A method for early warning and scheduling based on SCADA system and SCADA system
By preprocessing and modeling the basic parameters of wind turbines, reasonable scheduling instructions are generated, which solves the problem of insufficient early warning signals for wind turbines in the SCADA system and improves the operating efficiency and reliability of wind farms.
Patent Information
- Application Number
- CN202511672625.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-14
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2045-11-14
AI Technical Summary
The existing SCADA system in wind farms has failed to effectively combine the status of wind turbines to issue reasonable early warning signals, making it difficult for staff to make timely and correct judgments.
By acquiring basic wind turbine parameters, preprocessing and grouping them, establishing fault diagnosis and selection models, generating scheduling instructions, and encrypting and transmitting them to the remote control terminal.
It enables further analysis of wind turbine operating status and power generation, providing more reasonable dispatch instructions for remote control personnel to refer to, thereby improving the accuracy and timeliness of operation.
Smart Images

Figure CN121408158B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of wind farm system control technology, and more specifically, to a SCADA system-based early warning and scheduling method and a SCADA system. Background Technology
[0002] Supervisory Control and Data Acquisition (SCADA) systems are the core technology platform for wind farm operation and control. In the early stages, wind farms were small-scale and geographically dispersed, relying primarily on manual on-site monitoring and maintenance, which was inefficient and costly. As the wind power industry has evolved towards larger scale and clusters, traditional control methods have become insufficient to meet the demands for real-time monitoring, centralized management, and intelligent operation and maintenance. Early SCADA systems were relatively simple, focusing mainly on data monitoring and basic control. With technological advancements, modern wind farm SCADA systems have evolved into intelligent integrated management systems that combine real-time monitoring, power prediction, fault diagnosis, performance analysis, and report generation, providing crucial technical support for the reliable and efficient operation of wind farms.
[0003] However, current technologies generally only perform simple data collection and fault diagnosis analysis, without considering the current status of all wind turbines to issue a reasonable early warning signal. They only focus on simple data analysis, providing staff with limited reference information, which may lead to the inability to make timely and correct judgments. Summary of the Invention
[0004] The purpose of this invention is to provide a SCADA system-based early warning and scheduling method and SCADA system to solve the above-mentioned problems in the prior art.
[0005] This invention is achieved through the following technical solution: In a first aspect, the present invention provides an early warning and scheduling method based on a SCADA system, comprising: Input the basic parameters of the wind turbine obtained from the SCADA system, and preprocess the basic parameters of the wind turbine to obtain several target parameter groups of different data types; The unit status of the wind turbine is obtained, including the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. The first wind turbine is diagnosed based on the target parameters, and an instruction is output on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. Obtain the current power generation of the target wind farm and determine whether the current power generation is greater than or equal to the preset minimum power generation value; If so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine, sort the fault indices, and generate a scheduling instruction to shut down several third wind turbines based on the sorting results and the corresponding power generation. If not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines respectively, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output the selection index of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indexes, and generate a scheduling instruction for the priority processing of the second or fourth wind turbine based on the sorting result. The scheduling instructions are encrypted and transmitted to the remote control terminal.
[0006] Preferably, the preprocessing of the wind turbine's basic parameters to obtain several target parameter sets of different data types includes: The current basic parameters of the wind turbine are grouped according to the type of data, and sorted according to the time sequence based on the time node obtained, resulting in several different types of data groups; Determine whether each time node in the data group corresponds to a wind turbine basic parameter. If it corresponds to a wind turbine basic parameter, obtain the number of wind turbine basic parameters. If it is equal to 1, proceed to determine the wind turbine basic parameter of the next time node. If it is not equal to 1, select one of all wind turbine basic parameters of that time node as the replacement value of that time node. If there are no corresponding wind turbine basic parameters, then obtain the wind turbine basic parameters of several other different time nodes in the same data group as correction parameters, obtain supplementary parameters based on several correction parameters, and use the supplementary parameters as the replacement value for that time node. After iterating through the basic parameters of all time points, output the target parameter set.
[0007] Preferably, selecting one of the wind turbine foundation parameters at that time point as the replacement value for that time point includes: Obtain the judgment threshold of the wind turbine basic parameters at this time point under normal wind turbine operation, and determine whether there are wind turbine basic parameters within the judgment threshold; If so, the first wind turbine basic parameters that are outside the judgment threshold are removed, and the second wind turbine basic parameters that are within the judgment threshold are retained. The average value of the second wind turbine basic parameters is used as the replacement value for that time node. If not, when the number of basic parameters of the first wind turbine is 2, the average value of the basic parameters of the first wind turbine is used as the replacement value for that time point. When the number of basic parameters of the first wind turbine is 3, the maximum and minimum values of the basic parameters of the first wind turbine are removed to obtain the basic parameters of the third wind turbine, and the basic parameters of the third wind turbine are used as the replacement values at this time point. When the number of basic parameters of the first wind turbine is 4, the average value of the basic parameters of the third wind turbine is used as the replacement value at that time point. When the number of basic parameters of the first wind turbine is greater than 4, a data selection model is established. Based on the data selection model and the basic parameters of the third wind turbine, a reference value is output and used as the replacement value for that time node.
[0008] Preferably, the establishment of the data selection model includes:
[0009] In the formula, For reference only. This represents the maximum value of the foundation parameters for the third wind turbine. This represents the minimum value of the foundation parameters for the third wind turbine. This represents the median of the basic parameters for the third wind turbine.
[0010] Preferably, the supplementary parameters obtained based on several correction parameters include:
[0011] In the formula, To supplement parameters, These are the basic parameters of the wind turbine at the previous time point. For the wind turbine basic parameters at the next time point, The maximum value of the current threshold for judging the basic parameters of the wind turbine. This is the minimum value of the judgment threshold for the current basic parameters of the wind turbine; when At that time, delete the current time node.
[0012] Preferably, the establishment of the fault severity diagnosis model includes:
[0013]
[0014] In the formula, The failure index, The number of data types. For the first The calculation factors for the target parameter set, For the first The number of parameters in the target parameter. For the first The first type of target parameter One target parameter, For the first The average value between the maximum and minimum values of the judgment threshold for a set of target parameters.
[0015] Preferably, the establishment of the selection model, based on the interval time and annual average power generation, and the output of selection indices for the second and fourth wind turbines through the selection model, includes:
[0016] In the formula, To select an index, This refers to the interval between the current time point and the restart time point for the second or fourth fan. The average time taken to restart all wind turbines. This refers to the average annual power generation of the second or fourth wind turbine. The average annual power generation of all wind turbines. The average cost of maintaining or overhauling the second and fourth fans. This refers to the maintenance or repair costs of the current second or fourth wind turbine.
[0017] Preferably, the step of encrypting and transmitting the scheduling command to the remote control terminal includes: A first private key and a second private key are randomly generated at the remote control terminal. Based on the first private key and the second private key, scalar multiplication operations are performed with the base point to obtain the first public key and the second public key. Sequentially obtain the first public key or the second public key, divide the scheduling instruction into two data packets, and encrypt the two data packets using the first public key and the second public key respectively; One of the encrypted data packets is sent to the remote control terminal. After the remote control terminal decrypts the packet and receives acceptance feedback, it sends the second data packet. Otherwise, the process terminates.
[0018] Preferably, encrypting data packets includes:
[0019]
[0020]
[0021]
[0022] In the formula, It is a base point in elliptic curve cryptography. It is an integer. , To pass The coordinates of the base points after multiplication For plain text, These are pseudo-random numbers derived from the key or values generated by a specific algorithm. For hash functions, , These are values related to the encryption process. For final ciphertext, , and Each is a part of the ciphertext.
[0023] Secondly, the present invention also incorporates a SCADA system for executing the aforementioned SCADA system-based early warning and scheduling method, comprising: The data processing module is configured to take into account the basic wind turbine parameters obtained from the SCADA system and preprocess the basic wind turbine parameters to obtain several target parameter groups of different data types. The unit status of the wind turbine is obtained, including the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. The first wind turbine is diagnosed based on the target parameters, and an instruction is output on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. The dispatching and early warning module is configured to obtain the current power generation of the target wind farm, determine whether the current power generation is greater than or equal to a preset minimum power generation value; if so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine through the fault severity diagnosis model, sort the fault indices, and generate dispatching instructions to shut down several third wind turbines based on the sorting results and the corresponding power generation; if not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output selection indices of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indices, and generate dispatching instructions to prioritize the second or fourth wind turbine based on the sorting results; and encrypt and transmit the dispatching instructions to the remote control terminal.
[0024] The technical solution of the present invention has at least the following advantages and beneficial effects: The method and system provided by this invention mainly include acquiring the unit status of wind turbines, which includes a first wind turbine operating normally, a second wind turbine shut down for maintenance, a third wind turbine operating with a fault, and a fourth wind turbine shut down for repair. Based on the sorting results and the corresponding power generation, a scheduling instruction to shut down several third wind turbines is generated, or a scheduling instruction to prioritize the second or fourth wind turbines is generated based on the sorting results. Through the above-mentioned method of this invention, the operating status of the wind turbines and the power generation of the wind farm are combined to further analyze the collected data and obtain more reasonable results for reference by the staff at the remote control terminal, so as to make more accurate operations in a timely manner. Attached Figure Description
[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0026] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation
[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not imply that the steps in the method flow must be executed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical objective, as long as the same or similar technical effect is achieved.
[0029] The independently described modules or sub-modules may or may not be physically separated; they may be implemented in software or hardware, and some modules or sub-modules may be implemented in software, with the processor calling the software to implement the function of these modules or sub-modules, while other modules or sub-modules may be implemented in hardware, such as through hardware circuits. Furthermore, some or all of the modules can be selected to achieve the purpose of this application's solution according to actual needs.
[0030] Please refer to Figures 1-2 A method for early warning and scheduling based on a SCADA system, comprising: S101: Input the basic parameters of the wind turbine obtained from the SCADA system, and preprocess the basic parameters of the wind turbine to obtain several target parameter groups of different data types; In this embodiment, the basic parameters of the wind turbine may include key data such as wind speed, wind direction, ambient temperature, atmospheric pressure / humidity, rotor speed, generator speed, yaw angle / position, pitch angle, power generation, gearbox oil temperature / bearing temperature, and generator winding temperature / bearing temperature. After processing each type of data, several preprocessed target parameter sets are formed.
[0031] S102: Obtain the unit status of the wind turbine, which includes the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. Perform fault diagnosis on the first wind turbine based on the target parameters, and output an instruction on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. In this embodiment, the status of the fan is divided into four basic states. The current operating parameters or historical diagnostic data of the fan can be obtained to determine the current operating status of the fan. If the first fan is determined to be faulty, but the operation of the fan does not need to be immediately shut down, it can be classified as the third fan. If the operation needs to be stopped immediately, it is classified as the fourth fan. Whether the fan needs to be stopped immediately can be determined according to the specific criteria set by those skilled in the art. This solution will not elaborate further. If there is no fault, it is still the first fan.
[0032] The second fan is the one that is undergoing normal maintenance, while the third fan is the one that has a fault but does not need to be stopped immediately.
[0033] S103: Obtain the current power generation of the target wind farm and determine whether the current power generation is greater than or equal to the preset minimum power generation value; S104: If so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine through the fault severity diagnosis model, sort the fault indices, and generate a scheduling instruction to shut down several third wind turbines based on the sorting results and the corresponding power generation. Specifically, when the number of third wind turbines shut down is reduced to a point where the total power generation is just below the minimum power generation value if the next third wind turbine is shut down, the shutdown of the third wind turbines will be stopped.
[0034] S105: If not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines respectively, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output the selection index of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indexes, and generate a scheduling instruction for the priority processing of the second or fourth wind turbine based on the sorting result. Among them, the second fan that needs to be shut down for maintenance requires a comprehensive inspection and replacement of vulnerable parts, while the fourth fan that needs to be shut down for maintenance requires replacement of parts to troubleshoot the fault. In this embodiment, the second fan and the fourth fan have different time and cost requirements, so a selection model is established for further selection.
[0035] In this embodiment, the priority order processing specifically involves issuing a notification and dispatching more operators to the second or fourth fan that ranks higher according to the selection index. This expedites the preparation work for the second or fourth fan to restart operation and reduces maintenance or repair time. The specific number of operators to be dispatched to the fan that ranks higher can be set according to the site conditions. This solution only provides a reference for the sorting.
[0036] S106: The scheduling instruction is encrypted and transmitted to the remote control terminal.
[0037] Because power data needs to be kept confidential during transmission to prevent external attacks that could damage the power grid.
[0038] By combining the operating status of the wind turbine and the power generation of the wind farm with the above-described method of the present invention, the collected data is further analyzed to obtain more reasonable results, which can be used as a reference for the staff at the remote control end, so as to make more accurate operations in a timely manner.
[0039] In one exemplary embodiment of the present invention, in order to reduce data errors, it is necessary to preprocess the data, i.e., perform data cleaning, and preprocess the basic parameters of the wind turbine to obtain several target parameter sets of different data types, including: S201: Group the current wind turbine basic parameters according to the data type, and sort them according to the time series based on the acquired time points to obtain several different types of data groups; S202: Determine whether each time node in the data group corresponds to a wind turbine basic parameter. If it corresponds to a wind turbine basic parameter, obtain the number of wind turbine basic parameters. If it is equal to 1, determine the wind turbine basic parameter of the next time node. If it is not equal to 1, select one of all wind turbine basic parameters of the time node as the replacement value of the time node. This solution primarily addresses situations where data is missing or multiple data points appear at a specific point in time during the data collection process.
[0040] Specifically, the threshold values for the basic parameters of the wind turbine at that time point under normal wind turbine operation are obtained to determine whether any basic parameters of the wind turbine are within the threshold values. The specific threshold values can be set directly from historical data based on the basic parameters of the current wind turbine.
[0041] If so, the first wind turbine basic parameters that are outside the judgment threshold are removed, and the second wind turbine basic parameters that are within the judgment threshold are retained. The average value of the second wind turbine basic parameters is used as the replacement value for that time node. If multiple data points of the same type appear at a given time point, and if there are normal values, the abnormal first wind turbine basic parameters are considered to be normal data fluctuations, and the normal second wind turbine basic parameters are used as replacement values to reduce errors.
[0042] If not, when the number of basic parameters of the first wind turbine is 2, the average value of the basic parameters of the first wind turbine is used as the replacement value for that time point. When the number of basic parameters for the first wind turbine is 3, the maximum and minimum values of the basic parameters for the first wind turbine are removed to obtain the basic parameters for the third wind turbine, and the basic parameters for the third wind turbine are used as the replacement values for that time node; when the number of basic parameters for the first wind turbine is 4, the average value of the basic parameters for the third wind turbine is used as the replacement value for that time node; when the number of basic parameters for the first wind turbine is greater than 4, a data selection model is established, and a reference value is output based on the data selection model and the basic parameters for the third wind turbine, and the reference value is used as the replacement value for that time node.
[0043] In this embodiment, different methods for obtaining replacement values are set according to the number of basic parameters of the first wind turbine, so as to further reduce the subsequent calculation errors brought to the entire data set.
[0044] Specifically, establishing a data selection model includes:
[0045] In the formula, For reference only. This represents the maximum value of the foundation parameters for the third wind turbine. This represents the minimum value of the foundation parameters for the third wind turbine. The median of the basic parameters of the third wind turbine If there are no basic wind turbine parameters corresponding to S203, then obtain the basic wind turbine parameters of several other different time points in the same data group as correction parameters, obtain supplementary parameters based on several correction parameters, and use the supplementary parameters as the replacement value for that time point. Specifically, the supplementary parameters obtained based on several correction parameters include:
[0046] In the formula, To supplement parameters, These are the basic parameters of the wind turbine at the previous time point. For the wind turbine basic parameters at the next time point, The maximum value of the current threshold for judging the basic parameters of the wind turbine. The minimum value of the current wind turbine basic parameter judgment threshold; when At that time, delete the current time node.
[0047] Among them, when If the current missing value is the first data in the target parameter group, and there is no preceding data for reference, then the entire time node is directly deleted to minimize the impact on subsequent data.
[0048] S204: After traversing all the basic parameters of all time nodes, output the target parameter group.
[0049] In one exemplary embodiment of the present invention, establishing the fault severity diagnosis model includes:
[0050]
[0051] In the formula, The failure index, The number of data types. For the first The calculation factors for the target parameter set, For the first The number of parameters in the target parameter. For the first The first type of target parameter One target parameter, For the first The average value between the maximum and minimum values of the judgment threshold for a set of target parameters.
[0052] The fault index is derived by using the relationship between each parameter and the normal judgment threshold of the target parameter group. This index measures the current fault severity of the wind turbine, reflecting both data fluctuations and the degree to which outliers deviate from the judgment threshold. A higher fault index indicates a more severe fault in the wind turbine.
[0053] In one exemplary embodiment of the present invention, the selection indices for the second and fourth wind turbines are output through a selection model based on the interval time and annual average power generation, including:
[0054] In the formula, To select an index, This refers to the interval between the current time point and the restart time point for the second or fourth fan. The average time taken to restart all wind turbines. This refers to the average annual power generation of the second or fourth wind turbine. The average annual power generation of all wind turbines. The average cost of maintaining or overhauling the second and fourth fans. This refers to the maintenance or repair costs of the current second or fourth wind turbine.
[0055] In this embodiment, the time required to restart the wind turbine and its power generation are taken into account. Certain second or fourth wind turbines are processed more quickly, and a signal to increase maintenance personnel is sent. The selection index is used as the basis for remote control personnel to refer to. The higher the selection index, the higher the priority level for starting the current wind turbine. However, if the total power generation of the started second or fourth wind turbine and the first wind turbine exceeds the minimum power generation value, the second or fourth wind turbine can be maintained or repaired normally according to the initial plan.
[0056] In one exemplary embodiment of the present invention, encrypting and transmitting the scheduling instruction to the remote control terminal includes: A first private key and a second private key are randomly generated at the remote control terminal. Based on the first private key and the second private key, scalar multiplication operations are performed with the base point to obtain the first public key and the second public key. Sequentially obtain the first public key or the second public key, divide the scheduling instruction into two data packets, and encrypt the two data packets using the first public key and the second public key respectively; One of the encrypted data packets is sent to the remote control terminal. After the remote control terminal decrypts the packet and receives acceptance feedback, it sends the second data packet. Otherwise, the process terminates.
[0057] In this embodiment, two private keys are used to generate two public keys. Unlike the prior art, the present invention divides the entire instruction into two parts. After receiving feedback, the other part is sent to avoid the entire instruction data being intercepted. In this way, even if a part is intercepted, the data will be incomplete and cannot be opened normally.
[0058] Specifically, encrypting data packets includes:
[0059]
[0060]
[0061]
[0062] In the formula, It is a base point in elliptic curve cryptography. It is an integer. , To pass The coordinates of the base points after multiplication For plain text, These are pseudo-random numbers derived from the key or values generated by a specific algorithm. For hash functions, , These are values related to the encryption process. For final ciphertext, , and Each is a part of the ciphertext.
[0063] A SCADA system for executing the above-mentioned SCADA system-based early warning scheduling method includes: The data processing module is configured to take into account the basic wind turbine parameters obtained from the SCADA system and preprocess the basic wind turbine parameters to obtain several target parameter groups of different data types. The unit status of the wind turbine is obtained, including the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. The first wind turbine is diagnosed based on the target parameters, and an instruction is output on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. The dispatching and early warning module is configured to obtain the current power generation of the target wind farm, determine whether the current power generation is greater than or equal to a preset minimum power generation value; if so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine through the fault severity diagnosis model, sort the fault indices, and generate dispatching instructions to shut down several third wind turbines based on the sorting results and the corresponding power generation; if not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output selection indices of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indices, and generate dispatching instructions to prioritize the second or fourth wind turbine based on the sorting results; and encrypt and transmit the dispatching instructions to the remote control terminal.
[0064] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0065] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0066] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for early warning and scheduling based on a SCADA system, characterized in that, include: Input the basic parameters of the wind turbine obtained from the SCADA system, and preprocess the basic parameters of the wind turbine to obtain several target parameter groups of different data types; The unit status of the wind turbine is obtained, including the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. The first wind turbine is diagnosed based on the target parameters, and an instruction is output on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. Obtain the current power generation of the target wind farm and determine whether the current power generation is greater than or equal to the preset minimum power generation value; If so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine, sort the fault indices, and generate a scheduling instruction to shut down several third wind turbines based on the sorting results and the corresponding power generation. If not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines respectively, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output the selection index of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indexes, and generate a scheduling instruction for the priority processing of the second or fourth wind turbine based on the sorting result. The scheduling instructions are encrypted and transmitted to the remote control terminal; The wind turbine's basic parameters are preprocessed to obtain several target parameter groups of different data types, including: The current basic parameters of the wind turbine are grouped according to the type of data, and sorted according to the time sequence based on the time node obtained, resulting in several different types of data groups; Determine whether each time node in the data group corresponds to a wind turbine basic parameter. If it corresponds to a wind turbine basic parameter, obtain the number of wind turbine basic parameters. If it is equal to 1, proceed to determine the wind turbine basic parameter of the next time node. If it is not equal to 1, select one of all wind turbine basic parameters of that time node as the replacement value of that time node. If there are no corresponding wind turbine basic parameters, then obtain the wind turbine basic parameters of several other different time nodes in the same data group as correction parameters, obtain supplementary parameters based on several correction parameters, and use the supplementary parameters as the replacement value for that time node. After iterating through the basic parameters of all time points, output the target parameter set; The supplementary parameters obtained based on several correction parameters include: In the formula, To supplement parameters, These are the basic parameters of the wind turbine at the previous time point. For the basic parameters of the wind turbine at the next time point, The maximum value of the current threshold for judging the basic parameters of the wind turbine. This is the minimum value of the judgment threshold for the current basic parameters of the wind turbine; when At that time, delete the current time node.
2. The SCADA system-based early warning and scheduling method according to claim 1, characterized in that, The selection of one of all wind turbine foundation parameters at that time point as the replacement value for that time point includes: Obtain the judgment threshold of the wind turbine basic parameters at this time point under normal wind turbine operation, and determine whether there are wind turbine basic parameters within the judgment threshold; If so, the first wind turbine basic parameters that are outside the judgment threshold are removed, the second wind turbine basic parameters that are within the judgment threshold are retained, and the average value of the second wind turbine basic parameters is used as the replacement value for that time node. If not, when the number of basic parameters of the first wind turbine is 2, the average value of the basic parameters of the first wind turbine is used as the replacement value for that time point; When the number of basic parameters of the first wind turbine is 3, the maximum and minimum values of the basic parameters of the first wind turbine are removed to obtain the basic parameters of the third wind turbine, and the basic parameters of the third wind turbine are used as the replacement values at this time point. When the number of basic parameters of the first wind turbine is 4, the average value of the basic parameters of the third wind turbine is used as the replacement value at that time point. When the number of basic parameters of the first wind turbine is greater than 4, a data selection model is established. Based on the data selection model and the basic parameters of the third wind turbine, a reference value is output and used as the replacement value for that time node.
3. The SCADA system-based early warning and scheduling method according to claim 2, characterized in that, The establishment of the data selection model includes: In the formula, For reference only. This represents the maximum value of the foundation parameters for the third wind turbine. This represents the minimum value of the foundation parameters for the third wind turbine. This represents the median of the basic parameters for the third wind turbine.
4. The SCADA system-based early warning and scheduling method according to claim 1, characterized in that, The establishment of the fault severity diagnosis model includes: In the formula, The failure index, The number of data types. For the first The calculation factors for the target parameter set, For the first The number of parameters in the target parameter. For the first The first type of target parameter One target parameter, For the first The average value between the maximum and minimum values of the judgment threshold for a set of target parameters.
5. The SCADA system-based early warning and scheduling method according to claim 4, characterized in that, The establishment of the selection model, based on the interval time and annual average power generation, outputs selection indices for the second and fourth wind turbines, including: In the formula, To select an index, This refers to the interval between the current time point and the restart time point for the second or fourth fan. The average time taken to restart all wind turbines. This refers to the average annual power generation of the second or fourth wind turbine. The average annual power generation of all wind turbines. The average cost of maintaining or overhauling the second and fourth fans. This refers to the maintenance or repair costs of the current second or fourth wind turbine.
6. The SCADA system-based early warning and scheduling method according to claim 1, characterized in that, The step of encrypting and transmitting the scheduling command to the remote control terminal includes: A first private key and a second private key are randomly generated at the remote control terminal. Based on the first private key and the second private key, scalar multiplication operations are performed with the base point to obtain the first public key and the second public key. Sequentially obtain the first public key or the second public key, divide the scheduling instruction into two data packets, and encrypt the two data packets using the first public key and the second public key respectively; One of the encrypted data packets is sent to the remote control terminal. After the remote control terminal decrypts the packet and receives acceptance feedback, it sends the second data packet. Otherwise, the process terminates.
7. The SCADA system-based early warning and scheduling method according to claim 6, characterized in that, Encrypting data packets includes: In the formula, It is a base point in elliptic curve cryptography. It is an integer. , To pass The coordinates of the base points after multiplication For plain text, These are pseudo-random numbers derived from the key or values generated by a specific algorithm. For hash functions, , These are values related to the encryption process. For final ciphertext, , and Each is a part of the ciphertext.
8. A SCADA system, characterized in that, A method for executing a SCADA system-based early warning and scheduling method according to any one of claims 1-7 includes: The data processing module is configured to take into account the basic wind turbine parameters obtained from the SCADA system and preprocess the basic wind turbine parameters to obtain several target parameter groups of different data types. The unit status of the wind turbine is obtained, including the first wind turbine operating normally, the second wind turbine shut down for maintenance, the third wind turbine operating with a fault, and the fourth wind turbine shut down for maintenance. The first wind turbine is diagnosed based on the target parameters, and an instruction is output on whether the fault of the first wind turbine should be changed to the third wind turbine based on the result of the fault diagnosis. The dispatching and early warning module is configured to obtain the current power generation of the target wind farm, determine whether the current power generation is greater than or equal to a preset minimum power generation value; if so, establish a fault severity diagnosis model, output a fault index based on the target parameter group of the third wind turbine through the fault severity diagnosis model, sort the fault indices, and generate dispatching instructions to shut down several third wind turbines based on the sorting results and the corresponding power generation; if not, obtain the interval between the current time node and the restart time node of the second and fourth wind turbines, obtain the annual average power generation of the second and fourth wind turbines, establish a selection model, output selection indices of the second and fourth wind turbines through the selection model based on the interval time and annual average power generation, sort the selection indices, and generate dispatching instructions to prioritize the second or fourth wind turbine based on the sorting results; and encrypt and transmit the dispatching instructions to the remote control terminal.
Citation Information
Patent Citations
Active power control method for enhancing wind power plant operation economy
CN107658912A
Offshore wind turbine generator maintenance planning system and method based on genetic algorithm
CN117291572A
