Multifunctional wind power plant intelligent monitoring platform

Abstract

The invention discloses a multifunctional wind power plant intelligent monitoring platform, and relates to the technical field of wind power plant monitoring, the multifunctional wind power plant intelligent monitoring platform comprises a data acquisition terminal, a central processing terminal and a fan early warning terminal, the data acquisition terminal comprehensively collects multiple attribute state parameters of a fan, and provides an accurate data basis for subsequent analysis and early warning; the central processing terminal scientifically divides time periods, calculates a plurality of indexes and quantifies the operation state of the fan from different angles, so that anomaly analysis is more accurate and reliable. The fan early warning terminal displays information according to the abnormal signal, so that workers can handle the information in time, the downtime is shortened, and the economic loss is reduced; the platform realizes real-time monitoring and analysis, provides a scientific basis for wind power plant management, and improves the management level and the operation benefit; the system is high in automation and intelligence degree, reduces manual intervention, reduces the cost, improves the working efficiency, guarantees the stable operation and power supply of the wind power plant, and plays an important role in promoting the sustainable development of the wind power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farm monitoring, and in particular to a multifunctional wind farm intelligent monitoring platform. Background Art

[0002] As the global demand for clean energy continues to grow, wind farms have been widely developed as an important renewable energy power generation facility. However, wind farms are usually composed of a large number of wind turbines distributed over a wide area, and the monitoring and management of their operating status face many challenges.

[0003] Traditional wind farm monitoring methods mainly rely on manual inspections and regular maintenance, which is inefficient and difficult to detect potential faults and abnormal conditions of wind turbines in a timely manner. At the same time, since the operating status of wind turbines is affected by many factors, such as wind speed, wind direction, temperature, humidity, etc., traditional monitoring methods are difficult to conduct comprehensive and accurate analysis and evaluation of the operating status of wind turbines.

[0004] In order to solve the above problems, a multifunctional wind farm intelligent monitoring platform is needed, which can collect the operating status data of wind turbines in real time, conduct in-depth analysis and processing of these data, timely detect abnormal conditions of wind turbines, and improve the operating efficiency and reliability of wind farms. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a multifunctional wind farm intelligent monitoring platform.

[0006] A multifunctional wind farm intelligent monitoring platform, including:

[0007] Data collection terminal, which collects the operating status data of each wind turbine in the wind farm and transmits it to the central processing terminal;

[0008] The operating status data includes, but is not limited to, the status parameters of multiple attributes corresponding to the power generation, fan speed, fan component temperature, and vibration amplitude;

[0009] The central processing terminal is used to process the operating status data of each fan, and then perform abnormal analysis of the fan based on the data processing results, and determine whether the corresponding fan has abnormalities based on the abnormal analysis results. At the same time, according to the fan determined to be abnormal, a corresponding abnormal signal is generated and transmitted to the fan early warning terminal;

[0010] The wind turbine early warning terminal is used to obtain the number of the corresponding wind turbine based on the abnormal signal, and generate corresponding information based on the fan number, which is then transmitted and displayed to the corresponding personnel.

[0011] As a further solution of the present invention: the data processing method in the central processing terminal is as follows:

[0012] Step 1.1, get the status parameter value

[0013] Take the state parameter of a selected attribute as an example;

[0014] Get multiple status parameter values ​​of the attribute in real time within a specified period;

[0015] Step 1.2: Data processing within a time period

[0016] Divide the specified period into several time periods, and then extract the state parameter value with the largest corresponding value of the attribute in each time period;

[0017] At the same time, the average value of all state parameter values ​​corresponding to the attribute in each time period is calculated;

[0018] Step 1.3, calculate the state mean

[0019] Get the average value of all state parameter values ​​corresponding to the attribute in each time period, then calculate the average value, and record the result as the state mean value of the attribute in the specified period;

[0020] The corresponding preset formula in the central processing terminal for this step is as follows:

[0021]

[0022] Where U p is the state mean of the attribute in the specified period, S p，i Indicates the average value of all state parameter values ​​corresponding to the attribute in each time period, n indicates the number of time periods in the specified cycle, and i = 1, 2, ... n, i indicates the number of time periods;

[0023] Step 1.4. Calculate the state standard deviation

[0024] The average value of all state parameter values ​​corresponding to the attribute in each time period is combined with the state mean value to obtain the standard deviation of all state parameter values ​​corresponding to the attribute in each time period, and it is recorded as the state standard deviation;

[0025] The corresponding preset formula in the central processing terminal for this step is as follows:

[0026]

[0027] Where U c is the state standard deviation of the attribute within the specified period, S p，i It represents the average value of all state parameter values ​​corresponding to the attribute in each time period, U pis the state mean of the attribute in the specified period, n represents the number of time periods in the specified period, and i = 1, 2, ... n, i represents the number of time periods;

[0028] Step 1.5. Calculate the state peak value

[0029] Get the state parameter value with the largest corresponding value of the attribute in each time period, then calculate its average value, and record the result as the state peak value of the attribute in the specified period;

[0030] The corresponding preset formula in the central processing terminal for this step is as follows:

[0031]

[0032] Where U max is the state peak value of the attribute within the specified period, S max，i Indicates the state parameter value with the maximum corresponding value of the attribute in each time period, n indicates the number of time periods in the specified period, and i = 1, 2, ... n, i indicates the number of time periods;

[0033] Step 1.6. Calculate the state mean change coefficient

[0034] In the specified period, calculate the absolute value of the difference between the average values ​​of all state parameter values ​​corresponding to the attribute in each time period, and divide it by the state mean value of the attribute, and then record the results corresponding to each adjacent time period as the parameter difference ratio;

[0035] Then, the average value of the corresponding parameter difference ratios of all adjacent time periods is calculated, and the result is marked as the state mean change coefficient;

[0036] The corresponding preset formula in the central processing terminal for this step is as follows:

[0037]

[0038] In the formula, R p is the state mean change coefficient of the attribute within the specified period, S p，i is the average value of all state parameter values ​​corresponding to the attribute in each time period, S p，i-1 To follow the time trend, with S p，i The average value of all state parameter values ​​corresponding to this attribute in the previous adjacent time period;

[0039] Step 1.7. Calculate the state peak variation coefficient

[0040] In the specified period, the absolute value of the difference between the maximum state parameter values ​​corresponding to the attribute in each adjacent time period is calculated, and it is divided by the state peak value of the attribute, and then the result corresponding to each adjacent time period is recorded as the peak value difference ratio;

[0041] Then, the average value of the peak difference ratios corresponding to all adjacent time periods is calculated, and the result is marked as the state peak change coefficient;

[0042] The corresponding preset formula in the central processing terminal for this step is as follows:

[0043]

[0044] In the formula, R max is the state peak change coefficient of the attribute within the specified period, S max，i Indicates the state parameter value with the largest corresponding value of the attribute in each time period, S max，i-1 To follow the time trend, with S p，i The state parameter value with the largest corresponding value of the attribute in the previous adjacent time period;

[0045] Step 1.8, calculate the state peak difference variation coefficient

[0046] The average value of all state parameter values ​​corresponding to the attribute in each time period is subtracted from the state parameter value with the largest value corresponding to the attribute in each time period to obtain the parameter peak-mean difference corresponding to the attribute in each time period;

[0047] In the specified period, calculate the absolute value of the peak-to-mean difference of the corresponding parameters of the attribute in each adjacent time period, and divide it by the state standard deviation of the attribute, and then record the corresponding results of each adjacent time period as the peak-to-mean difference percentage;

[0048] Then, the average value of the corresponding peak-to-average difference ratios of all adjacent time periods is calculated, and the result is marked as the state peak difference variation coefficient;

[0049] The corresponding preset formula in the central processing terminal for this step is as follows:

[0050]

[0051] Where Rc is the state peak difference variation coefficient of the attribute within the specified period, S max，i Indicates the state parameter value with the largest corresponding value of the attribute in each time period, S p，i is the average value of all state parameter values ​​corresponding to the attribute in each time period, S c，i Indicates the peak-to-mean difference of the parameters corresponding to the attribute in each time period, S c，i-1 Expressed as time trend, with S p，iThe peak-to-mean difference of the parameter corresponding to this attribute in the adjacent previous time period.

[0052] As a further solution of the present invention: the fan abnormality analysis method in the central processing terminal is as follows:

[0053] Step 2.1. Calculate the first determination factor

[0054] extracting a state threshold predetermined according to the attribute;

[0055] Then, the state threshold is subtracted from the state mean, divided by the state standard deviation, and the result is multiplied by the corresponding preset weight value;

[0056] At the same time, subtract the state threshold from the state peak value, divide it by the state standard deviation, and multiply the result by the corresponding preset weight value;

[0057] Then, the results are added together to obtain the first determining factor of the state parameter corresponding to the attribute within the specified period;

[0058] The corresponding preset formula in the central processing terminal for this step is as follows:

[0059]

[0060] Where U0 is the first determining factor U0 of the state parameter corresponding to the attribute within the specified period, U p is the state mean of the attribute in the specified period, U max is the state peak value of the attribute within the specified period, U c is the state standard deviation of the attribute within the specified period, U y is the state threshold predetermined according to the attribute, α1 and α2 are the corresponding preset weight values;

[0061] Step 2.2, calculate the second determination factor

[0062] Multiply the state peak value variation coefficient, the state mean value variation coefficient, and the state peak difference variation coefficient by the preset weight values ​​respectively, and add the results thereof to obtain a second determination factor of the state parameter corresponding to the attribute within the specified period;

[0063] The corresponding preset formula in the central processing terminal for this step is as follows:

[0064] R0=R max ×γ1+R p ×γ2+R c ×γ3

[0065] In the formula, R0 is the second determining factor of the state parameter corresponding to the attribute within the specified period, R max is the state peak change coefficient of the attribute within the specified period, R pis the state mean change coefficient of the attribute within the specified period, Rc is the state peak difference change coefficient of the attribute within the specified period, γ1, γ2, and γ3 are the corresponding preset weight values ​​respectively;

[0066] Step 2.3, calculate the fan abnormality judgment value

[0067] Multiply the first determination factor of the state parameter corresponding to each attribute by the corresponding preset weight value, and then add the results to obtain the first abnormal determination value of the corresponding fan;

[0068] At the same time, the second determination factors of the state parameters corresponding to each attribute are multiplied by the corresponding preset weight values, and then the results are added to obtain the second abnormal determination value of the corresponding fan;

[0069] The corresponding preset formula in the central processing terminal for this step is as follows:

[0070]

[0071] Where, P1 is the first abnormality judgment value of the corresponding fan, P2 is the second abnormality judgment value of the corresponding fan, and U0 j and R0 j are the first determining factor and the second determining factor of the state parameters corresponding to each attribute, respectively, wherein j=1, 2, ... m, m represents the number of all attribute items, βj and λj are respectively the weight values ​​preset according to the first determining factor and the second determining factor of each attribute state parameter;

[0072] Step 2.4, fan abnormality determination

[0073] The first abnormality determination value P1 and the second abnormality determination value P2 of the corresponding fan are respectively compared with the preset determination threshold value P1 y and P2 y For comparison:

[0074] If P1>P1 y and P2>P2 y If any one of the following is true, it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated;

[0075] If P1≤P1 y and P2≤P2 y If all of them are true, it is determined that there is no abnormality in the corresponding fan.

[0076] As a further solution of the present invention: wherein the algorithm formula in the central processing terminal is executed by a pre-set arithmetic logic unit in the central processing terminal;

[0077] When a calculation formula is required, the central processing unit will transfer the data to the arithmetic logic unit. The arithmetic logic unit will perform corresponding operations on the corresponding data according to the instructions, and then feed the results back to the central processing unit.

[0078] Compared with the prior art, the present invention has the following beneficial effects:

[0079] In the present invention, the data acquisition terminal can collect the operating status data of each wind turbine in the wind farm, including status parameters of multiple attributes such as power generation power, wind turbine speed, wind turbine component temperature, vibration amplitude, etc., which comprehensively covers the key indicators of wind turbine operation and provides a rich and accurate data basis for subsequent analysis and early warning.

[0080] In the present invention, the central processing terminal adopts a scientific and reasonable data processing method, divides the specified cycle into several time periods, extracts the state parameter value with the largest attribute corresponding value in each time period, and calculates the average value and other operations, which can more carefully grasp the changes in the fan operation status in different time periods.

[0081] The present invention quantifies the characteristics of the fan operating state from different angles by calculating multiple indicators such as the state mean, state standard deviation, state peak value, state mean variation coefficient, state peak variation coefficient and state peak difference variation coefficient, so as to make the abnormal analysis more accurate and reliable.

[0082] In the present invention, the abnormality analysis method of the fan comprehensively considers the relationship between multiple indicators of the state parameters and the predetermined state threshold value, as well as the change trend of the state parameters of different attributes, and obtains the first abnormality judgment value and the second abnormality judgment value of the fan by calculating the first judgment factor and the second judgment factor. It can comprehensively and accurately judge whether the fan has an abnormality, thereby improving the accuracy and reliability of abnormality detection.

[0083] In the present invention, the wind turbine early warning terminal can obtain the number of the corresponding wind turbine according to the abnormal signal, and generate corresponding information in combination with the wind turbine number to display to the corresponding personnel, so that the staff can timely understand the abnormal situation of the wind turbine, quickly take corresponding maintenance and treatment measures, avoid the expansion of the fault, reduce downtime, and improve the operation efficiency and reliability of the wind farm. The timely early warning mechanism helps to reduce the economic losses caused by wind turbine failure, extend the service life of the wind turbine, and ensure the stable operation and power supply of the wind farm.

[0084] The present invention realizes real-time monitoring, data processing and abnormal analysis of the operating status of wind turbines in wind farms, provides a scientific basis and decision-making support for the management of wind farms, and helps to improve the management level and operating efficiency of wind farms; the platform has a high degree of automation and intelligence, reduces manual intervention, reduces management costs, and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 is a system block diagram of the present invention;

[0086] Figure 2 The process diagram of the central processing terminal of the present invention is shown in FIG. Figure 1 ;

[0087] Figure 3 The process diagram of the central processing terminal of the present invention is shown in FIG. Figure 2 . DETAILED DESCRIPTION

[0088] The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0089] Embodiment 1

[0090] See also Figure 1 and Figure 3 As shown, the present invention is a multifunctional wind farm intelligent monitoring platform, comprising:

[0091] Data collection terminal, which collects the operating status data of each wind turbine in the wind farm and transmits it to the central processing terminal;

[0092] The operating status data includes, but is not limited to, the status parameters of multiple attributes corresponding to the power generation, fan speed, fan component temperature, and vibration amplitude;

[0093] In this embodiment, the power generation of the wind turbine is monitored in real time to ensure that it operates within a normal range. Abnormal fluctuations in power output may indicate a failure of a wind turbine component or changes in the external environment that affect power generation efficiency. By comparing the power outputs of different wind turbines, wind turbines with poor performance can be found so that maintenance and repair can be performed in a timely manner.

[0094] Monitor the speed of wind turbine blades and generators in real time. Abnormal speed may be caused by mechanical failure, wind condition changes or control system problems. Too high or too low speed may damage the mechanical structure and electrical system of the wind turbine, so timely adjustment and maintenance are required.

[0095] Real-time monitoring of the temperature of key parts of the fan, such as the generator, gearbox, bearings, etc. Temperature rise may be caused by friction, overload or cooling system failure; high temperature will affect the life and reliability of the equipment, and may even cause equipment damage, so timely cooling measures or maintenance are required;

[0096] Real-time detection of fan vibration, including horizontal and vertical vibration; excessive vibration amplitude may be caused by mechanical imbalance, looseness, wear or bad wind conditions; long-term high vibration will damage the fan structure and affect its stability and safety, so timely fault diagnosis and processing are required;

[0097] Central processing terminal, used for data processing of the operating status data of each fan and analysis of fan abnormalities;

[0098] The data processing and fan abnormality analysis methods are as follows:

[0099] StepA1. Select a state parameter of an attribute as an example;

[0100] Get multiple status parameter values ​​of the attribute in real time within a specified period;

[0101] Step A2: Divide the specified period into several time periods, and then extract the state parameter value with the largest corresponding value of the attribute in each time period, and then mark it as S max，i , i = 1, 2, ... n, indicating the number of time periods in a specified cycle, i indicating the number of time periods, S max，i It is expressed as the maximum state parameter value corresponding to the attribute in the time period;

[0102] StepA3. At the same time, calculate the average value of all state parameter values ​​corresponding to the attribute in each time period, and then mark it as S p，i ;

[0103] StepA4, through Calculate the state mean U of the attribute within the specified period p ;

[0104] StepA5. Pass Calculate the standard deviation U of the state parameter value of the attribute within the specified period c ;

[0105] StepA6. Pass Calculate the state peak value U of the attribute within the specified period max ;

[0106] Step A7: Extract the state threshold U predetermined according to the attribute y ;

[0107] Then through Calculate the first determination factor U0 of the state parameter corresponding to the attribute within the specified period;

[0108] Among them, α1 and α2 are the corresponding preset weight values ​​respectively;

[0109] StepA8: Calculate the first determination factor of the state parameter corresponding to each attribute according to the method from StepA1 to StepA7, and mark it as U0 j , j = 1, 2, ... m, m represents the number of all item attributes;

[0110] StepA9, pass Calculate a first abnormality determination value P1 of the corresponding fan;

[0111] Wherein, βj is a weight value preset according to the first determination factor of each attribute state parameter;

[0112] Step A10, compare the first abnormality judgment value P1 of the corresponding fan with the preset judgment threshold value P1 y For comparison:

[0113] If P1>P1 y , it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated;

[0114] If P1≤P1 y , it is determined that there is no abnormality in the corresponding fan;

[0115] The wind turbine early warning terminal is used to obtain the number of the corresponding wind turbine based on the abnormal signal, and generate corresponding information based on the fan number, which is then transmitted and displayed to the corresponding personnel.

[0116] In terms of data collection, the data collection terminal of this embodiment comprehensively collects the operating status data of each wind turbine in the wind farm, provides rich and accurate raw data for subsequent analysis and early warning, and ensures comprehensive control of the operating status of the wind turbine; divides the specified period into several time periods, extracts the state parameter value with the largest attribute corresponding value in each time period, and calculates the average value. This method can carefully show the changing characteristics of the wind turbine operating status in different time intervals. By calculating indicators such as the state mean, standard deviation, and state peak, the operating status characteristics of the wind turbine are quantified from multiple dimensions. At the same time, the first determination factor is calculated based on the state threshold predetermined by the attribute, and the degree of deviation of the wind turbine operating status from the normal range is comprehensively considered, which greatly improves the accuracy of abnormal detection and provides a reliable basis for timely discovery of potential problems; the wind turbine early warning terminal can quickly obtain the number of the corresponding wind turbine according to the abnormal signal, and generate information in combination with the number to display to relevant personnel. This enables the staff to understand the abnormal situation of the wind turbine at the first time, so as to take maintenance and treatment measures in time, effectively avoid the expansion of faults, reduce the downtime of wind turbines, and greatly improve the operating efficiency of wind farms.

[0117] Embodiment 2

[0118] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from the first embodiment only in that in the present embodiment, the data processing and fan abnormality analysis method are also as follows:

[0119] Step B1, select a state parameter of an attribute as an example;

[0120] Get multiple status parameter values ​​of the attribute in real time within a specified period;

[0121] Step B2: Divide the specified period into several time periods, and then extract the state parameter value with the largest corresponding value of the attribute in each time period, and then mark it as S max，i , i = 1, 2, ... n, indicating the number of time periods in a specified cycle, i indicating the number of time periods, S max，i It is expressed as the maximum state parameter value corresponding to the attribute in the time period;

[0122] Step B3. At the same time, calculate the average value of all state parameter values ​​corresponding to the attribute in each time period, and then mark it as S p，i ;

[0123] Step B4, pass Calculate the state mean change coefficient R of the attribute within the specified period p ;

[0124] Step B5, pass Calculate the state peak change coefficient R of the attribute within the specified period max ;

[0125] Step B6, pass Calculate the state peak difference variation coefficient of the attribute within the specified period;

[0126] Step B7, through R0 = R max ×γ1+R p ×γ2+R c ×γ3, calculate the second determination factor R0 of the attribute within the specified period;

[0127] Among them, γ1, γ2, and γ3 are the corresponding preset weight values;

[0128] Step B8: Calculate the second determination factor of the state parameter corresponding to each attribute according to the method from Step B1 to Step B7, and mark it as R0 j , j = 1, 2, ... m, m represents the number of all item attributes;

[0129] Step B9, pass Calculate a second abnormality determination value P2 of the corresponding fan;

[0130] Wherein, λj is a weight value preset according to the second determination factor of each attribute state parameter;

[0131] Step B10: Compare the first abnormality determination value P1 and the second abnormality determination value P2 of the corresponding fan with the preset determination threshold value P1 y and P2 y For comparison:

[0132] If P2>P2 y , it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated;

[0133] If P2≤P2 y , it is determined that there is no abnormality in the corresponding fan.

[0134] Compared with the first embodiment, the present embodiment adds the calculation of the state mean variation coefficient, the state peak variation coefficient and the state peak difference variation coefficient, which can more comprehensively analyze the variation trend of the wind turbine operating state and improve the accuracy of abnormality detection; the wind turbine abnormality is judged by calculating the second determination factor, and multiple indicators of the wind turbine operating state are comprehensively considered from different angles, which provides more reference basis for the wind turbine abnormality analysis and helps to more accurately judge the operating status of the wind turbine; the second abnormal determination value is compared with the preset threshold value to judge whether the wind turbine has abnormality, which provides another method for judging wind turbine abnormality for wind farm managers and increases the reliability of abnormality detection.

[0135] Embodiment 3

[0136] As the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is that:

[0137] In this embodiment:

[0138] If P1>P1 y and P2>P2 y If any one of the following is true, it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated;

[0139] If P≤P1 y and P≤P1 y If all of them are true, it is determined that there is no abnormality in the corresponding fan.

[0140] This embodiment combines the solutions of embodiment one and embodiment two, and comprehensively considers the first abnormal judgment value and the second abnormal judgment value. As long as any one of them is established, it is determined that the wind turbine is abnormal, which improves the sensitivity of abnormality detection and can discover potential problems of the wind turbine more timely; the judgment of wind turbine abnormalities is more comprehensive and accurate, avoiding the misjudgment or missed judgment that may occur in a single judgment method, and providing a more reliable guarantee for the stable operation of the wind farm; the generated abnormal signal can notify relevant personnel in time, so that they can quickly take corresponding maintenance and processing measures to reduce the impact of faults on the operation of the wind farm.

[0141] Embodiment 4

[0142] As the fourth embodiment of the present invention, when the present application is specifically implemented, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second and third embodiments.

[0143] This embodiment combines the solutions of Embodiment 1, Embodiment 2 and Embodiment 3 for implementation, giving full play to the advantages of each solution, and realizing all-round and multi-angle monitoring and analysis of the operating status of wind turbines in wind farms; further improving the performance and reliability of the wind farm smart monitoring platform, and providing more powerful technical support for the efficient operation and management of wind farms; being able to adapt to different wind farm operating environments and requirements, and having broader application prospects and promotion value.

[0144] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0145] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A multifunctional wind farm intelligent monitoring platform, characterized in that: include: Data collection terminal, which collects the operating status data of each wind turbine in the wind farm; The central processing terminal is used to process the operating status data of each fan, and then perform fan abnormality analysis based on the data processing results, and determine whether the corresponding fan has an abnormality based on the abnormality analysis results. At the same time, according to the fan determined to be abnormal, a corresponding abnormal signal is generated.

2. A multifunctional wind farm intelligent monitoring platform according to claim 1, characterized in that: The data processing method in the central processing terminal includes the following steps: Step 1.1, select a state parameter of an attribute, and obtain multiple state parameter values ​​of the attribute in real time within a specified period; Step 1.2, divide the specified period into several time periods, and then extract the state parameter value with the largest corresponding value of the attribute in each time period; At the same time, the average value of all state parameter values ​​corresponding to the attribute in each time period is calculated; Step 1.3, obtain the average value of all state parameter values ​​corresponding to the attribute in each time period, and then calculate the average value, and record the result as the state mean value of the attribute in the specified period; Step 1.4, combine the average value of all state parameter values ​​corresponding to the attribute in each time period with the state mean, calculate the standard deviation of all state parameter values ​​corresponding to the attribute in each time period, and record it as the state standard deviation; Step 1.

5. Obtain the state parameter value with the maximum corresponding value of the attribute in each time period, then calculate its average value, and record the result as the state peak value of the attribute in the specified period.

3. A multifunctional wind farm intelligent monitoring platform according to claim 2, characterized in that: The fan abnormality analysis method in the central processing terminal is as follows: extracting a state threshold predetermined according to the attribute; Then, the state threshold is subtracted from the state mean, divided by the state standard deviation, and the result is multiplied by the corresponding preset weight value; At the same time, subtract the state threshold from the state peak value, divide it by the state standard deviation, and multiply the result by the corresponding preset weight value; Then, the results are added together to obtain the first determining factor of the state parameter corresponding to the attribute within the specified period; Then, the first determination factors of the state parameters corresponding to each attribute are multiplied by the corresponding preset weight values, and then the results are added to obtain the first abnormal determination value of the corresponding fan; Finally, the first abnormality judgment value of the corresponding fan is compared with the corresponding preset judgment threshold. When the first abnormality judgment value exceeds the preset judgment threshold, it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated; otherwise, it is not.

4. A multifunctional wind farm intelligent monitoring platform according to claim 3, characterized in that: The data processing method in the central processing terminal also includes the following steps: Step 1.

6. In the specified period, calculate the absolute value of the difference between the average values ​​of all state parameter values ​​corresponding to the attribute in each time period, and divide it by the state mean value of the attribute, and then record the results corresponding to each adjacent time period as the parameter difference ratio; Then, the average value of the corresponding parameter difference ratios of all adjacent time periods is calculated, and the result is marked as the state mean change coefficient; Step 1.

7. In the specified period, calculate the absolute value of the difference between the maximum state parameter values ​​corresponding to the attribute in each adjacent time period, and divide it by the state peak value of the attribute, and then record the results corresponding to each adjacent time period as the peak value difference ratio; Then, the average value of the peak difference ratios corresponding to all adjacent time periods is calculated, and the result is marked as the state peak change coefficient; Step 1.8, subtract the state parameter value with the largest value corresponding to the attribute in each time period from the average value of all state parameter values ​​corresponding to the attribute in each time period, and obtain the peak-to-mean difference of the parameter corresponding to the attribute in each time period; In the specified period, calculate the absolute value of the peak-to-mean difference of the corresponding parameters of the attribute in each adjacent time period, and divide it by the state standard deviation of the attribute, and then record the corresponding results of each adjacent time period as the peak-to-mean difference percentage; Then, the average value of the corresponding peak-to-average difference ratios of all adjacent time periods is calculated, and the result is marked as the state peak difference variation coefficient.

5. A multifunctional wind farm intelligent monitoring platform according to claim 4, characterized in that: The fan abnormality analysis method in the central processing terminal is also as follows: First, the state peak value variation coefficient, the state mean value variation coefficient, and the state peak difference variation coefficient are multiplied by the preset weight values ​​respectively, and the results are added to obtain the second determination factor of the state parameter corresponding to the attribute within the specified period; Then, the second determination factors of the state parameters corresponding to each attribute are multiplied by the corresponding preset weight values, and then the results are added to obtain the second abnormal determination value of the corresponding fan; Finally, the second abnormality judgment value of the corresponding fan is compared with the corresponding preset judgment threshold. When the second abnormality judgment value exceeds the preset judgment threshold, it is determined that the corresponding fan is abnormal and a corresponding abnormal signal is generated; otherwise, it is not.

6. A multifunctional wind farm intelligent monitoring platform according to claim 5, characterized in that: in, When both the first abnormality determination value and the second abnormality determination value do not exceed the corresponding preset determination threshold value, it is determined that there is no abnormality in the corresponding fan, and no corresponding abnormal signal is generated; otherwise, it is not.

7. The multifunctional wind farm intelligent monitoring platform according to claim 1 is characterized in that: The operating status data includes, but is not limited to, status parameters of multiple attributes corresponding to power generation, fan speed, fan component temperature, and vibration amplitude.

8. The multifunctional wind farm intelligent monitoring platform according to claim 1 is characterized in that: In the central processing terminal, corresponding algorithm formulas are preset according to the steps of data processing and fan abnormality analysis.

9. The multifunctional wind farm intelligent monitoring platform according to claim 1, characterized in that: It also includes a wind turbine early warning terminal; The wind turbine warning terminal is used to obtain the number of the corresponding wind turbine according to the abnormal signal, and generate corresponding information in combination with the wind turbine number, which is then transmitted and displayed to the corresponding personnel.

Images