower unit and multiple hydropower units of the same family within a preset time period in multiple historical periods to obtain an operational stability data set; Set the operational stability dataset as the main sequence; Multiple sets of historical vibration signal features are used as multiple influence sequences; The data within the main sequence and multiple affected sequences are normalized to obtain the processing result; Based on the processing results, the correlation between the main sequence and multiple influencing sequences is calculated.

4. The method according to claim 3, characterized in that, The calculation of the correlation between the main sequence and the multiple influencing sequences includes: Based on the data within the main sequence and multiple influence sequences, the influence correlation coefficients between the multiple influence sequences and the main sequence are calculated using the following formula to obtain a set of influence correlation coefficients. in, Let be the correlation coefficient between the k-th data point in the i-th influence sequence and the k-th data point in the main sequence. The calculation coefficients are adjustable. Based on the set of influence correlation coefficients, the influence correlation degree of multiple influence sequences on the main sequence is calculated to obtain the first set of correlation degrees.

5. The method according to claim 1, characterized in that, The step of clustering multiple coordinate points based on the operating status of the hydropower unit includes: The hydropower unit was collected and acquired from multiple different operating states in history, including normal, fault-prone, and fault-occurring states. Collect and acquire the characteristics of sensitive historical vibration signals under different time periods corresponding to the aforementioned operating states in history, and obtain multiple corresponding coordinate points; Clustering is performed on the coordinate points corresponding to different operating states to obtain multiple clustering results.

6. A system for assessing the condition of a hydropower unit based on vibration signals, characterized in that, The system includes: The first acquisition unit is used to collect historical vibration signals during the operation of the hydropower unit in the previous history and obtain a set of historical vibration signals. The first processing unit is configured to extract multi-dimensional historical vibration signal feature information from the historical vibration signal set to obtain multiple historical vibration signal feature sets. The second processing unit is used to analyze the correlation between multiple sets of historical vibration signal features and the operational stability of the hydropower unit to obtain a first correlation set. The second obtaining unit is used to obtain at least two vibration signal features with the highest correlation based on the first correlation set, as sensitive vibration signal features. The first construction unit is used to obtain a set of corresponding sensitive historical vibration signal features based on the sensitive vibration signal features, and to construct a hydropower unit state assessment space. The third processing unit is used to collect the real-time vibration signal of the current hydropower unit, input it into the hydropower unit state evaluation space, and obtain the hydropower unit state evaluation result. The second construction unit is used to construct a coordinate space based on the multiple sensitive vibration signal features; The tenth processing unit is used to input multiple sets of sensitive historical vibration signal features into the coordinate space to obtain multiple coordinate points; The eleventh processing unit is used to cluster multiple coordinate points according to the operating status of the hydropower unit to obtain multiple clustering results. The twelfth processing unit is used to obtain the hydropower unit state evaluation space based on multiple clustering results and the coordinate space. The seventh acquisition unit is used to acquire the real-time vibration signal of the current hydropower unit; The sixteenth processing unit is used to extract features based on the real-time vibration signal to obtain real-time sensitive vibration signal feature data. The seventeenth processing unit is used to input the real-time sensitive vibration signal feature data into the hydropower unit state assessment space to obtain the corresponding real-time coordinate points. The eighteenth processing unit is used to calculate multiple Euclidean distances between the real-time coordinate point and multiple clustering result centers; The nineteenth processing unit is used to perform weight allocation based on the magnitude of the multiple Euclidean distances to obtain a first weight allocation result; The twentieth processing unit is used to perform weighted adjustment on the multiple Euclidean distances using the first weight allocation result. The 21st processing unit is used to obtain the operating status corresponding to the clustering result corresponding to the smallest Euclidean distance based on the adjusted multiple Euclidean distances, and use it as the state evaluation result of the hydropower unit.

7. A system for assessing the condition of a hydropower unit based on vibration signals, characterized in that, include: A processor coupled to a memory for storing a program, which, when executed by the processor, causes the system to perform the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images