Hydropower station electric power production equipment state diagnosis and analysis visualization method

Abstract

The invention relates to the technical field of hydroelectric generating set state monitoring, in particular to a hydroelectric generating set state diagnosis and analysis visualization method, which comprises the following steps of: acquiring operation data of a hydroelectric generating set; a first database is constructed, the first database is constructed based on historical operation data of the hydroelectric generating set, and meanwhile a relational data table between parameters in the operation data of the hydroelectric generating set is configured; constructing a second database, importing the operation data of the hydroelectric generating set into the second database, sequentially inputting the data in the second database into a first calculation module and a second calculation module for calculation, and inputting the solved hydroelectric generating set equipment diagnosis result into the second calculation module for calculation by the first calculation module; and obtaining a hydroelectric generating set equipment diagnosis result and an early warning scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower unit status monitoring, and in particular to a method for visualizing status diagnosis and analysis of power production equipment in a hydropower station. Background Art

[0002] As the core equipment for clean energy production, the safe and stable operation of hydropower units is crucial to the power system. With the development of information technology, equipment diagnosis and early warning technology based on big data and artificial intelligence has gradually become a research hotspot. This technology collects and analyzes the operating data of hydropower units, establishes databases and calculation models, and realizes real-time monitoring, fault diagnosis and early warning of equipment status. At present, traditional monitoring and diagnosis technology of hydropower units has many shortcomings. First, data collection is often limited to a small number of key parameters, which is difficult to fully reflect the operating status of the equipment. Secondly, the data storage and management methods are relatively simple, lacking effective integration of historical data and real-time data, resulting in low data utilization. Furthermore, the existing diagnostic methods mostly rely on empirical rules and simple threshold judgments, which are not only difficult to cope with complex fault modes and dynamic operating environments, but also difficult to support predictive maintenance and refined management, limiting the intelligence and precision of hydropower unit operation and maintenance. Summary of the invention

[0003] The purpose of the present invention is to provide a visualization method for status diagnosis and analysis of power production equipment in a hydropower station. By constructing a dual database system, the method realizes the effective integration of historical data and real-time data. By combining a first calculation module with a second calculation module, accurate equipment diagnosis and early warning can be performed, which greatly improves the accuracy of diagnosis of key equipment of hydropower units and the timeliness of early warning, and provides strong technical support for the intelligent operation and maintenance of hydropower units.

[0004] The present invention is achieved through the following technical solutions:

[0005] A method for visualizing the state diagnosis and analysis of power production equipment in a hydropower station, the method comprising the following steps:

[0006] Collecting the operation data of hydropower units;

[0007] Constructing a first database, wherein the first database is constructed based on historical operation data of the hydropower unit, and configuring a relationship data table between various parameters in the operation data of the hydropower unit;

[0008] Construct a second database, import the operating data of the hydropower unit into the second database, input the data in the second database into the first calculation module and the second calculation module in turn for calculation, the first calculation module inputs the solved hydropower unit equipment diagnosis result into the second calculation module for calculation, and obtains the hydropower unit equipment diagnosis result and early warning plan.

[0009] Optionally, the collecting of the operating data of the hydropower unit is specifically: deploying a variety of sensors on the auxiliary control system equipment of the hydropower unit, the various sensors including temperature sensors, pressure sensors and flow sensors, to obtain the operating data of the hydropower unit.

[0010] Optionally, the data in the second database is sequentially input into the first calculation module and the second calculation module for calculation, wherein before the data in the second database is input into the first calculation module for calculation, a preprocessing step is also included, and the preprocessing step includes: removing outliers from the data in the second database and standardizing the data in the second database.

[0011] Optionally, the data in the second database is input into the first calculation module for calculation, and the calculation steps are:

[0012] Perform feature extraction on the preprocessed data in the second database to obtain time domain features and frequency domain features;

[0013] Combine the time domain features with the frequency domain features to obtain a feature vector;

[0014] The feature vector is input into the preset SVM model for calculation to obtain the fault type of the hydropower unit equipment to represent the diagnosis result of the hydropower unit equipment.

[0015] Optionally, the feature extraction is performed on the pre-processed data in the second database, wherein the calculation formula of the time domain feature is:

[0016]

[0017] Among them, x i is the sampling data point of the time domain signal, N is the number of sampling points, RMS is the root mean square value, CF is the peak factor, and IF is the impulse factor.

[0018] Optionally, the calculation formula for the frequency domain feature is:

[0019]

[0020] Where X(f) is the Fourier transform of the signal, f is the frequency, E is the spectral energy, X is the original data, and FC is the frequency center.

[0021] Optionally, the feature vector is input into a preset SVM model for calculation, and the calculation formula is:

[0022] X'=[RMS,CF,IF,E,FC] T

[0023]

[0024] σ=argmax k f k (X')

[0025]

[0026] Among them, X' is the input feature vector, X i ' is the support vector, K(X i ',X') is the kernel function, α i is the Lagrange multiplier, y i is the class label, b is the bias term, n is the number of support vectors, and f k (X') is the decision function of the kth binary classifier, σ is the fault type of the hydropower unit equipment fault, A and B are calibrated parameters, and P(σ=k|X') is the confidence level.

[0027] Optionally, the calculation formula of the second calculation module is:

[0028]

[0029]

[0030] Where σ is the fault type, F(σ) is the severity function of the fault type, and α σ is the basic severity coefficient associated with the fault type 0<α σ ≤1, n is the number of influencing factors considered, β i is the weight of the i-th influencing factor, γ i (σ) is the score of the fault type on the i-th influencing factor 0≤γ i (σ)≤1, m is the number of data indicators in the second database, S is the comprehensive severity score, y j is the current value of the i-th indicator, yj,min,y j,max are the minimum and maximum values ​​of the i-th indicator respectively, and w1 and w2 are the weights respectively.

[0031] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0032] The present invention realizes the effective integration of historical data and real-time data by constructing a dual database system. By combining the first calculation module with the second calculation module, accurate equipment diagnosis and early warning can be performed, which greatly improves the accuracy of diagnosis of key equipment of hydropower units and the timeliness of early warning, and provides strong technical support for the intelligent operation and maintenance of hydropower units. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1A schematic flow chart of a method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station provided by the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, what is described is only a part of the present invention, not all of it. Generally, the components of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0035] like Figure 1 As shown, the present invention provides one embodiment: a method for visualizing the state diagnosis and analysis of power production equipment in a hydropower station, the method comprising the steps of:

[0036] Collecting the operation data of hydropower units;

[0037] Constructing a first database, wherein the first database is constructed based on historical operation data of the hydropower unit, and configuring a relationship data table between various parameters in the operation data of the hydropower unit;

[0038] Construct a second database, import the operating data of the hydropower unit into the second database, input the data in the second database into the first calculation module and the second calculation module in turn for calculation, the first calculation module inputs the solved hydropower unit equipment diagnosis result into the second calculation module for calculation, and obtains the hydropower unit equipment diagnosis result and early warning plan.

[0039] During implementation, this embodiment deploys various types of sensors, builds a communication network architecture and constructs a database to collect and store the operating data of the equipment in real time; displays the operating data of the equipment in real time through a graphical interface, and allows users to build real-time monitoring pages configured on demand, including tables, line charts, bar charts, equipment icons, status indicator lights and other visual elements, and can also customize the color of the page and the color of the icon. The platform monitoring page is simple and easy to learn, has lossless page scaling, and has permission-based access; by analyzing the type of equipment, operating characteristics and historical data, formulate appropriate risk alarm logic. The alarm logic can be formulated based on threshold judgment, trend analysis, pattern recognition and other methods. Construct a first database, which is used to store the relationship data table between the parameters in the relevant data of the hydropower station; construct a second database, which is used to store the real-time data of the hydropower station. The data from the equipment side are collected through the IEC61850 protocol and the Modbus TCP protocol respectively, and are sent to the DAI data acquisition interface after being unified as the OPC protocol interface by the OPC Server, and then sent to the DAS data acquisition workstation. The DAS uploads the data to the PRASS real-time database, and the data in the database are sent to the PRASS application service and the PRASS calculation service respectively. The PRASS calculation service represents the first calculation module, and the PRASS application service represents the second calculation module. The PRASS calculation service is responsible for diagnosing the fault types of key equipment of the hydropower unit, and the PRASS application service is responsible for generating comprehensive diagnosis results and early warning plans.

[0040] In this embodiment, the operation data of the hydropower unit is collected, which specifically includes: deploying a variety of sensors on the auxiliary control system equipment of the hydropower unit, the various sensors include temperature sensors, pressure sensors and flow sensors, to obtain the operation data of the hydropower unit.

[0041] In this embodiment, various types of sensors, such as temperature sensors, pressure sensors, flow sensors, etc., are deployed in key equipment and areas of the auxiliary control system of the hydropower station to collect the operation data of the equipment in real time. These sensors should have the characteristics of high precision and high stability to ensure that the collected data is accurate and reliable.

[0042] In the specific application of this embodiment, the data in the second database is sequentially input into the first calculation module and the second calculation module for calculation, wherein before the data in the second database is input into the first calculation module for calculation, a preprocessing step is also included, and the preprocessing step includes: removing outliers from the data in the second database and standardizing the data in the second database.

[0043] The data in the second database is input into the first calculation module for calculation, and the calculation steps are as follows:

[0044] Perform feature extraction on the preprocessed data in the second database to obtain time domain features and frequency domain features;

[0045] The calculation formula of time domain characteristics is:

[0046]

[0047] Among them, x i is the sampling data point of the time domain signal, N is the number of sampling points, RMS is the root mean square value, CF is the peak factor, and IF is the impulse factor.

[0048] The calculation formula of frequency domain features is:

[0049]

[0050] Where X(f) is the Fourier transform of the signal, f is the frequency, E is the spectral energy, X is the original data, and FC is the frequency center.

[0051] Combine the time domain features with the frequency domain features to obtain a feature vector;

[0052] X'=[RMS,CF,IF,E,FC] T

[0053] The feature vector is input into the preset SVM model for calculation to obtain the fault type of the hydropower unit equipment to represent the diagnosis result of the hydropower unit equipment.

[0054]

[0055] σ=argmax k f k (X')

[0056]

[0057] Among them, X' is the input feature vector, X i ' is the support vector, K(X i ',X') is the kernel function, α i is the Lagrange multiplier, y i is the class label, b is the bias term, n is the number of support vectors, and f k (X') is the decision function of the kth binary classifier, σ is the fault type of the hydropower unit equipment fault, A and B are calibrated parameters, and P(σ=k|X') is the confidence level.

[0058] The second calculation module is based on the output of the first calculation module, and its calculation formula is:

[0059]

[0060] Where σ is the fault type, F(σ) is the severity function of the fault type, and α σ is the basic severity coefficient associated with the fault type 0<α σ ≤1, n is the number of influencing factors considered, β i is the weight of the i-th influencing factor, γ i (σ) is the score of the fault type on the i-th influencing factor 0≤γ i (σ)≤1, m is the number of data indicators in the second database, S is the comprehensive severity score, y j is the current value of the i-th indicator, yj,min,y j,max are the minimum and maximum values ​​of the i-th indicator respectively, and w1 and w2 are the weights respectively.

[0061] During implementation, the comprehensive severity score is divided into warning levels, including normal, attention, warning and severe levels. The warning plan selects the set warning plan according to the specific warning level and fault type. It can be understood that the warning plan is configured for the specific site, including warning, shutdown, operation personnel processing, etc., which will not be repeated in this embodiment.

[0062] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station, characterized in that: The steps of the method include: Collecting operating data of hydropower units; Constructing a first database, wherein the first database is constructed based on historical operating data of the hydropower unit and configuring a relationship data table between various parameters in the operating data of the hydropower unit; Construct a second database, import the operating data of the hydropower unit into the second database, and input the data in the second database into the first calculation module and the second calculation module in turn for calculation. The first calculation module inputs the solved hydropower unit equipment diagnosis results into the second calculation module for calculation to obtain the hydropower unit equipment diagnosis results and early warning plan.

2. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 1, characterized in that: The collecting of the operating data of the hydropower unit is specifically as follows: multiple sensors are arranged on the auxiliary control system equipment of the hydropower unit, and the multiple sensors include temperature sensors, pressure sensors and flow sensors to obtain the operating data of the hydropower unit.

3. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 2, characterized in that: The data in the second database are sequentially input into the first calculation module and the second calculation module for calculation, wherein, before the data in the second database is input into the first calculation module for calculation, a preprocessing step is also included, and the preprocessing step includes: removing outliers from the data in the second database and standardizing the data in the second database.

4. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 3 is characterized in that: The data in the second database is input into the first calculation module for calculation, and the calculation steps are as follows: Performing feature extraction on the pre-processed data in the second database to obtain time domain features and frequency domain features; Combine the time domain features with the frequency domain features to obtain the feature vector; The feature vector is input into the preset SVM model for calculation to obtain the fault type of the hydropower unit equipment to represent the diagnosis result of the hydropower unit equipment.

5. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 4, characterized in that: The feature extraction is performed on the data in the second database after preprocessing, wherein the calculation formula of the time domain feature is: Among them, x i is the sampling data point of the time domain signal, N is the number of sampling points, RMS is the root mean square value, CF is the crest factor, and IF is the impulse factor.

6. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 4, characterized in that: The calculation formula of frequency domain characteristics is: Where X(f) is the Fourier transform of the signal, f is the frequency, E is the spectral energy, X is the original data, and FC is the frequency center.

7. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 4, characterized in that: The feature vector is input into the preset SVM model for calculation, and the calculation formula is: X'=[RMS,CF,IF,E,FC] T σ=argmax k f k (X') Among them, X' is the input feature vector, X i ' is the support vector, K(X i ',X') is the kernel function, α i is the Lagrange multiplier, y i is the class label, b is the bias term, n is the number of support vectors, f k (X') is the decision function of the kth binary classifier, σ is the fault type of the hydropower unit equipment fault, A and B are calibrated parameters, and P(σ=k|X') is the confidence level.

8. The method for visualizing the status diagnosis and analysis of power production equipment in a hydropower station according to claim 3, characterized in that: The calculation formula of the second calculation module is: Where σ is the fault type, F(σ) is the severity function of the fault type, and α σ is the basic severity coefficient related to the fault type 0<α σ ≤1, n is the number of influencing factors considered, β i is the weight of the i-th influencing factor, γ i (σ) is the score of the fault type on the i-th influencing factor 0≤γ i (σ)≤1, m is the number of data indicators in the second database, S is the comprehensive severity score, y j is the current value of the jth indicator, y j,min 、y j,max are the minimum and maximum values ​​of the j-th indicator, respectively, and w1 and w2 are the weights, respectively.

Images