Sensor configuration adjusting method and device, storage medium and electronic device

Abstract

The invention discloses a sensor configuration adjusting method and device, a storage medium and an electronic device. The method comprises the steps that according to historical operation information corresponding to a target fan, disturbance indexes on the output power of the target fan when different operation variable data of the fan are changed are determined; grading different operation variables of the fan according to the disturbance indexes to obtain a plurality of sensitive grades; and according to the multiple sensitivity levels, corresponding sensor configuration schemes of the target draught fan under different draught fan operation variables are adjusted. By adopting the technical scheme, the problem that the operation variable of the fan cannot be accurately monitored to improve the operation efficiency and stability of the fan is solved. Furthermore, the performance and the efficiency of the fan are improved by adjusting the sensor configuration schemes corresponding to different operation variables of the fan.

Description

Technical Field

[0001] The present application relates to the field of wind power monitoring, and more specifically, to a sensor configuration adjustment method and device, a storage medium, and an electronic device. Background Art

[0002] Offshore wind power is a new type of energy generation method that uses offshore wind energy to generate electricity. Compared with traditional land wind farms, offshore wind farms are far from the shore, with harsh operating environments, difficult operation and maintenance, and high costs. They are greatly affected by various hydrological phenomena such as tides and currents, as well as factors such as vibration and corrosion. The loss of various equipment is often higher than in other environments, and wind turbines are very likely to cause failures. Monitoring, analyzing and diagnosing the operating status of wind turbines is an important means to ensure their safe operation. Sensors, as the core source of data collection, play a vital role in this. The existing selection and deployment methods of wind power sensors are usually considered from the perspective of economy and past experience, and the impact of different monitoring variables on system performance and health status is not fully combined. Therefore, key variables are not selected for monitoring in a targeted manner, and the number of sensors deployed may be redundant or insufficient, which leads to low efficiency and economy of monitoring, and fails to fully respond to the actual needs of the system.

[0003] With regard to the problem in related technologies that the operating variables of the fan cannot be accurately monitored to improve the operating efficiency and stability of the fan, no effective solution has been proposed so far.

[0004] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0005] The embodiments of the present application provide a sensor configuration adjustment method and device, a storage medium and an electronic device, so as to at least solve the problem that the operating variables of the fan cannot be accurately monitored to improve the operating efficiency and stability of the fan.

[0006] According to one aspect of an embodiment of the present application, a method for adjusting sensor configuration is provided, including: determining a disturbance index on the output power of a target wind turbine when different operating variable data of the wind turbine change based on historical operating information corresponding to the target wind turbine; classifying different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels; and adjusting the sensor configuration scheme corresponding to the target wind turbine according to the multiple sensitivity levels.

[0007] In an exemplary embodiment, before determining the disturbance index of the target wind turbine output power when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine, the method also includes: collecting current wind turbine data corresponding to the wind farm, and screening the current wind turbine data; determining multiple wind turbine variables to be monitored from the screening results, and determining the monitoring data corresponding to the multiple wind turbine variables in different time periods, and obtaining a combination of multiple wind turbine variables corresponding to different time periods; wherein each combination includes the wind turbine power and different operating variables of the wind turbine, and the different operating variables of the wind turbine include at least one of the following: the wind speed corresponding to the fan, the wind direction corresponding to the fan, the temperature corresponding to each component on the fan, the vibration corresponding to the fan, the blade angle corresponding to the fan, and the air density at the location of the fan; using the combination as training data to train the preset fan operation model, and obtaining a target fan operation model with the input as the operation information and the output as the fan power; fitting the target fan operation model to generate a nonlinear function, wherein the nonlinear function is used to represent the correlation change between different operating variables of the fan and the fan power.

[0008] In an exemplary embodiment, after fitting the target wind turbine operation model and generating a nonlinear function, the method also includes: simulating the adjustment of the numerical value of any operating variable in the combination of each wind turbine variable; determining the range of change of wind turbine power caused by any operating variable based on the nonlinear function; associating the numerical value and the range of change to obtain a set of change data; calculating a set of change data to perform sensitivity analysis on the target wind turbine operation model to obtain the sensitivity value corresponding to the target wind turbine operation model when any operating variable changes.

[0009] In an exemplary embodiment, different operating variables of the wind turbine are graded according to disturbance indicators to obtain multiple sensitivity levels, including: obtaining threshold intervals set for the disturbance indicators of the target object, wherein the threshold intervals include at least: a first threshold interval, a second threshold interval, a third threshold interval, and a fourth threshold interval; the first threshold interval is the highest level interval, mainly for disturbance indicators with high sensitivity and high uncertainty; the second threshold interval is mainly for disturbance indicators with high sensitivity and low uncertainty; the third threshold interval is mainly for disturbance indicators with low sensitivity and high uncertainty; the fourth threshold interval is mainly for disturbance indicators with low sensitivity and low uncertainty; the disturbance indicators are graded according to the threshold intervals to obtain multiple sensitivity levels.

[0010] In an exemplary embodiment, the sensor configuration scheme corresponding to the target fan under different operating variables of the fan is adjusted according to the multiple sensitivity levels, including: determining a historical sensor configuration scheme corresponding to the target fan, and a target sensor configuration scheme corresponding to the multiple sensitivity levels; comparing the accuracy difference between the historical sensor configuration scheme and the target sensor configuration scheme; and determining the sensor configuration scheme corresponding to the target fan according to the accuracy difference.

[0011] In an exemplary embodiment, the sensor configuration scheme corresponding to the target fan is determined based on the accuracy difference, including: when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is greater than or equal to the target sensor configuration scheme, determining to maintain the sensor configuration scheme corresponding to different operating variables of the current fan of the target fan unchanged; when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is less than the target sensor configuration scheme, determining to adjust the sensor configuration scheme corresponding to different operating variables of the current fan of the target fan to the target sensor configuration scheme.

[0012] In an exemplary embodiment, adjusting the sensor configuration scheme corresponding to the target fan under different operating variables of the fan according to the multiple sensitivity levels also includes: calculating the actual usage quantity of different types of sensors required for monitoring different operating variables of the fan required by the target sensor configuration scheme; determining the difference between the actual usage quantity and the historical usage quantity of different types of sensors installed on the target fan for monitoring different operating variables of the fan; and determining the configuration focus of the sensor configuration scheme based on the difference.

[0013] According to another aspect of an embodiment of the present application, a sensor configuration adjustment device is also provided, including: a first determination module, used to determine the disturbance index to the output power of the target wind turbine when the data of different operating variables of the wind turbine changes based on the historical operating information corresponding to the target wind turbine; a grading module, used to grade the different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels; and an adjustment module, used to adjust the sensor configuration scheme corresponding to the different operating variables of the wind turbine according to the multiple sensitivity levels.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned sensor configuration adjustment method when running.

[0015] According to another aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the sensor configuration adjustment method through the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and the method for adjusting the sensor configuration described above is implemented when the computer program is executed by a processor.

[0017] Through this application, the disturbance index of the output power of the target fan when the data of different operating variables of the fan change is determined according to the historical operating information corresponding to the target fan; the different operating variables of the fan are graded according to the disturbance index to obtain multiple sensitivity levels; the sensor configuration scheme corresponding to the different operating variables of the fan is adjusted according to the multiple sensitivity levels. The above technical solution solves the problem of being unable to accurately monitor the operating variables of the fan to improve the operating efficiency and stability of the fan. Furthermore, the performance and efficiency of the fan are improved by adjusting the sensor configuration scheme corresponding to the different operating variables of the fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal of a sensor configuration adjustment method according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for adjusting sensor configuration according to an embodiment of the present application;

[0022] Figure 3 is a flow chart of a wind power system sensor deployment optimization method according to an embodiment of the present application;

[0023] Figure 4 It is a structural block diagram of adjustment of sensor configuration according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a mobile terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a computer terminal of a sensor configuration adjustment method according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 The computer terminal includes a processor 102 (only one is shown in the figure) (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, CPU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the adjustment method of the sensor configuration in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0028] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a method for adjusting sensor configuration is provided. Figure 2 is a flow chart of a method for adjusting sensor configuration according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps S202-S206:

[0030] Step S202: determining a disturbance index on the output power of the target wind turbine when different operating variable data of the wind turbine change according to historical operating information corresponding to the target wind turbine;

[0031] Step S204: classifying different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels;

[0032] Step S206: adjusting the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels.

[0033] Through the above steps, the disturbance index of the output power of the target fan when the data of different operating variables of the fan change is determined according to the historical operating information corresponding to the target fan; the different operating variables of the fan are graded according to the disturbance index to obtain multiple sensitivity levels; the sensor configuration scheme corresponding to the target fan under different operating variables of the fan is adjusted according to the multiple sensitivity levels. The problem of being unable to accurately monitor the operating variables of the fan to improve the operating efficiency and stability of the fan is solved. Furthermore, the performance and efficiency of the fan are improved by adjusting the sensor configuration scheme corresponding to different operating variables of the fan.

[0034] In an exemplary embodiment, before determining the disturbance index of the target wind turbine output power when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine, the method also includes: collecting current wind turbine data corresponding to the wind farm, and screening the current wind turbine data; determining multiple wind turbine variables to be monitored from the screening results, and determining the monitoring data corresponding to the multiple wind turbine variables in different time periods, and obtaining a combination of multiple wind turbine variables corresponding to different time periods; wherein each combination includes the wind turbine power and different operating variables of the wind turbine, and the different operating variables of the wind turbine include at least one of the following: the wind speed corresponding to the fan, the wind direction corresponding to the fan, the temperature corresponding to each component of the fan, the vibration corresponding to the fan, the blade angle corresponding to the fan, and the air density at the location of the fan; using the combination as training data to train the preset fan operation model, and obtaining a target fan operation model with the input as the operation information and the output as the fan power; fitting the target fan operation model to generate a nonlinear function, wherein the nonlinear function is used to represent the correlation change between different operating variables of the fan and the fan power.

[0035] It is understandable that multiple wind turbine variables in the site where the wind turbine is located are screened out based on historical data, and the above-mentioned wind turbine variables may include but are not limited to variables such as wind speed, wind direction, and temperature. The operation model of the target wind turbine is trained using a combination of multiple sets of wind turbine data that all contain the above-mentioned multiple wind turbine variables, and a nonlinear function is obtained to represent the correlation changes between different wind turbine operating variables and the wind turbine output power. When changes in wind speed or wind direction are monitored, the output power change of the wind turbine can be quickly and accurately predicted based on the fitted nonlinear function, so as to adjust the control strategy in time to ensure the stability and efficiency of the wind turbine operation. Through this process, the operation of the wind turbine can be understood more accurately, providing stronger support for subsequent monitoring and optimization.

[0036] Optionally, in actual applications, the above-mentioned fan variables may also include: the vibration corresponding to the fan, the blade angle corresponding to the fan, the air density at the fan location, the temperature at the fan location, the humidity at the fan location, the altitude at the fan location, the speed of the fan, etc. The above is merely an example and does not limit the above-mentioned fan variables.

[0037] In an exemplary embodiment, after fitting the target wind turbine operation model and generating a nonlinear function, the method further includes: simulating the adjustment of the numerical value of any one operating variable in the combination of each wind turbine variable; determining the range of change of wind turbine power caused by any one operating variable based on the nonlinear function; associating the numerical value with the change range to obtain a set of change data; performing a sensitivity analysis on the target wind turbine operation model through the set of change data to obtain the sensitivity value corresponding to the target wind turbine operation model when any one of the operating variables changes.

[0038] It is understandable that by simulating the adjustment of an operating variable in the combination of each fan variable, such as adjusting the blade angle, and observing the range of changes in the fan power, we can better understand and grasp the influence of the fan operating parameters on the power, which is helpful to optimize the fan operation management strategy. Correlating the numerical value of the adjusted blade angle with the power variation range to obtain a set of change data will help establish the correlation between the operating variables and the power, and provide a basis for subsequent data analysis and decision-making. By calculating a set of change data to perform a sensitivity analysis on the target fan operation model, the degree of influence of different operating variables on the fan power can be quantified, helping to identify key influencing factors and formulate corresponding adjustment measures. Through this process, we can gain an in-depth understanding of the degree of influence of the blade angle on the fan power, providing a scientific basis for optimizing the fan operating parameters.

[0039] In an exemplary embodiment, different operating variables of the wind turbine are graded according to the disturbance index to obtain multiple sensitivity levels, including: obtaining a threshold interval set for the target object for the disturbance index, wherein the threshold interval includes at least: a first threshold interval, a second threshold interval, a third threshold interval, and a fourth threshold interval; the first threshold interval is the highest level interval, mainly for disturbance indicators with high sensitivity and high uncertainty; the second threshold interval is mainly for disturbance indicators with high sensitivity and low uncertainty; the third threshold interval is mainly for disturbance indicators with low sensitivity and high uncertainty; the fourth threshold interval is mainly for disturbance indicators with low sensitivity and low uncertainty; the disturbance indicators are graded according to the threshold intervals to obtain multiple sensitivity levels.

[0040] It is understandable that by setting different threshold intervals, the fan operating variables can be finely graded according to the sensitivity and uncertainty of the disturbance index, making the monitoring and adjustment of different fan operating variables more targeted and effective. According to the different characteristics of sensitivity and uncertainty, the different fan operating variables are divided into multiple sensitivity levels, and targeted monitoring and processing can more effectively respond to various disturbance situations and improve the stability and reliability of fan operation. Dividing the fan operating variables into multiple sensitivity levels can help operation and maintenance personnel respond to different situations more quickly and accurately, improve the efficiency of fault diagnosis and processing, and reduce downtime and losses.

[0041] In an exemplary embodiment, adjusting the sensor configuration scheme corresponding to the target fan under different operating variables of the fan according to the multiple sensitivity levels includes: determining a historical sensor configuration scheme corresponding to the target fan, and a target sensor configuration scheme corresponding to the multiple sensitivity levels; comparing the accuracy difference between the historical sensor configuration scheme and the target sensor configuration scheme; and determining the sensor configuration scheme corresponding to the target fan according to the accuracy difference.

[0042] Optionally, when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is greater than or equal to the target sensor configuration scheme, it is determined to maintain the sensor configuration scheme corresponding to different operating variables of the current target fan unchanged; when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is less than the target sensor configuration scheme, it is determined to adjust the sensor configuration scheme corresponding to different operating variables of the current target fan to the target sensor configuration scheme.

[0043] It is understandable that if there are multiple wind turbines running in a wind farm, each wind turbine corresponds to a different historical sensor configuration scheme. By analyzing the historical data of each wind turbine, the key variables, sensitivity level and target sensor configuration scheme of each wind turbine are determined. Furthermore, by comparing the difference between the target sensor configuration scheme currently determined for each wind turbine and the target configuration corresponding to the dynamically changing sensitivity level, the target sensor scheme is slightly adjusted. For example, the monitoring accuracy of one of the wind turbines is lower than the target configuration, and the sensor configuration scheme needs to be adjusted. According to the method, the sensor configuration of the wind turbine is adjusted to the target configuration scheme to improve the monitoring accuracy and operating efficiency. At the same time, for wind turbines with a monitoring accuracy higher than the target configuration, the original configuration can be maintained to avoid additional adjustments and costs. This can more effectively manage the operating status of the wind farm and improve the performance and reliability of the wind turbine.

[0044] It should be noted that the above target sensor configuration scheme is not only accurate, but also can clearly indicate the number of different types of sensors to be configured. The combination of the two further improves the accuracy of wind turbine monitoring data.

[0045] As an optional implementation, after adjusting the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels, the monitoring focus of the current wind turbine is determined by determining the usage changes of different types of sensors in the currently used sensor configuration scheme, thereby improving the emphasis of wind turbine data monitoring, facilitating the use of sensors to accurately monitor the data corresponding to factors that have a greater impact on wind turbine power changes, and improving the operating efficiency of the wind turbine.

[0046] In an exemplary embodiment, adjusting the sensor configuration scheme corresponding to the target fan under different operating variables of the fan according to the multiple sensitivity levels also includes: measuring the actual usage quantity of different types of sensors required for monitoring different operating variables of the fan required by the target sensor configuration scheme; determining the difference between the actual usage quantity and the historical usage quantity of different types of sensors installed on the target fan for monitoring different operating variables of the fan; and determining the configuration focus of the sensor configuration scheme based on the difference.

[0047] In summary, the sensitivity level is used to measure whether the sensor needs to be adjusted, so that the sensitivity level can be used to flexibly configure the number and type of sensors. For example, for a certain wind turbine, after the sensitivity level is determined, the historical sensor configuration scheme is compared with the recommended target sensor configuration scheme for the sensor on the wind turbine. When the difference is determined, the sensitivity level is used to determine whether to adjust it, and then the sensor layout position and quantity are changed to achieve efficient layout of wind turbine sensors and improve the reliability and effectiveness of wind turbine monitoring using sensors.

[0048] It can be understood that in the above embodiment, if a certain wind turbine statistically locates the differences between different types of sensors during the process of adjusting the sensor configuration scheme, the target type sensors with differences can be preferentially configured when executing the above new configuration scheme, thereby improving the execution efficiency of the above new configuration scheme, achieving faster and more accurate adjustment of the fan sensor configuration, improving monitoring efficiency and accuracy, and avoiding waste of resources and over-configuration.

[0049] Obviously, the embodiments described above are only some embodiments of the present application, not all embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:

[0050] An optional embodiment of the present application provides a method for optimizing the placement of sensors in a wind power system to solve the problem of being unable to accurately monitor the operating variables of a wind turbine to improve the operating efficiency and stability of the wind turbine. The method first collects various sensor data of the wind turbine to obtain monitoring variables related to the operation of the wind turbine. Then, based on the big data model, an accurate wind turbine operation model is constructed. Next, a nonlinear function is fitted to the established model and a sensitivity analysis is performed. Finally, the sensitivity level of the variable is evaluated based on the calculation results. Furthermore, sensors are placed according to the sensitivity level.

[0051] Optional, Figure 3 This is a flow chart of a wind power system sensor deployment optimization method according to an embodiment of the present application; specifically comprising the following steps:

[0052] Step 1: Screen wind turbine monitoring variables. First, collect wind turbine data from system sensors such as SCADA (Supervisory Control Data Acquisition, SCADA), including wind turbine power and possible other monitoring variables, such as wind speed, wind direction, temperature, vibration, and blade angle. Determine the variables that have a more important impact on wind turbine performance in the monitoring system. The specific method can be to calculate the correlation between these monitoring variables and wind turbine power, which can be quantified using the Pearson correlation coefficient. In this process, a threshold value of the correlation coefficient can be set, such as 0.7 (the threshold value can be adjusted according to the number of variables). When the absolute value of the correlation coefficient is greater than the threshold, it can be considered that there is a strong correlation between this variable and the wind turbine power, and it is a monitoring variable that needs attention. Alternatively, a visualization method can be used to evaluate the relationship between the variable and power.

[0053] Optionally, SCADA is an automation system for real-time monitoring, control and data acquisition, often used to monitor industrial processes, infrastructure and utilities. SCADA systems are usually composed of one or more computers, sensors, controllers and network devices, which can remotely monitor and control various devices and systems. SCADA systems are widely used in the field of industrial control and monitoring, which can improve production efficiency, reduce costs and enhance safety.

[0054] Step 2: Establish a fan operation model. Using neural network algorithms such as long short-term memory networks and convolutional neural networks, the model input is the screened monitoring variables, and the output is the power of the fan. In this way, a mathematical model of the fan operation is constructed, and the number of neural network layers, the number of neurons, and the learning rate are adjusted to ensure that the model can reasonably reflect the behavior of the system.

[0055] Step 3: Fitting the model with nonlinear functions. Fit the established model to generate nonlinear functions. This can be achieved through machine learning methods, polynomial regression and other technologies. The fitted mathematical model can more accurately capture the complex relationship between variables.

[0056] Step 4: Perform sensitivity analysis. Perform sensitivity analysis, change the input variables one by one, and observe the changes in the output. The Morris sensitivity analysis method can be used to observe the single impact of each input variable on the output. Specifically, define the range of variation of each selected variable, select a set of sampling points (for each variable, select at least two points, one as the reference point, and the other or several as disturbance points), and introduce a small disturbance to each sampling point of each variable except the reference point. You can choose a fixed-size disturbance or a percentage relative to the variable range. Run the model and record the output results. For each variable, calculate the Morris indicator, which describes the change in output when a small disturbance is introduced at the disturbance point. The specific calculation method is as follows:

[0057] Calculate the mean:

[0058]

[0059] Calculate the standard deviation:

[0060]

[0061] in, is the output after applying the perturbation to the ith variable, Y(x) is the output at the reference point, and n is the number of sampling points.

[0062] Optionally, the Morr is indicator reflects the degree of influence of each variable on the output. i It indicates the size of the average effect of each disturbance direction on the variable in the full range of the variable. The larger its value is, the greater the average impact of the variable on the system output is, which means that the variable has a more significant impact on the system output. i represents the variance of the effect of each disturbance direction on the variable over the full range of the variable, σ i The larger the value, the greater the change in the effect of the variable on the system output in different disturbance directions, that is, there is a greater uncertainty.

[0063] Step 5: Evaluate the sensitivity level of the variables. Based on the sensitivity results, evaluate the impact of each variable on system performance. Specifically, the variables can be classified into sensitivity levels based on the Morr is index to better understand their impact on system behavior. For example, thresholds can be set for the mean and standard deviation based on the results, and the variables can be divided into four levels based on the thresholds:

[0064] (1) Level A: High sensitivity and high uncertainty. i , σ i are all large, indicating that the variable has a greater impact on the system output in the entire input space and has greater uncertainty under different conditions.

[0065] (2) Level B: high sensitivity and low uncertainty. i Large, σ i Small, indicating that the variable has a greater and relatively stable impact on the system output in the entire input space.

[0066] (3) Level C: low sensitivity and high uncertainty. i Small, σ i Large, indicating that the variable has a small impact on the system output and has a large uncertainty under different conditions.

[0067] (4) Level D: Low sensitivity and low uncertainty. i , σ i are all small, indicating that the variable has little impact on the system output and is relatively stable.

[0068] Optionally, an example of statistical results is shown in Table 1 below:

[0069] Table 1

[0070] Disturbance Variable <![CDATA[Morris mean value u i > <![CDATA[Morris standard deviation σ i > Sensitivity level Variable 1 …… …… …… Variable 2 …… …… …… Variable 3 …… …… ……

[0071] Step 6: Deploy sensors. According to the classification level, consider choosing an appropriate sensor deployment method and change the existing sensor deployment location, quantity, and accuracy.

[0072] Optionally, for Class A variables, give priority to sensors with high precision, and regularly maintain and calibrate the sensors to ensure their normal operation; pay attention to the layout position to ensure that the changes of key variables of the system can be accurately captured; consider using redundant sensor design and consider arranging redundant sensors in different directions. So that when one sensor fails, other sensors can still provide monitoring values, improving the reliability and fault tolerance of the system.

[0073] Optionally, for Class B variables, it is recommended to deploy sensors with higher accuracy and regularly maintain and calibrate the sensors to ensure their normal operation; the number of sensors can be optimized based on the cost and performance requirements of the system to avoid over-investing resources in these variables, thereby achieving a balance between cost and performance.

[0074] Optionally, for Class C variables, pay attention to the sensor placement to ensure that changes in key system variables can be accurately captured. It is recommended to select sensors with lower deployment costs and optimize the number of sensors to avoid over-investing resources in these variables, thereby achieving a balance between cost and performance.

[0075] Optionally, for variables of level D, the number and accuracy of sensors can be relatively small or no sensors can be deployed, and attention can be paid to other more important variables in the system.

[0076] It should be noted that when studying the interaction effects between variables, in addition to paying attention to the sensitivity of a single variable, it is also necessary to consider the impact of the mutual influence between variables on the system output. Because the interaction between variables may aggravate or weaken the impact of a certain variable on the system output, thereby affecting the operation and results of the entire system. By analyzing the interaction effects between variables, we can have a more comprehensive understanding of the operating mechanism of the system, which helps to more accurately predict the behavior and results of the system. In addition, considering the interaction effects between variables can also help optimize system design and decision-making, thereby improving the efficiency and performance of the system. Therefore, when studying the interaction effects between variables, it is very important to comprehensively consider the sensitivity of a single variable and the interaction effects between variables.

[0077] In summary, the optional embodiments of the present application can not only reduce unnecessary monitoring by collecting various types of sensor data of the wind turbine and selectively selecting key variables for monitoring, but also ensure that the monitoring of key variables is more intensive and accurate, thereby more accurately understanding the system status. Through the big data model, the operation of the wind turbine can be more accurately analyzed and predicted to improve the operating efficiency and performance of the wind turbine. The established model is fitted with nonlinear functions and a sensitivity analysis is performed. Furthermore, through sensitivity analysis, it is possible to more clearly understand which variables have the greatest impact on the performance and health of the system, optimize the layout of sensors, concentrate resources on the key variables that have the greatest impact on the system, and achieve optimal resource allocation.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0079] In this embodiment, a sensor configuration adjustment device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0080] Figure 4 : is a structural block diagram of a sensor configuration adjustment device according to an embodiment of the present application, the device comprising:

[0081] A first determination module 42 is used to determine, based on historical operation information corresponding to the target wind turbine, a disturbance index on the output power of the target wind turbine when different operation variable data of the wind turbine change;

[0082] A classification module 44, used to classify different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels;

[0083] The adjustment module 46 is used to adjust the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels.

[0084] Based on the above device, the disturbance index of the output power of the target fan when the data of different operating variables of the fan change is determined according to the historical operating information corresponding to the target fan; the different operating variables of the fan are graded according to the disturbance index to obtain multiple sensitivity levels; the sensor configuration scheme corresponding to the target fan under different operating variables of the fan is adjusted according to the multiple sensitivity levels. The problem of being unable to accurately monitor the operating variables of the fan to improve the operating efficiency and stability of the fan is solved. Furthermore, the performance and efficiency of the fan are improved by adjusting the sensor configuration scheme corresponding to different operating variables of the fan.

[0085] In an exemplary embodiment, the above-mentioned device also includes: a screening module, which is used to collect current wind turbine data corresponding to the wind field and screen the current wind turbine data before determining the disturbance index of the target wind turbine output power when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine; determine multiple wind turbine variables to be monitored from the screening results, and determine the monitoring data corresponding to the multiple wind turbine variables in different time periods, and obtain a combination of multiple wind turbine variables corresponding to different time periods; wherein each combination includes wind turbine power and different operating variables of the wind turbine, and the different operating variables of the wind turbine include at least one of the following: wind speed corresponding to the wind turbine, wind direction corresponding to the fan, temperature corresponding to each component on the fan, vibration corresponding to the fan, blade angle corresponding to the fan, and air density at the location of the fan; use the combination as training data to train the preset wind turbine operation model to obtain a target wind turbine operation model with operation information as input and wind power as output; fit the target wind turbine operation model to generate a nonlinear function, wherein the nonlinear function is used to represent the correlation change between different operating variables of the fan and the wind turbine power.

[0086] In an exemplary embodiment, the above-mentioned device also includes: a second determination module, which is used to fit the target wind turbine operation model, generate a nonlinear function, and then simulate the adjustment of the numerical value of any operating variable in the combination of each wind turbine variable; determine the range of change of wind turbine power caused by any operating variable based on the nonlinear function; associate the numerical value with the change range to obtain a set of change data; perform sensitivity analysis on the target wind turbine operation model through the set of change data to obtain the sensitivity value corresponding to the target wind turbine operation model when any operating variable changes.

[0087] In an exemplary embodiment, the above-mentioned grading module is also used to obtain the threshold interval set for the disturbance index of the target object, wherein the threshold interval includes at least: a first threshold interval, a second threshold interval, a third threshold interval, and a fourth threshold interval; the first threshold interval is the highest level interval, mainly for disturbance indexes with high sensitivity and high uncertainty; the second threshold interval is mainly for disturbance indexes with high sensitivity and low uncertainty; the third threshold interval is mainly for disturbance indexes with low sensitivity and high uncertainty; the fourth threshold interval is mainly for disturbance indexes with low sensitivity and low uncertainty; the disturbance index is graded according to the threshold intervals to obtain multiple sensitivity levels.

[0088] In an exemplary embodiment, the above-mentioned adjustment module is also used to determine the historical sensor configuration scheme corresponding to the target fan, and the target sensor configuration scheme corresponding to the multiple sensitivity levels; compare the accuracy difference between the historical sensor configuration scheme and the target sensor configuration scheme; when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is greater than or equal to the target sensor configuration scheme, determine to maintain the sensor configuration scheme corresponding to different operating variables of the current fan of the target fan unchanged; when the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is less than the target sensor configuration scheme, determine to adjust the sensor configuration scheme corresponding to different operating variables of the current fan of the target fan to the target sensor configuration scheme.

[0089] In an exemplary embodiment, the above-mentioned adjustment module is also used to measure the actual usage quantity of different types of sensors required for monitoring different operating variables of the fan by the target sensor configuration scheme; determine the difference between the actual usage quantity and the historical usage quantity of different types of sensors installed on the target fan for monitoring different operating variables of the fan; and determine the configuration focus of the sensor configuration scheme based on the difference.

[0090] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0091] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0092] S1. Determine the disturbance index of the output power of the target wind turbine when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine;

[0093] S2. Classifying different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels;

[0094] S3. Adjusting the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels.

[0095] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0096] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0097] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are performed.

[0098] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0099] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0100] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0101] S1. Determine the disturbance index of the output power of the target wind turbine when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine;

[0102] S2. Classifying different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels;

[0103] S3. Adjusting the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels.

[0104] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0105] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0106] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0107] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting sensor configuration, characterized in that: include: Determine the disturbance index on the output power of the target wind turbine when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine; Different operating variables of the fan are graded according to the disturbance index to obtain a plurality of sensitivity levels; and sensor configuration schemes corresponding to the target fan under different operating variables of the fan are adjusted according to the plurality of sensitivity levels.

2. The method according to claim 1, characterized in that Before determining the disturbance index of the target wind turbine output power when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine, the method further includes: Collect current wind turbine data corresponding to the wind farm, and filter the current wind turbine data; Determine multiple fan variables to be monitored from the screening results, and determine the monitoring data corresponding to the multiple fan variables in different time periods, and obtain combinations of multiple fan variables corresponding to different time periods; wherein each combination includes the fan power and different operating variables of the fan, and the different operating variables of the fan include at least one of the following: the wind speed corresponding to the fan, the wind direction corresponding to the fan, the temperature corresponding to each component of the fan, the vibration corresponding to the fan, the blade angle corresponding to the fan, and the air density at the location of the fan; Using the combination as training data to train a preset wind turbine operation model, to obtain a target wind turbine operation model with operation information as input and wind turbine power as output; The target wind turbine operation model is fitted to generate a nonlinear function, wherein the nonlinear function is used to represent the correlation change between different wind turbine operation variables and wind turbine power.

3. The method according to claim 2, characterized in that After fitting the target wind turbine operation model to generate a nonlinear function, the method further includes: Simulate and adjust the numerical value of any operating variable of each combination of fan variables; Determine the variation range of wind turbine power caused by any operating variable based on the nonlinear function; associate the numerical value with the variation range to obtain a set of variation data; A sensitivity analysis is performed on the target wind turbine operation model through the set of change data to obtain a sensitivity value corresponding to the target wind turbine operation model when any one of the operation variables changes.

4. The method according to claim 1, characterized in that: Different operating variables of the wind turbine are classified according to the disturbance index to obtain multiple sensitivity levels, including: Acquire a threshold interval set by the target object for the disturbance index, wherein the threshold interval includes at least: a first threshold interval, a second threshold interval, a third threshold interval, and a fourth threshold interval; the first threshold interval is the highest level interval, mainly for disturbance indexes with high sensitivity and high uncertainty; the second threshold interval is mainly for disturbance indexes with high sensitivity and low uncertainty; the third threshold interval is mainly for disturbance indexes with low sensitivity and high uncertainty; the fourth threshold interval is mainly for disturbance indexes with low sensitivity and low uncertainty; The disturbance index is graded according to the threshold interval to obtain a plurality of sensitivity levels.

5. The method according to claim 1, characterized in that Adjusting the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels includes: Determine a historical sensor configuration scheme corresponding to the target wind turbine, and a target sensor configuration scheme corresponding to the multiple sensitivity levels; Comparing the accuracy difference between the historical sensor configuration scheme and the target sensor configuration scheme; A sensor configuration scheme corresponding to the target wind turbine is determined according to the accuracy difference.

6. The method according to claim 5, characterized in that Determining a sensor configuration scheme corresponding to the target wind turbine according to the accuracy difference includes: When the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is greater than or equal to the target sensor configuration scheme, determining to maintain the sensor configuration scheme corresponding to different current wind turbine operating variables of the target wind turbine unchanged; When the accuracy difference indicates that the monitoring accuracy of the historical sensor configuration scheme is less than that of the target sensor configuration scheme, it is determined to adjust the sensor configuration scheme corresponding to different current operating variables of the target wind turbine to the target sensor configuration scheme.

7. The method according to claim 5, characterized in that Determining a sensor configuration scheme corresponding to the target wind turbine according to the accuracy difference also includes: Calculate the actual number of different types of sensors required to monitor different operating variables of the wind turbine by the target sensor configuration scheme; Determine the difference between the actual usage quantity and the historical usage quantity of different types of sensors installed on the target wind turbine for monitoring different operating variables of the wind turbine; A configuration focus of the sensor configuration solution is determined based on the difference.

8. A sensor configuration adjustment device, characterized in that: include: A first determination module is used to determine the disturbance index of the output power of the target wind turbine when different operating variable data of the wind turbine change according to the historical operating information corresponding to the target wind turbine; A grading module, used to grade different operating variables of the wind turbine according to the disturbance index to obtain multiple sensitivity levels; The adjustment module is used to adjust the sensor configuration scheme corresponding to the target wind turbine under different operating variables of the wind turbine according to the multiple sensitivity levels.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images