Multi-sensor-based Comprehensive Monitoring Method, System and Power Distribution Cabinet for Wind Power Generation Equipment

Abstract

The present invention relates to the field of wind power generation control, and particularly to an integrated monitoring method, system and power distribution cabinet for wind power generation equipment based on multiple sensors. It includes: collecting wind power parameters of each power generation equipment in the target area through a monitoring unit and generating a wind power map, and verifying by combining the position vectors between the power generation equipment and the target wind power vectors in the wind power map; generating N groups of input data based on the wind power parameters, equipment parameters and N operating modes, and respectively calculating the wake distribution, power generation amount and equipment loss value corresponding to each group of data through a wake prediction model and a power generation prediction model; superimposing each wake information on the wind power data of other equipment, and finally calculating the total power generation amount and total loss amount of all wake branches, and selecting the optimal operating mode of each power generation equipment through multi-objective optimization. It realizes the collaborative control of power generation equipment and effectively balances the power generation efficiency and equipment loss.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation control, and particularly to a comprehensive monitoring method, system and power distribution cabinet for wind power generation equipment based on multi-sensors. Background Art

[0002] Existing wind power generation equipment monitoring technologies mostly rely on single sensors or local data collection, making it difficult to comprehensively reflect the dynamic interactions of multiple wind power generation equipment in complex wind farms. For example, traditional methods usually ignore the impact of wake effects on downstream equipment, resulting in significant deviations between power generation predictions and actual operating conditions. In addition, most monitoring systems lack the ability to dynamically balance the operating mode and losses of equipment, often sacrificing equipment lifespan in pursuit of short-term power generation efficiency or operating in a conservative mode, leading to underutilization of power generation potential. Similar prior arts include a Chinese patent with publication number CN118934443A, which proposes an optimization method and system for the power generation efficiency of a wind turbine based on wind direction and wind speed monitoring. The method includes: analyzing the data of wind direction and wind speed monitoring; according to the analysis results, retrieving the corresponding working parameter set from the pre-configured working mode library of the wind turbine; configuring the wind turbine according to the working parameter set. The optimization method for the power generation efficiency of the wind turbine based on wind direction and wind speed monitoring in this invention monitors the changes in wind direction and wind speed in real time, adjusts the operating state of the wind turbine, optimizes the rotational speed and qualified power output of the turbine by monitoring and predicting wind condition changes, and thus achieves the maximization of wind energy conversion. In addition, a similar prior art is a European patent with publication number EP2111509B1, which discloses a wind farm monitoring and control system. The system includes: at least one wind farm; at least one intelligent management server that can be connected to the at least one wind farm through a data communication network; at least one wind farm configuration. Tools related to the intelligent management server for establishing a connection to the at least one wind farm. The present invention proposes a system for monitoring and controlling a wind farm. Monitoring and control are performed so that multiple wind farms can be uniformly monitored and controlled. Therefore, different wind farms can be uniformly monitored and controlled with a uniform output, and data from the wind farms can also be compared. The technical solutions of the above two patents have solved the monitoring problems of wind power generation, but neither has considered analyzing the mutual relationship between the wake of the wind turbine, power generation, and equipment losses, and thus achieving a balance between increasing power generation and reducing equipment losses. Summary of the Invention

[0003] The present invention provides a comprehensive monitoring method, system and power distribution cabinet for wind power generation equipment based on multi-sensors, which significantly improves the monitoring accuracy and operating efficiency of wind power generation equipment through a multi-sensor data fusion and collaborative control mechanism. The method includes:

[0004] Step S1: Obtain the wind power information at each power generation device in the target area through the monitoring unit, obtain a wind power map based on the wind power information, and verify the wind power information through the position vector between adjacent power generation devices and the target wind power vector in the wind power map;

[0005] Step S2: Obtain N groups of input information based on the wind power information, device information, and N operating modes of the power generation devices, and obtain N groups of wake information and corresponding power generation amounts and device losses according to each group of the input information, wake prediction model, and power generation prediction model;

[0006] Step S3: Add each group of the wake information to the wind power information of the corresponding other power generation devices, repeat Step S2, obtain the prediction information of the corresponding power generation devices on each wake branch, and calculate the total power generation amount and total device loss on each wake branch;

[0007] Step S4: Select the optimal operating mode corresponding to each power generation device based on the total power generation amount and the total device loss.

[0008] As a preferred technical solution of the present invention, the device information is the structural parameters of the generator set, at least including the windmill height, rotor diameter, and blade angle.

[0009] As a preferred technical solution of the present invention, verifying the wind power information through the position vector between adjacent power generation devices and the target wind power vector in the wind power map includes:

[0010] According to the position information of the first power generation device and the second power generation device, obtain the position vector pointing from the first power generation device to the second power generation device. Also, according to the wind power information monitored by the first power generation device and the second power generation device, respectively obtain the first wind power map and the second wind power map, compare the first wind power map and the second wind power map, obtain the target wind power vector at the position with the largest wind power difference according to the comparison result, compare the target wind power vector with the position vector, and verify the wind power information corresponding to the second power generation device according to the comparison result. And through this step, verify the wind power information of each power generation device, where the first power generation device is located upstream of the second power generation device.

[0011] As a preferred technical solution of the present invention, respectively obtaining the wake information, power generation amount, and device loss corresponding to each group of the input data includes:

[0012] Sort the power generation equipment in the target area according to the location information, and use the wind power information and equipment information after inspection of the corresponding power generation equipment in the sorted order as the first information. Combine the first information with different operating modes corresponding to the power generation equipment respectively to obtain multiple groups of the input information. Input each group of the input information into the wake prediction model and the power generation prediction model respectively, and obtain the wake information, the power generation amount, and the equipment loss corresponding to each group of the input information, where the operating modes include a high-speed mode, a normal mode, and a low-speed mode.

[0013] As a preferred technical solution of the present invention, calculating the total power generation amount and the total equipment loss on each wake branch includes:

[0014] Add the N wake information of the power generation equipment to the wind power information corresponding to the i-th power generation equipment to obtain N new wind power information. Based on each of the N new wind power information, equipment information, and each of the N operating modes corresponding to the i-th power generation equipment, perform combination to obtain groups of input information, and repeat the step S3 to obtain the prediction information corresponding to the other power generation equipment. The prediction information includes wake information, power generation amount, and equipment loss, and repeat this step to obtain the prediction information corresponding to each power generation equipment for each wake branch;

[0015] Based on the prediction information of each power generation equipment on each wake branch, calculate the total power generation amount and the total equipment loss of M power generation equipment on each wake information branch.

[0016] As a preferred technical solution of the present invention, selecting the optimal operating mode corresponding to each power generation equipment based on the total power generation amount and the total equipment loss on each wake branch includes:

[0017] Based on the total power generation amount and the total equipment loss of each wake branch, calculate the first value of the total power generation amount of each wake branch and the second value corresponding to the total equipment loss. Select several candidate wake branches where the first value is greater than the second value and the ratio between the second value and the total power generation amount is the smallest, and calculate the sum of the squared differences between the equipment loss of each power generation equipment on each candidate wake branch and the average equipment loss. And use the operating mode of each power generation equipment on the candidate wake branch corresponding to the smallest sum of the squared differences as the optimal operating mode.

[0018] As a preferred technical solution of the present invention, after the step S4, there is also a step S5:

[0019] When each of the power generation devices operates in the optimal operation mode, the real-time power generation amount and real-time device loss of the power generation device are also collected in real time. The real-time power generation amount is compared with the predicted power generation amount to obtain a first difference. The real-time device loss is also compared with the predicted device loss to obtain a second difference. The first difference and the second difference are weighted to obtain a weighted result, and it is determined whether the power generation device is abnormal according to the weighted result.

[0020] The present invention also provides a multi-sensor-based comprehensive monitoring system for wind power generation devices to implement the above method. The system includes:

[0021] A monitoring unit for obtaining wind power information at each power generation device in a target area and obtaining a wind power map according to the wind power information;

[0022] A verification unit for verifying the wind power information through the position vector between adjacent power generation devices and the target wind power vector in the wind power map;

[0023] A prediction unit for obtaining N groups of input information based on the wind power information, device information, and N operation modes of the power generation device. According to each group of the input information, a wake prediction model, and a power generation prediction model, N groups of wake information and corresponding power generation amounts and device losses are obtained; each group of the wake information is added to the wind power information of the corresponding other power generation device, and step S3 is repeated to obtain the prediction information of the corresponding power generation device on each wake branch;

[0024] A calculation unit for calculating the total power generation amount and total device loss on each wake branch and selecting the operation mode corresponding to each power generation device based on the total power generation amount and the total device loss.

[0025] The present invention also provides a power distribution cabinet for multi-sensor-based comprehensive monitoring of wind power generation devices. The power distribution cabinet includes: a memory and at least one processor, and instructions are stored in the memory;

[0026] The at least one processor calls the instructions in the memory to enable the power distribution cabinet for multi-sensor-based comprehensive monitoring of wind power generation devices to execute the above method.

[0027] The present invention also provides a computer-readable storage medium, and instructions are stored on the computer-readable storage medium. When the instructions are executed by a processor, the above method is implemented.

[0028] The beneficial effects of the present invention are as follows:

[0029] Through a multi-sensor data fusion and collaborative control mechanism, the present invention significantly improves the monitoring accuracy and operation efficiency of wind power generation equipment. Traditional monitoring systems rely on single sensors or local data collection, making it difficult to comprehensively reflect the dynamic interactions of multiple wind power generation equipment in complex wind farms. In particular, the impact of wake effects on downstream equipment is often overlooked, leading to deviations in power generation prediction and imbalances in equipment life management. The present invention effectively reduces sensor errors and environmental interference by collecting wind parameters in real time and generating wind maps, and verifying the data by combining the position vectors of adjacent equipment with the target wind vectors, ensuring the accuracy of the input data. On this basis, multiple sets of input data are generated by combining equipment structure parameters and various operating modes. The power generation and equipment losses under different operating modes are evaluated through a wake prediction model and a power generation prediction model, and the wake information is recursively superimposed on the wind power data of downstream equipment to form a global chain effect calculation. This method breaks through the limitation of single-unit optimization, comprehensively considers the mutual shielding effects of equipment in the wind farm, and screens out the optimal balance point between power generation efficiency and equipment losses through multi-objective optimization. For example, when the wind is strong, the load of downstream equipment is reduced to reduce losses while maintaining the overall power generation efficiency. In addition, the system collects operation data in real time and compares it with the predicted values, and judges equipment anomalies through weighted differences, supporting timely maintenance and fault prevention, and improving system reliability. Through dynamic collaborative control, not only the problem of overestimating power generation caused by wake effects in traditional methods is solved, but also the uniform distribution of equipment losses is achieved, facilitating the synchronous arrangement of maintenance plans and extending the equipment life. This technical solution flexibly adapts to different wind farm conditions and equipment configurations, taking into account both short-term power generation potential and long-term equipment health management, providing effective support for the intelligent and efficient operation of wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a flowchart of the comprehensive monitoring method for wind power generation equipment based on multi-sensors of the present invention;

[0032] Figure 2 It is a flowchart of the verification method for wind power information of power generation equipment;

[0033] Figure 3 It is a schematic diagram of the wake branch of the present invention;

[0034] Figure 4 It is a structural diagram of the comprehensive monitoring system for wind power generation equipment based on multi-sensors of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] An embodiment of the present invention provides a multi-sensor-based integrated monitoring method, system and power distribution cabinet for wind power generation equipment. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0036] For ease of understanding, the specific process of the embodiment of the present invention will be described below. As Figure 1 shown, an embodiment of the multi-sensor-based integrated monitoring method for wind power generation equipment in the embodiment of the present invention includes:

[0037] Step S1: Obtain the wind power information at each power generation equipment in the target area through the monitoring unit, and obtain a wind power map according to the wind power information. Verify the wind power information through the position vector between adjacent power generation equipment and the target wind power vector in the wind power map;

[0038] Specifically, the wind power parameters at each equipment are monitored in real time through multiple sensors in the monitoring unit. The above sensors include wind sensors. Using a spatial interpolation algorithm, such as Kriging interpolation, the discrete sensor data is converted into a continuous wind field distribution map. The above wind power map includes the wind power map of each wind power equipment. Intuitively display the wind power intensity and direction in different regions. Calculate the direction vector according to the geographical coordinates of adjacent equipment, such as the vector from upstream equipment A to downstream equipment B. Extract the actual measured value of the wind power direction between equipment from the wind power map. If the deviation between the position vector and the wind power vector direction exceeds the threshold, trigger data correction. Through the above technical solution, sensor errors or environmental interference can be reduced, ensuring the accuracy of the input data of the wake prediction model and avoiding misjudgment of the power generation efficiency of downstream equipment due to incorrect wind power information.

[0039] Step S2: Obtain N groups of input information based on the wind power information, equipment information and N operating modes of the power generation equipment. According to each group of the input information, wake prediction model and power generation prediction model, obtain N groups of wake information and the corresponding power generation amount and equipment loss;

[0040] Specifically, N sets of input combinations are generated by combining real-time wind power parameters, equipment structure parameters (such as blade angle, tower height), and preset operation modes (high-speed mode, normal mode, low-speed mode). For example, the value of N is 3. Based on the wind power information of each power generation device, that is, the wind farm information at the location or the wind farm information after superimposing the wake information of the upstream power generation device, the above-mentioned equipment information, namely the equipment structure parameters and N operation modes, is respectively input into the above-mentioned wake prediction model and power generation prediction model to calculate the power generation and loss of each device under different operation modes. Among them, the above-mentioned wake prediction model and power generation prediction model both use historical wind power information, operation modes, and equipment information as variables, and respectively use the corresponding historical wake information, historical power generation, and historical equipment loss as the results of the wake prediction model and power generation prediction model. Through the above technical solution, the shielding effect of upstream equipment on downstream equipment can be accurately evaluated, the problem of overestimating power generation caused by ignoring wakes in traditional methods can be solved, and prediction results of multiple operation modes are provided for each device. For example, the power generation in the high-speed mode is high but the loss is large, laying a foundation for obtaining the optimal operation mode subsequently.

[0041] Step S3: Add each set of the wake information to the wind power information of the corresponding other power generation device, repeat Step S2, obtain the prediction information of the power generation device corresponding to each wake branch, and calculate the total power generation and total equipment loss on each wake branch;

[0042] Specifically, the wake distribution of each device in Step S2, such as the wind speed attenuation area, is recursively superimposed on the wind power data of downstream devices to form a chain effect calculation. For example, device A affects device B, and device B further affects device C. For each wake branch, such as A→B→C, the total power generation and total loss are accumulated to form a global evaluation result, breaking through the limitation of single-unit optimization, comprehensively considering the mutual influence of devices in the wind farm, avoiding local optimal solutions, and supporting multi-device cooperative control under complex wind farm conditions. For example, when the wind is strong, the operation load of downstream devices is reduced to reduce losses.

[0043] Step S4: Select the optimal operation mode corresponding to each power generation device based on the total power generation and the total equipment loss.

[0044] Specifically, by maximizing the total power generation and minimizing the total loss, the optimal balance point between power generation efficiency and equipment life is screened, and the operation mode combination with high total power generation and uniform equipment loss distribution is selected. On the premise of ensuring the health of the equipment, the overall power generation efficiency is improved. By dynamically adjusting the operation mode, for example, enabling a low-loss mode when the wind is strong to reduce wear of key components.

[0045] Furthermore, the equipment information is the structure parameters of the generator set, including at least the windmill height, rotor diameter, and blade angle.

[0046] Further, verify the wind power information through the position vector between adjacent power generation devices and the target wind power vector in the wind power map, as Figure 2 shown, including:

[0047] According to the position information of the first power generation device and the second power generation device, obtain the position vector pointing from the first power generation device to the second power generation device. Also, according to the wind power information monitored by the first power generation device and the second power generation device, respectively obtain the first wind power map and the second wind power map. Compare the first wind power map and the second wind power map, obtain the target wind power vector at the position with the largest wind power difference according to the comparison result, compare the target wind power vector with the position vector, and verify the wind power information corresponding to the second power generation device according to the comparison result. Through this step, verify the wind power information of each power generation device, where the first power generation device is located upstream of the second power generation device.

[0048] Specifically, when encountering severe convective weather in the above-mentioned target area, since the wind sensor may be interfered by strong winds or the sensor drifts, resulting in inaccurate monitoring of the wind information of the second power generation device, which will affect subsequent turbulence prediction and loss prediction. Therefore, through the position information of the first power generation device and the second power generation device, that is, the position coordinates, the position coordinates are the coordinates of the first power generation device and the second power generation device in the target area. And the difference between the ordinates and the difference between the abscissas in the position coordinates of the second power generation device and the first power generation device are used as the position vector pointing from the first power generation device to the second power generation device. Also, according to the wind information of the first power generation device and the second power generation device, a first wind map corresponding to the first power generation device and a second wind map are respectively obtained. Among them, the first wind map and the second wind map are wind intensity distribution maps in different directions. Since the wake of the first power generation device will affect the wind field of the second power generation device and reduce the wind force in the wake direction of the second power generation device, the first wind map and the second wind map are compared to obtain the target wind direction with a larger wind force difference between the second wind map and the first wind map, that is, the comparison result, which is also the wake direction from the first power generation device to the second power generation device. Since the wake is a fan-shaped area behind the first power generation device, the direction of the wake is consistent with the direction of the position vector. Therefore, a target wind vector can be obtained through the target wind direction, and the target wind vector is compared with the position vector. When the directions of the target wind vector and the position vector are consistent, the wind information of the second power generation device is accurate. On the contrary, when there is a deviation in the direction between the two, it indicates that the wind information of the second power generation device is inaccurate, and the deviation angle between the two is used to correct the deviation of the wind information of the second power generation device. For example: if the angle between the target wind vector and the position vector is +5 degrees, the wind direction in the wind information of the second power generation device is compensated by 5°. Through the above technical solution, relatively accurate wind information of each power generation device can be obtained, laying a foundation for further predicting the power generation and loss of each power generation device based on the wind information.

[0049] Further, the wake information, power generation, and equipment loss corresponding to each group of the input data are respectively obtained, including:

[0050] The power generation equipment in the target area is sorted according to the location information, and the wind information and equipment information of the corresponding power generation equipment after inspection are used as the first information according to the sorting, and the first information is respectively combined with the different operating modes corresponding to the power generation equipment to obtain multiple groups of input information, and each group of the input information is respectively input into the wake prediction model and the power generation prediction model to obtain the wake information, the power generation and the equipment loss corresponding to each group of the input information, wherein the operating mode includes a high-speed mode, a normal mode and a low-speed mode.

[0051] Specifically, the power generation equipment in the target area is sorted according to the position information, that is, according to the direction of the wake, the upstream power generation equipment is sorted first, and the downstream power generation equipment is sorted last, wherein the front power generation equipment is not affected by the wake, and this step is carried out for the front power generation equipment. The wind information and equipment information of the power generation equipment after verification are used as the first information, wherein the equipment information is the structural parameters of the generator set, including at least: windmill height, rotor diameter, blade angle, and the first information is respectively combined with different operating modes of the power generation equipment, and the operating modes include high-speed mode, normal mode and protection mode, and multiple groups of input data are obtained, and each group of the input data is respectively input into the wake prediction model and the power generation prediction model, and the corresponding wake information, power generation and equipment loss under the input data conditions are respectively obtained. Through the technical solution, the wake information, power generation and equipment loss of the power generation equipment under different operating modes can be obtained, laying a foundation for further calculating the total power generation and total equipment loss in the target area.

[0052] Further, the total power generation and total equipment loss on each of the tail flow branches are calculated, including:

[0053] Add the N wake information of the power generation equipment to the wind power information corresponding to the corresponding i-th power generation equipment to obtain N new wind power information, and combine each of the new wind power information, equipment information and each of the N working modes corresponding to the i-th power generation equipment to obtain The group inputs information, and repeats step S3 to obtain the corresponding The prediction information includes wake information, power generation and equipment loss, and repeating this step to obtain the prediction information of each wake branch corresponding to each power generation device;

[0054] Based on the prediction information of each power generation equipment on each wake branch, the total power generation and total equipment loss of the M power generation equipment on each wake information branch are calculated.

[0055] Specifically, each set of wake information of the above power generation equipment is added to the wind power information corresponding to the corresponding other power generation equipment. The i-th power generation equipment is the downstream power generation equipment of the above power generation equipment. Based on the wake information corresponding to N different input information in the above power generation equipment, it is added to the wind power information of the corresponding other power generation equipment, and N new wind power information is obtained. Each of the N new wind power information is combined with the equipment information of the i-th power generation equipment to form N second information. Each of the second information is also combined with each of the N working modes of the other power generation equipment to obtain a set of input information, and then the method of step S3 is repeated to obtain the wake information, power generation information, and equipment loss corresponding to each input information of the i-th power generation equipment, and the method of this step is repeated to obtain multiple sets of wake information, power generation information, and equipment loss corresponding to each power generation equipment downstream of the i-th power generation equipment. Taking two power generation equipment as an example, as Figure 3 shown, the p-th set of prediction information corresponding to the p-th input information of the first power generation equipment, namely the l-th wake information, the p-th power generation information, and the p-th equipment loss, are added to the wind power information of the second power generation equipment to form new wind power information, and combined with the equipment information of the second power generation equipment and the j-th power generation mode to form the k-th input information, where k = (p - 1) * 3 + j, and based on the k-th input information, the k-th prediction information corresponding to the second power generation equipment is obtained, that is Figure 2 in, the k-th wake information, the k-th power generation information, and the k-th equipment loss corresponding to the second equipment, and each branch of the p-th prediction information of the first power generation equipment pointing to the k-th prediction information corresponding to the second power generation equipment is used as a wake branch, and the total power generation and total equipment loss of all M power generation equipment on each of the above wake branches are calculated. The value of M is a positive integer greater than or equal to 2 and less than or equal to 4. Since during wind power generation, especially in severe convective weather, not only the power generation of the power generation equipment needs to be considered, but also the equipment loss of the power generation equipment needs to be considered. If the increase in power generation is at the cost of a high equipment loss, and the cost of the equipment loss is greater than the value of the power generation, then even if the power generation is increased, it is meaningless. Therefore, by calculating the total power generation and total equipment loss on each wake branch, it lays a foundation for further selecting the optimal operation mode for each power generation equipment.

[0056] Furthermore, based on the total power generation and the total equipment loss on each wake branch, selecting the optimal operation mode corresponding to each power generation equipment includes:

[0057] Based on the total power generation amount and the total equipment loss of each of the wake branches, calculate the first value of the total power generation amount of each wake branch and the second value corresponding to the total equipment loss. Select several candidate wake branches where the first value is greater than the second value and the ratio between the second value and the total power generation amount is the smallest. Calculate the sum of the squared differences between the equipment loss of each power generation device on each of the candidate wake branches and the average equipment loss, and use the operating mode of each power generation device on the candidate wake branch corresponding to the smallest sum of the squared differences as the optimal operating mode.

[0058] Specifically, by calculating the total power generation amount and the total equipment loss of each of the above-mentioned wake branches, the power generation situation and equipment loss situation on each wake branch can be understood as a whole, thus avoiding local optimal solutions. Generally, in the ideal state of wind power generation, the more power generated, the smaller the equipment loss. Therefore, by calculating the value of the total power generation amount on each wake branch and taking it as the first value, that is, the product of the total power generation amount and the electricity price, and also calculating the total equipment loss value and taking it as the second value, that is, the sum of the products of the equipment loss corresponding to each equipment on the above-mentioned wake branch and the total price of the equipment. And take several of the above-mentioned wake branches where the first value is greater than the second value and the ratio between the first value and the total power generation amount is the smallest as the above-mentioned candidate wake branches, that is, several wake branches with the smallest power generation cost. Also calculate the average equipment loss on each of the above-mentioned candidate wake branches, and calculate the sum of the squared differences between each power generation device on the above-mentioned candidate wake branch and the average equipment loss. Take the candidate wake branch with the smallest sum of the above-mentioned average differences as the target wake branch, that is, the candidate wake branch with a relatively uniform distribution of equipment loss, so that the service lives of the power generation devices in the above-mentioned target area differ less. Through the above technical solution, it is convenient to synchronously arrange preventive maintenance, overhauls or replacements, and reduce frequent maintenance activities.

[0059] Further, after step S4, there is also step S5:

[0060] When each of the power generation devices operates in the optimal operating mode, also collect the real-time power generation amount and the real-time equipment loss of the power generation device in real time. Compare the real-time power generation amount with the predicted power generation amount to obtain a first difference. Also compare the real-time equipment loss with the predicted equipment loss to obtain a second difference. Weight the first difference and the second difference to obtain a weighted result, and judge whether the power generation device is abnormal according to the weighted result.

[0061] Specifically, when the device operates in the optimal operation mode, its power generation and device losses are collected in real time, as well as the deviation between the real-time power generation and the predicted power generation and the deviation between the real-time device losses and the predicted device losses. Then, the above two deviations are weighted. For example, the weights of power generation and device losses are both 0.5, and it is determined whether the corresponding power generation device is abnormal according to the weighted result. Among them, when the above weighted result is greater than or equal to the set threshold, the above power generation device is abnormal; when the above weighted result is less than the above set threshold, the above power generation device is normal. Through the above technical solution, the abnormal state of the above power generation device can be obtained in real time. When the power generation device is abnormal, measures can be taken immediately to avoid the deterioration of the situation.

[0062] The present invention also provides a multi-sensor-based comprehensive monitoring system for wind power generation equipment to implement the above method, as Figure 4 shown. The system includes:

[0063] A monitoring unit for obtaining wind power information at each power generation device in the target area and obtaining a wind power map according to the wind power information.

[0064] A verification unit for verifying the wind power information through the position vector between adjacent power generation devices and the target wind power vector in the wind power map.

[0065] A prediction unit for obtaining N groups of input information based on the wind power information, device information and N operation modes of the power generation device, and obtaining N groups of wake information and corresponding power generation and device losses according to each group of the input information, the wake prediction model and the power generation prediction model; adding each group of the wake information to the wind power information of the corresponding other power generation device, and repeating step S3 to obtain the prediction information of the corresponding power generation device on each wake branch.

[0066] A calculation unit for calculating the total power generation and total device losses on each wake branch and selecting the operation mode corresponding to each power generation device based on the total power generation and the total device losses.

[0067] The present invention also provides a power distribution cabinet for multi-sensor-based comprehensive monitoring of wind power generation equipment. The power distribution cabinet includes: a memory and at least one processor, and instructions are stored in the memory.

[0068] The at least one processor calls the instructions in the memory to enable the power distribution cabinet for multi-sensor-based comprehensive monitoring of wind power generation equipment to execute the above method.

[0069] The present invention also provides a computer-readable storage medium, on which instructions are stored, and when the instructions are executed by a processor, the above method is implemented.

[0070] In summary, through the multi-sensor data fusion and collaborative control mechanism, the present invention significantly improves the monitoring accuracy and operation efficiency of wind power generation equipment. Traditional monitoring systems rely on single sensors or local data collection, making it difficult to comprehensively reflect the dynamic interactions of multiple wind power generation equipment in complex wind farms. In particular, the impact of wake effects on downstream equipment is often overlooked, leading to power generation prediction deviations and unbalanced equipment life management. The present invention effectively reduces sensor errors and environmental interference by collecting wind parameters in real time and generating wind maps, and verifying the data by combining the position vectors of adjacent equipment and the target wind vectors, ensuring the accuracy of the input data. On this basis, by combining the equipment structure parameters and various operation modes, multiple sets of input data are generated. Through the wake prediction model and power generation prediction model, the power generation and equipment losses under different operation modes are evaluated, and the wake information is recursively superimposed on the wind power data of downstream equipment to form a global chain effect calculation. This method breaks through the limitation of single-machine optimization, comprehensively considers the mutual shielding effects of equipment in the wind farm, and selects the optimal balance point between power generation efficiency and equipment losses through multi-objective optimization. For example, when the wind is strong, the load of downstream equipment is reduced to reduce losses while maintaining the overall power generation efficiency. In addition, the system collects operation data in real time and compares it with the predicted values, and judges equipment anomalies through weighted differences, supporting timely maintenance and fault prevention, and improving system reliability. Through dynamic collaborative control, not only the problem of overestimating power generation caused by wake effects in traditional methods is solved, but also the uniform distribution of equipment losses is achieved, facilitating the synchronous arrangement of maintenance plans and extending the equipment life. This technical solution flexibly adapts to different wind farm conditions and equipment configurations, taking into account both short-term power generation potential and long-term equipment health management, providing effective support for the intelligent and efficient operation of wind farms.

[0071] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0073] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An integrated monitoring method for wind power generation equipment based on multi-sensors, characterized in that, Including: Step S1: Obtain the wind power information at each power generation device in the target area through the monitoring unit, obtain a wind power map based on the wind power information, and verify the wind power information through the position vectors between adjacent power generation devices and the target wind power vectors in the wind power map; Step S2: Obtain N groups of input information based on the wind power information, device information, and N operating modes of the power generation device. According to each group of input information, wake prediction model, and power generation prediction model, obtain N groups of wake information and corresponding power generation and device losses; Step S3: Add each group of wake information to the wind power information of the corresponding other power generation equipment, repeat Step S2 to obtain the prediction information of the corresponding power generation equipment on each wake branch, and calculate the total power generation and total equipment losses on each wake branch, including: adding the N wake information of the power generation equipment to the wind power information corresponding to the i-th power generation equipment to obtain N new wind power information, and combining each new wind power information corresponding to the i-th power generation equipment, the equipment information, and each of the N operating modes to obtain groups of input information, and repeat Step S3 to obtain the corresponding prediction information of other power generation equipment. The prediction information includes wake information, power generation, and equipment losses, and repeat this step to obtain the prediction information of each power generation equipment corresponding to each wake branch; based on the prediction information of each power generation equipment on each wake branch, calculate the total power generation and total equipment losses of the M power generation equipment on each wake information branch; Step S4: Select the optimal operating mode corresponding to each power generation device based on the total power generation and total device losses, including: Based on the total power generation and total device losses of each wake branch, calculate the first value of the total power generation of each wake branch and the second value corresponding to the total device losses, select several candidate wake branches where the first value is greater than the second value and the ratio between the second value and the total power generation is the smallest, and calculate the sum of the squared differences between the device losses of each power generation device on each candidate wake branch and the average device loss, and use the operating mode of each power generation device on the candidate wake branch with the smallest corresponding sum of squared differences as the optimal operating mode; Step S5: When each power generation device operates in the optimal operating mode, also collect the real-time power generation and real-time device losses of the power generation device in real time, compare the real-time power generation with the predicted power generation to obtain a first difference, and also compare the real-time device loss with the predicted device loss to obtain a second difference, weight the first difference and the second difference to obtain a weighted result, and judge whether the power generation device is abnormal according to the weighted result.

2. The method according to claim 1, wherein The device information is the structural parameters of the generator set, including at least the windmill height, rotor diameter, and blade angle.

3. The method according to claim 1, characterized in that Verifying the wind power information through the position vectors between adjacent power generation devices and the target wind power vectors in the wind power map includes: According to the position information of the first power generation device and the second power generation device, obtain the position vector pointing from the first power generation device to the second power generation device. Also, according to the wind power information monitored by the first power generation device and the second power generation device, obtain a first wind power map and a second wind power map respectively, compare the first wind power map and the second wind power map, obtain the target wind power vector at the position with the largest wind power difference according to the comparison result, compare the target wind power vector with the position vector, and verify the wind power information corresponding to the second power generation device according to the comparison result. Through this step, verify the wind power information of each power generation device, where the first power generation device is located upstream of the second power generation device.

4. The method according to claim 1, wherein Obtaining multiple groups of wake information and corresponding power generation and device losses includes: Sort the power generation equipment in the target area according to the location information, and take the wind power information and equipment information of the corresponding power generation equipment according to the sorting as the first information. Combine the first information with different operation modes respectively to obtain different multiple groups of the input information. Input each group of the input information into the wake prediction model and the power generation prediction model respectively, and obtain the wake information, the power generation amount, and the equipment loss corresponding to each group of the input information.

5. A comprehensive monitoring system for wind power generation equipment based on multi-sensors, which is used to implement the method described in any one of claims 1-4, characterized in that, The system includes: A monitoring unit, configured to obtain the wind power information at each power generation equipment in the target area, and obtain a wind power map according to the wind power information; A verification unit, configured to verify the wind power information through the position vector between adjacent power generation equipment and the target wind power vector in the wind power map; A prediction unit, configured to obtain N groups of input information based on the wind power information, equipment information, and N operation modes of the power generation equipment. According to each group of the input information, the wake prediction model, and the power generation prediction model, obtain N groups of wake information and the corresponding power generation amount and equipment loss; add each group of the wake information to the wind power information of the corresponding other power generation equipment, and repeat step S3 to obtain the prediction information of the power generation equipment corresponding to each wake branch; A calculation unit, configured to calculate the total power generation amount and the total equipment loss on each wake branch, and select the operation mode corresponding to each power generation equipment based on the total power generation amount and the total equipment loss.

6. A power distribution cabinet for comprehensive monitoring of wind power generation equipment based on multi-sensors, characterized in that, The equipment includes: a memory and at least one processor, and instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the distribution cabinet for comprehensive monitoring of the wind power generation equipment based on multiple sensors to execute the method according to any one of claims 1-4.

7. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instructions are executed by the processor, the method according to any one of claims 1-4 is implemented.

Images