An intelligent monitoring and fault diagnosis system for new energy wind farms

Abstract

The present invention discloses an intelligent monitoring and fault diagnosis system for a new energy wind farm, including a data monitoring module, an acquisition processing module, an acquisition analysis module, a deep diagnosis module and a visualization module; it relates to the field of new energy technology. The present invention can timely discover and handle abnormal conditions of equipment through real-time monitoring and automatic fault diagnosis, avoid downtime caused by equipment failure, and thus improve the operation efficiency of the wind farm. At the same time, it can also avoid the safety risks that may be caused by equipment failure, improve the safety of the wind farm, and match the real-time collected data with the model to determine whether the operating status of the equipment is normal. If the equipment is operating abnormally, the system will generate an abnormal signal. According to the abnormal signal, the system will perform a deep diagnosis on the abnormal equipment, find out the specific cause of the equipment abnormality, and generate a fault signal. This system has important practical value and economic benefits for the operation and maintenance of new energy wind farms.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to an intelligent monitoring and fault diagnosis system for a new energy wind farm. Background Art

[0002] With the continuous development of new energy technologies, wind power, as a clean and renewable energy source, has received more and more attention for its development and utilization. New energy wind farms are the main places for wind power generation, and their operating status directly affects the power generation efficiency and economic benefits of wind power. However, due to the complexity of wind farm equipment and the harsh operating environment, equipment failures occur from time to time, which requires real-time monitoring and fault diagnosis of wind farms to ensure the normal operation of wind farms;

[0003] At present, the traditional wind farm monitoring system mainly relies on manual inspection and regular maintenance, which is not only inefficient, but also difficult to timely discover and deal with equipment failures. In addition, due to the large number of wind farm equipment and the strong correlation between equipment, once a failure occurs, it often affects the operation of the entire wind farm and may even cause safety accidents. Therefore, how to achieve real-time monitoring and fault diagnosis of wind farms has become an important issue in current wind farm management.

[0004] Based on this, the present invention provides an intelligent monitoring and fault diagnosis system for a new energy wind farm. The system can realize comprehensive and real-time monitoring of the wind farm, and can automatically perform fault diagnosis and early warning. It has important practical significance for improving the operating efficiency and safety of the new energy wind farm and reducing operation and maintenance costs. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent monitoring and fault diagnosis system for a new energy wind farm, which solves the technical problems raised in the background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An intelligent monitoring and fault diagnosis system for a new energy wind farm, comprising:

[0008] The data monitoring module is used to collect information parameters corresponding to the new energy wind farm in real time through sensors installed on key equipment of the new energy wind farm;

[0009] The acquisition processing module is used to obtain information parameters corresponding to different time nodes collected in multiple standard cycles of the new energy wind farm under normal operation, mark and organize the information parameters, add specific codes for each cycle and time node, and then filter and organize the information parameters to obtain the marked mother code and marked child code attached to the information parameters;

[0010] The acquisition and analysis module is used to obtain the corresponding information parameters of the same tag code from the extracted information parameters, then select the maximum and minimum values ​​of each parameter, construct the parameter range, and establish a fault analysis model, and then obtain the information parameters corresponding to the real-time acquisition of the new energy wind farm, and import the real-time data into the model. If it is found that any parameter exceeds the corresponding parameter range, an abnormal signal is generated;

[0011] The deep diagnosis module is used to extract the information parameters corresponding to the abnormal signal and the parameters of the previous and next time nodes according to the abnormal signal, and compare them with the parameter interval. Then, the matching results are arranged in chronological order, and the pre-trained rules are applied for classification and judgment. Then, the abnormal parameter ratio is calculated and compared with the preset value. If it exceeds the threshold, a fault signal is generated;

[0012] The visualization module is used to display the monitoring and diagnosis results to operation and maintenance personnel in a graphical manner.

[0013] As a further solution of the present invention: wherein the information parameters include vibration parameters, temperature parameters, power parameters, current and voltage parameters;

[0014] Vibration parameters refer to the vibration conditions of key equipment in new energy wind farms;

[0015] Temperature parameters refer to the temperature values ​​of key equipment in new energy wind farms;

[0016] The power parameter refers to the power generation value of the new energy wind farm;

[0017] Current and voltage parameters refer to the current and voltage values ​​of key equipment in new energy wind farms.

[0018] As a further solution of the present invention: the specific method of obtaining the processing module is as follows:

[0019] SA1. Obtain information parameters corresponding to different time nodes of the new energy wind farm in multiple standard cycles when the new energy wind farm is operating normally;

[0020] The number of the multiple standard periods and the multiple time nodes are preset values, and each standard period has a corresponding time node;

[0021] SA2. Mark and organize the information parameters. The marking and organizing methods are as follows:

[0022] Add different marking mother codes to each standard period according to the preset period marking rules;

[0023] At the same time, different marking sub-codes are added to each time node according to the preset node marking rules;

[0024] Then, the marker mother code and the marker child code are combined and attached to the information parameters, and the vibration parameters, temperature parameters, power parameters, current and voltage parameters in the corresponding information parameters at the same time node in the same standard period have the same marker mother code and marker child code attached to them;

[0025] SA3. Filter and sort the information parameters, and obtain the marker parent code and marker child code attached to the information parameters according to the filtering and sorting results.

[0026] As a further solution of the present invention: in step SA3, the screening and sorting method is as follows:

[0027] SA31, taking vibration parameters as an example: first, obtain the vibration parameters at the same time node within multiple standard cycles;

[0028] SA32, and calculate the average value of all vibration parameters at the same time node in multiple standard cycles and mark it as FP;

[0029] SA33, simultaneously marking the vibration parameters of each time node in multiple standard cycles as FS i, i = 1, 2, ... n, n represents the number of the same standard cycle;

[0030] SA34, then obtain the absolute value of the difference of each vibration parameter FC i through FCi=|FSi-FP|;

[0031] SA35, then pass Calculate the deviation value L0 of the absolute value of the difference of each vibration parameter, where FCp represents the average value of the absolute value of the difference of the vibration parameters used to calculate L0;

[0032] SA36, then compare the deviation value L0 with the preset deviation threshold LY:

[0033] If L0 is greater than LY, it means that the degree of dispersion between the vibration parameters is large. Then calculate the value of each |FCi-FCp| and delete the FC i with the largest corresponding value in order from large to small. Then calculate the variance value of the FC i that has not been deleted until L0 is less than or equal to LY;

[0034] Then extract all FSi corresponding to FC i that have not been deleted, as well as the marked mother code and marked child code attached to FSi;

[0035] SA37. Finally, according to the method of steps SA31-SA37, the temperature parameters, power parameters, current and voltage parameters are screened and sorted, and the marking mother code and marking child code attached to the corresponding temperature parameters, power parameters, current and voltage parameters are extracted.

[0036] As a further solution of the present invention: the specific method of obtaining the analysis module is as follows:

[0037] SD1. First, on all the extracted vibration parameters, temperature parameters, power parameters, current and voltage parameters containing the marker mother code and the marker child code, obtain the vibration parameters, temperature parameters, power parameters, current and voltage parameters of the same marker mother code and the marker child code;

[0038] SD2. Then, from the vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking mother code and marking child code, obtain multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking child code, wherein the marking child codes of the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters are the same, and the marking mother codes are different;

[0039] SD3. Then, from among the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters encoded in the same marker, the maximum and minimum parameters of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters are selected, and the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval are formed using the maximum and minimum parameters.

[0040] SD3. Build a fault analysis model based on vibration range, temperature parameter range, power parameter range, and current and voltage parameter range;

[0041] SD4, import the information parameters corresponding to the new energy wind farm collected in real time into the pre-trained fault analysis model after construction;

[0042] The fault analysis model extracts vibration parameters, temperature parameters, power parameters, and current and voltage parameters from the information parameters collected in real time, and matches them with the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval respectively:

[0043] If at least one of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters is not within the vibration range, temperature parameter range, power parameter range, and current and voltage parameter range, it indicates that the operation of the new energy wind farm is abnormal, and an abnormal signal is subsequently generated.

[0044] As a further solution of the present invention: in step SD4, if the vibration parameters, temperature parameters, power parameters, current and voltage parameters are all within the vibration range, temperature parameter range, power parameter range, and current and voltage parameter range, it indicates that the new energy wind farm is operating normally.

[0045] As a further solution of the present invention: the specific method of the deep diagnosis module is as follows:

[0046] SF1. According to the abnormal signal, obtain the information parameter that is not in the corresponding parameter interval. Taking the vibration parameter as an example, if the vibration parameter is not in the vibration interval, obtain the vibration parameter of the previous t1 time nodes of the current vibration parameter, and obtain the vibration parameter of the next t2 time nodes of the current vibration parameter;

[0047] SF2, then matching the vibration parameters corresponding to the first t1 time nodes and the last t2 time nodes corresponding to the current vibration parameters with the vibration intervals corresponding to the corresponding time nodes, and obtaining corresponding matching results;

[0048] SF3, then according to the order of the time nodes, the matching results of the t1 time nodes, the next t2 time nodes and the current vibration parameters are arranged in sequence;

[0049] SF4. Combine the arrangement order corresponding to the matching results with the pre-trained abnormal sorting rules for classification and judgment, and obtain the corresponding rule 1 or rule 2:

[0050] SF5. In the matching results, obtain the number t0 of the corresponding vibration parameters that are not in the corresponding parameter interval;

[0051] SF6, then through Calculate the abnormal proportion of the corresponding information parameters, where 1 refers to the value assigned to the current vibration parameter corresponding to the abnormal signal;

[0052] SF7, then compare Bt with the preset value By:

[0053] If Bt is greater than By, it means that the key equipment corresponding to the vibration parameter is operating abnormally and a fault signal is generated.

[0054] As a further solution of the present invention: in step SF4, the pre-trained abnormal sorting rules are as follows:

[0055] Rule 1: In the arrangement order corresponding to the matching results, if there are r1 or more consecutive matching results, the vibration parameters are not in the vibration interval;

[0056] Rule 2: In the arrangement order corresponding to the matching results, the number of consecutive adjacent matching results whose vibration parameters are not in the vibration interval is less than r1.

[0057] As a further solution of the present invention: in step SF7, the value of By is two groups, one group is preset according to rule 1 of the pre-trained abnormal sorting rule, and the other group is preset according to rule 2 of the pre-trained abnormal sorting rule;

[0058] Among them, if Bt is less than or equal to By, it means that the key equipment corresponding to the vibration parameter operates normally and does not generate a fault signal.

[0059] Beneficial effects of the present invention:

[0060] The present invention can effectively realize real-time monitoring and fault diagnosis of the operating status of the new energy wind farm by real-time collection, processing and analysis of information parameters, and classification judgment and abnormal proportion calculation in combination with pre-training rules;

[0061] Real-time and accuracy: The present invention collects information parameters in real time through sensors installed on key equipment, ensuring the real-time and accuracy of data. At the same time, by marking and sorting the information parameters, the information parameters of each period and time node can be accurately obtained;

[0062] Fault early warning: By constructing a fault analysis model, the present invention can timely detect abnormal conditions in operation and generate abnormal signals, thereby realizing fault early warning, avoiding or reducing downtime losses caused by equipment failures. At the same time, it can also avoid the safety risks that may be caused by equipment failures and improve the safety of wind farms;

[0063] Fault location: The deep diagnosis module of the present invention can extract the information parameters corresponding to the abnormal signal and the parameters of the time nodes before and after the abnormal signal, and compare them with the parameter interval to accurately locate the location where the fault occurs;

[0064] Intelligent judgment: The present invention can realize intelligent fault judgment by applying pre-training rules for classification judgment, calculating the proportion of abnormal parameters, and comparing them with preset values;

[0065] Easy to understand and operate: The present invention uses a visualization module to display monitoring and diagnostic results to operation and maintenance personnel in a graphical manner, making the use of the system more intuitive and simple;

[0066] Improve operation and maintenance efficiency: The present invention realizes real-time monitoring and fault diagnosis of the operation status of the new energy wind farm in an automated manner, greatly improving the work efficiency of the operation and maintenance personnel and reducing the operation and maintenance costs;

[0067] In summary, the intelligent monitoring and fault diagnosis system of new energy wind farms has important practical value and economic benefits for the operation and maintenance of new energy wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Figure 1 It is a system block diagram of an intelligent monitoring and fault diagnosis system for a new energy wind farm of the present invention.

[0070] Figure 2 It is a flow chart of an acquisition and analysis module of an intelligent monitoring and fault diagnosis system for a new energy wind farm of the present invention. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0072] Embodiment 1

[0073] See also Figure 1 and Figure 2 As shown, the present invention is an intelligent monitoring and fault diagnosis system for a new energy wind farm, comprising:

[0074] The data monitoring module is used to collect information parameters corresponding to the new energy wind farm in real time through sensors installed on key equipment of the new energy wind farm, where the information parameters include vibration parameters, temperature parameters, power parameters, current and voltage parameters;

[0075] Vibration parameters refer to the vibration conditions of key equipment in new energy wind farms;

[0076] Temperature parameters refer to the temperature values ​​of key equipment in new energy wind farms;

[0077] The power parameter refers to the power generation value of the new energy wind farm;

[0078] Current and voltage parameters refer to the current and voltage values ​​of key equipment in new energy wind farms;

[0079] This embodiment sets up a data monitoring module, which is responsible for collecting information parameters about the wind farm from sensors on various key devices in real time and performing preliminary processing.

[0080] The acquisition processing module is used to obtain the new energy wind farm in normal operation. The data monitoring module collects the corresponding information parameters, then pre-processes the information parameters, and obtains the corresponding information intervals, and then summarizes the information intervals to generate a monitoring comparison summary table;

[0081] The preprocessing method is as follows:

[0082] SA1. Obtain information parameters corresponding to different time nodes of the new energy wind farm in multiple standard cycles when the new energy wind farm is operating normally;

[0083] The number of the multiple standard periods and the multiple time nodes are preset values, and each standard period has a corresponding time node;

[0084] SA2. Mark and organize the information parameters. The marking and organizing methods are as follows:

[0085] Add different marking mother codes to each standard period according to the preset period marking rules;

[0086] At the same time, different marking sub-codes are added to each time node according to the preset node marking rules;

[0087] Then, the marker mother code and the marker child code are combined and attached to the information parameters, and the vibration parameters, temperature parameters, power parameters, current and voltage parameters in the corresponding information parameters at the same time node in the same standard period have the same marker mother code and marker child code attached to them;

[0088] SA3. Filter and sort the information parameters. The filtering and sorting methods are as follows:

[0089] SA31, taking vibration parameters as an example: within multiple standard periods, obtain the vibration parameters at the same time node;

[0090] SA32, and calculate the average value of all vibration parameters at the same time node in multiple standard cycles and mark it as FP;

[0091] SA33, marking the vibration parameters of each time node in multiple standard cycles as FSi, i = 1, 2, ... n, n represents the number of the same standard cycle;

[0092] SA34, obtain the absolute value FCi of the difference of each vibration parameter through FCi=|FSi-FP|;

[0093] SA35, Pass Calculate the deviation value L0 of the absolute value of the difference of each vibration parameter, where FCp represents the average value of the absolute value of the difference of the vibration parameters used to calculate L0;

[0094] SA36. Compare the deviation value L0 with the preset deviation threshold LY:

[0095] If L0 is greater than LY, it means that the degree of dispersion between the vibration parameters is large. Then calculate the value of each |FCi-FCp| and delete the FC i with the largest corresponding value in order from large to small. Then calculate the variance value of the FC i that has not been deleted until L0 is less than or equal to LY;

[0096] Then extract all FSi corresponding to FC i that have not been deleted, as well as the marked mother code and marked child code attached to FSi;

[0097] SA37. According to steps SA31-SA37, the temperature parameters, power parameters, current and voltage parameters are screened and sorted, and the marking mother code and marking child code attached to the corresponding temperature parameters, power parameters, current and voltage parameters are extracted;

[0098] This embodiment sets an acquisition processing module to further process the information parameters under normal conditions and generate a monitoring comparison summary table, which includes acquiring information parameters at different time nodes of multiple standard cycles, marking and sorting them, and screening and sorting out useful information parameters.

[0099] The acquisition and analysis module is used to acquire the information parameters corresponding to the new energy wind farm in real time, and perform diagnostic analysis in combination with the processing results of the acquisition and processing module. The diagnostic analysis method is as follows:

[0100] SD1, from all the extracted vibration parameters, temperature parameters, power parameters, current and voltage parameters containing the marker mother code and the marker child code, obtain the vibration parameters, temperature parameters, power parameters, current and voltage parameters of the same marker mother code and the marker child code;

[0101] SD2. From the vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking mother code and marking child code, obtain multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking child code, wherein the marking child codes of the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters are the same, and the marking mother codes are different;

[0102] SD3. Among the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters encoded in the same marker, the maximum and minimum parameters of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters are selected, and the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval are formed using the maximum and minimum parameters.

[0103] SD3. Build a fault analysis model based on vibration range, temperature parameter range, power parameter range, and current and voltage parameter range;

[0104] SD4, import the information parameters corresponding to the new energy wind farm collected in real time into the pre-trained fault analysis model after construction;

[0105] The fault analysis model extracts vibration parameters, temperature parameters, power parameters, and current and voltage parameters from the information parameters collected in real time, and matches them with the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval respectively:

[0106] If the vibration parameters, temperature parameters, power parameters, current and voltage parameters are all within the vibration range, temperature parameter range, power parameter range, and current and voltage parameter range, it means that the new energy wind farm is operating normally;

[0107] If at least one of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters is not within the vibration range, temperature parameter range, power parameter range, and current and voltage parameter range, it indicates that the operation of the new energy wind farm is abnormal, and an abnormal signal is subsequently generated;

[0108] This embodiment sets up an acquisition and analysis module: combines the results of the processing module to analyze the information parameters of the new energy wind farm in real time for fault diagnosis and analysis. This involves building a fault analysis model and matching the real-time data with it to determine whether there is an abnormality.

[0109] The deep diagnosis module is used to perform deep diagnosis on the new energy wind farm according to abnormal signals. The specific methods are as follows:

[0110] SF1. According to the abnormal signal, obtain the information parameter that is not in the corresponding parameter interval. Taking the vibration parameter as an example, if the vibration parameter is not in the vibration interval, obtain the vibration parameter of the previous t1 time nodes of the current vibration parameter, and obtain the vibration parameter of the next t2 time nodes of the current vibration parameter;

[0111] SF2, matching the vibration parameters corresponding to the first t1 time nodes and the last t2 time nodes corresponding to the current vibration parameters with the vibration intervals corresponding to the corresponding time nodes, and obtaining corresponding matching results;

[0112] SF3. In the matching results, obtain the number t0 of the corresponding vibration parameters that are not in the corresponding parameter interval;

[0113] SF4, through Calculate the abnormal proportion of the corresponding information parameters, where 1 refers to the value assigned to the current vibration parameter corresponding to the abnormal signal;

[0114] SF5, then compare Bt with the preset value By:

[0115] If Bt is greater than By, it means that the key equipment corresponding to the vibration parameter is operating abnormally and a fault signal is generated;

[0116] If Bt is less than or equal to By, it means that the key equipment corresponding to the vibration parameter is operating normally and no fault signal is generated;

[0117] This embodiment sets up a deep diagnosis module: after detecting an abnormal signal, a deeper diagnosis analysis is performed to determine whether a fault actually exists and the nature of the fault.

[0118] Embodiment 2

[0119] 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 that of the first embodiment only in that:

[0120] When the deep diagnosis module performs deep diagnosis on the new energy wind farm according to the abnormal signal, it also arranges the matching results of the t1 time node and the next t2 time node and the current vibration parameter in sequence according to the sequence of the time nodes;

[0121] Then, the arrangement order corresponding to the matching results is combined with the pre-trained abnormal sorting rules for classification and judgment, and the corresponding rule one or rule two is obtained:

[0122] Among them, the pre-trained exception sorting rules are as follows:

[0123] Rule 1: In the arrangement order corresponding to the matching results, if there are r1 or more consecutive matching results, the vibration parameters are not in the vibration interval;

[0124] Rule 2: In the order of matching results, the number of consecutive matching results whose vibration parameters are not in the vibration interval is less than r1;

[0125] In this example:

[0126] If the value of t1 is 5, the value of t2 is 4, and the matching results of t1 are in, not in, in, not in, and not in, respectively, the matching results of t2 are not in, in, in, and not in, respectively;

[0127] The results are arranged in order: 1) in, 2) not in, 3) in, 4) not in, 5) not in, 6) not in, 7) not in, 8) in, 9) in, 10) not in, where 5) means the current vibration parameter is not in the vibration range;

[0128] When the value of r1 is 4, the classification result corresponding to the arrangement order is rule 1;

[0129] When the value of r1 is 5, the classification result corresponding to the arrangement order is rule 2;

[0130] In this embodiment, there are two groups of By values, one group is preset according to rule 1 of the pre-trained abnormal sorting rule, and the other group is preset according to rule 2 of the pre-trained abnormal sorting rule;

[0131] Embodiment 3

[0132] As the third embodiment of the present invention, when the present application is 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 in this embodiment:

[0133] It also includes a visualization module, which is used to display the monitoring and diagnosis results in a graphical way to facilitate the understanding and operation of operation and maintenance personnel.

[0134] This embodiment sets a visualization module to display the monitoring and diagnosis results in a graphical manner, which is convenient for operation and maintenance personnel to understand and operate.

[0135] Embodiment 4

[0136] 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.

[0137] Through the collaborative work of multiple modules, this embodiment can monitor the operating status of the wind farm in an all-round and real-time manner, can automatically perform fault diagnosis and early warning, reduce reliance on manual inspection, and can timely discover and handle faults, which helps to improve the operating efficiency and safety of the wind farm, thereby achieving effective monitoring and fault diagnosis of the wind farm.

[0138] 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.

[0139] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent monitoring and fault diagnosis system for a new energy wind farm, characterized in that: include: The data monitoring module is used to collect information parameters corresponding to the new energy wind farm in real time through sensors installed on key equipment of the new energy wind farm; The acquisition processing module is used to obtain information parameters corresponding to different time nodes collected in multiple standard cycles of the new energy wind farm under normal operation, mark and organize the information parameters, add specific codes for each cycle and time node, and then filter and organize the information parameters to obtain the marked mother code and marked child code attached to the information parameters; Among them, the information parameters include vibration parameters, temperature parameters, power parameters, current and voltage parameters; The specific method of obtaining the processing module is as follows: SA1. Obtain information parameters corresponding to different time nodes of the new energy wind farm in multiple standard cycles when the new energy wind farm is operating normally; The number of the multiple standard periods and the multiple time nodes are preset values, and each standard period has a corresponding time node; SA2. Mark and organize the information parameters. The marking and organizing methods are as follows: Add different marking mother codes to each standard period according to the preset period marking rules; At the same time, different marking sub-codes are added to each time node according to the preset node marking rules; Then, the marker mother code and the marker child code are combined and attached to the information parameters, and the vibration parameters, temperature parameters, power parameters, current and voltage parameters in the corresponding information parameters at the same time node in the same standard period have the same marker mother code and marker child code attached to them; SA3. Screen and sort the information parameters, and obtain the marker mother code and marker child code attached to the information parameters according to the screening and sorting results; The filtering and sorting methods are as follows: SA31. Select vibration parameters for screening and sorting: first, obtain vibration parameters at the same time node within multiple standard cycles; SA32, and calculate the average value of all vibration parameters at the same time node in multiple standard cycles and mark it as FP; SA33, simultaneously marking the vibration parameters of each time node in multiple standard cycles as FSi, i = 1, 2, ... n, n represents the number of the same standard cycle; SA34, obtain the absolute value FCi of the difference of each vibration parameter through FCi=|FSi-FP|; SA35, Pass Calculate the deviation value L0 of the absolute value of the difference of each vibration parameter, where FCp represents the average value of the absolute value of the difference of the vibration parameters used to calculate L0; SA36. Compare the deviation value L0 with the preset deviation threshold LY: If L0 is greater than LY, it means that the degree of dispersion between the vibration parameters is large. Then calculate the value of each |FCi-FCp| and delete the FCi with the largest corresponding value in order from large to small. Then calculate the variance value of the FCi that has not been deleted until L0 is less than or equal to LY. Then extract the FSi corresponding to all the FCi that have not been deleted, as well as the marked mother code and marked child code attached to FSi; SA37. According to steps SA31-SA37, the temperature parameters, power parameters, current and voltage parameters are screened and sorted, and the marking mother code and marking child code attached to the corresponding temperature parameters, power parameters, current and voltage parameters are extracted; The acquisition and analysis module is used to obtain the corresponding information parameters of the same tag code from the extracted information parameters, then select the maximum and minimum values ​​of each parameter, construct the parameter range, and establish a fault analysis model, and then obtain the information parameters corresponding to the real-time acquisition of the new energy wind farm, and import the real-time data into the model. If it is found that any parameter exceeds the corresponding parameter range, an abnormal signal is generated; The deep diagnosis module is used to extract the information parameters corresponding to the abnormal signal and the parameters of the previous and next time nodes according to the abnormal signal, and compare them with the parameter interval. Then, the matching results are arranged in chronological order, and the pre-trained rules are applied for classification and judgment. The proportion of abnormal parameters is calculated and compared with the preset value. If it exceeds the threshold, a fault signal is generated.

2. According to claim 1, a new energy wind farm intelligent monitoring and fault diagnosis system is characterized in that: in, Vibration parameters refer to the vibration conditions of key equipment in new energy wind farms; Temperature parameters refer to the temperature values ​​of key equipment in new energy wind farms; The power parameter refers to the power generation value of the new energy wind farm; Current and voltage parameters refer to the current and voltage values ​​of key equipment in new energy wind farms.

3. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 1 is characterized in that: The specific method of obtaining the analysis module is as follows: SD1, from all the extracted vibration parameters, temperature parameters, power parameters, current and voltage parameters containing the marker mother code and the marker child code, obtain the vibration parameters, temperature parameters, power parameters, current and voltage parameters of the same marker mother code and the marker child code; SD2. From the vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking mother code and marking child code, obtain multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters of the same marking child code, wherein the marking child codes of the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters are the same, and the marking mother codes are different; SD3. Among the multiple vibration parameters, temperature parameters, power parameters, and current and voltage parameters encoded in the same marker, the maximum and minimum parameters of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters are selected, and the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval are formed using the maximum and minimum parameters. SD3. Build a fault analysis model based on vibration range, temperature parameter range, power parameter range, and current and voltage parameter range; SD4, import the information parameters corresponding to the new energy wind farm collected in real time into the pre-trained fault analysis model after construction; The fault analysis model extracts vibration parameters, temperature parameters, power parameters, and current and voltage parameters from the information parameters collected in real time, and matches them with the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval respectively: If at least one of the vibration parameters, temperature parameters, power parameters, and current and voltage parameters is not within the vibration range, temperature parameter range, power parameter range, and current and voltage parameter range, it indicates that the operation of the new energy wind farm is abnormal, and an abnormal signal is subsequently generated.

4. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 2 is characterized in that: In step SD4, if the vibration parameter, temperature parameter, power parameter, current and voltage parameters are all within the vibration interval, temperature parameter interval, power parameter interval, and current and voltage parameter interval, it indicates that the new energy wind farm is operating normally.

5. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 2 is characterized in that: The specific method of the deep diagnosis module is as follows: SF1. According to the abnormal signal, obtain the information parameter that is not in the corresponding parameter interval, select the abnormal signal corresponding to the vibration parameter, and if the vibration parameter is not in the vibration interval, obtain the vibration parameter of the previous t1 time nodes of the current vibration parameter, and obtain the vibration parameter of the next t2 time nodes of the current vibration parameter; SF2, matching the vibration parameters corresponding to the first t1 time nodes and the last t2 time nodes corresponding to the current vibration parameters with the vibration intervals corresponding to the corresponding time nodes, and obtaining corresponding matching results; SF3, according to the sequence of the time nodes, the matching results of the t1 time nodes, the next t2 time nodes and the current vibration parameters are arranged in sequence; SF4. Combine the arrangement order corresponding to the matching results with the pre-trained abnormal sorting rules for classification and judgment, and obtain the corresponding rule 1 or rule 2: SF5. In the matching results, obtain the number t0 of the corresponding vibration parameters that are not in the corresponding parameter interval; SF6, through Calculate the abnormal proportion of the corresponding information parameters, where 1 refers to the value assigned to the current vibration parameter corresponding to the abnormal signal; SF7. Compare Bt with the preset value By: If Bt is greater than By, it means that the key equipment corresponding to the vibration parameter is operating abnormally and a fault signal is generated.

6. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 5 is characterized in that: In step SF4, the pre-trained anomaly sorting rules are as follows: Rule 1: In the arrangement order corresponding to the matching results, if there are r1 or more consecutive matching results, the vibration parameters are not in the vibration interval; Rule 2: In the arrangement order corresponding to the matching results, the number of consecutive adjacent matching results whose vibration parameters are not in the vibration interval is less than r1.

7. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 6 is characterized in that: In step SF7, the value of By is two groups, one group is preset according to rule 1 of the pre-trained abnormal sorting rule, and the other group is preset according to rule 2 of the pre-trained abnormal sorting rule; Among them, if Bt is less than or equal to By, it means that the key equipment corresponding to the vibration parameter operates normally and does not generate a fault signal.

8. The intelligent monitoring and fault diagnosis system for a new energy wind farm according to claim 1 is characterized in that: Also includes: The visualization module is used to display the monitoring and diagnosis results to operation and maintenance personnel in a graphical manner.

Images