Intelligent analysis system and method for start-up and shutdown data of hydro-generator sets

Abstract

The present invention discloses an intelligent analysis system and method for the start-up and shutdown data of a hydro-generator set, relating to the technical field of hydro-generator set start-up and shutdown data analysis. The system comprises: an operation data acquisition module for collecting key operation data during the start-up and shutdown process of the unit, forming analysis report data for each start-up and shutdown of the unit; a first early warning module for analyzing data changes during the start-up and shutdown of the unit during the operating condition conversion, and generating a first early warning message when the data change amplitude does not meet a predetermined threshold; a second early warning module for obtaining the distribution interval of the unit equipment operation data, and generating a second early warning message when the unit equipment operation data deviates from the distribution interval; and a correlation analysis module for determining the correlation relationship between the first early warning message and the second early warning message based on the first early warning message and the second early warning message, and storing the correlation relationship in a database. The present application can analyze the equipment that affects the start-up and shutdown process, reduce the start-up and shutdown time, and improve the success rate of the start-up and shutdown.

Description

Technical Field

[0001] The present invention relates to the technical field of hydro-generator set start-up and shutdown data analysis, and in particular to a system and method for intelligent analysis of start-up and shutdown data of a hydro-generator set. Background Art

[0002] In today's new power systems, the proportion of renewable energy sources such as wind and solar power continues to increase. Large hydropower units, due to their unique characteristics of rapid response and regulation, are gradually becoming peak-shaving and frequency-regulating power stations, playing a vital role in grid stability. However, due to the frequent and deeper peak-shaving and frequency-regulating tasks, frequent unit startups and shutdowns have become the norm, posing a severe challenge to equipment operation and maintenance management.

[0003] Currently, the analysis of start-up and shutdown data of hydro-turbine generator sets mainly relies on manual analysis based on expert experience, which places high demands on personnel and cannot be analyzed dynamically in real time. With the rise of advanced technologies such as artificial intelligence and machine learning, how to rely on the industrial Internet platform, introduce advanced algorithms such as artificial intelligence and machine learning, and make intelligent judgments and analyses on auxiliary equipment that affect the start-up and shutdown process, thereby reducing the start-up and shutdown time and improving the success rate has become one of the problems that need to be solved urgently. Summary of the Invention

[0004] The object of the present invention is to provide a system and method for intelligent analysis of start-up and shutdown data of a hydro-generator set, so as to solve the problems raised in the prior art.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for intelligently analyzing the start-up and shutdown data of a hydro-generator set, the method comprising:

[0006] S1. Collect key operating data during the unit startup and shutdown process to generate analysis report data for each unit startup and shutdown;

[0007] S2. Analyze data changes during the unit startup and shutdown process, and generate a first warning message when the data change amplitude does not meet a predetermined threshold;

[0008] S3. Obtaining a distribution interval of the unit equipment operation data, and generating a second warning message when the unit equipment operation data deviates from the distribution interval;

[0009] S4. Based on the first warning information and the second warning information, determine the correlation between the first warning information and the second warning information, and store the correlation in a database.

[0010] According to the above technical solution, the key operating data include: unit start-up and shutdown time data, unit start-up and shutdown parameter data, unit start-up and shutdown bearing pad temperature data and unit start-up and shutdown vibration data.

[0011] According to the above technical solution, the unit startup and shutdown time data refers to the time data used for a single unit startup and shutdown under the same operating condition conversion; specifically, it includes: the time from the start of unit rotation to the unit speed reaching the rated value, the time for the guide vane opening to reach the steady-state value, and the time from the start of guide vane movement to the first entry into the synchronization zone during startup; the time from the unit speed dropping to the set speed during shutdown, and the time for the guide vane opening to drop from zero; wherein, the rated value, steady state, synchronization zone, and set speed are all based on the values ​​set by the system staff;

[0012] The unit startup and shutdown parameter data refers to the parameter change data during a single unit startup and shutdown process, specifically including: the swing data of the guide vanes and the pause data during the swing of the guide vanes;

[0013] The unit start-up and shutdown bearing shoe temperature data refers to the bearing shoe temperature, oil temperature and cooling water temperature data of each part of the unit during the start-up and shutdown process;

[0014] The unit start-up and shutdown vibration data refers to the unit vibration, swing and pressure pulsation signal data during the start-up and shutdown process.

[0015] According to the above technical solution, the operating condition conversion specifically includes: shutdown to idling operating condition conversion, shutdown to no-load operating condition conversion, shutdown to power generation operating condition conversion, idling to no-load operating condition conversion, idling to power generation operating condition conversion conditions, no-load to power generation operating condition conversion, power generation to no-load operating condition conversion, power generation to idling operating condition conversion, power generation to shutdown operating condition conversion, no-load to idling operating condition conversion, no-load to shutdown operating condition conversion and idling to shutdown operating condition conversion.

[0016] According to the above technical solution, the analysis of data changes of the unit equipment during the operating state conversion includes:

[0017] Take the start-up and shutdown time consumption data of N groups of units under any operating condition conversion as the historical reference data group under the operating condition conversion, wherein the predetermined threshold calculation includes:

[0018]

[0019] Among them, h min With h max They represent the upper and lower limits of the predetermined threshold respectively; h0 represents the average value of the start-up and shutdown time consumption data of N groups of units; h1 and h2 represent the minimum and maximum values ​​of the start-up and shutdown time consumption data of N groups of units respectively; N refers to the constant term;

[0020] If the start-up and shutdown time data of the unit under this working condition conversion is less than h min or higher than h max , it is determined that the predetermined threshold is not met.

[0021] According to the above technical solution, the determination of the deviation of the unit equipment operating data from the distribution interval includes:

[0022] Obtain the distribution range of unit equipment operation data, including:

[0023] For any of the unit equipment operation data, including the unit start-up and shutdown parameter data, the unit start-up and shutdown bearing shoe temperature data, and the unit start-up and shutdown vibration data, establish a two-dimensional reference point corresponding to the data, and write it in the format of (x0, y0), where x0 represents the data collection batch; y0 represents the actual number of the data;

[0024] Obtain the corresponding two-dimensional reference points of the equipment operation data to be judged, and at the same time obtain the corresponding two-dimensional reference points of the corresponding N groups of historical data to form a judgment set;

[0025] Set the neighbor point parameter k for the judgment set. For each point in the judgment set, calculate its distance to other points, find the nearest k points, and calculate the local density of the point to be tested:

[0026]

[0027] Among them, L p represents the local density of the test point p; m represents the set of k points closest to the test point p; q represents any point in the set m; D(p, q) refers to the reachable distance between points p and q. The reachable distance calculation includes:

[0028] D(p,q)=max(k distance、q , d(p,q))

[0029] Among them, k distance、q represents the distance from point q to its kth nearest neighbor; d(p,q) represents the actual distance between point p and point q;

[0030] Calculate the local outlier factor of the test point p:

[0031]

[0032] Among them, L q represents the local density of point q; LOF(p) represents the local outlier factor of the test point p;

[0033] If the local outlier factor of the test point p is the highest among the local outlier factors of the N groups of historical data, it is determined that the unit equipment operation data corresponding to the test point p deviates from the distribution interval.

[0034] According to the above technical solution, determining the association relationship between the first warning information and the second warning information includes:

[0035] Take N groups of early warning data. If at least one type of early warning information exists in any group of early warning data, calculate the prior probability of the existence of the second early warning information, denoted as G1 and G2, respectively. G1 refers to the prior probability of the existence of the second early warning information, and G2 refers to the prior probability of the absence of the second early warning information. Calculate the probability G3 that the first early warning information does not exist under the premise that the second early warning information exists. Calculate the probability G4 that the first early warning information does not exist under the premise that the second early warning information does not exist.

[0036] Calculate the marginal probability G5 = G1*G3+G2*G4;

[0037] Based on the marginal probability G5, the probability G6 of the existence of the second warning information under the premise that the first warning information does not exist is formed:

[0038]

[0039] Based on the probability G6, a reference point for equipment maintenance is formed, and new data is added to the N groups of early warning data in real time. The probability G6 is continuously solved. If the probability G6 increases, the interval time of equipment maintenance decreases. If the probability G6 decreases, the interval time of equipment maintenance increases.

[0040] An intelligent analysis system for start-up and shutdown data of a hydro-generator set, comprising:

[0041] The operation data acquisition module is used to collect key operation data during the start-up and shutdown of the unit, and form analysis report data for each start-up and shutdown of the unit;

[0042] The first warning module is used to analyze the data changes during the operation state conversion of the unit when it is started and shut down, and generate a first warning message when the data change amplitude does not meet the predetermined threshold;

[0043] A second warning module is used to obtain the distribution interval of the unit equipment operation data, and generate a second warning message when the unit equipment operation data deviates from the distribution interval;

[0044] The correlation analysis module determines the correlation relationship between the first warning information and the second warning information based on the first warning information and the second warning information, and stores the correlation relationship in the database.

[0045] According to the above technical solution, based on the correlation between the first warning information and the second warning information, a reference point for the unit equipment maintenance is formed, and new data is added to the warning data group in real time during the training process, and the solution is continuously sought. If the solution value increases, the interval time of equipment maintenance decreases, and if the solution value decreases, the interval time of equipment maintenance increases.

[0046] Compared with the prior art, the beneficial effects of the present invention are: this application is based on the collection and analysis of key influencing factors during the start-up and shutdown process of the unit, realizes the extraction of key operating data features during the start-up and shutdown process of the unit, and uses advanced technologies such as artificial intelligence and machine learning to analyze and process the key operating data of each start-up and shutdown, forming data comparison under different operating condition conversion conditions, and can effectively judge the fault condition of the unit based on the data changes during the operating condition conversion of the unit start-up and shutdown and the distribution range of the unit equipment operating data, thereby reducing the start-up and shutdown time and improving the success rate of start-up and shutdown. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The figure is a flow chart of the method for intelligent analysis of start-up and shutdown data of a hydro-generator set according to the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0049] Example: Figure 1 As shown, the present invention provides a method for intelligent analysis of start-up and shutdown data of a hydro-generator set, the method comprising:

[0050] Collect key operating data during the unit startup and shutdown process to generate analytical report data for each unit startup and shutdown;

[0051] The key operating data include: unit start-up and shutdown time consumption data, unit start-up and shutdown parameter data, unit start-up and shutdown bearing bush temperature data and unit start-up and shutdown vibration data.

[0052] The unit startup and shutdown time data refers to the time data used for a single unit startup and shutdown under the same operating condition conversion; specifically, it includes: the time from the start of unit rotation to the unit speed reaching the rated value, the time for the guide vane opening to reach the steady-state value, and the time from the start of guide vane movement to the first entry into the synchronization zone during startup; the time from the unit speed dropping to the set speed during shutdown, and the time for the guide vane opening to drop from zero; the rated value, steady state, synchronization zone, and set speed are all based on the values ​​set by the system staff;

[0053] The unit startup and shutdown parameter data refers to the parameter changes during a single startup and shutdown process, specifically including: guide vane swing data and pause data during guide vane swing; the unit startup and shutdown bearing pad temperature data refers to the bearing pad temperature, oil temperature, and cooling water temperature data of various parts of the unit during startup and shutdown; the unit startup and shutdown vibration data refers to the unit vibration, swing, and pressure pulsation signal data during startup and shutdown. Data cleaning is the process of filtering out duplicate and redundant data, completing missing data, and correcting or deleting erroneous data, ultimately organizing it into data that can be further processed and used.

[0054] In this embodiment, the development and application are based on the Industrial Internet platform to intelligently collect and analyze data and equipment related to key factors of unit startup and shutdown. The hardware resources include the following Table 1:

[0055] Table 1: Hardware resources at the plant side

[0056]

[0057] The virtual node resources include the following Table 2:

[0058] Table 2: Virtual node resources

[0059]

[0060] In the data collection process, the following methods are commonly used to deal with missing data values: deleting missing values; when the number of samples is large and the proportion of samples with missing values ​​in the entire sample is relatively small, in this case, we can use the simplest and most effective method to deal with missing values, which is to directly discard the samples with missing values.

[0061] Mean imputation method: divide the data into several groups according to the attribute with the largest attribute correlation coefficient of the missing value, then calculate the mean of each group separately, and put these means into the missing values.

[0062] Hot card filling method: find an object in the database that is most similar to it, and then fill it with the value of this similar object.

[0063] The operating condition conversion specifically includes: shutdown to idling operating condition conversion, shutdown to no-load operating condition conversion, shutdown to power generation operating condition conversion, idling to no-load operating condition conversion, idling to power generation operating condition conversion conditions, no-load to power generation operating condition conversion, power generation to no-load operating condition conversion, power generation to idling operating condition conversion, power generation to shutdown operating condition conversion, no-load to idling operating condition conversion, no-load to shutdown operating condition conversion and idling to shutdown operating condition conversion.

[0064] The specific start-up and shutdown processes include: Start-up process: shutdown state → start the unit technical water supply → remove the foundation pit heater → start the generator oil mist absorption device → start the carbon powder vacuum cleaner → start the hydraulic system → start the high-pressure oil → pull out the relay lock → start the machine to the speed regulator → idling state → close the demagnetization switch → turn on the excitation → no-load state → close the generator output circuit breaker → power generation state.

[0065] The startup process includes six sub-processes: "from shutdown to idling", "from shutdown to no-load", "from shutdown to power generation", "from idling to no-load", "idling to power generation", and "from no-load to power generation".

[0066] The start-up command can be issued to the unit only when the unit is in one of the states of "shutdown", "idling" or "no load" and the corresponding operating conditions are met.

[0067] The specific shutdown process is: power generation state → reduce load to zero → trip generator output circuit breaker → shutdown to excitation → shutdown to speed governor → apply high-pressure oil → apply electric brake → check guide vane position → check unit speed → apply brake and dust collector → check unit speed → apply relay lock → cut off brake → shut down unit technical water supply and main shaft sealing water → apply pit heater → cut off generator oil mist absorption device → cut off carbon powder dust collector → cut off brake dust collector → apply creep monitoring device → shutdown state.

[0068] Analyze the data changes during the unit startup and shutdown operation, and generate a first warning message when the data change amplitude does not meet the predetermined threshold;

[0069] The data changes of the analysis unit equipment during the working condition conversion include:

[0070] Take the start-up and shutdown time consumption data of N groups of units under any operating condition conversion as the historical reference data group under the operating condition conversion, wherein the predetermined threshold calculation includes:

[0071]

[0072] Among them, h min With h max They represent the upper and lower limits of the predetermined threshold respectively; h0 represents the average value of the start-up and shutdown time consumption data of N groups of units; h1 and h2 represent the minimum and maximum values ​​of the start-up and shutdown time consumption data of N groups of units respectively; N refers to the constant term;

[0073] If the start-up and shutdown time data of the unit under this working condition conversion is less than h min or higher than h max , it is determined that the predetermined threshold is not met.

[0074] Obtaining a distribution interval of the unit equipment operation data, and generating a second warning message when the unit equipment operation data deviates from the distribution interval;

[0075] Determining the deviation of the unit equipment operating data from the distribution range includes:

[0076] Obtain the distribution range of unit equipment operation data, including:

[0077] For any of the unit equipment operation data, including the unit start-up and shutdown parameter data, the unit start-up and shutdown bearing shoe temperature data, and the unit start-up and shutdown vibration data, establish a two-dimensional reference point corresponding to the data, and write it in the format of (x0, y0), where x0 represents the data collection batch; y0 represents the actual number of the data;

[0078] Obtain the corresponding two-dimensional reference points of the equipment operation data to be judged, and at the same time obtain the corresponding two-dimensional reference points of the corresponding N groups of historical data to form a judgment set;

[0079] Set the neighbor point parameter k for the judgment set. For each point in the judgment set, calculate its distance to other points, find the nearest k points, and calculate the local density of the point to be tested:

[0080]

[0081] Among them, L p represents the local density of the test point p; m represents the set of k points closest to the test point p; q represents any point in the set m; D(p, q) refers to the reachable distance between points p and q. The reachable distance calculation includes:

[0082] D(p,q)=max(k distance、q , d(p,q))

[0083] Among them, k distance、q represents the distance from point q to its kth nearest neighbor; d(p,q) represents the actual distance between point p and point q;

[0084] Calculate the local outlier factor of the test point p:

[0085]

[0086] Among them, L q represents the local density of point q; LOF(p) represents the local outlier factor of the test point p;

[0087] If the local outlier factor of the test point p is the highest among the local outlier factors of the N groups of historical data, it is determined that the unit equipment operation data corresponding to the test point p deviates from the distribution interval.

[0088] Based on the first warning information and the second warning information, the correlation relationship between the first warning information and the second warning information is determined and stored in a database.

[0089] Determining the association between the first warning information and the second warning information includes:

[0090] Take N groups of early warning data. If at least one type of early warning information exists in any group of early warning data, calculate the prior probability of the existence of the second early warning information, denoted as G1 and G2, respectively. G1 refers to the prior probability of the existence of the second early warning information, and G2 refers to the prior probability of the absence of the second early warning information. Calculate the probability G3 that the first early warning information does not exist under the premise that the second early warning information exists. Calculate the probability G4 that the first early warning information does not exist under the premise that the second early warning information does not exist.

[0091] Calculate the marginal probability G5 = G1*G3+G2*G4;

[0092] Based on the marginal probability G5, the probability G6 of the existence of the second warning information under the premise that the first warning information does not exist is formed:

[0093]

[0094] Based on the probability G6, a reference point for equipment maintenance is formed, and new data is added to the N groups of early warning data in real time. The probability G6 is continuously solved. If the probability G6 increases, the interval time of equipment maintenance decreases. If the probability G6 decreases, the interval time of equipment maintenance increases.

[0095] It also includes an intelligent analysis system for start-up and shutdown data of hydro-generator sets, which includes:

[0096] The operation data acquisition module is used to collect key operation data during the start-up and shutdown of the unit, and form analysis report data for each start-up and shutdown of the unit;

[0097] The first warning module is used to analyze the data changes during the operation state conversion of the unit when it is started and shut down, and generate a first warning message when the data change amplitude does not meet the predetermined threshold;

[0098] A second warning module is used to obtain the distribution interval of the unit equipment operation data, and generate a second warning message when the unit equipment operation data deviates from the distribution interval;

[0099] The correlation analysis module determines the correlation relationship between the first warning information and the second warning information based on the first warning information and the second warning information, and stores the correlation relationship in the database.

[0100] Based on the correlation between the first warning information and the second warning information, a reference point for the unit equipment maintenance is formed. New data is added to the warning data group in real time during the training process, and the solution is continuously sought. If the solution value increases, the interval time of equipment maintenance decreases. If the solution value decreases, the interval time of equipment maintenance increases.

[0101] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. An intelligent analysis method for start-up and shutdown data of a hydro-generator set, characterized by: The method includes: S1. Collect key operating data during the unit startup and shutdown process to generate analysis report data for each unit startup and shutdown; S2. Analyze data changes of the unit equipment during operating mode conversion, and generate a first warning message when the data change amplitude does not meet a predetermined threshold; S3. Obtaining a distribution interval of the unit equipment operation data, and generating a second warning message when the unit equipment operation data deviates from the distribution interval; S4. Based on the first warning information and the second warning information, determine the correlation between the first warning information and the second warning information, and store the correlation in a database; The key operating data include: unit start-up and shutdown time data, unit start-up and shutdown parameter data, unit start-up and shutdown bearing shoe temperature data, and unit start-up and shutdown vibration data; The unit startup and shutdown time data refers to the time data used for a single unit startup and shutdown under the same operating condition conversion; specifically, it includes: the time from the start of unit rotation to the unit speed reaching the rated value, the time for the guide vane opening to reach the steady-state value, and the time from the start of guide vane movement to the first entry into the synchronization zone during startup; the time from the unit speed dropping to the set speed during shutdown, and the time for the guide vane opening to drop from zero; the rated value, steady state, synchronization zone, and set speed are all based on the values ​​set by the system staff; The unit startup and shutdown parameter data refers to the parameter change data during a single unit startup and shutdown process, specifically including: the swing data of the guide vanes and the pause data during the swing of the guide vanes; The unit start-up and shutdown bearing shoe temperature data refers to the bearing shoe temperature, oil temperature and cooling water temperature data of each part of the unit during the start-up and shutdown process; The unit start-up and shutdown vibration data refers to the unit vibration, swing and pressure pulsation signal data during the start-up and shutdown process.

2. The method for intelligent analysis of start-up and shutdown data of a hydro-generator set according to claim 1, characterized in that: The operating condition conversion specifically includes: shutdown to idling operating condition conversion, shutdown to no-load operating condition conversion, shutdown to power generation operating condition conversion, idling to no-load operating condition conversion, idling to power generation operating condition conversion conditions, no-load to power generation operating condition conversion, power generation to no-load operating condition conversion, power generation to idling operating condition conversion, power generation to shutdown operating condition conversion, no-load to idling operating condition conversion, no-load to shutdown operating condition conversion and idling to shutdown operating condition conversion.

3. The intelligent analysis method for start-up and shutdown data of a hydro-generator set according to claim 1 is characterized in that: The data changes of the analysis unit equipment during the working condition conversion include: The start-up and shutdown time consumption data of N groups of units under any operating condition conversion are taken as the historical reference data group under the operating condition conversion, wherein the calculation of the predetermined threshold includes: Among them, h min With h max They represent the upper and lower limits of the predetermined threshold respectively; h0 represents the average value of the start-up and shutdown time consumption data of N groups of units; h1 and h2 represent the minimum and maximum values ​​of the start-up and shutdown time consumption data of N groups of units respectively; N refers to the constant term; If the start-up and shutdown time data of the unit under this working condition conversion is less than h min or higher than h max , it is determined that the predetermined threshold is not met.

4. The method for intelligent analysis of start-up and shutdown data of a hydro-generator set according to claim 3 is characterized in that: Determining the deviation of the unit equipment operating data from the distribution range includes: Obtain the distribution range of unit equipment operation data, including: For any of the unit equipment operation data, including the unit start-up and shutdown parameter data, the unit start-up and shutdown bearing shoe temperature data, and the unit start-up and shutdown vibration data, establish a two-dimensional reference point corresponding to the data, and write it in the format of (x0, y0), where x0 represents the data collection batch; y0 represents the actual number of the data; Obtain the corresponding two-dimensional reference points of the equipment operation data to be judged, and at the same time obtain the corresponding two-dimensional reference points of the corresponding N groups of historical data to form a judgment set; Set the neighbor point parameter k for the judgment set. For each point in the judgment set, calculate its distance to other points, find the nearest k points, and calculate the local density of the point to be tested: Among them, L p represents the local density of the test point p; m represents the set of k points closest to the test point p; q represents any point in the set m; D(p, q) refers to the reachable distance between points p and q. The calculation of the reachable distance includes: D(p、q)=max(k distance、q ,d(p、q)) Among them, k distance、q represents the distance from point q to its kth nearest neighbor; d(p,q) represents the actual distance between point p and point q; Calculate the local outlier factor of the test point p: Among them, L q Represents the local density of point q; LOF(p) represents the local outlier factor of the test point p; If the local outlier factor of the test point p is the highest among the local outlier factors of the N groups of historical data, it is determined that the unit equipment operation data corresponding to the test point p deviates from the distribution interval.

5. The method for intelligent analysis of start-up and shutdown data of a hydro-generator set according to claim 4 is characterized in that: Determining the association between the first warning information and the second warning information includes: Take N groups of early warning data. If at least one type of early warning information exists in any group of early warning data, calculate the prior probability of the existence of the second early warning information, denoted as G1 and G2, respectively. G1 refers to the prior probability of the existence of the second early warning information, and G2 refers to the prior probability of the absence of the second early warning information. Calculate the probability G3 that the first early warning information does not exist under the premise that the second early warning information exists. Calculate the probability G4 that the first early warning information does not exist under the premise that the second early warning information does not exist. Calculate the marginal probability G5 = G1*G3+G2*G4; Based on the marginal probability G5, the probability G6 of the existence of the second warning information under the premise that the first warning information does not exist is formed: Based on the probability G6, a reference point for equipment maintenance is formed, and new data is added to the N groups of early warning data in real time. The probability G6 is continuously solved. If the probability G6 increases, the interval time of equipment maintenance decreases. If the probability G6 decreases, the interval time of equipment maintenance increases.

6. An intelligent analysis system for start-up and shutdown data of a hydro-generator set, for implementing the intelligent analysis method for start-up and shutdown data of a hydro-generator set as claimed in claim 1, characterized in that: The system includes: The operation data acquisition module is used to collect key operation data during the start-up and shutdown of the unit, and form analysis report data for each start-up and shutdown of the unit; The first warning module is used to analyze the data changes during the operation state conversion of the unit when it is started and shut down, and generate a first warning message when the data change amplitude does not meet the predetermined threshold; A second warning module is used to obtain the distribution interval of the unit equipment operation data, and generate a second warning message when the unit equipment operation data deviates from the distribution interval; The correlation analysis module determines the correlation relationship between the first warning information and the second warning information based on the first warning information and the second warning information, and stores the correlation relationship in the database.

7. The intelligent analysis system for start-up and shutdown data of a hydro-generator set according to claim 6 is characterized in that: Based on the correlation between the first warning information and the second warning information, a reference point for the unit equipment maintenance is formed. New data is added to the warning data group in real time during the training process, and the solution is continuously sought. If the solution value increases, the interval time of equipment maintenance decreases. If the solution value decreases, the interval time of equipment maintenance increases.

Images